From joachim at fit.qut.edu.au Sun Oct 2 23:25:50 1994 From: joachim at fit.qut.edu.au (Joachim Diederich) Date: Mon, 3 Oct 1994 13:25:50 +1000 Subject: Academic Position, QUT Brisbane, Australia Message-ID: <199410030325.NAA09067@fitmail.fit.qut.edu.au> The following position is open for applicants with a background in neurocomputing/connectionist systems. Please direct enquiries to Prof Mohay or to me. Best regards, Joachim ------------------------------------------------------------------------- SENIOR LECTURER IN THE SCHOOL OF COMPUTING SCIENCE QUEENSLAND UNIVERSITY OF TECHNOLOGY INTRODUCTION The Faculty of Information Technology is located on the Gardens Point (City Centre) campus of Queensland University of Technology. It currently comprises three Schools: Computing Science, Data Communications and Information Systems and four Research Centres: Cooperative Information Systems, Information Security, Neurocomputing and Programming Languages and Systems. In addition, the Faculty is a major partner in the Commonwealth funded Distributed Systems Technology Centre. POSITION The appointee will be responsible to the Head, School of Computing Science and will be expected to undertake a leadership role in teaching in undergraduate and postgraduate courses, in research and in academic administration. QUALIFICATION/SKILLS: Applicants must have a doctoral qualification or equivalent accreditation or standing, and must have a record of demonstrable scholarly achievement in one or more of the following areas of computer science: programming languages, software engineering, operating systems, neurocomputing or computer architecture. SALARY: Salary will be in the range $50,225 to $$57,913. FURTHER INFORMATION Duty statement and selection criteria are available from the Human Resources Department telephone (07) 864 3166. For further information contact the Head of School, Associate Professor George Mohay, telephone +61 7 864 1964, fax +61 7 964 1801 or email g.mohay at qut.edu.au. APPLICATIONS Applications and envelopes should quote {reference number} and include evidence of academic qualifications, experience and teaching evaluations, copies of three best publications or papers plus the names, addresses, facsimile and telephone numbers (and e-mail address if possible) of three referees. Applications should address the selection criteria and reach the Human Resources Director QUT Locked Bag No 2 Red Hill 4059 by Friday, 28 October, 1994. Smoking is not permitted in QUT buildings or vehicles. An Equal Opportunity Employer  From Adriaan.Tijsseling at phil.ruu.nl Mon Oct 3 04:29:03 1994 From: Adriaan.Tijsseling at phil.ruu.nl (Adriaan Tijsseling) Date: Mon, 3 Oct 1994 09:29:03 +0100 (MET) Subject: Thesis available: A Stagewise Treatment of Connectionism Message-ID: <199410030829.JAA08374@laurel.stud.phil.ruu.nl> The following master thesis is available as a PostScript file through ftp: ftp://ftp.phil.ruu.nl/pub/papers/meijer-STC94.ps.gz. Login as anonymous, email as password. The file is compressed with gnuzip. 63 pages total A Stagewise Treatment of Connectionism Roy Meijer Cognitive Artificial Intelligence Department of Philosophy Utrecht University Heidelberglaan 8 3584 CS Utrecht The Netherlands August 1994 Roy.Meijer at phil.ruu.nl Keywords: connectionism, developmental psychology, methodology, neural networks, symbolism. ABSTRACT Connectionism, the research program that is based on neural network techniques, has continued to grow explosively since its reappearance on the cognitive scene in the middle of the eighties. Usually some aspect of human cognition is singled out (e.g. the role of attention in visual tasks), modelled and experimented with. Experimenters often conclude that neural networks are able to do the task while showing some interesting side effects, which sometimes resemble human behavior in those tasks. But what happens next? It looks as if much fragmented work is being done without some sort of coherence, or some sort of strategy. From udah057 at bay.cc.kcl.ac.uk Mon Oct 3 06:36:12 1994 From: udah057 at bay.cc.kcl.ac.uk (udah057@bay.cc.kcl.ac.uk) Date: Mon, 03 Oct 1994 10:36:12 GMT Subject: de Garis PerAc Report Message-ID: <00985633.0D29C9EC.4@bay.cc.kcl.ac.uk> I was shocked to read the personal attack on me put out by de Garis under the heading of the Per Ac94 report. It is very useful to use the connectionist email net as a medium for conference reports, provided that they keep a professional level. An objective approach needs to be brought to writing such items; this was singularly not the case with the de Garis report. I would be grateful if de Garis, and similarly minded people, could restrain themselves in the future. John.G.Taylor  From MDUDZIAK at Gems.VCU.EDU Mon Oct 3 19:00:00 1994 From: MDUDZIAK at Gems.VCU.EDU (MARTIN DUDZIAK) Date: Mon, 03 Oct 1994 19:00:00 -0400 (EDT) Subject: Some activity announc.--- molec. sys/engr and neurocomp/complex sys. Message-ID: From: Dr. M. Dudziak, Biomedical Engineering Dept., Virginia Commonwealth Univ. Four announcements from the Biomedical Engineering Program at Virginia Commonwealth University, Richmond, VA 1) Introductory Workshop on Scanning Probe Microscopy Nov. 18, 1994 (full-day) 2) Public presentation and forum on issues of neuroscience, nanosystems (molecular engineering), and biotechnology Nov. 17, 1994 (PM) 3,4) General information about research, services and educational (graduate-level) programs at MS and PhD level in molecular systems/engineering and in dynamical systems modeling and neurocomputing Please Post and Distribute ================================================================= INTRODUCTORY WORKSHOP SCANNING PROBE MICROSCOPY For BIOLOGICAL AND MATERIALS SCIENCES Friday, November 18, 1994 8:00 AM - 5:00 PM McGuire Hall VCU Medical College of Virginia 12th and Clay Sts. Richmond, VA Sponsored By Biomedical Engineering Program Virginia Commonwealth University An introduction to the field of nanotechnology will be provided with a focus on the uses of scanning probe microscopy for research and engineering applications in the biological and material sciences. Speakers from VCU and other institutions including the manufacturer of the Nanoscope-III Multi-mode Atomic Force Microscope and Scanning Tunneling Microscope will present information on the capabilities, experiences, and recent discoveries using this technology. A perspective on engineering applications of nanotechnology and prospects for federal scientific research and funding within the nanosystems field will be given. Hands-on observation and experience with the Nanoscope-III will be provided. Attendees are welcome to discuss in advance the feasibility of bringing a sample to the workshop for scanning. Friday, Nov. 18 : 8:00 AM: Invited talks and discussions Location: McGuire Hall 118 12:15 PM: Lunch Location: McGuire Hall 118 2:30 PM: Demonstration and hands-on sample processing Location: McGuire Annex 124 For further information contact: Dr. Martin Dudziak, (804) 828-2905, mdudziak at gems.vcu.edu Ms. Elizabeth Faircloth, (804) 828-2591, efaircloth at gems.vcu.edu Workshop Presentations: Chairperson: Dr. Richard Freer, Chairman of Biomedical Engineering Dept., VCU, and CEO of Commonwealth Biotechnologies, Inc., Virginia Biotechnology Research Park 8:15 Dr. Richard Freer Nanotechnology and Complex Systems in 21st Century Medicine: Integration of Academic and Private Sector Biotechnology Research 8:40 Dr. Martin Dudziak, Biomedical Engineering and Physics, VCU Overview of the Molecular Systems and Engineering Lab and work in progress: Quantum Neurodynamics and the Application of AFM to Neuronal Imaging 9:00 Dr. Yale Strausser, Digital Instruments, Inc. Introduction to SPM and the Nanoscope-III: Advances in Biological and Fluid Imaging 10:00 Break / Coffee and Tea 10:15 Dr. Carol R. Kalil, NASA Langley Research Center Surface Analysis of High Performance Materials using STM and AFM 10:45 Dr. Zhifeng Shao, Dept. of Physiology, University of Virginia Instrumentation Development with AFM and Applications to the Study of Membrane Proteins 11:15 Dr. John Cooper, Depts. of Chemistry and Biochemistry, Old Dominion University Scanning Tunneling Microscopy of Novel Electrical Materials 11:45 Mr. Dirk Bosbach, Dept. of Geology, Virginia Polytechnic Institute and State University Applications of SPM in Geochemistry and Environmental Research 12:15 Lunch (Catered) 1:30 Dr. Jan Hoh, Dept. of Physiology, Johns Hopkins University Exploring the Local Properties of Biological Surfaces 2:00 Dr. Peter Moon, School of Dentistry and Biomedical Engineering, VCU Characterizations of Dentin Structure and Comparisons with Modeling and Electron Microscopy 2:30 Demonstrations and Hands-On Imaging with Multi-Mode Atomic Force Microscope (There may be one or two additional speakers) ================================================== BUILDING BRAINS: NEW SCIENCE, NEW BUSINESS Thursday, November 17, 1994 7:00 PM Sanger Hall 1044 VCU Medical College of Virginia 12th and Marshall Streets Richmond, VA A Public Seminar and Forum on how advances in the fields of molecular engineering and nanotechnology, combined with new understandings of the brain and perception, affect the future of medicine, biotechnology, and the economic growth they create. Guest Lecture: Prof. Karl Pribram, pre-eminent neuroscientist, professor emeritus of neuroscience (Stanford University) and Director of the Center for Brain Research and Information Sciences (Radford University) will speak on: Brain Dynamics, the Holonomic Model, and the Emergence of Consciousness Other invited speakers and discussion leaders include: Dr.Paul Werbos, Program Director for Neuro-Engineering, National Science Foundation Dr. Werbos has been active in the development of neural networks for process control and engineering systems as well as in mathematical physics and dynamical systems. Dr. Yale Strausser, Senior Scientist, Digital Instruments, Inc. Dr. Strausser is a principal developer of the Nanoscope architecture and the specialized microscopy tools used in the semiconductor, metallurgical, and chemical industries. Dr. Bijan Rao, Dept. of Physics, Virginia Commonwealth University Dr. Rao has been involved in ground- breaking research in the area of atomic clusters and nanostructured materials, with applications to biomedicine, chemistry, and electronics. Some of the topics and questions that will be addressed during the meeting: What is the new understanding and paradigm emerging through diverse fields of computing, physics, neuroscience, and engineering? What are some of the advances in molecular engineering and nanotechnology and how do these fit with activities in biotech research and development? How may the ability to build molecular-scale machines and computers affect medicine and health in the 21st Century? How can new models of brain function and information processing affect the way we think, act, and respond to long-term illnesses and to individual differences? How will these developments be relevant and important to the people and economy of Richmond and Virginia and the focus upon developing Richmond as a biotechnology center? The meeting is intended to be a presentation of ideas and information and an open discussion among participants. It is open to all members of the public and is particularly geared toward members of the greater Richmond civic, corporate, and educational communities. The seminar is sponsored by the Biomedical Engineering Program at Virginia Commonwealth University. For further information contact: Dr. M. Dudziak McGuire Hall 126 (804) 828-2905, (804) 828-2594 FAX (804) 828-4454 mdudziak at gems.vcu.edu Ms. E. Faircloth Biomed Engineering (804) 828-2591 FAX (804) 828-4454 efaircloth at gems.vcu.edu ======================================================================= MOLECULAR SYSTEMS AND ENGINEERING LABORATORY Services, Training, and Consulting Provided for: Structural Biology Imaging and Engineering (submicron and nanometer level) Surface Imaging and Measurement (molecular and atomic resolution) Micro- and Nanoscale Lithography, Assembly, and Real-Time 3D Modeling Micromachine Design, Simulation, and Testing Uses of Scanning Probe Microscope, Confocal Microscope, Image Processing Tools for Materials Sciences and Biomedical Applications Contractual Imaging and Surface Manipulation is available for departments and labs within VCU and for companies outside the university Resources include: Digital Instruments Nanoscope-III with Multi-Modal Atomic Force Microscope and Scanning Tunneling Microscope Silicon Graphics Indigo workstations with 3D-graphics Multi-processor (parallel computer) workstations and embedded systems Image processing and pattern recognition software and hardware Access to Confocal Microscope, Bioscope AFM, and Vacuum-Based AFM The laboratory is an integrated component of the Biomedical Engineering Program and is located on the MCV Campus of Virginia Commonwealth University *********** The areas of research in this lab are components of the Master's and Doctoral programs in Biomedical Engineering at VCU and both core and elective courses cover topics in these areas. *********** Open House hours for visits and discussions every Tuesday 4 - 6 PM by appointment, please. Dr. M. Dudziak, Director McGuire Hall 126 (804) 828-2905, (804) 828-2594 FAX (804) 828-4454 mdudziak at gems.vcu.edu ========================================================================= COMPLEX DYNAMICAL SYSTEMS AND NEUROCOMPUTING FACILITY Services, Training, and Consulting Provided for: Pattern Classification, Recognition, and Forecasting using: Neural Networks, Genetic Algorithms, and Fuzzy Logic for: Medical, Engineering, Physical Sciences, and Financial Applications Diagnostic Tools for Clinical Neuroscience, Cardiology, Related Fields Modeling of Non-Linear and Chaotic Systems Advanced Medical and Image Processing Techniques Multi-Processor (parallel) Programming and Modeling Multi-media Database Design and Implementation Contractual Arrangements are available for departments and labs within VCU and for companies outside the university Resources include: Silicon Graphics Indigo workstations with 3D-graphics Multi-processor (parallel computer) workstations and embedded systems Image processing and pattern recognition software and hardware Access to Massively-Parallel Supercomputer Resources and Software Tools Digital Instruments Nanoscope-III with Multi-Modal Atomic Force Microscope and Scanning Tunneling Microscope The laboratory is an integrated component of the Biomedical Engineering Program and is located on the MCV Campus of Virginia Commonwealth University *********** The areas of research in this lab are components of the Master's and Doctoral programs in Biomedical Engineering at VCU and both core and elective courses cover topics in these areas. *********** Open House hours for visits and discussions every Tuesday 4 - 6 PM by appointment, please. Dr. M. Dudziak, Director McGuire Hall 126 (804) 828-2905, (804) 828-2594 FAX (804) 828-4454 mdudziak at gems.vcu.edu =============================================================== Further information about the above and other areas of research and education in the biomedical and life sciences may be obtained by accessing the VCU Mosaic/Web servers. The VCU home page is at http://cabell.vcu.edu/vcu/vcu.html  From schmidhu at informatik.tu-muenchen.de Tue Oct 4 05:32:09 1994 From: schmidhu at informatik.tu-muenchen.de (Juergen Schmidhuber) Date: Tue, 4 Oct 1994 10:32:09 +0100 Subject: paper available Message-ID: <94Oct4.103217met.42322@papa.informatik.tu-muenchen.de> ALGORITHMIC ART Report FKI-197-94 (19 pages, non-scientific paper) Juergen Schmidhuber Fakultaet fuer Informatik Technische Universitaet Muenchen 80290 Muenchen, Germany Many artists try to depict ``the essence'' of objects to be represented. In an attempt to formalize certain aspects of the ``the essence'', I propose an art form called algorithmic art. It is based on concepts from algorithmic information theory. Suppose the task is to draw a given object. Usually there are many ways of doing so. The goal of algorithmic art is to draw the object such that the drawing can be specified by an algorithm and two properties hold: (1) The drawing should ``look right''. (2) the Kolmo- gorov complexity of the drawing should be small (the algorithm should be short), and a typical observer should be able to see this. Examples of algorithmic art are given in form of ``algorithmically simple'' cartoons of various objects, including a pin-up girl and a weight lifter. Relations to previous work are established. Finally, attempts are made to relate the formalism of the theory of minimum description length to informal notions like ``good artistic style'' and ``beauty''. To obtain a copy, do: unix> ftp 131.159.8.35 Name: anonymous Password: (your email address, please) ftp> binary ftp> cd pub/fki ftp> get fki-197-94.ps.gz ftp> bye unix> gunzip fki-197-94.ps.gz unix> lpr fki-197-94.ps Alternatively, check out my home page: http://papa.informatik.tu-muenchen.de/mitarbeiter/schmidhu.html Use a high resolution printer (600 dpi) to print the file (the layout is designed for European A4 paper). On many printers you will have to use the -s option ( > 1MB uncompressed). Comments are welcome. Are you aware of any other mailing lists or publishers who might be interested in this work? Please tell me. Juergen Schmidhuber  From gar at eng.cam.ac.uk Tue Oct 4 11:20:12 1994 From: gar at eng.cam.ac.uk (gar@eng.cam.ac.uk) Date: Tue, 4 Oct 94 11:20:12 BST Subject: TR: On-line Q-learning using Connectionist Systems Message-ID: <29766.9410041020@hope.eng.cam.ac.uk> The following technical report is available by anonymous ftp from the archive of the Speech, Vision and Robotics Group at the Cambridge University Engineering Department. ON-LINE Q-LEARNING USING CONNECTIONIST SYSTEMS G. A. Rummery and M. Niranjan Technical Report CUED/F-INFENG/TR 166 Cambridge University Engineering Department Trumpington Street Cambridge CB2 1PZ England Abstract Reinforcement learning algorithms are a powerful machine learning technique. However, much of the work on these algorithms has been developed with regard to discrete finite-state Markovian problems, which is too restrictive for many real-world environments. Therefore, it is desirable to extend these methods to high dimensional continuous state-spaces, which requires the use of function approximation to generalise the information learnt by the system. In this report, the use of back-propagation neural networks (Rumelhart et al, 1986) is considered in this context. We consider a number of different algorithms based around Q-Learning (Watkins, 1989) combined with the Temporal Difference algorithm (Sutton, 1988), including a new algorithm (Modified Connectionist Q-Learning), and Q(lambda) (Peng and Williams, 1994). In addition, we present algorithms for applying these updates on-line during trials, unlike backward replay used by Lin (1993) that requires waiting until the end of each trial before updating can occur. On-line updating is found to be more robust to the choice of training parameters than backward replay, and also enables the algorithms to be used in continuously operating systems where no end of trial conditions occur. We compare the performance of these algorithms on a realistic robot navigation problem, where a simulated mobile robot is trained to guide itself to a goal position in the presence of obstacles. The robot must rely on limited sensory feedback from its surroundings, and make decisions that can be generalised to arbitrary layouts of obstacles. These simulations show that on-line learning algorithms are less sensitive to the choice of training parameters than backward replay, and that the alternative update rules of MCQ-L and Q(lambda) are more robust than standard Q-learning updates. ************************ How to obtain a copy ************************ Via anonymous ftp: unix> ftp svr-ftp.eng.cam.ac.uk Name: anonymous Password: (type your email address) ftp> cd reports ftp> binary ftp> get rummery_tr166.ps.Z ftp> quit unix> uncompress rummery_tr166.ps.Z unix> lpr rummery_tr166.ps (or however you print PostScript)  From cowan at synapse.uchicago.edu Tue Oct 4 12:46:47 1994 From: cowan at synapse.uchicago.edu (Jack Cowan) Date: Tue, 4 Oct 94 10:46:47 -0600 Subject: de Garis PerAc Report Message-ID: <9410041646.AA00766@synapse> I'd like to second John Taylor's request. I was really surprised to read the report in question. In my opinion personal comments of such a nature should not be transmitted through the connectionist or any other public mailings. Jack Cowan ............... MODERATOR'S NOTE: I don't edit submissions to CONNECTIONISTS for style or detailed content; I only check to make sure they're relevant to the list and contain at least some technical material of value. In the case of de Garis' conference reports, he (and I) have now been suitably warned by the readership about what constitutes acceptable material for this list. Any further discussion of the de Garis article should probably take place via private email. If people would like to submit alternative accounts of the PerAc conference, I would be hapy to receive them. -- Dave Touretzky, CONNECTIONISTS moderator  From mbrown at aero.soton.ac.uk Tue Oct 4 16:24:53 1994 From: mbrown at aero.soton.ac.uk (Martin Brown) Date: Tue, 4 Oct 94 16:24:53 BST Subject: Postdoctoral Position Message-ID: <21277.9410041524@aero.soton.ac.uk> Department of Aeronautics and Astronautics Southampton University, UK Postdoctoral Position in Intelligent Characterisation (Modelling) and Control of Plasma Etching Processes Applicants are invited to apply for a 3 year Postdoctoral position in the above area. The primary objective of the project is to develop real-time intelligent modelling and control methods for reactive ion etching of semi-conducting materials. The research grant is funded by EPSRC as a ROPA award. Both experimental and modelling work will be involved and candidates should ideally have experience in experimental physics (optical emission spectroscopy, laser interferometry) and neural net/neuro-fuzzy control techniques. Applicants with experience in either one of the areas and a strong interest in the other area are encouraged to apply. The position will be on the RA1A scale with a salary in the range 13,941-20,953 (UK pounds) and will commence as soon as possible. For further information and informal discussions call either Dr. Stephen Gabriel on 0703 593222, email sbg at aero.soton.ac.uk, or Professor Chris Harris on 0703 592353, email cjh at aero.soton.ac.uk. Closing date for applications will be in approximately 5-6 weeks time.  From B.DASGUPTA at fs3.mbs.ac.uk Tue Oct 4 17:06:19 1994 From: B.DASGUPTA at fs3.mbs.ac.uk (BHASKAR DASGUPTA ALIAS BD) Date: 4 Oct 94 17:06:19 BST Subject: GARCH MODELS COMPARED TO CONNECTIONIST MODELS Message-ID: <30656710BC7@fs3.mbs.ac.uk> Hello, I have a query about the suitability of using GARCH(p,q) models in modelling economic and financial time series. I was advised to compare my NN performance in foreign exchange rate prediction to the performance of a GARCH model. I checked up in the Gershenfield & Weigend Book on Time Series Forecasting, and in the chapter on Foreign exchange data series prediction written by LeBaron, I could only find reference to a ARCH model used to determine non-linearity along with the BDS and TSAY tests, but the ARCH model was not used to predict or compare predictions. Is this approach of comparing NN forecasts with GARCH models prevalent, or is anyone working on this?, In the Trippi & Turban book, ARIMA models are compared, but not GARCH/ ARCH. I am looking to contact someone who is working on this, or someone who can guide me to some code which does this, either as in a macro in LOTUS123, or RATS or SPSS (the only statistical software I have access to :-). I would appreciate any response, and if there are sufficient responses, I would summarize and repost to the group. Thanks in advance. bd PS: I shall also be posting this message on the ALLSTAT group, so apologies for the cross post. Bhaskar Dasgupta SnailMail Manchester Business School Phone ::010-44-61-275-6547 Booth Street West Fax ::010-44-61-273-7732 Manchester, M15 6PB, England. email ::b.dasgupta at fs3.mbs.ac.uk  From mingli at dimacs.rutgers.edu Tue Oct 4 14:25:04 1994 From: mingli at dimacs.rutgers.edu (Ming Li) Date: Tue, 4 Oct 94 14:25:04 EDT Subject: Call For Papers: COLT'95 -- Plaintext Version Message-ID: <9410041825.AA10901@dimacs.rutgers.edu> ______________________________________________________________________ CALL FOR PAPERS---COLT 95 Eighth Conference on Computational Learning Theory Santa Cruz, California, USA; July 5-8, 1995 ______________________________________________________________________ The Eighth Conference on Computational Learning Theory (COLT 95) will be held on the campus of the University of California at Santa Cruz, USA, from the late afternoon of Wednesday, July 5, through Saturday, July 8, 1995. COLT 95 is sponsored by the University of California, in cooperation with the ACM Special Interest Groups for Algorithms and Computation Theory (SIGACT) and Artificial Intelligence (SIGART). We invite papers in all areas that relate directly to the analysis of learning algorithms and the theory of machine learning, including artificial and biological neural networks. We also invite papers on learning from related theoretical and applied areas, such as statistics, statistical physics, Bayesian/MDL estimation, information theory, inductive inference, logic, inductive logic programming, knowledge representation, knowledge discovery in databases, natural language processing, robotics, and pattern recognition. Besides purely theoretical papers we encourage the submission of papers on experimental results that also provide a theoretical analysis. INVITED TALKS. Invited talks will be given by Terry Sejnowski (Salk Institute and University of California at San Diego) and Les Valiant (Harvard University). ABSTRACT SUBMISSION. Authors should submit fourteen copies (preferably two-sided copies) of an extended abstract to Wolfgang Maass - COLT 95 Institute for Theoretical Computer Science Technische Universitaet Graz, Klosterwiesgasse 32/2 A-8010 Graz, Austria An abstract must be RECEIVED BY JANUARY 10, 1995 (or postmarked by January 2 and sent airmail). This deadline is FIRM! Papers that have appeared in journals or other conferences, or that are being submitted to other conferences, are not appropriate for submission to COLT. There is a single exception: Since in 1995 the notification date for STOC is shortly after the submission deadline for COLT, these conferences have agreed that a paper can be submitted both to STOC 95 and COLT 95, with the understanding that such paper is automatically withdrawn from COLT if accepted at STOC. ABSTACT FORMAT. The extended abstract should consist of a cover page with title, authors' names, postal and e-mail addresses, and a 200-word summary. The body of the abstract should be no longer than 10 pages with roughly 35 lines/page in 12-point font. Papers deviating significantly from this length constraint will not be considered. The body should include a clear definition of the theoretical model used, an overview of the results, and some discussion of their significance, including comparison to other work. Proofs or proof sketches should be included. PROGRAM FORMAT. The program will consist of both "long" talks, and "short" talks, corresponding to longer and shorter papers in the proceedings. The short talks will also be coupled with a poster presentation in special poster sessions. By default, all papers will be considered for both categories. Authors who DO NOT want their papers considered for the short category should indicate that fact in the cover letter. The cover letter should also specify the contact author and give his/her e-mail. NOTIFICATION. Authors will be notified of acceptance or rejection by a letter mailed on or before Friday, March 10, with possible earlier notification via e-mail. Final camera-ready papers will be due by Tuesday, April 11. PROGRAM CHAIR. Wolfgang Maass (TU Graz, Austria, e-mail: maass at igi.tu-graz.ac.at). CONFERENCE AND LOCAL ARRANGEMENTS CHAIRS. David Haussler and Manfred Warmuth (U. of California at Santa Cruz) PROGRAM COMMITTEE. Dana Angluin (Yale), Peter Bartlett (ANU, Australia), Tom Dietterich (Oregon State Univ.), Haym Hirsh (Rutgers), Jeff Jackson (CMU), Martin Kummer (Univ. Karlsruhe), Phil Long (Duke Univ.), Ron Rivest (MIT), Robert Schapire (AT&T), Ted Slaman (Univ. of Chicago), Naftali Tishby (Hebrew Univ.), Gyorgy Turan (UIC, Chicago). COLT AND ML. The Twelfth Intern. Conf. on Machine Learning (ML 95) will be held right after COLT 95 on July 9 - 12 at Tahoe City, California. Car pools from Santa Cruz to Tahoe City on July 8 will be arranged.  From moody at chianti.cse.ogi.edu Tue Oct 4 16:28:13 1994 From: moody at chianti.cse.ogi.edu (John Moody) Date: Tue, 4 Oct 94 13:28:13 -0700 Subject: Neural Networks in the Capital Markets Conference Message-ID: <9410042028.AA12835@chianti.cse.ogi.edu> Fellow Connectionists: This is a reminder to register for NNCM*94 as soon as possible. The deadline for reserving rooms at the Pasadena Ritz Carlton at the conference rate is October 15. Yaser Abu-Mostafa John Moody ******************************************************************* --- Registration Package and Preliminary Program --- NNCM-94 Second International Workshop NEURAL NETWORKS in the CAPITAL MARKETS Thursday-Friday, November 17-18, 1994 with tutorials on Wednesday, November 16, 1994 The Ritz-Carlton Hotel, Pasadena, California, U.S.A. Sponsored by Caltech and London Business School Neural networks have now been applied to a number of live systems in the capital markets, and in many cases have demonstrated better performance than competing approaches. Because of the overwhelming interest in the first NNCM workshop held in London in November 1993, the second annual NNCM workshop will be held November 17-18, 1994, in Pasadena, California. This is a research meeting where original, high-quality contributions to the field are presented and discussed. In addition, a day of introductory tutorials (Wednesday, November 16) will be included to familiarize audiences of different backgrounds with the financial aspects, and the mathematical aspects, of the field. --Invited Speakers: The workshop will feature invited talks by four internationally recognized researchers: Dr. Andrew Lo, MIT Sloan School Dr. Paul Refenes, London Business School Dr. Robert Shiller, Yale University Dr. Hal White, UC San Diego --Contributed Papers: NNCM-94 will have 4 oral sessions and 2 poster sessions with more than 40 contributed papers presented by academicians and practitioners from both the neural networks side and the capital markets side. Each paper has been refereed by 4 experts in the field. The areas of the accepted papers include: Stock and bond valuation and trading, asset allocation and portfolio management, real trading using neural networks, foreign exchange rate prediction, option pricing, univariate time series analysis, neural network methodology, statistical analysis and hints, theory of forecasting, and neural network modeling. --Tutorials: Before the main program, there will be a day of tutorials on Wednesday, November 16, 1994. The morning session will focus on the financial side and the afternoon session will focus on the mathematical side. -Morning Session- Dynamics of Trading and Market Microstructure Dr. Larry Harris, University of Southern California Empirical Research on Market Inefficiencies Dr. Blake LeBaron, University of Wisconsin -Afternoon Session- Neural Networks, Time Series, and Finance Dr. John Moody, Oregon Graduate Institute Statistical Inference for Neural Networks Dr. Brian Ripley, Oxford University We are very pleased to have tutors of such caliber help bring new audiences from different backgrounds up to speed in this hybrid area. --Schedule Outline: Wednesday, November 16: 8:00-12:15 Tutorials I & II 1:30-5:45 Tutorials III & IV Thursday, November 17: 8:30-11:30 Oral Session I 11:30-2:00 Luncheon & Poster Session I 2:00-5:00 Oral Session II Friday, November 18: 8:30-11:30 Oral Session III 11:30-2:00 Luncheon & Poster Session II 2:00-5:00 Oral Session IV --Location: The workshop will be held at the Ritz-Carlton Huntington Hotel in Pasadena, within two miles from the Caltech campus. One of the most beautiful hotels in the U.S., the Ritz is a 35-minute drive from Los Angeles International Airport (LAX) with nonstop flights from most major cities in North America, Europe, the Far East, Australia, and South America. Home of Caltech, Pasadena has recently become a major dining/hangout center for Southern California with the growth of its `Old Town', built along the styles of the 1950's. Among the cultural attractions of Pasadena are the Norton Simon Museum, the Huntington Library/ Gallery/Gardens, and a number of theaters including the Ambassador Theater. --Organizing Committee: Dr. Y. Abu-Mostafa, California Institute of Technology Dr. A. Atiya, Cairo University Dr. N. Biggs, London School of Economics Dr. D. Bunn, London Business School Dr. B. LeBaron, University of Wisconsin Dr. A. Lo, MIT Sloan School Dr. J. Moody, Oregon Graduate Institute Dr. A. Refenes, London Business School Dr. M. Steiner, Universitaet Munster Dr. A. Timmermann, Birkbeck College, London Dr. A. Weigend, University of Colorado Dr. H. White, University of California, San Diego --Registration and Hotel Reservation: Registration is done by mail on a first-come, first-served basis (last year we had to return the checks to more than 50 people for lack of space). To ensure your place at the workshop, please send the enclosed registration form and payment as soon as possible to Ms. Lucinda Acosta, Caltech 116-81, Pasadena, CA 91125, U.S.A. Please make checks payable to Caltech. Hotel reservations are made by contacting the Ritz-Carlton Hotel directly. Their phone number is (818) 568-3900 and fax number is (818) 792-6613. Please mention that you are with NNCM-94 in order to get the (very) special rate that we negotiated. The rate is $79+taxes ($99 with $20 credited by NNCM-94 upon registration) per room (single or double occupancy) per night. Please make the hotel reservation IMMEDIATELY as the rate is based on availability. --Secretariat: For further information, please contact the NNCM-94 secretariat Ms. Lucinda Acosta, Caltech 116-81, Pasadena, CA 91125, U.S.A. e-mail: lucinda at sunoptics.caltech.edu , phone (818) 395-4843, fax (818) 568-8437 ******************************************************************* -- NNCM-94 Registration Form -- Title:--------- Name:------------------------------------ Mailing Address:------------------------------------------- ----------------------------------------------------------- e-mail:---------------------------- fax:------------------- ********Please circle the applicable fees and write the total******** --Main Conference (November 17-18): Registration fee $500 Discounted fee for academicians $250 (letter on university letterhead required) Discounted fee for full-time students $125 (letter from registrar or faculty advisor required) --Tutorials (November 16): You must be registered for the main conference in order to register for the tutorials. Morning Session Only $100 Afternoon Session Only $100 Both Sessions $150 Full-time students $50 (letter from registrar or faculty advisor required) TOTAL: $-------- Please include payment (check or money order in US currency). PLEASE MAKE CHECK PAYABLE TO CALTECH. --Hotel Reservation: Please contact the Ritz-Carlton Huntington Hotel in Pasadena directly. The phone number is (818) 568-3900 and the fax number is (818) 792-6613. Ask for the NNCM-94 rate. We have negotiated an (incredible) rate of $79+taxes ($99 with $20 credited by NNCM-94 upon registration) per room (single or double occupancy) per night, based on availability. ********Please mail your completed registration form and payment to******** Ms. Lucinda Acosta, Caltech 116-81, Pasadena, CA 91125, U.S.A.  From P.McKevitt at dcs.shef.ac.uk Tue Oct 4 16:39:26 1994 From: P.McKevitt at dcs.shef.ac.uk (Paul Mc Kevitt) Date: Tue, 4 Oct 94 16:39:26 BST Subject: No subject Message-ID: <9410041539.AA07917@dcs.shef.ac.uk> CONFERENCE ANNOUNCEMENT AND PRELIMINARY CALL FOR PAPERS AISB-95: Hybrid Problems, Hybrid Solutions. ============================================ Monday 3rd -- Friday 7th April 1995 Halifax Hall of Residence & Computer Science Department University of Sheffield Sheffield, ENGLAND The Tenth Biennial Conference on AI and Cognitive Science organised by the Society for the Study of Artificial Intelligence and the Simulation of Behaviour Programme Chair: John Hallam (University of Edinburgh) Programme Committee: Dave Cliff (University of Sussex) Erik Sandewall (University of Linkoeping) Nigel Shadbolt (University of Nottingham) Sam Steel (University of Essex) Yorick Wilks (University of Sheffield) Local Organisation: Paul Mc Kevitt (University of Sheffield) The past few years have seen an increasing tendency for diversification in research into Artificial Intelligence, Cognitive Science and Artificial Life. A number of approaches are being pursued, based variously on symbolic reasoning, connectionist systems and models, behaviour-based systems, and ideas from complex dynamical systems. Each has its own particular insight and philosophical position. This variety of approaches appears in all areas of Artificial Intelligence. There are both sybmolic and connectionist natural language processing, both classical and behaviour-based vision research, for instance. While purists from each approach may claim that all the problems of cognition can in principle be tackled without recourse to other methods, in practice (and maybe in theory, also) combinations of methods from the different approaches (hybrid methods) are more successful than a pure approach for certain kinds of problems. The committee feels that there is an unrealised synergy between the various approaches that an AISB conference may be able to explore. Thus, the focus of the tenth AISB Conference is on such hybrid methods. We particularly seek papers that describe novel theoretical and/or experimental work which uses a hybrid approach or papers from purists, arguing cogently that compromise is unnecessary or unproductive. While papers such as those are particularly sought, good papers on any topic in Artificial Intelligence will be considered: as always, the most important criteria for acceptance will be soundness, originality, substance and clarity. Research in all areas is equally welcome. The AISB conference is a single track conference lasting three days, with a two day tutorial and workshop programme preceding the main technical event, and around twenty high calibre papers will be presented in the technical sessions. It is expected that the proceedings of the conference will be published in book form in time to be available at the conference itself, making it a forum for rapid dissemination of research results. SUBMISSIONS: High quality original papers dealing with the issues raised by mixing different approaches, or otherwise related to the Conference Theme, should be sent to the Programme Chair. Papers which give comparative experimental evaluation of methods from different paradigms applied to the same problem, papers which propose and evaluate mixed-paradigm theoretical models or tools, and papers that focus on hybrid systems applied to real world problems will be particularly welcome, as will papers from purists who argue cogently that the hybrid approach is flawed and a particular pure approach is to be preferred. Papers being submitted, whether verbatim or in essence, to other conferences whose review process runs concurrently with AISB-95 should indicate this fact on their title page. If a submitted paper appears at another conference it must be withdrawn from AISB-95 (this does not apply to presentation at specialist workshops). Papers that violate these requirements may be rejected without review. SHEFFIELD: Sheffield is one of the friendliest cities in the UK and is situated well having the best and closest surrounding countryside of any major city in the UK. The Peak District National Park is only minutes away. It is a good city for walkers, runners, and climbers. It has two theatres, the Crucible and Lyceum. The Lyceum, a beautiful Victorian theatre, has recently been renovated. Also, the city has three 10 screen cinemas. There is a library theatre which shows more artistic films. The city has a large number of museums many of which demonstrate Sheffield's industrial past, and there are a number of Galleries in the City, including the Mapping Gallery and Ruskin. A number of important ancient houses are close to Sheffield such as Chatsworth House. The Peak District National Park is a beautiful site for visiting and rambling upon. There are large shopping areas in the City and by 1995 Sheffield will be served by a 'supertram' system: the line to the Meadowhall shopping and leisure complex is already open. The University of Sheffield's Halls of Residence are situated on the western side of the city in a leafy residential area described by John Betjeman as ``the prettiest suburb in England''. Halifax Hall is centred on a local Steel Baron's house, dating back to 1830 and set in extensive grounds. It was acquired by the University in 1830 and converted into a Hall of Residence for women with the addition of a new wing. ARTIFICIAL INTELLIGENCE AT SHEFFIELD: Sheffield Computer Science Department has a strong programme in Cognitive Systems and is part of the University's Institute for Language, Speech and Hearing (ILASH). ILASH has its own machines and support staff, and academic staff attached to it from nine departments. Sheffield Psychology Department has the Artificial Intelligence Vision Research Unit (AIVRU) which was founded in 1984 to coordinate a large industry/university Alvey research consortium working on the development of computer vision systems for autonomous vehicles and robot workstations. FORMAT AND DEADLINES: Four copies of submitted papers must be received by the Programme Chair no later than 24 OCTOBER 1994 to be considered. Papers should be at most 12 pages in length and be produced in 12 point, with at most 60 lines of text per A4 page and margins at least 1 inch (2.5cm) wide on all sides (default LaTeX article style is OK). They should include a cover sheet (not counted in the 12 page limit) giving the paper title, the abstract, the authors and their affiliations, including a contact address for both electronic and paper mail for the principal author. Papers should be submitted in hard-copy, not electronically. Papers that do not adhere to this format specification may be rejected without review. Notification of acceptance will be sent to authors by 7 DECEMBER 1994 and full camera-ready copy will be due in early JANUARY 1995 (publishers' deadlines permitting). CONFERENCE ADDRESS: Correspondence relating to the conference programme, submissions of papers, etc. should be directed to the conference programme chair at the address below. John Hallam, Department of Artificial Intelligence, University of Edinburgh, 5 Forrest Hill, Edinburgh EH1 2QL, SCOTLAND. Phone: + 44 31 650 3097 FAX: + 44 31 650 6899 E-mail: john at aifh.edinburgh.ac.uk Correspondence concerning local arrangements should be directed to the local arrangements organiser at the following address. Paul Mc Kevitt, Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, ENGLAND. Phone: + 44 742 825572 FAX: + 44 742 780972 E-mail: p.mckevitt at dcs.sheffield.ac.uk  From john at dcs.rhbnc.ac.uk Wed Oct 5 07:47:33 1994 From: john at dcs.rhbnc.ac.uk (john@dcs.rhbnc.ac.uk) Date: Wed, 05 Oct 94 12:47:33 +0100 Subject: Technical Report Series in Neural and Computational Learning Message-ID: <25115.9410051147@platon.cs.rhbnc.ac.uk> The European Community ESPRIT Working Group in Neural and Computational Learning Theory (NeuroCOLT): two new reports available ---------------------------------------- NeuroCOLT Technical Report NC-TR-94-010: ---------------------------------------- Computational Complexity of Neural Networks: a Survey by Pekka Orponen, Department of Computer Science, P. O. Box 26, FIN-00014 University of Helsinki, Finland Abstract: We survey some of the central results in the complexity theory of discrete neural networks, with pointers to the literature. Our main emphasis is on the computational power of various acyclic and cyclic network models, but we also discuss briefly the complexity aspects of synthesizing networks from examples of their behavior. ---------------------------------------- NeuroCOLT Technical Report NC-TR-94-012: ---------------------------------------- A Note on Testing the Resultant by T. Lickteig Universit\"at Bonn and K. Meer RWTH Aachen Germany Abstract: \def\C{\prime \kern -5pt C} % Menge der komplexen Zahlen : \C In a recent paper Shub proposes to attack the complex $P_{\C} $ versus $NP_{\C} $ problem by focussing on lower bounds on testing the resultant of quadratic forms for zero. Taking up this question we show in the present paper a lower bound of order $n^3$ for testing the resultant of $n$ homogeneous polynomials of degree 2 in $n$ unknowns to vanish. ----------------------- The Report NC-TR-94-010 can be accessed and printed as follows % ftp cscx.cs.rhbnc.ac.uk (134.219.200.45) Name: anonymous password: your full email address ftp> cd pub/neurocolt/tech_reports ftp> binary ftp> get nc-tr-94-010.ps.Z ftp> bye % zcat nc-tr-94-010.ps.Z | lpr -l Likewise for NC-TR-94-012. Uncompressed versions of the postscript files have also been left for anyone not having an uncompress facility. A full list of the currently available Technical Reports in the Series is held in a file `abstracts' in the same directory. Best wishes John Shawe-Taylor  From esann at dice.ucl.ac.be Wed Oct 5 11:40:03 1994 From: esann at dice.ucl.ac.be (esann@dice.ucl.ac.be) Date: Wed, 5 Oct 1994 17:40:03 +0200 Subject: ESANN'95: European Symposium on Artificial Neural Networks Message-ID: <9410051637.AA23814@ns1.dice.ucl.ac.be> ******************************************************** * ESANN95 * * * * 3rd European Symposium on Artificial Neural Networks * * Brussels - April 19-20-21, 1995 * * * * What's new in fundamental research ? * * * ******************************************************** First announcement and call for papers ______________________________________ Invitation and Scope of the conference ______________________________________ In 1995, the third European Symposium on Artificial Neural Networks will be organized in Brussels, Belgium. The two first successful editions each gathered about 100 scientists, coming from Western and Eastern Europe, but also from USA, Japan, Australia, New Zealand,... The field of Artificial Neural Networks includes a lot of different disciplines, from mathematics and statistics to robotics and electronics. For this reason, actual studies concern various aspects of the field, sometimes to the detriment of strong, well established foundations for these researches; it is obvious that a better knowledge of the basic aspects of neurocomputing, and more effective comparisons with other computing methods are strongly necessary for a profitable long-term use of neural networks in applications. The purpose of the ESANN conferences is to present the latest results in the fundamental aspects of artificial neural networks. Invited and survey talks will also present a comprehensive view of particular topics of the conference. The program committee of ESANN'95 welcomes papers covering new results or being of tutorial nature, and dealing with theoretical, biological or mathematical aspects of artificial neural networks, or with the relations between neural networks and other fields. The following is a non-exhaustive list of topics which will be covered during ESANN'95 : + theory + models and architectures + mathematics + learning algorithms + biologically plausible artificial networks + formal models of biological phenomena + neurobiological systems + approximation of functions + adaptive behavior + signal processing + statistics + self-organization + evolutive learning Invited talks will be given by H.P. Mallot (Max-Planck-Institut fur Biologische Kybernetik, Tbingen, Germany), and by P. Comon (Thomson-Sintra Sophia Antipolis, France). Other invited talks are to be announced. The conference will be held in the center of Brussels, the capital of Belgium. Close to most great European cities, Brussels is exceptionally well served by closely-knit motorway and railway systems, and an international airport. Besides an artistic and cultural center of attraction, Brussels is also renowned for its countless typical cafs, for its famous and typical Belgian food, and for its considerable night life. Call for contributions ______________________ Prospective authors are invited to submit six originals of their contribution before November 29, 1994. Working language of the conference (including proceedings) is English. Papers should not exceed six A4 pages (including figures and references). Printing area will be 12.2 x 19.3 cm (centered on the A4 page); left, right, top and bottom margins will thus respectively be 4.4, 4.4, 5.2 and 5.2 cm. 10-point Times font will be used for the main text; headings will be in bold characters (but not underlined), and will be separated from the main text by two blank lines before and one after. Manuscripts prepared in this format will be reproduced in the same size in the book. Originals of the figures will be pasted into the manuscript and centered between the margins. The lettering of the figures should be in 10-point Times font size. Figures should be numbered. The legends also should be centered between the margins and be written in 9-point Times font size as follows: Fig. 3. Text follows ... The pages of the manuscript will not be numbered (numbering decided by the editor). AUTHORS ARE STRONGLY INVITED TO ASK FOR THE FULL INSTRUCTIONS FOR AUTHORS (see coordinates below). A separate page (not included in the manuscript) will indicate: + the title of the manuscript + author(s) name(s) + the complete address (including phone & fax numbers and E-mail) of the corresponding author + a list of five keywords or topics On the same page, the authors will copy and sign the following paragraph: "in case of acceptation of the paper for presentation at ESANN 95: - at least one of the authors will register to the conference and will present the paper - the author(s) give their rights up over the paper to the organizers of ESANN 95, for the proceedings and any publication that could directly be generated by the conference - if the paper does not match the format requirements for the proceedings, the author(s) will send a revised version within two weeks of the notification of acceptation." Contributions must be sent to the conference secretariat. Examples of camera-ready contributions can be obtained by writing to the same address. Registration fees _________________ registration before registration after February 1st, 1995 February 1st, 1995 Universities BEF 15000 BEF 16000 Industries BEF 19000 BEF 20000 An "advanced registration form" is available by writing to the conference secretariat (see reply form below). Please ask for this form in order to benefit from the reduced registration fee before February 1st, 1995. Deadlines _________ Submission of papers November 29, 1994 Notification of acceptance January 20, 1995 Symposium April 19-21, 1995 Grants ______ A limited number of grants (registration fees and economic accommodation) will be given to young scientists coming from the European Community or from Central and Eastern European countries (E.C. Human Capital and Mobility program). Please write to the conference secretariat to get an application form for these grants. Deadline for applications: December 31, 1994. Conference secretariat ______________________ Dr. Michel Verleysen D facto conference services 45 rue Masui B - 1210 Brussels (Belgium) phone: + 32 2 245 43 63 Fax: + 32 2 245 46 94 E-mail: esann at dice.ucl.ac.be Information is also available through WWW and anonymous FTP on the following sites: URL: http://www.dice.ucl.ac.be/neural-nets/ESANN/ESANN.html FTP: ftp.dice.ucl.ac.be, directory /pub/neural-nets/ESANN Steering committee __________________ Francois Blayo EERIE, Nimes (F) Marie Cottrell Univ. Paris I (F) Nicolas Franceschini CNRS Marseille (F) Jeanny Herault INPG Grenoble (F) Michel Verleysen UCL Louvain-la-Neuve (B) Scientific committee ____________________ (to be confirmed) Luis Almeida INESC - Lisboa (P) Jorge Barreto UCL Louvain-en-Woluwe (B) Herv Bourlard ICSI Berkeley (USA) Joan Cabestany Univ. Polit. de Catalunya (E) Dave Cliff University of Sussex (UK) Holk Cruse Universitat Bielefeld (D) Dante Del Corso Politecnico di Torino (I) Marc Duranton Philips / LEP (F) Jean-Claude Fort Universite Nancy I (F) Karl Goser Universitat Dortmund (D) Martin Hasler EPFL Lausanne (CH) Philip Husbands University of Sussex (UK) Christian Jutten INPG Grenoble (F) Vera Kurkova Acad. of Science of the Czech Rep. (CZ) Petr Lansky Acad. of Science of the Czech Rep. (CZ) Jean-Didier Legat UCL Louvain-la-Neuve (B) Eddy Mayoraz Rutgers University (USA) Jean Arcady Meyer Ecole Normale Suprieure - Paris (F) Erkki Oja Helsinky University of Technology (SF) Gilles Pags Universite Paris I (F) Alberto Prieto Universitad de Granada (E) Pierre Puget LETI Grenoble (F) Ronan Reilly University College Dublin (IRE) Tamas Roska Hungarian Academy of Science (H) Jean-Pierre Rospars INRA Versailles (F) Jean-Pierre Royet Universite Lyon 1 (F) John Stonham Brunel University (UK) Lionel Tarassenko University of Oxford (UK) John Taylor King's College London (UK) Vincent Torre Universita di Genova (I) Claude Touzet EERIE Nmes (F) Joos Vandewalle KU Leuven (B) Marc Van Hulle KU Leuven (B) Eric Vittoz CSEM Neuchatel (CH) Christian Wellekens Eurecom Sophia-Antipolis (F) Reply form __________ If you wish to receive the final program of ESANN'95, for any address change, or to add one of your colleagues in our database, please send this form to the conference secretariat: D facto conference services 45 rue Masui B - 1210 Brussels (Belgium) phone: + 32 2 245 43 63 Fax: + 32 2 245 46 94 E-mail: esann at dice.ucl.ac.be Please indicate if you wish to receive the advanced registration form. ---------------------------------------------------------------- Name: .......................................................... First Name: .................................................... University or Company: ......................................... Address: ....................................................... ZIP: ................... Town: ................................ Country: ....................................................... Tel: ........................................................... Fax: ........................................................... E-mail: ........................................................ O Please send me the "advanced registration form" ---------------------------------------------------------------- _____________________________ D facto publications - conference services 45 rue Masui 1210 Brussels Belgium tel: +32 2 245 43 63 fax: +32 2 245 46 94 _____________________________  From nadal at physique.ens.fr Wed Oct 5 13:27:31 1994 From: nadal at physique.ens.fr (NADAL Jean-Pierre) Date: Wed, 5 Oct 1994 18:27:31 +0100 Subject: New Paper: infomax and redundancy reduction Message-ID: <199410051727.SAA01831@droopy.ens.fr> FTP-host: archive.cis.ohio-state.edu FTP-file: pub/neuroprose/nadalparga.infomaxredred.ps.Z The following paper has been placed in the Neuroprose repository: "Non linear neurons in the low noise limit: a factorial code maximizes information transfer" J.-P. Nadal (ENS, Paris) and N. Parga (UAM, Madrid) (19 pages) To appear in NETWORK: computation in neural systems ABSTRACT: We investigate the consequences of maximizing information transfer in a simple neural network (one input layer, one output layer), focussing on the case of {\it non linear} transfer functions. We assume that both receptive fields (synaptic efficacies) and transfer functions can be adapted to the environment. he main result is that, for bounded and invertible transfer functions, in the case of a vanishing {\it additive} output noise, and no input noise, maximization of information (Linsker's{\it infomax} principle) leads to a factorial code - hence to the same solution as required by the redundancy reduction principle of Barlow. We show also that this result is valid for {\it linear}, more generally unbounded, transfer functions, provided optimization is performed under an additive constraint, that is which can be written as a sum of terms, each one being specific to one output neuron. Finally we study the effect of a non zero input noise. We find that, at first order in the input noise, assumed to be small as compared to the - small - output noise, the above results are still valid, provided the {\it output} noise is uncorrelated from one neuron to the other. Jean-Pierre Nadal nadal at physique.ens.fr Laboratoire de Physique Statistique Ecole Normale Sup\'erieure 24, rue Lhomond 75231 Paris Cedex05 - France Nestor Parga parga at ccuam3.sdi.uam.es Departamento de F\'isica Te\'orica Universidad Aut\'onoma de Madrid Canto Blanco, 28049 Madrid - Spain ============================================ Retrieve this paper by anonymous ftp from: archive.cis.ohio-state.edu in the /pub/neuroprose directory The name of the paper in this archive is: nadalparga.infomaxredred.ps.Z (19 pages. No hard copy available.)  From sirosh at cs.utexas.edu Thu Oct 6 00:45:31 1994 From: sirosh at cs.utexas.edu (Joseph Sirosh) Date: Thu, 6 Oct 1994 04:45:31 +0000 Subject: CFP: NIPS Post-Conference Workshop on Lateral Connections in the Cortex Message-ID: <199410060445.EAA34040@duckula.cs.utexas.edu> CALL FOR PARTICIPANTS: NIPS POST-CONFERENCE WORKSHOP ---------------------------------------------------- COMPUTATIONAL ROLE OF LATERAL CONNECTIONS IN THE CORTEX Substantial recent evidence indicates that intracortical connections develop in an activity-dependent manner much like the afferent connections to the cortex. For example, the pattern of long-range lateral connections is closely coupled to the pattern of feature detectors in the visual cortex, and can be altered by strabismus and visual deprivation. Several possible functions have been suggested for the lateral connections. They may (1) modulate receptive field properties in a context-dependent manner and mediate perceptual filling in, (2) mediate adult cortical plasticity such as dynamic receptive fields, (3) store associatory information such as Gestalt rules, (4) act as the substrate for stimulus-dependent synchronization and feature binding, and (5) form the locus of perceptual learning in the primary visual cortex. The workshop will focus on collating the open questions and hypotheses about the functional role of intracortical connectivity, and formulating an agenda for computational and analytical modeling. How do patterned lateral connections form and develop? What do the patterns of lateral connectivity tell us about information stored in the cortex? How could associatory information in the lateral connections be expressed during cortical processing? How could lateral connections mediate learning processes in the cortex? What is their role in cortical plasticity? What types of neural network models are best suited for addressing such questions? Organizers: Email: ---------- ------ Joseph Sirosh and Risto Miikkulainen sirosh at cs.utexas.edu Dept of Computer Sciences risto at cs.utexas.edu University of Texas at Austin Austin, TX--78712. The workshop will be one day in length. Tentative speakers at the workshop include Terrence Sejnowski, Jack Cowan and Gary Blasdel. If you would like to contribute a talk, please get in touch with one of the organizers. --  From Dave_Touretzky at DST.BOLTZ.CS.CMU.EDU Sun Oct 9 21:18:57 1994 From: Dave_Touretzky at DST.BOLTZ.CS.CMU.EDU (Dave_Touretzky@DST.BOLTZ.CS.CMU.EDU) Date: Sun, 09 Oct 94 21:18:57 -0400 Subject: Faculty positions in neural computation Message-ID: <25670.781751937@DST.BOLTZ.CS.CMU.EDU> NEURAL COMPUTATION AT CARNEGIE MELLON The Computer Science Department at Carnegie Mellon University, in collaboration with the Center for the Neural Basis of Cognition (CNBC), is soliciting applications for faculty positions in neural computation. The CNBC is a newly-formed research center jointly operated by Carnegie Mellon and the University of Pittsburgh. Through an agressive recruiting program, the Center seeks to increase the already substantial community of Pittsburgh researchers working on the neural basis of cognitive functions such as perception, memory, language, and the planning and coordination of action. Techniques employed by researchers associated with the Center include neuroimaging, single-unit recording, neuronal modeling, computational analysis of neural systems, and clinical patient studies. For the Computer Science positions, investigators are sought who bring strong computational/theoretical skills to bear on the effort to understand intelligent functions in the brain. Send a vita, a statement of interests, copies of relevant publications, and three letters of reference to: Dr. David S. Touretzky Computer Science Department Carnegie Mellon University Pittsburgh, PA 15213-3891 The deadline for initial consideration of applications is January 1, though applications arriving after that date will be considered until the positions are filled. Carnegie Mellon University is an Equal Opportunity Employer.  From mav at psych.psy.uq.oz.au Mon Oct 10 19:55:19 1994 From: mav at psych.psy.uq.oz.au (Simon Dennis) Date: Tue, 11 Oct 1994 09:55:19 +1000 (EST) Subject: Conference of the Australasian Cognitive Science Society Message-ID: - CALL FOR PAPERS - 3rd Conference of the Australasian Cognitive Science Society at The University of Queensland Brisbane, Australia April 18-20, 1995 (Preceding the 22nd Australian Experimental Psychology Conference) Abstracts Due: December 2, 1994 Please address all e-mail correspondence to: cogsci95 at psy.uq.oz.au (Do not reply directly to this message) The 3rd Conference of the Australasian Cognitive Science Society will be held at the University of Queensland from Tuesday April 18 to Thursday April 20, 1995. CogSci'95 will precede the 22nd Experimental Psychology Conference (April 21-23). One focus of CogSci'95 will be the application of Cognitive Science to fields such as industry, commerce, and government. VENUE The venue for the Conference is Emmanuel College which is located on the campus of the University of Queensland. The campus, only 4 kms from the centre of Brisbane, is spacious and leafy with exotic and colourful subtropical vegetation, and is surrounded on three sides by a sweeping bend of the Brisbane River. Brisbane, with a population of 1.4 million, is Australia's third largest city, and is the capital of the state of Queensland - the "Sunshine State". Although it is Australia's fastest growing city, it retains and cherishes an enviable lifestyle influenced by its sunny, subtropical climate. It is a scenic and cosmopolitan city of palm studded parks, colourful gardens, shady verandahs, riverside walks and cafes, and al fresco dining. The Brisbane River snakes lazily through the city from the forest clad foothills of the Great Dividing Range which frame the city to the west, to the Pacific Ocean which frames it to the east. Within 90 minutes drive of Brisbane are rainforested mountains, pristine Pacific beaches, tranquil sand islands, and buzzing coastal resorts. Brisbane is the gateway to Queensland which, one fifth the size of the USA, encompasses the Simpson Desert in the west, the tropical rainforests of the north, and of course the Great Barrier Reef along its beautiful Pacific coast. SCIENTIFIC PROGRAMME The aim of the Conference is to promote the interests of the multi- disciplinary field of Cognitive Science. The participation of scholars from all areas of Cognitive Science is invited, including: - Computer Science - Linguistics - Neuroscience - Philosophy - Psychology Additionally, the Conference aims to promote applications of Cognitive Science and encourage participation from researchers in the Asia-Pacific region. The Scientific Programme will include oral and poster presentations, together with symposia. KEYNOTE SPEAKER A keynote speaker will be selected from the submitted papers. SUBMISSION OF ABSTRACTS and PAPERS All abstracts/papers will be refereed. It is intended that selected papers will be published. FULL PAPERS: The submission of full papers will be required if they are to be considered for publication, and will be reviewed. Papers should be 4,000 to 6,000 words with an upper limit of 8,000 words. Please forward FIVE hard copies of the paper, ONE hard copy of the abstract, and the abstract by email or on disk (IBM or Mac) in either ascii or postscript format. ABSTRACTS: If publication is not desired, abstracts only are required and will not be reviewed externally. Abstracts should be 500 words/two pages maximum. Please forward a hard copy and an email or floppy disk version (IBM/Mac) in either ascii or postscript format. SYMPOSIA: Proposals for symposia are invited and should be forwarded to Rebecca Farley at the address below. Symposium organisors are asked to submit an abstract for the symposium, an abstract for each paper, and contact details for each participant. Please submit abstracts as hard copy and by e-mail or on floppy disk (IBM or Mac) in ascii or postscript format. Platform papers will be allocated 20-minutes presentation time plus a 10-minute question time. Symposia will be allocated 90-minutes to 2 hours depending on the number of speakers. Poster dimensions: 1 x 1.2 metres. The deadline for submission of all papers and abstracts is FRIDAY DECEMBER 2, 1994. Notification of acceptance for the conference as poster, platform presentation or symposium paper will be forwarded February 15, 1995. The deadline for submission of revised papers for publication is May 15, 1995. EXHIBITS and WORKSHOP The Conference will include displays of recent books. A Workshop on Applications of Cognitive Science will be held on the afternoon of Thursday April 20. The Workshop is planned to be of interest to delegates of both CogSci'95 and the Experimental Psychology Conference. The emphasis will be on applications of Cognitive Science and Experimental Psychology to industry, government, and commerce. The Organising Committee invites suggestions for applied activities at the Workshop including proposals for symposia, displays, demonstrations, papers, posters, or any ideas that might help to increase interest in applications. It is anticipated that representatives of organisations which are actual or potential users of Cognitive Science and Experimental Psychology will attend the Workshop. Please forward proposals for applied activities to Rebecca Farley by Friday, December 2, 1994. AUSTRALASIAN COGNITIVE SCIENCE SOCIETY AWARD The Australasian Cognitive Science Society Award will be made for an outstanding project by a student on an application of Cognitive Science. The award at CogSci'95 is sponsored by the University of Queensland and comprises $750 prize money and complimentary conference registration. Free registration will also be awarded for commended entries. The Programming Committee would like to encourage the submission of ideas for an applied project from all students. Collaboration with other students on an application of Cognitive Science is also encouraged. Detailed proposals are sought, approximately 6-10 pages in length. The level of detail supplied in a grant application should be taken as a guide for the amount of information to be included in a competition entry. The Organising Committee reserves the right to not award prizes if no entry of sufficient merit is received. For additional information on the Applied Project Competition, contact Rebecca Farley on (07) 365 6230 or email: cogsci95 at psy.uq.oz.au The closing date for entries is Friday, December 2, 1994. SOCIAL PROGRAMME The Social Programme covered by the registration fee includes the opening reception on Monday evening, morning and afternoon teas, lunches on Tuesday and Wednesday, and dinner at Emmanuel College on Tuesday. Delegates are also invited to attend the Conference dinner at Oxley's on the Wharf on Wednesday evening (cost: $40, includes transport and some alcohol), and a BBQ lunch (cost: $10) which will precede the Workshop on Applications on Thursday afternoon. The BBQ and Workshop are to be held in conjunction with EPC. REGISTRATION and SOCIETY MEMBERSHIP The registration fee covers the above social events and also includes membership of the Australasian Cognitive Science Society. The Society is being re-established to promote the interests of Cognitive Science in Australia and to provide a membership base for biennial conference meetings of the Society. Payment by 28/2/95 attracts a reduced registration fee. There are also reduced rates for full-time students and delegates attending both CogSci'95 and EPC. Cheques should be made payable to the Australasian Cognitive Science Society. ACCOMMODATION Accommodation has been booked at King's College, University of Queensland, which is adjacent to the conference venue. Rooms will be allocated on a first-registered, first-served basis. Cost per person per night is $46. Please make your bookings on the attached registration form. ALTERNATIVE ACCOMMODATION Special conference rates apply at the following hotels. Individuals are asked to make their own bookings. When booking, please mention that you are attending the Cognitive Science Conference Toowong Villas (Serviced apartments: $69 per night; 3 nights min.) 11 Ascog Terrace, Toowong Tel: (07) 371 4855 / (008) 777 092; Fax: (07) 371 4661 Inn on the Park ($90 per night) 507 Coronation Drive, Auchenflower Tel: (07) 870 9222 (008) 773 774 All Seasons Abbey Hotel ($90 per night) 160 Roma Street, Brisbane Tel: (07) 236 1444 DOMESTIC AIR TRAVEL - How to book We are pleased to have appointed Ansett Australia as our sole domestic official carrier for CogSci'95. Please support this appointment by flying Ansett Australia when air travel is required. For the cost of a local call, Australia wide, please phone 008 810 532 and quote File Number MC 07272. Ansett Australia will offer the best available discount fare (up to 50% or better). Also available is a range of conference airfares from 15% to 50% off the applicable economy class airfare on Ansett Australia services. These fares are fully refundable. Access to these special fares is via a unique computer file reference number on telephone 008 810 532 Australia wide. Discounted fares are strictly subject to availability and conditions do apply. INTERNATIONAL AIR TRAVEL Air New Zealand is offering a reduction of 7% on the cost of an airfare for conference delegates who are travelling from the USA. To phone the Los Angeles office of Air New Zealand from anywhere in the United States dial 1-800/ 262 1234 SPONSORS The University of Queensland Ansett Australia TIMETABLE & CLOSING DATES Submission of papers/abstracts December 2, 1994 Notification of acceptance for Conference/book February 15, 1995 Registration with discount February 28, 1995 Submission of revised paper for publication May 15, 1995 ADDRESS FOR ALL CORRESPONDENCE Rebecca Farley CogSci'95 - Department of Psychology University of Queensland Brisbane QLD Australia 4072 Phone: (+617) 365 6230 Fax: (+617) 365 4466 E-mail: cogsci95 at psy.uq.oz.au World-wide web: http://psy.uq.oz.au/CogPsych/cogsci95/home.html CogSci'95 ORGANISING COMMITTEE ------------------------------ CONFERENCE CHAIR: Graeme Halford, Psychology, UQ SECRETARIAT: Kerry Chalmers (Sec), Psychology, UQ Glenda Andrews (Treas), Psychology, UQ Rebecca Farley (Admin), Psychology, UQ PROGRAMME & AWARDS: Doug Saddy, Psychology & English, UQ Janet Wiles, Psychology & Comp. Sci, UQ Simon Dennis, Psychology, UQ Terry Dartnall, Computing & IT, Griffith Marilyn Ford, Computing & IT, Griffith Ottmar Lipp, Psychology, UQ PUBLICATIONS & EDITING: Ellen Watson, Philosophy, UQ Terry Dartnall, Computing & IT, Griffith Peter Slezak, Philosophy, UNSW Doug Saddy, Psychology & English, UQ NOTICES & MEMBERSHIP: Kate Stevens, Psychology, UQ Rebecca Farley, Psychology, UQ SOCIAL PROGRAMME: Helen Purchase, Computer Science, UQ VENUE & ACCOMMODATION: Len Dalgleish, Psychology, UQ Helen Purchase, Computer Science, UQ SPONSORSHIP: Joachim Diederich, Computer Science, QUT INCORPORATION: Alan Hayes, Education, UQ Helen Purchase, Computer Science, UQ ---------------------------------------------------------------------------- CogSci'95 REGISTRATION FORM I would like to: attend CogSci'95 yes/no present a paper yes/no organise a symposium yes/no My preferred format is: platform / poster Author(s): Title: Name: Address: Tel: ( ) Fax: ( ) E-mail address: Facilities for slide and overhead projection will be available. Please specify any other requirements: $$ All prices are in Australian dollars $$ King's College ACCOMMODATION (bed & breakfast $46/night): Day of arrival: Day of departure: No. nights: ________ @ $46/night = $ ________ Please notify us of any special dietary requirements. CONFERENCE DINNER - Wednesday ($40) yes/no BBQ LUNCH - Thursday ($10) yes/no $ ________ REGISTRATION (select one) Full paid by 28/2/95........................... $140 Full paid after 28/2/95........................ $150 CogSci if also attending EPC................... $135 CogSci (late) if also attending EPC............ $145 Student paid by 28/2/95........................ $ 90 Student paid after 28/2/95..................... $100 Student CogSci if attending EPC................ $ 85 Student CogSci (late) if attending EPC......... $ 95 $ ________ TOTAL: $ ________ Cheques to be made payable to the Australasian Cognitive Science Society. ADDRESS FOR ALL CORRESPONDENCE Rebecca Farley CogSci'95 - Department of Psychology University of Queensland Brisbane QLD Australia 4072 Phone: (+617) 365 6230 Fax: (+617) 365 4466 E-mail: cogsci95 at psy.uq.oz.au World-wide web: http://psy.uq.oz.au/CogPsych/cogsci95/home.html *************************** Simon Dennis Department of Psychology mav at psych.psy.uq.oz.au Post Doctoral The University of Queensland Research Fellow QLD 4072 Australia  From sassk at macaulay-land-use.scot-agric-res-inst.ac.uk Mon Oct 10 15:21:43 1994 From: sassk at macaulay-land-use.scot-agric-res-inst.ac.uk (Jim Kay) Date: Mon, 10 Oct 94 19:21:43 GMT Subject: Stat-NN reminder Message-ID: <13351.9410101921@mluri.sari.ac.uk> Statistics vs. Neural Networks A Competition Reminder Can artificial neural networks outperform statistical methods in a fair comparison ? Finding applications where they can is one of the main objectives of a two-day workshop to be held on April 19-20, 1995 in Edinburgh, Scotland. We invite entries to this competition which should reach Jim Kay at the address given below by November the first. The decisions reached will be communicated to applicants by the 15th of January, 1995. The best four entries will be selected and one applicant per entry will be invited to attend the workshop and make an oral presentation of their results; costs of accommodation and travel (within the UK) will be provided subject to certain upper bounds. The other general objectives of the workshop are: to discuss problems of statistical interest within ANN research; to discuss statistical concepts and tools that expand the technology of ANN research; to enhance collaborative research involving experts from one or more of the two communities. We look forward to receiving your applications which should include a contact name and address and be no more than 10 typed A4 pages. Jim Kay and Mike Titterington SASS Environmental Modelling Unit Macaulay Land Use Research Institute Craigiebuckler Aberdeen AB9 2 QJ Scotland, UK e-mail : j.kay at uk.ac.sari.mluri (within the UK) j.kay at mluri.sari.ac.uk (internet address) Tel. : +224 - 318611 (ext. 2269) Fax : +224 - 208065  From yves at netid.com Tue Oct 11 14:47:51 1994 From: yves at netid.com (Yves Chauvin) Date: Tue, 11 Oct 94 11:47:51 PDT Subject: Paper available: HMMs and Comput. Biol. Message-ID: <9410111847.AA02335@netid.com> The following paper, "Hidden Markov Models of the G-Protein-Coupled Receptor Family", to be published in the Journal of Computational Biology, and the associated GPCR multiple alignment have been placed on ftp site. Retrieval instructions are given below. Yves Chauvin yves at netid.com ___________________________________________________________________________ Hidden Markov Models of the G-Protein-Coupled Receptor Family Pierre Baldi Jet Propulsion Laboratory and Division of Biology, California Institute of Technology Pasadena, CA 91109 Yves Chauvin Net-ID, Inc. Hidden Markov Model techniques are used to derive a new model of the G-Protein-Coupled Receptor family. The transition and emission parameters of the model are adjusted using a training set comprising 142 sequences. The resulting model is shown to perform well on a number of tasks, including multiple alignments, discrimination, large data base searches, classification and fragment detection. General analytical results on the expectation and standard deviation of the likelihood of random sequences are also presented. ___________________________________________________________________________ Retrieval instructions: The paper is "baldi.hmmgpcr.ps.z". The multiple alignment is "mahmmgpcr.ps.z". Both are in gzip compressed postscript format. To retrieve these files: % ftp ftp.netcom.com Connected to netcom.com. 220 netcom FTP server (Version 2.0WU(10) [...] ready. Name (netcom.com:yourname): anonymous 331 Guest login ok, send your complete e-mail address as password. Password: .. ftp> cd pub/netid/papers ftp> ls ftp> binary ftp> get ftp> close .. % gunzip (The postcript file is large and old printers may not be able to print it).  From cristina at idsia.ch Wed Oct 12 07:11:49 1994 From: cristina at idsia.ch (Cristina Versino) Date: Wed, 12 Oct 94 12:11:49 +0100 Subject: Position Announcement Message-ID: <9410121111.AA03255@fava.idsia.ch> The Istituto Dalle Molle di Studi sull'Intelligenza Artificiale (IDSIA) has an immediate opening for a: Director of research in AI learning paradigms. The ideal candidate should: - have a PhD in Artificial Intelligence - have three years experience in managing projects - have a strong interest in learning paradigms IDSIA - Istituto Dalle Molle di Studi sull'Intelligenza Artificiale is a research center located in Lugano, in the Italian part of Switzerland. The Institute receives subsidies from both private and public sectors and has been operational since 1989. IDSIA is committed to further investigating AI learning paradigms in the area of reinforcement learning, genetic algorithms, neural networks (among others). The initial contract would be for one year (starting beginning 1995) with the possibility of an extension, subject to funding, of a further four years. If interested, please send resume, description of your current interests in learning paradigms, the names of three referees, and other related information to: IDSIA Luca M. Gambardella Cso. Elvezia 36 CH - 6900 - Lugano Switzerland email: luca at idsia.ch  From ifsa95 at dep.fem.unicamp.br Wed Oct 12 10:26:45 1994 From: ifsa95 at dep.fem.unicamp.br (IFSA95) Date: Wed, 12 Oct 94 09:26:45 EST Subject: IFSA'95 Second Short Call For Papers Message-ID: <9410121226.AA19478@jaguar> Second Call for Papers (short version) ___________ IFSA '95 Sixth International Fuzzy Systems Association World Congress Sao Paulo-Brazil July 22-28, 1995 * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * The full version of IFSA'95 2nd call-for-papers is * * stored in the file * * * * calif.doc * * * * which can be obtained by anonynmous FTP from: * * * * spock.dep.fem.unicamp.br * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * The latest information about IFSA'95 (including the * * call-for-papers) can be obtained via WWW on URL: * * * * htpp://www.inpe.br/meetings/IFSA95/home * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * For further information please contact: * * * * ifsa95 at dep.fem.unicamp.br * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * DEADLINES _________ Reception of 4 copies of 4-page extended abstracts; 1 pre-registration form for each author; and 1 paper submission form - Nov 1st, 1994 Notification of acceptance - Feb 1st, 1995 Reception of camera ready copy for proceedings - Apr 1st, 1995 SECRETARIAT ___________ Address : INPE/Setor de Eventos/ IFSA'95 Av. dos Astronautas, 1758 - Caixa Postal 515 12201-970 Sao Jose' dos Campos - SP - Brazil Phone: +55-123-418977 Fax: +55-123-218743 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - PRE-REGISTRATION FORM Last Name ____________________________________________________________ First name ___________________________________________________________ Organization/Affiliation _____________________________________________ Address ______________________________________________________________ Zip/Postal Code _____________________ City ___________________________ Country ______________________________________________________________ Telephone ___________________________________________________________ Fax __________________________________________________________________ E-mail address ______________________________________________________ 1a) Do you intend to submit a paper at the conference ? Yes __ No __ 1b) As main author ? Yes __ No __ 2) Do you intend to attend the conference ? Yes __ No __ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -  From koch at klab.caltech.edu Wed Oct 12 11:59:44 1994 From: koch at klab.caltech.edu (Christof Koch) Date: Wed, 12 Oct 1994 08:59:44 -0700 Subject: No subject Message-ID: <199410121559.IAA22224@kant.klab.caltech.edu> ASSISTANT PROFESSOR PSYCHOPHYSICS/COGNITIVE AND COMPUTATIONAL NEUROSCIENCE/ NEUROPHYSIOLOGY We invite applications for a tenure-track Assistant Professor position in the Computation and Neural Systems Program and in the Division of Biology at the California Institute of Technology. Applicant should conduct research toward understanding higher perceptual and cognitive functions in humans and other primates. The candidate should carry out a research program in at least two of the following areas: psychophysics, computational and cognitive neuroscience, and behavioral neurophysiology. The initial appointment term is four years, and appointment is contingent upon completion of PhD. Applicants should submit a curriculum vitae, a description of research and three reprints, and arrange for three letters of recommendation to be sent to Prof. Christof Koch, Division of Biology 139-74, Caltech, Pasadena, CA 91125. The California Institute of Technology is an affirmative action / equal opportunity employer. Women, minorities, veterans, and disabled persons are encouraged to apply.  From sbh at eng.cam.ac.uk Wed Oct 12 15:41:45 1994 From: sbh at eng.cam.ac.uk (S.B. Holden) Date: Wed, 12 Oct 1994 15:41:45 BST Subject: Article available by ftp Message-ID: <199410121441.11573@tw700.eng.cam.ac.uk> The following technical report is available by anonymous ftp from the archive of the Speech, Vision and Robotics Group at the Cambridge University Engineering Department. It is accepted for publication in "Neural Computation". On the Practical Applicability of VC Dimension Bounds Sean B. Holden and Mahesan Niranjan Technical Report CUED/F-INFENG/TR.155 October 12, 1994 Cambridge University Engineering Department Trumpington Street Cambridge CB2 1PZ England Abstract This article addresses the question of whether some recent Vapnik-Chervonenkis (VC) dimension based bounds on sample complexity can be regarded as a practical design tool. Specifically, we are interested in bounds on the sample complexity for the problem of training a pattern classifier such that we can expect it to perform valid generalization. Early results using the VC dimension, while being extremely powerful, suffered from the fact that their sample complexity predictions were rather impractical. More recent results have begun to improve the situation by attempting to take specific account of the precise algorithm used to train the classifier. We perform a series of experiments based on a task involving the classification of sets of vowel formant frequencies. The results of these experiments indicate that the more recent theories provide sample complexity predictions that are significantly more applicable in practice than those provided by earlier theories; however, we also find that the recent theories still have significant shortcomings. ************************ How to obtain a copy ************************ a) Via FTP: unix> ftp svr-ftp.eng.cam.ac.uk Name: anonymous Password: (type your email address) ftp> cd reports ftp> binary ftp> get holden_tr155.ps.Z ftp> quit unix> uncompress holden_tr155.ps.Z unix> lpr holden_tr155.ps (or however you print PostScript) The report is 22 pages in length. b) Via postal mail: Request a hardcopy from Dr. Sean B. Holden, Cambridge University Engineering Department, Trumpington Street, Cambridge CB2 1PZ, England. or email me: sbh at eng.cam.ac.uk  From whitney at psych.rochester.edu Wed Oct 12 10:28:43 1994 From: whitney at psych.rochester.edu (Whitney Tabor) Date: Wed, 12 Oct 1994 10:28:43 -0400 Subject: Thesis available: Syntactic Innovation--a Connectionist Model Message-ID: <199410121428.KAA22739@muki.psych.rochester.edu> The following dissertation is available by ftp. There are two alternative formats: tabor.thesis.2up.ps.Z (120 sheets of paper), tabor.thesis.ps.Z (230 sheets of paper). Ftp host: csli.stanford.edu Ftp filename: pub/Preprints/tabor.thesis.2up.ps.Z Ftp filename: pub/Preprints/tabor.thesis.ps.Z Syntactic Innovation: a Connectionist Model Whitney Tabor* Department of Linguistics Stanford University 1994 This thesis uses the continuous representation space of a connectionist network to model syntactic innovation in natural language. Current theories of grammar, following Chomsky 1957, generally take quantitative properties of language use (e.g., context-dependent word-frequency information) to be irrelevant to the determination of grammatical structure. Such theories are not very useful for making constrained predictions about historical grammar change for the changes they can model are unrealistically abrupt and there seems to be no domain-independent structuring of the representation space that reveals which changes are probable and which are not. But recent work in the field of grammaticalization (e.g., Traugott and Heine 1991, Hopper and Traugott 1993) indicates strong, general constraints on grammar change. Moreover, these constraints often have quantitative correlates: changes in the categorical status of a word or morpheme are often preceded by significant shifts in its relative frequency distribution. I show how a recurrent connectionist network trained on word prediction in the manner suggested by Elman 1990 and 1991 is sensitive to the information provided by these quantitative shifts and thus can be used to predict correlations between the frequency changes and categorical changes. The correctness of these predictions is borne out by case studies of degree modifier and future . Two additional empirical phenomena support the model: linked frequency changes in grammatically related constructions and emergence of hybrid structures during periods of transition. The model permits simplification of the theory of language change by replacing "reanalysis" and "analogical extension" with a single type of change-event. It also permits simplification of the theory of grammar by allowing the same interpolative mechanism to handle both normal productive syntax and the hitherto problematic hybrid cases. *Current address: Whitney Tabor Department of Psychology University of Rochester Meliora Hall---River Campus Rochester, NY 14627  From maass at igi.tu-graz.ac.at Wed Oct 12 17:26:06 1994 From: maass at igi.tu-graz.ac.at (Wolfgang Maass) Date: Wed, 12 Oct 94 22:26:06 +0100 Subject: COLT 95: CALL FOR PAPERS (plaintext version) Message-ID: <9410122126.AA01624@figids01.tu-graz.ac.at> ______________________________________________________________________ CALL FOR PAPERS---COLT 95 Eighth Conference on Computational Learning Theory Santa Cruz, California, USA; July 5-8, 1995 ______________________________________________________________________ The Eighth Conference on Computational Learning Theory (COLT 95) will be held on the campus of the University of California at Santa Cruz, USA, from the late afternoon of Wednesday, July 5, through Saturday, July 8, 1995. COLT 95 is sponsored by the University of California, in cooperation with the ACM Special Interest Groups for Algorithms and Computation Theory (SIGACT) and Artificial Intelligence (SIGART). We invite papers in all areas that relate directly to the analysis of learning algorithms and the theory of machine learning, including ARTIFICIAL AND BIOLOGICAL NEURAL NETWORKS. We also invite papers on learning from related theoretical and applied areas, such as statistics, statistical physics, Bayesian/MDL estimation, information theory, inductive inference, logic, inductive logic programming, knowledge representation, knowledge discovery in databases, natural language processing, robotics, and pattern recognition. Besides purely theoretical papers we encourage the submission of papers on experimental results that also provide a theoretical analysis. INVITED TALKS. Invited talks will be given by Terry Sejnowski (Salk Institute and University of California at San Diego) and Les Valiant (Harvard University). ABSTRACT SUBMISSION. Authors should submit fourteen copies (preferably two-sided copies) of an extended abstract to Wolfgang Maass - COLT 95 Institute for Theoretical Computer Science Technische Universitaet Graz, Klosterwiesgasse 32/2 A-8010 Graz, Austria An abstract must be RECEIVED BY JANUARY 10, 1995 (or postmarked by January 2 and sent airmail). This deadline is FIRM! Papers that have appeared in journals or other conferences, or that are being submitted to other conferences, are not appropriate for submission to COLT. There is a single exception: Since in 1995 the notification date for STOC is shortly after the submission deadline for COLT, these conferences have agreed that a paper can be submitted both to STOC 95 and COLT 95, with the understanding that such paper is automatically withdrawn from COLT if accepted at STOC. ABSTACT FORMAT. The extended abstract should consist of a cover page with title, authors' names, postal and e-mail addresses, and a 200-word summary. The body of the abstract should be no longer than 10 pages with roughly 35 lines/page in 12-point font. Papers deviating significantly from this length constraint will not be considered. The body should include a clear definition of the theoretical model used, an overview of the results, and some discussion of their significance, including comparison to other work. Proofs or proof sketches should be included. PROGRAM FORMAT. The program will consist of both "long" talks, and "short" talks, corresponding to longer and shorter papers in the proceedings. The short talks will also be coupled with a poster presentation in special poster sessions. By default, all papers will be considered for both categories. Authors who DO NOT want their papers considered for the short category should indicate that fact in the cover letter. The cover letter should also specify the contact author and give his/her e-mail. NOTIFICATION. Authors will be notified of acceptance or rejection by a letter mailed on or before Friday, March 10, with possible earlier notification via e-mail. Final camera-ready papers will be due by Tuesday, April 11. PROGRAM CHAIR. Wolfgang Maass (TU Graz, Austria, e-mail: maass at igi.tu-graz.ac.at). CONFERENCE AND LOCAL ARRANGEMENTS CHAIRS. David Haussler and Manfred Warmuth (U. of California at Santa Cruz) PROGRAM COMMITTEE. Dana Angluin (Yale), Peter Bartlett (ANU, Australia), Tom Dietterich (Oregon State Univ.), Haym Hirsh (Rutgers), Jeff Jackson (CMU), Martin Kummer (Univ. Karlsruhe), Phil Long (Duke Univ.), Ron Rivest (MIT), Robert Schapire (AT&T), Ted Slaman (Univ. of Chicago), Naftali Tishby (Hebrew Univ.), Gyorgy Turan (UIC, Chicago). COLT AND ML. The Twelfth Intern. Conf. on Machine Learning (ML 95) will be held right after COLT 95 on July 9 - 12 at Tahoe City, California. Car pools from Santa Cruz to Tahoe City on July 8 will be arranged.  From MDUDZIAK at Gems.VCU.EDU Mon Oct 10 16:40:28 1994 From: MDUDZIAK at Gems.VCU.EDU (MARTIN DUDZIAK) Date: Mon, 10 Oct 1994 16:40:28 -0400 (EDT) Subject: A couple of these WWW servers of interest to the group Message-ID: NEW WWW SERVERS at Virginia Commonwealth Univ (VCU) & Medical College of Virginia Buzzwords: Biotech Biomaterials Biomedicine Dynamical (complex, non-linear) systems Neural nets / neurocomputing Molecular engineering Biocomputing Nanotechnology Quantum physics Biophysics Russia Ukraine FSU The following information is provided to a number of places that maintain WWW servers. Several topics are covered, not all of which will be of interest to everyone, but this seemed a simpler and more efficient way of disseminating the information: Homepage on Life Sciences R&D at VCU and MCV http://opal.vcu.edu/html/biomede/bio-science.html Hompage on Virginia Biotechnology Research Park http://opal.vcu.edu/html/biomede/vbrp.html Homepage on Molec Engineering and Nanotechnology and Scanning Probe Microscopy http://opal.vcu.edu/html/biomede/molsys.html Homepage on Complex Dynamical Systems Research including neurocomputing but with a strongly bio/physics approach (less of the standard ANNs, more of neurons) http://opal.vcu.edu/html/biomede/compdyn.html Homepage on the School of Medicine at MCV http://opal.vcu.edu/html/biomede/schofmed.html Homepage on Biotech activities in the Former Soviet Union http://opal.vcu.edu/html/biomede/fsu-biotech.html Homepage on the Biomedical Engineering Program (MS, PhD) at VCU http://opal.vcu.edu/html/biomede/departments/deptofbme.html The main instigator of most of this has been Dr. Martin Dudziak in the Biomed Engr. Dept., so if you want more info and want to make comments, send msgs to me at mdudziak at gems.vcu.edu  From kenm at sunrae.sscl.uwo.ca Thu Oct 13 01:25:27 1994 From: kenm at sunrae.sscl.uwo.ca (kenm@sunrae.sscl.uwo.ca) Date: Thu, 13 Oct 1994 10:25:27 +0500 Subject: Position in Psychology Message-ID: <9410131425.AA01044@sunrae.sscl.uwo.ca> *********************************************************************** FACULTY POSITION IN COGNITIVE PSYCHOLOGY *********************************************************************** The University of Western Ontario, Department of Psychology, invites applications for a probationary (tenure-track) position at the Assistant or beginning Associate Professor level. Individuals with research interests in any area of Cognitive Psychology are invited to apply as our intention is to hire the strongest candidate regardless of specialty area. The successful candidate will have strong doctoral-level academic training, plus demonstrated ability in research and teaching. Applicants should submit a copy of their vita, copies of representative publications, and arrange to have three letters of recommendation sent to: Dr. Clive Seligman, Chair Department of Psychology The University of Western Ontario London, Ontario, Canada N6A 5C2. This position is subject to budgetary approval. The scheduled starting date is July 1, 1995. In accordance with Canadian Immigration requirements, this advertisement is directed to Canadian Citizens and Permanent Residents of Canada. The University of Western Ontario is committed to employment equity, welcomes diversity in the workplace, and encourages applications from all qualified individuals including women, members of visible minorities, aboriginal persons,and persons with disabilities.  From harnad at ecs.soton.ac.uk Thu Oct 13 19:50:21 1994 From: harnad at ecs.soton.ac.uk (Stevan Harnad) Date: Thu, 13 Oct 94 19:50:21 BST Subject: Computer Models of Affective States Message-ID: <3910.9410131850@louis.ecs.soton.ac.uk> From KAISER at ch.unige.uni2a Wed Oct 12 12:21:50 1994 From: KAISER at ch.unige.uni2a (KAISER@ch.unige.uni2a) Date: Wed, 12 Oct 1994 16:21:50 +0000 (WET-DST) Subject: Program of GEW'95 Message-ID: Call for Applications GENEVA EMOTION WEEK '95 April 8 to April 13, 1995 University of Geneva, Switzerland The Emotion Research Group at the University of Geneva announces the third GENEVA EMOTION WEEK (GEW '95), consisting of a colloquium focusing on a major topic in the psychology of emotion, and of a series of workshops designed to introduce participants to advanced research methods in the field of emotion. The colloquium consists of extensive presentations of theoretical and methodological approaches as well as recent empirical work by a group of invited speakers and faculty members of the University of Geneva. Ample time is allotted for discussion. The colloquium lasts 3 days. The theme chosen for the GEW '95 is: Artificial Emotions The intention of GEW'95 is to bring together researchers in diverse disciplines, including AI, neurosciences, philosophy, and psychology, who share an interest in architectures and mechanisms underlying emotion, motivation, and intelligence. The focus is on architectural requirements for an autonomous agent, combining the various sub- functions and sub-mechanisms normally studied separately in AI and Psychology. GEW'95 is organized in collaboration with the Cognition and Affect Group under the direction of Prof. Aaron Sloman at the Cognitive Science Research Center, University of Birmingham. This group organized the first Workshop on Architectures for Understanding Motivation and Emotions (WAUME93) at Birmingham and is pleased that WAUME95 is to be merged with GEW'95. Speakers and Topics of the colloquium: -------------------------------------- Prof. Joseph Le Doux, New York University: - Neural Computation of Emotional Meaning by the Brain. Prof. Stevan Harnad, University of Southampton: - Measuring and Modelling Performance Capacities and Qualitative States. Prof. Aaron Sloman, University of Birmingham: - Architectures for Emotional Agents. Prof. Klaus Scherer, University of Geneva: - Computer Modeling of Appraisal Processes. Discussant: Prof. Nico Frijda, Univ. Amsterdam The workshops will be dedicated to practical work, e.g. simulation models, tools, problems, etc. The workshops listed below will be held by the organizers and the invited speakers. In addition, 2 or 3 workshop proposals from participants for workshops lasting between 1.5 and 3 hours will be selected on a competitive basis. At the end of each workshop day there will be a session (3 x 2h) for posters, demonstrations, videos, and individual discussions. The topics of the invited workshops, each lasting approx. 3 hours are: ---------------------------------------------------------------------- Dr. Jorge Armony, Center for Neuroscience, New York: - An Anatomically Constrained Connectionist Model of Fear Conditioning. Prof. Stevan Harnad, Southampton: - Turing Testing and the Causal Status of Affect. Prof. Aaron Sloman, Cognition and Affect Group, Birmingham: - Exploring Motivated Agent Design. Dr. Prem Kalra, Prof. Nadia Magnenat Thalmann, Miralab, Geneva: - Simulating Facial Expressions and Phonemes for Virtual Humans. Dr. Thomas Wehrle, Prof. Klaus Scherer, Emotion Research Group, Geneva: - Computational Models: Open Issues. - A Psychological Modeling Environment for Autonomous Agents. Prospective participants are researchers or doctoral students working in AI, neurosciences, philosophy, or psychology. Admission for the limited number of places is decided on the basis of prior application. People interested in participating are asked to fill in the enclosed application form as soon as possible and before January 31, 1995 ========================================================================= APPLICATION FORM (please append a short Curriculum Vitae) GENEVA EMOTION WEEK (GEW'95): April 8 to 13, 1995 Name:.................................................................... First Name:..............................................................  From eann95 at ra.abo.FI Fri Oct 14 02:44:22 1994 From: eann95 at ra.abo.FI (EANN-95 Konferensomrede VT) Date: Fri, 14 Oct 1994 08:44:22 +0200 (EET) Subject: Call for Papers Message-ID: <199410140644.IAA11985@aton.abo.fi> International Conference on Engineering Applications of Neural Networks (EANN '95) Helsinki, Finland August 21-23, 1995 First Call for Papers (ASCII version) The conference is a forum for presenting the latest results on neural network applications in technical fields. The applications may be in any engineering or technical field, including but not limited to systems engineering, mechanical engineering, robotics, process engineering, metallurgy, pulp and paper technology, aeronautical engineering, computer science, machine vision, chemistry, chemical engineering, physics, electrical engineering, electronics, civil engineering, geophysical sciences, biotechnology, and environmental engineering. Abstracts of one page (200 to 400 words) should be sent to eann95 at aton.abo.fi by 31 January 1995, preferably by e-mail in PostScript format, or in TeX or LaTeX. ASCII is also acceptable. Please mention two to four keywords, and whether you prefer it to be a short paper or a full paper. The short papers will be 4 pages in length, and full papers may be upto 8 pages. Tutorial proposals are also welcome until 31 January 1995. Notification of acceptance will be sent around 1 March. The number of full papers will be very limited. Local program committee (to be confirmed, extended) A. Bulsari (Finland) J. Heikkonen (Finland) E. Hyv\"onen (Finland) P. Linko (Finland) L. Nystr\"om (Finland) S. Palosaari (Finland) H. Sax\'en (Finland) J. Sepp\"anen (Finland) International program committee (to be confirmed, extended) G. Dorffner (Austria) A. da Silva (Brazil) V. Sgurev (Bulgaria) S. Dutta (France) C. M. Lee (Hong Kong) H. Siegelmann (Israel) R. Baratti (Italy) R. Serra (Italy) G. Baier (Germany) J. Fodor (Hungary) I. Kawakami (Japan) C. Kuroda (Japan) J. K. Lee (Korea) J. Kok (Netherlands) J. Paredis (Netherlands) S. Tan (Singapore) A. Dobnikar (Slovenia) B. Martinez (Spain) H. Liljenstr\"om (Sweden) G. Sj\"odin (Sweden) J. Sj\"oberg (Sweden) D. Tsaptsinos (UK) N. Steele (UK) S. Shekhar (USA)  From mike at PARK.BU.EDU Thu Oct 13 21:02:40 1994 From: mike at PARK.BU.EDU (mike@PARK.BU.EDU) Date: Thu, 13 Oct 1994 21:02:40 -0400 Subject: CNS graduate program Message-ID: <199410140102.VAA22895@space.bu.edu> *********************************************** * * * DEPARTMENT OF * * COGNITIVE AND NEURAL SYSTEMS (CNS) * * AT BOSTON UNIVERSITY * * * *********************************************** Stephen Grossberg, Chairman Gail A. Carpenter, Director of Graduate Studies The Boston University Department of Cognitive and Neural Systems offers comprehensive graduate training in the neural and computational principles, mechanisms, and architectures that underlie human and animal behavior, and the application of neural network architectures to the solution of technological problems. Applications for Fall, 1995 admission and financial aid are now being accepted for both the MA and PhD degree programs. To obtain a brochure describing the CNS Program and a set of application materials, write, telephone, or fax: Department of Cognitive & Neural Systems Boston University 111 Cummington Street, Room 240 Boston, MA 02215 617/353-9481 (phone) 617/353-7755 (fax) or send via email your full name and mailing address to: rll at cns.bu.edu Applications for admission and financial aid should be received by the Graduate School Admissions Office no later than January 15. Late applications will be considered until May 1; after that date applications will be considered only as special cases. Applicants are required to submit undergraduate (and, if applicable, graduate) transcripts, three letters of recommendation, and Graduate Record Examination (GRE) scores. The Advanced Test should be in the candidate's area of departmental specialization. GRE scores may be waived for MA candidates and, in exceptional cases, for PhD candidates, but absence of these scores may decrease an applicant's chances for admission and financial aid. Non-degree students may also enroll in CNS courses on a part-time basis. Description of the CNS Department: The Department of Cognitive and Neural Systems (CNS) provides advanced training and research experience for graduate students interested in the neural and computational principles, mechanisms, and architectures that underlie human and animal behavior, and the application of neural network architectures to the solution of technological problems. Students are trained in a broad range of areas concerning cognitive and neural systems, including vision and image processing; speech and language understanding; adaptive pattern recognition; cognitive information processing; self-organization; associative learning and long-term memory; computational neuroscience; nerve cell biophysics; cooperative and competitive network dynamics and short-term memory; reinforcement, motivation, and attention; adaptive sensory-motor control and robotics; active vision; and biological rhythms; as well as the mathematical and computational methods needed to support advanced modeling research and applications. The CNS Department awards MA, PhD, and BA/MA degrees. The CNS Department embodies a number of unique offerings. It has developed a curriculum that features twelve interdisciplinary graduate courses each of which integrates the psychological, neurobiological, mathematical, and computational information needed to theoretically investigate fundamental issues concerning mind and brain processes and the applications of neural networks to technology. Each course is typically taught once a week in the evening to make the program available to qualified students, including working professionals, throughout the Boston area. Nine additional research course are also offered. In these courses, one or two students meet regularly with one or two professors to pursue advanced reading and collaborative research. Students develop a coherent area of expertise by designing a program that includes courses in areas such as Biology, Computer Science, Engineering, Mathematics, and Psychology, in addition to courses in the CNS Department. The CNS Department prepares students for PhD thesis research with scientists in one of several Boston University research centers or groups, and with Boston-area scientists collaborating with these centers. The unit most closely linked to the department is the Center for Adaptive Systems (CAS). Students interested in neural network hardware work with researchers in CNS, the College of Engineering, and at MIT Lincoln Laboratory. Other research resources include distinguished research groups in neurophysiology, neuroanatomy, and neuropharmacology at the Medical School and the Charles River campus; in sensory robotics, biomedical engineering, computer and systems engineering, and neuromuscular research within the Engineering School; in dynamical systems within the Mathematics Department; in theoretical computer science within the Computer Science Department; and in biophysics and computational physics within the Physics Department. In addition to its basic research and training program, the Department offers a colloquium series, seminars, conferences, and special interest groups which bring many additional scientists from both experimental and theoretical disciplines into contact with the students. 1994-95 CAS MEMBERS and CNS FACULTY: Jelle Atema Helen Barbas Jacob Beck Daniel H. Bullock Gail A. Carpenter Laird Cermak Michael A. Cohen H. Steven Colburn William D. Eldred III Paolo Gaudiano Jean Berko Gleason Stephen Grossberg Frank H. Guenther Thomas G. Kincaid Nancy Kopell Ennio Mingolla Alan Peters Andrzej Przybyszewski Adam Reeves William D. Ross Robert Savoy Eric L. Schwartz Robert Sekuler Allen Waxman Jeremy Wolfe  From esann at dice.ucl.ac.be Fri Oct 14 12:35:01 1994 From: esann at dice.ucl.ac.be (esann@dice.ucl.ac.be) Date: Fri, 14 Oct 1994 18:35:01 +0200 Subject: Neural Processing Letters Vol.1 No.1 Message-ID: <9410141731.AA04018@ns1.dice.ucl.ac.be> The following articles may be found in the first issue of the "Neural Processing Letters" journal (September 1994): - Fast learning with incremental RBF networks B. Fritzke - Fractal variations of attractors in complex-valued neural networks A. Hirose - Basic mechanisms of coding stimulus intensity in olfactory sensory neuron P. Lansky, J.-P. Rospars, A. Vermeulen - A way to improve an architecture of neural network classifier for remote sensing applications J. Korczak, F. Hammadi-Mesmoudi - Intelligent judge network for speech recognition D.-S. Kim - An on-line learning algorithm for the orthogonal weight estimation of MLP N. Pican, J.-C. Fort, F. Alexandre - Texture segmentation using pyramidal Gabor functions and self-organising feature maps A. Guerin-Dugue, P.M. Palagui - Book review: Neural network time series forecasting of financial markets (E.M. Azoff) E. De Bodt We remind you that all information concerning this journal may be found on the following servers: - FTP server: ftp.dice.ucl.ac.be directory: /pub/neural-nets/NPL - WWW server: http://www.dice.ucl.ac.be/neural-nets/NPL/NPL.html For any information (subscriptions, instructions for authors,...), you can also directly contact the publisher: D facto publications 45 rue Masui B-1210 Brussels Belgium Phone: + 32 2 245 43 63 Fax: + 32 2 245 46 94 _____________________________ D facto publications - conference services 45 rue Masui 1210 Brussels Belgium tel: +32 2 245 43 63 fax: +32 2 245 46 94 _____________________________  From jose at scr.siemens.com Fri Oct 14 14:19:45 1994 From: jose at scr.siemens.com (Stephen Hanson) Date: Fri, 14 Oct 1994 14:19:45 -0400 (EDT) Subject: McDonnell-PEW Program in Cognitive Neuroscience Message-ID: McDonnell-Pew Program in Cognitive Neuroscience McDonnell-Pew Program in Cognitive Neuroscience announces new guidelines for Investigator - Initiated Grants. Awards are $35,000/year for up to three years for interdisciplinary research and training. Deadline for receipt of proposals is February, 1995. For proposal guidelines and additional information contact; Susan Fitzpatrick, Program Officer, James S. McDonnell Foundation email: C06819CN at WUVMD.WUSTL.edu phone: 314-721-1532 or fax: 314-721-7421. PLEASE REPOST sjh. Stephen J. Hanson, Ph.D. Head, Learning Systems Department SIEMENS Research 755 College Rd. East Princeton, NJ 08540  From harnad at ecs.soton.ac.uk Sat Oct 15 13:43:44 1994 From: harnad at ecs.soton.ac.uk (Stevan Harnad) Date: Sat, 15 Oct 94 13:43:44 BST Subject: Colloque de Lyon Message-ID: <25898.9410151243@louis.ecs.soton.ac.uk> From payette at ca.uqam.atoci.uranus Wed Oct 12 18:32:43 1994 From: payette at ca.uqam.atoci.uranus (payette@ca.uqam.atoci.uranus) Date: Wed, 12 Oct 94 18:32:43 EDT Subject: Colloque de Lyon Message-ID: The Seventh Colloquium of the Jacques Cartier Center Lyon, France. THE COGNITIVE SCIENCES: FROM COMPUTATIONAL MODELS TO THE PHILOSOPHY OF MIND Wednesday, November 30th to Friday, December 2nd 1994 under the aegis of: the Pole Rhones-Alpes of the Cognitive Sciences, Programme Interdisciplinaire de Recherche Cognisciences,CNRS Universite du Quebec a Montreal Universite de Montreal Universite Joseph Fourier Universite Claude Bernard Scientific committee: Denis Fisette (Universite du Quebec a Montreal, Quebec) Marc Jeannerod (Universite Claude Bernard, Lyon) Daniel Laurier (Universite de Montreal, Quebec) Daniel Payette (Universite du Quebec a Montreal, Quebec) Vincent Rialle (Universite Joseph Fourier, Grenoble) Guy Tiberghien (Universite Pierre Mendes-France, Grenoble) Coordination in North America: Daniel Payette and Denis Fisette Universite du Quebec a Montreal, Dpt de Philosophie, Dpt Psychology; C.P. 8888,Succ A, Montreal (Quebec) H3C-3P8, Canada; E.mail : payette at uranus.atoci.uqam.ca; tel (+514) 987 8418; Fax: (+514) 9876721 Coordination in Europe: Vincent Rialle Universite J. Fourier, Labo.TIMC-IMAG, Faculte de Medecine, 38706 LaTronche Cedex E.mail: Vincent.Rialle at imag.fr; Tel. (+33) 76 63 71 87; Fax. (+33) 76 51 8667 DATES: Wednesday, November 30th to Friday, December 2nd 1994 CONFERENCE SITE: Amphitheatre CHARLES BERAUDIER. Conseil Regional RHONE-ALPES,78 route de Paris, 69751 CHARBONNIERES-les-BAINS. France *Talks will only be given by invited speakers. (Simultaneous French-English and English-French will be provided). THEME OF COLLOQUIUM The modeling of mental processes in the various human cognitive activities has generated increasing interest in the scientific world today. Cognitive models, cognitive simulations, auto-organization, adaptation, emergence, genetic selection, Darwinian mentalism and enaction are active research topics in neurological and psychological theory. The cognitive sciences offer a continuum of research extending from the engineering sciences to the philosophy of mind, including the neurosciences, cognitive psychology, linguistics, semantics, semiotics and artificial intelligence. Three subconferences will organize themselves around the following major complementary themes: (i) Modeling (cognitive and brain functions), (ii) Philosophy of Mind and Epistemology, and (iii) Applications (AI, technical and computational engineering). (i) Modeling is a point of intersection for all these specialties because it includes the modeling of functions and dysfunctions of the central nervous system, the neurocomputer sciences, the modeling of psychocognitive and mental processes, the emergence of intentional structure on the basis of biological structure, enaction, genetic algorithms, neural networks, artificial "life," etc. (ii) The philosophical and epistemological subcomponent poses questions like the following: Can we elaborate mathematical models of the mind and use them to describe and explain human behavior? Are we aiming toward a mathematical model of the mind? Can we capture the formal principles of the development and emergence of cognition? Can we technologically recreate thought? Is the computational symbolic paradigm, which has imposed itself for the last decades, still a powerful conceptual tool or is it proving too reductionistic and if so, how? What is the epistemological status of, for example, the alternative proposed by the parallel distributed model to the computational models of classical cognitivism? Wich relations can be established between the modeling activity of the cognitive and neurosciences and human experience? (iii) The applications subconference will consider practical domains in which scientific results have been applied in the treatment of language, the automated cognitive analyses of textual documents (an intersection of linguistics, semantics, semiotics and artificial intelligence), aids to decision making, applications in sensory information processing, etc. OFFICIAL PROGRAM WEDNESDAY, 30 November 1994 8h15 - 8h30 Allocution d'accueil du Conseil Regional 8h30 - 9h Guy Tiberghien (Universite Pierre Mendes-France, Grenoble) Introduction SESSION 1 :NEURO AND PSYCHOLOGICAL MODELING 9h - 9h-30 Jean Francois Le Ny (Universite Paris-Sud, psychologie cognitive) Pourquoi les modeles cognitifs devraient-ils etre calculatoires ? 9h30 - 9h45 Discussion 9h-45 - 10h15 Marc Jeannerod (Universite Claude Bernard, Lyon, neurosciences) The Representational Brain 10h15 - 10h30 Discussion 10h30 - 10h45 PAUSE 10h45 - 11h15 Zenon Pylyshyn (Rutgers University, USA, psychologie cognitive) What's in the Mind? A Computational Approach to a Ancient Question. 11h15 - 11h30 Discussion 11h30 - 12h00 Stevan Harnad (Princeton University, psychologie cognitive) Modeles, mobiles et mentalite 12h00 - 12h15 Discussion MEAL 14h00 - 14h30 Michel Imbert (Universite Paul Sabatier, Toulouse, neurosciences) De l'etude du cerveau a la comprehension de l'esprit 14h30 - 14h45 Discussion 14h45 - 15h15 Guy Tiberghien (Univers Pierre Mendes-France,Grenoble,psychologie cognitive) Connexionnisme: stade supreme du behaviorisme ? 15h15 - 15h30 Discussion 15h30 - 15h45 PAUSE 15h45 - 16h15 Jacques Demongeot (Universite Joseph Fourier, Grenoble, neurosciences) Memoire d'evocation dans les reseaux de neurones 16h15 - 16h30 Discussion 16h30 - 17h00 Bennet Murdock (Universite de Toronto, psychologie cognitive) THE ROLE OF FORMAL MODELS IN MEMORY RESEARCH 17h00 - 17h15 Discussion 17h15 - 17h45 Robert Proulx (Universite du Quebec a Montreal, neuro-psychologie) Plausibilite biologique de certains systemes de categorisation adaptative a base de reseaux de neurones 17h45 - 18h00 Discussion TUESDAY, December 1 Session 2 : EPISTEMOLOGY, PHILOSOPHY OF MIND and COGNITION 9h - 9h30 Elisabeth Pacherie (Universite de Provence, CNRS & CREA, Paris) Cognitive Domains and Modularity 9h30 - 9h45 Discussion 9h-45 - 10h15 Pierre Livet (Universite de Provence & CREA, Paris, philosophie) Categorisation et connexionnisme 10h15 - 10h30 Discussion 10h30 - 10h45 PAUSE Normand Lacharite (Universite du Quebec a Montreal, epistemologie) 10h45 - 11h15 Conflits de modeles en theorie de la representation 11h15 - 11h30 Discussion 11h30 - 12h00 Peter Gardenfors (Lund University, Suede, philosophie) Language and the Evolution of Mind 12h15 - 12h15 Discussion MEAL 14h00 - 14h30 Andy Clark (Washington University, philosophie) Wild Cognition: Putting Representation in its Place 14h30 - 14h45 Discussion 14h45 - 15h15 Kevin Mulligan (Universite de Geneve, Suisse, philosophie) Constance perceptuelle et contenu spatial 15h15 - 15h30 Discussion 15h30 - 15h45 PAUSE 15h45 - 16h15 Ronald De Sousa (Universite de Toronto, epistemologie) La rationalite: un concept normatif ou descriptif ? 16h15 - 16h30 Discussion 16h30 - 17h00 Daniel Laurier (Universite de Montreal, philosophie) Rationalite et naturalisme 17h00 - 17h15 Discussion 17h15 - 17h45 Joelle Proust (CNRS & CREA, Paris, philosophie) Un modele naturaliste de l'intentionnalite 17h45 - 18h00 Discussion FRIDAY, December 2 Session 3: IA MODELING, LANGUAGE and COGNITIVE SEMANTIC Paul Jorion (Maison des Sciences de l'Homme, Paris, psychologie cognitive) 9h - 9h30 Modelisation du reseau mnesique : une utilisation minimaliste de l'IA 9h30 - 9h45 Discussion 9h-45 - 10h15 Bernard Amy (Universite Joseph Fourier, Grenoble, connexionnisme) Neural Networks in AI 10h15 - 10h30 Discussion 10h30 - 10h45 PAUSE 10h45 - 11h15 Paul Bourgine (CEMAGREF, Paris-Antony, IA-modelisation) Co-evolution et emergence du soi 11h15 - 11h30 Discussion 11h30 - 12h00 Paul Pietroski (Universite McGill, Canada, philosophie) What can linguistics teach us about belief 12h00 - 12h15 Discussion MEAL 14h00 - 14h30 Le paradigme hermeneutique et la mediation semiotique Francois Rastier (Institut National de la Langue Francaise, CNRS, linguistique computationnelle) 14h30 - 14h45 Discussion 14h45 - 15h15 L'impact des perspectives cognitives dans le traitement de l'information Jean-Guy Meunier (Universite du Quebec a Montreal, semiotique) 15h15 - 15h30 Discussion 15h30 - 15h45 PAUSE 15h45 - 16h15 Guy Denhiere (Universite Paris VIII, psychologie cognitive) Isabelle Tapiero (Universite Lyon II, psychologie cognitive) La signification comme structure emergente : de l'acces au lexique a la comprehension de textes 16h15 - 16h30 Discussion 16h30 - 17h00 Paul Freedman (Centre de Recherche en Informatique de Montreal, IA) La vision artificielle: le traitement intelligent de documents 17h00 - 17h15 Discussion 17h15 - 17h45 Denis Vernant (Universite Pierre Mendes-France, Grenoble, philosophie) L'intelligence de la machine et sa capacite dialogique 17h45 - 18h00 Discussion 18h00: END OF COLLOQUIUM ------------------------------------------------------------------------ -ADMISSION FEES- (Includes:access to the conference room, meals and the colloquium documents) Individuals-------------------------------------------------1500FF Student (join proof of eligibility with registration)------- 500FF ------------------------------------------------------------------------- REGISTRATION BULLETIN (The Cognitive Sciences:From computational models to philosophy of mind) Name:___________________________________________________________________ Status:_____________________________________ Institution/Company_________________________ Complete Address_________________________________________________________ Fax:________________________ Phone :______________________ @mail number__________________________________ Enclosed : Check or money order of (_____________________FF) (Make check or money order payable to CENTRE JACQUES CARTIER) -Send information on possibilities of housing in Lyon(______) _Send me the colloquium brochure (_____) -November 30 meal __ -December 1, meal __ -December 2, meal __ RETURN TO: CENTRE JACQUES CARTIER, 86 rue Pasteur, 69365 Lyon Cedex 07, France. Phone:(33) 78 69 72 21 @mail: ferreira at diogene.univ-lyon2.fr  From N.Sharkey at dcs.shef.ac.uk Sat Oct 15 12:13:32 1994 From: N.Sharkey at dcs.shef.ac.uk (N.Sharkey@dcs.shef.ac.uk) Date: Sat, 15 Oct 94 17:13:32 +0100 Subject: job opportunity Message-ID: <9410151613.AA01585@entropy.dcs.shef.ac.uk> Preliminary announcement please feel free to pass to other boards or colleagues. ******************************************** POST-DOCTORAL RESEARCHER POSITION NEURAL NETWORKS FOR COORDINATED ROBOTIC CONTROL Dept Computer Science University of Sheffield, UK ******************************************** A post-doctoral researcher is required for 18 months (in the first instance) to run a project with another researcher on the Coordination of Robotic Control funded by the Engineering and Physical Science Research Council, UK (EPSRC). The researcher would join a small productive team of researchers on two other projects in the Neurocomputing Group at Sheffield: Adaptive Generalisation and Dynamic Neural Nets (Economic and Social Research Council, UK) and Network Programming for Safety Critical Systems (Science and Engineering Research Council/Department of Trade and Industry). Although the project is housed in Computer Science, it is in collaboration with the Department of Automatic Control and Systems Engineering. Applicants should be skilled in C programming and have a proven track record of research on Artificial Neural Nets and be willing to move between different types of learning methods. Experience with robotics or control engineering would be useful but not essential. An important aspect of the project is to develop an intermediate level theory of applications focussed on the coordination of network modules with different architectures and that were trained by different learning methods. All formal application must be send to the University Personell Department who will also send out further particulars. I will send out a more formal advert to this effect next week. This is just a preliminary announcement to get an idea of the field of applications and to get some discussion going. If you are interested please send a brief CV or express your intention to apply to jill at dcs.sheffield.ac.uk Thanks Noel Sharkey Professor of Computer Science Department of Computer Science Regent Court University of Sheffield S1 4DP, Sheffield, UK N.Sharkey at dcs.shef.ac.uk FAX: (0742) 780972  From meade at caesar.rice.edu Sun Oct 16 17:04:13 1994 From: meade at caesar.rice.edu (Andrew Meade 238Cox x4906) Date: Sun, 16 Oct 94 16:04:13 CDT Subject: Paper on Neuroprose: Solution of Nonlinear ODEs Message-ID: <9410162104.AA03016@calpurnia.rice.edu> FTP-host: archive.cis.ohio-state.edu FTP-file: pub/neuroprose/meade.nonlinearodes.ps.Z ================================================================= The following paper has been placed in the Neuroprose archive at Ohio State University: "Solution of Nonlinear Ordinary Differential Equations by Feedforward Neural Networks" A.J. Meade, Jr. and A.A. Fernandez (25 pages. No hard copies available.) To appear in Mathematical and Computer Modelling ABSTRACT: It is demonstrated, through theory and numerical examples, how it is possible to directly construct a feedforward neural network to approximate nonlinear ordinary differential equations without the need for training. The method, utilizing a piecewise linear map as the activation function, is linear in storage, and the $L_2$ norm of the network approximation error decreases monotonically with the increasing number of hidden layer neurons. The construction requires imposing certain constraints on the values of the input, bias, and output weights, and the attribution of certain roles to each of these parameters. All results presented used the piecewise linear activation function. However, the presented approach should also be applicable to the use of hyperbolic tangents, sigmoids, and radial basis functions. Andrew J. Meade, Jr. and Alvaro A. Fernandez Rice University Department of Mechanical Engineering and Materials Science Mail Stop 321 Houston, Texas, 77251-1892, USA Phone: (713) 527-8101 ext. 3590 email: meade at rice.edu ============================================ Retrieve this paper by anonymous ftp: unix> ftp archive.cis.ohio-state.edu (or 128.146.8.52) Name: anonymous Password: ftp> cd pub/neuroprose ftp> binary ftp> get meade.nonlinearodes.ps.Z ftp> quit unix> uncompress meade.nonlinearodes.ps.Z Thanks to Jordan Pollack for maintaining this archive. A.J. Meade  From bogus@does.not.exist.com Mon Oct 17 15:28:30 1994 From: bogus@does.not.exist.com () Date: Mon, 17 Oct 1994 15:28:30 --100 Subject: No subject Message-ID: <9410171428.AA25623@ti-doz10.fh-weingarten.de> From tij at manet.espci.fr Mon Oct 17 10:59:20 1994 From: tij at manet.espci.fr (tareq i. j. albaho) Date: Mon, 17 Oct 1994 15:59:20 +0100 (MET) Subject: workshop announcement Message-ID: <199410171459.AA12936@muenter.espci.fr> WORKSHOP ON SUPERCOMPUTING IN BRAIN RESEARCH From Tomography to Neural Networks HLRZ, November 21-23, 1994 We are organizing a three days workshop at the HLRZ (German Supercomputer Center) in J\"ulich. As in previous years we have chosen a subject in which supercomputing is making an essential contribution to science; this time in biosciences. During recent years computers have become a central tool in brain research. On one hand the growing complexity of tomographic devices forces us to use reconstruction techniques of highest sophistication, which reach the limits of present computational power. On the other hand the modelling of the brain itself is becoming more and more detailed due to the enormous gain of insight of the last years. Large scale simulations of neural networks have recently even been used as benchmarks for parallel computing. In this workshop we want to bring together various communities interested in supercomputing in brain research: Applied mathematicians who understand how to reconstruct tomographic data; Experts on neural networks, including statistical physicists; Nurophysiologists who simulate neural models and discuss data handling and evaluation problems. The aim is to form a bridge between various levels of brain modelling and tomographically measurable information. If you are interested in participating (or presenting posters) you should contact as soon as possible either of the organizers, E.P\"oppel, H.J. Herrmann or D. Wolf, or the conference secretariat which will provide further information: HLRZ-Workshop; c/o Forschungszentrum J\"ulich, Postfach 1913, D-52425 J\"ulich, FRG Bitnet: HLR006 at djukfa11.bitnet Internet: HLR006 at zam001.zam.kfa-juelich.de Local Organizing Committee: H. Halling, H.J. Herrmann, H.-W. M\"uller-G\"artner, H. M\"uller-Krumbhaar, F. Pasemann, E. P\"oppel, W. Speier, D. Wolf Tentative Schedule, as known on 12 October 1994 Monday, November 21st ===================== 9.30 - 9.45 H. Rollnik, HLRZ-J\"ulich Welcome 9.45 - 10.30 H.-J. Freund, D\"usseldorf Cortical organisation of sensory-motor transformation Coffee Break 11.00 - 11.45 H. Scheich, Magdeburg Coding in the Auditory Pathway, Speech, and Cochlear Protheses 11.45 - 12.30 E. P\"oppel, KFA-J\"ulich Spatial and temporal information processing: Many open questions Lunch 14.00 - 14.45 R. Salmelin, Helsinki MEG in the Study of Human Cortical Functions 14.45 - 15.30 K. Friston, London Characterizing Neural Interactions with Functional Neuroimaging 15.30 - 16.00 B. Lautrup, Kopenhagen Extremely ill-posed learning Coffee Break 16.30 - 17.00 J.M. Drouffe, Saclay Simulating the nervous system of the nematode Caenorhabditis Elegans 17.00 - 17.30 A. Aertsen, Weizmann Inst. Coherent Dynamics of Cortical Activity 17.30 - 18.00 M.Wilson, MIT to be announced 18.00 Reception and Posters Tuesday, November 22nd ====================== 9.00 - 9.45 C. von der Malsburg, Temporal Correlations as Glue of the Mind -A Challenge for Brain Imaging Techniques 9.45 - 10.30 J. Taylor, London Modelling and Testing large scale Brain Activity Coffee Break 11.00 - 11.30 G. Palm, Ulm to be announced \cr 11.30 - 12.00 M. Abeles, Jerusalem Processing of information in the cerebral cortex by well-timed events 12.00 - 12.30 F. Pasemann, KFA J\"ulich Neuromodules: A dynamical systems approach to brain modelling Lunch 14.00 - 14.30 A. Zippelius, G\"ottingen Modelling of Synaptic Transmission 14.30 - 15.00 L. Martignon, Ulm Statistical inference methods for detecting and measuring higher order neural interactions 15.00 - 15.30 M. Opper, W\"urzburg Learning in Artificial Networks Coffee Break 16.00 - 16.30 A. Kleinschmidt, G\"ottingen Functional MRI of the Human Brain: Strategies and Findings 16.30 - 17.00 K. Kwong, Boston The Queen of fMRI: Echo Planar Imaging 17.00 - 17.30 H\"am\"al\"ainen, Helsinki Forward and inverse modelling of neuromagnetic signals \cr 17.30 - 18.00 M. Fuchs , Philips, Advanced Biomagnetic and Bioelectric Hamburg & Reconstruction Algorithms Wednesday, November 23rd ======================== 9.00 - 9.45 N. Logothetis, Houston Shape Representation in the Temporal Cortex of the Primate 9.45 - 10.30 N.N. Coffee Break 11.00 - 11.30 H. M\"uller-G\"artner, to be announced KFA-J\"ulich 11.30 - 12.00 R. G. Mangun, Davis Functional Architecture of Brain Attention Systems 12.00 - 12.30 H.J. Heinze, Magdeburg & Cognitve Modelling and Imaging 14.00 - 16.30 General Discussion, chairman E. P\"oppel Statements and Perspectives 16.30 End of Meeting  From njm at cupido.inesc.pt Tue Oct 18 06:54:50 1994 From: njm at cupido.inesc.pt (njm@cupido.inesc.pt) Date: Tue, 18 Oct 94 10:54:50 +0000 Subject: EPIA'95 - Fuzzy Logic & Neural Nets Worksop CFP Message-ID: <9410181054.AA27056@cupido.inesc.pt> -------------------------------------------------------- EPIA'95 WORKSHOPS - CALL FOR PARTICIPATION FUZZY LOGIC AND NEURAL NETWORKS IN ENGINEERING WORKSHOP -------------------------------------------------------- Seventh Portuguese Conference on Artificial Intelligence Funchal, Madeira Island, Portugal October 3-6, 1995 (Under the auspices of the Portuguese Association for AI) INTRODUCTION ~~~~~~~~~~~~ The Seventh Portuguese Conference on Artificial Intelligence (EPIA'95) will be held at Funchal, Madeira Island, Portugal, between October 3-6, 1995. As in previous cases ('89, '91, and '93), EPIA'95 will be run as an international conference, English being the official language. The scientific program includes tutorials, invited lectures, demonstrations, and paper presentations. The Conference will include three parallel workshops on Expert Systems, Fuzzy Logic and Neural Networks, and Applications of A.I. to Robotics and Vision Systems. These workshops will run simultaneously (see below) and consist of invited talks, panels, paper presentations and poster sessions. Fuzzy Logic And Neural Networks In Engineering workshop may last for either 1, 2 or 3 days, depending on the quantity and quality of submissions. FUZZY LOGIC AND NEURAL NETWORKS IN ENGINEERING WORKSHOP ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The search for systems simulating human reasoning in what regards uncertainty has created a strong research community. In particular, Fuzzy Logic and Neural Networks have been a source of synergies among researchers of both areas, aiming at developing theoretical approaches and applications towards the characterization and experimentation of such kinds of reasoning. The workshop is intended to promote the exchange of ideas and approaches in those areas, through paper presentations, open discussions, and the corresponding exhibition of running systems, demonstrations or simulations. The organization committee invites you to participate, submitting papers together with videos, demonstrations or running systems, to illustrate relevant issues and applications. EXHIBITIONS ~~~~~~~~~~~ In order to illustrate and to support theoretical presentations the organization will provide adequate conditions (space and facilities) for exhibitions regarding the three workshops mentioned. These exhibitions can include software running systems (several platforms are available), video presentations (PAL-G VHS system), robotics systems (such as robotics insects, and autonomous robots), and posters. On the one hand, this space will allow the presentation of results and real-world applications of the research developed by our community and, on the other it will serve as a source of motivation to students and young researchers. SUBMISSION REQUIREMENTS ~~~~~~~~~~~~~~~~~~~~~~~ Authors are asked to submit five (5) copies of their papers to the submissions address by May 2, 95. Notification of acceptance or rejection will be mailed to the first (or designated) author on June 5, 95, and camera ready copies for inclusion in the workshop proceedings will be due on July 3, 95. Each copy of submitted papers should include a separate title page giving the names, addresses, phone numbers and email addresses (where available) of all authors, and a list of keywords identifying the subject area of the paper. Papers should be a maximum of 16 pages and printed on A4 paper in 12 point type with a maximum of 38 lines per page and 75 characters per line ( corresponding to LaTeX article style, 12 pt). Double sided submissions are preferred. Electronic or faxed submissions will not be accepted. Further inquiries should be addressed to the inquiries address. ATTENDANCE ~~~~~~~~~~ Each workshop will be limited to at most fifty people. In addition to presenters of papers and posters, there will be space for a limited number of other participants chosen on the basis of a one- to two-page research summary which should include a list of relevant publications, along with an electronic mail address if possible. A set of working notes will be available prior to the commencement of the workshops. Registration information will be available in June 1995. Please write for registration information to the inquiries address. DEADLINES ~~~~~~~~~ Papers submission: ................. May 2, 1995 Notification of acceptance: ........ June 5, 1995 Camera Ready Copies Due: ........... July 3, 1995 PROGRAM-CHAIR ~~~~~~~~~~~~~ Jose Tome (IST, Portugal) ORGANIZING-CHAIR ~~~~~~~~~~~~~~~~ Luis Custodio (IST, Portugal) SUBMISSION AND INQUIRIES ADDRESS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ EPIA'95 Fuzzy Logic & Neural Networks Workshop INESC, Apartado 13069 1000 Lisboa Portugal Voice: +351 (1) 310-0325 Fax: +351 (1) 525843 Email: epia95-FLNNWorkshop at inesc.pt PLANNING TO ATTEND ~~~~~~~~~~~~~~~~~~ People planning to submit a paper or/and to attend the workshop are asked to complete and return the following form (by fax or email) to the inquiries address standing their intention. It will help the workshop organizer to estimate the facilities needed and will enable all interested people to receive updated information. +----------------------------------------------------------------+ | REGISTRATION OF INTEREST | | (Fuzzy Logic & Neural Networks Workshop) | | | | Title . . . . . Name . . . . . . . . . . . . . . . . . . . . | | Institution . . . . . . . . . . . . . . . . . . . . . . . . . | | Address1 . . . . . . . . . . . . . . . . . . . . . . . . . . . | | Address2 . . . . . . . . . . . . . . . . . . . . . . . . . . . | | Country . . . . . . . . . . . . . . . . . . . . . . . . . . . | | Telephone. . . . . . . . . . . . . . . Fax . . . . . . . . . . | | Email address. . . . . . . . . . . . . . . . . . . . . . . . . | | I intend to submit a paper (yes/no). . . . . . . . . . . . . . | | I intend to participate only (yes/no). . . . . . . . . . . . . | | I will travel with ... guests | +----------------------------------------------------------------+  From njm at cupido.inesc.pt Tue Oct 18 06:54:42 1994 From: njm at cupido.inesc.pt (njm@cupido.inesc.pt) Date: Tue, 18 Oct 94 10:54:42 +0000 Subject: EPIA'95 - Conference CFP Message-ID: <9410181054.AA27024@cupido.inesc.pt> EPIA'95 - CALL FOR PAPERS SEVENTH PORTUGUESE CONFERENCE ON ARTIFICIAL INTELLIGENCE Funchal, Madeira Island, Portugal October 3-6, 1995 (Under the auspices of the Portuguese Association for AI) The Seventh Portuguese Conference on Artificial Intelligence (EPIA'95) will be held at Funchal, Madeira Island, Portugal, on October 3-6, 1995. As in previous issues ('89, '91, and '93), EPIA'95 will be run as an international conference, English being the official language. The scientific program encompasses tutorials, invited lectures, demonstrations, and paper presentations. Five well known researchers will present invited lectures. The conference is devoted to all areas of Artificial Intelligence and will cover both theoretical and foundational issues and applications as well. Parallel workshops on Expert Systems, Fuzzy Logic and Neural Networks, and Applications of A.I. to Robotics and Vision Systems will run simultaneously (see below). INVITED LECTURERS ~~~~~~~~~~~~~~~~~ The following researchers have already confirmed their participation, as guest speakers: Marvin Minsky, MIT (USA) Manuela Veloso, CMU (USA) Luis Borges de Almeida, IST (Portugal) Rodney Brooks, MIT (USA) SUBMISSION OF PAPERS ~~~~~~~~~~~~~~~~~~~~ Authors must submit five (5) complete printed copies of their papers to the "EPIA'95 submission address". Fax or electronic submissions will not be accepted. Submissions must be printed on A4 or 8 1/2"x11" paper using 12 point type. Each page must have a maximum of 38 lines and an average of 75 characters per line (corresponding to the LaTeX article-style, 12 point). Double-sided printing is strongly encouraged. The body of submitted papers must be at most 12 pages, including title, abstract, figures, tables, and diagrams, but excluding the title page and bibliography. ELECTRONIC ABSTRACT ~~~~~~~~~~~~~~~~~~~ In addition to submitting the paper copies, authors should send to epia95-abstracts at inesc.pt a short (200 words) electronic abstract of their paper to aid the reviewing process. The electronic abstract must be in plain ASCII text (no LaTeX)) in the following format: TITLE: FIRST AUTHOR: <last name, first name> EMAIL: <email of the first author> FIRST ADDRESS: <first author address> COAUTHORS: <their names, if any> KEYWORDS: <keywords separated by commas> ABSTRACT: <text of the abstract> Authors are requested to select 1-3 appropriate keywords from the list below. Authors are welcome to add additional keywords descriptors as needed. Applications, agent-oriented programming, automated reasoning, belief revision, case-based reasoning, common sense reasoning, constraint satisfaction, distributed AI, expert systems, genetic algorithms, knowledge representation, logic programming, machine learning, natural language understanding, nonmonotonic reasoning, planning, qualitative reasoning, real-time systems, robotics, spatial reasoning, theorem proving, theory of computation, tutoring systems. REVIEW OF PAPERS ~~~~~~~~~~~~~~~~ Submissions will be judged on significance, originality, quality and clarity. Reviewing will be blind to the identities of the authors. This requires that authors exercise some care not to identify themselves in their papers. Each copy of the paper must have a title page, separated from the body of the paper, including the title of the paper, the names and addresses of all authors, a list of content areas (see above) and any acknowledgments. The second page should include the same title, a short abstract of less than 200 words, and the exact same contents areas, but not the names nor affiliations of the authors. This page may include text of the paper. The references should include all published literature relevant to the paper, including previous works of the authors, but should not include unpublished works of the authors. When referring to one's own work, use the third person. For example, say "previously, Peter [17] has shown that ...". Try to avoid including any information in the body of the paper or references that would identify the authors or their institutions. Such information can be added to the final camera-ready version for publication. Please do not staple the title page to the body of the paper. Submitted papers must be unpublished. PUBLICATION ~~~~~~~~~~~ The proceedings will be published by Springer-Verlag (lecture notes in A.I. series). Authors will be required to transfer copyright of their paper to Springer-Verlag. ASSOCIATED WORKSHOPS ~~~~~~~~~~~~~~~~~~~~ In the framework of the conference three workshops will be organized: Applications of Expert Systems, Fuzzy Logic and Neural Networks in Engineering, and Applications of Artificial Intelligence to Robotics and Vision Systems. Real world applications, running systems, and demos are welcome. CONFERENCE & PROGRAM CO-CHAIRS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Carlos Pinto-Ferreira Nuno Mamede Instituto Superior Tecnico Instituto Superior Tecnico ISR, Av. Rovisco Pais INESC, Apartado 13069 1000 Lisboa, Portugal 1000 Lisboa, Portugal Voice: +351 (1) 8475105 Voice: +351 (1) 310-0234 Fax: +351 (1) 3523014 Fax: +351 (1) 525843 Email: cpf at kappa.ist.utl.pt Email: njm at inesc.pt PROGRAM COMMITTEE ~~~~~~~~~~~~~~~~~ Antonio Porto (Portugal) Lauiri Carlson (Finland) Benjamin Kuipers (USA) Luc Steels (Belgium) Bernhard Nebel (Germany) Luigia Aiello (Italy) David Makinson (Germany) Luis Moniz Pereira (Portugal) Erik Sandewall (Sweden) Luis Monteiro (Portugal) Ernesto Costa (Portugal) Manuela Veloso (USA) Helder Coelho (Portugal) Maria Cravo (Portugal) Joao Martins (Portugal) Miguel Filgueiras (Portugal) John Self (UK) Yoav Shoham (USA) Jose Carmo (Portugal) Yves Kodratoff (France) DEADLINES ~~~~~~~~~ Papers Submission: ................. March 20, 1995 Notification of acceptance: ........ May 15, 1995 Camera Ready Copies Due: ........... June 12, 1995 SUBMISSION & INQUIRIES ADDRESS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ EPIA95 INESC, Apartado 13069 1000 Lisboa, Portugal Voice: +351 (1) 310-0325 Fax: +351 (1) 525843 Email: epia95 at inesc.pt SUPPORTERS ~~~~~~~~~~ Banco Nacional Ultramarino Governo Regional da Madeira Instituto Superior Tecnico INESC CITMA IBM TAPair Portugal PLANNING TO ATTEND ~~~~~~~~~~~~~~~~~~ People planning to submit a paper or/and to attend the conference or attend a workshop are asked to complete and return the following form (by fax or email) to the inquiries address standing their intention. It will help the conference organizers to estimate the facilities needed for the conference and will enable all interested people to receive updated information. +----------------------------------------------------------------+ | REGISTRATION OF INTEREST | | | | Title . . . . . Name . . . . . . . . . . . . . . . . . . . . | | Institution . . . . . . . . . . . . . . . . . . . . . . . . . | | Address1 . . . . . . . . . . . . . . . . . . . . . . . . . . . | | Address2 . . . . . . . . . . . . . . . . . . . . . . . . . . . | | Country . . . . . . . . . . . . . . . . . . . . . . . . . . . | | Telephone. . . . . . . . . . . . . . . Fax . . . . . . . . . . | | Email address. . . . . . . . . . . . . . . . . . . . . . . . . | | I intend to submit a paper (yes/no). . . . . . . . . . . . . . | | I intend to participate only (yes/no). . . . . . . . . . . . . | | I will travel with ... guests | +----------------------------------------------------------------+  From laura at predict.com Tue Oct 18 12:48:32 1994 From: laura at predict.com (Laura Barela) Date: Tue, 18 Oct 94 10:48:32 MDT Subject: Research Position in Financial Modeling Message-ID: <9410181648.AA12664@predict.com> PREDICTION COMPANY RESEARCH POSITION IN NONLINEAR MODELING OF FINANCIAL MARKETS October, 1994 Prediction Company is a small firm based in Santa Fe, NM, utilizing nonlinear forecasting technologies for prediction and computerized trading of financial instruments. The current research group consists of Doyne Farmer, Norman Packard, and William Finnoff, who have worked for over fifteen years in complex systems, including chaos and nonlinear prediction. We have the backing of a major European bank, and do propietary trading through them. Most employees own stock or stock options. We are seeking someone to join the research group. The basic task is to build models to predict and trade financial markets based on historical data. Responsibilities include application of existing technology, research and development of new technology, and participation in the design of an advanced software platform for modeling, trading, and risk control, using new methods that are well beyond the existing state of the art. The successful applicant for this job will have a Ph.D. in statistics, computer science, physics, mathematics, or a related field. Experience using neural nets, radial basis function, local approximation methods, decision trees, hidden markov models, projection-pursuit, generalized additive models, genetic algorithms, or other approximation and modeling methods, and familiarity with statistics and numerical analysis, are highly valuable. Software experience is desirable, particularly C++, S+ or related languages. Familiarity with finance, including technical trading analysis, is also desirable. Experience with real data is also highly desirable -- the nastier the better. The applicant should be willing to work in close collaboration with other researchers and software developers, and should be willing to take on what is unquestionably the most challenging but lucrative forecasting problem in existence. Prediction Company offers a relaxed and informal work environment. We are located in a converted studio on the top floor of a building in the Guadalupe commercial district. Our offices include a full kitchen, shower and roof deck. We are within easy walking distance of many cafes, restaurants and the historical central plaza of Santa Fe. Santa Fe: Santa Fe is an almost 400 year old city (settled in 1605, one of the oldest in the country) of ~60,000 people with a wealth of cultural and recreational opportunities. Known as a center for the visual arts, Santa Fe is host to many festivals and exhibitions. Located at 7000 feet elevation in the foothills of the Sangre De Cristo mountains in northern New Mexico, Santa Fe has an abundance of outdoor diversions. Biking, hiking, camping, rock climbing, fossil hunting and skiing (within 45 minutes at Ski Santa Fe and 90 minutes at Taos Ski Basin) are all possible within a short drive. US or Canadian Citizenship required, or US Permanent Residency. We are unable to assist persons requiring H-1 or F-1 Visas. Applicants should US mail resumes to: Prediction Company 320 Aztec Street, Suite B Santa Fe, NM 87501 attn: recruiting or email them to Laura Barela at laura at predict.com (postscript or ascii)  From singer at CS.HUJI.AC.IL Wed Oct 19 07:21:04 1994 From: singer at CS.HUJI.AC.IL (Yoram Singer) Date: Wed, 19 Oct 1994 13:21:04 +0200 Subject: thesis available Message-ID: <199410191121.AA02574@allegro.cs.huji.ac.il> ************* MSc THESIS AVAILABLE ************** *** DO NOT FORWARD TO ANY OTHER LISTS *** ************************************************* The following thesis has been placed in the cs.huji.ac.il (132.65.16.10) anonymous ftp. The file is igth.ps.gz (gzip compressed postscript) or igth.ps.Z (compressed postscript). Ftp instructions follow the abstract. ----------------------------------------------------- Unsupervised Learning of Cell Activities in the Associative Cortex of Behaving Monkeys, Using Hidden Markov Models Itay Gat Institute of Computer Science and Center for Neural Computation Hebrew University, Jerusalem 91904, Israel ABSTRACT: Hebb hypothesized in 1949 that the basic information processing unit in the cortex is a cell-assembly which can act, briefly, as a closed system after stimulation has ceased, and constitutes the simplest instance of a representative process. This hypothesized cell-assembly may include thousands of cells in a highly interconnected network. The cell-assembly hypothesis shifts the focus from the single cell to the complete network activity. So far, there has been no general method for relating extracellular electrophysiological measured activity of neurons in the associative cortex to the underlying network or the cell-assembly states. It is proposed here to model such data as a pair-wise correlated multivariate Poisson process. Based on these parameters, a Hidden Markov Model was computed. This modeling yielded a temporal segmentation and labeling of the data into a sequence of states. The first hypothesis of this work was that a connection exists between the states of the model and the behavioral events of the animal. i.e. based on the sequence of states of the model, the observed actions of the animal could be predicted. The second hypothesis was that a connection exists between the states defined above and the functional interaction between cells, i.e. the functional interaction between pairs of cells changes in different cognitive states. The application of this approach was demonstrated for temporal segmentation of the firing patterns, and for characterization of the cortical responses to external stimuli.This modeling was applied to 6 recording sessions of several single-unit recordings from behaving monkeys. At each session, 6-8 single-unit spike trains were recorded simultaneously. Using the Hidden Markov Model, two behavioral modes of the monkey were significantly discriminated. The two behavioral modes were characterized by different firing patterns, as well as by the level of coherency of their multi-unit firing activity. The result of the modeling showed a high degree of consistency, which implies that the model succeeds in capturing a basic structure underlying the data. Significant changes were found in the temporal cross-correlation of the same pair of cells in different states, indicating different functional connectivities of the small network being recorded. These changes suggest that the modeling captures the activity of the network and that the states of the model can be related to the cognitive states of the cortex. ----------------------------------------------------- FTP INSTRUCTIONS unix> ftp cs.huji.ac.il (or 132.65.16.10) Name: anonymous Password: full_email_address ftp> cd /pub/singer ftp> binary ftp> get igth.ps.Z or ftp> get igth.ps.gz ftp> quit unix> uncompress igth.ps.Z or unix> gunzip igth.ps.gz unix> lpr -P<printer-name> igth.ps ---------------------------------------------- Itay Gat Institute of Computer Science The Hebrew University, Givat-Ram Jerusalem 91904, Israel Email: itay at cs.huji.ac.il Fax: +972 2 58 5439  From jose at scr.siemens.com Wed Oct 19 13:56:10 1994 From: jose at scr.siemens.com (Stephen Hanson) Date: Wed, 19 Oct 1994 13:56:10 -0400 (EDT) Subject: More on McPew Message-ID: <QidJquO1GEMnENGDM1@tractatus.siemens.com> Good Luck, Steve The McDonnell-Pew Program in Cognitive Neuroscience Investigator-Initiated Grants 1994-1995 The McDonnell-Pew Program in Cognitive Neuroscience is a collaborative effort established by the James S. McDonnell Foundation, St. Louis, Missouri and the Pew Charitable Trusts, Philadelphia, Pennsylvania to support research. Since its inception in 1990, the Program has awarded $21.5 million in support of institutional centers and individual investigators. Cognitive neuroscience attempts to understand human mental events by specifying how neural tissue carries out computations. Work in cognitive neuroscience is multidisciplinary, drawing on developments in clinical and basic neuroscience, computer science, psychology, linguistics and philosophy. The McDonnell-Pew Program does not support research based on descriptions of psychological function that do not address underlying brain mechanisms or neuroscientific descriptions that do not speak to psychological function. The Program has two components: 1) Institutional Center grants that established large research and training programs; all Center grants have been awarded. 2) Investigator-initiated grants supporting interdisciplinary training and providing seed funds for collaborative research. The Program accepts investigator-initiated grants as described in this brochure. Program goals: The Program will preferentially support innovative, interdisciplinary research of the highest caliber that is unlikely to be funded from traditional sources. The Program hopes to encourage researchers to seek interdisciplinary training and collaborations with persons outside their own discipline. The Program particularly encourages research on higher cognitive functions including, high-order vision, language, planning, and problem-solving. The cognitive question to be studied and the neuroscientific methods to be applied must be clearly articulated in the research proposal. The awards will provide a maximum of $35,000 per year for up to 3 years. Indirect costs are included in the $35,000 maximum and cannot exceed 10% of total salaries plus fringe benefits. An individual cannot receive support from more than one investigator- initiated grant. The grants are non-renewable. Examples of the types of research proposals sought by the program include: using neurobiological methods to study higher cognitive processes applying formal modelling techniques to cognitive functions, including emotions and higher thought processes dveloping new theories of the human mind/brain systems using sensing (EEG, MEG) or imaging techniques (PET, MRI) to observe the brain during conscious activity. Preference will be given to training proposals that exemplify multi- disciplinary and collaborative research as described below: a junior scientist pursuing a research project in the laboratory of a senior scientist in a different field of cognitive neuroscience; collaborations between two or more scientists representing different subdisciplines of cognitive neuroscience; a scientist with expertise in a subdiscipline of cognitive neuroscience obtaining hands-on training in a new methodology or technique to be used in the study of higher cognitive function. Eligibility: Individual investigators at institutions with McDonnell-Pew Center grants, who are already receiving support from a McDonnell-Pew Center grant are not eligible for the investigator-initiated grant program. Researchers who are at institutions that have been awarded a McDonnell-Pew Center grant but who do not receive any support from the Center are eligible. There are no US citizenship restrictions or requirements, nor must the proposed work be conducted at a US institution, providing the sponsoring organization qualifies as tax-exempt under IRS guidelines (see the "Applications" section of this brochure). The Program described in this brochure will not support dissertation research, workshops, conferences, or travel for the purpose of attending meetings. Proposals to investigate basic neurobiology unrelated to human, higher-order cognition will not be funded. Application guidelines: Applicants should submit five (5) copies of the following information: 1) A completed cover sheet (enclosed); 2) A brief, one-page abstract describing the proposed work; 3) A brief, itemized budget that includes direct and indirect costs (indirect costs may not exceed 10 percent of total salaries and fringe benefits); 4) A budget justification; 5) A narrative proposal (not to exceed 5,000 words) that describes the cognitive question to be investigated and all methodological approaches in sufficient detail to allow the proposal to be evaluated by the advisory board. If the application is requesting support for training, a description of the training plan and the relationship of the training to the applicant's research goals should be included; 6) Curriculum vitae for each of the participating investigators; 7) An authorized document indicating clearance for the use of human and animal subjects; 8) An endorsement letter from the officer of the sponsoring institution who will be responsible for administering the grant. One copy of each of the following items must also be submitted along with the proposal. These documents can be obtained from the sponsoring institution's grants or development office. A copy of the IRS determination letter, or the international equivalent, stating that the sponsoring organization is a nonprofit, tax-exempt institution classified as a 501(c)(3) organization. A copy of the IRS determination letter stating that the sponsoring organization is not listed as a private foundation under section 509(a) of the Internal Revenue Service Code. No other documents should be appended to the application. Submissions will be reviewed by the program's advisory board. Applications must be received in the Foundation office no later than February 20, 1995. Incomplete or late proposals will not be reviewed. Contact: Susan M. Fitzpatrick, Ph.D. McDonnell-Pew Program in Cognitive Neuroscience James S. McDonnell Foundation 1034 South Brentwood Blvd., Suite 1610 St. Louis, Missouri 63117 Phone: 314/721-1532 e-mail: C 6819CN at WUVMD.WUSTL.edu  From cabestan at eel.upc.es Thu Oct 20 13:08:51 1994 From: cabestan at eel.upc.es (Joan Cabestany) Date: Thu, 20 Oct 1994 17:08:51 UTC Subject: IWANN'95 Call for Papers Message-ID: <786*/S=cabestan/OU=eel/O=upc/PRMD=iris/ADMD=mensatex/C=es/@MHS> Please find here the final announcement and definitive Call for Papers of IWANN'95 (International Workshop on Artificial Neural Networks) to be held next June 1995 in Malaga (Spain). Any questions could be addressed to: Prof. J.Cabestany - cabestan at eel.upc.es Prof. F.Sandoval - sandoval at tecma1.ctima.uma.es Sincerely yours J.Cabestany *********************************************************************** ================== INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORKS IWANN'95 Second and Final Call for Papers Hotel Melia - Costa del Sol Torremolinos (Malaga) - Spain June 7 - 9, 1995 SPONSORED BY Plan Nacional de I + D (CICYT) DGICYT (MEC) Junta de Andalucia Universidad de Malaga Universidad Nacional de Educacion a Distancia D. G. S. R. D., DG-XII Human Capital and Mobility (EC) Spanish RIG IEEE Neural Networks Council UK&RI communication Chapter of IEEE Spanish Computer Society Chapter of IEEE AEIA (IEEE affiliated society) ORGANISED BY Universidad de Malaga UNED (Madrid) ============================================================================= IWANN'95. The third International Workshop on Artificial Neural Networks, will take place in the Spanish "Costa del Sol" (Malaga) from 7 to 9 of June, 1995. This biennial meeting with focus on Biological Models and New Computing Paradigms, was first held in Granada (1991) and Sitges (1993) with a growing number of participants from more than 20 countries and with high quality papers published by Springer-Verlag (LNCS 540 and 686). SCOPE From the computational viewpoint, standard neural networks pa- radigms are nearly exhausted and some fresh air is needed. In this workshop, remaining with the powerful roots of neural computation (modularity, autonomy, distributed computation and self-programming via supervised or non-supervised learning), focus is placed on Biolo- gical Modeling, the search of Theory and Design Methodologies and the bridge between Connectionism and Symbolic Computation. IWANN's main objective is to offer an interdisciplinary forum for scientists and engineers from Neurology, Computer Science, Artifi- cial Intelligence, Electronics, Cognitive Science and applied domains, looking after brain storming and innovative formulations of Natural and Artificial Neural Computation. It is the deep feeling of the IWANN's organizers that this more- complex, biologically inspired, and theoretical and methodologically supported approach will also provide us with more powerful tools for applied domains. All received papers will be reviewed by the Programme Committee. Accepted papers may be presented orally or as poster panels, however all accepted contributions will be published in full length. (Springer-Verlag Proceedings are expected). Coordinated inscription with the 3rd. European Conference on Artifi- cial Life (ECAL95), to be held in Granada, JUNE 4-6,1995, is possible at special rates. Malaga and Granada are only one and a half hour apart by car. Contributions on the following or related topics are welcome. ============================================================================= TOPICS 1. Neuroscience: Principles, methodologies in brain research, mo- deling and simulation, central and peripheral neural coding, dendro-dendritic nets, local circuits, anatomical and physiolo- gical organizations, plasticity, learning and memory in natural neural nets, models of development and evolution, specific cir- cuits in sensorial and motor pathways, networks in the ce- rebral cortex. 2. Computational Models of Neurons and Neural Nets: Continuous (linear, high order, recurrent), logic, sequential, inferential (object oriented, production rules, frames), probabilistic, Bayesian, fuzzy and chaotic models, hybrid formulations, massive computation and learning enabling structures for all these for- mulations. 3 Organizational Principles: The living organization, determi- nistic networks dynamics, autopoiesis, self-organization, cooperative processes and emergent computation, synergetics, evolutive optimization and genetic algorithms. 4. Learning: Inspirations from the biological mechanisms of lear- ning, supervised and unsupervised strategies, local self- programming, continous learning, evolutive algorithms, symbolic-subsymbolic formulations. 5. Cognitive Science and AI: Neural networks for knowledge acqui- sition, multisensorial integration, perception, knowledge-based neural nets, inductive, deductive and abductive reasoning, me- mory mechanisms, natural language. 6. Neurosimulators: Languages, environments, parallelization, mo- dularity, extensibility and benchmarks. 7. Hardware Implementation: VLSI, parallel architectures, neuro- chips, preprocessing networks, neurodevices, FPGA's, benchmarks, optical and other technologies. 8. Neural Networks for Perception: Low level processing, segmenta- tion, feature extraction, pattern recognition, adaptive filte- ring, noise reduction, texture, motion analysis, hybrid symbolic-neural architectures for artificial vision. 9. Neural Networks for Communications Systems: Modems and codecs, network management, digital communications. 10. Neural Networks for Control and Robotics: Systems identification, motion planning and control, adaptive and predictive control, navigation, real time applications. ============================================================================= ____________________________________________________________________ | | | THE EMBODIMENTS OF MIND REVISITED | | MEMORIAL SPECIAL SESSION | | in the 25th ANNIVERSARY | | | | of the dead of | | WARREN S. McCULLOCH | | | | Papers for this special session are wellcome, with focus on | | the relevance at the present time of W.S. McCulloch's work | | (Epistemological Physiology, Formal Neurons, Universals, | | Anastomotic Nets, Triadic Relations, the Lekton, | | Reverberating Memory, a Calculus for Intention, Redundancy | | of Potencial Command,...) | |____________________________________________________________________| LOCATION Malaga - Costa del Sol, June 7-9, 1995. Malaga, capital of the Costa del Sol, is strategically located on the southern coast of Spain. It is a genuine crossroads of communication and culture. Malaga is well-know for its history (Cathedral, historic down-town, arabian citadel, roman amphitheatre, ...) and excelent beaches. Malaga, with many modern hotels, is very well communicated by car or plane; its international airport has direct flights to all major European capitals, to America and some destinations on the other continents. In June, weather is warm and pleasant. Averages temperatures:18-30C. Comfortable walking shoes, light clothes and bathing suits are recommended. TRAVEL AND ACCOMMODATION Viajes El Corte Ingles is the official travel and accomodation agent for the Workshop, and will provide all the necessary tourist services to participants: Travel arrangements, Accommodation, Rent-a-car, Pre and Post Workshop sightseeings tours, etc. Viajes El Corte Ingles, S.A. IWANN'95 Avda. Andalucia, 4 29007 Malaga, Spain. Phone:+ 34.5.230.82.00 / + 34.5.230.00.00 Fax: + 34.5.261.12.42 ============================================================================= CALL FOR PAPERS The Programme Committee seeks original papers on the above mentioned Topics. Authors should pay special attention to explanation of theoreti- cal and technical choices involved, point out possible limitations and describe the current state of their work. Authors must take into account the following: INSTRUCTIONS TO AUTHORS Authors must submit four copies of full papers, not exceeding 8 pa- ges in DIN-A4 format including figures, tables and references. English will be the official language. The heading should be centered and include: . Title in capitals. . Name(s) of author(s). . Address(es) of author(s). . A 10 lines abstract. Three blank lines should be left between each of the above items, and four between the heading and the body of the paper, 1.6 cm left, right, top and bottom margins, single-spaced and not exceeding the 8 pages limit. In addition, one sheet should be attached including the following information: . Title and author(s) name(s). . A list of five keywords. . A reference to the Topics the paper relates to. . Postal address, phone and fax numbers and E-mail (if available). CONTRIBUTIONS MUST BE SENT TO: Prof. Jose Mira Dpto. Informatica y Automatica UNED Senda del Rey, s/n Phone:+ 34.1.398.71.55 28040 MADRID (Spain) Fax:+ 34.1.398.66.97 IMPORTANT DATES Final date for submission January 15, 1995 Notification of acceptance March 15, 1995 Workshop June 7-9, 1995 ============================================================================= INVITED TALKS Prof. Stephen Grossberg Boston University (U.S.A.) Opening Session of IWANN'95 Dr. Jeanny Herault Institut National Polytecnique of Grenoble(F) Neural Networks for Perception Dr. Joshua Alspector Bellcore, AT&T (U.S.A.) Hardware Implementation and Applications to Communications. Prof. Igor Aleksander Imperial College of Science Tech. and Medicine,London (U.K.) Cognitive Science and AI Prof. Carme Torras Instituto de Cibernetica, CSIC (E) Learning and Application to Control and Robotics Prof. H.R. Maturana Universidad de Chile (Chile) Neuroscience and Organizational Principles. GENERAL CHAIRMAN Alberto Prieto Unv. de Granada (E) ORGANIZATION COMMITTEE Joan Cabestany Unv. Pltca. de Cataluna (E) Chairman Senen Barro Unv. de Santiago de Compostela (E) Trevor Clarkson King's College London (UK) Dante Del Corso Politecnico de Torino (I) Ana Delgado UNED. Madrid (E) Tom Gedeon Univ. of New South Wales (AUS) Karl Goser Unv. Dortmund (G) Jeanny Herault INPG Grenoble (F) K.Nicholas Leibovic SUNY at Buffalo (U.S.A.) Jose Mira UNED. Madrid (E) Federico Moran Unv. Complutense. Madrid (E) Stanislaw Osowski Tech. Unv. Warsaw (Po) Conrad Perez Unv. de Barcelona (E) Francisco Sandoval Unv. de Malaga (E) Juan A. Sigenza Inst. Ingenieria del Conocimiento, UAM (E) Elena Valderrama Centro Nacional Microelectrnica, UAB (E) Marley Vellasco Pont. Unv. Catolica do Rio de Janeiro (Br) Michel Verleysen Unv. Catholique de Louvain (B) ============================================================================= PROGRAMME COMMITTEE Jose Mira UNED. Madrid (E) Chairman Carlos Acuna C. Unv. Santiago de Compostela (E) Joshua Alspector Bellcore. (USA) Sanjeev B.Ahuja Nielsen A.I. Research & Development. Bannokburn (USA) Igor Aleksander Imperial College. London (UK) Shun-ichi Amari Unv. Tokyo (Jp) Xavier Arreguit CSEM SA (CH) Francois Blayo LERI-EERIE. Nimes (F) Colin Campbell University of Bristol (UK) Jordi Carrabina CNM- Universidad Autnoma de Barcelona (E) Francisco Castillo Unv. Pltca. de Cataluna (E) Andreu Catala Unv. Pltca. de Cataluna (E) Marco A. Cavalcanti P. Pontificia Universidade Catolica do Rio de Janeiro (Br) Gabriela Cembrano Instituto de Cibernetica. CSIC. Barcelona (E) Leon Chua Unv. California, Berkeley (USA) Michael Cosnard LIP. Ecole Normale Superieure de Lyon (F) Marie Cottrell Unv. Paris I (F) Dante A. Couto B. Instituto de Informatica (Br) Gerard Dreyfus ESPCI. Paris (F) F.K. Fogelman Soulie Mimetics. Chatenay Malabry (F) J. Simoes da Fonseca Unv. Lisboa (P) Kunihiko Fukushima Unv. Osaka (Jp) Hans Peter Graf AT&T Bell Laboratories, New Jersey (USA) Karl E. Grosspietsch Mathematik und Datenverarbeitung (GMD). St. Augustin (D) Mohamad H. Hassoun WayneState University (USA) Jaap Hoekstra Delft University of Technology (NL) Jose Luis Huertas CNM- Universidad de Sevilla (E) Simon Jones IERI Loughborough University of Technology(UK) Christian Jutten INPG Grenoble (F) H. Klar Technische Universitt Berlin (D) C.Koch CalTech. (USA) Michael D. Lemmon University of Notre Dame. Notre Dame (USA) Panos A. Ligomenides Unv. of Maryland (USA) Javier Lpez Aligue Unv. de Extremadura. (E) Pierre Marchal CSEM SA (CH) Anthony N. Michel University of Notre Dame. Notre Dame (USA) Roberto Moreno Unv. Las Palmas Gran Canaria (E) Jean Daniel Nicoud EPFL (CH) Josef A. Nossek Tech. Univ. of Munich (D) Julio Ortega Unv. de Granada (E) Francisco J. Pelayo Unv. de Granada (E) Franz Pichler Johannes Kepler Univ. (A) Vicenzo Piuri Politecnico di Milano (I) Ulrich Ramacher Siemens AG. Munich (D) J.Ramirez Paradigma C.A. Caracas (V) Leonardo Reyneri Unv. di Pisa (I) Tamas Roska Hungarian Academy of Science. Budapest (H) Peter A. Rounce Unv. College London (UK) V.B. David Sanchez German Aerospace Research Establishment. Wessling (G) Renato Stefanelli Politecnico di Milano (I) T.J. Stonham Brunel-University of West London (UK) John G. Taylor King's College London (UK) Carme Torras Instituto de Cibernetica. CSIC. Barcelona (E) Philip Treleaven Unv. College London (UK) Michel Weinfeld Ecole Polytechnique Paris (F) R.Yager Iona College NY (USA) ============================================================================= LOCAL COMMITTEE Francisco Sandoval Unv. de Malaga (E) Chairman Antonio Diaz Unv. de Malaga (E) Gonzalo Joya Unv. de Malaga (E) Francisco Vico Unv. de Malaga (E) FOR ADDITIONAL INFORMATION: Prof. F. Sandoval IWANN'95 Dept. Tecnologia Electronica Universidad de Malaga Plaza El Ejido, s/n E-29013 Malaga SPAIN Phone: +34.5.213.13.62 Fax: +34.5.213.14.47 E-mail:iwann95 at ctima.uma.es GRANTS Young researchers, citizens or residents in European Union States, may apply for grants offered by European Community (Human Capital and Mobility, DG XII). Deadline for application: February 15, 1995. Please, write for information to the Organization Committee Chairman: Joan Cabestany IWANN'95 Dpto. Ingenieria Electronica, UPC Gran Capitan, s/n Campus Nord, Edificio C4 08034 Barcelona, Spain Tf.+34-3-4016742; Fax: +34-3-4016756 Email:Cabestan at eel.upc.es ============================================================================= IWANN'95 INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORKS Hotel Melia -Costa del Sol, Torremolinos (Malaga), Spain-June 7th - 11th, 1995 REGISTRATION FORM Name:_______________________________________________________________ Last/Family First Company/University:_________________________________________________ Mailing Address: _________________________________________________ City/State/Zip/Country:_____________________________________________ Telephone: __________________________ Fax: ________________________ Email: _____________________________________________________________ REGISTRATION FEES Before April 5 After April 5 Full Inscription* 65.000.-ptas 75.000.-ptas ________ptas Basic Inscription ** 55.000.-ptas 65.000.-ptas ________ptas With ECAL95 Registration*** 55.000.-ptas 65.000.-ptas ________ptas Gala Dinner Invitation 8.000.-ptas X _____ = ________ptas TOTAL ATTACHED PAYEMENT ___________________ptas * Full inscription includes: wellcome reception, opening ceremony, lunches during session days, refreshments and coffee breaks, confe- rence kit and personal badges, proceedings, attendance at all sessions and Gala dinner. ** Basic inscription does not include: Gala dinner and lunches during session days. *** It includes the same that Full inscription. METHODS OF PAYMENT [ ] By bank draft in Pesetas, payable to IWANN-95. UNIVERSIDAD DE MALAGA on a Spanish Bank. [ ] By bank transfer to: Banco Espanol de Credito (c/o IWANN-95. UNIVERSIDAD DE MALAGA), Ofic. Principal, Alameda Principal, 8, 29005 Malaga (Spain), Acct. No. 105.123-271. Transfer fee to be paid by sender. Please attach copy of bank transfer to this Form. [ ] VISA CARD [ ] MASTER CARD [ ] AMERICAN EXPRESS CARD [ ] DINNERS CARD Credit Card Number___________________________ Expiration Date______________ Cardhlder Name ____________________________________________________________ Date __________________________________ Signature__________________________ Please, send this Registration Form, together with payement, to: Francisco Sandoval IWANN'95. Dept. Tecnologia Electronica. Universidad de Malaga. Plaza El Ejido s/n. E-29013 Malaga SPAIN. Tf.+34.5.213.13.62 Fax: +34.5.213.14.47 ============================================================================== IWANN'95 INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORKS Hotel Melia - Costa del Sol, Torremolinos (Malaga), Spain - June 7 - 9, 1995 HOTEL RESERVATION FORM Name:________________________________________________________________ Last/Family First Company/University: _________________________________________________ Mailing Address:_____________________________________________________ City/State/Zip/Country:______________________________________________ Telephone:__________________________ Fax:__________________________ Email:_______________________________________________________________ SPECIAL HOTEL RATES PER NIGHT AND ROOM (Breakfast and V.A.T. included) Single Use Room Twin Room [ ] Hotel Melia - Costa del Sol**** 6.200.-ptas 8.200.-ptas (Workshop Venue) [ ] Hotel Royal Park*** 4.200.-ptas 5.000.-ptas (1 Km apart Workshop Venue) Please reserve________room(s) [ ] Twin(s) [ ] Single(s) at Hotel _________ __________________________________________________________________________ (If twin room, give the name of person sharing accommodation). __________________________________________________________________________ Date of arrival __________________ Date of departure ____________________ HOTEL RESERVATION DEPOSIT A deposit of 16.000.-ptas per room will be necessary to confirm the Hotel reservation. Attached Hotel Deposit 16.000.-ptas X ______ room/s = ___________.-ptas. METHODS OF PAYMENT [ ] By bank draft in Pesetas, payable to Viajes el Corte Ingles S.A. on a Spanish bank. [ ] VISA CARD [ ] MASTER CARD [ ] AMERICAN EXPRESS CARD [ ] EL CORTE INGLES CARD [ ] DINNERS CARD Credit Card Number ________________________ Expiration Date _____________ Cardholder Name __________________________________________________________ Date________________________________ Signature _______________________ Please send this Hotel Reservation Form, before May 7, 1995, together with payement, to: Viajes el Corte Ingles, S.A. IWANN-95 Avda Andalucia, 4 29007 Malaga, Spain Tlf: +34.5.2308200; Fax: +34.5.2611242 ================================================================ IWANN'95 INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORKS Hotel Melia - Costa del Sol, Torremolinos (Malaga), Spain, June 7-9, 1995 GRANT APPLICATION The Organizing Committee of the IWANN'95 will grant a limited number of young researchers from Western European Countries, according to the conditions of the DG XII-G-3 Human Capital and Mobility Program (EC). The grants could support the global or partial expenses for assisting to the Workshop. Please mail this Form together with your Curriculum Vitae before February 15th, 1995 to: Prof. Joan Cabestany IWANN'95 DEE-UPC Campus Nord, Building C4 08034 BARCELONA, Spain Name: ................................................................... Institution or Center: .................................................. Position: ............................................................... Postal Address: ......................................................... ......................................................................... Zip/Code: ........................ Country: ............................. Phone: ........................... FAX: ................................. Email: .................................................................. I have submitted a paper to IWANN'95 with the title: ==============================================================================  From udee150 at bay.cc.kcl.ac.uk Thu Oct 20 08:12:45 1994 From: udee150 at bay.cc.kcl.ac.uk (Chris Christodoulou) Date: Thu, 20 Oct 1994 12:12:45 GMT Subject: UKRI IEEE Neural Networks Regional Interest Group Message-ID: <0098639C.5B23AA5C.148@bay.cc.kcl.ac.uk> Establishment of an IEEE Neural Networks Regional Interest Group in UKRI (United Kingdom and Republic of Ireland) Section) ------------------------------------------------------------------ This is to announce that an IEEE UKRI Neural Networks RIG has been established and had its inaugural meeting on 19th October 1994 at King's College London. The RIG will be under the UKRI IEEE Communications Chapter. The scope of interest of the RIG will include apart from Neural Networks, Fuzzy Systems and Genetic Algorithms. The RIG will organise, sponsor or co-sponsor activities like: * Evening Lectures * Workshops * Training Courses and will cooperate with other IEEE Societies and local and regional institutions. The RIG is keen to invite distinguished speakers from the Neural Network community worldwide to give lectures and therefore anyone from the Connectionists list who is in the UK or the Republic of Ireland and is interested in giving a lecture under the RIG's auspices is welcome. For further information and membership enquiries please contact: Dr Trevor G. Clarkson Chairman, UKRI Neural Networks RIG Dept. of Electronic & Electrical Eng. King's College London Strand, London WC2R 2LS England, UK Tel. (+44) 171-873 2367 Fax (+44) 171-836 4781 Email: tgc at kcl.ac.uk or fill in your details below and return them to Dr Trevor Clarkson by email, fax or post: _______________________________________________________________________ UKRI Neural Networks RIG REQUEST FOR INFORMATION Please supply the information shown to update our records. Name: ............................................................. < >Membership number (M ) and Grade (F / SM / M / Student) < >Postal Address < >Telephone and Fax numbers / < >Email < >IEEE Society affiliations < >I do*/do not* wish my name to be published in the RIG directory (*delete as required) Current interests: _______________________________________________________________________  From mike at PARK.BU.EDU Thu Oct 20 13:03:26 1994 From: mike at PARK.BU.EDU (mike@PARK.BU.EDU) Date: Thu, 20 Oct 1994 13:03:26 -0400 Subject: Job Announcement Message-ID: <199410201703.NAA29016@space.bu.edu> NEW SENIOR FACULTY IN COGNITIVE AND NEURAL SYSTEMS AT BOSTON UNIVERSITY BOSTON UNIVERSITY seeks an ASSOCIATE or FULL PROFESSOR for its graduate DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS. This department offers an integrated curriculum of psychological, neurobiological, and computational concepts, models, and methods in the fields of computational neuroscience, connectionist cognitive science, and neural network technology in which Boston University is a leader. Candidates should have an international research reputation, preferably including extensive analytic or computational research experience in modeling a broad range of nonlinear neural networks, especially in one or more of the areas: vision and image processing, adaptive pattern recognition, cognitive information processing, speech and language, and neural network technology. Send a complete curriculum vitae and three letters of recommendation to: Search Committee Department of Cognitive and Neural Systems 111 Cummington Street, Second Floor Boston University, Boston, MA 02215 Boston University is an Equal Opportunity/Affirmative Action Employer.  From liaw at bmsr14.usc.edu Thu Oct 20 14:52:28 1994 From: liaw at bmsr14.usc.edu (Jim Shih-Liaw) Date: Thu, 20 Oct 1994 11:52:28 -0700 Subject: Postdoc position: Motor pattern generation Message-ID: <199410201852.LAA22643@bmsr14.usc.edu> NEUROETHOLOGY OF MOTOR PATTERN GENERATION Postdoctoral position available immediately for three years to investigate neuroethological aspects of motor pattern generators and their coordination. The position is associated with an NSF sponsored collaborative research project between Michael Arbib (University of Southern California) and Ananda Weerasuriya (Mercer University School of Medicine, GA), and will be based at the latter location. The primary focus will be on characterizing the behavior and electromyography of rapidly adapting prey capture patterns of frogs. Experience with chronic electrophysiological recording techniques in small animals is highly desirable. Please send vita, summary of research experience and interests, and names and tel. numbers of three or more references to Ananda Weerasuriya, Division of Basic Medical Sciences, Mercer University School of Medicine, 1550 College Street, Macon, GA 31207. Fax: (912) 752-4038, email: weerasuriy_a at mercer.peachnet.edu. AA/EOE.  From marcus at dope.caltech.edu Thu Oct 20 15:07:25 1994 From: marcus at dope.caltech.edu (Marcus Quintana Mitchell) Date: Thu, 20 Oct 94 12:07:25 PDT Subject: No subject Message-ID: <9410201907.AA22324@dope.caltech.edu> ------------------------------------------------------------------- NIPS*94 Workshop: OPEN AND CLOSED PROBLEMS IN NEURAL NETWORK ROBOTICS --------------------------------------------------- Organizer: Marcus Mitchell CALL FOR PARTICIPATION ---------------------- Introduction ------------- Many of the presumed tenets of neural computation -- nonlinearity, parallelism, adaptation, real-time performance -- suggest that a "neuromorphic" approach to robotics problems could succeed where previous approaches have failed. Further, the amazing motor performance of humans and animals provides additional arguments for the potential benefits of "a sideways look" towards neurobiology. Spurred on by these and other factors, researchers from a variety of backgrounds have produced almost 15 years of research intended to elaborate a biologically-inspired robotics. This workshop will ask the questions "What has been accomplished so far?" and "What is to be done next?" Aims ---- For all the research attempts to apply neural network ideas to robotics, it is still difficult to get clear answers to questions like "Can you use a neural network to control a 6 d.o.f. arm?" or "Do reinforcement learning learning and dynamic programming methods get killed by the curse of dimensionality?" In addition, robotics is an area with a vast and intimidating "non-neural" literature which must be considered. The main goal of this workshop is to stimulate discussion about what problems have been successfully attacked and what the most important current open problems entail. A secondary goal of the workshop is to produce a short consensus list of problem descriptions and their status. Schedule for Saturday, December 3, 1994 --------------------------------------- (subject to change) 7:30 - 8:00 Opening Remarks Marcus Mitchell, Caltech 8:00 - 8:25 Why it's harder to control your robot than your arm: closed, open and irrelevant issues in inverse kinematics Dave Demers, UCSD 8:25 - 9:00 Discussion 9:00 - 9:25 Open Problem: Optimal Motor Hidden Units Terry Sanger, JPL 9:25 - 10:00 Discussion 10:00 - 10:25 Neural Network Vision for Outdoor Robot Navigation Dean Pomerleau, CMU 10:25 - 11:00 Discussion 11:00 - 4:30 FREE TIME 4:30 - 4:55 Learning New Representations and Strategies Chris Atkeson, Georgia Tech 4:55 - 5:30 Discussion 5:30 - 5:55 A Semi-Crisis for Neural Network Robotics: Formal Specification of Robot Learning Tasks Andrew Moore, CMU 5:55 - 6:30 Discussion 6:30 - 6:35 Closing Remarks Related workshop on control --------------------------- A complementary workshop, titled "Novel Control Techniques from Biological Inspiration", organized by Jim Schwaber et al., may be of interest to participants. None of the presentations in that session will be on robotics, and its main focus will be on nonlinear dynamical systems, e.g. in chemical processes and in neural systems. It is a one day workshop to be held Friday, December 2, 1994. For more information contact Richard Braatz (rdb at beethoven.che.caltech.edu). --------------------------------------------------------------------------- Marcus Q. Mitchell Computation and Neural Systems, Mail Code 139-74 California Institute of Technology Pasadena, CA 91125 Phone: (818) 395-2805 FAX: (818) 792-7402 email: marcus at hope.caltech.edu  From lbookman at tiac.net Fri Oct 21 01:05:43 1994 From: lbookman at tiac.net (Larry Bookman) Date: Fri, 21 Oct 1994 00:05:43 -0500 Subject: Book anouncement Message-ID: <199410210406.AAA29896@zork.tiac.net> *** Announcing a new book *** available from Kluwer Academic Publishers: Trajectories Through Knowledge Space: A Dynamic Framework For Machine Comprehension by Lawrence A. Bookman ISBN 0-7923-9487-9 (Order information is in the end of this message) A central focus of the book is on the developemnt of a framework for comprehension connecting research themes from cognitive psychology, cognitive science, corpus linguistics, and artificial intelligence. The book proposes a new architecture for semantic memory, providing a framework for addressing the problem of how to represent background knowledge in a machine. -------------------------------------------- Excerpt from FOREWORD .. this volume is without question a milestone in language processing scholarship. Bookman has pulled many research threads from a number of fields to weave a remarkably cohesive picture of the processes underlying human language comprehension. The net effect is both exciting and inspiring --- this book will be embraced by studious newcomers and appreciated by seasoned researchers as well. It is difficult to find cognitive researchers who have a visionary sense of the big picture. Larry Bookman's vision is both comprehensive and sparkling in its clarity. Read this book from cover to cover and then read it again. This is what the field of natural language processing is all about. Wendy Lehnert Professor of Computer Science Director of the Natural Language Processing Laboratory University of Massachusetts at Amherst -------------------------------------------- TABLE OF CONTENTS List Of Figures List Of Tables Foreword By Wendy Lehnert Preface Chapter 1 Introduction 1.1 Motivation 1.2 A View of Text Comprehension 1.3 Overview of the LeMICON System 1.4 Implementation 1.5 Points of Interest 1.6 The Impact of this Work on Four Related Fields 1.7 Development of the Two-Tier Model 1.8 A Guide to the Reader Chapter 2 An Overview of Connectionist and Probabilistic Approaches to Language Processing 2.1 A Computational Linguistics Perspective 2.2 A Connectionist Perspective 2.3 A Comparison of Connectionist and Probabilistic NLP Methods 2.4 Bridging the Gap --- Integrating Connectionist and Computational Linguistic Approaches Chapter 3 Memory Architecture 3.1 The Relational Tier 3.2 The Associational or ASF Tier 3.3 Connecting the Two Tiers 3.4 Working Memory 3.5 How New Knowledge Is Integrated Chapter 4 The Basic Computation 4.1 A Functional Description of the Algorithm 4.2 Representing the Input 4.3 Computational Details and Program Output at each Step 4.4 General Discussion of the Algorithm 4.5 How LeMICON Handles Binding 4.6 The Links to Psychology and Neurophysiology Revisited 4.7 Some Comparisons to Other Text Understanding Systems Chapter 5 Analysis of the Interpretation at the Relational and ASF Level 5.1 Introduction 5.2 Analyzing the Interpretation at the Relational Level 5.3 Analyzing the Interpretation at the ASF Level 5.4 Analyzing Time-Dependent Interactions at the ASF Level 5.5 Comparing Interpretations --- A Quantitative Analysis 5.6 An Ablation Study Chapter 6 Reasoning from the Relational Level of the Representation 6.1 Introduction 6.2 Identifying the Conceptual Roots 6.3 Explaining the Connections Between Events 6.4 Determining Important Concepts in the Interpretation Graph 6.5 Conceptual Roots and their Role in Summarization Chapter 7 Experiments in Acquiring Knowledge from On-line Corpora 7.1 Introduction 7.2 The Automatic Acquisition of Knowledge from On-line Sources 7.3 The Automatic Construction of the Relational Tier 7.4 The Automatic Construction of the Associational Tier 7.5 How Semantic Memory Evolves in Response to New Input 7.6 Changing the Link Weights 7.7 Implementation Details Chapter 8 An Analysis of the Acquired Knowledge 8.1 An Alternative View of the UnderlyingKnowledge Representation 8.2 Discussion of Soundness of Approach 8.3 An Evaluation of LeMICON's Representation 8.4 Previous Text Systems Revisited 8.5 The Knowledge Acquisition Continuum Chapter 9 Conclusions 9.1 Some Consequences of the Two-Tier Model of Memory 9.2 Associational Representations 9.3 The Universality of ASFs 9.4 Scalability 9.5 Automatic Acquisition of Knowledge 9.6 Building Large-Scale Knowledge Bases 9.7 A Link to Corpus Linguistics 9.8 The Interplay between Computation and Representation 9.9 Limitations Chapter 10 Future Directions 10.1 Expanding The Knowledge Base 10.2 Finding Deeper Semantic Relationships via Corpus Analysis 10.3 Handling Contradictory Input 10.4 Learning New Relationships 10.5 A Basic Level Semantic Encoding 10.6 Child Versus Adult Comprehension Appendix A The ASFs Used in the LeMICON Experiments Appendix B A Formal Analysis of the Dynamics B.1 The Defining Set of Equations B.2 An Analysis of the Defining Equations B.3 The ASF Contribution Appendix C Sample Parsed Input to LeMICON Appendix D Additional Results with SSS D.1 Further Examples of Summarization D.2 Importance Appendix E Proof of the Boundedness of the Measure I Appendix F The Dictionary Trees that Describe the Class ``Space'' References Author Index Subject Index ---------------------------------------------------------------------------- ISBN 0-7923-9487-9 e-mail: Kluwer at world.std.com To order in USA: | To order in Europe: | | Kluwer Academic Publishers, Order Dept. | Kluwer Academic Publishers, Order Dept. | P.O.B. 358 | P.O.B. 322 Accord Station, Hingham, MA 02018-0358 | 3300AH Dordrecht | The Netherlands | Phone: (617) 871-6300 | Phone: 31-77-524-400 FAX: (617) 871-6528 | FAX: 31-78-524-474 ----------------------------------------------------------------------------  From prechelt at ira.uka.de Fri Oct 21 08:51:21 1994 From: prechelt at ira.uka.de (Lutz Prechelt) Date: Fri, 21 Oct 1994 13:51:21 +0100 Subject: Techreport on Proben1 Neural Network benchmark collection Message-ID: <"irafs2.ira.229:21.10.94.12.50.46"@ira.uka.de> FTP-host: archive.cis.ohio-state.edu FTP-filename: /pub/neuroprose/prechelt.bench.ps.Z URL: ftp://archive.cis.ohio-state.edu/pub/neuroprose/prechelt.bench.ps.Z The technical report Proben1 --- A Set of Neural Network Benchmark Problems and Benchmarking Rules is now available for anonymous ftp as ftp.ira.uka.de /pub/papers/techreports/1994/1994-21.ps.Z and as archive.cis.ohio-state.edu /pub/neuroprose/prechelt.bench.ps.Z The report has 38 pages, the file is 158 Kb. The report is the documentation of a benchmark collection that I have prepared. This collection is the first closed and exactly documented benchmark collection specifically made for neural network research. All of its problems are 'real' problems in the sense that the data has not been generated artificially. Most of the problems were taken from the UCI machine learning databases archive. Particular emphasis lies on achieving reproducibility of results, which is difficult with most existing real world data benchmarks. Here is the abstract: Proben1 is a collection of problems for neural network learning in the realm of pattern classification and function approximation plus a set of rules and conventions for carrying out benchmark tests with these or similar problems. Proben1 contains 15 data sets from 12 different domains. All datasets represent realistic problems which could be called diagnosis tasks and all but one consist of real world data. The datasets are all presented in the same simple format, using an attribute representation that can directly be used for neural network training. Along with the datasets, Proben1 defines a set of rules for how to conduct and how to document neural network benchmarking. The purpose of the problem and rule collection is to give researchers easy access to data for the evaluation of their algorithms and networks and to make direct comparison of the published results feasible. This report describes the datasets and the benchmarking rules. It also gives some basic performance measures indicating the difficulty of the various problems. These measures can be used as baselines for comparison. -- Here is a bibtex entry of the report: @techreport{Prechelt94c, author = {Lutz Prechelt}, title = {{PROBEN1} --- {A} Set of Benchmarks and Benchmarking Rules for Neural Network Training Algorithms}, institution = {Fakult\"at f\"ur Informatik, Universit\"at Karlsruhe}, year = {1994}, number = {21/94}, address = {D-76128 Karlsruhe, Germany}, month = sep, note = {Anonymous FTP: /pub/pa\-pers/tech\-reports/1994/1994-21.ps.Z on ftp.ira.uka.de}, } The benchmark collection itself (including the report) is available for anonymous ftp from the directories ftp.ira.uka.de /pub/neuron and ftp.cs.cmu.edu /afs/cs/project/connect/bench/contrib/prechelt in both cases the file name is proben1.tar.gz (ca. 2 Mb) Lutz Lutz Prechelt (email: prechelt at ira.uka.de) | Whenever you Institut fuer Programmstrukturen und Datenorganisation | complicate things, Universitaet Karlsruhe; 76128 Karlsruhe; Germany | they get (Voice: ++49/721/608-4068, FAX: ++49/721/694092) | less simple.  From fogelman at laforia.ibp.fr Fri Oct 21 15:53:41 1994 From: fogelman at laforia.ibp.fr (FOGELMAN Francoise + 33 1 41 28 41 70) Date: Fri, 21 Oct 94 20:53:41 +0100 Subject: Call ICANN'95 Message-ID: <9410211953.AA23128@laforia.ibp.fr> Could you please post the following announcement ? Thanks in advance ***************************************************************************** XXX XXXX X XX XX XX XX XX XXXXX XXXXXX X X X X XXX XX XXX XX XX X XX X X X XXXXX XX X XX XX X XX XXXXX XXXXX X X X X XX XXX XX XXX XX XXX XXX XXXX X X XX XX XX XX XXXX XXXXX PARIS, OCTOBER 9-13, 1995 Maison de la Chimie NEURAL NETWORKS AND THEIR APPLICATIONS ***************************************************************************** SCIENTIFIC CONFERENCE INDUSTRIAL CONFERENCE TUTORIALS & EXHIBITION organized by EUROPEAN NEURAL NETWORK SOCIETY ***************************************************************************** REGISTRATION, INFORMATION ***************************************************************************** Over the last four years, the ENNS - European Neural Network Society - has held its annual conference ICANN in Helsinki (1991), Brighton (1992), Amsterdam (1993) and Sorrento (1994). This conference has become the foremost meeting for the European neural network scientific community. In 1995, ENNS will hold the ICANN meeting in Paris. The format of this conference will include a scientific conference, an industrial conference, tutorials, industrial forums and an industrial exhibition. Our challenge, in organizing this conference, is to achieve the highest scientific quality for papers presented at the scientific conference (there will be a high rejection rate if necessary), together with the most convincing set of applications presented at the industrial conference (only operational, top-level applications will be considered). We thus hope to demonstrate that Neural Networks are indeed a very deep and exciting field of research, as well as a most efficient, profitable technique for the industry. To achieve these goals, we seek contributions from all the scientists, both from academy and industry, who share our interests and our quality requirements. ***************************************************************************** CALL FOR PAPERS The conference will cover the following domains : SCIENTIFIC CONFERENCE * theory * algorithms & architectures * implementations (hardware & software) * cognitive sciences & AI * neurobiology * applications identification & control image processing & vision OCR speech & signal processing prediction optimization INDUSTRIAL CONFERENCE This conference will cover two main categories: on the one hand, descriptions of tools and methods and their use in real-life cases and, on the other hand, descriptions of concrete applications in industry and the sector of services. All fields of application are eligible. Special sessions will be organized on specific areas of industry such as: * banking, finance & insurance * telecommunications * teledetection * process engineering, control and monitoring * oil industry * power industry * food processing * transportation * robotics * speech processing * document processing, OCR, text retrieval & indexing * VLSI & dedicated hardware * forecasting & marketing * technical diagnosis * non destructive testing * medicine * defense LOCATION The conference will be held in la Maison de la Chimie, right in the center of Paris, close by les Invalides. Built in 1707, for Frederic-Maurice de la Tour, Comte d'Auvergne, Lieutenant General to King Louis XIV, the Mansion has today become a Congress Center equipped with all the modern facilities. INSTRUCTIONS TO AUTHORS Length of papers: not exceeding 6 pages in A4 format (i. e. about 8,000 characters). An electronic format will be made available at : ftp lix.polytechnique.fr login: anonymous password : your e-mail address in the directory /pub/ICANN95/out, read file README for instructions. If you want to leave messages or enquiries, you can also use : in the directory /pub/ICANN95/in, read file README for instructions. Seven copies of the papers should reach the Conference Secretariat at the address below by ****** MARCH 20 1995 ***** : ICANN'95 1 avenue Newton bp 207 92 142 CLAMART Cedex France Submitted papers should be accompanied by a cover page giving: * the title of the paper and the author(s) name(s), * the author's address, phone number and extension, fax number and, if possible, e-mail address, * a 10-line abstract together with a list of key-words, * an indication of which conference the paper should be included in: scientific or industrial LANGUAGE Papers submitted for the scientific conference should be in English. Papers submitted for the industrial conference may be either in English or French. TUTORIALS Tutorials will be organized. The Program Committee is open to proposals for tutorials covering industrial applications.Suggestions should describe the content of the tutorial (in 150-200 words) and the instructor's expertise and experience in the field concerned. The deadline for reception is MAY 15 1995. EXHIBITION From fogelman Fri Oct 21 15:36:19 1994 From: fogelman (FOGELMAN Francoise + 33 1 41 28 41 70) Date: Fri, 21 Oct 94 20:36:19 +0100 Subject: ICANN'95 Message-ID: <9410211936.AA23061@laforia.ibp.fr> ***************************************************************************** XXX XXXX X XX XX XX XX XX XXXXX XXXXXX X X X X XXX XX XXX XX XX X XX X X X XXXXX XX X XX XX X XX XXXXX XXXXX X X X X XX XXX XX XXX XX XXX XXX XXXX X X XX XX XX XX XXXX XXXXX PARIS, OCTOBER 9-13, 1995 Maison de la Chimie NEURAL NETWORKS AND THEIR APPLICATIONS ***************************************************************************** SCIENTIFIC CONFERENCE INDUSTRIAL CONFERENCE TUTORIALS & EXHIBITION organized by EUROPEAN NEURAL NETWORK SOCIETY ***************************************************************************** INFORMATION ***************************************************************************** Over the last four years, the ENNS - European Neural Network Society - has held its annual conference ICANN in Helsinki (1991), Brighton (1992), Amsterdam (1993) and Sorrento (1994). This conference has become the foremost meeting for the European neural network scientific community. In 1995, ENNS will hold the ICANN meeting in Paris. The format of this conference will include a scientific conference, an industrial conference, tutorials, industrial forums and an industrial exhibition. Our challenge, in organizing this conference, is to achieve the highest scientific quality for papers presented at the scientific conference (through a strict selection procedure), together with the most convincing set of applications presented at the industrial conference (only operational, top-level applications will be considered). Papers should stress the rationale of the Neural Network approach and provide a comparison with other techniques. We thus hope to demonstrate that Neural Networks are indeed a very deep and exciting field of research, as well as a most efficient, profitable technique for the industry. To achieve these goals, we seek contributions from all the scientists, both from academy and industry, who share our interests and our quality requirements. ***************************************************************************** CALL FOR PAPERS The conference will cover the following domains : SCIENTIFIC CONFERENCE * theory * algorithms & architectures * implementations (hardware & software) * cognitive sciences & AI * neurobiology * applications identification & control image processing & vision OCR speech & signal processing prediction optimization INDUSTRIAL CONFERENCE This conference will cover two main categories: on the one hand, descriptions of tools and methods and their use in real-life cases and, on the other, descriptions of concrete applications in industry and the sector of services. All fields of application are eligible. Special sessions will be organized on specific areas of industry such as: * banking, finance & insurance * telecommunications * teledetection * process engineering, control and monitoring * oil industry * power industry * food processing * transportation * robotics * speech processing * document processing, OCR, text retrieval & indexing * VLSI & dedicated hardware * forecasting & marketing * technical diagnosis * non destructive testing * medicine * defense LOCATION The conference will be held in la Maison de la Chimie, right in the center of Paris, near les Invalides. Built in 1707, for Frederic-Maurice de la Tour, Comte d'Auvergne, Lieutenant General to King Louis XIV, the Mansion has today become a Congress Center equipped with all the modern facilities. INSTRUCTIONS TO AUTHORS Length of papers: not exceeding 6 pages in A4 format (i. e. about 8,000 characters). An electronic format will be made available at : ftp lix.polytechnique.fr login: anonymous password : your e-mail address in the directory /pub/ICANN95/out, read file README for instructions. If you want to leave messages or enquiries, you can also use : in the directory /pub/ICANN95/in, read file README for instructions. Seven copies of the papers should reach the Conference Secretariat at the address below by ****** MARCH 20 1995 ***** : ICANN'95 1 avenue Newton bp 207 92 142 CLAMART Cedex France Submitted papers should be accompanied by a cover page giving: * the title of the paper and the author(s) name(s), * the author's address, phone number and extension, fax number and, if possible, e-mail address, * a 10-line abstract together with a list of key-words, * an indication of which conference the paper should be included in: scientific or industrial LANGUAGE Papers submitted for the scientific conference should be in English. Papers submitted for the industrial conference may be either in English or French. TUTORIALS Tutorials will be organized. The Program Committee is open to proposals for tutorials covering industrial applications. Suggestions should describe the content of the tutorial (in 150-200 words) and the instructor's expertise and experience in the field concerned. The deadline for reception is MAY 15 1995. EXHIBITION >From October 11-13, 1995, the Conference will host a trade fair of commercially available products relating to neural network tools and applications. In addition, advanced prototypes of tools and applications developed by public sector research organizations will be demonstrated. To receive a complete exhibitor's package, please contact the Conference Secretariat at the address indicated. ***************************************************************************** TEAR OFF HERE ***************************************************************************** INFORMATION FORM to be returned to: ICANN'95 1 avenue Newton bp 207 92 142 CLAMART Cedex France ICANN ' 95 Paris, October 9-13, 1995 Last name : .......................................................... First Name : ........................................................ Organization or company : ............................................ ...................................................................... ...................................................................... Postal code/Zip code : ............................................... City : ............................................................... Country : ............................................................ Tel : .................................Fax : ......................... Electronic mail:...................................................... * I wish to attend the O Scientific conference O Industrial conference * I intend to exhibit * I intend to submit a paper Provisional title.................................................... Author (s) : ........................................................ Brief outline of the subject : ...................................... ..................................................................... Category : * Scientific conference O Theory O Algorithms & architectures O Implementations O Cognitive sciences & AI O Neurobiology O Applications ( please specify) * Industrial conference O Tools O Techniques O Applications ( please specify) ***************************************************************************** TEAR OFF HERE ***************************************************************************** STEERING COMMITTEE Chair F. Fogelman - Sligos (Paris, F) Scientific Program co-chairs G. Dreyfus - ESPCI (Paris, F) M. Weinfeld - Ecole Polytechnique (Palaiseau, F) Industrial Program chair P. Corsi - CEC (Brussels, B) Tutorials & Publications chair P. Gallinari - Universite P.& M.Curie (Paris, F) SCIENTIFIC PROGRAM COMMITTEE (Preliminary) I. Aleksander (UK); L.B. Almeida (P); S.I. Amari (J); E. Bienenstock (USA); C. Bishop (UK); L. Bottou (F); J. M. Buhmann (D); S. Canu (F); V. Cerny (SL); M. Cosnard (F); R. De Mori (CAN); R. Eckmiller (D); N. Franceschini (F); S. Gielen (NL); J. Herault (F); M. Jordan (USA); D. Kayser (F); T. Kohonen (SF); A. Lansner (S); Z. Li (USA); L. Ljung (S); C. von der Malsburg (D); S. Marcos (F); P.Morasso (I); J.P.Nadal(F); E. Oja (SF); P. Peretto (F); C. Peterson (S); L. Personnaz (F); R. Pfeiffer (CH); T. Poggio (USA); P. Puget (F); S. Raudys (LT); H. Ritter (D); M. Saerens ( B); W. von Seelen (D); J.J. Slotine (USA); S. Solla (DK); J.G. Taylor (GB); C. Torras (E); B. Victorri (F); A. Weigend (USA). INDUSTRIAL PROGRAM COMMITTEE (Preliminary) M. Boda (S); B. Braunschweig (F); C. Bishop (UK); J.P. Corriou (F); M. Duranton (F); A. Germond (CH); I. Guyon (USA); P. Refenes (UK); S. Thiria (F); C. Wellekens (B); B. Wiggins (UK). *****************************************************************************  From singer at CS.HUJI.AC.IL Sun Oct 23 07:16:28 1994 From: singer at CS.HUJI.AC.IL (Yoram Singer) Date: Sun, 23 Oct 1994 13:16:28 +0200 Subject: thesis available (corrections) Message-ID: <199410231116.AA01484@minuet.cs.huji.ac.il> 1. The thesis "Unsupervised Learning of Cell Activities in the Associate Cortex of Behaving Monkeys, Using Hidden Markov Models" by Itay Gat was supervised by Dr. Naftali Tishby (Institute of Computer Science and Center for Neural Computation, Hebrew University) and Prof. Moshe Abeles (School of Medicine and Center for Neural Computation, Hebrew University). 2. Due to a major power breakdown the cs.huji.ac.il ftp server was down from Thursday afternoon to Sunday morning. The server is now up and operating. We apologize for the inconvenient. Itay Gat & Yoram Singer Institute of Computer Science The Hebrew University, Israel  From thrun at uran.informatik.uni-bonn.de Sun Oct 23 18:14:22 1994 From: thrun at uran.informatik.uni-bonn.de (Sebastian Thrun) Date: Sun, 23 Oct 1994 23:14:22 +0100 Subject: Paper available Message-ID: <199410232214.XAA12637@carbon.informatik.uni-bonn.de> This is to announce the following technical report (22 pages): LEARNING ONE MORE THING by Sebastian Thrun and Tom M. Mitchell Most research on machine learning has focused on scenarios in which a learner faces a single, isolated learning task. The lifelong learning framework assumes instead that the learner encounters a multitude of related learning tasks over its lifetime, providing the opportunity for the transfer of knowledge. This paper studies lifelong learning in the context of binary classification. It presents the invariance approach, in which knowledge is transferred via a learned model of the invariances of the domain. Results on learning to recognize objects from color images demonstrate superior generalization capabilities if invariances are learned and used to bias subsequent learning. ----------------------------------------------------------------- The paper can be retrieved via anonymous ftp by following these instructions: unix> ftp reports.adm.cs.cmu.edu ftp:name> anonymous Password:> mickey at mouse.gov ftp> cd 1994 ftp> get CMU-CS-94-184.ps (sorry, it's not compressed) ftp> bye unix> lpr CMU-CS-94-184.ps The paper uses Backprop/Tangentprop as the main learning engine, but it also addresses general machine learning issues. Your feedback is very much appreciated (thrun at cs.cmu.edu). Sebastian  From john at dcs.rhbnc.ac.uk Tue Oct 25 07:42:21 1994 From: john at dcs.rhbnc.ac.uk (john@dcs.rhbnc.ac.uk) Date: Tue, 25 Oct 94 11:42:21 +0000 Subject: Technical Report Series in Neural and Computational Learning Message-ID: <7985.9410251142@platon.cs.rhbnc.ac.uk> The European Community ESPRIT Working Group in Neural and Computational Learning Theory (NeuroCOLT): two new reports available ---------------------------------------- NeuroCOLT Technical Report NC-TR-94-009: ---------------------------------------- Complexity Issues in Discrete Hopfield Networks by Patrik Flor\'{e}en and Pekka Orponen University of Helsinki, Department of Computer Science P. O. Box 26, FIN-00014 University of Helsinki, Finland Abstract: We survey some aspects of the computational complexity theory of discrete-time and discrete-state Hopfield networks. The emphasis is on topics that are not adequately covered by the existing survey literature, most significantly: 1. the known upper and lower bounds for the convergence times of Hopfield nets (here we consider mainly worst-case results); 2. the power of Hopfield nets as general computing devices (as opposed to their applications to associative memory and optimization); 3. the complexity of the synthesis (``learning'') and analysis problems related to Hopfield nets as associative memories. ---------------------------------------- NeuroCOLT Technical Report NC-TR-94-013: ---------------------------------------- by Martin Anthony, Department of Mathematics, The London School of Economics and Political Science, Houghton Street, London WC2A 2AE, United Kingdom and Peter Bartlett, Department of Systems Engineering, Research School of Information Sciences and Engineering, The Australian National University, Canberra, 0200 Australia Abstract: In this paper, we study a statistical property of classes of real-valued functions that we call approximation from interpolated examples. We derive a characterization of function classes that have this property, in terms of their `fat-shattering function', a notion that has proven useful in computational learning theory. We discuss the implications for function learning of approximation from interpolated examples. Specifically, it can be interpreted as a problem of learning real-valued functions from random examples in which we require satisfactory performance from every algorithm that returns a function which approximately interpolates the training examples. ----------------------- The Report NC-TR-94-013 can be accessed and printed as follows % ftp cscx.cs.rhbnc.ac.uk (134.219.200.45) Name: anonymous password: your full email address ftp> cd pub/neurocolt/tech_reports ftp> binary ftp> get nc-tr-94-013.ps.Z ftp> bye % zcat nc-tr-94-013.ps.Z | lpr -l Likewise for NC-TR-94-009. Uncompressed versions of the postscript files have also been left for anyone not having an uncompress facility. A full list of the currently available Technical Reports in the Series is held in a file `abstracts' in the same directory. Best wishes John Shawe-Taylor  From plaut at cmu.edu Tue Oct 25 09:16:49 1994 From: plaut at cmu.edu (David Plaut) Date: Tue, 25 Oct 1994 09:16:49 -0400 Subject: Postdoctoral position available Message-ID: <4153.783091009@crab.psy.cmu.edu> POSTDOCTORAL FELLOW IN CONNECTIONIST NEUROPSYCHOLOGY OF READING AND LANGUAGE I have funding for a postdoctoral fellow to collaborate with me in the area of connectionist modeling of cognitive processes in reading and language and their breakdown following brain damage. It is a two-year position supported by the Center for the Neural Basis of Cognition of Carnegie Mellon University and the University of Pittsburgh, and located in the Department of Psychology at Carnegie Mellon. Applicants should have either expertise in connectionist modeling, or expertise in the cognitive psychology/neuropsychology of reading and language combined with some experience in modeling. Please send a vita, a brief description of research experience and interests, copies of representative publications, and three letters of reference to David Plaut, Department of Psychology, Carnegie Mellon University, Pittsburgh PA, 15213-3890. Consideration of applications will begin January 1 and continue until the position is filled. Carnegie Mellon is an affirmative action/equal opportunity employer. =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= David Plaut plaut at cmu.edu "Doubt is not a pleasant Department of Psychology 412/268-5145 condition, but certainty Carnegie Mellon University 412/268-5060 (FAX) is an absurd one." Pittsburgh, PA 15213-3890 345H Baker Hall --Voltaire =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=  From plunkett at psy.ox.ac.uk Tue Oct 25 09:26:37 1994 From: plunkett at psy.ox.ac.uk (Kim Plunkett) Date: Tue, 25 Oct 1994 13:26:37 GMT Subject: No subject Message-ID: <199410251326.NAA22996@unicorn.psych.ox.ac.uk> Oxford McDonnell-Pew Centre for Cognitive NeuroScience Neural Network Scientist Department of Experimental Psychology University of Oxford The McDonnell-Pew Centre for Cognitive Neuroscience wish to appoint a scientist to assist in the establishment of a Neu- roComputing Centre for Cognitive Scientists and NeuroScien- tists. The person appointed would be expected to provide advice on a wide range of neural network simulators running on Dec Alpha machines, and also to develop neural network software as part of a demonstration package to be used by cognitive neuroscientists and cognitive scientists. The successful applicant will be well-versed in C (or C++) pro- gramming, the X-windows interface and have a working knowledge of neural networks. The appointment, to start as soon as possible, is for one year and will be made at the appropriate level on the academically related RS1A scale (GBP 13,941 -> 20,953). Further information can be obtained from: Kim Plunkett (plunkett at psy.ox.ac.uk) Tel: 0865-271398 Ray Bellis (rpb at psy.ox.ac.uk) Tel: 0865-271359 Edmund Rolls (erolls at vax.ox.ac.uk) Tel: 0865-271348 all at: Department of Experimental Psychology University of Oxford South Parks Road Oxford OX1 3UD Applicants should send a full CV to Miss Lesley Court McDonnell-Pew Centre for Cognitive NeuroScience Department of Experimental Psychology South Parks Road Oxford OX1 3UD by November 15th 1994.  From dyyeung at cs.ust.hk Wed Oct 26 15:31:24 1994 From: dyyeung at cs.ust.hk (Dr. D.Y. Yeung) Date: Wed, 26 Oct 94 15:31:24 HKT Subject: Faculty Openings at HKUST -- a relatively new research university in Hong Kong Message-ID: <9410260731.AA03406@cs.ust.hk> THE HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY Department of Computer Science The Department of Computer Science will have at least 10 faculty positions open AT ALL LEVELS for the 1995-96 academic year. Applications for senior-level positions are particularly solicited. The department began its first classes in October, 1991. It currently has 41 faculty members recruited from major universities and research institutions around the world and 430 undergraduate and 95 postgraduate students. We have active research groups in the areas of artificial intelligence, computer engineering, data and knowledge base management, software technology, and theoretical computer science. We are looking for new faculty with research interests in these areas as well as in the areas of Chinese (or multi-lingual) computing, natural language processing, neural networks, and robotics. Research funding is available through government agencies and industry-sponsored research institutes at the university, such as the Hong Kong Telecom Institute of Information Technology and the Sino Software Research Centre. The Hong Kong University of Science and Technology is a publicly-funded research university. It has Schools of Science, Engineering, Business & Management, and Humanities and Social Science. It is located on a new, well-equipped coastal campus overlooking the spectacular Clear Water Bay. Students admitted to the department rank among the top 10% of Hong Kong's secondary school graduates. The medium of instruction is English. Salary and benefits are competitive. Initial appointments will normally be on a three-year contract which is renewable subject to mutual agreement. A gratuity of an amount equal to 25% of the total basic salary received will be payable upon contract completion. Shorter-term visiting positions are also available for senior applicants. Applicants should have an earned Ph.D. and high potential in teaching and research. Senior applicants must have exceptional research records. Applications/nominations should be sent with a curriculum vitae together with names of at least three references to: Prof. Vincent Y. Shen, Head Department of Computer Science The Hong Kong University of Science & Technology Clear Water Bay, Kowloon HONG KONG Fax No. : (852) 358-2679 E-mail : vshen at cs.ust.hk Applications will be evaluated immediately upon receipt. Maximum consideration will be given to applications received by December 31, 1994.  From lxu at cs.cuhk.hk Wed Oct 26 10:21:47 1994 From: lxu at cs.cuhk.hk (Dr. Xu Lei) Date: Wed, 26 Oct 94 22:21:47 +0800 Subject: A NIPS*94 WORKSHOP Message-ID: <9410261421.AA16797@cucs18.cs.cuhk.hk> A NIPS*94 POST CONFERENCE WORKSHOP UNSUPERVISED LEARNING RULES AND VISUAL PROCESSING Lei Xu$^1$, Zhaoping Li$^2$ and Laiwan Chan$^1$ 1. The Chinese University of Hong Kong 2. Hong Kong University of Science and Technology There are three major types of unsupervised learning rules: competitive learning or vector quantization type, information preserving or {\em Principal Component Analysis (PCA)} type, and the self-organizing topological map type. All of them are closely related to visual processing. For instance, they are used to interpret the developments of orientation and other feature selective cells, as well as development of cortical retinotopic maps such as ocular dominance and orientation columns. The development of the study of learning and the understanding of visual processing facilitate each other. Recent years, a number of advances have been made in both in the two areas. For instance, in the area of unsupervised learning, (1) numerous algorithms for competitive learning, PCA learning, and self-organizing maps have been proposed; (2) several new theories and principles, like maximum coherence, minimum description length, finite mixtures with EM learning, statistical physics, Bayesian theory, exploratory projection pursuit, and local PCA, have been developed; (3) theories for unifying various unsupervised learning rules (e.g., multisets modeling learning theory) have been explored. In the area of visual processing, more knowledge is being gathered experimentally about how visual development can be preserved or altered by neural activities, neural transmitters/receptors, and the visual environment etc, providing the bases and constraints for various learning rules and motivating new learning rule studies. In addition, there has been more theoretical understandings on the dependence of the visual processing units on the visual input environment, supporting the rationality of unsupervised learning. The purpose of this workshop is twofolds: (1) to summarize the advances on unsupervised learning and to discuss whether these advances can help the investigation on visual processing system; (2) to screening the current results on visual processing and to check if they can motivate or provide some hints on developing unsupervised learning theories. The targeted groups of participants are researchers working in either or both the area of learning and the study of visual processing. ----------------------------------------------------------------------------- NIPS*94 WORKSHOP PROGRAM The Friday morning session 7:30-9:30AM, Dec.2, chairperson Lei Xu 1. "Time-Domain Solutions of Oja's Equations", John Wyatt and Ibrahim Elfadel (MIT) 2. "Kmeans Performs Newton Optimization", Leon Bottou (Neuristique Paris) and Yoshua Bengio (University of Montreal) 3. "Multisets Modeling Learning: An Unified Framework for Unsupervised Learning", Lei Xu (The Chinese University of Hong Kong and Peking University) 4. "Information Theory Motivation For Projection Pursuit", Nathan Intrator (Tel-Aviv University) 5. "The Helmholtz Machine", Peter Dayan (University of Toronto) The Friday evening session, chairperson 4:30-6:30PM, Dec.2, Zhaoping Li 1. "Predictability Minimization And Visual Processing", Juergen Schmidhuber (Technische Universitaet Muenchen) 2. "Non-linear, Non-gaussian Information Maximisation: Why It's More Useful", Tony Bell (Salk Institute) 3. "Understanding The Visual Cortical Coding From Visual Input Statistics", Zhaoping Li (Hong Kong University of Science and Technology) 4. "Formation Of Orientation And Ocular Dominance In Macaque Striate Cortex", Klaus Obermayer (Universitaet Bielefel) 5. "Putative Functional Roles Of Self-organized Lateral Connectivity In The Primary Visual Cortex", Joseph Sirosh (University of Texas at Austin) The Saturday morning session 7:30-9:30AM, Dec.3, chairperson, Laiwan Chan 1. "Density Estimation with a Hybrid of Neural Networks and Gaussian Mixtures", Yoshua Bengio (University of Montreal) 2. "Learning Object Models through Domain-Specific Distance Measures" Eric Mjolsness (UCSD) and Steve Gold (Yale University) 3. "Auto-associative Learning of On-line Handwriting Using Recurrent Neural Networks", Dit-Yan Yeung (Hong Kong University of Science and Technology) 4. "Training Mixtures of Gaussians with Deficient Data", Volker Tresp (Siemens AG, Central Research) 5. "A Fast Method for Activating Competitive Self-Organizing Neural-Networks", George F. Harpur and Richard W. Prager (Cambridge University) The Saturday evening session 4:30-6:30PM, Dec.3, chairperson, Lei Xu 1. "Neuromodulatory Mechanisms For Regulation Of Cortical Self-organization", Michael E. Hasselmo (Harvard University) 2. "Learning To Cluster Visual Scenes With Contextual Modulation", Sue Becker (McMaster University) 3. "Invisibility in Vision: Occlusion, Motion, Grouping, and Self-Organization", Jonathan A. Marshall (University of North Carolina at Chapel Hill) 4. "A Comparative Study on Receptive Filters by PCA Learning and Gabor Functions", Irwin King and Lei Xu (The Chinese University of Hong Kong) 5. "Detection of Visual Feature Locations with a Growing Neural Gas Network" Bernd Fritzke (Ruhr-Universitaet Bochum)  From kolen-j at cis.ohio-state.edu Wed Oct 26 17:20:53 1994 From: kolen-j at cis.ohio-state.edu (john kolen) Date: Wed, 26 Oct 1994 17:20:53 -0400 Subject: Thesis announcement Message-ID: <199410262120.RAA16138@squirt.cis.ohio-state.edu> Many of you already know of its existance, but this is for the rest of the NN community. If you plan to retrieve this document make sure you read the warning at the end of this message. Ftp-site: cis.ohio-state.edu Ftp-directory: pub/neuroprose/Thesis/kolen.thesis.ps.Z PrintedPages: 191 Exploring the Computational Capabilities of Recurrent Neural Networks John F. Kolen While many researchers have successfully organized neural networks into structures displaying universal computational capability, most have ignored the more daunting endeavor of identifying ongoing computation, or information processing, as it occurs. My thesis addresses this problem as it relates to the understanding of the information processing capabilities of recurrent neural networks. I have isolated three important facets of recurrent neural networks that contribute to their computational power: internal dynamics, input modulation, and output generation. Theories of dynamical systems and iterated function systems have proven crucial in developing an understanding of these facets. With respect to my original question of identifying ongoing computation, the evidence suggests that the any observed computational powers of neural networks arise not from the network itself, but our application of it as a symbol processing device. If we consider recurrent neural networks as the a cognitive e. coli, this dissertation is a step toward understanding the nature cognition and intelligence. ********* WARNING *********** This document contains Level 2 PostScript commands that will not work on Level 1 printers (i.e. old LaserWriters and old versions of ghostview).  From sassk at macaulay-land-use.scot-agric-res-inst.ac.uk Thu Oct 27 09:03:06 1994 From: sassk at macaulay-land-use.scot-agric-res-inst.ac.uk (Jim Kay) Date: Thu, 27 Oct 94 13:03:06 GMT Subject: Stats/ANN Workshop Message-ID: <17956.9410271303@mluri.sari.ac.uk> STATISTICS AND NEURAL NETWORKS A research workshop on the above topic will be held in Edinburgh under the auspices of the International Centre for Mathematical Sciences. Invited speakers will include Leo Breiman (Berkeley), Phil Brown (Liverpool), David Hand (Open University), Trevor Hastie (ATT and Stanford), Nathan Intrator (Tel Aviv), Michael Jordan (MIT), Jim Kay (SASS), David Lowe (Aston), David Mackay (Cambridge), Radford Neal (Toronto) and Brian Ripley (Oxford). The workshop will take place on April 19-20, 1995, and will be followed by an Open Meeting on April 21, 1995. The meetings will form part of the Edinburgh Science Festival. Although participation in the Workshop will be predominantly by invitation, there will be a small number of places for direct applicants, with some priority given to research students who apply before November 30, 1994. For details contact either J. W. Kay (SASS, Macaulay Land Use Research Institute, Craigiebuckler, Aberdeen, AB9 2QJ; sassk at mluri.sari.ac.uk) or D. M. Titterington (Department of Statistics, University of Glasgow, Glasgow G12 8QQ; mike at stats.gla.ac.uk) as soon as possible. Applicants are welcome to use the attached electronic form. However, in view of the limited numbers at the Workshop and its strategic nature, not all applicants may be successful in obtaining places. Every effort will be made to notify applicants of the success, or otherwise, of their application by mid-December, 1994. =============================================================== STATISTICS AND NEURAL NETWORKS WORKSHOP: APRIL 19 - 20, 1994 International Centre for Mathematical Sciences 14 India Street, Edinburgh EH3 6EZ PARTICIPATION AND ACCOMMODATION REQUEST FORM TITLE: FIRST NAME: SECOND NAME: INSTITUTION: ADDRESS: TELEPHONE: FAX: EMAIL ADDRESS: DATE OF ARRIVAL: DATE OF DEPARTURE: (Note that there will be an Open Meeting on April 21, for which a form will follow soon) DETAILS OF ACCOMPANYING FAMILY MEMBERS (NUMBER, RELATIONS, AND AGES, IF CHILDREN): TYPE OF ACCOMMODATION REQUIRED (B&B about 20 pounds per person per night, Hotels about 25 pounds and upwards) ANY ADDITIONAL COMMENTS: PLEASE RETURN AS SOON AS POSSIBLE WITH REGISTRATION FEE OF 15 POUNDS (10 POUNDS FOR POST-GRADUATE STUDENTS) TO : Louise Williamson ICMS Tel:0131-220-1777 Fax:0131-220-1053 Email:icms at maths.ed.ac.uk * Please make cheques payable to HERIOT-WATT UNIVERSITY - ICMS * =====================================================  From dhw at santafe.edu Thu Oct 27 16:05:12 1994 From: dhw at santafe.edu (David Wolpert) Date: Thu, 27 Oct 94 14:05:12 MDT Subject: Paper announcement Message-ID: <9410272005.AA29375@sfi.santafe.edu> *** PAPER ANNOUNCEMENT *** *** DO NOT FORWARD TO OTHER LISTS/GROUPS *** Reconciling Bayesian and non-Bayesian analysis. by D. Wolpert. 8 pages long. To appear in "Maximum Entropy and Bayesian Methods", G. Heidberder (Ed.) Abstract: This paper shows that when one extends Bayesian analysis to distinguish the truth from one's guess for the truth, one gains a broader perspective which allows the inclusion of non-Bayesian formalisms. This perspective shows how it is possible for non-Bayesian techniques to perform well, despite their handicaps. It also highlights some difficulties with the ``degree of belief" interpretation of probability. *** This file can be retrieved by anonymous ftp to ftp.santafe.edu. Once logged in, go to pub/dhw_ftp. The file is either maxent.93.reconciling.ps.Z (binary; compressed postscript) or maxent.93.reconciling.ps.Z.encoded (ascii; uuencoded compressed postscript). If any problems arise, please contact me. David Wolpert The Santa Fe Institute 1399 Hyde Park Road Santa Fe, NM, 87501, USA (505) 984-8800 (voice); (505) 982-0565 (FAX). dhw at santafe.edu  From dhw at santafe.edu Wed Oct 26 18:04:23 1994 From: dhw at santafe.edu (David Wolpert) Date: Wed, 26 Oct 94 16:04:23 MDT Subject: Book announcement Message-ID: <9410262204.AA20883@sfi.santafe.edu> ************************************************************************* *** BOOK ANNOUNCEMENT *** Please *DO* forward to other list/groups. ************************************************************************* TITLE: The Mathematics of Generalization: Proceedings of the SFI/CNLS Workshop on Formal Approaches to Supervised Learning Edited by D. Wolpert Other (first) authors: L. Breiman P. Cheeseman J. Denker T. Dietterich D. Haussler G. Hinton S. Nowlan N. Tishby G. Wahba ======================================================================= Table of Contents: Reflections After Referring Papers for NIPS Leo Breiman The Probably Approximately Correct (PAC) and Other Learning Models David Haussler and Manfred Warmuth Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications David Haussler The Relationshop Between PAC, the Statistical Physics Framework, the Bayesian Framework, and the VC Framework {a heavily revised version of a paper that was posted to connectionist.net about six months ago} David H. Wolpert Statistical Physics Models of Supervised Learning Naftali Tishby On Exhaustive Learning David H. Wolpert and Alan S. Lapedes A Study of Maximal-Coverage Learning Algorithms Hussein Almuallim and Tom Dietterich On Bayesian Model Selection Peter Cheeseman Soft Classification, a.k.a. Risk Estimation, via Penalized Log Likelihood and Smoothing Spline Analysis of Variance Grace Wahba, Chong Gu, Yuedong Wang, and Richard Chappell Current Research Leo Brieman Preface to Simplifying Neural Networks by Soft Weight Sharing Geoffrey E. Hinton and Steven Nowlan Simplifying Neural Networks by Soft Weight Sharing Geoffrey E. Hinton and Steven Nowlan Error-Correcting Output Codes: A General Method for Improving Multiclass Inductive Learning Programs Thomas G. Dietterich and Ghulum Bakiri Image Segmentation and Recognition John S. Denker and Christopher C. J. Burges =========================================================== This book grew out of a workshop held under the auspices of the Center for Non-linear Studies at Los Alamos and the Santa Fe Institute. The idea for the workshop arose from a perception that there were many different fields that address supervised learning, but by and large these fields were not communicating with one another. (Examples of such fields are neural nets, conventional Bayesian statistics, conventional sampling theory statistics, computational learning theory, AI, and machine learning.) In particular, there were many different mathematical frameworks for addressing supervised learning. All had their own jargon, their own concerns, and their own results. And for the most part they weren't interacting. This was clearly a less than optimal state of affairs; we all have much to learn from one another, not only in terms of raw mathematical results, but also (perhaps more importantly) in perceptions of what the crucial issues are and how they should be addressed. Unfortunately, although it seems that this problem is abating, the rate of improvement is quite small. It seems possible that a general lack of communication amongst its practitioners will characterize supervised learning theory for some time to come. The purpose of the workshop was try to (begin to) rectify this situation. A small group of researchers from several of the different supervised learning fields was brought together and, in effect, forced to mingle. The format of the workshop was an intensive two-day session of talks and discussion. This volume is an attempt to try to replicate the success of the workshop in a broader context. Its purpose is to do for the reader what the workshop did for its participants: help a practitioner in one of the fields that make up supervised learning become acquainted with the relevant work by his or her colleagues in other fields. Obviously (and unfortunately) it isn't possible to duplicate in a reader of a book the experience of "an intensive two-day session .. (of being) forced to mingle ... (with) researchers from different fields". Given the different format, slightly different means are needed to achieve the same ends. Accordingly, it was decided that the papers in this volume should not so much be a formal compendium of the talks presented at the workshop as an overview of the work being performed by the researchers who attended the workshop. Some of the work represented in these papers hadn't even been completed at the time of the workshop. Some of the other papers are reprints of work published shortly before or soon after the workshop. However all of the papers were chosen by their authors with the same goal in mind: to help those from other supervised learning fields get acquainted with the lay of those authors' lands. Moreover, the instructions to the authors were that they should not try to provide tutorials on their individual fields. (There are many other sources for such tutorials.) Rather they should present current cutting-edge perspectives and work that provide an intuitive understanding of what their field "is all about". =========================================================== The order numbers are 40985 for the hardcover and 40983 for the paperback. The prices are: Paperback 0-201-40983-6 $31.25 Hardcover 0-201-40985-2 $59.25 It is recommended that people order through their home institutions (book stores or libraries) which may have a contract or working relationship with the publisher, Addison-Wesley. Otherwise they can call (800) 447-2226 to order by credit card. Alternatively, they can pay by check by writing to Advanced Book Marketing Addison-Wesley Publishing One Jacob Way Reading, MA 01867, USA.  From michael at imib.rwth-aachen.de Fri Oct 28 04:18:53 1994 From: michael at imib.rwth-aachen.de (Michael Egmont-Petersen #Alwd#) Date: Fri, 28 Oct 1994 09:18:53 +0100 Subject: Special issue of Artificial Intelligence in Medicine: Neurocomputing Message-ID: <9410280818.AA13164@tolkien> ARTIFICIAL INTELLIGENCE IN MEDICINE Special issue: Neural computing in medicine October 1994 Volume 6 Number 5 Editorial: Neural computing in medicine N. Ezquerra, A. Pazos Papers: On the quality of neural net classifiers M. Egmont-Petersen, J.L. Talmon, J. Brender and P. McNair A neural model of cortical map reorganization following a focal lesion S.L. Armentrout, J.A. Reggia and M. Weinrich Identifying the measurement noise in glaucomatous testing: An artificial neural network approach X. Liu, G. Cheng and J.X. Wu On using feedforward neural networks for clinical diagnostic tasks G. Dorffner and G. Porenta Removing the assumption of conditional independence from Bayesian decision models by using artificial neural networks: Some practical techniques and a case study Y.-C. Wu and D.H. Gustafson ----- SUBSCRIPTION Elsevier Science B.V. Journal Department P.O. Box 211 1000 AE Amsterdam The Netherlands Tel. +31-20-5803642 Fax +31-20-5803598 -----  From john at dcs.rhbnc.ac.uk Fri Oct 28 13:08:09 1994 From: john at dcs.rhbnc.ac.uk (john@dcs.rhbnc.ac.uk) Date: Fri, 28 Oct 94 17:08:09 +0000 Subject: EuroCOLT Proceedings Message-ID: <22863.9410281708@platon.cs.rhbnc.ac.uk> The proceedings of the first European Conference on Computational Learning Theory (EuroCOLT'93) are now available for purchase. The contents are attached. The purchasing details are as follows: The price of the book is 60.00. Address where to send orders: CWO Department, Oxford University Press, Saxon Way West, Corby, Northants. NN18 9ES. Phone: 0536 454-534 Fax: 0536 746-337 Many thanks John Shawe-Taylor ------------- @inproceedings{m-oclnn-93 , author = "W. Maass" , title = "On the Complexity of Learning on Neural Nets" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "1--17" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{fp-sndclt-93 , author = "M. Frazier and L. Pitt" , title = "Some New Directions in Computational Learning Theory" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "19--32" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{v-nmcf-93 , author = "L. Valiant" , title = "A Neuroidal Model for Cognitive Functions" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "2" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{kmu-lrle-93 , author = "J. Kivinen and H. Mannila and E. Ukkonen" , title = "Learning Rules with Local Exceptions" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "35--46" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{gm-olsdpnc-93 , author = "M. Golea and M. Marchand" , title = "On Learning Simple Deterministic and Probabilistic Neural Concepts" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "47--60" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{f-lucp-93 , author = "P. Fischer" , title = "Learning Unions of Convex Polygons" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "61--67" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{h-otsnnsn-93 , author = "T. Heged{\"u}s" , title = "On Training Simple Neural Networks and Small-weight Neurons" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "69--82" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{s-bnelf-93 , author = "H.U. Simon" , title = "Bounds on the Number of Examples needed for Learning Functions" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "83--94" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{ast-vgfcas-93 , author = "M. Anthony and J. Shawe-Taylor" , title = "Valid Generalisation of Functions from Close Approximations on a Sample" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "94--108" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{kw-uepco-93 , author = "J. Kivinen and M. Warmuth" , title = "Using Experts for Predicting Continuous Outcomes" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "109--120" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{pr-rdnffpl-93 , author = "K. Pillaipakkamnatt and V. Raghavan" , title = "Read-twice DNF Formulas are Properly Learnable" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "121--132" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{afhmh-tenasl-93 , author = "F. Ameur and P. Fischer and K.U. H{\"o}ffgen and F. Meyer auf der Heide" , title = "Trial and Error: a New Approach to Space-bounded Learning" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "133--144" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{ap-ukldlt-93 , author = "S. Anoulova and S. P{\"o}lt" , title = "Using Kullback-Leibler Divergence in Learning Theory" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "145--156" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{s-llrwmlp-93 , author = "A. Saoudi" , title = "Learning Local and Recognizable $\omega$-languages and Monadic Logic Programs" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "157--169" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{wsz-cpl-93 , author = "R. Wiehagen and C.H. Smith and T. Zeugmann" , title = "Classification of Predicates and Languages" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "171--181" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{w-tnnlpu-93 , author = "H. Wiklicky" , title = "The Neural Network Loading Problem is Undecidable" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "183--192" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{g-opeq-93 , author = "R. Gavald{\`a}" , title = "On the Power of Equivalence Queries" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "193--203" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{cbfhw-opcs-93 , author = "N. Cesa-Bianchi and Y. Freund and D. P. Helmbold and M. Warmuth" , title = "On-line Prediction and Conversion Strategies" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "205--216" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{y-lnsrsrfp-93 , author = "K. Yamanishi" , title = "Learning Non-parametric Smooth Rules by Stochastic Rules with Finite Partitioning" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "217--227" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{p-issbpab-93 , author = "S. P{\"o}lt" , title = "Improved Sample Size Bounds for PAB-decisions" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "229--239" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" }  From koza at CS.Stanford.EDU Fri Oct 28 23:43:48 1994 From: koza at CS.Stanford.EDU (John Koza) Date: Fri, 28 Oct 94 20:43:48 PDT Subject: Architecture-Altering Operations in Genetic Programming Message-ID: <CMM.0.90.4.783402228.koza@Sunburn.Stanford.EDU> Technical report available on new architecture-altering operations for evolving the architecture of a multi-part program in genetic programming. Title: Architecture-Altering Operations for Evolving the Architecture of a Multi- Part Program in Genetic Programming. John R. Koza Computer Science Department Stanford University October 21, 1994 P Report No. STAN-CS-TR-94-1528 ABSTRACT Previous work described a way to evolutionarily select the architecture of a multi-part computer program from among preexisting alternatives in the population while concurrently solving a problem during a run of genetic programming. This report describes six new architecture- altering operations that provide a way to evolve the architecture of a multi-part program in the sense of actually changing the architecture of programs dynamically during the run. The new architecture-altering operations are motivated by the naturally occurring operation of gene duplication as described in Susumu Ohno's provocative 1970 book Evolution by Means of Gene Duplication as well as the naturally occurring operation of gene deletion. The six new architecture-altering operations are branch duplication, argument duplication, branch creation, argument creation, branch deletion and argument deletion. A connection is made between genetic programming and other techniques of automated problem solving by interpreting the architecture-altering operations as providing an automated way to specialize and generalize programs. The report demonstrates that a hierarchical architecture can be evolved to solve an illustrative symbolic regression problem using the architecture-altering operations. Future work will study the amount of additional computational effort required to employ the architecture- altering operations. INTRODUCTION (SECTION 1 OF TECH REPORT) In nature, crossover ordinarily recombines a part of the chromosome of one parent with a corresponding (homologous) part of the second parent's chromosome. However, in certain very rare and unpredictable instances, this recombination does not occur in the usual way. A gene duplication is an illegitimate recombination event that results in the duplication of a lengthy subsequence of a chromosome. Susumu Ohno's seminal 1970 book Evolution by Gene Duplication proposed the provocative thesis that the creation of new proteins (and hence new structures and behaviors in living things) begins with a gene duplication and that gene duplication is "the major force of evolution." This report describes six new architecture-altering genetic operations for genetic programming that are suggested by the mechanism of gene duplication (and the complementary mechanism of gene deletion) in chromosome strings. This report proposes that these new operations be added to the toolkit of genetic programming when the user desires to evolve the architecture of a multi-part program containing automatically defined functions (ADFs) during the run of genetic programming. The six new architecture-altering operations can be viewed from five perspectives. First, the new architecture-altering operations provide a new way to solve the problem of determining the architecture of the overall program in the context of genetic programming with automatically defined functions. Second, the new architecture-altering operations provide an automatic implementation of the ability to specialize and generalize in the context of automated problem-solving. Third, the new architecture-altering operations automatically and dynamically change the representation of the problem while simultaneously and automatically solving the problem. Fourth, the new architecture-altering operations automatically and dynamically decompose problems into subproblems and then automatically solve the overall problem by assembling the solutions of the subproblems into a solution of the overall problem. Fifth, the new architecture-altering operations automatically and dynamically discover useful subspaces (usually of lower dimensionality than that of the overall problem) and then automatically assemble a solution of the overall problem from solutions applicable to the individual subspaces. Section 2 of this report describes the naturally occurring processes of gene duplication and gene deletion. Section 3 describes analogs of gene duplication and gene deletion that have appeared in previous work with character strings in the field of genetic algorithms and other evolutionary algorithms. Section 4.1 provides basic background information on genetic programming and automatically defined functions. Section 4.2 lists the steps for executing genetic programming. Section 4.3 describes the five existing methods for determining the architecture of multi- part programs in the context of genetic programming with automatically defined functions. Section 4.4 describes different methods of creating the initial random population when these new operations are being used. Section 4.5 describes structure-preserving crossover with point typing in an architecturally diverse population. Section 5 describes the six new architecture-altering operations. Section 6 illustrates the architecture-altering operations using a gedanken experiment involving the problem of rotating the tires on an automobile. Section 7 contains some examples of actual runs of genetic programming with the new architecture-altering operations. Section 8 is the conclusion and section 9 outlines future work. METHODS OF OBTAINING REPORT: You can get this 60-page technical report by anonymous FTP or you can order a hard copy directly from Stanford for $l0. HARD COPY ORDERS: $l0 should be sent to: Publications Office Computer Science Department Margaret Jacks Hall Stanford University Stanford, CA 94305-2140 USA FTP INSTRUCTIONS: FTP to elib.stanford.edu. The files containing the report are in the /pub/reports/cs/tr/94/1528 directory. Detailed FTP instructions: ftp elib.stanford.edu user anonymous cd /pub/reports/cs/tr/94/1528 Then, get all the files from that directory. Type the following three commands. prompt binary mget * This will transfer all of the files to your machine.  From piuri at elet.polimi.it Sat Oct 29 09:52:48 1994 From: piuri at elet.polimi.it (Vincenzo Piuri) Date: Sat, 29 Oct 1994 13:52:48 GMT Subject: MWSCAS95 call for papers Message-ID: <9410291352.AA17235@ipmel2.elet.polimi.it> ======================================================================= 38TH MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS Hotel Gloria, Rio de Janeiro, Brazil August 13-16, 1995 General Chairman: Luiz P. Caloba - caloba at coe.ufrj.br Program Chairman: Paulo S. R. Diniz - diniz at coe.ufrj.br ======================================================================= CALL FOR PAPER FOR THE SPECIAL SESSION ON NEURAL MODELLING AND CONTROL The 1995 Midwest Symposium on Circuits and Systems will be organized by the Federal University of Rio de Janeiro and co-sponsored by the IEEE Circuits and Systems Society. The Symposium will be devoted to the theory, design and applications of circuits and systems. In particular, papers are solicited on all aspects of the neural technologies concerning system identification, modelling, and control. Papers are welcome both on theory and on applications. Authors interested in the Special Session are requested to submit a two-page abstract to the Session Organizer, by January 13, 1995; title, author's name(s), address(es), affiliation(s), e-mail address(es), fax and telephone number(s) must be included. Submission by e-mail or fax is welcome. Preliminary acceptance/rejection will be mailed by March 1, 1995; final acceptance will be mailed by May 15, 1995. Prof. Vincenzo Piuri Organizer of the Special Session on Neural Modelling and Control Department of Electronics and Information Politecnico di Milano, Italy piazza L. da Vinci 32 I-20133 Milano, Italy phone +39-2-2399-3623 fax +39-2-2399-3411 email piuri at elet.polimi.it =======================================================================  From harnad at Princeton.EDU Sat Oct 29 09:49:19 1994 From: harnad at Princeton.EDU (Stevan Harnad) Date: Sat, 29 Oct 94 09:49:19 EDT Subject: Neuropsychology/Consciousness: BBS Call for Commentators Message-ID: <9410291349.AA00634@clarity.Princeton.EDU> Below is the abstract of a forthcoming target article by: Jeffrey Gray on: CONSCIOUSNESS AND NEUROPSYCOLOGY This article has been accepted for publication in Behavioral and Brain Sciences (BBS), an international, interdisciplinary journal providing Open Peer Commentary on important and controversial current research in the biobehavioral and cognitive sciences. Commentators must be current BBS Associates or nominated by a current BBS Associate. To be considered as a commentator for this article, to suggest other appropriate commentators, or for information about how to become a BBS Associate, please send email to: harnad at clarity.princeton.edu or harnad at pucc.bitnet or write to: BBS, 20 Nassau Street, #240, Princeton NJ 08542 [tel: 609-921-7771] To help us put together a balanced list of commentators, please give some indication of the aspects of the topic on which you would bring your areas of expertise to bear if you were selected as a commentator. An electronic draft of the full text is available for inspection by anonymous ftp (or gopher or world-wide-web) according to the instructions that follow after the abstract. ____________________________________________________________________ THE CONTENTS OF CONSCIOUSNESS: A NEUROPSYCHOLOGICAL CONJECTURE Jeffrey A. Gray Department of Psychology Institute of Psychiatry De Crespigny Park, Denmark Hill London SE5 8AF, England jgray at ux.psych.lon.ac.uk ABSTRACT: Drawing on previous models of anxiety, intermediate memory, the positive symptoms of schizophrenia and goal-directed behaviour, a neuropsychological hypothesis is proposed for the generation of the contents of consciousness. It is suggested that these correspond to the outputs of a comparator that, on a moment-by-moment basis, compares the current state of the organism's perceptual world with a predicted state. An outline is given of the information-processing functions of the comparator system and of the neural systems which mediate them. The hypothesis appears to be able to account for a number of key features of the contents of consciousness. However, it is argued that neither this nor any existing comparable hypothesis is yet able to explain why the brain should generate conscious experience of any kind at all. KEYWORDS: Conciousness, contents of consciousness, comparator, septohippocampal system, anxiety, schizophrenia. -------------------------------------------------------------- To help you decide whether you would be an appropriate commentator for this article, an electronic draft is retrievable by anonymous ftp from princeton.edu according to the instructions below (the filename is bbs.gray). Please do not prepare a commentary on this draft. Just let us know, after having inspected it, what relevant expertise you feel you would bring to bear on what aspect of the article. ------------------------------------------------------------- To retrieve a file by ftp from an Internet site, type either: ftp princeton.edu or ftp 128.112.128.1 When you are asked for your login, type: anonymous Enter password as queried (your password is your actual userid: yourlogin at yourhost.whatever.whatever - be sure to include the "@") cd /pub/harnad/BBS To show the available files, type: ls Next, retrieve the file you want with (for example): get bbs.mealet When you have the file(s) you want, type: quit These files can also be retrieved using gopher, archie, veronica, etc. URL: ftp//ftp.princeton.edu/pub/harnad/BBS/bbs.gray http://www.princeton.edu/~harnad/bbs.html gopher://gopher.princeton.edu/11/.libraries/.pujournals ---------- Where the above procedure is not available there are two fileservers: ftpmail at decwrl.dec.com and bitftp at pucc.bitnet that will do the transfer for you. To one or the other of them, send the following one line message: help for instructions (which will be similar to the above, but will be in the form of a series of lines in an email message that ftpmail or bitftp will then execute for you). JANET users without ftp can instead utilise the file transfer facilities at sites uk.ac.ft-relay or uk.ac.nsf.sun. Full details are available on request. -------------------------------------------------------------  From kolen-j at cis.ohio-state.edu Sat Oct 29 16:27:51 1994 From: kolen-j at cis.ohio-state.edu (john kolen) Date: Sat, 29 Oct 1994 16:27:51 -0400 Subject: Thesis anouncement, again Message-ID: <199410292027.QAA18730@squirt.cis.ohio-state.edu> This is a reposting of my original announcement. The orignal announcement had the wrong ftp address. (One of the benefits of being at OSU is that I can cd to the neuroprose archive, hence, I don't bother with ftp addresses.) In addition to the address change, I have added a long abstract to the the announcement. As still is the case, those with old PS printers and previewers will have difficulties (see warning below.) Ftp-site: ftp.cis.ohio-state.edu ^^^^ (archive still works, too) Ftp-directory: pub/neuroprose/Thesis/kolen.thesis.ps.Z PrintedPages: 191 EXPLORING THE COMPUTATIONAL CAPABILITIES OF RECURRENT NEURAL NETWORKS DISSERTATION By John F. Kolen Prof. Jordan B. Pollack, Adviser Short Abstract While many researchers have successfully organized neural networks into structures displaying universal computational capability, most have ignored the more daunting endeavor of identifying ongoing computation, or information processing, as it occurs. My thesis addresses this problem as it relates to the understanding of the information processing capabilities of recurrent neural networks. I have isolated three important facets of recurrent neural networks that contribute to their computational power: internal dynamics, input modulation, and output generation. Theories of dynamical systems and iterated function systems have proven crucial in developing an understanding of these facets. With respect to my original question of identifying ongoing computation, the evidence suggests that the any observed computational powers of neural networks arise not from the network itself, but our application of it as a symbol processing device. If we consider recurrent neural networks as the a cognitive e. coli, this dissertation is a step toward understanding the nature cognition and intelligence. Long Abstract This dissertation addresses the issues surrounding the computational capabilities of recurrent neural networks. My results apply not only to simple recurrent networks, Jordan networks, and higher order recurrent networks, but many other networks implemented as input-parameterized iterated functions. The following reasons have driven my efforts to understand their computational capabilities. First, the question of knowledge content arises whenever we attempt to understand how a given network produces its behavior. Second, knowing the range of what is computable by a recurrent network can guide us in their intelligent application. Finally, this knowledge may also help us to develop new training strategies which bias the network towards desirable solutions. While we already know that recurrent networks can perform complex computation by simulating machine tapes and stacks, one problem still remains: someone designed each universal-computing network by hand. We know the function decomposition because the designer can tell us what they intended each part to do. Unfortunately, weak learning methods, like back-propagation, that discover operable network weights cannot explain the internal functionality of final product. Thus, we are forced to externally determine the recurrent network's computation process by observing its structure and behavior. To this end, I identify three facets of recurrent networks that directly affect their emergent computational descriptions: system dynamics, input modulation of state dynamics, and output generation. System dynamics, the mapping of current state to next state, have been traditionally considered the source of complex behavior. Input modulation occurs as a finite set of input vectors and induces beiterated function system-like behavior from the recurrent network. This selection creates state space representations for information processing states which display recursive structure. I show that the mechanism producing discrete outputs has dramatic effects on the resulting system complexity by imposing information processing regularities in the output stream strong enough to manipulate both complexion (number of states) and generative class of the observed computation. As for new training methods, I outline a method of network training called entrainment learning which offers a novel explanation of the transmission of grammatical behavior structures between agents. ********* WARNING *********** This document contains Level 2 PostScript commands that will not work on Level 1 printers (i.e. old LaserWriters and old versions of ghostview).  From ruppin at cs.UMD.EDU Sun Oct 30 13:48:30 1994 From: ruppin at cs.UMD.EDU (eytan ruppin) Date: Sun, 30 Oct 1994 13:48:30 -0500 Subject: No subject Message-ID: <199410301848.NAA26552@rapid.cs.UMD.EDU> Workshop Announcement NEURAL MODELING OF COGNITIVE AND BRAIN DISORDERS Sponsors: Institute for Advanced Computer Studies, University of Maryland Dept. of Neurology, University of Maryland School of Medicine Center for the Neural Basis of Cognition, Carnegie Mellon and Pittsburgh Universities Center for Neural and Cognitive Studies, University of Maryland (Additional sponsors are currently being sought.) A workshop on Neural Modeling of Cognitive and Brain Disorders will be held June 8 - 10, 1995 at the University of Maryland, College Park, just outside of Washington, DC. The focus of this meeting will be on the lesioning of neural network models to study disorders in neurology, neuropsychology and psychiatry, such as Alzheimer's disease, amnesia, aphasia, depression, acquired dyslexia, epilepsy, schizophrenia, and stroke. These models attempt to explain how specific pathological neuroanatomical and neurophysiological changes can result in various clinical manifestations, and they investigate the functional organization of the symptoms that result from specific brain pathologies. The prospects and challenges of modeling brain disorders have recently attracted an increasing number of researchers with different backgrounds, such as physicians, psychologists and computer scientists. This, together with the inherent multidisciplinary nature of brain modeling research, has motivated the goals of this workshop: To evaluate current achievements critically, to discuss the possibilities for further advancement, and to identify brain disorders and cognitive phenomena that may be studied computationally. To examine methodological modeling issues, such as limitations of the networks currently employed, and the required computational properties of future models. To make the material presented at the workshop available to the wider audience of researchers interested in studying neural models of brain disorders. A Proceedings of abstracts will be compiled, and the production of a book of contributed chapters based on the workshop is under consideration. CALL FOR ABSTRACTS Individuals wishing to present a poster related to any aspect of the workshop's themes should submit an abstract describing the nature of their presentation. The single page submission should include title, author(s), contact information (address and email/fax), and abstract. One inch margins and a typesize of at least 10 points should be used. Abstracts will be reviewed by the Program Committee; those accepted will be published in the workshop proceedings. Six copies of the camera-ready abstract should be mailed TO ARRIVE by February 1, 1995 to James A. Reggia, Dept. of Computer Science, A.V. Williams Bldg., University of Maryland, College Park, MD 20742 USA. PRELIMINARY PROGRAM Each workshop session will be focused on specific disorders and composed of four invited presentations followed by a critical commentary and a general discussion. Thursday, June 8 ---------------- 8:30 AM: Welcome and Overview 9:00 AM: Alzheimer's Disease and Memory Disorders Chair and Discussant: Steven Small (University of Pittsburgh) James McClelland (Carnegie Mellon University) - Complementary learning systems in hippocampus and neocortex Michael Hasselmo (Harvard University) - Runway synaptic modification models of cortex: implications for the pathology of Alzheimer's disease David Horn (Tel-Aviv University, Israel) - Synaptic deletion and compensation in Alzheimer's disease: a computational study Martha Farah (University of Pennsylvania) - Computational models of semantic memory impairment Noon: Lunch Break 1:30 PM: Epilepsy Chair and Discussant: Michael Rogawski (National Institutes of Health) Roger Traub (IBM Watson) - Modeling synchronized neuronal oscillations in epilepsy John Rinzel (National Institutes of Health) - Reduced, cell-based models for epilepsy Bill Lytton (University of Wisconsin) - Modeling epilepsy and seizure spread Mayank Mehta (University of Arizona) - A neural network model for kindling of focal epilepsy 4:30 PM: Reception Friday, June 9 -------------- 9:00 AM: Stroke and Functional Effects of Focal Lesions Chair and Discussant: Barry Gordon (Johns Hopkins University) John Pearson (David Sarnoff Research Center) - The effects of focal deafferentation on cortical reorganization James Reggia (University of Maryland) - Lesioning cortical maps: a model of stroke in sensory and motor cortices Manfred Spitzer (University of Heidelberg, Germany) - A neural network model of phantom limbs Eytan Ruppin (Tel-Aviv University, Israel) - The functional effects of focal lesions in associative memory networks Noon: Lunch Break 1:30 PM: Aphasia and Acquired Dyslexia Chair and Discussant: Rita Berndt (University of Maryland) Gary Dell (University of Illinois) - Lesioning a connectionist model of sentence processing to simulate naming errors in aphasia Max Coltheart (Macquarie University, Australia) - Simulation of acquired dyslexia by DRC, a computational realization of a dual-route reading model Karalyn Patterson (MRC Appl. Psych. Unit, Cambridge) - Connections and dis- connections: acquired surface dyslexia in a connectionist model of reading David Plaut (Carnegie Mellon University) - Connectionist modeling of the breakdown and recovery of reading via meaning 4:30 PM: Dinner Break 7:00 PM: POSTER SESSION Saturday, June 10 ----------------- 9:00 AM: Schizophrenia, Frontal and Affective Disorders Chair and Discussant: Jonathan Cohen (Carnegie Mellon University & University of Pittsburgh) Ralph Hoffman (Yale University) - Modeling schizophrenic positive symptoms using attractor and backpropagation networks David Servan-Schreiber (University of Pittsburgh) - Modeling cognitive deficits in schizophrenia: neuromodulation of prefrontal cortex Dan Levine (University of Texas at Arlington) - Functional deficits of frontal lobe lesions Joanne Luciano and Michael Cohen (Boston University) - A neural model of major depression Noon: Lunch Break 1:30 PM: Commentary: James McClelland (Carnegie Mellon University) 2:00 PM: General Discussion A brief commentary will be followed by a general discussion of where we are and where we want to go from here. Among the issues to be considered are the successes and limitations of current models of neurological, neuropsychological and psychiatric disorders. What common methods have been identified? How can models of this sort be validated, and at what level of detail should they be formulated? What topics seem amenable to future neural modeling, and what are barriers to further progress in this field? Is there sufficient interest in contributing to a book on the subject of this workshop? Finally, feedback on the workshop format and content will be solicited, and the interest and usefulness of holding similar workshops or more formal conferences in the future will be assessed. 4:30 PM: Adjournment ------ Travel Fellowships: ------------------ Funding has been requested for a few fellowships to offset travel cost of students, postdocs, and/or residents. Further details will be forthcoming. Program Committee: ----------------- Rita Berndt (Maryland), Barry Gordon (Johns Hopkins), Michael Hasselmo (Harvard), Ralph Hoffman (Yale), Joanne Luciano (Boston), Jay McClelland (Carnegie Mellon), Al Nigrin (American), David Plaut (Carnegie Mellon), James Reggia (Maryland), Eytan Ruppin (Tel-Aviv), and Stanley Tuhrim (Mount Sinai). Registration or Further Information: ----------------------------------- To receive registration materials (distributed most likely in January/February), please send your name, address, email address, phone number and fax number to Johanna Weinstein UMIACS A. V. Williams Bldg. University of Maryland College Park, MD 20742 USA Tel.: (301)405-6722 Fax: (301)314-9658 email: johanna at umiacs.umd.edu Further questions about conference administration, hotel reservations, etc. should also be directed to Ms. Weinstein. For questions about the workshop technical/scientific content or absract submissions, please contact Eytan Ruppin Dept. of Computer Science A.V. Williams Bldg. University of Maryland College Park MD 20742 USA Tel.: (301) 405-2709 Fax: (301)405-6707 email: ruppin at cs.umd.edu  From ifsa95 at dep.fem.unicamp.br Mon Oct 31 09:10:29 1994 From: ifsa95 at dep.fem.unicamp.br (IFSA95) Date: Mon, 31 Oct 94 10:10:29 EDT Subject: No subject Message-ID: <9410311210.AA00496@jaguar> MESSAGE TO AUTHORS FROM IFSA'95 ORGANIZERS _____________________________________________________________________________ We have been contacted by authors asking if the papers acceptance deadline refers to the postage date or to the arrival of the papers in the secretariat. We would like to inform that we have decided to accept papers for review that are either posted before november 1st, or that arrive in our hands until november 11th. _____________________________________________________________________________ * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * IFSA '95 * * * * VI International Fuzzy Systems Association World Congress * * Sao Paulo-Brazil * * July 22-28, 1995 * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * The full version of IFSA'95 2nd call-for-papers is * * stored in the file * * * * calif.doc * * * * which can be obtained by anonynmous FTP from: * * * * spock.dep.fem.unicamp.br * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * The latest information about IFSA'95 (including the * * call-for-papers) can be obtained via WWW on URL: * * * * http://www.inpe.br/meetings/IFSA95/home * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * For further information please contact: * * * * ifsa95 at dep.fem.unicamp.br * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *  From bishopc at helios.aston.ac.uk Mon Oct 31 03:34:37 1994 From: bishopc at helios.aston.ac.uk (bishopc) Date: Mon, 31 Oct 1994 08:34:37 +0000 Subject: NIPS Workshop Message-ID: <8857.9410310834@sun.aston.ac.uk> ------------------------------------------------------------------- NIPS*94 Workshop: DOING IT BACKWARDS: ------------------- NEURAL NETWORKS AND THE SOLUTION OF INVERSE PROBLEMS ---------------------------------------------------- Organizer: Chris M Bishop (Aston University) Intended Audience ----------------- Researchers and practitioners in neural computing interested in inverse problems. Introduction ------------ Many of the tasks for which neural networks are commonly used correspond to the solution of an `inverse' problem. Such tasks are characterized by the existence of a well-defined, deterministic `forward' problem which might, for instance, correspond to causality in a physical system. By contrast the inverse problem may be ill-posed, and may exhibit multiple solutions. A wide range of different approaches have been developed to tackle inverse problems, and one of the main goals of the workshop is to contrast the way in which they address the underlying technical issues, and to identify key areas for future research. Ample time will be allowed for discussions. Morning Session --------------- 7:30 "Welcome and overview" Chris Bishop (Aston) 7:35 "From ill-posed problems to all neural networks and beyond through regularization" Tomaso Poggio / Federico Girosi (MIT) 7:55 "Solving inverse problems using an EM approach to density estimation" Zoubin Ghahramani (MIT) 8:15 "Density estimation with periodic variables" Chris Bishop (Aston) 8:35 "Doing it forwards, undoing it backwards: high-dimensional compression and expansion" Russell Beale (University of Birmingham) 8:55 "Inversion of feed-forward networks by gradient descent" Alexander Linden (Berkeley) 9.15 Discussion Afternoon Session ----------------- 4:30 "An iterative inverse of a talking machine" Sid Fels (Toronto) 4:50 "Diagnostic problem solving" Sungzoon Cho (Postech, S Korea) 5:10 "Multiple Models in Inverse Filtering of the Vocal Tract" M Niranjan (Cambridge) 5:30 "Goal directed model inversion" Silvano Colombano (NASA Ames) 5:50 "Predicting element concentrations in the SSME exhaust plume" Kevin Whitaker (University of Alabama) 6:10 Discussion  From joachim at fit.qut.edu.au Sun Oct 2 23:25:50 1994 From: joachim at fit.qut.edu.au (Joachim Diederich) Date: Mon, 3 Oct 1994 13:25:50 +1000 Subject: Academic Position, QUT Brisbane, Australia Message-ID: <199410030325.NAA09067@fitmail.fit.qut.edu.au> The following position is open for applicants with a background in neurocomputing/connectionist systems. Please direct enquiries to Prof Mohay or to me. Best regards, Joachim ------------------------------------------------------------------------- SENIOR LECTURER IN THE SCHOOL OF COMPUTING SCIENCE QUEENSLAND UNIVERSITY OF TECHNOLOGY INTRODUCTION The Faculty of Information Technology is located on the Gardens Point (City Centre) campus of Queensland University of Technology. It currently comprises three Schools: Computing Science, Data Communications and Information Systems and four Research Centres: Cooperative Information Systems, Information Security, Neurocomputing and Programming Languages and Systems. In addition, the Faculty is a major partner in the Commonwealth funded Distributed Systems Technology Centre. POSITION The appointee will be responsible to the Head, School of Computing Science and will be expected to undertake a leadership role in teaching in undergraduate and postgraduate courses, in research and in academic administration. QUALIFICATION/SKILLS: Applicants must have a doctoral qualification or equivalent accreditation or standing, and must have a record of demonstrable scholarly achievement in one or more of the following areas of computer science: programming languages, software engineering, operating systems, neurocomputing or computer architecture. SALARY: Salary will be in the range $50,225 to $$57,913. FURTHER INFORMATION Duty statement and selection criteria are available from the Human Resources Department telephone (07) 864 3166. For further information contact the Head of School, Associate Professor George Mohay, telephone +61 7 864 1964, fax +61 7 964 1801 or email g.mohay at qut.edu.au. APPLICATIONS Applications and envelopes should quote {reference number} and include evidence of academic qualifications, experience and teaching evaluations, copies of three best publications or papers plus the names, addresses, facsimile and telephone numbers (and e-mail address if possible) of three referees. Applications should address the selection criteria and reach the Human Resources Director QUT Locked Bag No 2 Red Hill 4059 by Friday, 28 October, 1994. Smoking is not permitted in QUT buildings or vehicles. An Equal Opportunity Employer  From Adriaan.Tijsseling at phil.ruu.nl Mon Oct 3 04:29:03 1994 From: Adriaan.Tijsseling at phil.ruu.nl (Adriaan Tijsseling) Date: Mon, 3 Oct 1994 09:29:03 +0100 (MET) Subject: Thesis available: A Stagewise Treatment of Connectionism Message-ID: <199410030829.JAA08374@laurel.stud.phil.ruu.nl> The following master thesis is available as a PostScript file through ftp: ftp://ftp.phil.ruu.nl/pub/papers/meijer-STC94.ps.gz. Login as anonymous, email as password. The file is compressed with gnuzip. 63 pages total A Stagewise Treatment of Connectionism Roy Meijer Cognitive Artificial Intelligence Department of Philosophy Utrecht University Heidelberglaan 8 3584 CS Utrecht The Netherlands August 1994 Roy.Meijer at phil.ruu.nl Keywords: connectionism, developmental psychology, methodology, neural networks, symbolism. ABSTRACT Connectionism, the research program that is based on neural network techniques, has continued to grow explosively since its reappearance on the cognitive scene in the middle of the eighties. Usually some aspect of human cognition is singled out (e.g. the role of attention in visual tasks), modelled and experimented with. Experimenters often conclude that neural networks are able to do the task while showing some interesting side effects, which sometimes resemble human behavior in those tasks. But what happens next? It looks as if much fragmented work is being done without some sort of coherence, or some sort of strategy. From udah057 at bay.cc.kcl.ac.uk Mon Oct 3 06:36:12 1994 From: udah057 at bay.cc.kcl.ac.uk (udah057@bay.cc.kcl.ac.uk) Date: Mon, 03 Oct 1994 10:36:12 GMT Subject: de Garis PerAc Report Message-ID: <00985633.0D29C9EC.4@bay.cc.kcl.ac.uk> I was shocked to read the personal attack on me put out by de Garis under the heading of the Per Ac94 report. It is very useful to use the connectionist email net as a medium for conference reports, provided that they keep a professional level. An objective approach needs to be brought to writing such items; this was singularly not the case with the de Garis report. I would be grateful if de Garis, and similarly minded people, could restrain themselves in the future. John.G.Taylor  From MDUDZIAK at Gems.VCU.EDU Mon Oct 3 19:00:00 1994 From: MDUDZIAK at Gems.VCU.EDU (MARTIN DUDZIAK) Date: Mon, 03 Oct 1994 19:00:00 -0400 (EDT) Subject: Some activity announc.--- molec. sys/engr and neurocomp/complex sys. Message-ID: <mailman.706.1149591318.29955.connectionists@cs.cmu.edu> From: Dr. M. Dudziak, Biomedical Engineering Dept., Virginia Commonwealth Univ. Four announcements from the Biomedical Engineering Program at Virginia Commonwealth University, Richmond, VA 1) Introductory Workshop on Scanning Probe Microscopy Nov. 18, 1994 (full-day) 2) Public presentation and forum on issues of neuroscience, nanosystems (molecular engineering), and biotechnology Nov. 17, 1994 (PM) 3,4) General information about research, services and educational (graduate-level) programs at MS and PhD level in molecular systems/engineering and in dynamical systems modeling and neurocomputing Please Post and Distribute ================================================================= INTRODUCTORY WORKSHOP SCANNING PROBE MICROSCOPY For BIOLOGICAL AND MATERIALS SCIENCES Friday, November 18, 1994 8:00 AM - 5:00 PM McGuire Hall VCU Medical College of Virginia 12th and Clay Sts. Richmond, VA Sponsored By Biomedical Engineering Program Virginia Commonwealth University An introduction to the field of nanotechnology will be provided with a focus on the uses of scanning probe microscopy for research and engineering applications in the biological and material sciences. Speakers from VCU and other institutions including the manufacturer of the Nanoscope-III Multi-mode Atomic Force Microscope and Scanning Tunneling Microscope will present information on the capabilities, experiences, and recent discoveries using this technology. A perspective on engineering applications of nanotechnology and prospects for federal scientific research and funding within the nanosystems field will be given. Hands-on observation and experience with the Nanoscope-III will be provided. Attendees are welcome to discuss in advance the feasibility of bringing a sample to the workshop for scanning. Friday, Nov. 18 : 8:00 AM: Invited talks and discussions Location: McGuire Hall 118 12:15 PM: Lunch Location: McGuire Hall 118 2:30 PM: Demonstration and hands-on sample processing Location: McGuire Annex 124 For further information contact: Dr. Martin Dudziak, (804) 828-2905, mdudziak at gems.vcu.edu Ms. Elizabeth Faircloth, (804) 828-2591, efaircloth at gems.vcu.edu Workshop Presentations: Chairperson: Dr. Richard Freer, Chairman of Biomedical Engineering Dept., VCU, and CEO of Commonwealth Biotechnologies, Inc., Virginia Biotechnology Research Park 8:15 Dr. Richard Freer Nanotechnology and Complex Systems in 21st Century Medicine: Integration of Academic and Private Sector Biotechnology Research 8:40 Dr. Martin Dudziak, Biomedical Engineering and Physics, VCU Overview of the Molecular Systems and Engineering Lab and work in progress: Quantum Neurodynamics and the Application of AFM to Neuronal Imaging 9:00 Dr. Yale Strausser, Digital Instruments, Inc. Introduction to SPM and the Nanoscope-III: Advances in Biological and Fluid Imaging 10:00 Break / Coffee and Tea 10:15 Dr. Carol R. Kalil, NASA Langley Research Center Surface Analysis of High Performance Materials using STM and AFM 10:45 Dr. Zhifeng Shao, Dept. of Physiology, University of Virginia Instrumentation Development with AFM and Applications to the Study of Membrane Proteins 11:15 Dr. John Cooper, Depts. of Chemistry and Biochemistry, Old Dominion University Scanning Tunneling Microscopy of Novel Electrical Materials 11:45 Mr. Dirk Bosbach, Dept. of Geology, Virginia Polytechnic Institute and State University Applications of SPM in Geochemistry and Environmental Research 12:15 Lunch (Catered) 1:30 Dr. Jan Hoh, Dept. of Physiology, Johns Hopkins University Exploring the Local Properties of Biological Surfaces 2:00 Dr. Peter Moon, School of Dentistry and Biomedical Engineering, VCU Characterizations of Dentin Structure and Comparisons with Modeling and Electron Microscopy 2:30 Demonstrations and Hands-On Imaging with Multi-Mode Atomic Force Microscope (There may be one or two additional speakers) ================================================== BUILDING BRAINS: NEW SCIENCE, NEW BUSINESS Thursday, November 17, 1994 7:00 PM Sanger Hall 1044 VCU Medical College of Virginia 12th and Marshall Streets Richmond, VA A Public Seminar and Forum on how advances in the fields of molecular engineering and nanotechnology, combined with new understandings of the brain and perception, affect the future of medicine, biotechnology, and the economic growth they create. Guest Lecture: Prof. Karl Pribram, pre-eminent neuroscientist, professor emeritus of neuroscience (Stanford University) and Director of the Center for Brain Research and Information Sciences (Radford University) will speak on: Brain Dynamics, the Holonomic Model, and the Emergence of Consciousness Other invited speakers and discussion leaders include: Dr.Paul Werbos, Program Director for Neuro-Engineering, National Science Foundation Dr. Werbos has been active in the development of neural networks for process control and engineering systems as well as in mathematical physics and dynamical systems. Dr. Yale Strausser, Senior Scientist, Digital Instruments, Inc. Dr. Strausser is a principal developer of the Nanoscope architecture and the specialized microscopy tools used in the semiconductor, metallurgical, and chemical industries. Dr. Bijan Rao, Dept. of Physics, Virginia Commonwealth University Dr. Rao has been involved in ground- breaking research in the area of atomic clusters and nanostructured materials, with applications to biomedicine, chemistry, and electronics. Some of the topics and questions that will be addressed during the meeting: What is the new understanding and paradigm emerging through diverse fields of computing, physics, neuroscience, and engineering? What are some of the advances in molecular engineering and nanotechnology and how do these fit with activities in biotech research and development? How may the ability to build molecular-scale machines and computers affect medicine and health in the 21st Century? How can new models of brain function and information processing affect the way we think, act, and respond to long-term illnesses and to individual differences? How will these developments be relevant and important to the people and economy of Richmond and Virginia and the focus upon developing Richmond as a biotechnology center? The meeting is intended to be a presentation of ideas and information and an open discussion among participants. It is open to all members of the public and is particularly geared toward members of the greater Richmond civic, corporate, and educational communities. The seminar is sponsored by the Biomedical Engineering Program at Virginia Commonwealth University. For further information contact: Dr. M. Dudziak McGuire Hall 126 (804) 828-2905, (804) 828-2594 FAX (804) 828-4454 mdudziak at gems.vcu.edu Ms. E. Faircloth Biomed Engineering (804) 828-2591 FAX (804) 828-4454 efaircloth at gems.vcu.edu ======================================================================= MOLECULAR SYSTEMS AND ENGINEERING LABORATORY Services, Training, and Consulting Provided for: Structural Biology Imaging and Engineering (submicron and nanometer level) Surface Imaging and Measurement (molecular and atomic resolution) Micro- and Nanoscale Lithography, Assembly, and Real-Time 3D Modeling Micromachine Design, Simulation, and Testing Uses of Scanning Probe Microscope, Confocal Microscope, Image Processing Tools for Materials Sciences and Biomedical Applications Contractual Imaging and Surface Manipulation is available for departments and labs within VCU and for companies outside the university Resources include: Digital Instruments Nanoscope-III with Multi-Modal Atomic Force Microscope and Scanning Tunneling Microscope Silicon Graphics Indigo workstations with 3D-graphics Multi-processor (parallel computer) workstations and embedded systems Image processing and pattern recognition software and hardware Access to Confocal Microscope, Bioscope AFM, and Vacuum-Based AFM The laboratory is an integrated component of the Biomedical Engineering Program and is located on the MCV Campus of Virginia Commonwealth University *********** The areas of research in this lab are components of the Master's and Doctoral programs in Biomedical Engineering at VCU and both core and elective courses cover topics in these areas. *********** Open House hours for visits and discussions every Tuesday 4 - 6 PM by appointment, please. Dr. M. Dudziak, Director McGuire Hall 126 (804) 828-2905, (804) 828-2594 FAX (804) 828-4454 mdudziak at gems.vcu.edu ========================================================================= COMPLEX DYNAMICAL SYSTEMS AND NEUROCOMPUTING FACILITY Services, Training, and Consulting Provided for: Pattern Classification, Recognition, and Forecasting using: Neural Networks, Genetic Algorithms, and Fuzzy Logic for: Medical, Engineering, Physical Sciences, and Financial Applications Diagnostic Tools for Clinical Neuroscience, Cardiology, Related Fields Modeling of Non-Linear and Chaotic Systems Advanced Medical and Image Processing Techniques Multi-Processor (parallel) Programming and Modeling Multi-media Database Design and Implementation Contractual Arrangements are available for departments and labs within VCU and for companies outside the university Resources include: Silicon Graphics Indigo workstations with 3D-graphics Multi-processor (parallel computer) workstations and embedded systems Image processing and pattern recognition software and hardware Access to Massively-Parallel Supercomputer Resources and Software Tools Digital Instruments Nanoscope-III with Multi-Modal Atomic Force Microscope and Scanning Tunneling Microscope The laboratory is an integrated component of the Biomedical Engineering Program and is located on the MCV Campus of Virginia Commonwealth University *********** The areas of research in this lab are components of the Master's and Doctoral programs in Biomedical Engineering at VCU and both core and elective courses cover topics in these areas. *********** Open House hours for visits and discussions every Tuesday 4 - 6 PM by appointment, please. Dr. M. Dudziak, Director McGuire Hall 126 (804) 828-2905, (804) 828-2594 FAX (804) 828-4454 mdudziak at gems.vcu.edu =============================================================== Further information about the above and other areas of research and education in the biomedical and life sciences may be obtained by accessing the VCU Mosaic/Web servers. The VCU home page is at http://cabell.vcu.edu/vcu/vcu.html  From schmidhu at informatik.tu-muenchen.de Tue Oct 4 05:32:09 1994 From: schmidhu at informatik.tu-muenchen.de (Juergen Schmidhuber) Date: Tue, 4 Oct 1994 10:32:09 +0100 Subject: paper available Message-ID: <94Oct4.103217met.42322@papa.informatik.tu-muenchen.de> ALGORITHMIC ART Report FKI-197-94 (19 pages, non-scientific paper) Juergen Schmidhuber Fakultaet fuer Informatik Technische Universitaet Muenchen 80290 Muenchen, Germany Many artists try to depict ``the essence'' of objects to be represented. In an attempt to formalize certain aspects of the ``the essence'', I propose an art form called algorithmic art. It is based on concepts from algorithmic information theory. Suppose the task is to draw a given object. Usually there are many ways of doing so. The goal of algorithmic art is to draw the object such that the drawing can be specified by an algorithm and two properties hold: (1) The drawing should ``look right''. (2) the Kolmo- gorov complexity of the drawing should be small (the algorithm should be short), and a typical observer should be able to see this. Examples of algorithmic art are given in form of ``algorithmically simple'' cartoons of various objects, including a pin-up girl and a weight lifter. Relations to previous work are established. Finally, attempts are made to relate the formalism of the theory of minimum description length to informal notions like ``good artistic style'' and ``beauty''. To obtain a copy, do: unix> ftp 131.159.8.35 Name: anonymous Password: (your email address, please) ftp> binary ftp> cd pub/fki ftp> get fki-197-94.ps.gz ftp> bye unix> gunzip fki-197-94.ps.gz unix> lpr fki-197-94.ps Alternatively, check out my home page: http://papa.informatik.tu-muenchen.de/mitarbeiter/schmidhu.html Use a high resolution printer (600 dpi) to print the file (the layout is designed for European A4 paper). On many printers you will have to use the -s option ( > 1MB uncompressed). Comments are welcome. Are you aware of any other mailing lists or publishers who might be interested in this work? Please tell me. Juergen Schmidhuber  From gar at eng.cam.ac.uk Tue Oct 4 11:20:12 1994 From: gar at eng.cam.ac.uk (gar@eng.cam.ac.uk) Date: Tue, 4 Oct 94 11:20:12 BST Subject: TR: On-line Q-learning using Connectionist Systems Message-ID: <29766.9410041020@hope.eng.cam.ac.uk> The following technical report is available by anonymous ftp from the archive of the Speech, Vision and Robotics Group at the Cambridge University Engineering Department. ON-LINE Q-LEARNING USING CONNECTIONIST SYSTEMS G. A. Rummery and M. Niranjan Technical Report CUED/F-INFENG/TR 166 Cambridge University Engineering Department Trumpington Street Cambridge CB2 1PZ England Abstract Reinforcement learning algorithms are a powerful machine learning technique. However, much of the work on these algorithms has been developed with regard to discrete finite-state Markovian problems, which is too restrictive for many real-world environments. Therefore, it is desirable to extend these methods to high dimensional continuous state-spaces, which requires the use of function approximation to generalise the information learnt by the system. In this report, the use of back-propagation neural networks (Rumelhart et al, 1986) is considered in this context. We consider a number of different algorithms based around Q-Learning (Watkins, 1989) combined with the Temporal Difference algorithm (Sutton, 1988), including a new algorithm (Modified Connectionist Q-Learning), and Q(lambda) (Peng and Williams, 1994). In addition, we present algorithms for applying these updates on-line during trials, unlike backward replay used by Lin (1993) that requires waiting until the end of each trial before updating can occur. On-line updating is found to be more robust to the choice of training parameters than backward replay, and also enables the algorithms to be used in continuously operating systems where no end of trial conditions occur. We compare the performance of these algorithms on a realistic robot navigation problem, where a simulated mobile robot is trained to guide itself to a goal position in the presence of obstacles. The robot must rely on limited sensory feedback from its surroundings, and make decisions that can be generalised to arbitrary layouts of obstacles. These simulations show that on-line learning algorithms are less sensitive to the choice of training parameters than backward replay, and that the alternative update rules of MCQ-L and Q(lambda) are more robust than standard Q-learning updates. ************************ How to obtain a copy ************************ Via anonymous ftp: unix> ftp svr-ftp.eng.cam.ac.uk Name: anonymous Password: (type your email address) ftp> cd reports ftp> binary ftp> get rummery_tr166.ps.Z ftp> quit unix> uncompress rummery_tr166.ps.Z unix> lpr rummery_tr166.ps (or however you print PostScript)  From cowan at synapse.uchicago.edu Tue Oct 4 12:46:47 1994 From: cowan at synapse.uchicago.edu (Jack Cowan) Date: Tue, 4 Oct 94 10:46:47 -0600 Subject: de Garis PerAc Report Message-ID: <9410041646.AA00766@synapse> I'd like to second John Taylor's request. I was really surprised to read the report in question. In my opinion personal comments of such a nature should not be transmitted through the connectionist or any other public mailings. Jack Cowan ............... MODERATOR'S NOTE: I don't edit submissions to CONNECTIONISTS for style or detailed content; I only check to make sure they're relevant to the list and contain at least some technical material of value. In the case of de Garis' conference reports, he (and I) have now been suitably warned by the readership about what constitutes acceptable material for this list. Any further discussion of the de Garis article should probably take place via private email. If people would like to submit alternative accounts of the PerAc conference, I would be hapy to receive them. -- Dave Touretzky, CONNECTIONISTS moderator  From mbrown at aero.soton.ac.uk Tue Oct 4 16:24:53 1994 From: mbrown at aero.soton.ac.uk (Martin Brown) Date: Tue, 4 Oct 94 16:24:53 BST Subject: Postdoctoral Position Message-ID: <21277.9410041524@aero.soton.ac.uk> Department of Aeronautics and Astronautics Southampton University, UK Postdoctoral Position in Intelligent Characterisation (Modelling) and Control of Plasma Etching Processes Applicants are invited to apply for a 3 year Postdoctoral position in the above area. The primary objective of the project is to develop real-time intelligent modelling and control methods for reactive ion etching of semi-conducting materials. The research grant is funded by EPSRC as a ROPA award. Both experimental and modelling work will be involved and candidates should ideally have experience in experimental physics (optical emission spectroscopy, laser interferometry) and neural net/neuro-fuzzy control techniques. Applicants with experience in either one of the areas and a strong interest in the other area are encouraged to apply. The position will be on the RA1A scale with a salary in the range 13,941-20,953 (UK pounds) and will commence as soon as possible. For further information and informal discussions call either Dr. Stephen Gabriel on 0703 593222, email sbg at aero.soton.ac.uk, or Professor Chris Harris on 0703 592353, email cjh at aero.soton.ac.uk. Closing date for applications will be in approximately 5-6 weeks time.  From B.DASGUPTA at fs3.mbs.ac.uk Tue Oct 4 17:06:19 1994 From: B.DASGUPTA at fs3.mbs.ac.uk (BHASKAR DASGUPTA ALIAS BD) Date: 4 Oct 94 17:06:19 BST Subject: GARCH MODELS COMPARED TO CONNECTIONIST MODELS Message-ID: <30656710BC7@fs3.mbs.ac.uk> Hello, I have a query about the suitability of using GARCH(p,q) models in modelling economic and financial time series. I was advised to compare my NN performance in foreign exchange rate prediction to the performance of a GARCH model. I checked up in the Gershenfield & Weigend Book on Time Series Forecasting, and in the chapter on Foreign exchange data series prediction written by LeBaron, I could only find reference to a ARCH model used to determine non-linearity along with the BDS and TSAY tests, but the ARCH model was not used to predict or compare predictions. Is this approach of comparing NN forecasts with GARCH models prevalent, or is anyone working on this?, In the Trippi & Turban book, ARIMA models are compared, but not GARCH/ ARCH. I am looking to contact someone who is working on this, or someone who can guide me to some code which does this, either as in a macro in LOTUS123, or RATS or SPSS (the only statistical software I have access to :-). I would appreciate any response, and if there are sufficient responses, I would summarize and repost to the group. Thanks in advance. bd PS: I shall also be posting this message on the ALLSTAT group, so apologies for the cross post. Bhaskar Dasgupta SnailMail Manchester Business School Phone ::010-44-61-275-6547 Booth Street West Fax ::010-44-61-273-7732 Manchester, M15 6PB, England. email ::b.dasgupta at fs3.mbs.ac.uk  From mingli at dimacs.rutgers.edu Tue Oct 4 14:25:04 1994 From: mingli at dimacs.rutgers.edu (Ming Li) Date: Tue, 4 Oct 94 14:25:04 EDT Subject: Call For Papers: COLT'95 -- Plaintext Version Message-ID: <9410041825.AA10901@dimacs.rutgers.edu> ______________________________________________________________________ CALL FOR PAPERS---COLT 95 Eighth Conference on Computational Learning Theory Santa Cruz, California, USA; July 5-8, 1995 ______________________________________________________________________ The Eighth Conference on Computational Learning Theory (COLT 95) will be held on the campus of the University of California at Santa Cruz, USA, from the late afternoon of Wednesday, July 5, through Saturday, July 8, 1995. COLT 95 is sponsored by the University of California, in cooperation with the ACM Special Interest Groups for Algorithms and Computation Theory (SIGACT) and Artificial Intelligence (SIGART). We invite papers in all areas that relate directly to the analysis of learning algorithms and the theory of machine learning, including artificial and biological neural networks. We also invite papers on learning from related theoretical and applied areas, such as statistics, statistical physics, Bayesian/MDL estimation, information theory, inductive inference, logic, inductive logic programming, knowledge representation, knowledge discovery in databases, natural language processing, robotics, and pattern recognition. Besides purely theoretical papers we encourage the submission of papers on experimental results that also provide a theoretical analysis. INVITED TALKS. Invited talks will be given by Terry Sejnowski (Salk Institute and University of California at San Diego) and Les Valiant (Harvard University). ABSTRACT SUBMISSION. Authors should submit fourteen copies (preferably two-sided copies) of an extended abstract to Wolfgang Maass - COLT 95 Institute for Theoretical Computer Science Technische Universitaet Graz, Klosterwiesgasse 32/2 A-8010 Graz, Austria An abstract must be RECEIVED BY JANUARY 10, 1995 (or postmarked by January 2 and sent airmail). This deadline is FIRM! Papers that have appeared in journals or other conferences, or that are being submitted to other conferences, are not appropriate for submission to COLT. There is a single exception: Since in 1995 the notification date for STOC is shortly after the submission deadline for COLT, these conferences have agreed that a paper can be submitted both to STOC 95 and COLT 95, with the understanding that such paper is automatically withdrawn from COLT if accepted at STOC. ABSTACT FORMAT. The extended abstract should consist of a cover page with title, authors' names, postal and e-mail addresses, and a 200-word summary. The body of the abstract should be no longer than 10 pages with roughly 35 lines/page in 12-point font. Papers deviating significantly from this length constraint will not be considered. The body should include a clear definition of the theoretical model used, an overview of the results, and some discussion of their significance, including comparison to other work. Proofs or proof sketches should be included. PROGRAM FORMAT. The program will consist of both "long" talks, and "short" talks, corresponding to longer and shorter papers in the proceedings. The short talks will also be coupled with a poster presentation in special poster sessions. By default, all papers will be considered for both categories. Authors who DO NOT want their papers considered for the short category should indicate that fact in the cover letter. The cover letter should also specify the contact author and give his/her e-mail. NOTIFICATION. Authors will be notified of acceptance or rejection by a letter mailed on or before Friday, March 10, with possible earlier notification via e-mail. Final camera-ready papers will be due by Tuesday, April 11. PROGRAM CHAIR. Wolfgang Maass (TU Graz, Austria, e-mail: maass at igi.tu-graz.ac.at). CONFERENCE AND LOCAL ARRANGEMENTS CHAIRS. David Haussler and Manfred Warmuth (U. of California at Santa Cruz) PROGRAM COMMITTEE. Dana Angluin (Yale), Peter Bartlett (ANU, Australia), Tom Dietterich (Oregon State Univ.), Haym Hirsh (Rutgers), Jeff Jackson (CMU), Martin Kummer (Univ. Karlsruhe), Phil Long (Duke Univ.), Ron Rivest (MIT), Robert Schapire (AT&T), Ted Slaman (Univ. of Chicago), Naftali Tishby (Hebrew Univ.), Gyorgy Turan (UIC, Chicago). COLT AND ML. The Twelfth Intern. Conf. on Machine Learning (ML 95) will be held right after COLT 95 on July 9 - 12 at Tahoe City, California. Car pools from Santa Cruz to Tahoe City on July 8 will be arranged.  From moody at chianti.cse.ogi.edu Tue Oct 4 16:28:13 1994 From: moody at chianti.cse.ogi.edu (John Moody) Date: Tue, 4 Oct 94 13:28:13 -0700 Subject: Neural Networks in the Capital Markets Conference Message-ID: <9410042028.AA12835@chianti.cse.ogi.edu> Fellow Connectionists: This is a reminder to register for NNCM*94 as soon as possible. The deadline for reserving rooms at the Pasadena Ritz Carlton at the conference rate is October 15. Yaser Abu-Mostafa John Moody ******************************************************************* --- Registration Package and Preliminary Program --- NNCM-94 Second International Workshop NEURAL NETWORKS in the CAPITAL MARKETS Thursday-Friday, November 17-18, 1994 with tutorials on Wednesday, November 16, 1994 The Ritz-Carlton Hotel, Pasadena, California, U.S.A. Sponsored by Caltech and London Business School Neural networks have now been applied to a number of live systems in the capital markets, and in many cases have demonstrated better performance than competing approaches. Because of the overwhelming interest in the first NNCM workshop held in London in November 1993, the second annual NNCM workshop will be held November 17-18, 1994, in Pasadena, California. This is a research meeting where original, high-quality contributions to the field are presented and discussed. In addition, a day of introductory tutorials (Wednesday, November 16) will be included to familiarize audiences of different backgrounds with the financial aspects, and the mathematical aspects, of the field. --Invited Speakers: The workshop will feature invited talks by four internationally recognized researchers: Dr. Andrew Lo, MIT Sloan School Dr. Paul Refenes, London Business School Dr. Robert Shiller, Yale University Dr. Hal White, UC San Diego --Contributed Papers: NNCM-94 will have 4 oral sessions and 2 poster sessions with more than 40 contributed papers presented by academicians and practitioners from both the neural networks side and the capital markets side. Each paper has been refereed by 4 experts in the field. The areas of the accepted papers include: Stock and bond valuation and trading, asset allocation and portfolio management, real trading using neural networks, foreign exchange rate prediction, option pricing, univariate time series analysis, neural network methodology, statistical analysis and hints, theory of forecasting, and neural network modeling. --Tutorials: Before the main program, there will be a day of tutorials on Wednesday, November 16, 1994. The morning session will focus on the financial side and the afternoon session will focus on the mathematical side. -Morning Session- Dynamics of Trading and Market Microstructure Dr. Larry Harris, University of Southern California Empirical Research on Market Inefficiencies Dr. Blake LeBaron, University of Wisconsin -Afternoon Session- Neural Networks, Time Series, and Finance Dr. John Moody, Oregon Graduate Institute Statistical Inference for Neural Networks Dr. Brian Ripley, Oxford University We are very pleased to have tutors of such caliber help bring new audiences from different backgrounds up to speed in this hybrid area. --Schedule Outline: Wednesday, November 16: 8:00-12:15 Tutorials I & II 1:30-5:45 Tutorials III & IV Thursday, November 17: 8:30-11:30 Oral Session I 11:30-2:00 Luncheon & Poster Session I 2:00-5:00 Oral Session II Friday, November 18: 8:30-11:30 Oral Session III 11:30-2:00 Luncheon & Poster Session II 2:00-5:00 Oral Session IV --Location: The workshop will be held at the Ritz-Carlton Huntington Hotel in Pasadena, within two miles from the Caltech campus. One of the most beautiful hotels in the U.S., the Ritz is a 35-minute drive from Los Angeles International Airport (LAX) with nonstop flights from most major cities in North America, Europe, the Far East, Australia, and South America. Home of Caltech, Pasadena has recently become a major dining/hangout center for Southern California with the growth of its `Old Town', built along the styles of the 1950's. Among the cultural attractions of Pasadena are the Norton Simon Museum, the Huntington Library/ Gallery/Gardens, and a number of theaters including the Ambassador Theater. --Organizing Committee: Dr. Y. Abu-Mostafa, California Institute of Technology Dr. A. Atiya, Cairo University Dr. N. Biggs, London School of Economics Dr. D. Bunn, London Business School Dr. B. LeBaron, University of Wisconsin Dr. A. Lo, MIT Sloan School Dr. J. Moody, Oregon Graduate Institute Dr. A. Refenes, London Business School Dr. M. Steiner, Universitaet Munster Dr. A. Timmermann, Birkbeck College, London Dr. A. Weigend, University of Colorado Dr. H. White, University of California, San Diego --Registration and Hotel Reservation: Registration is done by mail on a first-come, first-served basis (last year we had to return the checks to more than 50 people for lack of space). To ensure your place at the workshop, please send the enclosed registration form and payment as soon as possible to Ms. Lucinda Acosta, Caltech 116-81, Pasadena, CA 91125, U.S.A. Please make checks payable to Caltech. Hotel reservations are made by contacting the Ritz-Carlton Hotel directly. Their phone number is (818) 568-3900 and fax number is (818) 792-6613. Please mention that you are with NNCM-94 in order to get the (very) special rate that we negotiated. The rate is $79+taxes ($99 with $20 credited by NNCM-94 upon registration) per room (single or double occupancy) per night. Please make the hotel reservation IMMEDIATELY as the rate is based on availability. --Secretariat: For further information, please contact the NNCM-94 secretariat Ms. Lucinda Acosta, Caltech 116-81, Pasadena, CA 91125, U.S.A. e-mail: lucinda at sunoptics.caltech.edu , phone (818) 395-4843, fax (818) 568-8437 ******************************************************************* -- NNCM-94 Registration Form -- Title:--------- Name:------------------------------------ Mailing Address:------------------------------------------- ----------------------------------------------------------- e-mail:---------------------------- fax:------------------- ********Please circle the applicable fees and write the total******** --Main Conference (November 17-18): Registration fee $500 Discounted fee for academicians $250 (letter on university letterhead required) Discounted fee for full-time students $125 (letter from registrar or faculty advisor required) --Tutorials (November 16): You must be registered for the main conference in order to register for the tutorials. Morning Session Only $100 Afternoon Session Only $100 Both Sessions $150 Full-time students $50 (letter from registrar or faculty advisor required) TOTAL: $-------- Please include payment (check or money order in US currency). PLEASE MAKE CHECK PAYABLE TO CALTECH. --Hotel Reservation: Please contact the Ritz-Carlton Huntington Hotel in Pasadena directly. The phone number is (818) 568-3900 and the fax number is (818) 792-6613. Ask for the NNCM-94 rate. We have negotiated an (incredible) rate of $79+taxes ($99 with $20 credited by NNCM-94 upon registration) per room (single or double occupancy) per night, based on availability. ********Please mail your completed registration form and payment to******** Ms. Lucinda Acosta, Caltech 116-81, Pasadena, CA 91125, U.S.A.  From P.McKevitt at dcs.shef.ac.uk Tue Oct 4 16:39:26 1994 From: P.McKevitt at dcs.shef.ac.uk (Paul Mc Kevitt) Date: Tue, 4 Oct 94 16:39:26 BST Subject: No subject Message-ID: <9410041539.AA07917@dcs.shef.ac.uk> CONFERENCE ANNOUNCEMENT AND PRELIMINARY CALL FOR PAPERS AISB-95: Hybrid Problems, Hybrid Solutions. ============================================ Monday 3rd -- Friday 7th April 1995 Halifax Hall of Residence & Computer Science Department University of Sheffield Sheffield, ENGLAND The Tenth Biennial Conference on AI and Cognitive Science organised by the Society for the Study of Artificial Intelligence and the Simulation of Behaviour Programme Chair: John Hallam (University of Edinburgh) Programme Committee: Dave Cliff (University of Sussex) Erik Sandewall (University of Linkoeping) Nigel Shadbolt (University of Nottingham) Sam Steel (University of Essex) Yorick Wilks (University of Sheffield) Local Organisation: Paul Mc Kevitt (University of Sheffield) The past few years have seen an increasing tendency for diversification in research into Artificial Intelligence, Cognitive Science and Artificial Life. A number of approaches are being pursued, based variously on symbolic reasoning, connectionist systems and models, behaviour-based systems, and ideas from complex dynamical systems. Each has its own particular insight and philosophical position. This variety of approaches appears in all areas of Artificial Intelligence. There are both sybmolic and connectionist natural language processing, both classical and behaviour-based vision research, for instance. While purists from each approach may claim that all the problems of cognition can in principle be tackled without recourse to other methods, in practice (and maybe in theory, also) combinations of methods from the different approaches (hybrid methods) are more successful than a pure approach for certain kinds of problems. The committee feels that there is an unrealised synergy between the various approaches that an AISB conference may be able to explore. Thus, the focus of the tenth AISB Conference is on such hybrid methods. We particularly seek papers that describe novel theoretical and/or experimental work which uses a hybrid approach or papers from purists, arguing cogently that compromise is unnecessary or unproductive. While papers such as those are particularly sought, good papers on any topic in Artificial Intelligence will be considered: as always, the most important criteria for acceptance will be soundness, originality, substance and clarity. Research in all areas is equally welcome. The AISB conference is a single track conference lasting three days, with a two day tutorial and workshop programme preceding the main technical event, and around twenty high calibre papers will be presented in the technical sessions. It is expected that the proceedings of the conference will be published in book form in time to be available at the conference itself, making it a forum for rapid dissemination of research results. SUBMISSIONS: High quality original papers dealing with the issues raised by mixing different approaches, or otherwise related to the Conference Theme, should be sent to the Programme Chair. Papers which give comparative experimental evaluation of methods from different paradigms applied to the same problem, papers which propose and evaluate mixed-paradigm theoretical models or tools, and papers that focus on hybrid systems applied to real world problems will be particularly welcome, as will papers from purists who argue cogently that the hybrid approach is flawed and a particular pure approach is to be preferred. Papers being submitted, whether verbatim or in essence, to other conferences whose review process runs concurrently with AISB-95 should indicate this fact on their title page. If a submitted paper appears at another conference it must be withdrawn from AISB-95 (this does not apply to presentation at specialist workshops). Papers that violate these requirements may be rejected without review. SHEFFIELD: Sheffield is one of the friendliest cities in the UK and is situated well having the best and closest surrounding countryside of any major city in the UK. The Peak District National Park is only minutes away. It is a good city for walkers, runners, and climbers. It has two theatres, the Crucible and Lyceum. The Lyceum, a beautiful Victorian theatre, has recently been renovated. Also, the city has three 10 screen cinemas. There is a library theatre which shows more artistic films. The city has a large number of museums many of which demonstrate Sheffield's industrial past, and there are a number of Galleries in the City, including the Mapping Gallery and Ruskin. A number of important ancient houses are close to Sheffield such as Chatsworth House. The Peak District National Park is a beautiful site for visiting and rambling upon. There are large shopping areas in the City and by 1995 Sheffield will be served by a 'supertram' system: the line to the Meadowhall shopping and leisure complex is already open. The University of Sheffield's Halls of Residence are situated on the western side of the city in a leafy residential area described by John Betjeman as ``the prettiest suburb in England''. Halifax Hall is centred on a local Steel Baron's house, dating back to 1830 and set in extensive grounds. It was acquired by the University in 1830 and converted into a Hall of Residence for women with the addition of a new wing. ARTIFICIAL INTELLIGENCE AT SHEFFIELD: Sheffield Computer Science Department has a strong programme in Cognitive Systems and is part of the University's Institute for Language, Speech and Hearing (ILASH). ILASH has its own machines and support staff, and academic staff attached to it from nine departments. Sheffield Psychology Department has the Artificial Intelligence Vision Research Unit (AIVRU) which was founded in 1984 to coordinate a large industry/university Alvey research consortium working on the development of computer vision systems for autonomous vehicles and robot workstations. FORMAT AND DEADLINES: Four copies of submitted papers must be received by the Programme Chair no later than 24 OCTOBER 1994 to be considered. Papers should be at most 12 pages in length and be produced in 12 point, with at most 60 lines of text per A4 page and margins at least 1 inch (2.5cm) wide on all sides (default LaTeX article style is OK). They should include a cover sheet (not counted in the 12 page limit) giving the paper title, the abstract, the authors and their affiliations, including a contact address for both electronic and paper mail for the principal author. Papers should be submitted in hard-copy, not electronically. Papers that do not adhere to this format specification may be rejected without review. Notification of acceptance will be sent to authors by 7 DECEMBER 1994 and full camera-ready copy will be due in early JANUARY 1995 (publishers' deadlines permitting). CONFERENCE ADDRESS: Correspondence relating to the conference programme, submissions of papers, etc. should be directed to the conference programme chair at the address below. John Hallam, Department of Artificial Intelligence, University of Edinburgh, 5 Forrest Hill, Edinburgh EH1 2QL, SCOTLAND. Phone: + 44 31 650 3097 FAX: + 44 31 650 6899 E-mail: john at aifh.edinburgh.ac.uk Correspondence concerning local arrangements should be directed to the local arrangements organiser at the following address. Paul Mc Kevitt, Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, ENGLAND. Phone: + 44 742 825572 FAX: + 44 742 780972 E-mail: p.mckevitt at dcs.sheffield.ac.uk  From john at dcs.rhbnc.ac.uk Wed Oct 5 07:47:33 1994 From: john at dcs.rhbnc.ac.uk (john@dcs.rhbnc.ac.uk) Date: Wed, 05 Oct 94 12:47:33 +0100 Subject: Technical Report Series in Neural and Computational Learning Message-ID: <25115.9410051147@platon.cs.rhbnc.ac.uk> The European Community ESPRIT Working Group in Neural and Computational Learning Theory (NeuroCOLT): two new reports available ---------------------------------------- NeuroCOLT Technical Report NC-TR-94-010: ---------------------------------------- Computational Complexity of Neural Networks: a Survey by Pekka Orponen, Department of Computer Science, P. O. Box 26, FIN-00014 University of Helsinki, Finland Abstract: We survey some of the central results in the complexity theory of discrete neural networks, with pointers to the literature. Our main emphasis is on the computational power of various acyclic and cyclic network models, but we also discuss briefly the complexity aspects of synthesizing networks from examples of their behavior. ---------------------------------------- NeuroCOLT Technical Report NC-TR-94-012: ---------------------------------------- A Note on Testing the Resultant by T. Lickteig Universit\"at Bonn and K. Meer RWTH Aachen Germany Abstract: \def\C{\prime \kern -5pt C} % Menge der komplexen Zahlen : \C In a recent paper Shub proposes to attack the complex $P_{\C} $ versus $NP_{\C} $ problem by focussing on lower bounds on testing the resultant of quadratic forms for zero. Taking up this question we show in the present paper a lower bound of order $n^3$ for testing the resultant of $n$ homogeneous polynomials of degree 2 in $n$ unknowns to vanish. ----------------------- The Report NC-TR-94-010 can be accessed and printed as follows % ftp cscx.cs.rhbnc.ac.uk (134.219.200.45) Name: anonymous password: your full email address ftp> cd pub/neurocolt/tech_reports ftp> binary ftp> get nc-tr-94-010.ps.Z ftp> bye % zcat nc-tr-94-010.ps.Z | lpr -l Likewise for NC-TR-94-012. Uncompressed versions of the postscript files have also been left for anyone not having an uncompress facility. A full list of the currently available Technical Reports in the Series is held in a file `abstracts' in the same directory. Best wishes John Shawe-Taylor  From esann at dice.ucl.ac.be Wed Oct 5 11:40:03 1994 From: esann at dice.ucl.ac.be (esann@dice.ucl.ac.be) Date: Wed, 5 Oct 1994 17:40:03 +0200 Subject: ESANN'95: European Symposium on Artificial Neural Networks Message-ID: <9410051637.AA23814@ns1.dice.ucl.ac.be> ******************************************************** * ESANN95 * * * * 3rd European Symposium on Artificial Neural Networks * * Brussels - April 19-20-21, 1995 * * * * What's new in fundamental research ? * * * ******************************************************** First announcement and call for papers ______________________________________ Invitation and Scope of the conference ______________________________________ In 1995, the third European Symposium on Artificial Neural Networks will be organized in Brussels, Belgium. The two first successful editions each gathered about 100 scientists, coming from Western and Eastern Europe, but also from USA, Japan, Australia, New Zealand,... The field of Artificial Neural Networks includes a lot of different disciplines, from mathematics and statistics to robotics and electronics. For this reason, actual studies concern various aspects of the field, sometimes to the detriment of strong, well established foundations for these researches; it is obvious that a better knowledge of the basic aspects of neurocomputing, and more effective comparisons with other computing methods are strongly necessary for a profitable long-term use of neural networks in applications. The purpose of the ESANN conferences is to present the latest results in the fundamental aspects of artificial neural networks. Invited and survey talks will also present a comprehensive view of particular topics of the conference. The program committee of ESANN'95 welcomes papers covering new results or being of tutorial nature, and dealing with theoretical, biological or mathematical aspects of artificial neural networks, or with the relations between neural networks and other fields. The following is a non-exhaustive list of topics which will be covered during ESANN'95 : + theory + models and architectures + mathematics + learning algorithms + biologically plausible artificial networks + formal models of biological phenomena + neurobiological systems + approximation of functions + adaptive behavior + signal processing + statistics + self-organization + evolutive learning Invited talks will be given by H.P. Mallot (Max-Planck-Institut fur Biologische Kybernetik, Tbingen, Germany), and by P. Comon (Thomson-Sintra Sophia Antipolis, France). Other invited talks are to be announced. The conference will be held in the center of Brussels, the capital of Belgium. Close to most great European cities, Brussels is exceptionally well served by closely-knit motorway and railway systems, and an international airport. Besides an artistic and cultural center of attraction, Brussels is also renowned for its countless typical cafs, for its famous and typical Belgian food, and for its considerable night life. Call for contributions ______________________ Prospective authors are invited to submit six originals of their contribution before November 29, 1994. Working language of the conference (including proceedings) is English. Papers should not exceed six A4 pages (including figures and references). Printing area will be 12.2 x 19.3 cm (centered on the A4 page); left, right, top and bottom margins will thus respectively be 4.4, 4.4, 5.2 and 5.2 cm. 10-point Times font will be used for the main text; headings will be in bold characters (but not underlined), and will be separated from the main text by two blank lines before and one after. Manuscripts prepared in this format will be reproduced in the same size in the book. Originals of the figures will be pasted into the manuscript and centered between the margins. The lettering of the figures should be in 10-point Times font size. Figures should be numbered. The legends also should be centered between the margins and be written in 9-point Times font size as follows: Fig. 3. Text follows ... The pages of the manuscript will not be numbered (numbering decided by the editor). AUTHORS ARE STRONGLY INVITED TO ASK FOR THE FULL INSTRUCTIONS FOR AUTHORS (see coordinates below). A separate page (not included in the manuscript) will indicate: + the title of the manuscript + author(s) name(s) + the complete address (including phone & fax numbers and E-mail) of the corresponding author + a list of five keywords or topics On the same page, the authors will copy and sign the following paragraph: "in case of acceptation of the paper for presentation at ESANN 95: - at least one of the authors will register to the conference and will present the paper - the author(s) give their rights up over the paper to the organizers of ESANN 95, for the proceedings and any publication that could directly be generated by the conference - if the paper does not match the format requirements for the proceedings, the author(s) will send a revised version within two weeks of the notification of acceptation." Contributions must be sent to the conference secretariat. Examples of camera-ready contributions can be obtained by writing to the same address. Registration fees _________________ registration before registration after February 1st, 1995 February 1st, 1995 Universities BEF 15000 BEF 16000 Industries BEF 19000 BEF 20000 An "advanced registration form" is available by writing to the conference secretariat (see reply form below). Please ask for this form in order to benefit from the reduced registration fee before February 1st, 1995. Deadlines _________ Submission of papers November 29, 1994 Notification of acceptance January 20, 1995 Symposium April 19-21, 1995 Grants ______ A limited number of grants (registration fees and economic accommodation) will be given to young scientists coming from the European Community or from Central and Eastern European countries (E.C. Human Capital and Mobility program). Please write to the conference secretariat to get an application form for these grants. Deadline for applications: December 31, 1994. Conference secretariat ______________________ Dr. Michel Verleysen D facto conference services 45 rue Masui B - 1210 Brussels (Belgium) phone: + 32 2 245 43 63 Fax: + 32 2 245 46 94 E-mail: esann at dice.ucl.ac.be Information is also available through WWW and anonymous FTP on the following sites: URL: http://www.dice.ucl.ac.be/neural-nets/ESANN/ESANN.html FTP: ftp.dice.ucl.ac.be, directory /pub/neural-nets/ESANN Steering committee __________________ Francois Blayo EERIE, Nimes (F) Marie Cottrell Univ. Paris I (F) Nicolas Franceschini CNRS Marseille (F) Jeanny Herault INPG Grenoble (F) Michel Verleysen UCL Louvain-la-Neuve (B) Scientific committee ____________________ (to be confirmed) Luis Almeida INESC - Lisboa (P) Jorge Barreto UCL Louvain-en-Woluwe (B) Herv Bourlard ICSI Berkeley (USA) Joan Cabestany Univ. Polit. de Catalunya (E) Dave Cliff University of Sussex (UK) Holk Cruse Universitat Bielefeld (D) Dante Del Corso Politecnico di Torino (I) Marc Duranton Philips / LEP (F) Jean-Claude Fort Universite Nancy I (F) Karl Goser Universitat Dortmund (D) Martin Hasler EPFL Lausanne (CH) Philip Husbands University of Sussex (UK) Christian Jutten INPG Grenoble (F) Vera Kurkova Acad. of Science of the Czech Rep. (CZ) Petr Lansky Acad. of Science of the Czech Rep. (CZ) Jean-Didier Legat UCL Louvain-la-Neuve (B) Eddy Mayoraz Rutgers University (USA) Jean Arcady Meyer Ecole Normale Suprieure - Paris (F) Erkki Oja Helsinky University of Technology (SF) Gilles Pags Universite Paris I (F) Alberto Prieto Universitad de Granada (E) Pierre Puget LETI Grenoble (F) Ronan Reilly University College Dublin (IRE) Tamas Roska Hungarian Academy of Science (H) Jean-Pierre Rospars INRA Versailles (F) Jean-Pierre Royet Universite Lyon 1 (F) John Stonham Brunel University (UK) Lionel Tarassenko University of Oxford (UK) John Taylor King's College London (UK) Vincent Torre Universita di Genova (I) Claude Touzet EERIE Nmes (F) Joos Vandewalle KU Leuven (B) Marc Van Hulle KU Leuven (B) Eric Vittoz CSEM Neuchatel (CH) Christian Wellekens Eurecom Sophia-Antipolis (F) Reply form __________ If you wish to receive the final program of ESANN'95, for any address change, or to add one of your colleagues in our database, please send this form to the conference secretariat: D facto conference services 45 rue Masui B - 1210 Brussels (Belgium) phone: + 32 2 245 43 63 Fax: + 32 2 245 46 94 E-mail: esann at dice.ucl.ac.be Please indicate if you wish to receive the advanced registration form. ---------------------------------------------------------------- Name: .......................................................... First Name: .................................................... University or Company: ......................................... Address: ....................................................... ZIP: ................... Town: ................................ Country: ....................................................... Tel: ........................................................... Fax: ........................................................... E-mail: ........................................................ O Please send me the "advanced registration form" ---------------------------------------------------------------- _____________________________ D facto publications - conference services 45 rue Masui 1210 Brussels Belgium tel: +32 2 245 43 63 fax: +32 2 245 46 94 _____________________________  From nadal at physique.ens.fr Wed Oct 5 13:27:31 1994 From: nadal at physique.ens.fr (NADAL Jean-Pierre) Date: Wed, 5 Oct 1994 18:27:31 +0100 Subject: New Paper: infomax and redundancy reduction Message-ID: <199410051727.SAA01831@droopy.ens.fr> FTP-host: archive.cis.ohio-state.edu FTP-file: pub/neuroprose/nadalparga.infomaxredred.ps.Z The following paper has been placed in the Neuroprose repository: "Non linear neurons in the low noise limit: a factorial code maximizes information transfer" J.-P. Nadal (ENS, Paris) and N. Parga (UAM, Madrid) (19 pages) To appear in NETWORK: computation in neural systems ABSTRACT: We investigate the consequences of maximizing information transfer in a simple neural network (one input layer, one output layer), focussing on the case of {\it non linear} transfer functions. We assume that both receptive fields (synaptic efficacies) and transfer functions can be adapted to the environment. he main result is that, for bounded and invertible transfer functions, in the case of a vanishing {\it additive} output noise, and no input noise, maximization of information (Linsker's{\it infomax} principle) leads to a factorial code - hence to the same solution as required by the redundancy reduction principle of Barlow. We show also that this result is valid for {\it linear}, more generally unbounded, transfer functions, provided optimization is performed under an additive constraint, that is which can be written as a sum of terms, each one being specific to one output neuron. Finally we study the effect of a non zero input noise. We find that, at first order in the input noise, assumed to be small as compared to the - small - output noise, the above results are still valid, provided the {\it output} noise is uncorrelated from one neuron to the other. Jean-Pierre Nadal nadal at physique.ens.fr Laboratoire de Physique Statistique Ecole Normale Sup\'erieure 24, rue Lhomond 75231 Paris Cedex05 - France Nestor Parga parga at ccuam3.sdi.uam.es Departamento de F\'isica Te\'orica Universidad Aut\'onoma de Madrid Canto Blanco, 28049 Madrid - Spain ============================================ Retrieve this paper by anonymous ftp from: archive.cis.ohio-state.edu in the /pub/neuroprose directory The name of the paper in this archive is: nadalparga.infomaxredred.ps.Z (19 pages. No hard copy available.)  From sirosh at cs.utexas.edu Thu Oct 6 00:45:31 1994 From: sirosh at cs.utexas.edu (Joseph Sirosh) Date: Thu, 6 Oct 1994 04:45:31 +0000 Subject: CFP: NIPS Post-Conference Workshop on Lateral Connections in the Cortex Message-ID: <199410060445.EAA34040@duckula.cs.utexas.edu> CALL FOR PARTICIPANTS: NIPS POST-CONFERENCE WORKSHOP ---------------------------------------------------- COMPUTATIONAL ROLE OF LATERAL CONNECTIONS IN THE CORTEX Substantial recent evidence indicates that intracortical connections develop in an activity-dependent manner much like the afferent connections to the cortex. For example, the pattern of long-range lateral connections is closely coupled to the pattern of feature detectors in the visual cortex, and can be altered by strabismus and visual deprivation. Several possible functions have been suggested for the lateral connections. They may (1) modulate receptive field properties in a context-dependent manner and mediate perceptual filling in, (2) mediate adult cortical plasticity such as dynamic receptive fields, (3) store associatory information such as Gestalt rules, (4) act as the substrate for stimulus-dependent synchronization and feature binding, and (5) form the locus of perceptual learning in the primary visual cortex. The workshop will focus on collating the open questions and hypotheses about the functional role of intracortical connectivity, and formulating an agenda for computational and analytical modeling. How do patterned lateral connections form and develop? What do the patterns of lateral connectivity tell us about information stored in the cortex? How could associatory information in the lateral connections be expressed during cortical processing? How could lateral connections mediate learning processes in the cortex? What is their role in cortical plasticity? What types of neural network models are best suited for addressing such questions? Organizers: Email: ---------- ------ Joseph Sirosh and Risto Miikkulainen sirosh at cs.utexas.edu Dept of Computer Sciences risto at cs.utexas.edu University of Texas at Austin Austin, TX--78712. The workshop will be one day in length. Tentative speakers at the workshop include Terrence Sejnowski, Jack Cowan and Gary Blasdel. If you would like to contribute a talk, please get in touch with one of the organizers. --  From Dave_Touretzky at DST.BOLTZ.CS.CMU.EDU Sun Oct 9 21:18:57 1994 From: Dave_Touretzky at DST.BOLTZ.CS.CMU.EDU (Dave_Touretzky@DST.BOLTZ.CS.CMU.EDU) Date: Sun, 09 Oct 94 21:18:57 -0400 Subject: Faculty positions in neural computation Message-ID: <25670.781751937@DST.BOLTZ.CS.CMU.EDU> NEURAL COMPUTATION AT CARNEGIE MELLON The Computer Science Department at Carnegie Mellon University, in collaboration with the Center for the Neural Basis of Cognition (CNBC), is soliciting applications for faculty positions in neural computation. The CNBC is a newly-formed research center jointly operated by Carnegie Mellon and the University of Pittsburgh. Through an agressive recruiting program, the Center seeks to increase the already substantial community of Pittsburgh researchers working on the neural basis of cognitive functions such as perception, memory, language, and the planning and coordination of action. Techniques employed by researchers associated with the Center include neuroimaging, single-unit recording, neuronal modeling, computational analysis of neural systems, and clinical patient studies. For the Computer Science positions, investigators are sought who bring strong computational/theoretical skills to bear on the effort to understand intelligent functions in the brain. Send a vita, a statement of interests, copies of relevant publications, and three letters of reference to: Dr. David S. Touretzky Computer Science Department Carnegie Mellon University Pittsburgh, PA 15213-3891 The deadline for initial consideration of applications is January 1, though applications arriving after that date will be considered until the positions are filled. Carnegie Mellon University is an Equal Opportunity Employer.  From mav at psych.psy.uq.oz.au Mon Oct 10 19:55:19 1994 From: mav at psych.psy.uq.oz.au (Simon Dennis) Date: Tue, 11 Oct 1994 09:55:19 +1000 (EST) Subject: Conference of the Australasian Cognitive Science Society Message-ID: <Pine.3.89.9410110940.A339-0100000@psych.psy.uq.oz.au> - CALL FOR PAPERS - 3rd Conference of the Australasian Cognitive Science Society at The University of Queensland Brisbane, Australia April 18-20, 1995 (Preceding the 22nd Australian Experimental Psychology Conference) Abstracts Due: December 2, 1994 Please address all e-mail correspondence to: cogsci95 at psy.uq.oz.au (Do not reply directly to this message) The 3rd Conference of the Australasian Cognitive Science Society will be held at the University of Queensland from Tuesday April 18 to Thursday April 20, 1995. CogSci'95 will precede the 22nd Experimental Psychology Conference (April 21-23). One focus of CogSci'95 will be the application of Cognitive Science to fields such as industry, commerce, and government. VENUE The venue for the Conference is Emmanuel College which is located on the campus of the University of Queensland. The campus, only 4 kms from the centre of Brisbane, is spacious and leafy with exotic and colourful subtropical vegetation, and is surrounded on three sides by a sweeping bend of the Brisbane River. Brisbane, with a population of 1.4 million, is Australia's third largest city, and is the capital of the state of Queensland - the "Sunshine State". Although it is Australia's fastest growing city, it retains and cherishes an enviable lifestyle influenced by its sunny, subtropical climate. It is a scenic and cosmopolitan city of palm studded parks, colourful gardens, shady verandahs, riverside walks and cafes, and al fresco dining. The Brisbane River snakes lazily through the city from the forest clad foothills of the Great Dividing Range which frame the city to the west, to the Pacific Ocean which frames it to the east. Within 90 minutes drive of Brisbane are rainforested mountains, pristine Pacific beaches, tranquil sand islands, and buzzing coastal resorts. Brisbane is the gateway to Queensland which, one fifth the size of the USA, encompasses the Simpson Desert in the west, the tropical rainforests of the north, and of course the Great Barrier Reef along its beautiful Pacific coast. SCIENTIFIC PROGRAMME The aim of the Conference is to promote the interests of the multi- disciplinary field of Cognitive Science. The participation of scholars from all areas of Cognitive Science is invited, including: - Computer Science - Linguistics - Neuroscience - Philosophy - Psychology Additionally, the Conference aims to promote applications of Cognitive Science and encourage participation from researchers in the Asia-Pacific region. The Scientific Programme will include oral and poster presentations, together with symposia. KEYNOTE SPEAKER A keynote speaker will be selected from the submitted papers. SUBMISSION OF ABSTRACTS and PAPERS All abstracts/papers will be refereed. It is intended that selected papers will be published. FULL PAPERS: The submission of full papers will be required if they are to be considered for publication, and will be reviewed. Papers should be 4,000 to 6,000 words with an upper limit of 8,000 words. Please forward FIVE hard copies of the paper, ONE hard copy of the abstract, and the abstract by email or on disk (IBM or Mac) in either ascii or postscript format. ABSTRACTS: If publication is not desired, abstracts only are required and will not be reviewed externally. Abstracts should be 500 words/two pages maximum. Please forward a hard copy and an email or floppy disk version (IBM/Mac) in either ascii or postscript format. SYMPOSIA: Proposals for symposia are invited and should be forwarded to Rebecca Farley at the address below. Symposium organisors are asked to submit an abstract for the symposium, an abstract for each paper, and contact details for each participant. Please submit abstracts as hard copy and by e-mail or on floppy disk (IBM or Mac) in ascii or postscript format. Platform papers will be allocated 20-minutes presentation time plus a 10-minute question time. Symposia will be allocated 90-minutes to 2 hours depending on the number of speakers. Poster dimensions: 1 x 1.2 metres. The deadline for submission of all papers and abstracts is FRIDAY DECEMBER 2, 1994. Notification of acceptance for the conference as poster, platform presentation or symposium paper will be forwarded February 15, 1995. The deadline for submission of revised papers for publication is May 15, 1995. EXHIBITS and WORKSHOP The Conference will include displays of recent books. A Workshop on Applications of Cognitive Science will be held on the afternoon of Thursday April 20. The Workshop is planned to be of interest to delegates of both CogSci'95 and the Experimental Psychology Conference. The emphasis will be on applications of Cognitive Science and Experimental Psychology to industry, government, and commerce. The Organising Committee invites suggestions for applied activities at the Workshop including proposals for symposia, displays, demonstrations, papers, posters, or any ideas that might help to increase interest in applications. It is anticipated that representatives of organisations which are actual or potential users of Cognitive Science and Experimental Psychology will attend the Workshop. Please forward proposals for applied activities to Rebecca Farley by Friday, December 2, 1994. AUSTRALASIAN COGNITIVE SCIENCE SOCIETY AWARD The Australasian Cognitive Science Society Award will be made for an outstanding project by a student on an application of Cognitive Science. The award at CogSci'95 is sponsored by the University of Queensland and comprises $750 prize money and complimentary conference registration. Free registration will also be awarded for commended entries. The Programming Committee would like to encourage the submission of ideas for an applied project from all students. Collaboration with other students on an application of Cognitive Science is also encouraged. Detailed proposals are sought, approximately 6-10 pages in length. The level of detail supplied in a grant application should be taken as a guide for the amount of information to be included in a competition entry. The Organising Committee reserves the right to not award prizes if no entry of sufficient merit is received. For additional information on the Applied Project Competition, contact Rebecca Farley on (07) 365 6230 or email: cogsci95 at psy.uq.oz.au The closing date for entries is Friday, December 2, 1994. SOCIAL PROGRAMME The Social Programme covered by the registration fee includes the opening reception on Monday evening, morning and afternoon teas, lunches on Tuesday and Wednesday, and dinner at Emmanuel College on Tuesday. Delegates are also invited to attend the Conference dinner at Oxley's on the Wharf on Wednesday evening (cost: $40, includes transport and some alcohol), and a BBQ lunch (cost: $10) which will precede the Workshop on Applications on Thursday afternoon. The BBQ and Workshop are to be held in conjunction with EPC. REGISTRATION and SOCIETY MEMBERSHIP The registration fee covers the above social events and also includes membership of the Australasian Cognitive Science Society. The Society is being re-established to promote the interests of Cognitive Science in Australia and to provide a membership base for biennial conference meetings of the Society. Payment by 28/2/95 attracts a reduced registration fee. There are also reduced rates for full-time students and delegates attending both CogSci'95 and EPC. Cheques should be made payable to the Australasian Cognitive Science Society. ACCOMMODATION Accommodation has been booked at King's College, University of Queensland, which is adjacent to the conference venue. Rooms will be allocated on a first-registered, first-served basis. Cost per person per night is $46. Please make your bookings on the attached registration form. ALTERNATIVE ACCOMMODATION Special conference rates apply at the following hotels. Individuals are asked to make their own bookings. When booking, please mention that you are attending the Cognitive Science Conference Toowong Villas (Serviced apartments: $69 per night; 3 nights min.) 11 Ascog Terrace, Toowong Tel: (07) 371 4855 / (008) 777 092; Fax: (07) 371 4661 Inn on the Park ($90 per night) 507 Coronation Drive, Auchenflower Tel: (07) 870 9222 (008) 773 774 All Seasons Abbey Hotel ($90 per night) 160 Roma Street, Brisbane Tel: (07) 236 1444 DOMESTIC AIR TRAVEL - How to book We are pleased to have appointed Ansett Australia as our sole domestic official carrier for CogSci'95. Please support this appointment by flying Ansett Australia when air travel is required. For the cost of a local call, Australia wide, please phone 008 810 532 and quote File Number MC 07272. Ansett Australia will offer the best available discount fare (up to 50% or better). Also available is a range of conference airfares from 15% to 50% off the applicable economy class airfare on Ansett Australia services. These fares are fully refundable. Access to these special fares is via a unique computer file reference number on telephone 008 810 532 Australia wide. Discounted fares are strictly subject to availability and conditions do apply. INTERNATIONAL AIR TRAVEL Air New Zealand is offering a reduction of 7% on the cost of an airfare for conference delegates who are travelling from the USA. To phone the Los Angeles office of Air New Zealand from anywhere in the United States dial 1-800/ 262 1234 SPONSORS The University of Queensland Ansett Australia TIMETABLE & CLOSING DATES Submission of papers/abstracts December 2, 1994 Notification of acceptance for Conference/book February 15, 1995 Registration with discount February 28, 1995 Submission of revised paper for publication May 15, 1995 ADDRESS FOR ALL CORRESPONDENCE Rebecca Farley CogSci'95 - Department of Psychology University of Queensland Brisbane QLD Australia 4072 Phone: (+617) 365 6230 Fax: (+617) 365 4466 E-mail: cogsci95 at psy.uq.oz.au World-wide web: http://psy.uq.oz.au/CogPsych/cogsci95/home.html CogSci'95 ORGANISING COMMITTEE ------------------------------ CONFERENCE CHAIR: Graeme Halford, Psychology, UQ SECRETARIAT: Kerry Chalmers (Sec), Psychology, UQ Glenda Andrews (Treas), Psychology, UQ Rebecca Farley (Admin), Psychology, UQ PROGRAMME & AWARDS: Doug Saddy, Psychology & English, UQ Janet Wiles, Psychology & Comp. Sci, UQ Simon Dennis, Psychology, UQ Terry Dartnall, Computing & IT, Griffith Marilyn Ford, Computing & IT, Griffith Ottmar Lipp, Psychology, UQ PUBLICATIONS & EDITING: Ellen Watson, Philosophy, UQ Terry Dartnall, Computing & IT, Griffith Peter Slezak, Philosophy, UNSW Doug Saddy, Psychology & English, UQ NOTICES & MEMBERSHIP: Kate Stevens, Psychology, UQ Rebecca Farley, Psychology, UQ SOCIAL PROGRAMME: Helen Purchase, Computer Science, UQ VENUE & ACCOMMODATION: Len Dalgleish, Psychology, UQ Helen Purchase, Computer Science, UQ SPONSORSHIP: Joachim Diederich, Computer Science, QUT INCORPORATION: Alan Hayes, Education, UQ Helen Purchase, Computer Science, UQ ---------------------------------------------------------------------------- CogSci'95 REGISTRATION FORM I would like to: attend CogSci'95 yes/no present a paper yes/no organise a symposium yes/no My preferred format is: platform / poster Author(s): Title: Name: Address: Tel: ( ) Fax: ( ) E-mail address: Facilities for slide and overhead projection will be available. Please specify any other requirements: $$ All prices are in Australian dollars $$ King's College ACCOMMODATION (bed & breakfast $46/night): Day of arrival: Day of departure: No. nights: ________ @ $46/night = $ ________ Please notify us of any special dietary requirements. CONFERENCE DINNER - Wednesday ($40) yes/no BBQ LUNCH - Thursday ($10) yes/no $ ________ REGISTRATION (select one) Full paid by 28/2/95........................... $140 Full paid after 28/2/95........................ $150 CogSci if also attending EPC................... $135 CogSci (late) if also attending EPC............ $145 Student paid by 28/2/95........................ $ 90 Student paid after 28/2/95..................... $100 Student CogSci if attending EPC................ $ 85 Student CogSci (late) if attending EPC......... $ 95 $ ________ TOTAL: $ ________ Cheques to be made payable to the Australasian Cognitive Science Society. ADDRESS FOR ALL CORRESPONDENCE Rebecca Farley CogSci'95 - Department of Psychology University of Queensland Brisbane QLD Australia 4072 Phone: (+617) 365 6230 Fax: (+617) 365 4466 E-mail: cogsci95 at psy.uq.oz.au World-wide web: http://psy.uq.oz.au/CogPsych/cogsci95/home.html *************************** Simon Dennis Department of Psychology mav at psych.psy.uq.oz.au Post Doctoral The University of Queensland Research Fellow QLD 4072 Australia  From sassk at macaulay-land-use.scot-agric-res-inst.ac.uk Mon Oct 10 15:21:43 1994 From: sassk at macaulay-land-use.scot-agric-res-inst.ac.uk (Jim Kay) Date: Mon, 10 Oct 94 19:21:43 GMT Subject: Stat-NN reminder Message-ID: <13351.9410101921@mluri.sari.ac.uk> Statistics vs. Neural Networks A Competition Reminder Can artificial neural networks outperform statistical methods in a fair comparison ? Finding applications where they can is one of the main objectives of a two-day workshop to be held on April 19-20, 1995 in Edinburgh, Scotland. We invite entries to this competition which should reach Jim Kay at the address given below by November the first. The decisions reached will be communicated to applicants by the 15th of January, 1995. The best four entries will be selected and one applicant per entry will be invited to attend the workshop and make an oral presentation of their results; costs of accommodation and travel (within the UK) will be provided subject to certain upper bounds. The other general objectives of the workshop are: to discuss problems of statistical interest within ANN research; to discuss statistical concepts and tools that expand the technology of ANN research; to enhance collaborative research involving experts from one or more of the two communities. We look forward to receiving your applications which should include a contact name and address and be no more than 10 typed A4 pages. Jim Kay and Mike Titterington SASS Environmental Modelling Unit Macaulay Land Use Research Institute Craigiebuckler Aberdeen AB9 2 QJ Scotland, UK e-mail : j.kay at uk.ac.sari.mluri (within the UK) j.kay at mluri.sari.ac.uk (internet address) Tel. : +224 - 318611 (ext. 2269) Fax : +224 - 208065  From yves at netid.com Tue Oct 11 14:47:51 1994 From: yves at netid.com (Yves Chauvin) Date: Tue, 11 Oct 94 11:47:51 PDT Subject: Paper available: HMMs and Comput. Biol. Message-ID: <9410111847.AA02335@netid.com> The following paper, "Hidden Markov Models of the G-Protein-Coupled Receptor Family", to be published in the Journal of Computational Biology, and the associated GPCR multiple alignment have been placed on ftp site. Retrieval instructions are given below. Yves Chauvin yves at netid.com ___________________________________________________________________________ Hidden Markov Models of the G-Protein-Coupled Receptor Family Pierre Baldi Jet Propulsion Laboratory and Division of Biology, California Institute of Technology Pasadena, CA 91109 Yves Chauvin Net-ID, Inc. Hidden Markov Model techniques are used to derive a new model of the G-Protein-Coupled Receptor family. The transition and emission parameters of the model are adjusted using a training set comprising 142 sequences. The resulting model is shown to perform well on a number of tasks, including multiple alignments, discrimination, large data base searches, classification and fragment detection. General analytical results on the expectation and standard deviation of the likelihood of random sequences are also presented. ___________________________________________________________________________ Retrieval instructions: The paper is "baldi.hmmgpcr.ps.z". The multiple alignment is "mahmmgpcr.ps.z". Both are in gzip compressed postscript format. To retrieve these files: % ftp ftp.netcom.com Connected to netcom.com. 220 netcom FTP server (Version 2.0WU(10) [...] ready. Name (netcom.com:yourname): anonymous 331 Guest login ok, send your complete e-mail address as password. Password: .. ftp> cd pub/netid/papers ftp> ls ftp> binary ftp> get <filename> ftp> close .. % gunzip <filename> (The postcript file is large and old printers may not be able to print it).  From cristina at idsia.ch Wed Oct 12 07:11:49 1994 From: cristina at idsia.ch (Cristina Versino) Date: Wed, 12 Oct 94 12:11:49 +0100 Subject: Position Announcement Message-ID: <9410121111.AA03255@fava.idsia.ch> The Istituto Dalle Molle di Studi sull'Intelligenza Artificiale (IDSIA) has an immediate opening for a: Director of research in AI learning paradigms. The ideal candidate should: - have a PhD in Artificial Intelligence - have three years experience in managing projects - have a strong interest in learning paradigms IDSIA - Istituto Dalle Molle di Studi sull'Intelligenza Artificiale is a research center located in Lugano, in the Italian part of Switzerland. The Institute receives subsidies from both private and public sectors and has been operational since 1989. IDSIA is committed to further investigating AI learning paradigms in the area of reinforcement learning, genetic algorithms, neural networks (among others). The initial contract would be for one year (starting beginning 1995) with the possibility of an extension, subject to funding, of a further four years. If interested, please send resume, description of your current interests in learning paradigms, the names of three referees, and other related information to: IDSIA Luca M. Gambardella Cso. Elvezia 36 CH - 6900 - Lugano Switzerland email: luca at idsia.ch  From ifsa95 at dep.fem.unicamp.br Wed Oct 12 10:26:45 1994 From: ifsa95 at dep.fem.unicamp.br (IFSA95) Date: Wed, 12 Oct 94 09:26:45 EST Subject: IFSA'95 Second Short Call For Papers Message-ID: <9410121226.AA19478@jaguar> Second Call for Papers (short version) ___________ IFSA '95 Sixth International Fuzzy Systems Association World Congress Sao Paulo-Brazil July 22-28, 1995 * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * The full version of IFSA'95 2nd call-for-papers is * * stored in the file * * * * calif.doc * * * * which can be obtained by anonynmous FTP from: * * * * spock.dep.fem.unicamp.br * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * The latest information about IFSA'95 (including the * * call-for-papers) can be obtained via WWW on URL: * * * * htpp://www.inpe.br/meetings/IFSA95/home * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * For further information please contact: * * * * ifsa95 at dep.fem.unicamp.br * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * DEADLINES _________ Reception of 4 copies of 4-page extended abstracts; 1 pre-registration form for each author; and 1 paper submission form - Nov 1st, 1994 Notification of acceptance - Feb 1st, 1995 Reception of camera ready copy for proceedings - Apr 1st, 1995 SECRETARIAT ___________ Address : INPE/Setor de Eventos/ IFSA'95 Av. dos Astronautas, 1758 - Caixa Postal 515 12201-970 Sao Jose' dos Campos - SP - Brazil Phone: +55-123-418977 Fax: +55-123-218743 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - PRE-REGISTRATION FORM Last Name ____________________________________________________________ First name ___________________________________________________________ Organization/Affiliation _____________________________________________ Address ______________________________________________________________ Zip/Postal Code _____________________ City ___________________________ Country ______________________________________________________________ Telephone ___________________________________________________________ Fax __________________________________________________________________ E-mail address ______________________________________________________ 1a) Do you intend to submit a paper at the conference ? Yes __ No __ 1b) As main author ? Yes __ No __ 2) Do you intend to attend the conference ? Yes __ No __ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -  From koch at klab.caltech.edu Wed Oct 12 11:59:44 1994 From: koch at klab.caltech.edu (Christof Koch) Date: Wed, 12 Oct 1994 08:59:44 -0700 Subject: No subject Message-ID: <199410121559.IAA22224@kant.klab.caltech.edu> ASSISTANT PROFESSOR PSYCHOPHYSICS/COGNITIVE AND COMPUTATIONAL NEUROSCIENCE/ NEUROPHYSIOLOGY We invite applications for a tenure-track Assistant Professor position in the Computation and Neural Systems Program and in the Division of Biology at the California Institute of Technology. Applicant should conduct research toward understanding higher perceptual and cognitive functions in humans and other primates. The candidate should carry out a research program in at least two of the following areas: psychophysics, computational and cognitive neuroscience, and behavioral neurophysiology. The initial appointment term is four years, and appointment is contingent upon completion of PhD. Applicants should submit a curriculum vitae, a description of research and three reprints, and arrange for three letters of recommendation to be sent to Prof. Christof Koch, Division of Biology 139-74, Caltech, Pasadena, CA 91125. The California Institute of Technology is an affirmative action / equal opportunity employer. Women, minorities, veterans, and disabled persons are encouraged to apply.  From sbh at eng.cam.ac.uk Wed Oct 12 15:41:45 1994 From: sbh at eng.cam.ac.uk (S.B. Holden) Date: Wed, 12 Oct 1994 15:41:45 BST Subject: Article available by ftp Message-ID: <199410121441.11573@tw700.eng.cam.ac.uk> The following technical report is available by anonymous ftp from the archive of the Speech, Vision and Robotics Group at the Cambridge University Engineering Department. It is accepted for publication in "Neural Computation". On the Practical Applicability of VC Dimension Bounds Sean B. Holden and Mahesan Niranjan Technical Report CUED/F-INFENG/TR.155 October 12, 1994 Cambridge University Engineering Department Trumpington Street Cambridge CB2 1PZ England Abstract This article addresses the question of whether some recent Vapnik-Chervonenkis (VC) dimension based bounds on sample complexity can be regarded as a practical design tool. Specifically, we are interested in bounds on the sample complexity for the problem of training a pattern classifier such that we can expect it to perform valid generalization. Early results using the VC dimension, while being extremely powerful, suffered from the fact that their sample complexity predictions were rather impractical. More recent results have begun to improve the situation by attempting to take specific account of the precise algorithm used to train the classifier. We perform a series of experiments based on a task involving the classification of sets of vowel formant frequencies. The results of these experiments indicate that the more recent theories provide sample complexity predictions that are significantly more applicable in practice than those provided by earlier theories; however, we also find that the recent theories still have significant shortcomings. ************************ How to obtain a copy ************************ a) Via FTP: unix> ftp svr-ftp.eng.cam.ac.uk Name: anonymous Password: (type your email address) ftp> cd reports ftp> binary ftp> get holden_tr155.ps.Z ftp> quit unix> uncompress holden_tr155.ps.Z unix> lpr holden_tr155.ps (or however you print PostScript) The report is 22 pages in length. b) Via postal mail: Request a hardcopy from Dr. Sean B. Holden, Cambridge University Engineering Department, Trumpington Street, Cambridge CB2 1PZ, England. or email me: sbh at eng.cam.ac.uk  From whitney at psych.rochester.edu Wed Oct 12 10:28:43 1994 From: whitney at psych.rochester.edu (Whitney Tabor) Date: Wed, 12 Oct 1994 10:28:43 -0400 Subject: Thesis available: Syntactic Innovation--a Connectionist Model Message-ID: <199410121428.KAA22739@muki.psych.rochester.edu> The following dissertation is available by ftp. There are two alternative formats: tabor.thesis.2up.ps.Z (120 sheets of paper), tabor.thesis.ps.Z (230 sheets of paper). Ftp host: csli.stanford.edu Ftp filename: pub/Preprints/tabor.thesis.2up.ps.Z Ftp filename: pub/Preprints/tabor.thesis.ps.Z Syntactic Innovation: a Connectionist Model Whitney Tabor* Department of Linguistics Stanford University 1994 This thesis uses the continuous representation space of a connectionist network to model syntactic innovation in natural language. Current theories of grammar, following Chomsky 1957, generally take quantitative properties of language use (e.g., context-dependent word-frequency information) to be irrelevant to the determination of grammatical structure. Such theories are not very useful for making constrained predictions about historical grammar change for the changes they can model are unrealistically abrupt and there seems to be no domain-independent structuring of the representation space that reveals which changes are probable and which are not. But recent work in the field of grammaticalization (e.g., Traugott and Heine 1991, Hopper and Traugott 1993) indicates strong, general constraints on grammar change. Moreover, these constraints often have quantitative correlates: changes in the categorical status of a word or morpheme are often preceded by significant shifts in its relative frequency distribution. I show how a recurrent connectionist network trained on word prediction in the manner suggested by Elman 1990 and 1991 is sensitive to the information provided by these quantitative shifts and thus can be used to predict correlations between the frequency changes and categorical changes. The correctness of these predictions is borne out by case studies of degree modifier <sort/kind of> and future <be going to>. Two additional empirical phenomena support the model: linked frequency changes in grammatically related constructions and emergence of hybrid structures during periods of transition. The model permits simplification of the theory of language change by replacing "reanalysis" and "analogical extension" with a single type of change-event. It also permits simplification of the theory of grammar by allowing the same interpolative mechanism to handle both normal productive syntax and the hitherto problematic hybrid cases. *Current address: Whitney Tabor Department of Psychology University of Rochester Meliora Hall---River Campus Rochester, NY 14627  From maass at igi.tu-graz.ac.at Wed Oct 12 17:26:06 1994 From: maass at igi.tu-graz.ac.at (Wolfgang Maass) Date: Wed, 12 Oct 94 22:26:06 +0100 Subject: COLT 95: CALL FOR PAPERS (plaintext version) Message-ID: <9410122126.AA01624@figids01.tu-graz.ac.at> ______________________________________________________________________ CALL FOR PAPERS---COLT 95 Eighth Conference on Computational Learning Theory Santa Cruz, California, USA; July 5-8, 1995 ______________________________________________________________________ The Eighth Conference on Computational Learning Theory (COLT 95) will be held on the campus of the University of California at Santa Cruz, USA, from the late afternoon of Wednesday, July 5, through Saturday, July 8, 1995. COLT 95 is sponsored by the University of California, in cooperation with the ACM Special Interest Groups for Algorithms and Computation Theory (SIGACT) and Artificial Intelligence (SIGART). We invite papers in all areas that relate directly to the analysis of learning algorithms and the theory of machine learning, including ARTIFICIAL AND BIOLOGICAL NEURAL NETWORKS. We also invite papers on learning from related theoretical and applied areas, such as statistics, statistical physics, Bayesian/MDL estimation, information theory, inductive inference, logic, inductive logic programming, knowledge representation, knowledge discovery in databases, natural language processing, robotics, and pattern recognition. Besides purely theoretical papers we encourage the submission of papers on experimental results that also provide a theoretical analysis. INVITED TALKS. Invited talks will be given by Terry Sejnowski (Salk Institute and University of California at San Diego) and Les Valiant (Harvard University). ABSTRACT SUBMISSION. Authors should submit fourteen copies (preferably two-sided copies) of an extended abstract to Wolfgang Maass - COLT 95 Institute for Theoretical Computer Science Technische Universitaet Graz, Klosterwiesgasse 32/2 A-8010 Graz, Austria An abstract must be RECEIVED BY JANUARY 10, 1995 (or postmarked by January 2 and sent airmail). This deadline is FIRM! Papers that have appeared in journals or other conferences, or that are being submitted to other conferences, are not appropriate for submission to COLT. There is a single exception: Since in 1995 the notification date for STOC is shortly after the submission deadline for COLT, these conferences have agreed that a paper can be submitted both to STOC 95 and COLT 95, with the understanding that such paper is automatically withdrawn from COLT if accepted at STOC. ABSTACT FORMAT. The extended abstract should consist of a cover page with title, authors' names, postal and e-mail addresses, and a 200-word summary. The body of the abstract should be no longer than 10 pages with roughly 35 lines/page in 12-point font. Papers deviating significantly from this length constraint will not be considered. The body should include a clear definition of the theoretical model used, an overview of the results, and some discussion of their significance, including comparison to other work. Proofs or proof sketches should be included. PROGRAM FORMAT. The program will consist of both "long" talks, and "short" talks, corresponding to longer and shorter papers in the proceedings. The short talks will also be coupled with a poster presentation in special poster sessions. By default, all papers will be considered for both categories. Authors who DO NOT want their papers considered for the short category should indicate that fact in the cover letter. The cover letter should also specify the contact author and give his/her e-mail. NOTIFICATION. Authors will be notified of acceptance or rejection by a letter mailed on or before Friday, March 10, with possible earlier notification via e-mail. Final camera-ready papers will be due by Tuesday, April 11. PROGRAM CHAIR. Wolfgang Maass (TU Graz, Austria, e-mail: maass at igi.tu-graz.ac.at). CONFERENCE AND LOCAL ARRANGEMENTS CHAIRS. David Haussler and Manfred Warmuth (U. of California at Santa Cruz) PROGRAM COMMITTEE. Dana Angluin (Yale), Peter Bartlett (ANU, Australia), Tom Dietterich (Oregon State Univ.), Haym Hirsh (Rutgers), Jeff Jackson (CMU), Martin Kummer (Univ. Karlsruhe), Phil Long (Duke Univ.), Ron Rivest (MIT), Robert Schapire (AT&T), Ted Slaman (Univ. of Chicago), Naftali Tishby (Hebrew Univ.), Gyorgy Turan (UIC, Chicago). COLT AND ML. The Twelfth Intern. Conf. on Machine Learning (ML 95) will be held right after COLT 95 on July 9 - 12 at Tahoe City, California. Car pools from Santa Cruz to Tahoe City on July 8 will be arranged.  From MDUDZIAK at Gems.VCU.EDU Mon Oct 10 16:40:28 1994 From: MDUDZIAK at Gems.VCU.EDU (MARTIN DUDZIAK) Date: Mon, 10 Oct 1994 16:40:28 -0400 (EDT) Subject: A couple of these WWW servers of interest to the group Message-ID: <mailman.707.1149591318.29955.connectionists@cs.cmu.edu> NEW WWW SERVERS at Virginia Commonwealth Univ (VCU) & Medical College of Virginia Buzzwords: Biotech Biomaterials Biomedicine Dynamical (complex, non-linear) systems Neural nets / neurocomputing Molecular engineering Biocomputing Nanotechnology Quantum physics Biophysics Russia Ukraine FSU The following information is provided to a number of places that maintain WWW servers. Several topics are covered, not all of which will be of interest to everyone, but this seemed a simpler and more efficient way of disseminating the information: Homepage on Life Sciences R&D at VCU and MCV http://opal.vcu.edu/html/biomede/bio-science.html Hompage on Virginia Biotechnology Research Park http://opal.vcu.edu/html/biomede/vbrp.html Homepage on Molec Engineering and Nanotechnology and Scanning Probe Microscopy http://opal.vcu.edu/html/biomede/molsys.html Homepage on Complex Dynamical Systems Research including neurocomputing but with a strongly bio/physics approach (less of the standard ANNs, more of neurons) http://opal.vcu.edu/html/biomede/compdyn.html Homepage on the School of Medicine at MCV http://opal.vcu.edu/html/biomede/schofmed.html Homepage on Biotech activities in the Former Soviet Union http://opal.vcu.edu/html/biomede/fsu-biotech.html Homepage on the Biomedical Engineering Program (MS, PhD) at VCU http://opal.vcu.edu/html/biomede/departments/deptofbme.html The main instigator of most of this has been Dr. Martin Dudziak in the Biomed Engr. Dept., so if you want more info and want to make comments, send msgs to me at mdudziak at gems.vcu.edu  From kenm at sunrae.sscl.uwo.ca Thu Oct 13 01:25:27 1994 From: kenm at sunrae.sscl.uwo.ca (kenm@sunrae.sscl.uwo.ca) Date: Thu, 13 Oct 1994 10:25:27 +0500 Subject: Position in Psychology Message-ID: <9410131425.AA01044@sunrae.sscl.uwo.ca> *********************************************************************** FACULTY POSITION IN COGNITIVE PSYCHOLOGY *********************************************************************** The University of Western Ontario, Department of Psychology, invites applications for a probationary (tenure-track) position at the Assistant or beginning Associate Professor level. Individuals with research interests in any area of Cognitive Psychology are invited to apply as our intention is to hire the strongest candidate regardless of specialty area. The successful candidate will have strong doctoral-level academic training, plus demonstrated ability in research and teaching. Applicants should submit a copy of their vita, copies of representative publications, and arrange to have three letters of recommendation sent to: Dr. Clive Seligman, Chair Department of Psychology The University of Western Ontario London, Ontario, Canada N6A 5C2. This position is subject to budgetary approval. The scheduled starting date is July 1, 1995. In accordance with Canadian Immigration requirements, this advertisement is directed to Canadian Citizens and Permanent Residents of Canada. The University of Western Ontario is committed to employment equity, welcomes diversity in the workplace, and encourages applications from all qualified individuals including women, members of visible minorities, aboriginal persons,and persons with disabilities.  From harnad at ecs.soton.ac.uk Thu Oct 13 19:50:21 1994 From: harnad at ecs.soton.ac.uk (Stevan Harnad) Date: Thu, 13 Oct 94 19:50:21 BST Subject: Computer Models of Affective States Message-ID: <3910.9410131850@louis.ecs.soton.ac.uk> From KAISER at ch.unige.uni2a Wed Oct 12 12:21:50 1994 From: KAISER at ch.unige.uni2a (KAISER@ch.unige.uni2a) Date: Wed, 12 Oct 1994 16:21:50 +0000 (WET-DST) Subject: Program of GEW'95 Message-ID: <mailman.708.1149591319.29955.connectionists@cs.cmu.edu> Call for Applications GENEVA EMOTION WEEK '95 April 8 to April 13, 1995 University of Geneva, Switzerland The Emotion Research Group at the University of Geneva announces the third GENEVA EMOTION WEEK (GEW '95), consisting of a colloquium focusing on a major topic in the psychology of emotion, and of a series of workshops designed to introduce participants to advanced research methods in the field of emotion. The colloquium consists of extensive presentations of theoretical and methodological approaches as well as recent empirical work by a group of invited speakers and faculty members of the University of Geneva. Ample time is allotted for discussion. The colloquium lasts 3 days. The theme chosen for the GEW '95 is: Artificial Emotions The intention of GEW'95 is to bring together researchers in diverse disciplines, including AI, neurosciences, philosophy, and psychology, who share an interest in architectures and mechanisms underlying emotion, motivation, and intelligence. The focus is on architectural requirements for an autonomous agent, combining the various sub- functions and sub-mechanisms normally studied separately in AI and Psychology. GEW'95 is organized in collaboration with the Cognition and Affect Group under the direction of Prof. Aaron Sloman at the Cognitive Science Research Center, University of Birmingham. This group organized the first Workshop on Architectures for Understanding Motivation and Emotions (WAUME93) at Birmingham and is pleased that WAUME95 is to be merged with GEW'95. Speakers and Topics of the colloquium: -------------------------------------- Prof. Joseph Le Doux, New York University: - Neural Computation of Emotional Meaning by the Brain. Prof. Stevan Harnad, University of Southampton: - Measuring and Modelling Performance Capacities and Qualitative States. Prof. Aaron Sloman, University of Birmingham: - Architectures for Emotional Agents. Prof. Klaus Scherer, University of Geneva: - Computer Modeling of Appraisal Processes. Discussant: Prof. Nico Frijda, Univ. Amsterdam The workshops will be dedicated to practical work, e.g. simulation models, tools, problems, etc. The workshops listed below will be held by the organizers and the invited speakers. In addition, 2 or 3 workshop proposals from participants for workshops lasting between 1.5 and 3 hours will be selected on a competitive basis. At the end of each workshop day there will be a session (3 x 2h) for posters, demonstrations, videos, and individual discussions. The topics of the invited workshops, each lasting approx. 3 hours are: ---------------------------------------------------------------------- Dr. Jorge Armony, Center for Neuroscience, New York: - An Anatomically Constrained Connectionist Model of Fear Conditioning. Prof. Stevan Harnad, Southampton: - Turing Testing and the Causal Status of Affect. Prof. Aaron Sloman, Cognition and Affect Group, Birmingham: - Exploring Motivated Agent Design. Dr. Prem Kalra, Prof. Nadia Magnenat Thalmann, Miralab, Geneva: - Simulating Facial Expressions and Phonemes for Virtual Humans. Dr. Thomas Wehrle, Prof. Klaus Scherer, Emotion Research Group, Geneva: - Computational Models: Open Issues. - A Psychological Modeling Environment for Autonomous Agents. Prospective participants are researchers or doctoral students working in AI, neurosciences, philosophy, or psychology. Admission for the limited number of places is decided on the basis of prior application. People interested in participating are asked to fill in the enclosed application form as soon as possible and before January 31, 1995 ========================================================================= APPLICATION FORM (please append a short Curriculum Vitae) GENEVA EMOTION WEEK (GEW'95): April 8 to 13, 1995 Name:.................................................................... First Name:..............................................................  From eann95 at ra.abo.FI Fri Oct 14 02:44:22 1994 From: eann95 at ra.abo.FI (EANN-95 Konferensomrede VT) Date: Fri, 14 Oct 1994 08:44:22 +0200 (EET) Subject: Call for Papers Message-ID: <199410140644.IAA11985@aton.abo.fi> International Conference on Engineering Applications of Neural Networks (EANN '95) Helsinki, Finland August 21-23, 1995 First Call for Papers (ASCII version) The conference is a forum for presenting the latest results on neural network applications in technical fields. The applications may be in any engineering or technical field, including but not limited to systems engineering, mechanical engineering, robotics, process engineering, metallurgy, pulp and paper technology, aeronautical engineering, computer science, machine vision, chemistry, chemical engineering, physics, electrical engineering, electronics, civil engineering, geophysical sciences, biotechnology, and environmental engineering. Abstracts of one page (200 to 400 words) should be sent to eann95 at aton.abo.fi by 31 January 1995, preferably by e-mail in PostScript format, or in TeX or LaTeX. ASCII is also acceptable. Please mention two to four keywords, and whether you prefer it to be a short paper or a full paper. The short papers will be 4 pages in length, and full papers may be upto 8 pages. Tutorial proposals are also welcome until 31 January 1995. Notification of acceptance will be sent around 1 March. The number of full papers will be very limited. Local program committee (to be confirmed, extended) A. Bulsari (Finland) J. Heikkonen (Finland) E. Hyv\"onen (Finland) P. Linko (Finland) L. Nystr\"om (Finland) S. Palosaari (Finland) H. Sax\'en (Finland) J. Sepp\"anen (Finland) International program committee (to be confirmed, extended) G. Dorffner (Austria) A. da Silva (Brazil) V. Sgurev (Bulgaria) S. Dutta (France) C. M. Lee (Hong Kong) H. Siegelmann (Israel) R. Baratti (Italy) R. Serra (Italy) G. Baier (Germany) J. Fodor (Hungary) I. Kawakami (Japan) C. Kuroda (Japan) J. K. Lee (Korea) J. Kok (Netherlands) J. Paredis (Netherlands) S. Tan (Singapore) A. Dobnikar (Slovenia) B. Martinez (Spain) H. Liljenstr\"om (Sweden) G. Sj\"odin (Sweden) J. Sj\"oberg (Sweden) D. Tsaptsinos (UK) N. Steele (UK) S. Shekhar (USA)  From mike at PARK.BU.EDU Thu Oct 13 21:02:40 1994 From: mike at PARK.BU.EDU (mike@PARK.BU.EDU) Date: Thu, 13 Oct 1994 21:02:40 -0400 Subject: CNS graduate program Message-ID: <199410140102.VAA22895@space.bu.edu> *********************************************** * * * DEPARTMENT OF * * COGNITIVE AND NEURAL SYSTEMS (CNS) * * AT BOSTON UNIVERSITY * * * *********************************************** Stephen Grossberg, Chairman Gail A. Carpenter, Director of Graduate Studies The Boston University Department of Cognitive and Neural Systems offers comprehensive graduate training in the neural and computational principles, mechanisms, and architectures that underlie human and animal behavior, and the application of neural network architectures to the solution of technological problems. Applications for Fall, 1995 admission and financial aid are now being accepted for both the MA and PhD degree programs. To obtain a brochure describing the CNS Program and a set of application materials, write, telephone, or fax: Department of Cognitive & Neural Systems Boston University 111 Cummington Street, Room 240 Boston, MA 02215 617/353-9481 (phone) 617/353-7755 (fax) or send via email your full name and mailing address to: rll at cns.bu.edu Applications for admission and financial aid should be received by the Graduate School Admissions Office no later than January 15. Late applications will be considered until May 1; after that date applications will be considered only as special cases. Applicants are required to submit undergraduate (and, if applicable, graduate) transcripts, three letters of recommendation, and Graduate Record Examination (GRE) scores. The Advanced Test should be in the candidate's area of departmental specialization. GRE scores may be waived for MA candidates and, in exceptional cases, for PhD candidates, but absence of these scores may decrease an applicant's chances for admission and financial aid. Non-degree students may also enroll in CNS courses on a part-time basis. Description of the CNS Department: The Department of Cognitive and Neural Systems (CNS) provides advanced training and research experience for graduate students interested in the neural and computational principles, mechanisms, and architectures that underlie human and animal behavior, and the application of neural network architectures to the solution of technological problems. Students are trained in a broad range of areas concerning cognitive and neural systems, including vision and image processing; speech and language understanding; adaptive pattern recognition; cognitive information processing; self-organization; associative learning and long-term memory; computational neuroscience; nerve cell biophysics; cooperative and competitive network dynamics and short-term memory; reinforcement, motivation, and attention; adaptive sensory-motor control and robotics; active vision; and biological rhythms; as well as the mathematical and computational methods needed to support advanced modeling research and applications. The CNS Department awards MA, PhD, and BA/MA degrees. The CNS Department embodies a number of unique offerings. It has developed a curriculum that features twelve interdisciplinary graduate courses each of which integrates the psychological, neurobiological, mathematical, and computational information needed to theoretically investigate fundamental issues concerning mind and brain processes and the applications of neural networks to technology. Each course is typically taught once a week in the evening to make the program available to qualified students, including working professionals, throughout the Boston area. Nine additional research course are also offered. In these courses, one or two students meet regularly with one or two professors to pursue advanced reading and collaborative research. Students develop a coherent area of expertise by designing a program that includes courses in areas such as Biology, Computer Science, Engineering, Mathematics, and Psychology, in addition to courses in the CNS Department. The CNS Department prepares students for PhD thesis research with scientists in one of several Boston University research centers or groups, and with Boston-area scientists collaborating with these centers. The unit most closely linked to the department is the Center for Adaptive Systems (CAS). Students interested in neural network hardware work with researchers in CNS, the College of Engineering, and at MIT Lincoln Laboratory. Other research resources include distinguished research groups in neurophysiology, neuroanatomy, and neuropharmacology at the Medical School and the Charles River campus; in sensory robotics, biomedical engineering, computer and systems engineering, and neuromuscular research within the Engineering School; in dynamical systems within the Mathematics Department; in theoretical computer science within the Computer Science Department; and in biophysics and computational physics within the Physics Department. In addition to its basic research and training program, the Department offers a colloquium series, seminars, conferences, and special interest groups which bring many additional scientists from both experimental and theoretical disciplines into contact with the students. 1994-95 CAS MEMBERS and CNS FACULTY: Jelle Atema Helen Barbas Jacob Beck Daniel H. Bullock Gail A. Carpenter Laird Cermak Michael A. Cohen H. Steven Colburn William D. Eldred III Paolo Gaudiano Jean Berko Gleason Stephen Grossberg Frank H. Guenther Thomas G. Kincaid Nancy Kopell Ennio Mingolla Alan Peters Andrzej Przybyszewski Adam Reeves William D. Ross Robert Savoy Eric L. Schwartz Robert Sekuler Allen Waxman Jeremy Wolfe  From esann at dice.ucl.ac.be Fri Oct 14 12:35:01 1994 From: esann at dice.ucl.ac.be (esann@dice.ucl.ac.be) Date: Fri, 14 Oct 1994 18:35:01 +0200 Subject: Neural Processing Letters Vol.1 No.1 Message-ID: <9410141731.AA04018@ns1.dice.ucl.ac.be> The following articles may be found in the first issue of the "Neural Processing Letters" journal (September 1994): - Fast learning with incremental RBF networks B. Fritzke - Fractal variations of attractors in complex-valued neural networks A. Hirose - Basic mechanisms of coding stimulus intensity in olfactory sensory neuron P. Lansky, J.-P. Rospars, A. Vermeulen - A way to improve an architecture of neural network classifier for remote sensing applications J. Korczak, F. Hammadi-Mesmoudi - Intelligent judge network for speech recognition D.-S. Kim - An on-line learning algorithm for the orthogonal weight estimation of MLP N. Pican, J.-C. Fort, F. Alexandre - Texture segmentation using pyramidal Gabor functions and self-organising feature maps A. Guerin-Dugue, P.M. Palagui - Book review: Neural network time series forecasting of financial markets (E.M. Azoff) E. De Bodt We remind you that all information concerning this journal may be found on the following servers: - FTP server: ftp.dice.ucl.ac.be directory: /pub/neural-nets/NPL - WWW server: http://www.dice.ucl.ac.be/neural-nets/NPL/NPL.html For any information (subscriptions, instructions for authors,...), you can also directly contact the publisher: D facto publications 45 rue Masui B-1210 Brussels Belgium Phone: + 32 2 245 43 63 Fax: + 32 2 245 46 94 _____________________________ D facto publications - conference services 45 rue Masui 1210 Brussels Belgium tel: +32 2 245 43 63 fax: +32 2 245 46 94 _____________________________  From jose at scr.siemens.com Fri Oct 14 14:19:45 1994 From: jose at scr.siemens.com (Stephen Hanson) Date: Fri, 14 Oct 1994 14:19:45 -0400 (EDT) Subject: McDonnell-PEW Program in Cognitive Neuroscience Message-ID: <oibgj1_1GEMnI8PVIf@tractatus.siemens.com> McDonnell-Pew Program in Cognitive Neuroscience McDonnell-Pew Program in Cognitive Neuroscience announces new guidelines for Investigator - Initiated Grants. Awards are $35,000/year for up to three years for interdisciplinary research and training. Deadline for receipt of proposals is February, 1995. For proposal guidelines and additional information contact; Susan Fitzpatrick, Program Officer, James S. McDonnell Foundation email: C06819CN at WUVMD.WUSTL.edu phone: 314-721-1532 or fax: 314-721-7421. PLEASE REPOST sjh. Stephen J. Hanson, Ph.D. Head, Learning Systems Department SIEMENS Research 755 College Rd. East Princeton, NJ 08540  From harnad at ecs.soton.ac.uk Sat Oct 15 13:43:44 1994 From: harnad at ecs.soton.ac.uk (Stevan Harnad) Date: Sat, 15 Oct 94 13:43:44 BST Subject: Colloque de Lyon Message-ID: <25898.9410151243@louis.ecs.soton.ac.uk> From payette at ca.uqam.atoci.uranus Wed Oct 12 18:32:43 1994 From: payette at ca.uqam.atoci.uranus (payette@ca.uqam.atoci.uranus) Date: Wed, 12 Oct 94 18:32:43 EDT Subject: Colloque de Lyon Message-ID: <mailman.709.1149591319.29955.connectionists@cs.cmu.edu> The Seventh Colloquium of the Jacques Cartier Center Lyon, France. THE COGNITIVE SCIENCES: FROM COMPUTATIONAL MODELS TO THE PHILOSOPHY OF MIND Wednesday, November 30th to Friday, December 2nd 1994 under the aegis of: the Pole Rhones-Alpes of the Cognitive Sciences, Programme Interdisciplinaire de Recherche Cognisciences,CNRS Universite du Quebec a Montreal Universite de Montreal Universite Joseph Fourier Universite Claude Bernard Scientific committee: Denis Fisette (Universite du Quebec a Montreal, Quebec) Marc Jeannerod (Universite Claude Bernard, Lyon) Daniel Laurier (Universite de Montreal, Quebec) Daniel Payette (Universite du Quebec a Montreal, Quebec) Vincent Rialle (Universite Joseph Fourier, Grenoble) Guy Tiberghien (Universite Pierre Mendes-France, Grenoble) Coordination in North America: Daniel Payette and Denis Fisette Universite du Quebec a Montreal, Dpt de Philosophie, Dpt Psychology; C.P. 8888,Succ A, Montreal (Quebec) H3C-3P8, Canada; E.mail : payette at uranus.atoci.uqam.ca; tel (+514) 987 8418; Fax: (+514) 9876721 Coordination in Europe: Vincent Rialle Universite J. Fourier, Labo.TIMC-IMAG, Faculte de Medecine, 38706 LaTronche Cedex E.mail: Vincent.Rialle at imag.fr; Tel. (+33) 76 63 71 87; Fax. (+33) 76 51 8667 DATES: Wednesday, November 30th to Friday, December 2nd 1994 CONFERENCE SITE: Amphitheatre CHARLES BERAUDIER. Conseil Regional RHONE-ALPES,78 route de Paris, 69751 CHARBONNIERES-les-BAINS. France *Talks will only be given by invited speakers. (Simultaneous French-English and English-French will be provided). THEME OF COLLOQUIUM The modeling of mental processes in the various human cognitive activities has generated increasing interest in the scientific world today. Cognitive models, cognitive simulations, auto-organization, adaptation, emergence, genetic selection, Darwinian mentalism and enaction are active research topics in neurological and psychological theory. The cognitive sciences offer a continuum of research extending from the engineering sciences to the philosophy of mind, including the neurosciences, cognitive psychology, linguistics, semantics, semiotics and artificial intelligence. Three subconferences will organize themselves around the following major complementary themes: (i) Modeling (cognitive and brain functions), (ii) Philosophy of Mind and Epistemology, and (iii) Applications (AI, technical and computational engineering). (i) Modeling is a point of intersection for all these specialties because it includes the modeling of functions and dysfunctions of the central nervous system, the neurocomputer sciences, the modeling of psychocognitive and mental processes, the emergence of intentional structure on the basis of biological structure, enaction, genetic algorithms, neural networks, artificial "life," etc. (ii) The philosophical and epistemological subcomponent poses questions like the following: Can we elaborate mathematical models of the mind and use them to describe and explain human behavior? Are we aiming toward a mathematical model of the mind? Can we capture the formal principles of the development and emergence of cognition? Can we technologically recreate thought? Is the computational symbolic paradigm, which has imposed itself for the last decades, still a powerful conceptual tool or is it proving too reductionistic and if so, how? What is the epistemological status of, for example, the alternative proposed by the parallel distributed model to the computational models of classical cognitivism? Wich relations can be established between the modeling activity of the cognitive and neurosciences and human experience? (iii) The applications subconference will consider practical domains in which scientific results have been applied in the treatment of language, the automated cognitive analyses of textual documents (an intersection of linguistics, semantics, semiotics and artificial intelligence), aids to decision making, applications in sensory information processing, etc. OFFICIAL PROGRAM WEDNESDAY, 30 November 1994 8h15 - 8h30 Allocution d'accueil du Conseil Regional 8h30 - 9h Guy Tiberghien (Universite Pierre Mendes-France, Grenoble) Introduction SESSION 1 :NEURO AND PSYCHOLOGICAL MODELING 9h - 9h-30 Jean Francois Le Ny (Universite Paris-Sud, psychologie cognitive) Pourquoi les modeles cognitifs devraient-ils etre calculatoires ? 9h30 - 9h45 Discussion 9h-45 - 10h15 Marc Jeannerod (Universite Claude Bernard, Lyon, neurosciences) The Representational Brain 10h15 - 10h30 Discussion 10h30 - 10h45 PAUSE 10h45 - 11h15 Zenon Pylyshyn (Rutgers University, USA, psychologie cognitive) What's in the Mind? A Computational Approach to a Ancient Question. 11h15 - 11h30 Discussion 11h30 - 12h00 Stevan Harnad (Princeton University, psychologie cognitive) Modeles, mobiles et mentalite 12h00 - 12h15 Discussion MEAL 14h00 - 14h30 Michel Imbert (Universite Paul Sabatier, Toulouse, neurosciences) De l'etude du cerveau a la comprehension de l'esprit 14h30 - 14h45 Discussion 14h45 - 15h15 Guy Tiberghien (Univers Pierre Mendes-France,Grenoble,psychologie cognitive) Connexionnisme: stade supreme du behaviorisme ? 15h15 - 15h30 Discussion 15h30 - 15h45 PAUSE 15h45 - 16h15 Jacques Demongeot (Universite Joseph Fourier, Grenoble, neurosciences) Memoire d'evocation dans les reseaux de neurones 16h15 - 16h30 Discussion 16h30 - 17h00 Bennet Murdock (Universite de Toronto, psychologie cognitive) THE ROLE OF FORMAL MODELS IN MEMORY RESEARCH 17h00 - 17h15 Discussion 17h15 - 17h45 Robert Proulx (Universite du Quebec a Montreal, neuro-psychologie) Plausibilite biologique de certains systemes de categorisation adaptative a base de reseaux de neurones 17h45 - 18h00 Discussion TUESDAY, December 1 Session 2 : EPISTEMOLOGY, PHILOSOPHY OF MIND and COGNITION 9h - 9h30 Elisabeth Pacherie (Universite de Provence, CNRS & CREA, Paris) Cognitive Domains and Modularity 9h30 - 9h45 Discussion 9h-45 - 10h15 Pierre Livet (Universite de Provence & CREA, Paris, philosophie) Categorisation et connexionnisme 10h15 - 10h30 Discussion 10h30 - 10h45 PAUSE Normand Lacharite (Universite du Quebec a Montreal, epistemologie) 10h45 - 11h15 Conflits de modeles en theorie de la representation 11h15 - 11h30 Discussion 11h30 - 12h00 Peter Gardenfors (Lund University, Suede, philosophie) Language and the Evolution of Mind 12h15 - 12h15 Discussion MEAL 14h00 - 14h30 Andy Clark (Washington University, philosophie) Wild Cognition: Putting Representation in its Place 14h30 - 14h45 Discussion 14h45 - 15h15 Kevin Mulligan (Universite de Geneve, Suisse, philosophie) Constance perceptuelle et contenu spatial 15h15 - 15h30 Discussion 15h30 - 15h45 PAUSE 15h45 - 16h15 Ronald De Sousa (Universite de Toronto, epistemologie) La rationalite: un concept normatif ou descriptif ? 16h15 - 16h30 Discussion 16h30 - 17h00 Daniel Laurier (Universite de Montreal, philosophie) Rationalite et naturalisme 17h00 - 17h15 Discussion 17h15 - 17h45 Joelle Proust (CNRS & CREA, Paris, philosophie) Un modele naturaliste de l'intentionnalite 17h45 - 18h00 Discussion FRIDAY, December 2 Session 3: IA MODELING, LANGUAGE and COGNITIVE SEMANTIC Paul Jorion (Maison des Sciences de l'Homme, Paris, psychologie cognitive) 9h - 9h30 Modelisation du reseau mnesique : une utilisation minimaliste de l'IA 9h30 - 9h45 Discussion 9h-45 - 10h15 Bernard Amy (Universite Joseph Fourier, Grenoble, connexionnisme) Neural Networks in AI 10h15 - 10h30 Discussion 10h30 - 10h45 PAUSE 10h45 - 11h15 Paul Bourgine (CEMAGREF, Paris-Antony, IA-modelisation) Co-evolution et emergence du soi 11h15 - 11h30 Discussion 11h30 - 12h00 Paul Pietroski (Universite McGill, Canada, philosophie) What can linguistics teach us about belief 12h00 - 12h15 Discussion MEAL 14h00 - 14h30 Le paradigme hermeneutique et la mediation semiotique Francois Rastier (Institut National de la Langue Francaise, CNRS, linguistique computationnelle) 14h30 - 14h45 Discussion 14h45 - 15h15 L'impact des perspectives cognitives dans le traitement de l'information Jean-Guy Meunier (Universite du Quebec a Montreal, semiotique) 15h15 - 15h30 Discussion 15h30 - 15h45 PAUSE 15h45 - 16h15 Guy Denhiere (Universite Paris VIII, psychologie cognitive) Isabelle Tapiero (Universite Lyon II, psychologie cognitive) La signification comme structure emergente : de l'acces au lexique a la comprehension de textes 16h15 - 16h30 Discussion 16h30 - 17h00 Paul Freedman (Centre de Recherche en Informatique de Montreal, IA) La vision artificielle: le traitement intelligent de documents 17h00 - 17h15 Discussion 17h15 - 17h45 Denis Vernant (Universite Pierre Mendes-France, Grenoble, philosophie) L'intelligence de la machine et sa capacite dialogique 17h45 - 18h00 Discussion 18h00: END OF COLLOQUIUM ------------------------------------------------------------------------ -ADMISSION FEES- (Includes:access to the conference room, meals and the colloquium documents) Individuals-------------------------------------------------1500FF Student (join proof of eligibility with registration)------- 500FF ------------------------------------------------------------------------- REGISTRATION BULLETIN (The Cognitive Sciences:From computational models to philosophy of mind) Name:___________________________________________________________________ Status:_____________________________________ Institution/Company_________________________ Complete Address_________________________________________________________ Fax:________________________ Phone :______________________ @mail number__________________________________ Enclosed : Check or money order of (_____________________FF) (Make check or money order payable to CENTRE JACQUES CARTIER) -Send information on possibilities of housing in Lyon(______) _Send me the colloquium brochure (_____) -November 30 meal __ -December 1, meal __ -December 2, meal __ RETURN TO: CENTRE JACQUES CARTIER, 86 rue Pasteur, 69365 Lyon Cedex 07, France. Phone:(33) 78 69 72 21 @mail: ferreira at diogene.univ-lyon2.fr  From N.Sharkey at dcs.shef.ac.uk Sat Oct 15 12:13:32 1994 From: N.Sharkey at dcs.shef.ac.uk (N.Sharkey@dcs.shef.ac.uk) Date: Sat, 15 Oct 94 17:13:32 +0100 Subject: job opportunity Message-ID: <9410151613.AA01585@entropy.dcs.shef.ac.uk> Preliminary announcement please feel free to pass to other boards or colleagues. ******************************************** POST-DOCTORAL RESEARCHER POSITION NEURAL NETWORKS FOR COORDINATED ROBOTIC CONTROL Dept Computer Science University of Sheffield, UK ******************************************** A post-doctoral researcher is required for 18 months (in the first instance) to run a project with another researcher on the Coordination of Robotic Control funded by the Engineering and Physical Science Research Council, UK (EPSRC). The researcher would join a small productive team of researchers on two other projects in the Neurocomputing Group at Sheffield: Adaptive Generalisation and Dynamic Neural Nets (Economic and Social Research Council, UK) and Network Programming for Safety Critical Systems (Science and Engineering Research Council/Department of Trade and Industry). Although the project is housed in Computer Science, it is in collaboration with the Department of Automatic Control and Systems Engineering. Applicants should be skilled in C programming and have a proven track record of research on Artificial Neural Nets and be willing to move between different types of learning methods. Experience with robotics or control engineering would be useful but not essential. An important aspect of the project is to develop an intermediate level theory of applications focussed on the coordination of network modules with different architectures and that were trained by different learning methods. All formal application must be send to the University Personell Department who will also send out further particulars. I will send out a more formal advert to this effect next week. This is just a preliminary announcement to get an idea of the field of applications and to get some discussion going. If you are interested please send a brief CV or express your intention to apply to jill at dcs.sheffield.ac.uk Thanks Noel Sharkey Professor of Computer Science Department of Computer Science Regent Court University of Sheffield S1 4DP, Sheffield, UK N.Sharkey at dcs.shef.ac.uk FAX: (0742) 780972  From meade at caesar.rice.edu Sun Oct 16 17:04:13 1994 From: meade at caesar.rice.edu (Andrew Meade 238Cox x4906) Date: Sun, 16 Oct 94 16:04:13 CDT Subject: Paper on Neuroprose: Solution of Nonlinear ODEs Message-ID: <9410162104.AA03016@calpurnia.rice.edu> FTP-host: archive.cis.ohio-state.edu FTP-file: pub/neuroprose/meade.nonlinearodes.ps.Z ================================================================= The following paper has been placed in the Neuroprose archive at Ohio State University: "Solution of Nonlinear Ordinary Differential Equations by Feedforward Neural Networks" A.J. Meade, Jr. and A.A. Fernandez (25 pages. No hard copies available.) To appear in Mathematical and Computer Modelling ABSTRACT: It is demonstrated, through theory and numerical examples, how it is possible to directly construct a feedforward neural network to approximate nonlinear ordinary differential equations without the need for training. The method, utilizing a piecewise linear map as the activation function, is linear in storage, and the $L_2$ norm of the network approximation error decreases monotonically with the increasing number of hidden layer neurons. The construction requires imposing certain constraints on the values of the input, bias, and output weights, and the attribution of certain roles to each of these parameters. All results presented used the piecewise linear activation function. However, the presented approach should also be applicable to the use of hyperbolic tangents, sigmoids, and radial basis functions. Andrew J. Meade, Jr. and Alvaro A. Fernandez Rice University Department of Mechanical Engineering and Materials Science Mail Stop 321 Houston, Texas, 77251-1892, USA Phone: (713) 527-8101 ext. 3590 email: meade at rice.edu ============================================ Retrieve this paper by anonymous ftp: unix> ftp archive.cis.ohio-state.edu (or 128.146.8.52) Name: anonymous Password: <your e-mail address> ftp> cd pub/neuroprose ftp> binary ftp> get meade.nonlinearodes.ps.Z ftp> quit unix> uncompress meade.nonlinearodes.ps.Z Thanks to Jordan Pollack for maintaining this archive. A.J. Meade  From bogus@does.not.exist.com Mon Oct 17 15:28:30 1994 From: bogus@does.not.exist.com () Date: Mon, 17 Oct 1994 15:28:30 --100 Subject: No subject Message-ID: <9410171428.AA25623@ti-doz10.fh-weingarten.de> From tij at manet.espci.fr Mon Oct 17 10:59:20 1994 From: tij at manet.espci.fr (tareq i. j. albaho) Date: Mon, 17 Oct 1994 15:59:20 +0100 (MET) Subject: workshop announcement Message-ID: <199410171459.AA12936@muenter.espci.fr> WORKSHOP ON SUPERCOMPUTING IN BRAIN RESEARCH From Tomography to Neural Networks HLRZ, November 21-23, 1994 We are organizing a three days workshop at the HLRZ (German Supercomputer Center) in J\"ulich. As in previous years we have chosen a subject in which supercomputing is making an essential contribution to science; this time in biosciences. During recent years computers have become a central tool in brain research. On one hand the growing complexity of tomographic devices forces us to use reconstruction techniques of highest sophistication, which reach the limits of present computational power. On the other hand the modelling of the brain itself is becoming more and more detailed due to the enormous gain of insight of the last years. Large scale simulations of neural networks have recently even been used as benchmarks for parallel computing. In this workshop we want to bring together various communities interested in supercomputing in brain research: Applied mathematicians who understand how to reconstruct tomographic data; Experts on neural networks, including statistical physicists; Nurophysiologists who simulate neural models and discuss data handling and evaluation problems. The aim is to form a bridge between various levels of brain modelling and tomographically measurable information. If you are interested in participating (or presenting posters) you should contact as soon as possible either of the organizers, E.P\"oppel, H.J. Herrmann or D. Wolf, or the conference secretariat which will provide further information: HLRZ-Workshop; c/o Forschungszentrum J\"ulich, Postfach 1913, D-52425 J\"ulich, FRG Bitnet: HLR006 at djukfa11.bitnet Internet: HLR006 at zam001.zam.kfa-juelich.de Local Organizing Committee: H. Halling, H.J. Herrmann, H.-W. M\"uller-G\"artner, H. M\"uller-Krumbhaar, F. Pasemann, E. P\"oppel, W. Speier, D. Wolf Tentative Schedule, as known on 12 October 1994 Monday, November 21st ===================== 9.30 - 9.45 H. Rollnik, HLRZ-J\"ulich Welcome 9.45 - 10.30 H.-J. Freund, D\"usseldorf Cortical organisation of sensory-motor transformation Coffee Break 11.00 - 11.45 H. Scheich, Magdeburg Coding in the Auditory Pathway, Speech, and Cochlear Protheses 11.45 - 12.30 E. P\"oppel, KFA-J\"ulich Spatial and temporal information processing: Many open questions Lunch 14.00 - 14.45 R. Salmelin, Helsinki MEG in the Study of Human Cortical Functions 14.45 - 15.30 K. Friston, London Characterizing Neural Interactions with Functional Neuroimaging 15.30 - 16.00 B. Lautrup, Kopenhagen Extremely ill-posed learning Coffee Break 16.30 - 17.00 J.M. Drouffe, Saclay Simulating the nervous system of the nematode Caenorhabditis Elegans 17.00 - 17.30 A. Aertsen, Weizmann Inst. Coherent Dynamics of Cortical Activity 17.30 - 18.00 M.Wilson, MIT to be announced 18.00 Reception and Posters Tuesday, November 22nd ====================== 9.00 - 9.45 C. von der Malsburg, Temporal Correlations as Glue of the Mind -A Challenge for Brain Imaging Techniques 9.45 - 10.30 J. Taylor, London Modelling and Testing large scale Brain Activity Coffee Break 11.00 - 11.30 G. Palm, Ulm to be announced \cr 11.30 - 12.00 M. Abeles, Jerusalem Processing of information in the cerebral cortex by well-timed events 12.00 - 12.30 F. Pasemann, KFA J\"ulich Neuromodules: A dynamical systems approach to brain modelling Lunch 14.00 - 14.30 A. Zippelius, G\"ottingen Modelling of Synaptic Transmission 14.30 - 15.00 L. Martignon, Ulm Statistical inference methods for detecting and measuring higher order neural interactions 15.00 - 15.30 M. Opper, W\"urzburg Learning in Artificial Networks Coffee Break 16.00 - 16.30 A. Kleinschmidt, G\"ottingen Functional MRI of the Human Brain: Strategies and Findings 16.30 - 17.00 K. Kwong, Boston The Queen of fMRI: Echo Planar Imaging 17.00 - 17.30 H\"am\"al\"ainen, Helsinki Forward and inverse modelling of neuromagnetic signals \cr 17.30 - 18.00 M. Fuchs , Philips, Advanced Biomagnetic and Bioelectric Hamburg & Reconstruction Algorithms Wednesday, November 23rd ======================== 9.00 - 9.45 N. Logothetis, Houston Shape Representation in the Temporal Cortex of the Primate 9.45 - 10.30 N.N. Coffee Break 11.00 - 11.30 H. M\"uller-G\"artner, to be announced KFA-J\"ulich 11.30 - 12.00 R. G. Mangun, Davis Functional Architecture of Brain Attention Systems 12.00 - 12.30 H.J. Heinze, Magdeburg & Cognitve Modelling and Imaging 14.00 - 16.30 General Discussion, chairman E. P\"oppel Statements and Perspectives 16.30 End of Meeting  From njm at cupido.inesc.pt Tue Oct 18 06:54:50 1994 From: njm at cupido.inesc.pt (njm@cupido.inesc.pt) Date: Tue, 18 Oct 94 10:54:50 +0000 Subject: EPIA'95 - Fuzzy Logic & Neural Nets Worksop CFP Message-ID: <9410181054.AA27056@cupido.inesc.pt> -------------------------------------------------------- EPIA'95 WORKSHOPS - CALL FOR PARTICIPATION FUZZY LOGIC AND NEURAL NETWORKS IN ENGINEERING WORKSHOP -------------------------------------------------------- Seventh Portuguese Conference on Artificial Intelligence Funchal, Madeira Island, Portugal October 3-6, 1995 (Under the auspices of the Portuguese Association for AI) INTRODUCTION ~~~~~~~~~~~~ The Seventh Portuguese Conference on Artificial Intelligence (EPIA'95) will be held at Funchal, Madeira Island, Portugal, between October 3-6, 1995. As in previous cases ('89, '91, and '93), EPIA'95 will be run as an international conference, English being the official language. The scientific program includes tutorials, invited lectures, demonstrations, and paper presentations. The Conference will include three parallel workshops on Expert Systems, Fuzzy Logic and Neural Networks, and Applications of A.I. to Robotics and Vision Systems. These workshops will run simultaneously (see below) and consist of invited talks, panels, paper presentations and poster sessions. Fuzzy Logic And Neural Networks In Engineering workshop may last for either 1, 2 or 3 days, depending on the quantity and quality of submissions. FUZZY LOGIC AND NEURAL NETWORKS IN ENGINEERING WORKSHOP ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The search for systems simulating human reasoning in what regards uncertainty has created a strong research community. In particular, Fuzzy Logic and Neural Networks have been a source of synergies among researchers of both areas, aiming at developing theoretical approaches and applications towards the characterization and experimentation of such kinds of reasoning. The workshop is intended to promote the exchange of ideas and approaches in those areas, through paper presentations, open discussions, and the corresponding exhibition of running systems, demonstrations or simulations. The organization committee invites you to participate, submitting papers together with videos, demonstrations or running systems, to illustrate relevant issues and applications. EXHIBITIONS ~~~~~~~~~~~ In order to illustrate and to support theoretical presentations the organization will provide adequate conditions (space and facilities) for exhibitions regarding the three workshops mentioned. These exhibitions can include software running systems (several platforms are available), video presentations (PAL-G VHS system), robotics systems (such as robotics insects, and autonomous robots), and posters. On the one hand, this space will allow the presentation of results and real-world applications of the research developed by our community and, on the other it will serve as a source of motivation to students and young researchers. SUBMISSION REQUIREMENTS ~~~~~~~~~~~~~~~~~~~~~~~ Authors are asked to submit five (5) copies of their papers to the submissions address by May 2, 95. Notification of acceptance or rejection will be mailed to the first (or designated) author on June 5, 95, and camera ready copies for inclusion in the workshop proceedings will be due on July 3, 95. Each copy of submitted papers should include a separate title page giving the names, addresses, phone numbers and email addresses (where available) of all authors, and a list of keywords identifying the subject area of the paper. Papers should be a maximum of 16 pages and printed on A4 paper in 12 point type with a maximum of 38 lines per page and 75 characters per line ( corresponding to LaTeX article style, 12 pt). Double sided submissions are preferred. Electronic or faxed submissions will not be accepted. Further inquiries should be addressed to the inquiries address. ATTENDANCE ~~~~~~~~~~ Each workshop will be limited to at most fifty people. In addition to presenters of papers and posters, there will be space for a limited number of other participants chosen on the basis of a one- to two-page research summary which should include a list of relevant publications, along with an electronic mail address if possible. A set of working notes will be available prior to the commencement of the workshops. Registration information will be available in June 1995. Please write for registration information to the inquiries address. DEADLINES ~~~~~~~~~ Papers submission: ................. May 2, 1995 Notification of acceptance: ........ June 5, 1995 Camera Ready Copies Due: ........... July 3, 1995 PROGRAM-CHAIR ~~~~~~~~~~~~~ Jose Tome (IST, Portugal) ORGANIZING-CHAIR ~~~~~~~~~~~~~~~~ Luis Custodio (IST, Portugal) SUBMISSION AND INQUIRIES ADDRESS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ EPIA'95 Fuzzy Logic & Neural Networks Workshop INESC, Apartado 13069 1000 Lisboa Portugal Voice: +351 (1) 310-0325 Fax: +351 (1) 525843 Email: epia95-FLNNWorkshop at inesc.pt PLANNING TO ATTEND ~~~~~~~~~~~~~~~~~~ People planning to submit a paper or/and to attend the workshop are asked to complete and return the following form (by fax or email) to the inquiries address standing their intention. It will help the workshop organizer to estimate the facilities needed and will enable all interested people to receive updated information. +----------------------------------------------------------------+ | REGISTRATION OF INTEREST | | (Fuzzy Logic & Neural Networks Workshop) | | | | Title . . . . . Name . . . . . . . . . . . . . . . . . . . . | | Institution . . . . . . . . . . . . . . . . . . . . . . . . . | | Address1 . . . . . . . . . . . . . . . . . . . . . . . . . . . | | Address2 . . . . . . . . . . . . . . . . . . . . . . . . . . . | | Country . . . . . . . . . . . . . . . . . . . . . . . . . . . | | Telephone. . . . . . . . . . . . . . . Fax . . . . . . . . . . | | Email address. . . . . . . . . . . . . . . . . . . . . . . . . | | I intend to submit a paper (yes/no). . . . . . . . . . . . . . | | I intend to participate only (yes/no). . . . . . . . . . . . . | | I will travel with ... guests | +----------------------------------------------------------------+  From njm at cupido.inesc.pt Tue Oct 18 06:54:42 1994 From: njm at cupido.inesc.pt (njm@cupido.inesc.pt) Date: Tue, 18 Oct 94 10:54:42 +0000 Subject: EPIA'95 - Conference CFP Message-ID: <9410181054.AA27024@cupido.inesc.pt> EPIA'95 - CALL FOR PAPERS SEVENTH PORTUGUESE CONFERENCE ON ARTIFICIAL INTELLIGENCE Funchal, Madeira Island, Portugal October 3-6, 1995 (Under the auspices of the Portuguese Association for AI) The Seventh Portuguese Conference on Artificial Intelligence (EPIA'95) will be held at Funchal, Madeira Island, Portugal, on October 3-6, 1995. As in previous issues ('89, '91, and '93), EPIA'95 will be run as an international conference, English being the official language. The scientific program encompasses tutorials, invited lectures, demonstrations, and paper presentations. Five well known researchers will present invited lectures. The conference is devoted to all areas of Artificial Intelligence and will cover both theoretical and foundational issues and applications as well. Parallel workshops on Expert Systems, Fuzzy Logic and Neural Networks, and Applications of A.I. to Robotics and Vision Systems will run simultaneously (see below). INVITED LECTURERS ~~~~~~~~~~~~~~~~~ The following researchers have already confirmed their participation, as guest speakers: Marvin Minsky, MIT (USA) Manuela Veloso, CMU (USA) Luis Borges de Almeida, IST (Portugal) Rodney Brooks, MIT (USA) SUBMISSION OF PAPERS ~~~~~~~~~~~~~~~~~~~~ Authors must submit five (5) complete printed copies of their papers to the "EPIA'95 submission address". Fax or electronic submissions will not be accepted. Submissions must be printed on A4 or 8 1/2"x11" paper using 12 point type. Each page must have a maximum of 38 lines and an average of 75 characters per line (corresponding to the LaTeX article-style, 12 point). Double-sided printing is strongly encouraged. The body of submitted papers must be at most 12 pages, including title, abstract, figures, tables, and diagrams, but excluding the title page and bibliography. ELECTRONIC ABSTRACT ~~~~~~~~~~~~~~~~~~~ In addition to submitting the paper copies, authors should send to epia95-abstracts at inesc.pt a short (200 words) electronic abstract of their paper to aid the reviewing process. The electronic abstract must be in plain ASCII text (no LaTeX)) in the following format: TITLE: <title of the paper> FIRST AUTHOR: <last name, first name> EMAIL: <email of the first author> FIRST ADDRESS: <first author address> COAUTHORS: <their names, if any> KEYWORDS: <keywords separated by commas> ABSTRACT: <text of the abstract> Authors are requested to select 1-3 appropriate keywords from the list below. Authors are welcome to add additional keywords descriptors as needed. Applications, agent-oriented programming, automated reasoning, belief revision, case-based reasoning, common sense reasoning, constraint satisfaction, distributed AI, expert systems, genetic algorithms, knowledge representation, logic programming, machine learning, natural language understanding, nonmonotonic reasoning, planning, qualitative reasoning, real-time systems, robotics, spatial reasoning, theorem proving, theory of computation, tutoring systems. REVIEW OF PAPERS ~~~~~~~~~~~~~~~~ Submissions will be judged on significance, originality, quality and clarity. Reviewing will be blind to the identities of the authors. This requires that authors exercise some care not to identify themselves in their papers. Each copy of the paper must have a title page, separated from the body of the paper, including the title of the paper, the names and addresses of all authors, a list of content areas (see above) and any acknowledgments. The second page should include the same title, a short abstract of less than 200 words, and the exact same contents areas, but not the names nor affiliations of the authors. This page may include text of the paper. The references should include all published literature relevant to the paper, including previous works of the authors, but should not include unpublished works of the authors. When referring to one's own work, use the third person. For example, say "previously, Peter [17] has shown that ...". Try to avoid including any information in the body of the paper or references that would identify the authors or their institutions. Such information can be added to the final camera-ready version for publication. Please do not staple the title page to the body of the paper. Submitted papers must be unpublished. PUBLICATION ~~~~~~~~~~~ The proceedings will be published by Springer-Verlag (lecture notes in A.I. series). Authors will be required to transfer copyright of their paper to Springer-Verlag. ASSOCIATED WORKSHOPS ~~~~~~~~~~~~~~~~~~~~ In the framework of the conference three workshops will be organized: Applications of Expert Systems, Fuzzy Logic and Neural Networks in Engineering, and Applications of Artificial Intelligence to Robotics and Vision Systems. Real world applications, running systems, and demos are welcome. CONFERENCE & PROGRAM CO-CHAIRS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Carlos Pinto-Ferreira Nuno Mamede Instituto Superior Tecnico Instituto Superior Tecnico ISR, Av. Rovisco Pais INESC, Apartado 13069 1000 Lisboa, Portugal 1000 Lisboa, Portugal Voice: +351 (1) 8475105 Voice: +351 (1) 310-0234 Fax: +351 (1) 3523014 Fax: +351 (1) 525843 Email: cpf at kappa.ist.utl.pt Email: njm at inesc.pt PROGRAM COMMITTEE ~~~~~~~~~~~~~~~~~ Antonio Porto (Portugal) Lauiri Carlson (Finland) Benjamin Kuipers (USA) Luc Steels (Belgium) Bernhard Nebel (Germany) Luigia Aiello (Italy) David Makinson (Germany) Luis Moniz Pereira (Portugal) Erik Sandewall (Sweden) Luis Monteiro (Portugal) Ernesto Costa (Portugal) Manuela Veloso (USA) Helder Coelho (Portugal) Maria Cravo (Portugal) Joao Martins (Portugal) Miguel Filgueiras (Portugal) John Self (UK) Yoav Shoham (USA) Jose Carmo (Portugal) Yves Kodratoff (France) DEADLINES ~~~~~~~~~ Papers Submission: ................. March 20, 1995 Notification of acceptance: ........ May 15, 1995 Camera Ready Copies Due: ........... June 12, 1995 SUBMISSION & INQUIRIES ADDRESS ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ EPIA95 INESC, Apartado 13069 1000 Lisboa, Portugal Voice: +351 (1) 310-0325 Fax: +351 (1) 525843 Email: epia95 at inesc.pt SUPPORTERS ~~~~~~~~~~ Banco Nacional Ultramarino Governo Regional da Madeira Instituto Superior Tecnico INESC CITMA IBM TAPair Portugal PLANNING TO ATTEND ~~~~~~~~~~~~~~~~~~ People planning to submit a paper or/and to attend the conference or attend a workshop are asked to complete and return the following form (by fax or email) to the inquiries address standing their intention. It will help the conference organizers to estimate the facilities needed for the conference and will enable all interested people to receive updated information. +----------------------------------------------------------------+ | REGISTRATION OF INTEREST | | | | Title . . . . . Name . . . . . . . . . . . . . . . . . . . . | | Institution . . . . . . . . . . . . . . . . . . . . . . . . . | | Address1 . . . . . . . . . . . . . . . . . . . . . . . . . . . | | Address2 . . . . . . . . . . . . . . . . . . . . . . . . . . . | | Country . . . . . . . . . . . . . . . . . . . . . . . . . . . | | Telephone. . . . . . . . . . . . . . . Fax . . . . . . . . . . | | Email address. . . . . . . . . . . . . . . . . . . . . . . . . | | I intend to submit a paper (yes/no). . . . . . . . . . . . . . | | I intend to participate only (yes/no). . . . . . . . . . . . . | | I will travel with ... guests | +----------------------------------------------------------------+  From laura at predict.com Tue Oct 18 12:48:32 1994 From: laura at predict.com (Laura Barela) Date: Tue, 18 Oct 94 10:48:32 MDT Subject: Research Position in Financial Modeling Message-ID: <9410181648.AA12664@predict.com> PREDICTION COMPANY RESEARCH POSITION IN NONLINEAR MODELING OF FINANCIAL MARKETS October, 1994 Prediction Company is a small firm based in Santa Fe, NM, utilizing nonlinear forecasting technologies for prediction and computerized trading of financial instruments. The current research group consists of Doyne Farmer, Norman Packard, and William Finnoff, who have worked for over fifteen years in complex systems, including chaos and nonlinear prediction. We have the backing of a major European bank, and do propietary trading through them. Most employees own stock or stock options. We are seeking someone to join the research group. The basic task is to build models to predict and trade financial markets based on historical data. Responsibilities include application of existing technology, research and development of new technology, and participation in the design of an advanced software platform for modeling, trading, and risk control, using new methods that are well beyond the existing state of the art. The successful applicant for this job will have a Ph.D. in statistics, computer science, physics, mathematics, or a related field. Experience using neural nets, radial basis function, local approximation methods, decision trees, hidden markov models, projection-pursuit, generalized additive models, genetic algorithms, or other approximation and modeling methods, and familiarity with statistics and numerical analysis, are highly valuable. Software experience is desirable, particularly C++, S+ or related languages. Familiarity with finance, including technical trading analysis, is also desirable. Experience with real data is also highly desirable -- the nastier the better. The applicant should be willing to work in close collaboration with other researchers and software developers, and should be willing to take on what is unquestionably the most challenging but lucrative forecasting problem in existence. Prediction Company offers a relaxed and informal work environment. We are located in a converted studio on the top floor of a building in the Guadalupe commercial district. Our offices include a full kitchen, shower and roof deck. We are within easy walking distance of many cafes, restaurants and the historical central plaza of Santa Fe. Santa Fe: Santa Fe is an almost 400 year old city (settled in 1605, one of the oldest in the country) of ~60,000 people with a wealth of cultural and recreational opportunities. Known as a center for the visual arts, Santa Fe is host to many festivals and exhibitions. Located at 7000 feet elevation in the foothills of the Sangre De Cristo mountains in northern New Mexico, Santa Fe has an abundance of outdoor diversions. Biking, hiking, camping, rock climbing, fossil hunting and skiing (within 45 minutes at Ski Santa Fe and 90 minutes at Taos Ski Basin) are all possible within a short drive. US or Canadian Citizenship required, or US Permanent Residency. We are unable to assist persons requiring H-1 or F-1 Visas. Applicants should US mail resumes to: Prediction Company 320 Aztec Street, Suite B Santa Fe, NM 87501 attn: recruiting or email them to Laura Barela at laura at predict.com (postscript or ascii)  From singer at CS.HUJI.AC.IL Wed Oct 19 07:21:04 1994 From: singer at CS.HUJI.AC.IL (Yoram Singer) Date: Wed, 19 Oct 1994 13:21:04 +0200 Subject: thesis available Message-ID: <199410191121.AA02574@allegro.cs.huji.ac.il> ************* MSc THESIS AVAILABLE ************** *** DO NOT FORWARD TO ANY OTHER LISTS *** ************************************************* The following thesis has been placed in the cs.huji.ac.il (132.65.16.10) anonymous ftp. The file is igth.ps.gz (gzip compressed postscript) or igth.ps.Z (compressed postscript). Ftp instructions follow the abstract. ----------------------------------------------------- Unsupervised Learning of Cell Activities in the Associative Cortex of Behaving Monkeys, Using Hidden Markov Models Itay Gat Institute of Computer Science and Center for Neural Computation Hebrew University, Jerusalem 91904, Israel ABSTRACT: Hebb hypothesized in 1949 that the basic information processing unit in the cortex is a cell-assembly which can act, briefly, as a closed system after stimulation has ceased, and constitutes the simplest instance of a representative process. This hypothesized cell-assembly may include thousands of cells in a highly interconnected network. The cell-assembly hypothesis shifts the focus from the single cell to the complete network activity. So far, there has been no general method for relating extracellular electrophysiological measured activity of neurons in the associative cortex to the underlying network or the cell-assembly states. It is proposed here to model such data as a pair-wise correlated multivariate Poisson process. Based on these parameters, a Hidden Markov Model was computed. This modeling yielded a temporal segmentation and labeling of the data into a sequence of states. The first hypothesis of this work was that a connection exists between the states of the model and the behavioral events of the animal. i.e. based on the sequence of states of the model, the observed actions of the animal could be predicted. The second hypothesis was that a connection exists between the states defined above and the functional interaction between cells, i.e. the functional interaction between pairs of cells changes in different cognitive states. The application of this approach was demonstrated for temporal segmentation of the firing patterns, and for characterization of the cortical responses to external stimuli.This modeling was applied to 6 recording sessions of several single-unit recordings from behaving monkeys. At each session, 6-8 single-unit spike trains were recorded simultaneously. Using the Hidden Markov Model, two behavioral modes of the monkey were significantly discriminated. The two behavioral modes were characterized by different firing patterns, as well as by the level of coherency of their multi-unit firing activity. The result of the modeling showed a high degree of consistency, which implies that the model succeeds in capturing a basic structure underlying the data. Significant changes were found in the temporal cross-correlation of the same pair of cells in different states, indicating different functional connectivities of the small network being recorded. These changes suggest that the modeling captures the activity of the network and that the states of the model can be related to the cognitive states of the cortex. ----------------------------------------------------- FTP INSTRUCTIONS unix> ftp cs.huji.ac.il (or 132.65.16.10) Name: anonymous Password: full_email_address ftp> cd /pub/singer ftp> binary ftp> get igth.ps.Z or ftp> get igth.ps.gz ftp> quit unix> uncompress igth.ps.Z or unix> gunzip igth.ps.gz unix> lpr -P<printer-name> igth.ps ---------------------------------------------- Itay Gat Institute of Computer Science The Hebrew University, Givat-Ram Jerusalem 91904, Israel Email: itay at cs.huji.ac.il Fax: +972 2 58 5439  From jose at scr.siemens.com Wed Oct 19 13:56:10 1994 From: jose at scr.siemens.com (Stephen Hanson) Date: Wed, 19 Oct 1994 13:56:10 -0400 (EDT) Subject: More on McPew Message-ID: <QidJquO1GEMnENGDM1@tractatus.siemens.com> Good Luck, Steve The McDonnell-Pew Program in Cognitive Neuroscience Investigator-Initiated Grants 1994-1995 The McDonnell-Pew Program in Cognitive Neuroscience is a collaborative effort established by the James S. McDonnell Foundation, St. Louis, Missouri and the Pew Charitable Trusts, Philadelphia, Pennsylvania to support research. Since its inception in 1990, the Program has awarded $21.5 million in support of institutional centers and individual investigators. Cognitive neuroscience attempts to understand human mental events by specifying how neural tissue carries out computations. Work in cognitive neuroscience is multidisciplinary, drawing on developments in clinical and basic neuroscience, computer science, psychology, linguistics and philosophy. The McDonnell-Pew Program does not support research based on descriptions of psychological function that do not address underlying brain mechanisms or neuroscientific descriptions that do not speak to psychological function. The Program has two components: 1) Institutional Center grants that established large research and training programs; all Center grants have been awarded. 2) Investigator-initiated grants supporting interdisciplinary training and providing seed funds for collaborative research. The Program accepts investigator-initiated grants as described in this brochure. Program goals: The Program will preferentially support innovative, interdisciplinary research of the highest caliber that is unlikely to be funded from traditional sources. The Program hopes to encourage researchers to seek interdisciplinary training and collaborations with persons outside their own discipline. The Program particularly encourages research on higher cognitive functions including, high-order vision, language, planning, and problem-solving. The cognitive question to be studied and the neuroscientific methods to be applied must be clearly articulated in the research proposal. The awards will provide a maximum of $35,000 per year for up to 3 years. Indirect costs are included in the $35,000 maximum and cannot exceed 10% of total salaries plus fringe benefits. An individual cannot receive support from more than one investigator- initiated grant. The grants are non-renewable. Examples of the types of research proposals sought by the program include: using neurobiological methods to study higher cognitive processes applying formal modelling techniques to cognitive functions, including emotions and higher thought processes dveloping new theories of the human mind/brain systems using sensing (EEG, MEG) or imaging techniques (PET, MRI) to observe the brain during conscious activity. Preference will be given to training proposals that exemplify multi- disciplinary and collaborative research as described below: a junior scientist pursuing a research project in the laboratory of a senior scientist in a different field of cognitive neuroscience; collaborations between two or more scientists representing different subdisciplines of cognitive neuroscience; a scientist with expertise in a subdiscipline of cognitive neuroscience obtaining hands-on training in a new methodology or technique to be used in the study of higher cognitive function. Eligibility: Individual investigators at institutions with McDonnell-Pew Center grants, who are already receiving support from a McDonnell-Pew Center grant are not eligible for the investigator-initiated grant program. Researchers who are at institutions that have been awarded a McDonnell-Pew Center grant but who do not receive any support from the Center are eligible. There are no US citizenship restrictions or requirements, nor must the proposed work be conducted at a US institution, providing the sponsoring organization qualifies as tax-exempt under IRS guidelines (see the "Applications" section of this brochure). The Program described in this brochure will not support dissertation research, workshops, conferences, or travel for the purpose of attending meetings. Proposals to investigate basic neurobiology unrelated to human, higher-order cognition will not be funded. Application guidelines: Applicants should submit five (5) copies of the following information: 1) A completed cover sheet (enclosed); 2) A brief, one-page abstract describing the proposed work; 3) A brief, itemized budget that includes direct and indirect costs (indirect costs may not exceed 10 percent of total salaries and fringe benefits); 4) A budget justification; 5) A narrative proposal (not to exceed 5,000 words) that describes the cognitive question to be investigated and all methodological approaches in sufficient detail to allow the proposal to be evaluated by the advisory board. If the application is requesting support for training, a description of the training plan and the relationship of the training to the applicant's research goals should be included; 6) Curriculum vitae for each of the participating investigators; 7) An authorized document indicating clearance for the use of human and animal subjects; 8) An endorsement letter from the officer of the sponsoring institution who will be responsible for administering the grant. One copy of each of the following items must also be submitted along with the proposal. These documents can be obtained from the sponsoring institution's grants or development office. A copy of the IRS determination letter, or the international equivalent, stating that the sponsoring organization is a nonprofit, tax-exempt institution classified as a 501(c)(3) organization. A copy of the IRS determination letter stating that the sponsoring organization is not listed as a private foundation under section 509(a) of the Internal Revenue Service Code. No other documents should be appended to the application. Submissions will be reviewed by the program's advisory board. Applications must be received in the Foundation office no later than February 20, 1995. Incomplete or late proposals will not be reviewed. Contact: Susan M. Fitzpatrick, Ph.D. McDonnell-Pew Program in Cognitive Neuroscience James S. McDonnell Foundation 1034 South Brentwood Blvd., Suite 1610 St. Louis, Missouri 63117 Phone: 314/721-1532 e-mail: C 6819CN at WUVMD.WUSTL.edu  From cabestan at eel.upc.es Thu Oct 20 13:08:51 1994 From: cabestan at eel.upc.es (Joan Cabestany) Date: Thu, 20 Oct 1994 17:08:51 UTC Subject: IWANN'95 Call for Papers Message-ID: <786*/S=cabestan/OU=eel/O=upc/PRMD=iris/ADMD=mensatex/C=es/@MHS> Please find here the final announcement and definitive Call for Papers of IWANN'95 (International Workshop on Artificial Neural Networks) to be held next June 1995 in Malaga (Spain). Any questions could be addressed to: Prof. J.Cabestany - cabestan at eel.upc.es Prof. F.Sandoval - sandoval at tecma1.ctima.uma.es Sincerely yours J.Cabestany *********************************************************************** ================== INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORKS IWANN'95 Second and Final Call for Papers Hotel Melia - Costa del Sol Torremolinos (Malaga) - Spain June 7 - 9, 1995 SPONSORED BY Plan Nacional de I + D (CICYT) DGICYT (MEC) Junta de Andalucia Universidad de Malaga Universidad Nacional de Educacion a Distancia D. G. S. R. D., DG-XII Human Capital and Mobility (EC) Spanish RIG IEEE Neural Networks Council UK&RI communication Chapter of IEEE Spanish Computer Society Chapter of IEEE AEIA (IEEE affiliated society) ORGANISED BY Universidad de Malaga UNED (Madrid) ============================================================================= IWANN'95. The third International Workshop on Artificial Neural Networks, will take place in the Spanish "Costa del Sol" (Malaga) from 7 to 9 of June, 1995. This biennial meeting with focus on Biological Models and New Computing Paradigms, was first held in Granada (1991) and Sitges (1993) with a growing number of participants from more than 20 countries and with high quality papers published by Springer-Verlag (LNCS 540 and 686). SCOPE From the computational viewpoint, standard neural networks pa- radigms are nearly exhausted and some fresh air is needed. In this workshop, remaining with the powerful roots of neural computation (modularity, autonomy, distributed computation and self-programming via supervised or non-supervised learning), focus is placed on Biolo- gical Modeling, the search of Theory and Design Methodologies and the bridge between Connectionism and Symbolic Computation. IWANN's main objective is to offer an interdisciplinary forum for scientists and engineers from Neurology, Computer Science, Artifi- cial Intelligence, Electronics, Cognitive Science and applied domains, looking after brain storming and innovative formulations of Natural and Artificial Neural Computation. It is the deep feeling of the IWANN's organizers that this more- complex, biologically inspired, and theoretical and methodologically supported approach will also provide us with more powerful tools for applied domains. All received papers will be reviewed by the Programme Committee. Accepted papers may be presented orally or as poster panels, however all accepted contributions will be published in full length. (Springer-Verlag Proceedings are expected). Coordinated inscription with the 3rd. European Conference on Artifi- cial Life (ECAL95), to be held in Granada, JUNE 4-6,1995, is possible at special rates. Malaga and Granada are only one and a half hour apart by car. Contributions on the following or related topics are welcome. ============================================================================= TOPICS 1. Neuroscience: Principles, methodologies in brain research, mo- deling and simulation, central and peripheral neural coding, dendro-dendritic nets, local circuits, anatomical and physiolo- gical organizations, plasticity, learning and memory in natural neural nets, models of development and evolution, specific cir- cuits in sensorial and motor pathways, networks in the ce- rebral cortex. 2. Computational Models of Neurons and Neural Nets: Continuous (linear, high order, recurrent), logic, sequential, inferential (object oriented, production rules, frames), probabilistic, Bayesian, fuzzy and chaotic models, hybrid formulations, massive computation and learning enabling structures for all these for- mulations. 3 Organizational Principles: The living organization, determi- nistic networks dynamics, autopoiesis, self-organization, cooperative processes and emergent computation, synergetics, evolutive optimization and genetic algorithms. 4. Learning: Inspirations from the biological mechanisms of lear- ning, supervised and unsupervised strategies, local self- programming, continous learning, evolutive algorithms, symbolic-subsymbolic formulations. 5. Cognitive Science and AI: Neural networks for knowledge acqui- sition, multisensorial integration, perception, knowledge-based neural nets, inductive, deductive and abductive reasoning, me- mory mechanisms, natural language. 6. Neurosimulators: Languages, environments, parallelization, mo- dularity, extensibility and benchmarks. 7. Hardware Implementation: VLSI, parallel architectures, neuro- chips, preprocessing networks, neurodevices, FPGA's, benchmarks, optical and other technologies. 8. Neural Networks for Perception: Low level processing, segmenta- tion, feature extraction, pattern recognition, adaptive filte- ring, noise reduction, texture, motion analysis, hybrid symbolic-neural architectures for artificial vision. 9. Neural Networks for Communications Systems: Modems and codecs, network management, digital communications. 10. Neural Networks for Control and Robotics: Systems identification, motion planning and control, adaptive and predictive control, navigation, real time applications. ============================================================================= ____________________________________________________________________ | | | THE EMBODIMENTS OF MIND REVISITED | | MEMORIAL SPECIAL SESSION | | in the 25th ANNIVERSARY | | | | of the dead of | | WARREN S. McCULLOCH | | | | Papers for this special session are wellcome, with focus on | | the relevance at the present time of W.S. McCulloch's work | | (Epistemological Physiology, Formal Neurons, Universals, | | Anastomotic Nets, Triadic Relations, the Lekton, | | Reverberating Memory, a Calculus for Intention, Redundancy | | of Potencial Command,...) | |____________________________________________________________________| LOCATION Malaga - Costa del Sol, June 7-9, 1995. Malaga, capital of the Costa del Sol, is strategically located on the southern coast of Spain. It is a genuine crossroads of communication and culture. Malaga is well-know for its history (Cathedral, historic down-town, arabian citadel, roman amphitheatre, ...) and excelent beaches. Malaga, with many modern hotels, is very well communicated by car or plane; its international airport has direct flights to all major European capitals, to America and some destinations on the other continents. In June, weather is warm and pleasant. Averages temperatures:18-30C. Comfortable walking shoes, light clothes and bathing suits are recommended. TRAVEL AND ACCOMMODATION Viajes El Corte Ingles is the official travel and accomodation agent for the Workshop, and will provide all the necessary tourist services to participants: Travel arrangements, Accommodation, Rent-a-car, Pre and Post Workshop sightseeings tours, etc. Viajes El Corte Ingles, S.A. IWANN'95 Avda. Andalucia, 4 29007 Malaga, Spain. Phone:+ 34.5.230.82.00 / + 34.5.230.00.00 Fax: + 34.5.261.12.42 ============================================================================= CALL FOR PAPERS The Programme Committee seeks original papers on the above mentioned Topics. Authors should pay special attention to explanation of theoreti- cal and technical choices involved, point out possible limitations and describe the current state of their work. Authors must take into account the following: INSTRUCTIONS TO AUTHORS Authors must submit four copies of full papers, not exceeding 8 pa- ges in DIN-A4 format including figures, tables and references. English will be the official language. The heading should be centered and include: . Title in capitals. . Name(s) of author(s). . Address(es) of author(s). . A 10 lines abstract. Three blank lines should be left between each of the above items, and four between the heading and the body of the paper, 1.6 cm left, right, top and bottom margins, single-spaced and not exceeding the 8 pages limit. In addition, one sheet should be attached including the following information: . Title and author(s) name(s). . A list of five keywords. . A reference to the Topics the paper relates to. . Postal address, phone and fax numbers and E-mail (if available). CONTRIBUTIONS MUST BE SENT TO: Prof. Jose Mira Dpto. Informatica y Automatica UNED Senda del Rey, s/n Phone:+ 34.1.398.71.55 28040 MADRID (Spain) Fax:+ 34.1.398.66.97 IMPORTANT DATES Final date for submission January 15, 1995 Notification of acceptance March 15, 1995 Workshop June 7-9, 1995 ============================================================================= INVITED TALKS Prof. Stephen Grossberg Boston University (U.S.A.) Opening Session of IWANN'95 Dr. Jeanny Herault Institut National Polytecnique of Grenoble(F) Neural Networks for Perception Dr. Joshua Alspector Bellcore, AT&T (U.S.A.) Hardware Implementation and Applications to Communications. Prof. Igor Aleksander Imperial College of Science Tech. and Medicine,London (U.K.) Cognitive Science and AI Prof. Carme Torras Instituto de Cibernetica, CSIC (E) Learning and Application to Control and Robotics Prof. H.R. Maturana Universidad de Chile (Chile) Neuroscience and Organizational Principles. GENERAL CHAIRMAN Alberto Prieto Unv. de Granada (E) ORGANIZATION COMMITTEE Joan Cabestany Unv. Pltca. de Cataluna (E) Chairman Senen Barro Unv. de Santiago de Compostela (E) Trevor Clarkson King's College London (UK) Dante Del Corso Politecnico de Torino (I) Ana Delgado UNED. Madrid (E) Tom Gedeon Univ. of New South Wales (AUS) Karl Goser Unv. Dortmund (G) Jeanny Herault INPG Grenoble (F) K.Nicholas Leibovic SUNY at Buffalo (U.S.A.) Jose Mira UNED. Madrid (E) Federico Moran Unv. Complutense. Madrid (E) Stanislaw Osowski Tech. Unv. Warsaw (Po) Conrad Perez Unv. de Barcelona (E) Francisco Sandoval Unv. de Malaga (E) Juan A. Sigenza Inst. Ingenieria del Conocimiento, UAM (E) Elena Valderrama Centro Nacional Microelectrnica, UAB (E) Marley Vellasco Pont. Unv. Catolica do Rio de Janeiro (Br) Michel Verleysen Unv. Catholique de Louvain (B) ============================================================================= PROGRAMME COMMITTEE Jose Mira UNED. Madrid (E) Chairman Carlos Acuna C. Unv. Santiago de Compostela (E) Joshua Alspector Bellcore. (USA) Sanjeev B.Ahuja Nielsen A.I. Research & Development. Bannokburn (USA) Igor Aleksander Imperial College. London (UK) Shun-ichi Amari Unv. Tokyo (Jp) Xavier Arreguit CSEM SA (CH) Francois Blayo LERI-EERIE. Nimes (F) Colin Campbell University of Bristol (UK) Jordi Carrabina CNM- Universidad Autnoma de Barcelona (E) Francisco Castillo Unv. Pltca. de Cataluna (E) Andreu Catala Unv. Pltca. de Cataluna (E) Marco A. Cavalcanti P. Pontificia Universidade Catolica do Rio de Janeiro (Br) Gabriela Cembrano Instituto de Cibernetica. CSIC. Barcelona (E) Leon Chua Unv. California, Berkeley (USA) Michael Cosnard LIP. Ecole Normale Superieure de Lyon (F) Marie Cottrell Unv. Paris I (F) Dante A. Couto B. Instituto de Informatica (Br) Gerard Dreyfus ESPCI. Paris (F) F.K. Fogelman Soulie Mimetics. Chatenay Malabry (F) J. Simoes da Fonseca Unv. Lisboa (P) Kunihiko Fukushima Unv. Osaka (Jp) Hans Peter Graf AT&T Bell Laboratories, New Jersey (USA) Karl E. Grosspietsch Mathematik und Datenverarbeitung (GMD). St. Augustin (D) Mohamad H. Hassoun WayneState University (USA) Jaap Hoekstra Delft University of Technology (NL) Jose Luis Huertas CNM- Universidad de Sevilla (E) Simon Jones IERI Loughborough University of Technology(UK) Christian Jutten INPG Grenoble (F) H. Klar Technische Universitt Berlin (D) C.Koch CalTech. (USA) Michael D. Lemmon University of Notre Dame. Notre Dame (USA) Panos A. Ligomenides Unv. of Maryland (USA) Javier Lpez Aligue Unv. de Extremadura. (E) Pierre Marchal CSEM SA (CH) Anthony N. Michel University of Notre Dame. Notre Dame (USA) Roberto Moreno Unv. Las Palmas Gran Canaria (E) Jean Daniel Nicoud EPFL (CH) Josef A. Nossek Tech. Univ. of Munich (D) Julio Ortega Unv. de Granada (E) Francisco J. Pelayo Unv. de Granada (E) Franz Pichler Johannes Kepler Univ. (A) Vicenzo Piuri Politecnico di Milano (I) Ulrich Ramacher Siemens AG. Munich (D) J.Ramirez Paradigma C.A. Caracas (V) Leonardo Reyneri Unv. di Pisa (I) Tamas Roska Hungarian Academy of Science. Budapest (H) Peter A. Rounce Unv. College London (UK) V.B. David Sanchez German Aerospace Research Establishment. Wessling (G) Renato Stefanelli Politecnico di Milano (I) T.J. Stonham Brunel-University of West London (UK) John G. Taylor King's College London (UK) Carme Torras Instituto de Cibernetica. CSIC. Barcelona (E) Philip Treleaven Unv. College London (UK) Michel Weinfeld Ecole Polytechnique Paris (F) R.Yager Iona College NY (USA) ============================================================================= LOCAL COMMITTEE Francisco Sandoval Unv. de Malaga (E) Chairman Antonio Diaz Unv. de Malaga (E) Gonzalo Joya Unv. de Malaga (E) Francisco Vico Unv. de Malaga (E) FOR ADDITIONAL INFORMATION: Prof. F. Sandoval IWANN'95 Dept. Tecnologia Electronica Universidad de Malaga Plaza El Ejido, s/n E-29013 Malaga SPAIN Phone: +34.5.213.13.62 Fax: +34.5.213.14.47 E-mail:iwann95 at ctima.uma.es GRANTS Young researchers, citizens or residents in European Union States, may apply for grants offered by European Community (Human Capital and Mobility, DG XII). Deadline for application: February 15, 1995. Please, write for information to the Organization Committee Chairman: Joan Cabestany IWANN'95 Dpto. Ingenieria Electronica, UPC Gran Capitan, s/n Campus Nord, Edificio C4 08034 Barcelona, Spain Tf.+34-3-4016742; Fax: +34-3-4016756 Email:Cabestan at eel.upc.es ============================================================================= IWANN'95 INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORKS Hotel Melia -Costa del Sol, Torremolinos (Malaga), Spain-June 7th - 11th, 1995 REGISTRATION FORM Name:_______________________________________________________________ Last/Family First Company/University:_________________________________________________ Mailing Address: _________________________________________________ City/State/Zip/Country:_____________________________________________ Telephone: __________________________ Fax: ________________________ Email: _____________________________________________________________ REGISTRATION FEES Before April 5 After April 5 Full Inscription* 65.000.-ptas 75.000.-ptas ________ptas Basic Inscription ** 55.000.-ptas 65.000.-ptas ________ptas With ECAL95 Registration*** 55.000.-ptas 65.000.-ptas ________ptas Gala Dinner Invitation 8.000.-ptas X _____ = ________ptas TOTAL ATTACHED PAYEMENT ___________________ptas * Full inscription includes: wellcome reception, opening ceremony, lunches during session days, refreshments and coffee breaks, confe- rence kit and personal badges, proceedings, attendance at all sessions and Gala dinner. ** Basic inscription does not include: Gala dinner and lunches during session days. *** It includes the same that Full inscription. METHODS OF PAYMENT [ ] By bank draft in Pesetas, payable to IWANN-95. UNIVERSIDAD DE MALAGA on a Spanish Bank. [ ] By bank transfer to: Banco Espanol de Credito (c/o IWANN-95. UNIVERSIDAD DE MALAGA), Ofic. Principal, Alameda Principal, 8, 29005 Malaga (Spain), Acct. No. 105.123-271. Transfer fee to be paid by sender. Please attach copy of bank transfer to this Form. [ ] VISA CARD [ ] MASTER CARD [ ] AMERICAN EXPRESS CARD [ ] DINNERS CARD Credit Card Number___________________________ Expiration Date______________ Cardhlder Name ____________________________________________________________ Date __________________________________ Signature__________________________ Please, send this Registration Form, together with payement, to: Francisco Sandoval IWANN'95. Dept. Tecnologia Electronica. Universidad de Malaga. Plaza El Ejido s/n. E-29013 Malaga SPAIN. Tf.+34.5.213.13.62 Fax: +34.5.213.14.47 ============================================================================== IWANN'95 INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORKS Hotel Melia - Costa del Sol, Torremolinos (Malaga), Spain - June 7 - 9, 1995 HOTEL RESERVATION FORM Name:________________________________________________________________ Last/Family First Company/University: _________________________________________________ Mailing Address:_____________________________________________________ City/State/Zip/Country:______________________________________________ Telephone:__________________________ Fax:__________________________ Email:_______________________________________________________________ SPECIAL HOTEL RATES PER NIGHT AND ROOM (Breakfast and V.A.T. included) Single Use Room Twin Room [ ] Hotel Melia - Costa del Sol**** 6.200.-ptas 8.200.-ptas (Workshop Venue) [ ] Hotel Royal Park*** 4.200.-ptas 5.000.-ptas (1 Km apart Workshop Venue) Please reserve________room(s) [ ] Twin(s) [ ] Single(s) at Hotel _________ __________________________________________________________________________ (If twin room, give the name of person sharing accommodation). __________________________________________________________________________ Date of arrival __________________ Date of departure ____________________ HOTEL RESERVATION DEPOSIT A deposit of 16.000.-ptas per room will be necessary to confirm the Hotel reservation. Attached Hotel Deposit 16.000.-ptas X ______ room/s = ___________.-ptas. METHODS OF PAYMENT [ ] By bank draft in Pesetas, payable to Viajes el Corte Ingles S.A. on a Spanish bank. [ ] VISA CARD [ ] MASTER CARD [ ] AMERICAN EXPRESS CARD [ ] EL CORTE INGLES CARD [ ] DINNERS CARD Credit Card Number ________________________ Expiration Date _____________ Cardholder Name __________________________________________________________ Date________________________________ Signature _______________________ Please send this Hotel Reservation Form, before May 7, 1995, together with payement, to: Viajes el Corte Ingles, S.A. IWANN-95 Avda Andalucia, 4 29007 Malaga, Spain Tlf: +34.5.2308200; Fax: +34.5.2611242 ================================================================ IWANN'95 INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORKS Hotel Melia - Costa del Sol, Torremolinos (Malaga), Spain, June 7-9, 1995 GRANT APPLICATION The Organizing Committee of the IWANN'95 will grant a limited number of young researchers from Western European Countries, according to the conditions of the DG XII-G-3 Human Capital and Mobility Program (EC). The grants could support the global or partial expenses for assisting to the Workshop. Please mail this Form together with your Curriculum Vitae before February 15th, 1995 to: Prof. Joan Cabestany IWANN'95 DEE-UPC Campus Nord, Building C4 08034 BARCELONA, Spain Name: ................................................................... Institution or Center: .................................................. Position: ............................................................... Postal Address: ......................................................... ......................................................................... Zip/Code: ........................ Country: ............................. Phone: ........................... FAX: ................................. Email: .................................................................. I have submitted a paper to IWANN'95 with the title: ==============================================================================  From udee150 at bay.cc.kcl.ac.uk Thu Oct 20 08:12:45 1994 From: udee150 at bay.cc.kcl.ac.uk (Chris Christodoulou) Date: Thu, 20 Oct 1994 12:12:45 GMT Subject: UKRI IEEE Neural Networks Regional Interest Group Message-ID: <0098639C.5B23AA5C.148@bay.cc.kcl.ac.uk> Establishment of an IEEE Neural Networks Regional Interest Group in UKRI (United Kingdom and Republic of Ireland) Section) ------------------------------------------------------------------ This is to announce that an IEEE UKRI Neural Networks RIG has been established and had its inaugural meeting on 19th October 1994 at King's College London. The RIG will be under the UKRI IEEE Communications Chapter. The scope of interest of the RIG will include apart from Neural Networks, Fuzzy Systems and Genetic Algorithms. The RIG will organise, sponsor or co-sponsor activities like: * Evening Lectures * Workshops * Training Courses and will cooperate with other IEEE Societies and local and regional institutions. The RIG is keen to invite distinguished speakers from the Neural Network community worldwide to give lectures and therefore anyone from the Connectionists list who is in the UK or the Republic of Ireland and is interested in giving a lecture under the RIG's auspices is welcome. For further information and membership enquiries please contact: Dr Trevor G. Clarkson Chairman, UKRI Neural Networks RIG Dept. of Electronic & Electrical Eng. King's College London Strand, London WC2R 2LS England, UK Tel. (+44) 171-873 2367 Fax (+44) 171-836 4781 Email: tgc at kcl.ac.uk or fill in your details below and return them to Dr Trevor Clarkson by email, fax or post: _______________________________________________________________________ UKRI Neural Networks RIG REQUEST FOR INFORMATION Please supply the information shown to update our records. Name: ............................................................. < >Membership number (M ) and Grade (F / SM / M / Student) < >Postal Address < >Telephone and Fax numbers / < >Email < >IEEE Society affiliations < >I do*/do not* wish my name to be published in the RIG directory (*delete as required) Current interests: _______________________________________________________________________  From mike at PARK.BU.EDU Thu Oct 20 13:03:26 1994 From: mike at PARK.BU.EDU (mike@PARK.BU.EDU) Date: Thu, 20 Oct 1994 13:03:26 -0400 Subject: Job Announcement Message-ID: <199410201703.NAA29016@space.bu.edu> NEW SENIOR FACULTY IN COGNITIVE AND NEURAL SYSTEMS AT BOSTON UNIVERSITY BOSTON UNIVERSITY seeks an ASSOCIATE or FULL PROFESSOR for its graduate DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS. This department offers an integrated curriculum of psychological, neurobiological, and computational concepts, models, and methods in the fields of computational neuroscience, connectionist cognitive science, and neural network technology in which Boston University is a leader. Candidates should have an international research reputation, preferably including extensive analytic or computational research experience in modeling a broad range of nonlinear neural networks, especially in one or more of the areas: vision and image processing, adaptive pattern recognition, cognitive information processing, speech and language, and neural network technology. Send a complete curriculum vitae and three letters of recommendation to: Search Committee Department of Cognitive and Neural Systems 111 Cummington Street, Second Floor Boston University, Boston, MA 02215 Boston University is an Equal Opportunity/Affirmative Action Employer.  From liaw at bmsr14.usc.edu Thu Oct 20 14:52:28 1994 From: liaw at bmsr14.usc.edu (Jim Shih-Liaw) Date: Thu, 20 Oct 1994 11:52:28 -0700 Subject: Postdoc position: Motor pattern generation Message-ID: <199410201852.LAA22643@bmsr14.usc.edu> NEUROETHOLOGY OF MOTOR PATTERN GENERATION Postdoctoral position available immediately for three years to investigate neuroethological aspects of motor pattern generators and their coordination. The position is associated with an NSF sponsored collaborative research project between Michael Arbib (University of Southern California) and Ananda Weerasuriya (Mercer University School of Medicine, GA), and will be based at the latter location. The primary focus will be on characterizing the behavior and electromyography of rapidly adapting prey capture patterns of frogs. Experience with chronic electrophysiological recording techniques in small animals is highly desirable. Please send vita, summary of research experience and interests, and names and tel. numbers of three or more references to Ananda Weerasuriya, Division of Basic Medical Sciences, Mercer University School of Medicine, 1550 College Street, Macon, GA 31207. Fax: (912) 752-4038, email: weerasuriy_a at mercer.peachnet.edu. AA/EOE.  From marcus at dope.caltech.edu Thu Oct 20 15:07:25 1994 From: marcus at dope.caltech.edu (Marcus Quintana Mitchell) Date: Thu, 20 Oct 94 12:07:25 PDT Subject: No subject Message-ID: <9410201907.AA22324@dope.caltech.edu> ------------------------------------------------------------------- NIPS*94 Workshop: OPEN AND CLOSED PROBLEMS IN NEURAL NETWORK ROBOTICS --------------------------------------------------- Organizer: Marcus Mitchell CALL FOR PARTICIPATION ---------------------- Introduction ------------- Many of the presumed tenets of neural computation -- nonlinearity, parallelism, adaptation, real-time performance -- suggest that a "neuromorphic" approach to robotics problems could succeed where previous approaches have failed. Further, the amazing motor performance of humans and animals provides additional arguments for the potential benefits of "a sideways look" towards neurobiology. Spurred on by these and other factors, researchers from a variety of backgrounds have produced almost 15 years of research intended to elaborate a biologically-inspired robotics. This workshop will ask the questions "What has been accomplished so far?" and "What is to be done next?" Aims ---- For all the research attempts to apply neural network ideas to robotics, it is still difficult to get clear answers to questions like "Can you use a neural network to control a 6 d.o.f. arm?" or "Do reinforcement learning learning and dynamic programming methods get killed by the curse of dimensionality?" In addition, robotics is an area with a vast and intimidating "non-neural" literature which must be considered. The main goal of this workshop is to stimulate discussion about what problems have been successfully attacked and what the most important current open problems entail. A secondary goal of the workshop is to produce a short consensus list of problem descriptions and their status. Schedule for Saturday, December 3, 1994 --------------------------------------- (subject to change) 7:30 - 8:00 Opening Remarks Marcus Mitchell, Caltech 8:00 - 8:25 Why it's harder to control your robot than your arm: closed, open and irrelevant issues in inverse kinematics Dave Demers, UCSD 8:25 - 9:00 Discussion 9:00 - 9:25 Open Problem: Optimal Motor Hidden Units Terry Sanger, JPL 9:25 - 10:00 Discussion 10:00 - 10:25 Neural Network Vision for Outdoor Robot Navigation Dean Pomerleau, CMU 10:25 - 11:00 Discussion 11:00 - 4:30 FREE TIME 4:30 - 4:55 Learning New Representations and Strategies Chris Atkeson, Georgia Tech 4:55 - 5:30 Discussion 5:30 - 5:55 A Semi-Crisis for Neural Network Robotics: Formal Specification of Robot Learning Tasks Andrew Moore, CMU 5:55 - 6:30 Discussion 6:30 - 6:35 Closing Remarks Related workshop on control --------------------------- A complementary workshop, titled "Novel Control Techniques from Biological Inspiration", organized by Jim Schwaber et al., may be of interest to participants. None of the presentations in that session will be on robotics, and its main focus will be on nonlinear dynamical systems, e.g. in chemical processes and in neural systems. It is a one day workshop to be held Friday, December 2, 1994. For more information contact Richard Braatz (rdb at beethoven.che.caltech.edu). --------------------------------------------------------------------------- Marcus Q. Mitchell Computation and Neural Systems, Mail Code 139-74 California Institute of Technology Pasadena, CA 91125 Phone: (818) 395-2805 FAX: (818) 792-7402 email: marcus at hope.caltech.edu  From lbookman at tiac.net Fri Oct 21 01:05:43 1994 From: lbookman at tiac.net (Larry Bookman) Date: Fri, 21 Oct 1994 00:05:43 -0500 Subject: Book anouncement Message-ID: <199410210406.AAA29896@zork.tiac.net> *** Announcing a new book *** available from Kluwer Academic Publishers: Trajectories Through Knowledge Space: A Dynamic Framework For Machine Comprehension by Lawrence A. Bookman ISBN 0-7923-9487-9 (Order information is in the end of this message) A central focus of the book is on the developemnt of a framework for comprehension connecting research themes from cognitive psychology, cognitive science, corpus linguistics, and artificial intelligence. The book proposes a new architecture for semantic memory, providing a framework for addressing the problem of how to represent background knowledge in a machine. -------------------------------------------- Excerpt from FOREWORD .. this volume is without question a milestone in language processing scholarship. Bookman has pulled many research threads from a number of fields to weave a remarkably cohesive picture of the processes underlying human language comprehension. The net effect is both exciting and inspiring --- this book will be embraced by studious newcomers and appreciated by seasoned researchers as well. It is difficult to find cognitive researchers who have a visionary sense of the big picture. Larry Bookman's vision is both comprehensive and sparkling in its clarity. Read this book from cover to cover and then read it again. This is what the field of natural language processing is all about. Wendy Lehnert Professor of Computer Science Director of the Natural Language Processing Laboratory University of Massachusetts at Amherst -------------------------------------------- TABLE OF CONTENTS List Of Figures List Of Tables Foreword By Wendy Lehnert Preface Chapter 1 Introduction 1.1 Motivation 1.2 A View of Text Comprehension 1.3 Overview of the LeMICON System 1.4 Implementation 1.5 Points of Interest 1.6 The Impact of this Work on Four Related Fields 1.7 Development of the Two-Tier Model 1.8 A Guide to the Reader Chapter 2 An Overview of Connectionist and Probabilistic Approaches to Language Processing 2.1 A Computational Linguistics Perspective 2.2 A Connectionist Perspective 2.3 A Comparison of Connectionist and Probabilistic NLP Methods 2.4 Bridging the Gap --- Integrating Connectionist and Computational Linguistic Approaches Chapter 3 Memory Architecture 3.1 The Relational Tier 3.2 The Associational or ASF Tier 3.3 Connecting the Two Tiers 3.4 Working Memory 3.5 How New Knowledge Is Integrated Chapter 4 The Basic Computation 4.1 A Functional Description of the Algorithm 4.2 Representing the Input 4.3 Computational Details and Program Output at each Step 4.4 General Discussion of the Algorithm 4.5 How LeMICON Handles Binding 4.6 The Links to Psychology and Neurophysiology Revisited 4.7 Some Comparisons to Other Text Understanding Systems Chapter 5 Analysis of the Interpretation at the Relational and ASF Level 5.1 Introduction 5.2 Analyzing the Interpretation at the Relational Level 5.3 Analyzing the Interpretation at the ASF Level 5.4 Analyzing Time-Dependent Interactions at the ASF Level 5.5 Comparing Interpretations --- A Quantitative Analysis 5.6 An Ablation Study Chapter 6 Reasoning from the Relational Level of the Representation 6.1 Introduction 6.2 Identifying the Conceptual Roots 6.3 Explaining the Connections Between Events 6.4 Determining Important Concepts in the Interpretation Graph 6.5 Conceptual Roots and their Role in Summarization Chapter 7 Experiments in Acquiring Knowledge from On-line Corpora 7.1 Introduction 7.2 The Automatic Acquisition of Knowledge from On-line Sources 7.3 The Automatic Construction of the Relational Tier 7.4 The Automatic Construction of the Associational Tier 7.5 How Semantic Memory Evolves in Response to New Input 7.6 Changing the Link Weights 7.7 Implementation Details Chapter 8 An Analysis of the Acquired Knowledge 8.1 An Alternative View of the UnderlyingKnowledge Representation 8.2 Discussion of Soundness of Approach 8.3 An Evaluation of LeMICON's Representation 8.4 Previous Text Systems Revisited 8.5 The Knowledge Acquisition Continuum Chapter 9 Conclusions 9.1 Some Consequences of the Two-Tier Model of Memory 9.2 Associational Representations 9.3 The Universality of ASFs 9.4 Scalability 9.5 Automatic Acquisition of Knowledge 9.6 Building Large-Scale Knowledge Bases 9.7 A Link to Corpus Linguistics 9.8 The Interplay between Computation and Representation 9.9 Limitations Chapter 10 Future Directions 10.1 Expanding The Knowledge Base 10.2 Finding Deeper Semantic Relationships via Corpus Analysis 10.3 Handling Contradictory Input 10.4 Learning New Relationships 10.5 A Basic Level Semantic Encoding 10.6 Child Versus Adult Comprehension Appendix A The ASFs Used in the LeMICON Experiments Appendix B A Formal Analysis of the Dynamics B.1 The Defining Set of Equations B.2 An Analysis of the Defining Equations B.3 The ASF Contribution Appendix C Sample Parsed Input to LeMICON Appendix D Additional Results with SSS D.1 Further Examples of Summarization D.2 Importance Appendix E Proof of the Boundedness of the Measure I Appendix F The Dictionary Trees that Describe the Class ``Space'' References Author Index Subject Index ---------------------------------------------------------------------------- ISBN 0-7923-9487-9 e-mail: Kluwer at world.std.com To order in USA: | To order in Europe: | | Kluwer Academic Publishers, Order Dept. | Kluwer Academic Publishers, Order Dept. | P.O.B. 358 | P.O.B. 322 Accord Station, Hingham, MA 02018-0358 | 3300AH Dordrecht | The Netherlands | Phone: (617) 871-6300 | Phone: 31-77-524-400 FAX: (617) 871-6528 | FAX: 31-78-524-474 ----------------------------------------------------------------------------  From prechelt at ira.uka.de Fri Oct 21 08:51:21 1994 From: prechelt at ira.uka.de (Lutz Prechelt) Date: Fri, 21 Oct 1994 13:51:21 +0100 Subject: Techreport on Proben1 Neural Network benchmark collection Message-ID: <"irafs2.ira.229:21.10.94.12.50.46"@ira.uka.de> FTP-host: archive.cis.ohio-state.edu FTP-filename: /pub/neuroprose/prechelt.bench.ps.Z URL: ftp://archive.cis.ohio-state.edu/pub/neuroprose/prechelt.bench.ps.Z The technical report Proben1 --- A Set of Neural Network Benchmark Problems and Benchmarking Rules is now available for anonymous ftp as ftp.ira.uka.de /pub/papers/techreports/1994/1994-21.ps.Z and as archive.cis.ohio-state.edu /pub/neuroprose/prechelt.bench.ps.Z The report has 38 pages, the file is 158 Kb. The report is the documentation of a benchmark collection that I have prepared. This collection is the first closed and exactly documented benchmark collection specifically made for neural network research. All of its problems are 'real' problems in the sense that the data has not been generated artificially. Most of the problems were taken from the UCI machine learning databases archive. Particular emphasis lies on achieving reproducibility of results, which is difficult with most existing real world data benchmarks. Here is the abstract: Proben1 is a collection of problems for neural network learning in the realm of pattern classification and function approximation plus a set of rules and conventions for carrying out benchmark tests with these or similar problems. Proben1 contains 15 data sets from 12 different domains. All datasets represent realistic problems which could be called diagnosis tasks and all but one consist of real world data. The datasets are all presented in the same simple format, using an attribute representation that can directly be used for neural network training. Along with the datasets, Proben1 defines a set of rules for how to conduct and how to document neural network benchmarking. The purpose of the problem and rule collection is to give researchers easy access to data for the evaluation of their algorithms and networks and to make direct comparison of the published results feasible. This report describes the datasets and the benchmarking rules. It also gives some basic performance measures indicating the difficulty of the various problems. These measures can be used as baselines for comparison. -- Here is a bibtex entry of the report: @techreport{Prechelt94c, author = {Lutz Prechelt}, title = {{PROBEN1} --- {A} Set of Benchmarks and Benchmarking Rules for Neural Network Training Algorithms}, institution = {Fakult\"at f\"ur Informatik, Universit\"at Karlsruhe}, year = {1994}, number = {21/94}, address = {D-76128 Karlsruhe, Germany}, month = sep, note = {Anonymous FTP: /pub/pa\-pers/tech\-reports/1994/1994-21.ps.Z on ftp.ira.uka.de}, } The benchmark collection itself (including the report) is available for anonymous ftp from the directories ftp.ira.uka.de /pub/neuron and ftp.cs.cmu.edu /afs/cs/project/connect/bench/contrib/prechelt in both cases the file name is proben1.tar.gz (ca. 2 Mb) Lutz Lutz Prechelt (email: prechelt at ira.uka.de) | Whenever you Institut fuer Programmstrukturen und Datenorganisation | complicate things, Universitaet Karlsruhe; 76128 Karlsruhe; Germany | they get (Voice: ++49/721/608-4068, FAX: ++49/721/694092) | less simple.  From fogelman at laforia.ibp.fr Fri Oct 21 15:53:41 1994 From: fogelman at laforia.ibp.fr (FOGELMAN Francoise + 33 1 41 28 41 70) Date: Fri, 21 Oct 94 20:53:41 +0100 Subject: Call ICANN'95 Message-ID: <9410211953.AA23128@laforia.ibp.fr> Could you please post the following announcement ? Thanks in advance ***************************************************************************** XXX XXXX X XX XX XX XX XX XXXXX XXXXXX X X X X XXX XX XXX XX XX X XX X X X XXXXX XX X XX XX X XX XXXXX XXXXX X X X X XX XXX XX XXX XX XXX XXX XXXX X X XX XX XX XX XXXX XXXXX PARIS, OCTOBER 9-13, 1995 Maison de la Chimie NEURAL NETWORKS AND THEIR APPLICATIONS ***************************************************************************** SCIENTIFIC CONFERENCE INDUSTRIAL CONFERENCE TUTORIALS & EXHIBITION organized by EUROPEAN NEURAL NETWORK SOCIETY ***************************************************************************** REGISTRATION, INFORMATION ***************************************************************************** Over the last four years, the ENNS - European Neural Network Society - has held its annual conference ICANN in Helsinki (1991), Brighton (1992), Amsterdam (1993) and Sorrento (1994). This conference has become the foremost meeting for the European neural network scientific community. In 1995, ENNS will hold the ICANN meeting in Paris. The format of this conference will include a scientific conference, an industrial conference, tutorials, industrial forums and an industrial exhibition. Our challenge, in organizing this conference, is to achieve the highest scientific quality for papers presented at the scientific conference (there will be a high rejection rate if necessary), together with the most convincing set of applications presented at the industrial conference (only operational, top-level applications will be considered). We thus hope to demonstrate that Neural Networks are indeed a very deep and exciting field of research, as well as a most efficient, profitable technique for the industry. To achieve these goals, we seek contributions from all the scientists, both from academy and industry, who share our interests and our quality requirements. ***************************************************************************** CALL FOR PAPERS The conference will cover the following domains : SCIENTIFIC CONFERENCE * theory * algorithms & architectures * implementations (hardware & software) * cognitive sciences & AI * neurobiology * applications identification & control image processing & vision OCR speech & signal processing prediction optimization INDUSTRIAL CONFERENCE This conference will cover two main categories: on the one hand, descriptions of tools and methods and their use in real-life cases and, on the other hand, descriptions of concrete applications in industry and the sector of services. All fields of application are eligible. Special sessions will be organized on specific areas of industry such as: * banking, finance & insurance * telecommunications * teledetection * process engineering, control and monitoring * oil industry * power industry * food processing * transportation * robotics * speech processing * document processing, OCR, text retrieval & indexing * VLSI & dedicated hardware * forecasting & marketing * technical diagnosis * non destructive testing * medicine * defense LOCATION The conference will be held in la Maison de la Chimie, right in the center of Paris, close by les Invalides. Built in 1707, for Frederic-Maurice de la Tour, Comte d'Auvergne, Lieutenant General to King Louis XIV, the Mansion has today become a Congress Center equipped with all the modern facilities. INSTRUCTIONS TO AUTHORS Length of papers: not exceeding 6 pages in A4 format (i. e. about 8,000 characters). An electronic format will be made available at : ftp lix.polytechnique.fr login: anonymous password : your e-mail address in the directory /pub/ICANN95/out, read file README for instructions. If you want to leave messages or enquiries, you can also use : in the directory /pub/ICANN95/in, read file README for instructions. Seven copies of the papers should reach the Conference Secretariat at the address below by ****** MARCH 20 1995 ***** : ICANN'95 1 avenue Newton bp 207 92 142 CLAMART Cedex France Submitted papers should be accompanied by a cover page giving: * the title of the paper and the author(s) name(s), * the author's address, phone number and extension, fax number and, if possible, e-mail address, * a 10-line abstract together with a list of key-words, * an indication of which conference the paper should be included in: scientific or industrial LANGUAGE Papers submitted for the scientific conference should be in English. Papers submitted for the industrial conference may be either in English or French. TUTORIALS Tutorials will be organized. The Program Committee is open to proposals for tutorials covering industrial applications.Suggestions should describe the content of the tutorial (in 150-200 words) and the instructor's expertise and experience in the field concerned. The deadline for reception is MAY 15 1995. EXHIBITION From fogelman Fri Oct 21 15:36:19 1994 From: fogelman (FOGELMAN Francoise + 33 1 41 28 41 70) Date: Fri, 21 Oct 94 20:36:19 +0100 Subject: ICANN'95 Message-ID: <9410211936.AA23061@laforia.ibp.fr> ***************************************************************************** XXX XXXX X XX XX XX XX XX XXXXX XXXXXX X X X X XXX XX XXX XX XX X XX X X X XXXXX XX X XX XX X XX XXXXX XXXXX X X X X XX XXX XX XXX XX XXX XXX XXXX X X XX XX XX XX XXXX XXXXX PARIS, OCTOBER 9-13, 1995 Maison de la Chimie NEURAL NETWORKS AND THEIR APPLICATIONS ***************************************************************************** SCIENTIFIC CONFERENCE INDUSTRIAL CONFERENCE TUTORIALS & EXHIBITION organized by EUROPEAN NEURAL NETWORK SOCIETY ***************************************************************************** INFORMATION ***************************************************************************** Over the last four years, the ENNS - European Neural Network Society - has held its annual conference ICANN in Helsinki (1991), Brighton (1992), Amsterdam (1993) and Sorrento (1994). This conference has become the foremost meeting for the European neural network scientific community. In 1995, ENNS will hold the ICANN meeting in Paris. The format of this conference will include a scientific conference, an industrial conference, tutorials, industrial forums and an industrial exhibition. Our challenge, in organizing this conference, is to achieve the highest scientific quality for papers presented at the scientific conference (through a strict selection procedure), together with the most convincing set of applications presented at the industrial conference (only operational, top-level applications will be considered). Papers should stress the rationale of the Neural Network approach and provide a comparison with other techniques. We thus hope to demonstrate that Neural Networks are indeed a very deep and exciting field of research, as well as a most efficient, profitable technique for the industry. To achieve these goals, we seek contributions from all the scientists, both from academy and industry, who share our interests and our quality requirements. ***************************************************************************** CALL FOR PAPERS The conference will cover the following domains : SCIENTIFIC CONFERENCE * theory * algorithms & architectures * implementations (hardware & software) * cognitive sciences & AI * neurobiology * applications identification & control image processing & vision OCR speech & signal processing prediction optimization INDUSTRIAL CONFERENCE This conference will cover two main categories: on the one hand, descriptions of tools and methods and their use in real-life cases and, on the other, descriptions of concrete applications in industry and the sector of services. All fields of application are eligible. Special sessions will be organized on specific areas of industry such as: * banking, finance & insurance * telecommunications * teledetection * process engineering, control and monitoring * oil industry * power industry * food processing * transportation * robotics * speech processing * document processing, OCR, text retrieval & indexing * VLSI & dedicated hardware * forecasting & marketing * technical diagnosis * non destructive testing * medicine * defense LOCATION The conference will be held in la Maison de la Chimie, right in the center of Paris, near les Invalides. Built in 1707, for Frederic-Maurice de la Tour, Comte d'Auvergne, Lieutenant General to King Louis XIV, the Mansion has today become a Congress Center equipped with all the modern facilities. INSTRUCTIONS TO AUTHORS Length of papers: not exceeding 6 pages in A4 format (i. e. about 8,000 characters). An electronic format will be made available at : ftp lix.polytechnique.fr login: anonymous password : your e-mail address in the directory /pub/ICANN95/out, read file README for instructions. If you want to leave messages or enquiries, you can also use : in the directory /pub/ICANN95/in, read file README for instructions. Seven copies of the papers should reach the Conference Secretariat at the address below by ****** MARCH 20 1995 ***** : ICANN'95 1 avenue Newton bp 207 92 142 CLAMART Cedex France Submitted papers should be accompanied by a cover page giving: * the title of the paper and the author(s) name(s), * the author's address, phone number and extension, fax number and, if possible, e-mail address, * a 10-line abstract together with a list of key-words, * an indication of which conference the paper should be included in: scientific or industrial LANGUAGE Papers submitted for the scientific conference should be in English. Papers submitted for the industrial conference may be either in English or French. TUTORIALS Tutorials will be organized. The Program Committee is open to proposals for tutorials covering industrial applications. Suggestions should describe the content of the tutorial (in 150-200 words) and the instructor's expertise and experience in the field concerned. The deadline for reception is MAY 15 1995. EXHIBITION >From October 11-13, 1995, the Conference will host a trade fair of commercially available products relating to neural network tools and applications. In addition, advanced prototypes of tools and applications developed by public sector research organizations will be demonstrated. To receive a complete exhibitor's package, please contact the Conference Secretariat at the address indicated. ***************************************************************************** TEAR OFF HERE ***************************************************************************** INFORMATION FORM to be returned to: ICANN'95 1 avenue Newton bp 207 92 142 CLAMART Cedex France ICANN ' 95 Paris, October 9-13, 1995 Last name : .......................................................... First Name : ........................................................ Organization or company : ............................................ ...................................................................... ...................................................................... Postal code/Zip code : ............................................... City : ............................................................... Country : ............................................................ Tel : .................................Fax : ......................... Electronic mail:...................................................... * I wish to attend the O Scientific conference O Industrial conference * I intend to exhibit * I intend to submit a paper Provisional title.................................................... Author (s) : ........................................................ Brief outline of the subject : ...................................... ..................................................................... Category : * Scientific conference O Theory O Algorithms & architectures O Implementations O Cognitive sciences & AI O Neurobiology O Applications ( please specify) * Industrial conference O Tools O Techniques O Applications ( please specify) ***************************************************************************** TEAR OFF HERE ***************************************************************************** STEERING COMMITTEE Chair F. Fogelman - Sligos (Paris, F) Scientific Program co-chairs G. Dreyfus - ESPCI (Paris, F) M. Weinfeld - Ecole Polytechnique (Palaiseau, F) Industrial Program chair P. Corsi - CEC (Brussels, B) Tutorials & Publications chair P. Gallinari - Universite P.& M.Curie (Paris, F) SCIENTIFIC PROGRAM COMMITTEE (Preliminary) I. Aleksander (UK); L.B. Almeida (P); S.I. Amari (J); E. Bienenstock (USA); C. Bishop (UK); L. Bottou (F); J. M. Buhmann (D); S. Canu (F); V. Cerny (SL); M. Cosnard (F); R. De Mori (CAN); R. Eckmiller (D); N. Franceschini (F); S. Gielen (NL); J. Herault (F); M. Jordan (USA); D. Kayser (F); T. Kohonen (SF); A. Lansner (S); Z. Li (USA); L. Ljung (S); C. von der Malsburg (D); S. Marcos (F); P.Morasso (I); J.P.Nadal(F); E. Oja (SF); P. Peretto (F); C. Peterson (S); L. Personnaz (F); R. Pfeiffer (CH); T. Poggio (USA); P. Puget (F); S. Raudys (LT); H. Ritter (D); M. Saerens ( B); W. von Seelen (D); J.J. Slotine (USA); S. Solla (DK); J.G. Taylor (GB); C. Torras (E); B. Victorri (F); A. Weigend (USA). INDUSTRIAL PROGRAM COMMITTEE (Preliminary) M. Boda (S); B. Braunschweig (F); C. Bishop (UK); J.P. Corriou (F); M. Duranton (F); A. Germond (CH); I. Guyon (USA); P. Refenes (UK); S. Thiria (F); C. Wellekens (B); B. Wiggins (UK). *****************************************************************************  From singer at CS.HUJI.AC.IL Sun Oct 23 07:16:28 1994 From: singer at CS.HUJI.AC.IL (Yoram Singer) Date: Sun, 23 Oct 1994 13:16:28 +0200 Subject: thesis available (corrections) Message-ID: <199410231116.AA01484@minuet.cs.huji.ac.il> 1. The thesis "Unsupervised Learning of Cell Activities in the Associate Cortex of Behaving Monkeys, Using Hidden Markov Models" by Itay Gat was supervised by Dr. Naftali Tishby (Institute of Computer Science and Center for Neural Computation, Hebrew University) and Prof. Moshe Abeles (School of Medicine and Center for Neural Computation, Hebrew University). 2. Due to a major power breakdown the cs.huji.ac.il ftp server was down from Thursday afternoon to Sunday morning. The server is now up and operating. We apologize for the inconvenient. Itay Gat & Yoram Singer Institute of Computer Science The Hebrew University, Israel  From thrun at uran.informatik.uni-bonn.de Sun Oct 23 18:14:22 1994 From: thrun at uran.informatik.uni-bonn.de (Sebastian Thrun) Date: Sun, 23 Oct 1994 23:14:22 +0100 Subject: Paper available Message-ID: <199410232214.XAA12637@carbon.informatik.uni-bonn.de> This is to announce the following technical report (22 pages): LEARNING ONE MORE THING by Sebastian Thrun and Tom M. Mitchell Most research on machine learning has focused on scenarios in which a learner faces a single, isolated learning task. The lifelong learning framework assumes instead that the learner encounters a multitude of related learning tasks over its lifetime, providing the opportunity for the transfer of knowledge. This paper studies lifelong learning in the context of binary classification. It presents the invariance approach, in which knowledge is transferred via a learned model of the invariances of the domain. Results on learning to recognize objects from color images demonstrate superior generalization capabilities if invariances are learned and used to bias subsequent learning. ----------------------------------------------------------------- The paper can be retrieved via anonymous ftp by following these instructions: unix> ftp reports.adm.cs.cmu.edu ftp:name> anonymous Password:> mickey at mouse.gov ftp> cd 1994 ftp> get CMU-CS-94-184.ps (sorry, it's not compressed) ftp> bye unix> lpr CMU-CS-94-184.ps The paper uses Backprop/Tangentprop as the main learning engine, but it also addresses general machine learning issues. Your feedback is very much appreciated (thrun at cs.cmu.edu). Sebastian  From john at dcs.rhbnc.ac.uk Tue Oct 25 07:42:21 1994 From: john at dcs.rhbnc.ac.uk (john@dcs.rhbnc.ac.uk) Date: Tue, 25 Oct 94 11:42:21 +0000 Subject: Technical Report Series in Neural and Computational Learning Message-ID: <7985.9410251142@platon.cs.rhbnc.ac.uk> The European Community ESPRIT Working Group in Neural and Computational Learning Theory (NeuroCOLT): two new reports available ---------------------------------------- NeuroCOLT Technical Report NC-TR-94-009: ---------------------------------------- Complexity Issues in Discrete Hopfield Networks by Patrik Flor\'{e}en and Pekka Orponen University of Helsinki, Department of Computer Science P. O. Box 26, FIN-00014 University of Helsinki, Finland Abstract: We survey some aspects of the computational complexity theory of discrete-time and discrete-state Hopfield networks. The emphasis is on topics that are not adequately covered by the existing survey literature, most significantly: 1. the known upper and lower bounds for the convergence times of Hopfield nets (here we consider mainly worst-case results); 2. the power of Hopfield nets as general computing devices (as opposed to their applications to associative memory and optimization); 3. the complexity of the synthesis (``learning'') and analysis problems related to Hopfield nets as associative memories. ---------------------------------------- NeuroCOLT Technical Report NC-TR-94-013: ---------------------------------------- by Martin Anthony, Department of Mathematics, The London School of Economics and Political Science, Houghton Street, London WC2A 2AE, United Kingdom and Peter Bartlett, Department of Systems Engineering, Research School of Information Sciences and Engineering, The Australian National University, Canberra, 0200 Australia Abstract: In this paper, we study a statistical property of classes of real-valued functions that we call approximation from interpolated examples. We derive a characterization of function classes that have this property, in terms of their `fat-shattering function', a notion that has proven useful in computational learning theory. We discuss the implications for function learning of approximation from interpolated examples. Specifically, it can be interpreted as a problem of learning real-valued functions from random examples in which we require satisfactory performance from every algorithm that returns a function which approximately interpolates the training examples. ----------------------- The Report NC-TR-94-013 can be accessed and printed as follows % ftp cscx.cs.rhbnc.ac.uk (134.219.200.45) Name: anonymous password: your full email address ftp> cd pub/neurocolt/tech_reports ftp> binary ftp> get nc-tr-94-013.ps.Z ftp> bye % zcat nc-tr-94-013.ps.Z | lpr -l Likewise for NC-TR-94-009. Uncompressed versions of the postscript files have also been left for anyone not having an uncompress facility. A full list of the currently available Technical Reports in the Series is held in a file `abstracts' in the same directory. Best wishes John Shawe-Taylor  From plaut at cmu.edu Tue Oct 25 09:16:49 1994 From: plaut at cmu.edu (David Plaut) Date: Tue, 25 Oct 1994 09:16:49 -0400 Subject: Postdoctoral position available Message-ID: <4153.783091009@crab.psy.cmu.edu> POSTDOCTORAL FELLOW IN CONNECTIONIST NEUROPSYCHOLOGY OF READING AND LANGUAGE I have funding for a postdoctoral fellow to collaborate with me in the area of connectionist modeling of cognitive processes in reading and language and their breakdown following brain damage. It is a two-year position supported by the Center for the Neural Basis of Cognition of Carnegie Mellon University and the University of Pittsburgh, and located in the Department of Psychology at Carnegie Mellon. Applicants should have either expertise in connectionist modeling, or expertise in the cognitive psychology/neuropsychology of reading and language combined with some experience in modeling. Please send a vita, a brief description of research experience and interests, copies of representative publications, and three letters of reference to David Plaut, Department of Psychology, Carnegie Mellon University, Pittsburgh PA, 15213-3890. Consideration of applications will begin January 1 and continue until the position is filled. Carnegie Mellon is an affirmative action/equal opportunity employer. =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= David Plaut plaut at cmu.edu "Doubt is not a pleasant Department of Psychology 412/268-5145 condition, but certainty Carnegie Mellon University 412/268-5060 (FAX) is an absurd one." Pittsburgh, PA 15213-3890 345H Baker Hall --Voltaire =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=  From plunkett at psy.ox.ac.uk Tue Oct 25 09:26:37 1994 From: plunkett at psy.ox.ac.uk (Kim Plunkett) Date: Tue, 25 Oct 1994 13:26:37 GMT Subject: No subject Message-ID: <199410251326.NAA22996@unicorn.psych.ox.ac.uk> Oxford McDonnell-Pew Centre for Cognitive NeuroScience Neural Network Scientist Department of Experimental Psychology University of Oxford The McDonnell-Pew Centre for Cognitive Neuroscience wish to appoint a scientist to assist in the establishment of a Neu- roComputing Centre for Cognitive Scientists and NeuroScien- tists. The person appointed would be expected to provide advice on a wide range of neural network simulators running on Dec Alpha machines, and also to develop neural network software as part of a demonstration package to be used by cognitive neuroscientists and cognitive scientists. The successful applicant will be well-versed in C (or C++) pro- gramming, the X-windows interface and have a working knowledge of neural networks. The appointment, to start as soon as possible, is for one year and will be made at the appropriate level on the academically related RS1A scale (GBP 13,941 -> 20,953). Further information can be obtained from: Kim Plunkett (plunkett at psy.ox.ac.uk) Tel: 0865-271398 Ray Bellis (rpb at psy.ox.ac.uk) Tel: 0865-271359 Edmund Rolls (erolls at vax.ox.ac.uk) Tel: 0865-271348 all at: Department of Experimental Psychology University of Oxford South Parks Road Oxford OX1 3UD Applicants should send a full CV to Miss Lesley Court McDonnell-Pew Centre for Cognitive NeuroScience Department of Experimental Psychology South Parks Road Oxford OX1 3UD by November 15th 1994.  From dyyeung at cs.ust.hk Wed Oct 26 15:31:24 1994 From: dyyeung at cs.ust.hk (Dr. D.Y. Yeung) Date: Wed, 26 Oct 94 15:31:24 HKT Subject: Faculty Openings at HKUST -- a relatively new research university in Hong Kong Message-ID: <9410260731.AA03406@cs.ust.hk> THE HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY Department of Computer Science The Department of Computer Science will have at least 10 faculty positions open AT ALL LEVELS for the 1995-96 academic year. Applications for senior-level positions are particularly solicited. The department began its first classes in October, 1991. It currently has 41 faculty members recruited from major universities and research institutions around the world and 430 undergraduate and 95 postgraduate students. We have active research groups in the areas of artificial intelligence, computer engineering, data and knowledge base management, software technology, and theoretical computer science. We are looking for new faculty with research interests in these areas as well as in the areas of Chinese (or multi-lingual) computing, natural language processing, neural networks, and robotics. Research funding is available through government agencies and industry-sponsored research institutes at the university, such as the Hong Kong Telecom Institute of Information Technology and the Sino Software Research Centre. The Hong Kong University of Science and Technology is a publicly-funded research university. It has Schools of Science, Engineering, Business & Management, and Humanities and Social Science. It is located on a new, well-equipped coastal campus overlooking the spectacular Clear Water Bay. Students admitted to the department rank among the top 10% of Hong Kong's secondary school graduates. The medium of instruction is English. Salary and benefits are competitive. Initial appointments will normally be on a three-year contract which is renewable subject to mutual agreement. A gratuity of an amount equal to 25% of the total basic salary received will be payable upon contract completion. Shorter-term visiting positions are also available for senior applicants. Applicants should have an earned Ph.D. and high potential in teaching and research. Senior applicants must have exceptional research records. Applications/nominations should be sent with a curriculum vitae together with names of at least three references to: Prof. Vincent Y. Shen, Head Department of Computer Science The Hong Kong University of Science & Technology Clear Water Bay, Kowloon HONG KONG Fax No. : (852) 358-2679 E-mail : vshen at cs.ust.hk Applications will be evaluated immediately upon receipt. Maximum consideration will be given to applications received by December 31, 1994.  From lxu at cs.cuhk.hk Wed Oct 26 10:21:47 1994 From: lxu at cs.cuhk.hk (Dr. Xu Lei) Date: Wed, 26 Oct 94 22:21:47 +0800 Subject: A NIPS*94 WORKSHOP Message-ID: <9410261421.AA16797@cucs18.cs.cuhk.hk> A NIPS*94 POST CONFERENCE WORKSHOP UNSUPERVISED LEARNING RULES AND VISUAL PROCESSING Lei Xu$^1$, Zhaoping Li$^2$ and Laiwan Chan$^1$ 1. The Chinese University of Hong Kong 2. Hong Kong University of Science and Technology There are three major types of unsupervised learning rules: competitive learning or vector quantization type, information preserving or {\em Principal Component Analysis (PCA)} type, and the self-organizing topological map type. All of them are closely related to visual processing. For instance, they are used to interpret the developments of orientation and other feature selective cells, as well as development of cortical retinotopic maps such as ocular dominance and orientation columns. The development of the study of learning and the understanding of visual processing facilitate each other. Recent years, a number of advances have been made in both in the two areas. For instance, in the area of unsupervised learning, (1) numerous algorithms for competitive learning, PCA learning, and self-organizing maps have been proposed; (2) several new theories and principles, like maximum coherence, minimum description length, finite mixtures with EM learning, statistical physics, Bayesian theory, exploratory projection pursuit, and local PCA, have been developed; (3) theories for unifying various unsupervised learning rules (e.g., multisets modeling learning theory) have been explored. In the area of visual processing, more knowledge is being gathered experimentally about how visual development can be preserved or altered by neural activities, neural transmitters/receptors, and the visual environment etc, providing the bases and constraints for various learning rules and motivating new learning rule studies. In addition, there has been more theoretical understandings on the dependence of the visual processing units on the visual input environment, supporting the rationality of unsupervised learning. The purpose of this workshop is twofolds: (1) to summarize the advances on unsupervised learning and to discuss whether these advances can help the investigation on visual processing system; (2) to screening the current results on visual processing and to check if they can motivate or provide some hints on developing unsupervised learning theories. The targeted groups of participants are researchers working in either or both the area of learning and the study of visual processing. ----------------------------------------------------------------------------- NIPS*94 WORKSHOP PROGRAM The Friday morning session 7:30-9:30AM, Dec.2, chairperson Lei Xu 1. "Time-Domain Solutions of Oja's Equations", John Wyatt and Ibrahim Elfadel (MIT) 2. "Kmeans Performs Newton Optimization", Leon Bottou (Neuristique Paris) and Yoshua Bengio (University of Montreal) 3. "Multisets Modeling Learning: An Unified Framework for Unsupervised Learning", Lei Xu (The Chinese University of Hong Kong and Peking University) 4. "Information Theory Motivation For Projection Pursuit", Nathan Intrator (Tel-Aviv University) 5. "The Helmholtz Machine", Peter Dayan (University of Toronto) The Friday evening session, chairperson 4:30-6:30PM, Dec.2, Zhaoping Li 1. "Predictability Minimization And Visual Processing", Juergen Schmidhuber (Technische Universitaet Muenchen) 2. "Non-linear, Non-gaussian Information Maximisation: Why It's More Useful", Tony Bell (Salk Institute) 3. "Understanding The Visual Cortical Coding From Visual Input Statistics", Zhaoping Li (Hong Kong University of Science and Technology) 4. "Formation Of Orientation And Ocular Dominance In Macaque Striate Cortex", Klaus Obermayer (Universitaet Bielefel) 5. "Putative Functional Roles Of Self-organized Lateral Connectivity In The Primary Visual Cortex", Joseph Sirosh (University of Texas at Austin) The Saturday morning session 7:30-9:30AM, Dec.3, chairperson, Laiwan Chan 1. "Density Estimation with a Hybrid of Neural Networks and Gaussian Mixtures", Yoshua Bengio (University of Montreal) 2. "Learning Object Models through Domain-Specific Distance Measures" Eric Mjolsness (UCSD) and Steve Gold (Yale University) 3. "Auto-associative Learning of On-line Handwriting Using Recurrent Neural Networks", Dit-Yan Yeung (Hong Kong University of Science and Technology) 4. "Training Mixtures of Gaussians with Deficient Data", Volker Tresp (Siemens AG, Central Research) 5. "A Fast Method for Activating Competitive Self-Organizing Neural-Networks", George F. Harpur and Richard W. Prager (Cambridge University) The Saturday evening session 4:30-6:30PM, Dec.3, chairperson, Lei Xu 1. "Neuromodulatory Mechanisms For Regulation Of Cortical Self-organization", Michael E. Hasselmo (Harvard University) 2. "Learning To Cluster Visual Scenes With Contextual Modulation", Sue Becker (McMaster University) 3. "Invisibility in Vision: Occlusion, Motion, Grouping, and Self-Organization", Jonathan A. Marshall (University of North Carolina at Chapel Hill) 4. "A Comparative Study on Receptive Filters by PCA Learning and Gabor Functions", Irwin King and Lei Xu (The Chinese University of Hong Kong) 5. "Detection of Visual Feature Locations with a Growing Neural Gas Network" Bernd Fritzke (Ruhr-Universitaet Bochum)  From kolen-j at cis.ohio-state.edu Wed Oct 26 17:20:53 1994 From: kolen-j at cis.ohio-state.edu (john kolen) Date: Wed, 26 Oct 1994 17:20:53 -0400 Subject: Thesis announcement Message-ID: <199410262120.RAA16138@squirt.cis.ohio-state.edu> Many of you already know of its existance, but this is for the rest of the NN community. If you plan to retrieve this document make sure you read the warning at the end of this message. Ftp-site: cis.ohio-state.edu Ftp-directory: pub/neuroprose/Thesis/kolen.thesis.ps.Z PrintedPages: 191 Exploring the Computational Capabilities of Recurrent Neural Networks John F. Kolen While many researchers have successfully organized neural networks into structures displaying universal computational capability, most have ignored the more daunting endeavor of identifying ongoing computation, or information processing, as it occurs. My thesis addresses this problem as it relates to the understanding of the information processing capabilities of recurrent neural networks. I have isolated three important facets of recurrent neural networks that contribute to their computational power: internal dynamics, input modulation, and output generation. Theories of dynamical systems and iterated function systems have proven crucial in developing an understanding of these facets. With respect to my original question of identifying ongoing computation, the evidence suggests that the any observed computational powers of neural networks arise not from the network itself, but our application of it as a symbol processing device. If we consider recurrent neural networks as the a cognitive e. coli, this dissertation is a step toward understanding the nature cognition and intelligence. ********* WARNING *********** This document contains Level 2 PostScript commands that will not work on Level 1 printers (i.e. old LaserWriters and old versions of ghostview).  From sassk at macaulay-land-use.scot-agric-res-inst.ac.uk Thu Oct 27 09:03:06 1994 From: sassk at macaulay-land-use.scot-agric-res-inst.ac.uk (Jim Kay) Date: Thu, 27 Oct 94 13:03:06 GMT Subject: Stats/ANN Workshop Message-ID: <17956.9410271303@mluri.sari.ac.uk> STATISTICS AND NEURAL NETWORKS A research workshop on the above topic will be held in Edinburgh under the auspices of the International Centre for Mathematical Sciences. Invited speakers will include Leo Breiman (Berkeley), Phil Brown (Liverpool), David Hand (Open University), Trevor Hastie (ATT and Stanford), Nathan Intrator (Tel Aviv), Michael Jordan (MIT), Jim Kay (SASS), David Lowe (Aston), David Mackay (Cambridge), Radford Neal (Toronto) and Brian Ripley (Oxford). The workshop will take place on April 19-20, 1995, and will be followed by an Open Meeting on April 21, 1995. The meetings will form part of the Edinburgh Science Festival. Although participation in the Workshop will be predominantly by invitation, there will be a small number of places for direct applicants, with some priority given to research students who apply before November 30, 1994. For details contact either J. W. Kay (SASS, Macaulay Land Use Research Institute, Craigiebuckler, Aberdeen, AB9 2QJ; sassk at mluri.sari.ac.uk) or D. M. Titterington (Department of Statistics, University of Glasgow, Glasgow G12 8QQ; mike at stats.gla.ac.uk) as soon as possible. Applicants are welcome to use the attached electronic form. However, in view of the limited numbers at the Workshop and its strategic nature, not all applicants may be successful in obtaining places. Every effort will be made to notify applicants of the success, or otherwise, of their application by mid-December, 1994. =============================================================== STATISTICS AND NEURAL NETWORKS WORKSHOP: APRIL 19 - 20, 1994 International Centre for Mathematical Sciences 14 India Street, Edinburgh EH3 6EZ PARTICIPATION AND ACCOMMODATION REQUEST FORM TITLE: FIRST NAME: SECOND NAME: INSTITUTION: ADDRESS: TELEPHONE: FAX: EMAIL ADDRESS: DATE OF ARRIVAL: DATE OF DEPARTURE: (Note that there will be an Open Meeting on April 21, for which a form will follow soon) DETAILS OF ACCOMPANYING FAMILY MEMBERS (NUMBER, RELATIONS, AND AGES, IF CHILDREN): TYPE OF ACCOMMODATION REQUIRED (B&B about 20 pounds per person per night, Hotels about 25 pounds and upwards) ANY ADDITIONAL COMMENTS: PLEASE RETURN AS SOON AS POSSIBLE WITH REGISTRATION FEE OF 15 POUNDS (10 POUNDS FOR POST-GRADUATE STUDENTS) TO : Louise Williamson ICMS Tel:0131-220-1777 Fax:0131-220-1053 Email:icms at maths.ed.ac.uk * Please make cheques payable to HERIOT-WATT UNIVERSITY - ICMS * =====================================================  From dhw at santafe.edu Thu Oct 27 16:05:12 1994 From: dhw at santafe.edu (David Wolpert) Date: Thu, 27 Oct 94 14:05:12 MDT Subject: Paper announcement Message-ID: <9410272005.AA29375@sfi.santafe.edu> *** PAPER ANNOUNCEMENT *** *** DO NOT FORWARD TO OTHER LISTS/GROUPS *** Reconciling Bayesian and non-Bayesian analysis. by D. Wolpert. 8 pages long. To appear in "Maximum Entropy and Bayesian Methods", G. Heidberder (Ed.) Abstract: This paper shows that when one extends Bayesian analysis to distinguish the truth from one's guess for the truth, one gains a broader perspective which allows the inclusion of non-Bayesian formalisms. This perspective shows how it is possible for non-Bayesian techniques to perform well, despite their handicaps. It also highlights some difficulties with the ``degree of belief" interpretation of probability. *** This file can be retrieved by anonymous ftp to ftp.santafe.edu. Once logged in, go to pub/dhw_ftp. The file is either maxent.93.reconciling.ps.Z (binary; compressed postscript) or maxent.93.reconciling.ps.Z.encoded (ascii; uuencoded compressed postscript). If any problems arise, please contact me. David Wolpert The Santa Fe Institute 1399 Hyde Park Road Santa Fe, NM, 87501, USA (505) 984-8800 (voice); (505) 982-0565 (FAX). dhw at santafe.edu  From dhw at santafe.edu Wed Oct 26 18:04:23 1994 From: dhw at santafe.edu (David Wolpert) Date: Wed, 26 Oct 94 16:04:23 MDT Subject: Book announcement Message-ID: <9410262204.AA20883@sfi.santafe.edu> ************************************************************************* *** BOOK ANNOUNCEMENT *** Please *DO* forward to other list/groups. ************************************************************************* TITLE: The Mathematics of Generalization: Proceedings of the SFI/CNLS Workshop on Formal Approaches to Supervised Learning Edited by D. Wolpert Other (first) authors: L. Breiman P. Cheeseman J. Denker T. Dietterich D. Haussler G. Hinton S. Nowlan N. Tishby G. Wahba ======================================================================= Table of Contents: Reflections After Referring Papers for NIPS Leo Breiman The Probably Approximately Correct (PAC) and Other Learning Models David Haussler and Manfred Warmuth Decision Theoretic Generalizations of the PAC Model for Neural Net and Other Learning Applications David Haussler The Relationshop Between PAC, the Statistical Physics Framework, the Bayesian Framework, and the VC Framework {a heavily revised version of a paper that was posted to connectionist.net about six months ago} David H. Wolpert Statistical Physics Models of Supervised Learning Naftali Tishby On Exhaustive Learning David H. Wolpert and Alan S. Lapedes A Study of Maximal-Coverage Learning Algorithms Hussein Almuallim and Tom Dietterich On Bayesian Model Selection Peter Cheeseman Soft Classification, a.k.a. Risk Estimation, via Penalized Log Likelihood and Smoothing Spline Analysis of Variance Grace Wahba, Chong Gu, Yuedong Wang, and Richard Chappell Current Research Leo Brieman Preface to Simplifying Neural Networks by Soft Weight Sharing Geoffrey E. Hinton and Steven Nowlan Simplifying Neural Networks by Soft Weight Sharing Geoffrey E. Hinton and Steven Nowlan Error-Correcting Output Codes: A General Method for Improving Multiclass Inductive Learning Programs Thomas G. Dietterich and Ghulum Bakiri Image Segmentation and Recognition John S. Denker and Christopher C. J. Burges =========================================================== This book grew out of a workshop held under the auspices of the Center for Non-linear Studies at Los Alamos and the Santa Fe Institute. The idea for the workshop arose from a perception that there were many different fields that address supervised learning, but by and large these fields were not communicating with one another. (Examples of such fields are neural nets, conventional Bayesian statistics, conventional sampling theory statistics, computational learning theory, AI, and machine learning.) In particular, there were many different mathematical frameworks for addressing supervised learning. All had their own jargon, their own concerns, and their own results. And for the most part they weren't interacting. This was clearly a less than optimal state of affairs; we all have much to learn from one another, not only in terms of raw mathematical results, but also (perhaps more importantly) in perceptions of what the crucial issues are and how they should be addressed. Unfortunately, although it seems that this problem is abating, the rate of improvement is quite small. It seems possible that a general lack of communication amongst its practitioners will characterize supervised learning theory for some time to come. The purpose of the workshop was try to (begin to) rectify this situation. A small group of researchers from several of the different supervised learning fields was brought together and, in effect, forced to mingle. The format of the workshop was an intensive two-day session of talks and discussion. This volume is an attempt to try to replicate the success of the workshop in a broader context. Its purpose is to do for the reader what the workshop did for its participants: help a practitioner in one of the fields that make up supervised learning become acquainted with the relevant work by his or her colleagues in other fields. Obviously (and unfortunately) it isn't possible to duplicate in a reader of a book the experience of "an intensive two-day session .. (of being) forced to mingle ... (with) researchers from different fields". Given the different format, slightly different means are needed to achieve the same ends. Accordingly, it was decided that the papers in this volume should not so much be a formal compendium of the talks presented at the workshop as an overview of the work being performed by the researchers who attended the workshop. Some of the work represented in these papers hadn't even been completed at the time of the workshop. Some of the other papers are reprints of work published shortly before or soon after the workshop. However all of the papers were chosen by their authors with the same goal in mind: to help those from other supervised learning fields get acquainted with the lay of those authors' lands. Moreover, the instructions to the authors were that they should not try to provide tutorials on their individual fields. (There are many other sources for such tutorials.) Rather they should present current cutting-edge perspectives and work that provide an intuitive understanding of what their field "is all about". =========================================================== The order numbers are 40985 for the hardcover and 40983 for the paperback. The prices are: Paperback 0-201-40983-6 $31.25 Hardcover 0-201-40985-2 $59.25 It is recommended that people order through their home institutions (book stores or libraries) which may have a contract or working relationship with the publisher, Addison-Wesley. Otherwise they can call (800) 447-2226 to order by credit card. Alternatively, they can pay by check by writing to Advanced Book Marketing Addison-Wesley Publishing One Jacob Way Reading, MA 01867, USA.  From michael at imib.rwth-aachen.de Fri Oct 28 04:18:53 1994 From: michael at imib.rwth-aachen.de (Michael Egmont-Petersen #Alwd#) Date: Fri, 28 Oct 1994 09:18:53 +0100 Subject: Special issue of Artificial Intelligence in Medicine: Neurocomputing Message-ID: <9410280818.AA13164@tolkien> ARTIFICIAL INTELLIGENCE IN MEDICINE Special issue: Neural computing in medicine October 1994 Volume 6 Number 5 Editorial: Neural computing in medicine N. Ezquerra, A. Pazos Papers: On the quality of neural net classifiers M. Egmont-Petersen, J.L. Talmon, J. Brender and P. McNair A neural model of cortical map reorganization following a focal lesion S.L. Armentrout, J.A. Reggia and M. Weinrich Identifying the measurement noise in glaucomatous testing: An artificial neural network approach X. Liu, G. Cheng and J.X. Wu On using feedforward neural networks for clinical diagnostic tasks G. Dorffner and G. Porenta Removing the assumption of conditional independence from Bayesian decision models by using artificial neural networks: Some practical techniques and a case study Y.-C. Wu and D.H. Gustafson ----- SUBSCRIPTION Elsevier Science B.V. Journal Department P.O. Box 211 1000 AE Amsterdam The Netherlands Tel. +31-20-5803642 Fax +31-20-5803598 -----  From john at dcs.rhbnc.ac.uk Fri Oct 28 13:08:09 1994 From: john at dcs.rhbnc.ac.uk (john@dcs.rhbnc.ac.uk) Date: Fri, 28 Oct 94 17:08:09 +0000 Subject: EuroCOLT Proceedings Message-ID: <22863.9410281708@platon.cs.rhbnc.ac.uk> The proceedings of the first European Conference on Computational Learning Theory (EuroCOLT'93) are now available for purchase. The contents are attached. The purchasing details are as follows: The price of the book is 60.00. Address where to send orders: CWO Department, Oxford University Press, Saxon Way West, Corby, Northants. NN18 9ES. Phone: 0536 454-534 Fax: 0536 746-337 Many thanks John Shawe-Taylor ------------- @inproceedings{m-oclnn-93 , author = "W. Maass" , title = "On the Complexity of Learning on Neural Nets" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "1--17" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{fp-sndclt-93 , author = "M. Frazier and L. Pitt" , title = "Some New Directions in Computational Learning Theory" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "19--32" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{v-nmcf-93 , author = "L. Valiant" , title = "A Neuroidal Model for Cognitive Functions" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "2" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{kmu-lrle-93 , author = "J. Kivinen and H. Mannila and E. Ukkonen" , title = "Learning Rules with Local Exceptions" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "35--46" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{gm-olsdpnc-93 , author = "M. Golea and M. Marchand" , title = "On Learning Simple Deterministic and Probabilistic Neural Concepts" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "47--60" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{f-lucp-93 , author = "P. Fischer" , title = "Learning Unions of Convex Polygons" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "61--67" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{h-otsnnsn-93 , author = "T. Heged{\"u}s" , title = "On Training Simple Neural Networks and Small-weight Neurons" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "69--82" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{s-bnelf-93 , author = "H.U. Simon" , title = "Bounds on the Number of Examples needed for Learning Functions" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "83--94" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{ast-vgfcas-93 , author = "M. Anthony and J. Shawe-Taylor" , title = "Valid Generalisation of Functions from Close Approximations on a Sample" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "94--108" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{kw-uepco-93 , author = "J. Kivinen and M. Warmuth" , title = "Using Experts for Predicting Continuous Outcomes" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "109--120" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{pr-rdnffpl-93 , author = "K. Pillaipakkamnatt and V. Raghavan" , title = "Read-twice DNF Formulas are Properly Learnable" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "121--132" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{afhmh-tenasl-93 , author = "F. Ameur and P. Fischer and K.U. H{\"o}ffgen and F. Meyer auf der Heide" , title = "Trial and Error: a New Approach to Space-bounded Learning" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "133--144" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{ap-ukldlt-93 , author = "S. Anoulova and S. P{\"o}lt" , title = "Using Kullback-Leibler Divergence in Learning Theory" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "145--156" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{s-llrwmlp-93 , author = "A. Saoudi" , title = "Learning Local and Recognizable $\omega$-languages and Monadic Logic Programs" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "157--169" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{wsz-cpl-93 , author = "R. Wiehagen and C.H. Smith and T. Zeugmann" , title = "Classification of Predicates and Languages" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "171--181" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{w-tnnlpu-93 , author = "H. Wiklicky" , title = "The Neural Network Loading Problem is Undecidable" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "183--192" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{g-opeq-93 , author = "R. Gavald{\`a}" , title = "On the Power of Equivalence Queries" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "193--203" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{cbfhw-opcs-93 , author = "N. Cesa-Bianchi and Y. Freund and D. P. Helmbold and M. Warmuth" , title = "On-line Prediction and Conversion Strategies" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "205--216" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{y-lnsrsrfp-93 , author = "K. Yamanishi" , title = "Learning Non-parametric Smooth Rules by Stochastic Rules with Finite Partitioning" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "217--227" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" } @inproceedings{p-issbpab-93 , author = "S. P{\"o}lt" , title = "Improved Sample Size Bounds for PAB-decisions" , booktitle = "Computational Learning Theory: Eurocolt '93" , year = "1994" , pages = "229--239" , isbn = "0 19 853492 2" , publisher = "Oxford University Press" , address = "Oxford" , series = "The Institute of Mathematics and its Applications Conference Series" , volume = "New Series Number 53" }  From koza at CS.Stanford.EDU Fri Oct 28 23:43:48 1994 From: koza at CS.Stanford.EDU (John Koza) Date: Fri, 28 Oct 94 20:43:48 PDT Subject: Architecture-Altering Operations in Genetic Programming Message-ID: <CMM.0.90.4.783402228.koza@Sunburn.Stanford.EDU> Technical report available on new architecture-altering operations for evolving the architecture of a multi-part program in genetic programming. Title: Architecture-Altering Operations for Evolving the Architecture of a Multi- Part Program in Genetic Programming. John R. Koza Computer Science Department Stanford University October 21, 1994 P Report No. STAN-CS-TR-94-1528 ABSTRACT Previous work described a way to evolutionarily select the architecture of a multi-part computer program from among preexisting alternatives in the population while concurrently solving a problem during a run of genetic programming. This report describes six new architecture- altering operations that provide a way to evolve the architecture of a multi-part program in the sense of actually changing the architecture of programs dynamically during the run. The new architecture-altering operations are motivated by the naturally occurring operation of gene duplication as described in Susumu Ohno's provocative 1970 book Evolution by Means of Gene Duplication as well as the naturally occurring operation of gene deletion. The six new architecture-altering operations are branch duplication, argument duplication, branch creation, argument creation, branch deletion and argument deletion. A connection is made between genetic programming and other techniques of automated problem solving by interpreting the architecture-altering operations as providing an automated way to specialize and generalize programs. The report demonstrates that a hierarchical architecture can be evolved to solve an illustrative symbolic regression problem using the architecture-altering operations. Future work will study the amount of additional computational effort required to employ the architecture- altering operations. INTRODUCTION (SECTION 1 OF TECH REPORT) In nature, crossover ordinarily recombines a part of the chromosome of one parent with a corresponding (homologous) part of the second parent's chromosome. However, in certain very rare and unpredictable instances, this recombination does not occur in the usual way. A gene duplication is an illegitimate recombination event that results in the duplication of a lengthy subsequence of a chromosome. Susumu Ohno's seminal 1970 book Evolution by Gene Duplication proposed the provocative thesis that the creation of new proteins (and hence new structures and behaviors in living things) begins with a gene duplication and that gene duplication is "the major force of evolution." This report describes six new architecture-altering genetic operations for genetic programming that are suggested by the mechanism of gene duplication (and the complementary mechanism of gene deletion) in chromosome strings. This report proposes that these new operations be added to the toolkit of genetic programming when the user desires to evolve the architecture of a multi-part program containing automatically defined functions (ADFs) during the run of genetic programming. The six new architecture-altering operations can be viewed from five perspectives. First, the new architecture-altering operations provide a new way to solve the problem of determining the architecture of the overall program in the context of genetic programming with automatically defined functions. Second, the new architecture-altering operations provide an automatic implementation of the ability to specialize and generalize in the context of automated problem-solving. Third, the new architecture-altering operations automatically and dynamically change the representation of the problem while simultaneously and automatically solving the problem. Fourth, the new architecture-altering operations automatically and dynamically decompose problems into subproblems and then automatically solve the overall problem by assembling the solutions of the subproblems into a solution of the overall problem. Fifth, the new architecture-altering operations automatically and dynamically discover useful subspaces (usually of lower dimensionality than that of the overall problem) and then automatically assemble a solution of the overall problem from solutions applicable to the individual subspaces. Section 2 of this report describes the naturally occurring processes of gene duplication and gene deletion. Section 3 describes analogs of gene duplication and gene deletion that have appeared in previous work with character strings in the field of genetic algorithms and other evolutionary algorithms. Section 4.1 provides basic background information on genetic programming and automatically defined functions. Section 4.2 lists the steps for executing genetic programming. Section 4.3 describes the five existing methods for determining the architecture of multi- part programs in the context of genetic programming with automatically defined functions. Section 4.4 describes different methods of creating the initial random population when these new operations are being used. Section 4.5 describes structure-preserving crossover with point typing in an architecturally diverse population. Section 5 describes the six new architecture-altering operations. Section 6 illustrates the architecture-altering operations using a gedanken experiment involving the problem of rotating the tires on an automobile. Section 7 contains some examples of actual runs of genetic programming with the new architecture-altering operations. Section 8 is the conclusion and section 9 outlines future work. METHODS OF OBTAINING REPORT: You can get this 60-page technical report by anonymous FTP or you can order a hard copy directly from Stanford for $l0. HARD COPY ORDERS: $l0 should be sent to: Publications Office Computer Science Department Margaret Jacks Hall Stanford University Stanford, CA 94305-2140 USA FTP INSTRUCTIONS: FTP to elib.stanford.edu. The files containing the report are in the /pub/reports/cs/tr/94/1528 directory. Detailed FTP instructions: ftp elib.stanford.edu user anonymous cd /pub/reports/cs/tr/94/1528 Then, get all the files from that directory. Type the following three commands. prompt binary mget * This will transfer all of the files to your machine.  From piuri at elet.polimi.it Sat Oct 29 09:52:48 1994 From: piuri at elet.polimi.it (Vincenzo Piuri) Date: Sat, 29 Oct 1994 13:52:48 GMT Subject: MWSCAS95 call for papers Message-ID: <9410291352.AA17235@ipmel2.elet.polimi.it> ======================================================================= 38TH MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS Hotel Gloria, Rio de Janeiro, Brazil August 13-16, 1995 General Chairman: Luiz P. Caloba - caloba at coe.ufrj.br Program Chairman: Paulo S. R. Diniz - diniz at coe.ufrj.br ======================================================================= CALL FOR PAPER FOR THE SPECIAL SESSION ON NEURAL MODELLING AND CONTROL The 1995 Midwest Symposium on Circuits and Systems will be organized by the Federal University of Rio de Janeiro and co-sponsored by the IEEE Circuits and Systems Society. The Symposium will be devoted to the theory, design and applications of circuits and systems. In particular, papers are solicited on all aspects of the neural technologies concerning system identification, modelling, and control. Papers are welcome both on theory and on applications. Authors interested in the Special Session are requested to submit a two-page abstract to the Session Organizer, by January 13, 1995; title, author's name(s), address(es), affiliation(s), e-mail address(es), fax and telephone number(s) must be included. Submission by e-mail or fax is welcome. Preliminary acceptance/rejection will be mailed by March 1, 1995; final acceptance will be mailed by May 15, 1995. Prof. Vincenzo Piuri Organizer of the Special Session on Neural Modelling and Control Department of Electronics and Information Politecnico di Milano, Italy piazza L. da Vinci 32 I-20133 Milano, Italy phone +39-2-2399-3623 fax +39-2-2399-3411 email piuri at elet.polimi.it =======================================================================  From harnad at Princeton.EDU Sat Oct 29 09:49:19 1994 From: harnad at Princeton.EDU (Stevan Harnad) Date: Sat, 29 Oct 94 09:49:19 EDT Subject: Neuropsychology/Consciousness: BBS Call for Commentators Message-ID: <9410291349.AA00634@clarity.Princeton.EDU> Below is the abstract of a forthcoming target article by: Jeffrey Gray on: CONSCIOUSNESS AND NEUROPSYCOLOGY This article has been accepted for publication in Behavioral and Brain Sciences (BBS), an international, interdisciplinary journal providing Open Peer Commentary on important and controversial current research in the biobehavioral and cognitive sciences. Commentators must be current BBS Associates or nominated by a current BBS Associate. To be considered as a commentator for this article, to suggest other appropriate commentators, or for information about how to become a BBS Associate, please send email to: harnad at clarity.princeton.edu or harnad at pucc.bitnet or write to: BBS, 20 Nassau Street, #240, Princeton NJ 08542 [tel: 609-921-7771] To help us put together a balanced list of commentators, please give some indication of the aspects of the topic on which you would bring your areas of expertise to bear if you were selected as a commentator. An electronic draft of the full text is available for inspection by anonymous ftp (or gopher or world-wide-web) according to the instructions that follow after the abstract. ____________________________________________________________________ THE CONTENTS OF CONSCIOUSNESS: A NEUROPSYCHOLOGICAL CONJECTURE Jeffrey A. Gray Department of Psychology Institute of Psychiatry De Crespigny Park, Denmark Hill London SE5 8AF, England jgray at ux.psych.lon.ac.uk ABSTRACT: Drawing on previous models of anxiety, intermediate memory, the positive symptoms of schizophrenia and goal-directed behaviour, a neuropsychological hypothesis is proposed for the generation of the contents of consciousness. It is suggested that these correspond to the outputs of a comparator that, on a moment-by-moment basis, compares the current state of the organism's perceptual world with a predicted state. An outline is given of the information-processing functions of the comparator system and of the neural systems which mediate them. The hypothesis appears to be able to account for a number of key features of the contents of consciousness. However, it is argued that neither this nor any existing comparable hypothesis is yet able to explain why the brain should generate conscious experience of any kind at all. KEYWORDS: Conciousness, contents of consciousness, comparator, septohippocampal system, anxiety, schizophrenia. -------------------------------------------------------------- To help you decide whether you would be an appropriate commentator for this article, an electronic draft is retrievable by anonymous ftp from princeton.edu according to the instructions below (the filename is bbs.gray). Please do not prepare a commentary on this draft. Just let us know, after having inspected it, what relevant expertise you feel you would bring to bear on what aspect of the article. ------------------------------------------------------------- To retrieve a file by ftp from an Internet site, type either: ftp princeton.edu or ftp 128.112.128.1 When you are asked for your login, type: anonymous Enter password as queried (your password is your actual userid: yourlogin at yourhost.whatever.whatever - be sure to include the "@") cd /pub/harnad/BBS To show the available files, type: ls Next, retrieve the file you want with (for example): get bbs.mealet When you have the file(s) you want, type: quit These files can also be retrieved using gopher, archie, veronica, etc. URL: ftp//ftp.princeton.edu/pub/harnad/BBS/bbs.gray http://www.princeton.edu/~harnad/bbs.html gopher://gopher.princeton.edu/11/.libraries/.pujournals ---------- Where the above procedure is not available there are two fileservers: ftpmail at decwrl.dec.com and bitftp at pucc.bitnet that will do the transfer for you. To one or the other of them, send the following one line message: help for instructions (which will be similar to the above, but will be in the form of a series of lines in an email message that ftpmail or bitftp will then execute for you). JANET users without ftp can instead utilise the file transfer facilities at sites uk.ac.ft-relay or uk.ac.nsf.sun. Full details are available on request. -------------------------------------------------------------  From kolen-j at cis.ohio-state.edu Sat Oct 29 16:27:51 1994 From: kolen-j at cis.ohio-state.edu (john kolen) Date: Sat, 29 Oct 1994 16:27:51 -0400 Subject: Thesis anouncement, again Message-ID: <199410292027.QAA18730@squirt.cis.ohio-state.edu> This is a reposting of my original announcement. The orignal announcement had the wrong ftp address. (One of the benefits of being at OSU is that I can cd to the neuroprose archive, hence, I don't bother with ftp addresses.) In addition to the address change, I have added a long abstract to the the announcement. As still is the case, those with old PS printers and previewers will have difficulties (see warning below.) Ftp-site: ftp.cis.ohio-state.edu ^^^^ (archive still works, too) Ftp-directory: pub/neuroprose/Thesis/kolen.thesis.ps.Z PrintedPages: 191 EXPLORING THE COMPUTATIONAL CAPABILITIES OF RECURRENT NEURAL NETWORKS DISSERTATION By John F. Kolen Prof. Jordan B. Pollack, Adviser Short Abstract While many researchers have successfully organized neural networks into structures displaying universal computational capability, most have ignored the more daunting endeavor of identifying ongoing computation, or information processing, as it occurs. My thesis addresses this problem as it relates to the understanding of the information processing capabilities of recurrent neural networks. I have isolated three important facets of recurrent neural networks that contribute to their computational power: internal dynamics, input modulation, and output generation. Theories of dynamical systems and iterated function systems have proven crucial in developing an understanding of these facets. With respect to my original question of identifying ongoing computation, the evidence suggests that the any observed computational powers of neural networks arise not from the network itself, but our application of it as a symbol processing device. If we consider recurrent neural networks as the a cognitive e. coli, this dissertation is a step toward understanding the nature cognition and intelligence. Long Abstract This dissertation addresses the issues surrounding the computational capabilities of recurrent neural networks. My results apply not only to simple recurrent networks, Jordan networks, and higher order recurrent networks, but many other networks implemented as input-parameterized iterated functions. The following reasons have driven my efforts to understand their computational capabilities. First, the question of knowledge content arises whenever we attempt to understand how a given network produces its behavior. Second, knowing the range of what is computable by a recurrent network can guide us in their intelligent application. Finally, this knowledge may also help us to develop new training strategies which bias the network towards desirable solutions. While we already know that recurrent networks can perform complex computation by simulating machine tapes and stacks, one problem still remains: someone designed each universal-computing network by hand. We know the function decomposition because the designer can tell us what they intended each part to do. Unfortunately, weak learning methods, like back-propagation, that discover operable network weights cannot explain the internal functionality of final product. Thus, we are forced to externally determine the recurrent network's computation process by observing its structure and behavior. To this end, I identify three facets of recurrent networks that directly affect their emergent computational descriptions: system dynamics, input modulation of state dynamics, and output generation. System dynamics, the mapping of current state to next state, have been traditionally considered the source of complex behavior. Input modulation occurs as a finite set of input vectors and induces beiterated function system-like behavior from the recurrent network. This selection creates state space representations for information processing states which display recursive structure. I show that the mechanism producing discrete outputs has dramatic effects on the resulting system complexity by imposing information processing regularities in the output stream strong enough to manipulate both complexion (number of states) and generative class of the observed computation. As for new training methods, I outline a method of network training called entrainment learning which offers a novel explanation of the transmission of grammatical behavior structures between agents. ********* WARNING *********** This document contains Level 2 PostScript commands that will not work on Level 1 printers (i.e. old LaserWriters and old versions of ghostview).  From ruppin at cs.UMD.EDU Sun Oct 30 13:48:30 1994 From: ruppin at cs.UMD.EDU (eytan ruppin) Date: Sun, 30 Oct 1994 13:48:30 -0500 Subject: No subject Message-ID: <199410301848.NAA26552@rapid.cs.UMD.EDU> Workshop Announcement NEURAL MODELING OF COGNITIVE AND BRAIN DISORDERS Sponsors: Institute for Advanced Computer Studies, University of Maryland Dept. of Neurology, University of Maryland School of Medicine Center for the Neural Basis of Cognition, Carnegie Mellon and Pittsburgh Universities Center for Neural and Cognitive Studies, University of Maryland (Additional sponsors are currently being sought.) A workshop on Neural Modeling of Cognitive and Brain Disorders will be held June 8 - 10, 1995 at the University of Maryland, College Park, just outside of Washington, DC. The focus of this meeting will be on the lesioning of neural network models to study disorders in neurology, neuropsychology and psychiatry, such as Alzheimer's disease, amnesia, aphasia, depression, acquired dyslexia, epilepsy, schizophrenia, and stroke. These models attempt to explain how specific pathological neuroanatomical and neurophysiological changes can result in various clinical manifestations, and they investigate the functional organization of the symptoms that result from specific brain pathologies. The prospects and challenges of modeling brain disorders have recently attracted an increasing number of researchers with different backgrounds, such as physicians, psychologists and computer scientists. This, together with the inherent multidisciplinary nature of brain modeling research, has motivated the goals of this workshop: To evaluate current achievements critically, to discuss the possibilities for further advancement, and to identify brain disorders and cognitive phenomena that may be studied computationally. To examine methodological modeling issues, such as limitations of the networks currently employed, and the required computational properties of future models. To make the material presented at the workshop available to the wider audience of researchers interested in studying neural models of brain disorders. A Proceedings of abstracts will be compiled, and the production of a book of contributed chapters based on the workshop is under consideration. CALL FOR ABSTRACTS Individuals wishing to present a poster related to any aspect of the workshop's themes should submit an abstract describing the nature of their presentation. The single page submission should include title, author(s), contact information (address and email/fax), and abstract. One inch margins and a typesize of at least 10 points should be used. Abstracts will be reviewed by the Program Committee; those accepted will be published in the workshop proceedings. Six copies of the camera-ready abstract should be mailed TO ARRIVE by February 1, 1995 to James A. Reggia, Dept. of Computer Science, A.V. Williams Bldg., University of Maryland, College Park, MD 20742 USA. PRELIMINARY PROGRAM Each workshop session will be focused on specific disorders and composed of four invited presentations followed by a critical commentary and a general discussion. Thursday, June 8 ---------------- 8:30 AM: Welcome and Overview 9:00 AM: Alzheimer's Disease and Memory Disorders Chair and Discussant: Steven Small (University of Pittsburgh) James McClelland (Carnegie Mellon University) - Complementary learning systems in hippocampus and neocortex Michael Hasselmo (Harvard University) - Runway synaptic modification models of cortex: implications for the pathology of Alzheimer's disease David Horn (Tel-Aviv University, Israel) - Synaptic deletion and compensation in Alzheimer's disease: a computational study Martha Farah (University of Pennsylvania) - Computational models of semantic memory impairment Noon: Lunch Break 1:30 PM: Epilepsy Chair and Discussant: Michael Rogawski (National Institutes of Health) Roger Traub (IBM Watson) - Modeling synchronized neuronal oscillations in epilepsy John Rinzel (National Institutes of Health) - Reduced, cell-based models for epilepsy Bill Lytton (University of Wisconsin) - Modeling epilepsy and seizure spread Mayank Mehta (University of Arizona) - A neural network model for kindling of focal epilepsy 4:30 PM: Reception Friday, June 9 -------------- 9:00 AM: Stroke and Functional Effects of Focal Lesions Chair and Discussant: Barry Gordon (Johns Hopkins University) John Pearson (David Sarnoff Research Center) - The effects of focal deafferentation on cortical reorganization James Reggia (University of Maryland) - Lesioning cortical maps: a model of stroke in sensory and motor cortices Manfred Spitzer (University of Heidelberg, Germany) - A neural network model of phantom limbs Eytan Ruppin (Tel-Aviv University, Israel) - The functional effects of focal lesions in associative memory networks Noon: Lunch Break 1:30 PM: Aphasia and Acquired Dyslexia Chair and Discussant: Rita Berndt (University of Maryland) Gary Dell (University of Illinois) - Lesioning a connectionist model of sentence processing to simulate naming errors in aphasia Max Coltheart (Macquarie University, Australia) - Simulation of acquired dyslexia by DRC, a computational realization of a dual-route reading model Karalyn Patterson (MRC Appl. Psych. Unit, Cambridge) - Connections and dis- connections: acquired surface dyslexia in a connectionist model of reading David Plaut (Carnegie Mellon University) - Connectionist modeling of the breakdown and recovery of reading via meaning 4:30 PM: Dinner Break 7:00 PM: POSTER SESSION Saturday, June 10 ----------------- 9:00 AM: Schizophrenia, Frontal and Affective Disorders Chair and Discussant: Jonathan Cohen (Carnegie Mellon University & University of Pittsburgh) Ralph Hoffman (Yale University) - Modeling schizophrenic positive symptoms using attractor and backpropagation networks David Servan-Schreiber (University of Pittsburgh) - Modeling cognitive deficits in schizophrenia: neuromodulation of prefrontal cortex Dan Levine (University of Texas at Arlington) - Functional deficits of frontal lobe lesions Joanne Luciano and Michael Cohen (Boston University) - A neural model of major depression Noon: Lunch Break 1:30 PM: Commentary: James McClelland (Carnegie Mellon University) 2:00 PM: General Discussion A brief commentary will be followed by a general discussion of where we are and where we want to go from here. Among the issues to be considered are the successes and limitations of current models of neurological, neuropsychological and psychiatric disorders. What common methods have been identified? How can models of this sort be validated, and at what level of detail should they be formulated? What topics seem amenable to future neural modeling, and what are barriers to further progress in this field? Is there sufficient interest in contributing to a book on the subject of this workshop? Finally, feedback on the workshop format and content will be solicited, and the interest and usefulness of holding similar workshops or more formal conferences in the future will be assessed. 4:30 PM: Adjournment ------ Travel Fellowships: ------------------ Funding has been requested for a few fellowships to offset travel cost of students, postdocs, and/or residents. Further details will be forthcoming. Program Committee: ----------------- Rita Berndt (Maryland), Barry Gordon (Johns Hopkins), Michael Hasselmo (Harvard), Ralph Hoffman (Yale), Joanne Luciano (Boston), Jay McClelland (Carnegie Mellon), Al Nigrin (American), David Plaut (Carnegie Mellon), James Reggia (Maryland), Eytan Ruppin (Tel-Aviv), and Stanley Tuhrim (Mount Sinai). Registration or Further Information: ----------------------------------- To receive registration materials (distributed most likely in January/February), please send your name, address, email address, phone number and fax number to Johanna Weinstein UMIACS A. V. Williams Bldg. University of Maryland College Park, MD 20742 USA Tel.: (301)405-6722 Fax: (301)314-9658 email: johanna at umiacs.umd.edu Further questions about conference administration, hotel reservations, etc. should also be directed to Ms. Weinstein. For questions about the workshop technical/scientific content or absract submissions, please contact Eytan Ruppin Dept. of Computer Science A.V. Williams Bldg. University of Maryland College Park MD 20742 USA Tel.: (301) 405-2709 Fax: (301)405-6707 email: ruppin at cs.umd.edu  From ifsa95 at dep.fem.unicamp.br Mon Oct 31 09:10:29 1994 From: ifsa95 at dep.fem.unicamp.br (IFSA95) Date: Mon, 31 Oct 94 10:10:29 EDT Subject: No subject Message-ID: <9410311210.AA00496@jaguar> MESSAGE TO AUTHORS FROM IFSA'95 ORGANIZERS _____________________________________________________________________________ We have been contacted by authors asking if the papers acceptance deadline refers to the postage date or to the arrival of the papers in the secretariat. We would like to inform that we have decided to accept papers for review that are either posted before november 1st, or that arrive in our hands until november 11th. _____________________________________________________________________________ * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * IFSA '95 * * * * VI International Fuzzy Systems Association World Congress * * Sao Paulo-Brazil * * July 22-28, 1995 * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * The full version of IFSA'95 2nd call-for-papers is * * stored in the file * * * * calif.doc * * * * which can be obtained by anonynmous FTP from: * * * * spock.dep.fem.unicamp.br * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * The latest information about IFSA'95 (including the * * call-for-papers) can be obtained via WWW on URL: * * * * http://www.inpe.br/meetings/IFSA95/home * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * For further information please contact: * * * * ifsa95 at dep.fem.unicamp.br * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *  From bishopc at helios.aston.ac.uk Mon Oct 31 03:34:37 1994 From: bishopc at helios.aston.ac.uk (bishopc) Date: Mon, 31 Oct 1994 08:34:37 +0000 Subject: NIPS Workshop Message-ID: <8857.9410310834@sun.aston.ac.uk> ------------------------------------------------------------------- NIPS*94 Workshop: DOING IT BACKWARDS: ------------------- NEURAL NETWORKS AND THE SOLUTION OF INVERSE PROBLEMS ---------------------------------------------------- Organizer: Chris M Bishop (Aston University) Intended Audience ----------------- Researchers and practitioners in neural computing interested in inverse problems. Introduction ------------ Many of the tasks for which neural networks are commonly used correspond to the solution of an `inverse' problem. Such tasks are characterized by the existence of a well-defined, deterministic `forward' problem which might, for instance, correspond to causality in a physical system. By contrast the inverse problem may be ill-posed, and may exhibit multiple solutions. A wide range of different approaches have been developed to tackle inverse problems, and one of the main goals of the workshop is to contrast the way in which they address the underlying technical issues, and to identify key areas for future research. Ample time will be allowed for discussions. Morning Session --------------- 7:30 "Welcome and overview" Chris Bishop (Aston) 7:35 "From ill-posed problems to all neural networks and beyond through regularization" Tomaso Poggio / Federico Girosi (MIT) 7:55 "Solving inverse problems using an EM approach to density estimation" Zoubin Ghahramani (MIT) 8:15 "Density estimation with periodic variables" Chris Bishop (Aston) 8:35 "Doing it forwards, undoing it backwards: high-dimensional compression and expansion" Russell Beale (University of Birmingham) 8:55 "Inversion of feed-forward networks by gradient descent" Alexander Linden (Berkeley) 9.15 Discussion Afternoon Session ----------------- 4:30 "An iterative inverse of a talking machine" Sid Fels (Toronto) 4:50 "Diagnostic problem solving" Sungzoon Cho (Postech, S Korea) 5:10 "Multiple Models in Inverse Filtering of the Vocal Tract" M Niranjan (Cambridge) 5:30 "Goal directed model inversion" Silvano Colombano (NASA Ames) 5:50 "Predicting element concentrations in the SSME exhaust plume" Kevin Whitaker (University of Alabama) 6:10 Discussion