From gaudiano at cns.bu.edu Mon Aug 2 17:32:33 1999 From: gaudiano at cns.bu.edu (Paolo Gaudiano) Date: Mon, 2 Aug 1999 17:32:33 -0400 Subject: Update: Posters now accepted at UI-CANCS conference Message-ID: <199908022132.RAA27988@cochlea.bu.edu> This announcement is being sent to multiple lists. We are sorry if you receive multiple copies. IMPORTANT UPDATE: Now accepting contributed posters First USA-Italy Conference on Applied Neural and Cognitive Sciences UI-CANCS'99 Boston, October 3-6, 1999 In response to popular demand we are expanding UI-CANCS'99 to include a poster session for contributed work. Submissions should focus on applications of neural and cognitive sciences. Applications describing collaborations between industry and research are especially relevant. Please send a title and abstract (up to one page) with the name and affiliation of all authors to info at usa-italy.org. Abstracts will be reviewed promptly and, if appropriate, will be accepted on a first-come basis as long as there is room available. The posters will be available for viewing all day on October 4 and 5. For additional information please visit http://www.usa-italy.org or send e-mail to info at usa-italy.org. From char-ci0 at wpmail.paisley.ac.uk Tue Aug 3 12:48:55 1999 From: char-ci0 at wpmail.paisley.ac.uk (Darryl Charles) Date: Tue, 03 Aug 1999 16:48:55 +0000 Subject: Ph.D. studentship Message-ID: PhD studentship available in the Applied Computational Intelligence Research Group at the University of Paisley, Scotland. A bursary (approx. =A35500) is available for the successful applicant who will examine the positive effects of additive noise in unsupervised artificial neural networks, particularly networks that have been developed here at Paisley. Visual data is of particular interest in this research. Applicants should be suitably qualified and preferably have neural network and/or vision related experience/interest. Supervisory team will consist of Dr. Darryl Charles (Director of studies) and Prof. Colin Fyfe. Send a CV to char-ci0 at paisley.ac.uk Darryl Charles CIS dept. University of Paisley Paisley Scotland PA1 2BE From marwan at ee.usyd.edu.au Wed Aug 4 08:06:39 1999 From: marwan at ee.usyd.edu.au (Marwan Jabri) Date: Wed, 4 Aug 1999 22:06:39 +1000 Subject: Faculty Positions Message-ID: <002201bede71$ceabf840$cb184e81@majhome.sedal.usyd.edu.au> POSITION: Lecturer/Senior Lecturer in Computer Engineering (2 positions) DEPARTMENT: School of Electrical and Information Engineering, The University of Sydney TYPE: Academic APPOINTMENT: continuing REF NO: A20/01 Closing Date: 26/08/99 The School of Electrical and Information Engineering is expanding its teaching and research programs in the area of computer and software engineering following the introduction of degree programs in these areas, and invites applications for two continuing positions. Applicants should be able to contribute to teaching of advanced courses in these areas and research in one or more of the Schools major research areas. The existing academic staff in related areas have research interests in low power integrated circuits, artificial intelligence and neuromorphic engineering, biomedical systems, automatic control, communications systems and image processing. Within computer engineering, particular areas of interest include neuromorphic engineering, reconfigurable computing; integrated circuits and systems; hardware/software co-design; advanced digital engineering; and parrallel and distributed processing. The development of software engineering is occurring in collaboration with the Department of Computer Science. Applicants at the Senior Lecturer level should have a PhD in Electrical or Computer Engineering. Applicants at the Lecturer level should have or should be expecting soon to be awarded a PhD. A PhD in computer science with a substantial engineering background may be considered. The position requires commitment to leadership in research and teaching. Candidates must have a high level of research outcomes and would have the capability to teach undergraduate classes and supervise research students. Undergraduate teaching experience and industrial applications experience are desirable. The position is full-time continuing, subject to the completion of a satisfactory probation period for new appointees. Membership of a University approved superannuation scheme is a condition of employment for new appointees. For further information contact Professor M A Jabri on (+61-2) 9351 2240, fax: (+61-2) 9351 7209, email: marwan at sedal.usyd.edu.au, or the Head of Department, Professor D J Hill on (+61-2) 9351 4647, fax (+61-2) 9351 3847, e-mail: davidh at ee.usyd.edu.au. (Level of appointment and responsibility will be commensurate with qualifications and experience) Academic staff at the School of Electrical and Information Engineering is currently entitled to receive a market loading (up to a maximum of 33.33% of base salary). The market loading scheme is expected to continue until the end of 1999 when it will be reviewed. WE ARE AN EQUAL OPPORTUNITY EMPLOYER AND WE OFFER A SMOKE FREE WORKPLACE Availability: Internal & External Salary: Lecturer $48,440 -$57,523 p.a. Senior Lecturer $59,338 - $68,422 p.a. ---------------------------------------------------------------------------- ---- Application Information No smoking in the workplace is University policy. Equal employment opportunity is University policy. Other than in exceptional circumstances all vacancies within the University are advertised in the Bulletin Board and on the World Wide Web. Intending applicants are encouraged to seek further information from the contact given before submitting a formal application. Academic positions: Applications (five copies for levels A-D and ten copies for level E), which should quote the reference no, address the selection criteria, and include a CV, a list of publications, the names, addresses, e-mail, fax and phone number of confidential referees (three for levels A-D and five for level E), should be forwarded to: General Staff positions: Applications, which should quote the reference no, address the selection criteria, and include a CV, the names, addresses, e-mail, fax and phone number of two confidential referees, should be forwarded to: The Personnel Officer, College of Sciences and Technology, Carslaw Building, (F07), The University of Sydney, NSW, 2006 The University is a non-smoking workplace and is committed to the policies and principles of equal employment opportunity and cultural diversity. The University reserves the right not to proceed with any appointment for financial or other reasons. ---------------------------------------------------------------------------- ---- Authorised Publication of Personnel Services ~ Last updated 4/8/99 -------------- Marwan Jabri, Professor Director, Computer & Software Engineering Programs School of Electrical & Information Engineering The University of Sydney NSW 2006, Australia Tel: (+61-2) 9351-2240, Fax:(+61-2) 9351-7209 Email: marwan at sedal.usyd.edu.au, http://www.sedal.usyd.edu.au/~marwan/ From oreilly at grey.colorado.edu Fri Aug 6 01:29:50 1999 From: oreilly at grey.colorado.edu (Randall C. O'Reilly) Date: Thu, 5 Aug 1999 23:29:50 -0600 Subject: SENIOR and/or JUNIOR COGNITIVE NEUROSCIENCE POSITIONS Message-ID: <199908060529.XAA28247@grey.colorado.edu> The following is our advertisement for faculty positions available at the University of Colorado, Boulder. One of the directions we are interested in pursuing is to enhance our strength in computational modeling as a cognitive neuroscience methodology, so modelers are encouraged to apply. Feel free to contact me for further information. - Randy SENIOR and/or JUNIOR COGNITIVE NEUROSCIENCE POSITIONS Department of Psychology, University of Colorado, Boulder The Department of Psychology, University of Colorado, Boulder, invites applications for two tenure-track positions in Cognitive Psychology, beginning August 2000. At least one of these positions will be in Cognitive Neuroscience. One appointment will be at the rank of Associate or Full Professor, and the second is likely to be at the rank of Assistant Professor. Applicants should send a Curriculum Vitae, a statement of research and teaching interests, example research papers, and at least three letters of recommendation to: Ms. Deborah Aguiar, Administrative Assistant-Cognitive Psychology Search, Department of Psychology, University of Colorado, Boulder, CO 80309-0345. Inquiries should be addressed to Dr. Lyle E. Bourne, Jr., Chair--Cognitive Search, (303) 492-4210, lbourne at psych.colorado.edu. Applications will be reviewed as they are completed and until the position is filled. To insure full consideration, however, the application should be complete by November 1, 1999. The University of Colorado at Boulder is committed to diversity and equality in education and employment. +-----------------------------------------------------------------------------+ | Dr. Randall C. O'Reilly | | | Assistant Professor | | | Department of Psychology | Phone: (303) 492-0054 | | University of Colorado Boulder | Fax: (303) 492-2967 | | Muenzinger D251C | Home: (303) 448-1810 | | Campus Box 345 | email: oreilly at psych.colorado.edu | | Boulder, CO 80309-0345 | www: http://psych.colorado.edu/~oreilly | +-----------------------------------------------------------------------------+ From renner at ecst.csuchico.edu Fri Aug 6 16:15:44 1999 From: renner at ecst.csuchico.edu (renner@ecst.csuchico.edu) Date: Fri, 6 Aug 1999 13:15:44 -0700 (PDT) Subject: PhD Thesis on nnet ensembles Message-ID: <19990806201544.13443.qmail@pitbull.ecst.csuchico.edu> Dear Connectionists, The following dissertation is now available on-line from http://www.ecst.csuchico.edu/~renner or directly from http://www.ecst.csuchico.edu/~renner/Diss/ Improving Generalization of Constructive Neural Networks Using Ensembles by R.S. Renner ABSTRACT Ensemble networks have been receiving considerable attention within the last few years. Most existing models are created with linear networks. Ensembles of linear networks have demonstrated improved performance over individual networks, but linear models have limited capacity problems. Ensembles of more complex well-trained networks offer a promising alternative. Unfortunately, the computational expense involved in training large numbers of well-trained networks may be prohibitive. An ensemble of non-linear feed-forward neural networks generated by a constructive algorithm is presented. The ensemble method presented exhibits better generalization than linear ensembles, and shows promise toward a reduction in time-complexity over well-trained ensembles. The problems addressed in this research are: generalization of non-linear data, time-complexity, structural dilemmas, model creation, and model combination. The Neural Network Ensemble Simulator (NNES) is also introduced as a simulation tool for managing ensemble experiments. NNES provides routines for ensemble creation, selection, combination, and analysis. Keywords: ensembles, constructive neural networks, generalization, Cascade-Correlation, Surrogate Bayes Combination Method (SBCM), Neural Network Ensemble Simulator (NNES). NOTE: Files in directory are pdf format. Please notify me via email if you are unable to read this format. Table of Contents is available in 'preface.pdf' __ __ __ __ __ __ __ __ __ __ __ __ __ / // // // // // // // // // // // // / \ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \ R.S. Renner, Ph.D. Assistant Professor, College of ECT California State Univeristy - Chico Department of Computer Science Chico, CA 95929-0410 (530)898-5419 fax: 5995 www.ecst.csuchico.edu/~renner renner at ecst.csuchico.edu / // // // // // // // // // // // // / \ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \ From X.Yao at cs.bham.ac.uk Mon Aug 9 05:53:43 1999 From: X.Yao at cs.bham.ac.uk (Xin Yao) Date: Mon, 9 Aug 1999 10:53:43 +0100 (BST) Subject: Combinations of EC and NNs Message-ID: <199908090953.KAA04028@edward.cs.bham.ac.uk> The First IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks Co-sponsored by IEEE Neural Network Council The Center for Excellence in Evolutionary Computation May 11-12, 2000 The Gunter Hotel, San Antonio, TX, USA Symposium URL: http://www.cs.bham.ac.uk/~xin/ecnn2000 CALL FOR PAPERS The recent increasing interest in the synergy between evolutionary computation and neural networks provides an impetus for a symposium dedicated to furthering our understanding of this synergy and the potential utility of hybridizing evolutionary and neural techniques. The First IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks will offer a forum that focuses specifically on the hybridization of evolutionary and neural computation. In particular, papers are solicited in the areas of + evolutionary training of neural networks, + evolutionary design of network topologies, + evolution of learning (weight updating) rules, + evolving solutions to inverse neural network problems, + the performance of alternative variation operators in designing neural networks, + comparisons between evolutionary and other training methods, + evolving developmental rules for neural network design, and + the use of coevolution in optimizing neural networks for pattern recognition, gaming, or other applications. Other topics that combine evolutionary and neural computation are also welcome. Submitted papers should represent unpublished, original work. PAPER SUBMISSION Send three (3) copies of your manuscript to Xin Yao School of Computer Science The University of Birmingham Edgbaston, Birmingham B15 2TT U.K. Email: x.yao at cs.bham.ac.uk All three hardcopies should be printed on 8.5 by 11 inch or A4 paper using 11 point Times. Allow at least one inch (25mm) margins on all borders. A paper must include a title, an abstract, and the body and references. It must also include the names and addresses of all authors, their email addresses, and their telephone/fax numbers. The length of submitted papers must be no more than 15 single-spaced, single-column pages, including all figures, tables, and references. Shorter papers are encouraged. In addition to hardcopies, please send a postscript file of your paper (gzipped if possible) to facilitate electronic reviewing to the following email address: x.yao at cs.bham.ac.uk. Please check the symposium's web site http://www.cs.bham.ac.uk/~xin/ecnn2000 for more details as they become available. SUBMISSION DEADLINE: DECEMBER 1, 1999 General Chair: Xin Yao Programme Chair: D.B. Fogel PROGRAMME COMMITTEE: P.J. Angeline K. Chellapilla J.-C. Chen S.-B. Cho D.B. Fogel G.W. Greenwood L. Guan N. Kasabov S. Lucas N. Murshed V. Nissen M. Rizki R. Salomon G. Yen B.-T. Zhang Q. Zhao The Symposium follows The 9th IEEE International Conference on Fuzzy Systems (FUZZ-IEEE2000), Hilton Palacio del Rio, San Antonio, TX, USA, 7-10 May 1999. (URL: http://fuzzieee2000.cs.tamu.edu/) From juergen at idsia.ch Mon Aug 9 04:56:52 1999 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Mon, 9 Aug 1999 10:56:52 +0200 Subject: exploration Message-ID: <199908090856.KAA02848@ruebe.idsia.ch> Two papers on exploration are now available in digital form: ----------------------------------------------------------------------- Efficient Model-Based Exploration Marco Wiering & Juergen Schmidhuber, IDSIA, Lugano, Switzerland In R. Pfeiffer, B. Blumberg, J. Meyer, S. W. Wilson, eds., From Animals to Animats 5: Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior, p. 223-228, MIT Press, 1998. ftp://ftp.idsia.ch/pub/juergen/sab98explore.ps.gz Model-Based Reinforcement Learning (MBRL) can greatly profit from using world models for estimating the consequences of selecting particular actions: an animat can construct such a model from its experiences and use it for computing rewarding behavior. We study the problem of collecting useful experiences through exploration in stochastic environments. Towards this end we use MBRL to maximize exploration rewards (in addition to environmental rewards) for visits of states that promise information gain. We also combine MBRL and the Interval Estimation algorithm (Kaelbling, 1993). Experimental results demonstrate the advantages of our approaches. ----------------------------------------------------------------------- Artificial Curiosity Based on Discovering Novel Algorithmic Predictability Through Coevolution Juergen Schmidhuber, IDSIA, Lugano, Switzerland In P. Angeline, Z. Michalewicz, M. Schoenauer, X. Yao, Z. Zalzala, eds., Congress on Evolutionary Computation, p. 1612-1618, IEEE Press, Piscataway, NJ, 1999. (based on TR IDSIA-35-97, 1997) ftp://ftp.idsia.ch/pub/juergen/cec99.ps.gz How to explore a spatio-temporal domain? By predicting and learning from success/failure what's predictable and what's not. I study a "curious" embedded agent that differs from previous explorers in the sense that it can limit its predictions to fairly arbitrary, computable aspects of event sequences and thus can explicitly ignore almost arbitrary unpredictable, random aspects. It constructs initially random algorithms mapping event sequences to abstract internal representations (IRs). It also constructs algorithms predicting IRs from IRs computed earlier. It wants to learn novel algorithms creating IRs useful for correct IR predictions, without wasting time on those learned before. This is achieved by a co-evolutionary scheme involving two competing modules COLLECTIVELY designing SINGLE algorithms to be executed. The modules can bet on the outcome of IR predictions computed by the algorithms they have agreed upon. If their opinions differ then the system checks who's right, punishes the loser (the surprised one), and rewards the winner. A reinforcement learning algorithm forces each module to maximixe reward. This motivates both modules to lure the other into agreeing upon algorithms involving predictions that surprise it. Since each module essentially can put in its veto against algorithms it does not consider profitable, the system is motivated to focus on those computable aspects of the environment where both modules still have confident but different opinions. Once both share the same opinion on a particular issue (via the loser's learning process, e.g., the winner is simply copied onto the loser), the winner loses a source of reward - an incentive to shift the focus of interest onto novel, yet unknown algorithms. Simulations include an example where surprise-generation of this kind helps to speed up external reward. ----------------------------------------------------------------------- Several additional postscripts now available in http://www.idsia.ch/~juergen/onlinepub.html Juergen Schmidhuber www.idsia.ch From koza at smi.stanford.edu Tue Aug 10 12:26:29 1999 From: koza at smi.stanford.edu (John Koza) Date: Tue, 10 Aug 1999 09:26:29 -0700 Subject: 1000-Pentium beowulf computer for genetic programming research Message-ID: <005d01bee34d$19a0ad20$050010ac@mendel> Hello: We have just posted photos of our recently installed 1,000-Pentium Beowulf-style cluster computer system consisting of a server and 1,000 Pentium II 350-MHz processors. It is constructed entirely from "Commodity Off The Shelf" (COTS) components. This new machine is operated by Genetic Programming Inc., a privately funded research group aimed at producing human-competitive results using genetic programming. We are currently working in the areas of automated synthesis of analog electrical circuits and controllers, problems in computational molecular biology, various other problems involving cellular automata, multi-agent systems, operations research, and other areas of design, and using genetic programming as an automated "invention machine" for creating new and useful patentable inventions. There are now a number of instances where genetic programming has automatically produced a computer program that is competitive with human performance. Competitiveness with human performance can be established in a variety of ways. For example, genetic programming may produce a result that is slightly better, equal, or slightly worse than that produced by a succession of human researchers working on an well-defined problem over a period of years. Or, genetic programming may produce a result that is equivalent to an invention that was patented in the past or that is patentable today as a new invention. The fact that genetic programming can evolve entities that are competitive with human-produced results suggests that genetic programming may possibly be used as an "invention machine" to create new and useful patentable inventions. Each of the 1,000 processors of our parallel computer system has a Pentium II 350-MHz processor. Each processor uses 64 megabytes of RAM (so that the system as a whole has 64 gigabytes of RAM). The 1000 Pentium II processors reside on 500 dual-CPU ATX motherboards and each motherboard is housed in a standard mini-tower box. Each mini-tower box contains 128 megabytes of RAM, a 100 megabit-per-second Ethernet NIC, and a standard 300W power switching power supply. There is no hard disk, video monitor, keyboard, floppy disk drive, or other input-output device associated with any of the 1,000 processors. The processors run the Linux operating system (Red Hat Linux 6.0). The communication between processors and between the server and the processors is by means of 100 megabit-per-second Ethernet. Each group 40 processors (20 boxes) is connected to one 24-port 100 megabit-per-second Ethernet hub. There are 25 hubs in the system. Each hub is connected on its uplink to one of two 100 megabit-per-second 16-port Ethernet switches. The two switches are connected to each other and to the server. The server computer is also a dual Pentium II 350-MHz processor. The server has 256 MB of RAM. It runs on the Linux operating system (Red Hat Linux 6.0 from VA Linux Research). The server contains a 14 GB hard disk, a video display monitor, a floppy disk drive, a CD ROM drive, and a keyboard. The system is booted using a DHCP message from the server to the 1,000 processors. We used the Beoboot software from Rembo Technology SaRL, Geneva, Switzerland. The 500 boxes directly access the server's file system using NFS. Additional information about the machine and genetic programming (and job opportunities) can be found at http://www.genetic-programming.com John R. Koza Consulting Professor Stanford Medical Informatics Department of Medicine Medical School Office Building Stanford University Stanford, California 94305 Consulting Professor Department of Electrical Engineering School of Engineering Stanford University Phone: 650-941-0336 Fax: 650-941-9430 E-Mail: koza at stanford.edu E-Mail: koza at genetic-programming.com For information about GECCO-2000 (GP-2000) conference in Las Vegas on July 8 -12, 2000, visit: http://www.genetic-algorithm.org/GECCO2000/gecco2000mainpage.htm From chiru at csa.iisc.ernet.in Wed Aug 11 03:30:51 1999 From: chiru at csa.iisc.ernet.in (Chiranjib Bhattacharya) Date: Wed, 11 Aug 1999 13:00:51 +0530 (IST) Subject: TR Announcement Message-ID: Technical Report Announcement: Platt's SMO algorithm is an excellent algorithm for designing SVMs because it is very efficient. It has become popular since it is also extremely simple to implement. Our recent research has shown that there is an important source of inefficiency in the SMO algorithm that has to do with choosing the threshold parameter, b. We remove this inefficiency by carefully modifying SMO while keeping the main ideas of SMO in tact. The modified algorithms run much faster than the original SMO. Details are given in the Technical Report mentioned below. A gzipped post- script file containing the report can be downloaded from: http://guppy.mpe.nus.edu.sg/~mpessk/ Send any comments to: mpessk at guppy.mpe.nus.edu.sg ---------------------------------------------------------------------------- Improvements to Platt's SMO Algorithm for SVM Classifier Design Technical Report CD-99-14 S.S. Keerthi, S.K. Shevade, C. Bhattacharyya & K.R.K. Murthy Abstract This paper points out an important source of confusion and inefficiency in Platt's Sequential Minimal Optimization (SMO) algorithm that is caused by the use of a single threshold value. Using clues from the KKT conditions for the dual problem, two threshold parameters are employed to derive modifications of SMO. These modified algorithms perform significantly faster than the original SMO on all benchmark datasets tried. ---------------------------------------------------------------------------- From Paul.Keller at pnl.gov Wed Aug 11 10:26:05 1999 From: Paul.Keller at pnl.gov (Keller, Paul E) Date: Wed, 11 Aug 1999 07:26:05 -0700 Subject: CFP: Applications and Science of Computational Intelligence III Message-ID: <9623E2E264D9D211B5FA0008C7A4B5CC3F9355@pnlmse2.pnl.gov> * * * C A L L F O R P A P E R S * * * Applications and Science of Computational Intelligence III http://www.spie.org/web/meetings/calls/or00/confs/OR16.html Applications and Science of Computational Intelligence III (OR16) On-site Proceedings. Abstracts for this conference are due by 13 September 1999. Manuscripts are due by 31 January 2000. Conference Chairs: Kevin L. Priddy, Battelle Memorial Institute; Paul E. Keller, Battelle/Pacific Northwest National Lab.; David B. Fogel, Natural Selection, Inc. Program Committee: Shun-ichi Amari, RIKEN (Japan); Stanley C. Ahalt, The Ohio State Univ.; Peter J. Angeline, Natural Selection, Inc.; Gianfranco Basti, Pontifical Lateran Univ. (Italy); James C. Bezdek, Univ. of West Florida; Bruno Bosacchi, Lucent Technologies/Bell Labs.; David Brown, Food and Drug Administration; David P. Casasent, Carnegie Mellon Univ.; Nick DeClaris, Univ. of Maryland; Joydeep Ghosh, Univ. of Texas/Austin; Charles W. Glover, Oak Ridge National Lab.; Clifford G. Lau, Office of Naval Research; Karl Mathia, Equipe Technologies, Inc.; Antonio L. Perrone, Univ. of Rome (Italy); Steven K. Rogers, Qualia Computing, Inc.; Stephan Rudolph, Univ. Stuttgart (Germany); Bradley C. Wallet, Naval Surface Warfare Ctr. The focus of this conference is on real-world applications of computational intelligence (neural networks, fuzzy logic, and/or evolutionary computation) and on recent theoretical developments (principal components analysis/independent components analysis, etc.) applicable to current problem domains. The goal is to provide a forum for interaction between researchers and industrial/ government agencies with information processing requirements. Sessions containing papers from the different disciplines in related applications will be the highlight of this conference. Papers that investigate advantages/disadvantages of computational intelligence solutions in specific real-world applications will be presented as oral and posters. The poster session will contain papers by the session chairs to allow interaction by attendees in small groups. Papers that clearly state existing problems in information processing that could potentially be solved by computational intelligence techniques will also be considered. Sessions will concentrate on: comparative performance in applications of target recognition, object recognition, speech processing, speaker identification, co-channel processing, signal processing in realistic environments, robotics, process control, and image processing demonstrations of properties and limitations of existing or new computational intelligence techniques as shown by or related to an application environments for development of computational intelligence solutions hardware implementation technologies that are either general purpose or application specific knowledge acquisition and representation physiologically motivated information processing and representation independent component analyses (ICA) generalizing principal component analyses (PCA) innovative applications of computational intelligence to solve real-world problems with Receiver Operation Characteristics (ROC). Special Instructions to Authors Oral Presentations are scheduled for Monday and Tuesday with poster sessions scheduled Tuesday evening. On the occasion of NASA's 40th Anniversary, Wednesday will be devoted to joint sessions on Remote Sensing using both Computational Intelligence and Wavelet Analysis. Honorary co-chairs: William J. Campbell, Milton Halem, NASA Goddard Space Flight Ctr. Due to the limited number of oral sessions, we cannot accommodate requests for oral-only presentations without prior approval of the Conference Chair. Any program committee member can guarantee acceptance of brief oral overviews followed by poster interactive presentations. Poster submission will be encouraged with the popup short talks and the Best Poster Award. There will be no differentiation between poster and oral papers in the proceedings. Please indicate your preference for oral or poster sessions. Abstract Submissions Information On-Site Abstract Due Date: 13 September 1999 On-Site Manuscript Due Date: 31 January 2000 To receive a complete Call for Papers via postal mail, or to request an Advance Technical Program for any of these conferences (when available), please contact SPIE Phone: +1 360/676-3290. Fax: +1 360/647-1445. E-mail: OR at spie.org For further information please contact: http://www.spie.org Paul E. Keller, PhD Conference Co-Chair Paul.Keller at pnl.gov From sirosh at hnc.com Wed Aug 11 23:19:39 1999 From: sirosh at hnc.com (Sirosh, Joseph) Date: Wed, 11 Aug 1999 20:19:39 -0700 Subject: Neural Networks/Machine Learning Position at HNC Software Inc Message-ID: <72A838A51366D211B3B30008C7F4D36301773BE5@pchnc.hnc.com> > POSITION: Staff Scientist/Sr. Staff Scientist > BUSINESS UNIT: HNC Advanced Technology Solutions > LOCATION: San Diego, CA > NUMBER: A003SDW1 > > Duties/Job Description: > Develop innovative solutions to a wide variety of technical problems using > various data mining techniques and statistics. Projects may include > fundamental research (e.g. new data mining technologies, multimedia and > web mining, mining temporal data) and applications to business problems in > the financial, internet, telecommunications, retail or insurance > industries. Opportunity to contribute to the evaluation of new, > externally-developed technologies and explore new business models. > > Required Qualifications (Experience/Skills): > MS/Ph.D. in Computer Science, Engineering, Statistics, Math, or related > field. Broad experience applying data mining techniques, neural networks, > statistics, pattern recognition, nonlinear optimization and/or genetic > algorithms to real-world data. Ability to work independently and research > innovative solutions to challenging technical problems. Programming > experience in C/C++ and Unix. Familiarity with statistical packages and > computer software systems such as SAS, SPLUS, Matlab, Java, Tcl/Tk. Good > oral and written communications skills, both in terms of interacting with > customers and with co-workers. > > Preferred Qualifications: > Ph.D. with established research expertise in one or more of the above > areas. Significant experience solving business problems involving retail, > financial, or internet data mining. Substantial expertise with large > business data sets. Familiarity with products in any or all of HNC's > business units. Good Unix scripting and rapid prototyping skill. > > Careers at HNC Software Inc: > Headquartered in San Diego, California, HNC Software Inc. (Nasdaq: HNCS) > is the world's leading provider of Predictive Software Solutions for > service industries, including financial, retail, insurance, Internet, and > telecommunications. It is HNC's employment philosophy to create a dynamic > work environment that allows each employee to feel challenged and > experience personal growth that maximizes each person's potential. HNC > also offers a comprehensive array of employee benefits including stock > options, employee stock purchase plan, competitive health benefits, 401(k) > plans and tuition support for continuing education. > > Apply Online: http://www.hnc.com/careers/index.html > By Email: hnc at webhire.com > By Fax: (800) 438-0957 > By Mail: > HNC Software Inc. > c/o Resume Processing Center > P.O. Box 828 > Burlington, MA 01803 > > Please reference job number: A003SDW1 > > > > From jose at psychology.rutgers.edu Fri Aug 13 07:27:51 1999 From: jose at psychology.rutgers.edu (stephen jose hanson) Date: Fri, 13 Aug 1999 07:27:51 -0400 Subject: COGNITIVE SCIENCE/COGNITIVE NEUROSCIENCE FELLOWSHIPS --RUTGERS-Newark Message-ID: <37B40137.97E12464@kreizler.rutgers.edu> PSYCHOLOGY GRADUATE PROGRAM- Newark Campus GRADUATE RESEARCH FELLOWSHIPS. Fall 99 & Fall 00. The graduate program in COGNITIVE SCIENCE and COGNITIVE NEUROSCIENCE seeks students for FALL 99 & FALL 00. Interested applicants from Psychology, Computer Science or Cognitive Science undergrad programs are encouraged to apply. These fellowships are competitive and provide comprehensive training in computation, neuro-imaging and cognitive science/perception research. Please send enquiries and applications to Professor S. J. Hanson, Chair, Department of Psychology Rutgers University, Newark, NJ 07102. Please make an Email enquiry to gradpgm at tractatus.rutgers.edu also please see our web page for more information on the graduate faculty and program http://www.psych.rutgers.edu From jfgf at eng.cam.ac.uk Fri Aug 13 10:04:34 1999 From: jfgf at eng.cam.ac.uk (J.F. Gomes De Freitas) Date: Fri, 13 Aug 1999 15:04:34 +0100 (BST) Subject: MCMC and SMC model selection Message-ID: Dear colleagues, The following papers and Matlab software on MCMC algorithms for batch and on-line learning are now available from my website: http://svr-www.eng.cam.ac.uk/~jfgf/publications.html http://svr-www.eng.cam.ac.uk/~jfgf/software.html KEYWORDS: Reversible jump MCMC, model selection, sequential Monte Carlo, particle filters, AIC, MDL, simulated annealing, robust priors, geometric convergence proofs. PAPER 1: Sequential Bayesian Estimation and Model Selection Applied to Neural Networks. Technical report CUED/F-INFENG/TR 341, Cambridge University Department of Engineering, May 1999. PAPER 2: Robust Full Bayesian Learning for Neural Networks. Technical report CUED/F-INFENG/TR 343, Cambridge University Department of Engineering, May 1999. The abstracts follow: Paper 1: ======= In this paper, we address the complex problem of sequential Bayesian estimation and model selection. This problem does not usually admit any type of closed-form analytical solutions and, as a result, one has to resort to numerical methods. We propose here an original sequential simulation-based strategy to perform the necessary computations. It combines sequential importance sampling, a selection procedure and reversible jump MCMC moves. We demonstrate the effectiveness of the method by applying it to radial basis function networks. The approach can be easily extended to other interesting on-line model selection problems. Paper 2: ======= In this paper, we propose a hierarchical full Bayesian model for neural networks. This model treats the model dimension (number of neurons), model parameters, regularisation parameters and noise parameters as random variables that need to be estimated. We develop a reversible jump Markov chain Monte Carlo (MCMC) method to perform the necessary computations. We find that the results obtained using this method are not only better than the ones reported previously, but also appear to be robust with respect to the prior specification. In addition, we propose a novel and computationally efficient reversible jump MCMC simulated annealing algorithm to optimise neural networks. This algorithm enables us to maximise the joint posterior distribution of the network parameters and the number of basis function. It performs a global search in the joint space of the parameters and number of parameters, thereby surmounting the problem of local minima. We show that by calibrating the full hierarchical Bayesian prior, we can obtain the classical AIC, BIC and MDL model selection criteria within a penalised likelihood framework. Finally, we present a geometric convergence theorem for the algorithm with homogeneous transition kernel and a convergence theorem for the reversible jump MCMC simulated annealing method. I hope some of you find them interesting and, as always, feedback of all sorts is most welcome. Nando _______________________________________________________________________________ JFG de Freitas (Nando) Speech, Vision and Robotics Group Information Engineering Cambridge University CB2 1PZ England http://svr-www.eng.cam.ac.uk/~jfgf Tel (01223) 302323 (H) (01223) 332754 (W) _______________________________________________________________________________ From POCASIP at aol.com Fri Aug 13 22:09:48 1999 From: POCASIP at aol.com (POCASIP@aol.com) Date: Fri, 13 Aug 1999 22:09:48 EDT Subject: R&D position in DSP & NeuroControl in California Message-ID: The Advanced Signal and Image Processing Laboratory of Intelligent Optical Systems Inc. (IOS) is looking for a candidate who has expertise and experience in the following two areas: 1. Digital Signal Processing and 2. NeuroControl (Nonlinear Adaptive Control) + Knowledge of electronic (CMOS) design, and programming fluency in C++ and Java are important assets. + Experience in solving real-world problems in a wide variety of applications is a definite plus. The activities of the Advanced Signal and Image Processing Laboratory include system control, hazardous waste analysis, skin injury diagnosis, silicon wafer inspection, food quality control, and target recognition, using neural computation implementations in software and hardware. IOS is a rapidly growing dynamic high-tech R&D company with a focus on commercializing optical sensors and advanced information processing. Ii employs about 35 people, including 13 scientists from a variety of backgrounds. We are located in Torrance, California, which is a pleasant seaside town with a high standard of living and year-round perfect weather. Please send your application including curriculum vitae, and three references, in ASCII only, by e-mail to POCASIP at aol.com E. Fiesler From X.Yao at cs.bham.ac.uk Mon Aug 16 07:32:24 1999 From: X.Yao at cs.bham.ac.uk (Xin Yao) Date: Mon, 16 Aug 1999 12:32:24 +0100 (BST) Subject: PhD scholarship/studentship in EC+NNs Message-ID: The following PhD scholarship/studentship is available from the School of Computer Science, the University of Birmingham, UK. For more information about this EPSRC CASE Studentship, please go to http://www.cs.bham.ac.uk/~pjh/prospectus/research/xy_bt.html For more information about the School, please go to http://www.cs.bham.ac.uk ---------------------------------------------------------------------------- EPSRC CASE Studentship on Combinations Between Evolutionary Computation and Neural Networks supported by BT Applications are invited for a studentship starting in Autumn 1999 under the supervision of Professor Xin Yao and in co-operation with BT Laboratories' Future Technologies Group. Applications are restricted to students with a " relevant connection" to the European Union. For the successful candidate, the scholarship will pay their tuition fees and (if they have a "relevant connection" with the United Kingdom) a tax-free maintenance allowance of between GBP10,620 and GBP12,130 per year, depending on age. More details: http://www.cs.bham.ac.uk/~pjh/prospectus/research/xy_bt.html Enquiries: Prof Xin Yao (x.yao at cs.bham.ac.uk) Dr Peter Hancox (P.J.Hancox at bham.ac.uk) ---------------------------------------------------------------------------- From motoda at ar.sanken.osaka-u.ac.jp Tue Aug 17 20:46:41 1999 From: motoda at ar.sanken.osaka-u.ac.jp (Hiroshi Motoda) Date: Wed, 18 Aug 1999 09:46:41 +0900 Subject: Last CFP: Special Issue of INSTANCE SELECTION for DMKD Journal Message-ID: <19990818004641.AAA21208@[127.0.0.1]> Call for Papers - INSTANCE SELECTION A Special Issue of the Data Mining and Knowledge Discovery Journal http://www.comp.nus.edu.sg/~liuh/dmkd.html Due date: 18 Sept 1999, electronic submission INTRODUCTION Knowledge discovery and data mining (KDD) is growing rapidly as computer technologies advance. However, no matter how powerful computers are now or will be in the future, KDD researchers and practitioners must consider how to manage ever-growing data which is, ironically, due to the extensive use of computers and ease of data collection with computers. Many different approaches have been used to address the data explosion issue. Algorithm scale-up is one and data reduction is another. Instance, example, or tuple selection is about algorithms that select or search for a representative portion of data that can fulfill a KDD task as if the whole data is used. Instance selection is directly related to data reduction and becomes increasingly important in many KDD applications due to the need for processing efficiency and/or storage efficiency. One of the major means of instance selection is sampling whereby a sample is selected for testing and analysis, and randomness is a key element in the process. Instance selection also covers other methods that require search. Examples can be found in density estimation - finding the representative instances (data points) for each cluster, and boundary hunting - finding the critical instances to form boundaries to differentiate data points of different classes. Other important issues related to instance selection extend to unwanted precision, focusing, concept drifts, noise/outlier removal, data smoothing, etc. OBJECTIVES This special issue on instance selection brings researchers and practitioners together to report new developments and applications, share hard-learned experiences to avoid similar pitfalls, and shed light on the future development of instance selection. Several critical questions are interesting to practitioners in KDD, and practically useful in real-life applications: * What are the existing methods? * Are they the same or just different names coined by researchers in different fields? * Are they application dependent or stand-alone? * Are new methods needed? * If there is no generic selection algorithm, are these algorithms specific to tasks such as classification, clustering, association, parallelization? * Are there common and reusable components in instance selection methods? * How can we reconfigure some components of instance selection for a particular task/application? * What are the new challenging issues of instance selection in the context of KDD? Sensible answers to these questions can greatly advance the field of KDD in handling large databases. This special issue hopes to answer these questions and to provide an easy reference point for further research and development. COVERAGE All aspects of instance selection will be considered: theories, methodologies, algorithms, and applications. Also studied are issues such as costs of selection, the gains and losses due to the selection, how to balance the gains and losses, and when to use what. Researchers and practitioners in KDD-related fields (Statistics, Databases, Machine Learning, etc.) are encouraged to submit their work to this special issue to share and exchange ideas and problems in any forms: survey, research manuscript, experimental comparison, theoretical study, or report on applications. IMPORTANT DATES 18 September, 1999 - Submissions due 15 November, 1999 - Reviews due (mainly peer review and the guest editors will review all the submissions) 22 Janurary, 2000 - Revised papers due 13 February, 2000 - To Editor-in-Chief FORMAT and PAGE LIMIT Each submission should be no more than 25 pages, have a line spacing of 1.5, use no smaller than a 12pt font, and have at least a 1 inch margin on each side. CONTACT INFORMATION Please direct any enquiries to the guest editors: Huan Liu, liuh at comp.nus.edu.sg, National University of Singapore Hiroshi Motoda, motoda at sanken.osaka-u.ac.jp, Osaka University, Japan. Please submit your work electronically (postscript file) to either guest editor. If you have to submit it in hard copy, please discuss it with the guest editors first. INFORMATION about the JOURNAL Data Mining and Knowledge Discovery, Kluwer Academic Publishers. http://www.wkap.nl/journalhome.htm/1384-5810 Editors-in-Chief: Usama Fayyad, Gregory Piatetsky-Shapiro, Heikki Mannila. From rknott at cup.cam.ac.uk Tue Aug 17 06:47:06 1999 From: rknott at cup.cam.ac.uk (Richard Knott) Date: Tue, 17 Aug 1999 10:47:06 +0000 Subject: book announcement: Neural Network Learning Message-ID: Neural Network Learning Theoretical Foundations Martin Anthony London School of Economics and Political Science and Peter Bartlett Australian National University This book describes recent theoretical advances in the study of artificial neural networks. It explores probabilistic models of supervised learning problems, and addresses the key statistical and computational questions. Research on pattern classification with binary-output networks is surveyed, including a discussion of the relevance of the Vapnik-Chervonenkis dimension, and calculating estimates of the dimension for several neural network models. A model of classification by real-output networks is developed, and the usefulness of classification with a 'large margin' is demonstrated. The authors explain the role of scale-sensitive versions of the Vapnik-Chervonenkis dimension in large margin classification, and in real prediction. They also discuss the computational complexity of neural network learning, describing a variety of hardness results, and outlining two efficient constructive learning algorithms. The book is self-contained and is intended to be accessible to researchers and graduate students in computer science, engineering, and mathematics. Contents: 1. Introduction; Part I. Pattern Recognition with Binary-output Neural Networks: 2. The pattern recognition problem; 3. The growth function and VC-dimension; 4. General upper bounds on sample complexity; 5. General lower bounds; 6. The VC-dimension of linear threshold networks; 7. Bounding the VC-dimension using geometric techniques; 8. VC-dimension bounds for neural networks; Part II. Pattern Recognition with Real-output Neural Networks: 9. Classification with real values; 10. Covering numbers and uniform convergence; 11. The pseudo-dimension and fat-shattering dimension; 12. Bounding covering numbers with dimensions; 13. The sample complexity of classification learning; 14. The dimensions of neural networks; 15. Model selection; Part III. Learning Real-Valued Functions: 16. Learning classes of real functions; 17. Uniform convergence results for real function classes; 18. Bounding covering numbers; 19. The sample complexity of learning function classes; 20. Convex classes; 21. Other learning problems; Part IV. Algorithmics: 22. Efficient learning; 23. Learning as optimisation; 24. The Boolean perceptron; 25. Hardness results for feed-forward networks; 26. Constructive learning algorithms for two-layered networks. 1999 228 x 152 mm 416pp 0 521 57353 X Hardback For further information see http://www.cup.cam.ac.uk or http://www.cup.org **************************************************************************** Richard Knott STM Marketing Dept. Cambridge University Press The Edinburgh Building Cambridge CB2 2RU, UK email:rknott at cup.cam.ac.uk tel: ++44 (0)1223 325916 fax: ++44 (0)1223 315052 Web: http://www.cup.cam.ac.uk **************************************************************************** From saadd at aston.ac.uk Wed Aug 18 06:31:27 1999 From: saadd at aston.ac.uk (David Saad) Date: Wed, 18 Aug 1999 11:31:27 +0100 (BST) Subject: Post-doc positions Message-ID: Neural Computing Research Group ------------------------------- School of Engineering and Applied Sciences Aston University, Birmingham, UK TWO POSTDOCTORAL RESEARCH FELLOWSHIPS ------------------------------------- There are two postdoctoral research fellowships at the NCRG available for October 1999 or as soon as possible thereafter. *** Full details at http://www.ncrg.aston.ac.uk/ *** 1. Analysis of Learning in Support Vector Machines ----------------------------------------------- The Neural Computing Research Group at Aston is looking for a highly motivated individual for a 2 year postdoctoral research position in the area of `Analysis of Learning in Support Vector Machines'. The emphasis of the research will be on applying a theoretically well-founded approach based on methods adopted from statistical mechanics to analyse learning in support vector machines. Potential candidates should have strong mathematical and computational skills, with a background in statistical mechanics and support vector machines. Conditions of Service --------------------- Salaries will be up to point 11 on the RA 1A scale, currently 21,815 UK pounds. The salary scale is subject to annual increments. How to Apply ------------ If you wish to be considered for this Fellowship, please send a full CV and publications list, including full details and grades of academic qualifications, together with the names of 3 referees, to: Dr. Manfred Opper Neural Computing Research Group School of Engineering and Applied Sciences Aston University Birmingham B4 7ET, U.K. Tel: 0121 333 4631 Fax: 0121 333 4586 e-mail: opperm at aston.ac.uk e-mail submission of postscript files is welcome. Closing date: 13 September, 1999. =========================================================================== 2. Searching for Patterns in Activity across Multiple Targets ---------------------------------------------------------- This 3 year post aims to develop novel data visualisation and modelling techniques for analysing large biological activity databases. The work will be carried out together with a PhD student funded by Pfizer. Candidates should have strong mathematical and computational skills; a background in biological sciences would be an advantage. Conditions of Service --------------------- Salaries will be up to point 6 on the RA 1A scale, currently 17,570 UK pounds per annum. The salary scale is subject to annual increments. How to Apply ------------ If you wish to be considered for this Fellowship, please send a full CV and publications list, including full details and grades of academic qualifications, together with the names of 3 referees, to: Dr. Ian Nabney Neural Computing Research Group School of Engineering and Applied Sciences Aston University Birmingham B4 7ET, U.K. Tel: 0121 333 4631 Fax: 0121 333 4586 e-mail: i.t.nabney at aston.ac.uk e-mail submission of postscript or pdf files is welcome. Closing date: 13 September, 1999. From rod at dcs.gla.ac.uk Wed Aug 18 11:53:52 1999 From: rod at dcs.gla.ac.uk (Roderick Murray-Smith) Date: Wed, 18 Aug 1999 16:53:52 +0100 Subject: Post-doc position at University of Glasgow Message-ID: <37BAD710.F449D98@dcs.gla.ac.uk> Vacancy: Post-doctoral research assistant at University of Glasgow, Dept. of Computing Science Applications are invited for a Post-doctoral Research Assistantship (RA-1A, salary range 16,286-18,185, depending on experience, up to a maximum of scale point 6) at the University of Glasgow. The appointee will be based in the Department of Computing Science. The work will be directed by R. Murray-Smith (Computing Science), D. M. Titterington (Statistics) and K. J. Hunt (Mechanical Engineering). The appointment is for three years, funded by an EPSRC project "Modern Statistical Approaches to off-equilibrium modelling for nonlinear system control", which starts on 1st January 2000, or as soon as possible thereafter. This project aims to develop modern statistical theory and methodology to improve the performance and interpretability of the multiple-model approach to modelling and control of dynamic systems in engineering. The primary application will be in rehabilitation engineering, where improved modelling and control methods are needed. Candidates should ideally have a strong statistics background. Skills in the following areas will be advantageous: Markov-Chain Monte Carlo methods, Bayesian inference, time series modelling and control. The candidate should also be keen on applying leading-edge techniques to challenging problems, and dealing with the concrete programming work needed to produce successful results. The work will involve algorithm implementation, application and some system development in MATLAB. Further details available at: http://www.dcs.gla.ac.uk/~rod/vacancy.htm http://www.dcs.gla.ac.uk/~rod/MSAFCproject.htm Please send a letter of application and c.v. to Roderick Murray-Smith, rod at dcs.gla.ac.uk (informal enquiries by e-mail welcome) before the end of September 1999. Please note that because of work permit restrictions, non European Union/European Economic Area nationals can only be considered if no suitably qualified EU/EEA national can be found. Postal address: Roderick Murray-Smith, Department of Computing Science, Glasgow University Glasgow G12 8QQ Scotland UK Fax. +44 141 330 4913 http://www.dcs.gla.ac.uk/~rod From allinson at umist.ac.uk Thu Aug 12 13:04:25 1999 From: allinson at umist.ac.uk (Nigel M. Allinson) Date: Thu, 12 Aug 1999 18:04:25 +0100 (BST) Subject: Workshop on Self-Organising Systems Message-ID: Dear All, Emergent Behaviour Computing - one of EPSRCs Emerging Computing networks- is holding its first two-day workshop on "Self-Organising Systems - Future Prospects for Computing" at UMIST, Manchester, England on 28/29 October, 1999 The Workshop covers divers aspects of self-organising systems - both natural and artificial, and aims to present the best of international and UK activity. The overall focus is the current and future application of self-organisation as an alternate paradigm for "intelligent" computation. The Workshop represents an important opportunity for those active, or just interested, in self-organising system research and application to hear about current work, discuss future directions and priorities, and form research contacts. There are several leading overseas speakers, and contributions from the UK community are invited. Details of submission and registration can be obtained from http://images.ee.umist.ac.uk/emergent. -- | Prof. Nigel M. Allinson |______________________________________ Dept. of Electrical Engineering and Electronics UMIST, Manchester, M60 1QD, England ________ | | allinson at umist.ac.uk | Office Phone: (+44) (0) 161 200 4641 | Office Fax: (+44) (0) 161 200 4784 | Home Phone: (+44) (0) 1904 626756 |______________________________________ | http://images.ee.umist.ac.uk |______________________________________ From isahara at crl.go.jp Sat Aug 21 00:10:38 1999 From: isahara at crl.go.jp (Isahara Hitoshi) Date: Sat, 21 Aug 1999 13:10:38 +0900 Subject: NLPRS'99 Workshop -- Natural Language Processing and Neural Networks Message-ID: <9908210410.AA19824@margaux.crl.go.jp> Dear Colleagues, Attached is the call for papers for the NLPRS'99 workshop of Natural Language Processing and Neural Networks. Please help us to distribute this to people who will be interested in. --------------------------------------------------------------------------- Call for Papers NLPRS'99 Workshop Natural Language Processing and Neural Networks Beijing, China, November 5, 1999 http://korterm.kaist.ac.kr/~nlprs99/ The artificial neural networks (ANN) began to be an attract approach to natural language processing (NLP) since several works on parsing were done using ANN techniques in 1985. Since then, with the boom of NLP research based on very large corpora, the ANN, as a powerful parallel and distributed learning/processing machine, attract a more great deal of attention from both the ANN and NLP researchers and have been successfully used in many areas of NLP. This workshop will provide a forum for researchers in both the areas of ANN and NLP who are interested in advancing the state in developing NLP techniques by using ANN approach. Submissions are invited on all NLP topics in the context of using ANN techniques. The workshop review and acceptance will be based on a two-page extended summary (2000 words or less). The summary must be accompanied by paper title and author information including full names, affiliations of all authors and the postal mailing address and email of the corresponding author. Submit by email to qma at crl.go.jp IMPORTANT DATES Summary submission deadline: September 15 Notification of acceptance: September 30 Camera ready papers due: October 15 Inquiries concerning the workshop can be sent to one of the organisers either by email to qma at crl.go.jp or by post to the following address: Dr. Qing Ma Intelligent Processing Section Kansai Advanced Research Center Communications Research Laborotory Ministry of Posts and Telecommunications 588-2, Iwaoka, Nishi-ku, Kobe, 651-2401, Japan --------------------------------------------------------------------------- Dr. Hitoshi Isahara Dr. Qing Ma Intelligent Processing Section Kansai Advanced Research Center Communications Research Laborotory Ministry of Posts and Telecommunications 588-2, Iwaoka, Nishi-ku, Kobe, 651-2401, Japan From kenm at sunrae.sscl.uwo.ca Sat Aug 21 00:37:09 1999 From: kenm at sunrae.sscl.uwo.ca (kenm@sunrae.sscl.uwo.ca) Date: Sat, 21 Aug 1999 00:37:09 -0400 (EDT) Subject: Faculty Position in Cognition at Western Ontario Message-ID: FACULTY POSITION IN COGNITION. The University of Western Ontario, Department of Psychology invites applications for a tenure-track position for a Cognitive Psychologist at the Assistant Professor level. Individuals with research interests in any area of Cognition, including memory, language, computational modelling, concepts and categorization, cognitive development, or animal cognition are invited to apply. Duties will include maintaining an active research program, graduate student supervision, and graduate and undergraduate teaching. The Cognition Program at the University of Western Ontario emphasizes a multidisciplinary approach to research in the cognitive sciences, featuring close ties with researchers in artificial intelligence, linguistics, visual neuroscience, neuroimaging, and evolutionary psychology. Applicants should submit a vita, copies of representative publications and arrange to have three letters of recommendation sent to Dr. Jim Olson, Chair, Department of Psychology, The University of Western Ontario, London, Ontario, Canada N6A 5C2 by January 1, 2000. This position is subject to budgetary approval. The scheduled starting date is July 1, 2000. In accordance with Canadian Immigration requirements, first priority will be given to applicants who are Canadian Citizens or 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 tommi at ai.mit.edu Sat Aug 21 14:45:27 1999 From: tommi at ai.mit.edu (Tommi Jaakkola) Date: Sat, 21 Aug 1999 14:45:27 -0400 Subject: paper available: maximum entropy discrimination Message-ID: The following technical report (MIT AITR-1668) is now available on-line Maximum entropy discrimination Jaakkola T., Meila M., Jebara T. We present a general framework for discriminative estimation based on the maximum entropy principle and its extensions. All calculations involve distributions over structures and/or parameters rather than specific settings and reduce to relative entropy projections. This holds even when the data is not separable within the chosen parametric class, in the context of anomaly detection rather than classification, or when the labels in the training set are uncertain or incomplete. Support vector machines are naturally subsumed under this class and we provide several extensions. We are also able to estimate exactly and efficiently discriminative distributions over tree structures of class-conditional models within this framework. Preliminary experimental results are indicative of the potential in these techniques. http://www.ai.mit.edu/~tommi/publications/maxent.ps.gz 26 pages, about 400KB compressed. Tommi - ====================================================== Tommi Jaakkola MIT Artificial Intelligence Laboratory 545 Technology Square, NE43-735 Cambridge, MA 02139 Tel: (617) 253 0440 Fax: (617) 253 5060 http://www.ai.mit.edu/~tommi ====================================================== From ingber at ingber.com Mon Aug 23 08:21:21 1999 From: ingber at ingber.com (Lester Ingber) Date: Mon, 23 Aug 1999 07:21:21 -0500 Subject: PAPER: ... EEG eigenfunctions of short-term memory Message-ID: <19990823072121.A4177@ingber.com> The draft paper, %A L. Ingber %T Statistical mechanics of neocortical interactions: EEG eigenfunctions of short-term memory %J Behavioral and Brain Sciences %D 2000 %O URL http://www.ingber.com/smni00_eeg_stm.ps.gz is now available at www.ingber.com. Instructions for retrieval are given below. Behavioral and Brain Sciences Commentary on Toward a Quantitative Description of Large-Scale Neo-Cortical Dynamic Function and EEG by Paul Nunez ABSTRACT: This paper focuses on how bottom-up neocortical models can be developed into eigenfunction expansions of probability distributions appropriate to describe short-term memory in the context of scalp EEG. The mathematics of eigenfunctions are similar to the top-down eigenfunctions developed by Nunez, albeit they have different physical manifestations. The bottom-up eigenfunctions are at the local mesocolumnar scale, whereas the top-down eigenfunctions are at the global regional scale. However, as described in several joint papers, our approaches have regions of substantial overlap, and future studies may expand top-down eigenfunctions into the bottom-up eigenfunctions, yielding a model of scalp EEG that is ultimately expressed in terms of columnar states of neocortical processing of attention and short-term memory. Links to informations and utilities for compression/expansion and for viewing and printing PostScript are in http://www.ingber.com/Z_gz_ps_tar_shar.txt Lester ======================================================================== Instructions for Retrieval of Code and Reprints Interactively Via WWW The archive can be accessed via WWW path http://www.ingber.com/ http://www.alumni.caltech.edu/~ingber/ where the last address is a mirror homepage for the full archive. Interactively Via Anonymous FTP Code and reprints can be retrieved via anonymous ftp from ftp.ingber.com. Interactively [brackets signify machine prompts]: [your_machine%] ftp ftp.ingber.com [Name (...):] anonymous [Password:] your_e-mail_address [ftp>] binary [ftp>] ls [ftp>] get file_of_interest [ftp>] quit The 00index file contains an index of the other files. Files have the same WWW and FTP paths under the main / directory; e.g., http://www.ingber.com/MISC.DIR/00index_misc and ftp://ftp.ingber.com/MISC.DIR/00index_misc reference the same file. Electronic Mail If you do not have WWW or FTP access, get the Guide to Offline Internet Access, returned by sending an e-mail to mail-server at rtfm.mit.edu with only the words send usenet/news.answers/internet-services/access-via-email in the body of the message. The guide gives information on using e-mail to access just about all InterNet information and documents. Additional Information Lester Ingber Research (LIR) develops projects in areas of expertise documented in the ingber.com InterNet archive. Limited help assisting people with queries on my codes and papers is available only by electronic mail correspondence. Sorry, I cannot mail out hardcopies of code or papers. Lester ======================================================================== -- Lester Ingber http://www.ingber.com/ http://www.alumni.caltech.edu/~ingber/ From magnus at cs.man.ac.uk Mon Aug 23 10:31:55 1999 From: magnus at cs.man.ac.uk (Magnus Rattray) Date: Mon, 23 Aug 1999 15:31:55 +0100 Subject: Post-doctoral position Message-ID: <37C15B5A.377B33D3@cs.man.ac.uk> Readers of the list may be interested in the following post-doc position, which is jointly offered by the University of Manchester and Rh?ne-Poulenc Rorer. Candidates with experience in neural networks and related machine-learning/visualisation techniques are particularly encouraged to apply. Magnus Rattray, Dept. of Computer Science, University of Manchester, Manchester M13 9PL. -------------------------------------------------------------------- Post-doctoral research associate for gene expression analysis (Rh?ne-Poulenc Rorer and University of Manchester) We are looking for a post-doctoral research associate to work on a 2 year project on the analysis of gene expression patterns from DNA arrays. The work would be done in a collaboration between Rh?ne-Poulenc Rorer and the University of Manchester. The post would provide an ideal opportunity for a mathematically trained scientist to apply their skills to one of the fastest growing and most exciting areas of modern biology. The successful candidate will work primarily at Rh?ne-Poulenc Rorer's site near London and liaise extensively with experimentalists. He/she will be part of a large multidisciplinary team involving biologists and bioinformaticians that is applying and developing state of the art mathematical and computational methods for biologically relevant problems. The ideal candidate would have excellent communication skills, a mathematical background, preferably in areas such as multivariate statistical analysis and pattern recognition, and a strong interest in molecular biology. As an Equal Opportunities Employer, we welcome applications from suitably qualified people from all sections of the community regardless of race, religion, gender or disability. For further details please contact: Dr Burkhard Morgenstern, Rh?ne-Poulenc Rorer Limited, JA3-3 Rainham Road South, Dagenham, Essex. RM10 7XS UK. Email: burkhard.morgenstern at rp-rorer.co.uk From mondada at k-team.com Tue Aug 24 03:20:41 1999 From: mondada at k-team.com (Francesco Mondada) Date: Tue, 24 Aug 1999 09:20:41 +0200 Subject: IKW99 call for participation Message-ID: CALL FOR PARTICIPATION The Heinz Nixdorf Institute, with support from K-Team, organizes the 1ST International KHEPERA Workshop http://ikw99.k-team.com 10th and 11th December 1999, Paderborn, Germany. This workshop aims to bring together researchers from many different fields who utilize the mini-robot Khepera as an experimental platform. The intention is to give a comprehensive overview of the Khepera related work done so far and to provide a forum for scientific exchange. For KHEPERA USERS: The best opportunity to exchange ideas, experience, hardware, software and tips on Khepera. The latest research results and developments will be shown. ******** BRING YOUR KHEPERA ROBOTS for the big clustering demo ******** ******** AND GET A CHANCE TO REPRODUCE ONE OF THEM !!! ******** One of the Khepera robots participating to the demo will be selected and his owner will win a Khepera robot kit offered by K-Team. For NON KHEPERA USERS: The best opportunity to see how to implement real robotics experiences with the standard mobile robot, Khepera, used by more than 350 research groups. Exchange experience and tips with the best Khepera users and developers. This is the only conference where only papers using real robots are accepted! *** PAPERS *** DEMOS *** ROBOTIC NIGHT *** COLLECTIVE ROBOT SHOW *** From d.mareschal at bbk.ac.uk Tue Aug 24 04:47:02 1999 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Tue, 24 Aug 1999 09:47:02 +0100 Subject: models of cognitive development Message-ID: Dear all, The following book chapter may be of interest to readers of this list. It reviews current connectionist modelling efforts with regards to modelling cognitive development. The chapter situates normal and abnormal development within the same framework and illustrates how differences in boundary conditions (constraints) can lead to the emergence of behaviours classified as normal or abnormal. Special attention is paid to models of development in autistic children. Copies of this chapter can be obtained from the following web page: http://www.psyc.bbk.ac.uk/staff/dm.html Self-organization in Normal and Abnormal Cognitive Development Denis Mareschal & Michael S. C. Thomas To appear in: Kalverboer, A. F. & Gramsbergen, A. (2000). Brain and Behaviour in Human Development A source book. Dordecht. Kluwer Academic Publishers. ABSTRACT This chapter discusses self-organization as a motor for cognitive development. Self-organization occurs in systems with many degrees of freedom and is ubiquitous in the brain. The principal means of investigating the role of self-organization in cognitive development is through connectionist computational modeling. Connectionist models are computer models loosely based on neural information processing. We survey a range of models of cognitive development in infants and children and identify the constraints on self-organization that lead to the emergence of target behaviors. A survey of connectionist models of abnormal cognitive development illustrates how deviations in these constraints can lead to the development of abnormal behaviors. Special attention is paid to models of development in autistic children. ================================================= Dr. Denis Mareschal Centre for Brain and Cognitive Development Department of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 171 631-6582/6207 fax +44 171 631-6312 http://www.psyc.bbk.ac.uk/staff/dm.html ================================================= From triesch at cs.rochester.edu Wed Aug 25 09:58:32 1999 From: triesch at cs.rochester.edu (Jochen Triesch) Date: Wed, 25 Aug 1999 09:58:32 -0400 Subject: Thesis on Robotic Gesture Recognition / Sensory Integration available Message-ID: <199908251358.JAA01357@tbird.cs.rochester.edu> Dear connectionists, the following thesis is available from my homepage at http://www.cs.rochester.edu/u/triesch/home.html The thesis was prepared under the supervision of Prof. C. von der Malsburg at the Institut fuer Neuroinformatik, Ruhr-Universitaet Bochum, Germany. http://www.neuroinformatik.ruhr-uni-bochum.de Best Regards, Jochen Triesch Titel: Vision-Based Robotic Gesture Recognition Abstract: Vision in complex environments is a big scientific challenge for two reasons. First, in complex environments it is not possible to segment a scene into the constituent objects on the basis of simple cues. Second, unpredictable changes in the environment must be tolerated. A proper domain for investigating these problems is robotic gesture recognition, since the two problems arise there naturally. Furthermore, gesture recognition holds the promise of making man-machine interaction more natural and intuitive. The principal idea for tackling the first problem is the integration of information stemming from different cues. In the first part of this thesis, methods for tracking human hands, finding fingertips and recognizing hand postures despite complex backgrounds are presented, which owe their robustness to the integration of different complementary cues. The components have been integrated into a user-independent gesture interface implemented on an anthropomorphic robot. The second part is concerned with the adaptive integration of different cues, aimed at addressing the second problem. A model of adaptive sensory integration in the brain is proposed, which relates the psychophysical phenomena of suppression and recalibration of discordant sensory information to a self-organized adaptation employing fast synaptic plasticity mechanisms. Finally, the idea of self-organized adaptation is applied to the tracking of human faces in a scene. To this end, an adaptive tracking scheme is proposed which combines different cues in a "democratic" manner. _______________________________________________________________________________ Jochen Triesch Computer Science Department, University of Rochester RC PO Box 270226, Rochester, NY 14627-0226, USA phone : +1 (716) 275-2957, fax: +1 (716) 461-2018 email : triesch at cs.rochester.edu URL : www.cs.rochester.edu/u/triesch/ _______________________________________________________________________________ From lemm at lorentz.uni-muenster.de Wed Aug 25 05:37:42 1999 From: lemm at lorentz.uni-muenster.de (Joerg_Lemm) Date: Wed, 25 Aug 1999 11:37:42 +0200 (MEST) Subject: New Papers on Bayesian Inverse Quantum Theorie Message-ID: Connectionists at cs.cmu.edu Two papers (MS-TP1-99-6 and MS-TP1-99-10) applying Bayesian methods to inverse problems in quantum mechanics ("empirical learning of potentials") are now available on-line at http://pauli.uni-muenster.de/~lemm/ Joerg ---------------------------------------------------------------------------- 1. A Bayesian Approach to Inverse Quantum Statistics. (MS-TP1-99-6) J. C. Lemm, J. Uhlig, A. Weiguny A nonparametric Bayesian approach is developed to determine quantum potentials from empirical data for quantum systems at finite temperature. The approach combines the likelihood model of quantum mechanics with a priori information on potentials implemented in form of stochastic processes. Its specific advantages are the possibilities to deal with heterogeneous data and to express a priori information explicitly in terms of the potential of interest. A numerical solution in maximum a posteriori approximation is obtained for one--dimensional problems. The results depend strongly on the implemented a priori information. http://xxx.lanl.gov/ps/cond-mat/9907013 or http://pauli.uni-muenster.de/~lemm/papers/iqs.ps.gz 4 pages, 6 figures ---------------------------------------------------------------------------- 2. Hartree-Fock Approximation for Inverse Many-Body Problems. (MS-TP1-99-10) J. C. Lemm, J. Uhlig A new method is presented to reconstruct the potential of a quantum mechanical many--body system from observational data, combining a nonparametric Bayesian approach with a Hartree--Fock approximation. A priori information is implemented as a stochastic process, defined on the space of potentials. The method is computationally feasible and provides a general framework to treat inverse problems for quantum mechanical many--body systems. http://xxx.lanl.gov/ps/nucl-th/9908056 or http://pauli.uni-muenster.de/~lemm/papers/ihf.ps.gz 4 pages, 2 figures ======================================================================== Joerg Lemm Universitaet Muenster Email: lemm at uni-muenster.de Institut fuer Theoretische Physik I Phone: +49(251)83-34922 Wilhelm-Klemm-Str.9 Fax: +49(251)83-36328 D-48149 Muenster, Germany http://pauli.uni-muenster.de/~lemm ======================================================================== From riedml at ira.uka.de Thu Aug 26 18:23:48 1999 From: riedml at ira.uka.de (Martin Riedmiller) Date: Thu, 26 Aug 99 18:23:48 EDT Subject: Job announcement: University of Karlsruhe Message-ID: <"i11s5.ira..851:26.08.99.16.23.51"@ira.uka.de> The following announces a job opportunity for a postdoc or a PhD candidate at the University of Karlsruhe, Germany. Since we are looking for a German speaking applicant, a German version is attached. The University of Karlsruhe, Computer Science Department, is looking for a (post-doc) research assistant in the domain Computability and Complexity Theory of adaptive Systems (Prof.\ W.\ Menzel) The salary is BAT II a. We are looking for a highly qualified mathematician or computer scientist with experience in at least one of the following domains: - Computability and Complexity - Theory of adaptive Systems - Probability Theory Please send your application to Prof. Dr. W. Menzel Institut f\"ur Logik, Komplexit\"at und Deduktionssysteme Universit\"at Karlsruhe 76128 Karlsruhe ------------------------- An der Fakult\"at Informatik, Universit\"at Karlsruhe, ist im Bereich Berechenbarkeit und Komplexit\"at,\\ Theorie adaptiver Systeme\\ (Prof.\ W.\ Menzel) eine Stelle BAT IIa eines wissenschaftlichen Mitarbeiters/einer wissenschaftlichen Mitarbeiterin zu besetzen. Bewerber/Bewerberinnen sollten einen sehr guten Hochschulabschlu\ss{} in Informatik oder in Mathematik mit starkem Informatikbezug besitzen. Vorteilhaft sind vertiefte Kenntnisse in mindestens einem der Gebiete - Berechenbarkeit/Komplexit\"at - Adaptive Systeme, wie etwa neuronale Netze, Support Vector Machines, Evolution\"are Algorithmen - Stochastik. F\"ur promovierte Bewerber/Bewerberinnen besteht die M\"oglichkeit einer Einstellung als wissenschaftliche(r) Assistent(in) (C1). Ansonsten ist die M\"oglichkeit zur Promotion gegeben. Bitte richten Sie Ihre Bewerbung an Prof. Dr. W. Menzel Institut f\"ur Logik, Komplexit\"at und Deduktionssysteme Universit\"at Karlsruhe 76128 Karlsruhe From rn519343 at exchange.UnitedKingdom.NCR.COM Thu Aug 26 07:45:40 1999 From: rn519343 at exchange.UnitedKingdom.NCR.COM (Nakisa, Ramin) Date: Thu, 26 Aug 1999 12:45:40 +0100 Subject: Research Fellowship at NCR Knowledge Lab Message-ID: Reminder: Closing date is in five days. NCR's Knowledge Lab conducts leading-edge research in the areas of data mining, consumer behaviour, emerging technologies and electronic commerce. Research is carried out in close collaboration with a group of banking and academic research partners. Our research interests are wide-ranging and interdisciplinary within the financial services industry. In the area of data mining the Knowledge Lab is investigating the potential of Bayesian statistics applied to very large data sets. The Knowledge Lab invites applicants for a Knowledge Lab Research Fellowship. The fellowship will be awarded to conduct innovative research in developing and applying new machine learning methods to banking problems. Candidates will have a Ph.D. in a numerate discipline and sound knowledge of the theory and computational practice of analysing large data sets. The ability to code fluently in C/C++ is a prerequisite. Fellows are expected to carry out research of an exceptionally high standard and to publish in leading international journals. The fellowship will be for an initial period of one year with the possibility of a permanent position. The fellow will be based in the Knowledge Lab in central London. Salaries will be above the post-doctoral level (which ranges from ?21,293 to ?28,919). The fellowship offers a unique opportunity to both conduct leading-edge research and to also gain experience of the application of research with a world-leading technology company. NCR is the world's leading provider of electronic banking solutions and massively parallel computing for data warehousing. Applicants should send a full CV, indicating their research interests, to Dr. Ramin Nakisa, The Knowledge Lab, NCR Financial Solutions Limited, 206 Marylebone Road, London NW1 6LY. Closing date for applications September 1st, 1999 with a starting date of October 1st, 1999. Informal inquiries may be made by phone to 0171 725 8144 or email ramin.nakisa at unitedkingdom.ncr.com. For more information on the Knowledge Lab, please visit our web site at http://www.knowledgelab.com. From grb at neuralt.com Fri Aug 27 05:06:49 1999 From: grb at neuralt.com (George Bolt) Date: Fri, 27 Aug 1999 10:06:49 +0100 Subject: Neural Scientist Position at Neural Technologies Limited Message-ID: Neural Scientists Wanted! Do you want to apply your neural computing skills to solve real-world problems? Neural Technologies can offer you this opportunity - just some of the areas we work in are: * Telecommunications - fraud, churn, etc. * Finance - credit scoring, risk management, instrument trading, etc. * Marketing - modelling and analysis * Data Analysis and Visualisation - virtual reality Neural Technologies Limited is the leading UK company working in the application and exploitation of neural computing across a wide range of industrial and commercial environments. We are looking not only for high standards of professionalism but also technical innovation second to none. Self confidence, adaptability and communication skills are as important as the technical skills. You will be working within a highly motivated team in our offices in Petersfield, Hampshire. Required skills are: * Well versed in neural network and other advanced algorithm development and their practical application, should have at least 2 years applied knowledge of at least 2 of the following: * MLP, RBF, Decision Trees, etc. * Kohonen/SOM, LVQ, etc. * Rule induction and inferencing, case-based reasoning, etc. * Evolution, GA's, etc. * Optimisation * Experienced using MATLAB * Proven problem solving abilities and system design * Good mathematical background * Able to code in C or C++ within the PC environment Experience of the following would also be an advantage: * Knowledge of conventional statistics * Signal processing techniques (e.g. speech) * Application domains (credit scoring, fraud analysis, telecommunications, banking and finance) All candidates should be working at a practical research level or have extensive industrial experience. A keen view to the commercial realities of working within a small, but fast growing, company is required. Neural Technologies Limited operate a non-smoking policy. Contact: Kirsten Tait Human Resources Executive Neural Technologies Limited Bedford Road PETERSFIELD Hampshire GU32 3QA Phone: +44 (0) 1730 260256 Fax: +44 (0) 1730 260466 Email: kdt at neuralt.com Website: http://www.neuralt.com George Bolt Director of Product Innovation Neural Technologies Cafe Neural: http://www.neuralt.com Tel: +44 (0) 1730 260 256 Fax: +44 (0) 1730 260 466 > ********** NOTE > Any views expressed in this message are those of the individual > sender, > except where the sender specifically states them to be the views of > Neural Technologies Limited > ********** > From John.Carney at cs.tcd.ie Fri Aug 27 09:44:25 1999 From: John.Carney at cs.tcd.ie (John Carney) Date: Fri, 27 Aug 1999 14:44:25 +0100 Subject: TECH-REPORT on bagging neural networks Message-ID: <3.0.1.32.19990827144425.009dbcd0@mail.cs.tcd.ie> Dear Connectionists, The following technical report is available for download from: http://www.cs.tcd.ie/publications/tech-reports/tr-index.99.html REPORT NUMBER: TCD-CS-1999-44 TITLE: Tuning diversity in bagged neural network ensembles ABSTRACT: In this paper we address the issue of how to optimize the generalization performance of bagged neural network ensembles. We investigate how diversity amongst networks in bagged ensembles can signifcantly influence ensemble generalization performance and propose a new early-stopping technique that effectively tunes this diversity so that overall ensemble generalization performance is optimized. Experiments performed on benchmark regression data-sets demonstrate the potential of the technique. KEYWORDS: Bagging, diversity, ensemble, generalization, early-stopping Any comments or feedback welcome. Regards, John Carney. __________________________________________________________ John Carney Department of Computer Science University of Dublin Trinity College Ireland http://www.cs.tcd.ie/John.Carney ______________________________________________________ From harnad at coglit.ecs.soton.ac.uk Fri Aug 27 16:00:52 1999 From: harnad at coglit.ecs.soton.ac.uk (Stevan Harnad) Date: Fri, 27 Aug 1999 21:00:52 +0100 (BST) Subject: Individual Differences in Reasoning: BBS Call for Commentators Message-ID: Below is the abstract of a forthcoming BBS target article INDIVIDUAL DIFFERENCES IN REASONING: IMPLICATIONS FOR THE RATIONALITY DEBATE? by Keith E. Stanovich and Richard F. West *** please see also 5 important announcements about new BBS policies and address change at the bottom of this message) *** 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 BBS Associates or nominated by a 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 reply by EMAIL by September 20th to: bbs at cogsci.soton.ac.uk or write to: Behavioral and Brain Sciences ECS: New Zepler Building University of Southampton Highfield, Southampton SO17 1BJ UNITED KINGDOM http://www.princeton.edu/~harnad/bbs/ http://www.cogsci.soton.ac.uk/bbs/ If you are not a BBS Associate, please send your CV and the name of a BBS Associate (there are currently over 10,000 worldwide) who is familiar with your work. All past BBS authors, referees and commentators are eligible to become BBS Associates. 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 with a WWW browser according to the instructions that follow after the abstract. _____________________________________________________________ INDIVIDUAL DIFFERENCES IN REASONING: IMPLICATIONS FOR THE RATIONALITY DEBATE? Keith E. Stanovich Department of Human Development and Applied Psychology University of Toronto 252 Bloor Street West Toronto, ON Canada M5S 1V6 kstanovich at oise.utoronto.ca Richard F. West School of Psychology James Madison University Harrisonburg, VA 22807 USA westrf at jmu.edu ABSTRACT: Much research in the last two decades has demonstrated that human responses deviate from the performance deemed normative according to various models of decision making and rational judgment (e.g., the basic axioms of utility theory). This gap between the normative and the descriptive can be interpreted as indicating systematic irrationalities in human cognition. However, four alternative interpretations preserve the assumption that human behavior and cognition is largely rational. According to these explanations, the gap is due to (1) performance errors, (2) computational limitations, (3) the wrong norm being applied by the experimenter and (4) a different construal of the task by the subject. In the debates about the viability of these alternative explanations, attention has been focused too narrowly on the modal response. In a series of experiments involving most of the classic tasks in the heuristics and biases literature, we have examined the implications of individual differences in performance for each of the four explanations of the normative and descriptive gap. Performance errors are a minor factor in the gap, computational limitations underlie non-normative responding on several tasks, particularly those that involve some type of cognitive decontextualization. Unexpected patterns of covariance can suggest when the wrong norm is being applied to a task or when an alternative construal of the task is called for. KEYWORDS: rationality, normative models, descriptive models, heuristics, biases, reasoning, individual differences ___________________________________________________________ To help you decide whether you would be an appropriate commentator for this article, an electronic draft is retrievable from the World Wide Web or by anonymous ftp from the US or UK BBS Archive. Ftp instructions follow below. 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. The URLs you can use to get to the BBS Archive: http://www.princeton.edu/~harnad/bbs/ http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.stanovich.html ____________________________________________________________ *** FIVE IMPORTANT ANNOUNCEMENTS *** ------------------------------------------------------------------ (1) There have been some very important developments in the area of Web archiving of scientific papers very recently. Please see: Science: http://www.cogsci.soton.ac.uk/~harnad/science.html Nature: http://www.cogsci.soton.ac.uk/~harnad/nature.html American Scientist: http://www.cogsci.soton.ac.uk/~harnad/amlet.html Chronicle of Higher Education: http://www.chronicle.com/free/v45/i04/04a02901.htm --------------------------------------------------------------------- (2) All authors in the biobehavioral and cognitive sciences are strongly encouraged to archive all their papers (on their Home-Servers as well as) on CogPrints: http://cogprints.soton.ac.uk/ It is extremely simple to do so and will make all of our papers available to all of us everywhere at no cost to anyone. --------------------------------------------------------------------- (3) BBS has a new policy of accepting submissions electronically. Authors can specify whether they would like their submissions archived publicly during refereeing in the BBS under-refereeing Archive, or in a referees-only, non-public archive. Upon acceptance, preprints of final drafts are moved to the public BBS Archive: ftp://ftp.princeton.edu/pub/harnad/BBS/.WWW/index.html http://www.cogsci.soton.ac.uk/bbs/Archive/ -------------------------------------------------------------------- (4) BBS has expanded its annual page quota and is now appearing bimonthly, so the service of Open Peer Commentary can now be be offered to more target articles. The BBS refereeing procedure is also going to be considerably faster with the new electronic submission and processing procedures. Authors are invited to submit papers to: Email: bbs at cogsci.soton.ac.uk Web: http://cogprints.soton.ac.uk http://bbs.cogsci.soton.ac.uk/ INSTRUCTIONS FOR AUTHORS: http://www.princeton.edu/~harnad/bbs/instructions.for.authors.html http://www.cogsci.soton.ac.uk/bbs/instructions.for.authors.html --------------------------------------------------------------------- (5) Call for Book Nominations for BBS Multiple Book Review In the past, Behavioral and Brain Sciences (BBS) journal had only been able to do 1-2 BBS multiple book treatments per year, because of our limited annual page quota. BBS's new expanded page quota will make it possible for us to increase the number of books we treat per year, so this is an excellent time for BBS Associates and biobehavioral/cognitive scientists in general to nominate books you would like to see accorded BBS multiple book review. (Authors may self-nominate, but books can only be selected on the basis of multiple nominations.) It would be very helpful if you indicated in what way a BBS Multiple Book Review of the book(s) you nominate would be useful to the field (and of course a rich list of potential reviewers would be the best evidence of its potential impact!). From harnad at coglit.ecs.soton.ac.uk Fri Aug 27 16:08:16 1999 From: harnad at coglit.ecs.soton.ac.uk (Stevan Harnad) Date: Fri, 27 Aug 1999 21:08:16 +0100 (BST) Subject: SIMPLE HEURISTICS: BBS Call for Multiple Book Review Message-ID: Below is the abstract of the Precis of a book that will shortly be circulated for Multiple Book Review in Behavioral and Brain Sciences (BBS): SIMPLE HEURISTICS THAT MAKE US SMART: BBS MULTIPLE BOOK REVIEW Gerd Gigerenzer, Peter M. Todd, and the ABC Research Group, This book has been accepted for a muliple book review to be published 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. Reviewers must be BBS Associates or nominated by a BBS Associate. (All prior BBS referees, editors, authors, and commentators are also equivalent to Associates.) To be considered as a reviewer for this article, to suggest other appropriate reviewers, or for information about how to become a BBS Associate, please send EMAIL to, BEFORE September 20, 1999: bbs at cogsci.soton.ac.uk or write to [PLEASE NOTE SLIGHTLY CHANGED ADDRESS]: Behavioral and Brain Sciences ECS: New Zepler Building University of Southampton Highfield, Southampton SO17 1BJ UNITED KINGDOM http://www.princeton.edu/~harnad/bbs/ http://www.cogsci.soton.ac.uk/bbs/ If you are not a BBS Associate, please send your CV and the name of a BBS Associate (there are currently over 10,000 worldwide) who is familiar with your work. All past BBS authors, referees and commentators are eligible to become BBS Associates. To help us put together a balanced list of reviewers, 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 reviewer. An electronic draft of the full text is available for inspection with a WWW browser according to the instructions that follow after the abstract. Please also specify (1) If you need the book (2) whether you can make it by the deadline of December 10, 1999. Please note that it is the book, not the Precis, that is to be reviewed. It would be helpful if you indicated in your reply whether you already have the book or would require a copy. _____________________________________________________________ Precis of Simple Heuristics That Make Us Smart BBS MULTIPLE BOOK REVIEW Simple Heuristics That Make Us Smart, was published by Oxford University Press 1999. Peter M. Todd & Gerd Gigerenzer Center for Adaptive Behavior and Cognition Max Planck Institute for Human Development Lentzeallee 94, 14195 Berlin, Germany ptodd at mpib-berlin.mpg.de gigerenzer at mpib-berlin.mpg.de http://www.mpib-berlin.mpg.de/abc ABSTRACT: How can anyone be rational in a world where knowledge is limited, time is pressing, and deep thought is often an unattainable luxury? Traditional models of unbounded rationality and optimization in cognitive science, economics, and animal behavior have tended to view decision-makers as possessing supernatural powers of reason, limitless knowledge, and endless time. But understanding decisions in the real world requires a more psychologically plausible notion of bounded rationality. In "Simple heuristics that make us smart", we explore fast and frugal heuristics--simple rules in the mind's adaptive toolbox for making decisions with realistic mental resources. These heuristics can enable both living organisms and artificial systems to make smart choices quickly and with a minimum of information by exploiting the way that information is structured in particular environments. In this precis, we show how simple building blocks that control information search, stop search, and make decisions can be put together to form classes of heuristics, including: ignorance-based and one-reason decision making for choice, elimination models for categorization, and satisficing heuristics for sequential search. These simple heuristics perform comparably to more complex algorithms, particularly when generalizing to new data--that is, simplicity leads to robustness. We present evidence regarding when people use simple heuristics and describe the challenges to be addressed by this research program. KEYWORDS: Bounded rationality, heuristics, decision making, simplicity, robustness, limited information search, satisficing, ignorance-based reasoning, elimination models, environment structure, adaptive toolbox ____________________________________________________________ To help you decide whether you would be an appropriate commentator for this article, an electronic draft is retrievable from the World Wide Web or by anonymous ftp from the US or UK BBS Archive. Ftp instructions follow below. 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. The URLs you can use to get to the BBS Archive: http://www.princeton.edu/~harnad/bbs/ http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.todd.html *** FIVE IMPORTANT ANNOUNCEMENTS *** ------------------------------------------------------------------ (1) There have been some very important developments in the area of Web archiving of scientific papers very recently. Please see: Science: http://www.cogsci.soton.ac.uk/~harnad/science.html Nature: http://www.cogsci.soton.ac.uk/~harnad/nature.html American Scientist: http://www.cogsci.soton.ac.uk/~harnad/amlet.html Chronicle of Higher Education: http://www.chronicle.com/free/v45/i04/04a02901.htm --------------------------------------------------------------------- (2) All authors in the biobehavioral and cognitive sciences are strongly encouraged to archive all their papers (on their Home-Servers as well as) on CogPrints: http://cogprints.soton.ac.uk/ It is extremely simple to do so and will make all of our papers available to all of us everywhere at no cost to anyone. --------------------------------------------------------------------- (3) BBS has a new policy of accepting submissions electronically. Authors can specify whether they would like their submissions archived publicly during refereeing in the BBS under-refereeing Archive, or in a referees-only, non-public archive. Upon acceptance, preprints of final drafts are moved to the public BBS Archive: ftp://ftp.princeton.edu/pub/harnad/BBS/.WWW/index.html http://www.cogsci.soton.ac.uk/bbs/Archive/ -------------------------------------------------------------------- (4) BBS has expanded its annual page quota and is now appearing bimonthly, so the service of Open Peer Commentary can now be be offered to more target articles. The BBS refereeing procedure is also going to be considerably faster with the new electronic submission and processing procedures. Authors are invited to submit papers to: Email: bbs at cogsci.soton.ac.uk Web: http://cogprints.soton.ac.uk http://bbs.cogsci.soton.ac.uk/ INSTRUCTIONS FOR AUTHORS: http://www.princeton.edu/~harnad/bbs/instructions.for.authors.html http://www.cogsci.soton.ac.uk/bbs/instructions.for.authors.html --------------------------------------------------------------------- (5) Call for Book Nominations for BBS Multiple Book Review In the past, Behavioral and Brain Sciences (BBS) journal had only been able to do 1-2 BBS multiple book treatments per year, because of our limited annual page quota. BBS's new expanded page quota will make it possible for us to increase the number of books we treat per year, so this is an excellent time for BBS Associates and biobehavioral/cognitive scientists in general to nominate books you would like to see accorded BBS multiple book review. (Authors may self-nominate, but books can only be selected on the basis of multiple nominations.) It would be very helpful if you indicated in what way a BBS Multiple Book Review of the book(s) you nominate would be useful to the field (and of course a rich list of potential reviewers would be the best evidence of its potential impact!). From georgiou at csusb.edu Fri Aug 27 17:15:54 1999 From: georgiou at csusb.edu (georgiou@csusb.edu) Date: 27 Aug 1999 14:15:54 -0700 Subject: CFP: 4th ICCIN (Feb. 27-Mar. 3, 2000) Message-ID: Call for Papers 4th International Conference on COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE http://www.csci.csusb.edu/iccin Trump Taj Mahal Casino and Resort]], Atlantic City, NJ USA February 27 -- March 3, 2000 Summary Submission Deadline: September 1, 1999 Conference Co-chairs: Subhash C. Kak, Louisiana State University Jeffrey P. Sutton, Harvard University This conference is part of the Fourth Joint Conference Information Sciences. http://www.ee.duke.edu/JCIS/ ***Added plenary speakers***: Marvin Minsky and Brian Josephson Plenary Speakers include the following: +------------------------------------------------------------------------+ |James Anderson |Wolfgang Banzhaf |B. Chandrasekaran|Lawrence J. Fogel| |-----------------+------------------+-----------------+-----------------| |Walter J. Freeman|David E. Goldberg |Irwin Goodman |Stephen Grossberg| |-----------------+------------------+-----------------+-----------------| |Thomas S.Huang |Janusz Kacprzyk |A. C. Kak |Subhash C. Kak | |-----------------+------------------+-----------------+-----------------| |John Mordeson |Kumpati S. Narenda|Anil Nerode |Huang T. Nguyen | |-----------------+------------------+-----------------+-----------------| |Jeffrey P. Sutton|Ron Yager | | | +------------------------------------------------------------------------+ Special Sessions on Quantum Computation. More to be added. Areas for which papers are sought include: o Artificial Life o Artificially Intelligent NNs o Associative Memory o Cognitive Science o Computational Intelligence o DNA Computing o Efficiency/Robustness Comparisons o Evaluationary Computation for Neural Networks o Feature Extraction & Pattern Recognition o Implementations (electronic, Optical, Biochips) o Intelligent Control o Learning and Memory o Neural Network Architectures o Neurocognition o Neurodynamics o Optimization o Parallel Computer Applications o Theory of Evolutionary Computation Summary Submission Deadline: September 1, 1999 Notification of authors upon review: November 1, 1999 December 1, 1999 - Deadline for invited sessions and exhibition proposals Papers will be accepted based on summaries. A summary shall not exceed 4 pages of 10-point font, double-column, single-spaced text, with figures and tables included. For the Fourth ICCIN, send 3 copies of summaries to: George M. Georgiou Computer Science Department California State University San Bernardino, CA 92407-2397 U.S.A. georgiou at csci.csusb.edu From terry at salk.edu Fri Aug 27 21:03:23 1999 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 27 Aug 1999 18:03:23 -0700 (PDT) Subject: NEURAL COMPUTATION 11:7 Message-ID: <199908280103.SAA10599@tesla-e0.salk.edu> NEURAL COMPUTATION 11:7 Neural Computation - Contents - Volume 11, Number 7 - October 1, 1999 ARTICLE Prediction Games and Arcing Algorithms Leo Breiman NOTES Can Hebbian Volume Learning Explain Discontinuities In Cortical Maps? Graeme J. Mitchison and Nicholas V. Swindale Disambiguating Different Covariation Types Carlos Brody LETTER Correlations Without Synchrony Carlos Brody On Decoding The Responses Of A Population of Neurons From geoff at giccs.georgetown.edu Sun Aug 29 10:08:34 1999 From: geoff at giccs.georgetown.edu (Geoff Goodhill) Date: Sun, 29 Aug 1999 10:08:34 -0400 Subject: Postdoc position available Message-ID: <199908291408.KAA13562@brecker.giccs.georgetown.edu> POSTDOCTORAL POSITION IN AXON GUIDANCE A postdoctoral position in now available to join a small team of physicists, biologists and computational neuroscientists investigating mechanisms of axon guidance in the developing nervous system. We are combining mathematical modeling with the development of a novel bioengineering technology for complementary quantitative experiments. We are looking for someone with skills in mathematical biological modeling, dynamics of complex systems, or quantitative imaging and data acquisition. For more details see http://www.giccs.georgetown.edu/labs/cns/axon.html Send a CV and contact information for at least two referees, preferably be email, to Geoffrey J Goodhill Georgetown Institute for Cognitive and Computational Sciences Georgetown University Medical Center 3970 Reservoir Road NW Washington DC 20007 Tel: (202) 687 6889 Fax: (202) 687 0617 Email: geoff at giccs.georgetown.edu Homepage: www.giccs.georgetown.edu/labs/cns From juergen at idsia.ch Mon Aug 30 03:34:44 1999 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Mon, 30 Aug 1999 09:34:44 +0200 Subject: job opening Message-ID: <199908300734.JAA13770@ruebe.idsia.ch> POSTDOC JOB OPENING The Swiss machine learning research institute IDSIA offers a 1-year postdoc position with possibility of renewal for 2 additional years. It is the position currently held by Fred Cummins who recently accepted a professorship at the University of Ireland, Dublin. The position is funded by an SNF research grant on recurrent neural networks. Ideal candidates have strong mathematical and programming skills, outstanding research potential, excellent ability to communicate research results, interest in recurrent network research, experience in one or more of the following fields: speech processing, neural nets, prediction (e.g., finance), control, music, program evolution. For more information, please see http://www.idsia.ch/~juergen/lstm99.html Juergen Schmidhuber IDSIA http://www.idsia.ch/~juergen From smagt at dlr.de Mon Aug 30 07:11:19 1999 From: smagt at dlr.de (Patrick van der Smagt) Date: Mon, 30 Aug 1999 13:11:19 +0200 (MET DST) Subject: CFP: Scalable Robotic Applications of Neural Networks Message-ID: <199908301111.NAA29171@ilz.robotic> Scalable Robotic Applications of Neural Networks ================================================ Special Issue of "Applied Intelligence" Editors: Patrick van der Smagt and Daniel Bullock http://www.robotic.dlr.de/Smagt/CFP/ In this special issue, we want to address the question of whether there are real robotic problems that can be better solved using existing neuro-computational principles than by using other standard engineering techniques. Where sensory-motor systems cannot be explicitly modeled, the brain's success leads us to expect that approaches based on adaptive neural control will someday provide a technically sound alternative. However, today's robotic engineers are appropriately skeptical regarding use of neural network principles because of the apparent scarcity of published research that demonstrates scalability of solutions to complex robotic control tasks. For example, like many traditional approaches, many neural network control strategies do not scale well from a two-degree-of-freedom robot arm to a seven degree-of-freedom system. For this special issue, papers are sought that: 1. introduce or review biologically plausible models of sensory-motor control that truly integrate action and perception; 2. newly apply such models to the control of realistic robots, especially manipulators; 3. describe hybrid robot control methodologies that incorporate cerebellar or other neuro-computational models (e.g., vision); 4. provide a case history that clearly defines, or illustrates overcoming of, barriers to successful competition by neural network models for robot control. The scalability of applications of biological models can only be fully assessed in the context of demonstrations that are representative of real-world complexities. Therefore, results on real hardware will generally be preferred. However, results on well-simulated complex problems will be preferred to results with hardware (e.g., 2 DoF robot arms) that can already be optimally controlled with conventional, non-neural techniques. Special Issue Editors: ---------------------- Patrick van der Smagt Institute of Robotics and System Dynamics DLR (German Aerospace Research Center) Oberpfaffenhofen, Germany smagt at dlr.de http://www.robotic.dlr.de/Smagt/ Daniel Bullock Cognitive and Neural Systems Department Boston University danb at cns.bu.edu http://cns-web.bu.edu/faculty.html#bullock Editor in Chief: ---------------- Moonis Ali Department of Computer Science Southwest Texas State University ma04 at swt.edu http://www.cs.swt.edu Submission ========== Deadline for submitting papers: Jan 15, 2000. The journal's instructions to authors can be read at http://www.robotic.dlr.de/Smagt/CFP/ifa.html. For this special issue, *all* papers must be submitted by the above date in Postscript or PDF format via email to smagt at dlr.de. Hardcopy submissions will not be accepted. To the extent that time permits, the editors will invite short external commentaries (to be published in the same issue) on the accepted papers. Submitters should inform the editors if they do *not* want their paper treated in an invited commentary. Suggestions of expert reviewers and commentators are welcome. About the journal ================= The objective of Applied Intelligence (IJAI) is to provide a medium for exchanging applied research on intelligent systems and technological achievements. IJAI is currently in its eighth year of publication. In order to meet the demand, the publication frequency has been increased from four to six issues per year effective 1998. IJAI is abstracted and/or indexed by twenty indexing publications. See http://www.wkap.nl/journals/apin -- Dr Patrick van der Smagt phone +49 8153 281152, fax -34 DLR/Institute of Robotics and System Dynamics smagt at dlr.de P.O.Box 1116, 82230 Wessling, Germany http://www.robotic.de/Smagt/ From georg at ai.univie.ac.at Mon Aug 30 12:32:26 1999 From: georg at ai.univie.ac.at (Georg Dorffner) Date: Mon, 30 Aug 1999 18:32:26 +0200 Subject: Workshop: Future and Prospects of Neural Networks Message-ID: <37CAB21A.4C1FA72C@ai.univie.ac.at> The following workshop is open to everyone. Your input to the discussion is needed! Since the workshop will take place during ICANN'99 at the conference venue, it will be of particular interest to conference participants. ============================================================= The Future and Prospects of Neural Networks ============================================================= a workshop Edinburgh University Appleton Tower, Lecture Theatre 2 Wednesday, Sep. 8, 1999, 6-8 p.m. Purpose The purpose of the workshop is to consolidate views and discuss perspectives of where the field of neural networks will be heading in the near and medium-term future. The ultimate goal of NEuroNet - the organiser of this workshop - is to compile a so-called "technological roadmap" of neural networks and related methodologies, that presents a visionary overview of the current trends in neural networks, as well as likely future developments, foci and prospects of both basic and applied research. For this, the opinions from neural network researchers are solicited. Format A number of panellists will present their short position papers about the future of neural networks. This will be followed by an open discussion, where everybody is invited to contribute their own view about the prospects of the field. Refreshments will be served to enable a continuation of the discussion over a glass of wine. Panellists: Georg Dorffner, OFAI Vienna Geoffrey Hinton, Univ. College London Erkki Oja, Helsinki Univ. of Technology Nic Schraudolph, IDSIA Lugano John Taylor, King's College London David Willshaw, Edinburgh Univ. Moderation: Mark Plumbley, NEuroNet The organizer This workshop is organised by NEuroNet - the network of excellence on neural networks, sponsored by the EU commission (http://www.kcl.ac.uk/neuronet). More information about the workshop can be found at http://www.ai.univie.ac.at/oefai/nn/neuronet/workshop.html From jknierim at nba19.med.uth.tmc.edu Mon Aug 30 11:48:54 1999 From: jknierim at nba19.med.uth.tmc.edu (James Knierim) Date: Mon, 30 Aug 1999 10:48:54 -0500 Subject: postdoctoral position available Message-ID: <37CAA7E6.4459CBAC@nba19.med.uth.tmc.edu> Postdoctoral position available in behavioral/cognitive neuroscience We use state-of the-art multi-electrode technology to record single-unit activity from neuronal ensembles in the hippocampus and related structures of freely moving animals. Current projects include studies of the interactions between place cells in the hippocampus and head direction cells of the thalamus, and the processing of information through the different areas of the hippocampal formation (entorhinal cortex, dentate gyrus, CA fields, and subiculum). Expertise in single-unit physiology, behavioral neuroscience, or computational neuroscience is preferred. Please send a CV, statement of research interests, and references to: James J. Knierim, Ph.D. Department of Neurobiology and Anatomy University of Texas-Houston Medical School P.O. Box 20708 Houston, TX 77225 E0E/AA/SSP/Smoke-free Environment From ted.carnevale at yale.edu Tue Aug 31 08:26:47 1999 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Tue, 31 Aug 1999 08:26:47 -0400 Subject: SFN 1999 NEURON course Message-ID: <37CBCA07.F2E22E68@yale.edu> This year, the Society for Neuroscience meeting is earlier than in 1997 or 19998, so the deadline to sign up for the NEURON short course is approaching rapidly. Seats are still available, but quick action is needed to take advantage of the early registration fee. Among the new features that will be covered, I should mention: The Cell Builder, which will be of particular interest to experimentalists and others whose models are closely linked to empirical observations. The Cell Builder makes it easy to construct new models, but its greatest strength may be in the management of anatomically complex models based on quantitative morphometric data. The Multiple Run Fitter, a powerful and flexible new tool for optimizing models with high-dimensional data sets. This tool is useful for experimentalists and theoreticians alike. Further information about the course and an electronic registration form are posted at http://www.neuron.yale.edu/miami99.html --Ted From ucganlb at ucl.ac.uk Tue Aug 31 14:51:45 1999 From: ucganlb at ucl.ac.uk (Neil Burgess - Anatomy UCL London) Date: Tue, 31 Aug 1999 19:51:45 +0100 Subject: C code available for model of STM for serial order. Message-ID: <2099.199908311851@socrates-a.ucl.ac.uk> The C code for the simulations in the following paper is available on: http://behemoth.maze.ucl.ac.uk/neil/PL_sim/ code and executables for running under MS windows/DOS can be found on: http://behemoth.maze.ucl.ac.uk/neil/PL_simPC/ MEMORY FOR SERIAL ORDER: A NETWORK MODEL OF THE PHONOLOGICAL LOOP AND ITS TIMING. N Burgess & GJ Hitch (1999) Psychological Review 106 551-581. Abstract: A connectionist model of human short-term memory is presented that extends the `phonological loop' (A. D. Baddeley, 1986) to encompass serial order and learning. Psychological and neuropsychological data motivate separate layers of lexical, timing and input and output phonemic information. Connection weights between layers show Hebbian learning and decay over short and long time scales. At recall, the timing signal is rerun, phonemic information feeds back from output to input and lexical nodes compete to be selected. The selected node then receives decaying inhibition. The model provides an explanatory mechanism for the phonological loop, and for the effects of serial position, presentation modality, lexicality, grouping and Hebb repetition. It makes new psychological and neuropsychological predictions and is a starting point for understanding the role of the phonological loop in vocabulary acquisition and for interpreting data from functional neuroimaging. Best wishes, Neil From gaudiano at cns.bu.edu Mon Aug 2 17:32:33 1999 From: gaudiano at cns.bu.edu (Paolo Gaudiano) Date: Mon, 2 Aug 1999 17:32:33 -0400 Subject: Update: Posters now accepted at UI-CANCS conference Message-ID: <199908022132.RAA27988@cochlea.bu.edu> This announcement is being sent to multiple lists. We are sorry if you receive multiple copies. IMPORTANT UPDATE: Now accepting contributed posters First USA-Italy Conference on Applied Neural and Cognitive Sciences UI-CANCS'99 Boston, October 3-6, 1999 In response to popular demand we are expanding UI-CANCS'99 to include a poster session for contributed work. Submissions should focus on applications of neural and cognitive sciences. Applications describing collaborations between industry and research are especially relevant. Please send a title and abstract (up to one page) with the name and affiliation of all authors to info at usa-italy.org. Abstracts will be reviewed promptly and, if appropriate, will be accepted on a first-come basis as long as there is room available. The posters will be available for viewing all day on October 4 and 5. For additional information please visit http://www.usa-italy.org or send e-mail to info at usa-italy.org. From char-ci0 at wpmail.paisley.ac.uk Tue Aug 3 12:48:55 1999 From: char-ci0 at wpmail.paisley.ac.uk (Darryl Charles) Date: Tue, 03 Aug 1999 16:48:55 +0000 Subject: Ph.D. studentship Message-ID: PhD studentship available in the Applied Computational Intelligence Research Group at the University of Paisley, Scotland. A bursary (approx. =A35500) is available for the successful applicant who will examine the positive effects of additive noise in unsupervised artificial neural networks, particularly networks that have been developed here at Paisley. Visual data is of particular interest in this research. Applicants should be suitably qualified and preferably have neural network and/or vision related experience/interest. Supervisory team will consist of Dr. Darryl Charles (Director of studies) and Prof. Colin Fyfe. Send a CV to char-ci0 at paisley.ac.uk Darryl Charles CIS dept. University of Paisley Paisley Scotland PA1 2BE From marwan at ee.usyd.edu.au Wed Aug 4 08:06:39 1999 From: marwan at ee.usyd.edu.au (Marwan Jabri) Date: Wed, 4 Aug 1999 22:06:39 +1000 Subject: Faculty Positions Message-ID: <002201bede71$ceabf840$cb184e81@majhome.sedal.usyd.edu.au> POSITION: Lecturer/Senior Lecturer in Computer Engineering (2 positions) DEPARTMENT: School of Electrical and Information Engineering, The University of Sydney TYPE: Academic APPOINTMENT: continuing REF NO: A20/01 Closing Date: 26/08/99 The School of Electrical and Information Engineering is expanding its teaching and research programs in the area of computer and software engineering following the introduction of degree programs in these areas, and invites applications for two continuing positions. Applicants should be able to contribute to teaching of advanced courses in these areas and research in one or more of the Schools major research areas. The existing academic staff in related areas have research interests in low power integrated circuits, artificial intelligence and neuromorphic engineering, biomedical systems, automatic control, communications systems and image processing. Within computer engineering, particular areas of interest include neuromorphic engineering, reconfigurable computing; integrated circuits and systems; hardware/software co-design; advanced digital engineering; and parrallel and distributed processing. The development of software engineering is occurring in collaboration with the Department of Computer Science. Applicants at the Senior Lecturer level should have a PhD in Electrical or Computer Engineering. Applicants at the Lecturer level should have or should be expecting soon to be awarded a PhD. A PhD in computer science with a substantial engineering background may be considered. The position requires commitment to leadership in research and teaching. Candidates must have a high level of research outcomes and would have the capability to teach undergraduate classes and supervise research students. Undergraduate teaching experience and industrial applications experience are desirable. The position is full-time continuing, subject to the completion of a satisfactory probation period for new appointees. Membership of a University approved superannuation scheme is a condition of employment for new appointees. For further information contact Professor M A Jabri on (+61-2) 9351 2240, fax: (+61-2) 9351 7209, email: marwan at sedal.usyd.edu.au, or the Head of Department, Professor D J Hill on (+61-2) 9351 4647, fax (+61-2) 9351 3847, e-mail: davidh at ee.usyd.edu.au. (Level of appointment and responsibility will be commensurate with qualifications and experience) Academic staff at the School of Electrical and Information Engineering is currently entitled to receive a market loading (up to a maximum of 33.33% of base salary). The market loading scheme is expected to continue until the end of 1999 when it will be reviewed. WE ARE AN EQUAL OPPORTUNITY EMPLOYER AND WE OFFER A SMOKE FREE WORKPLACE Availability: Internal & External Salary: Lecturer $48,440 -$57,523 p.a. Senior Lecturer $59,338 - $68,422 p.a. ---------------------------------------------------------------------------- ---- Application Information No smoking in the workplace is University policy. Equal employment opportunity is University policy. Other than in exceptional circumstances all vacancies within the University are advertised in the Bulletin Board and on the World Wide Web. Intending applicants are encouraged to seek further information from the contact given before submitting a formal application. Academic positions: Applications (five copies for levels A-D and ten copies for level E), which should quote the reference no, address the selection criteria, and include a CV, a list of publications, the names, addresses, e-mail, fax and phone number of confidential referees (three for levels A-D and five for level E), should be forwarded to: General Staff positions: Applications, which should quote the reference no, address the selection criteria, and include a CV, the names, addresses, e-mail, fax and phone number of two confidential referees, should be forwarded to: The Personnel Officer, College of Sciences and Technology, Carslaw Building, (F07), The University of Sydney, NSW, 2006 The University is a non-smoking workplace and is committed to the policies and principles of equal employment opportunity and cultural diversity. The University reserves the right not to proceed with any appointment for financial or other reasons. ---------------------------------------------------------------------------- ---- Authorised Publication of Personnel Services ~ Last updated 4/8/99 -------------- Marwan Jabri, Professor Director, Computer & Software Engineering Programs School of Electrical & Information Engineering The University of Sydney NSW 2006, Australia Tel: (+61-2) 9351-2240, Fax:(+61-2) 9351-7209 Email: marwan at sedal.usyd.edu.au, http://www.sedal.usyd.edu.au/~marwan/ From oreilly at grey.colorado.edu Fri Aug 6 01:29:50 1999 From: oreilly at grey.colorado.edu (Randall C. O'Reilly) Date: Thu, 5 Aug 1999 23:29:50 -0600 Subject: SENIOR and/or JUNIOR COGNITIVE NEUROSCIENCE POSITIONS Message-ID: <199908060529.XAA28247@grey.colorado.edu> The following is our advertisement for faculty positions available at the University of Colorado, Boulder. One of the directions we are interested in pursuing is to enhance our strength in computational modeling as a cognitive neuroscience methodology, so modelers are encouraged to apply. Feel free to contact me for further information. - Randy SENIOR and/or JUNIOR COGNITIVE NEUROSCIENCE POSITIONS Department of Psychology, University of Colorado, Boulder The Department of Psychology, University of Colorado, Boulder, invites applications for two tenure-track positions in Cognitive Psychology, beginning August 2000. At least one of these positions will be in Cognitive Neuroscience. One appointment will be at the rank of Associate or Full Professor, and the second is likely to be at the rank of Assistant Professor. Applicants should send a Curriculum Vitae, a statement of research and teaching interests, example research papers, and at least three letters of recommendation to: Ms. Deborah Aguiar, Administrative Assistant-Cognitive Psychology Search, Department of Psychology, University of Colorado, Boulder, CO 80309-0345. Inquiries should be addressed to Dr. Lyle E. Bourne, Jr., Chair--Cognitive Search, (303) 492-4210, lbourne at psych.colorado.edu. Applications will be reviewed as they are completed and until the position is filled. To insure full consideration, however, the application should be complete by November 1, 1999. The University of Colorado at Boulder is committed to diversity and equality in education and employment. +-----------------------------------------------------------------------------+ | Dr. Randall C. O'Reilly | | | Assistant Professor | | | Department of Psychology | Phone: (303) 492-0054 | | University of Colorado Boulder | Fax: (303) 492-2967 | | Muenzinger D251C | Home: (303) 448-1810 | | Campus Box 345 | email: oreilly at psych.colorado.edu | | Boulder, CO 80309-0345 | www: http://psych.colorado.edu/~oreilly | +-----------------------------------------------------------------------------+ From renner at ecst.csuchico.edu Fri Aug 6 16:15:44 1999 From: renner at ecst.csuchico.edu (renner@ecst.csuchico.edu) Date: Fri, 6 Aug 1999 13:15:44 -0700 (PDT) Subject: PhD Thesis on nnet ensembles Message-ID: <19990806201544.13443.qmail@pitbull.ecst.csuchico.edu> Dear Connectionists, The following dissertation is now available on-line from http://www.ecst.csuchico.edu/~renner or directly from http://www.ecst.csuchico.edu/~renner/Diss/ Improving Generalization of Constructive Neural Networks Using Ensembles by R.S. Renner ABSTRACT Ensemble networks have been receiving considerable attention within the last few years. Most existing models are created with linear networks. Ensembles of linear networks have demonstrated improved performance over individual networks, but linear models have limited capacity problems. Ensembles of more complex well-trained networks offer a promising alternative. Unfortunately, the computational expense involved in training large numbers of well-trained networks may be prohibitive. An ensemble of non-linear feed-forward neural networks generated by a constructive algorithm is presented. The ensemble method presented exhibits better generalization than linear ensembles, and shows promise toward a reduction in time-complexity over well-trained ensembles. The problems addressed in this research are: generalization of non-linear data, time-complexity, structural dilemmas, model creation, and model combination. The Neural Network Ensemble Simulator (NNES) is also introduced as a simulation tool for managing ensemble experiments. NNES provides routines for ensemble creation, selection, combination, and analysis. Keywords: ensembles, constructive neural networks, generalization, Cascade-Correlation, Surrogate Bayes Combination Method (SBCM), Neural Network Ensemble Simulator (NNES). NOTE: Files in directory are pdf format. Please notify me via email if you are unable to read this format. Table of Contents is available in 'preface.pdf' __ __ __ __ __ __ __ __ __ __ __ __ __ / // // // // // // // // // // // // / \ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \ R.S. Renner, Ph.D. Assistant Professor, College of ECT California State Univeristy - Chico Department of Computer Science Chico, CA 95929-0410 (530)898-5419 fax: 5995 www.ecst.csuchico.edu/~renner renner at ecst.csuchico.edu / // // // // // // // // // // // // / \ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \\ \ From X.Yao at cs.bham.ac.uk Mon Aug 9 05:53:43 1999 From: X.Yao at cs.bham.ac.uk (Xin Yao) Date: Mon, 9 Aug 1999 10:53:43 +0100 (BST) Subject: Combinations of EC and NNs Message-ID: <199908090953.KAA04028@edward.cs.bham.ac.uk> The First IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks Co-sponsored by IEEE Neural Network Council The Center for Excellence in Evolutionary Computation May 11-12, 2000 The Gunter Hotel, San Antonio, TX, USA Symposium URL: http://www.cs.bham.ac.uk/~xin/ecnn2000 CALL FOR PAPERS The recent increasing interest in the synergy between evolutionary computation and neural networks provides an impetus for a symposium dedicated to furthering our understanding of this synergy and the potential utility of hybridizing evolutionary and neural techniques. The First IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks will offer a forum that focuses specifically on the hybridization of evolutionary and neural computation. In particular, papers are solicited in the areas of + evolutionary training of neural networks, + evolutionary design of network topologies, + evolution of learning (weight updating) rules, + evolving solutions to inverse neural network problems, + the performance of alternative variation operators in designing neural networks, + comparisons between evolutionary and other training methods, + evolving developmental rules for neural network design, and + the use of coevolution in optimizing neural networks for pattern recognition, gaming, or other applications. Other topics that combine evolutionary and neural computation are also welcome. Submitted papers should represent unpublished, original work. PAPER SUBMISSION Send three (3) copies of your manuscript to Xin Yao School of Computer Science The University of Birmingham Edgbaston, Birmingham B15 2TT U.K. Email: x.yao at cs.bham.ac.uk All three hardcopies should be printed on 8.5 by 11 inch or A4 paper using 11 point Times. Allow at least one inch (25mm) margins on all borders. A paper must include a title, an abstract, and the body and references. It must also include the names and addresses of all authors, their email addresses, and their telephone/fax numbers. The length of submitted papers must be no more than 15 single-spaced, single-column pages, including all figures, tables, and references. Shorter papers are encouraged. In addition to hardcopies, please send a postscript file of your paper (gzipped if possible) to facilitate electronic reviewing to the following email address: x.yao at cs.bham.ac.uk. Please check the symposium's web site http://www.cs.bham.ac.uk/~xin/ecnn2000 for more details as they become available. SUBMISSION DEADLINE: DECEMBER 1, 1999 General Chair: Xin Yao Programme Chair: D.B. Fogel PROGRAMME COMMITTEE: P.J. Angeline K. Chellapilla J.-C. Chen S.-B. Cho D.B. Fogel G.W. Greenwood L. Guan N. Kasabov S. Lucas N. Murshed V. Nissen M. Rizki R. Salomon G. Yen B.-T. Zhang Q. Zhao The Symposium follows The 9th IEEE International Conference on Fuzzy Systems (FUZZ-IEEE2000), Hilton Palacio del Rio, San Antonio, TX, USA, 7-10 May 1999. (URL: http://fuzzieee2000.cs.tamu.edu/) From juergen at idsia.ch Mon Aug 9 04:56:52 1999 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Mon, 9 Aug 1999 10:56:52 +0200 Subject: exploration Message-ID: <199908090856.KAA02848@ruebe.idsia.ch> Two papers on exploration are now available in digital form: ----------------------------------------------------------------------- Efficient Model-Based Exploration Marco Wiering & Juergen Schmidhuber, IDSIA, Lugano, Switzerland In R. Pfeiffer, B. Blumberg, J. Meyer, S. W. Wilson, eds., From Animals to Animats 5: Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior, p. 223-228, MIT Press, 1998. ftp://ftp.idsia.ch/pub/juergen/sab98explore.ps.gz Model-Based Reinforcement Learning (MBRL) can greatly profit from using world models for estimating the consequences of selecting particular actions: an animat can construct such a model from its experiences and use it for computing rewarding behavior. We study the problem of collecting useful experiences through exploration in stochastic environments. Towards this end we use MBRL to maximize exploration rewards (in addition to environmental rewards) for visits of states that promise information gain. We also combine MBRL and the Interval Estimation algorithm (Kaelbling, 1993). Experimental results demonstrate the advantages of our approaches. ----------------------------------------------------------------------- Artificial Curiosity Based on Discovering Novel Algorithmic Predictability Through Coevolution Juergen Schmidhuber, IDSIA, Lugano, Switzerland In P. Angeline, Z. Michalewicz, M. Schoenauer, X. Yao, Z. Zalzala, eds., Congress on Evolutionary Computation, p. 1612-1618, IEEE Press, Piscataway, NJ, 1999. (based on TR IDSIA-35-97, 1997) ftp://ftp.idsia.ch/pub/juergen/cec99.ps.gz How to explore a spatio-temporal domain? By predicting and learning from success/failure what's predictable and what's not. I study a "curious" embedded agent that differs from previous explorers in the sense that it can limit its predictions to fairly arbitrary, computable aspects of event sequences and thus can explicitly ignore almost arbitrary unpredictable, random aspects. It constructs initially random algorithms mapping event sequences to abstract internal representations (IRs). It also constructs algorithms predicting IRs from IRs computed earlier. It wants to learn novel algorithms creating IRs useful for correct IR predictions, without wasting time on those learned before. This is achieved by a co-evolutionary scheme involving two competing modules COLLECTIVELY designing SINGLE algorithms to be executed. The modules can bet on the outcome of IR predictions computed by the algorithms they have agreed upon. If their opinions differ then the system checks who's right, punishes the loser (the surprised one), and rewards the winner. A reinforcement learning algorithm forces each module to maximixe reward. This motivates both modules to lure the other into agreeing upon algorithms involving predictions that surprise it. Since each module essentially can put in its veto against algorithms it does not consider profitable, the system is motivated to focus on those computable aspects of the environment where both modules still have confident but different opinions. Once both share the same opinion on a particular issue (via the loser's learning process, e.g., the winner is simply copied onto the loser), the winner loses a source of reward - an incentive to shift the focus of interest onto novel, yet unknown algorithms. Simulations include an example where surprise-generation of this kind helps to speed up external reward. ----------------------------------------------------------------------- Several additional postscripts now available in http://www.idsia.ch/~juergen/onlinepub.html Juergen Schmidhuber www.idsia.ch From koza at smi.stanford.edu Tue Aug 10 12:26:29 1999 From: koza at smi.stanford.edu (John Koza) Date: Tue, 10 Aug 1999 09:26:29 -0700 Subject: 1000-Pentium beowulf computer for genetic programming research Message-ID: <005d01bee34d$19a0ad20$050010ac@mendel> Hello: We have just posted photos of our recently installed 1,000-Pentium Beowulf-style cluster computer system consisting of a server and 1,000 Pentium II 350-MHz processors. It is constructed entirely from "Commodity Off The Shelf" (COTS) components. This new machine is operated by Genetic Programming Inc., a privately funded research group aimed at producing human-competitive results using genetic programming. We are currently working in the areas of automated synthesis of analog electrical circuits and controllers, problems in computational molecular biology, various other problems involving cellular automata, multi-agent systems, operations research, and other areas of design, and using genetic programming as an automated "invention machine" for creating new and useful patentable inventions. There are now a number of instances where genetic programming has automatically produced a computer program that is competitive with human performance. Competitiveness with human performance can be established in a variety of ways. For example, genetic programming may produce a result that is slightly better, equal, or slightly worse than that produced by a succession of human researchers working on an well-defined problem over a period of years. Or, genetic programming may produce a result that is equivalent to an invention that was patented in the past or that is patentable today as a new invention. The fact that genetic programming can evolve entities that are competitive with human-produced results suggests that genetic programming may possibly be used as an "invention machine" to create new and useful patentable inventions. Each of the 1,000 processors of our parallel computer system has a Pentium II 350-MHz processor. Each processor uses 64 megabytes of RAM (so that the system as a whole has 64 gigabytes of RAM). The 1000 Pentium II processors reside on 500 dual-CPU ATX motherboards and each motherboard is housed in a standard mini-tower box. Each mini-tower box contains 128 megabytes of RAM, a 100 megabit-per-second Ethernet NIC, and a standard 300W power switching power supply. There is no hard disk, video monitor, keyboard, floppy disk drive, or other input-output device associated with any of the 1,000 processors. The processors run the Linux operating system (Red Hat Linux 6.0). The communication between processors and between the server and the processors is by means of 100 megabit-per-second Ethernet. Each group 40 processors (20 boxes) is connected to one 24-port 100 megabit-per-second Ethernet hub. There are 25 hubs in the system. Each hub is connected on its uplink to one of two 100 megabit-per-second 16-port Ethernet switches. The two switches are connected to each other and to the server. The server computer is also a dual Pentium II 350-MHz processor. The server has 256 MB of RAM. It runs on the Linux operating system (Red Hat Linux 6.0 from VA Linux Research). The server contains a 14 GB hard disk, a video display monitor, a floppy disk drive, a CD ROM drive, and a keyboard. The system is booted using a DHCP message from the server to the 1,000 processors. We used the Beoboot software from Rembo Technology SaRL, Geneva, Switzerland. The 500 boxes directly access the server's file system using NFS. Additional information about the machine and genetic programming (and job opportunities) can be found at http://www.genetic-programming.com John R. Koza Consulting Professor Stanford Medical Informatics Department of Medicine Medical School Office Building Stanford University Stanford, California 94305 Consulting Professor Department of Electrical Engineering School of Engineering Stanford University Phone: 650-941-0336 Fax: 650-941-9430 E-Mail: koza at stanford.edu E-Mail: koza at genetic-programming.com For information about GECCO-2000 (GP-2000) conference in Las Vegas on July 8 -12, 2000, visit: http://www.genetic-algorithm.org/GECCO2000/gecco2000mainpage.htm From chiru at csa.iisc.ernet.in Wed Aug 11 03:30:51 1999 From: chiru at csa.iisc.ernet.in (Chiranjib Bhattacharya) Date: Wed, 11 Aug 1999 13:00:51 +0530 (IST) Subject: TR Announcement Message-ID: Technical Report Announcement: Platt's SMO algorithm is an excellent algorithm for designing SVMs because it is very efficient. It has become popular since it is also extremely simple to implement. Our recent research has shown that there is an important source of inefficiency in the SMO algorithm that has to do with choosing the threshold parameter, b. We remove this inefficiency by carefully modifying SMO while keeping the main ideas of SMO in tact. The modified algorithms run much faster than the original SMO. Details are given in the Technical Report mentioned below. A gzipped post- script file containing the report can be downloaded from: http://guppy.mpe.nus.edu.sg/~mpessk/ Send any comments to: mpessk at guppy.mpe.nus.edu.sg ---------------------------------------------------------------------------- Improvements to Platt's SMO Algorithm for SVM Classifier Design Technical Report CD-99-14 S.S. Keerthi, S.K. Shevade, C. Bhattacharyya & K.R.K. Murthy Abstract This paper points out an important source of confusion and inefficiency in Platt's Sequential Minimal Optimization (SMO) algorithm that is caused by the use of a single threshold value. Using clues from the KKT conditions for the dual problem, two threshold parameters are employed to derive modifications of SMO. These modified algorithms perform significantly faster than the original SMO on all benchmark datasets tried. ---------------------------------------------------------------------------- From Paul.Keller at pnl.gov Wed Aug 11 10:26:05 1999 From: Paul.Keller at pnl.gov (Keller, Paul E) Date: Wed, 11 Aug 1999 07:26:05 -0700 Subject: CFP: Applications and Science of Computational Intelligence III Message-ID: <9623E2E264D9D211B5FA0008C7A4B5CC3F9355@pnlmse2.pnl.gov> * * * C A L L F O R P A P E R S * * * Applications and Science of Computational Intelligence III http://www.spie.org/web/meetings/calls/or00/confs/OR16.html Applications and Science of Computational Intelligence III (OR16) On-site Proceedings. Abstracts for this conference are due by 13 September 1999. Manuscripts are due by 31 January 2000. Conference Chairs: Kevin L. Priddy, Battelle Memorial Institute; Paul E. Keller, Battelle/Pacific Northwest National Lab.; David B. Fogel, Natural Selection, Inc. Program Committee: Shun-ichi Amari, RIKEN (Japan); Stanley C. Ahalt, The Ohio State Univ.; Peter J. Angeline, Natural Selection, Inc.; Gianfranco Basti, Pontifical Lateran Univ. (Italy); James C. Bezdek, Univ. of West Florida; Bruno Bosacchi, Lucent Technologies/Bell Labs.; David Brown, Food and Drug Administration; David P. Casasent, Carnegie Mellon Univ.; Nick DeClaris, Univ. of Maryland; Joydeep Ghosh, Univ. of Texas/Austin; Charles W. Glover, Oak Ridge National Lab.; Clifford G. Lau, Office of Naval Research; Karl Mathia, Equipe Technologies, Inc.; Antonio L. Perrone, Univ. of Rome (Italy); Steven K. Rogers, Qualia Computing, Inc.; Stephan Rudolph, Univ. Stuttgart (Germany); Bradley C. Wallet, Naval Surface Warfare Ctr. The focus of this conference is on real-world applications of computational intelligence (neural networks, fuzzy logic, and/or evolutionary computation) and on recent theoretical developments (principal components analysis/independent components analysis, etc.) applicable to current problem domains. The goal is to provide a forum for interaction between researchers and industrial/ government agencies with information processing requirements. Sessions containing papers from the different disciplines in related applications will be the highlight of this conference. Papers that investigate advantages/disadvantages of computational intelligence solutions in specific real-world applications will be presented as oral and posters. The poster session will contain papers by the session chairs to allow interaction by attendees in small groups. Papers that clearly state existing problems in information processing that could potentially be solved by computational intelligence techniques will also be considered. Sessions will concentrate on: comparative performance in applications of target recognition, object recognition, speech processing, speaker identification, co-channel processing, signal processing in realistic environments, robotics, process control, and image processing demonstrations of properties and limitations of existing or new computational intelligence techniques as shown by or related to an application environments for development of computational intelligence solutions hardware implementation technologies that are either general purpose or application specific knowledge acquisition and representation physiologically motivated information processing and representation independent component analyses (ICA) generalizing principal component analyses (PCA) innovative applications of computational intelligence to solve real-world problems with Receiver Operation Characteristics (ROC). Special Instructions to Authors Oral Presentations are scheduled for Monday and Tuesday with poster sessions scheduled Tuesday evening. On the occasion of NASA's 40th Anniversary, Wednesday will be devoted to joint sessions on Remote Sensing using both Computational Intelligence and Wavelet Analysis. Honorary co-chairs: William J. Campbell, Milton Halem, NASA Goddard Space Flight Ctr. Due to the limited number of oral sessions, we cannot accommodate requests for oral-only presentations without prior approval of the Conference Chair. Any program committee member can guarantee acceptance of brief oral overviews followed by poster interactive presentations. Poster submission will be encouraged with the popup short talks and the Best Poster Award. There will be no differentiation between poster and oral papers in the proceedings. Please indicate your preference for oral or poster sessions. Abstract Submissions Information On-Site Abstract Due Date: 13 September 1999 On-Site Manuscript Due Date: 31 January 2000 To receive a complete Call for Papers via postal mail, or to request an Advance Technical Program for any of these conferences (when available), please contact SPIE Phone: +1 360/676-3290. Fax: +1 360/647-1445. E-mail: OR at spie.org For further information please contact: http://www.spie.org Paul E. Keller, PhD Conference Co-Chair Paul.Keller at pnl.gov From sirosh at hnc.com Wed Aug 11 23:19:39 1999 From: sirosh at hnc.com (Sirosh, Joseph) Date: Wed, 11 Aug 1999 20:19:39 -0700 Subject: Neural Networks/Machine Learning Position at HNC Software Inc Message-ID: <72A838A51366D211B3B30008C7F4D36301773BE5@pchnc.hnc.com> > POSITION: Staff Scientist/Sr. Staff Scientist > BUSINESS UNIT: HNC Advanced Technology Solutions > LOCATION: San Diego, CA > NUMBER: A003SDW1 > > Duties/Job Description: > Develop innovative solutions to a wide variety of technical problems using > various data mining techniques and statistics. Projects may include > fundamental research (e.g. new data mining technologies, multimedia and > web mining, mining temporal data) and applications to business problems in > the financial, internet, telecommunications, retail or insurance > industries. Opportunity to contribute to the evaluation of new, > externally-developed technologies and explore new business models. > > Required Qualifications (Experience/Skills): > MS/Ph.D. in Computer Science, Engineering, Statistics, Math, or related > field. Broad experience applying data mining techniques, neural networks, > statistics, pattern recognition, nonlinear optimization and/or genetic > algorithms to real-world data. Ability to work independently and research > innovative solutions to challenging technical problems. Programming > experience in C/C++ and Unix. Familiarity with statistical packages and > computer software systems such as SAS, SPLUS, Matlab, Java, Tcl/Tk. Good > oral and written communications skills, both in terms of interacting with > customers and with co-workers. > > Preferred Qualifications: > Ph.D. with established research expertise in one or more of the above > areas. Significant experience solving business problems involving retail, > financial, or internet data mining. Substantial expertise with large > business data sets. Familiarity with products in any or all of HNC's > business units. Good Unix scripting and rapid prototyping skill. > > Careers at HNC Software Inc: > Headquartered in San Diego, California, HNC Software Inc. (Nasdaq: HNCS) > is the world's leading provider of Predictive Software Solutions for > service industries, including financial, retail, insurance, Internet, and > telecommunications. It is HNC's employment philosophy to create a dynamic > work environment that allows each employee to feel challenged and > experience personal growth that maximizes each person's potential. HNC > also offers a comprehensive array of employee benefits including stock > options, employee stock purchase plan, competitive health benefits, 401(k) > plans and tuition support for continuing education. > > Apply Online: http://www.hnc.com/careers/index.html > By Email: hnc at webhire.com > By Fax: (800) 438-0957 > By Mail: > HNC Software Inc. > c/o Resume Processing Center > P.O. Box 828 > Burlington, MA 01803 > > Please reference job number: A003SDW1 > > > > From jose at psychology.rutgers.edu Fri Aug 13 07:27:51 1999 From: jose at psychology.rutgers.edu (stephen jose hanson) Date: Fri, 13 Aug 1999 07:27:51 -0400 Subject: COGNITIVE SCIENCE/COGNITIVE NEUROSCIENCE FELLOWSHIPS --RUTGERS-Newark Message-ID: <37B40137.97E12464@kreizler.rutgers.edu> PSYCHOLOGY GRADUATE PROGRAM- Newark Campus GRADUATE RESEARCH FELLOWSHIPS. Fall 99 & Fall 00. The graduate program in COGNITIVE SCIENCE and COGNITIVE NEUROSCIENCE seeks students for FALL 99 & FALL 00. Interested applicants from Psychology, Computer Science or Cognitive Science undergrad programs are encouraged to apply. These fellowships are competitive and provide comprehensive training in computation, neuro-imaging and cognitive science/perception research. Please send enquiries and applications to Professor S. J. Hanson, Chair, Department of Psychology Rutgers University, Newark, NJ 07102. Please make an Email enquiry to gradpgm at tractatus.rutgers.edu also please see our web page for more information on the graduate faculty and program http://www.psych.rutgers.edu From jfgf at eng.cam.ac.uk Fri Aug 13 10:04:34 1999 From: jfgf at eng.cam.ac.uk (J.F. Gomes De Freitas) Date: Fri, 13 Aug 1999 15:04:34 +0100 (BST) Subject: MCMC and SMC model selection Message-ID: Dear colleagues, The following papers and Matlab software on MCMC algorithms for batch and on-line learning are now available from my website: http://svr-www.eng.cam.ac.uk/~jfgf/publications.html http://svr-www.eng.cam.ac.uk/~jfgf/software.html KEYWORDS: Reversible jump MCMC, model selection, sequential Monte Carlo, particle filters, AIC, MDL, simulated annealing, robust priors, geometric convergence proofs. PAPER 1: Sequential Bayesian Estimation and Model Selection Applied to Neural Networks. Technical report CUED/F-INFENG/TR 341, Cambridge University Department of Engineering, May 1999. PAPER 2: Robust Full Bayesian Learning for Neural Networks. Technical report CUED/F-INFENG/TR 343, Cambridge University Department of Engineering, May 1999. The abstracts follow: Paper 1: ======= In this paper, we address the complex problem of sequential Bayesian estimation and model selection. This problem does not usually admit any type of closed-form analytical solutions and, as a result, one has to resort to numerical methods. We propose here an original sequential simulation-based strategy to perform the necessary computations. It combines sequential importance sampling, a selection procedure and reversible jump MCMC moves. We demonstrate the effectiveness of the method by applying it to radial basis function networks. The approach can be easily extended to other interesting on-line model selection problems. Paper 2: ======= In this paper, we propose a hierarchical full Bayesian model for neural networks. This model treats the model dimension (number of neurons), model parameters, regularisation parameters and noise parameters as random variables that need to be estimated. We develop a reversible jump Markov chain Monte Carlo (MCMC) method to perform the necessary computations. We find that the results obtained using this method are not only better than the ones reported previously, but also appear to be robust with respect to the prior specification. In addition, we propose a novel and computationally efficient reversible jump MCMC simulated annealing algorithm to optimise neural networks. This algorithm enables us to maximise the joint posterior distribution of the network parameters and the number of basis function. It performs a global search in the joint space of the parameters and number of parameters, thereby surmounting the problem of local minima. We show that by calibrating the full hierarchical Bayesian prior, we can obtain the classical AIC, BIC and MDL model selection criteria within a penalised likelihood framework. Finally, we present a geometric convergence theorem for the algorithm with homogeneous transition kernel and a convergence theorem for the reversible jump MCMC simulated annealing method. I hope some of you find them interesting and, as always, feedback of all sorts is most welcome. Nando _______________________________________________________________________________ JFG de Freitas (Nando) Speech, Vision and Robotics Group Information Engineering Cambridge University CB2 1PZ England http://svr-www.eng.cam.ac.uk/~jfgf Tel (01223) 302323 (H) (01223) 332754 (W) _______________________________________________________________________________ From POCASIP at aol.com Fri Aug 13 22:09:48 1999 From: POCASIP at aol.com (POCASIP@aol.com) Date: Fri, 13 Aug 1999 22:09:48 EDT Subject: R&D position in DSP & NeuroControl in California Message-ID: The Advanced Signal and Image Processing Laboratory of Intelligent Optical Systems Inc. (IOS) is looking for a candidate who has expertise and experience in the following two areas: 1. Digital Signal Processing and 2. NeuroControl (Nonlinear Adaptive Control) + Knowledge of electronic (CMOS) design, and programming fluency in C++ and Java are important assets. + Experience in solving real-world problems in a wide variety of applications is a definite plus. The activities of the Advanced Signal and Image Processing Laboratory include system control, hazardous waste analysis, skin injury diagnosis, silicon wafer inspection, food quality control, and target recognition, using neural computation implementations in software and hardware. IOS is a rapidly growing dynamic high-tech R&D company with a focus on commercializing optical sensors and advanced information processing. Ii employs about 35 people, including 13 scientists from a variety of backgrounds. We are located in Torrance, California, which is a pleasant seaside town with a high standard of living and year-round perfect weather. Please send your application including curriculum vitae, and three references, in ASCII only, by e-mail to POCASIP at aol.com E. Fiesler From X.Yao at cs.bham.ac.uk Mon Aug 16 07:32:24 1999 From: X.Yao at cs.bham.ac.uk (Xin Yao) Date: Mon, 16 Aug 1999 12:32:24 +0100 (BST) Subject: PhD scholarship/studentship in EC+NNs Message-ID: The following PhD scholarship/studentship is available from the School of Computer Science, the University of Birmingham, UK. For more information about this EPSRC CASE Studentship, please go to http://www.cs.bham.ac.uk/~pjh/prospectus/research/xy_bt.html For more information about the School, please go to http://www.cs.bham.ac.uk ---------------------------------------------------------------------------- EPSRC CASE Studentship on Combinations Between Evolutionary Computation and Neural Networks supported by BT Applications are invited for a studentship starting in Autumn 1999 under the supervision of Professor Xin Yao and in co-operation with BT Laboratories' Future Technologies Group. Applications are restricted to students with a " relevant connection" to the European Union. For the successful candidate, the scholarship will pay their tuition fees and (if they have a "relevant connection" with the United Kingdom) a tax-free maintenance allowance of between GBP10,620 and GBP12,130 per year, depending on age. More details: http://www.cs.bham.ac.uk/~pjh/prospectus/research/xy_bt.html Enquiries: Prof Xin Yao (x.yao at cs.bham.ac.uk) Dr Peter Hancox (P.J.Hancox at bham.ac.uk) ---------------------------------------------------------------------------- From motoda at ar.sanken.osaka-u.ac.jp Tue Aug 17 20:46:41 1999 From: motoda at ar.sanken.osaka-u.ac.jp (Hiroshi Motoda) Date: Wed, 18 Aug 1999 09:46:41 +0900 Subject: Last CFP: Special Issue of INSTANCE SELECTION for DMKD Journal Message-ID: <19990818004641.AAA21208@[127.0.0.1]> Call for Papers - INSTANCE SELECTION A Special Issue of the Data Mining and Knowledge Discovery Journal http://www.comp.nus.edu.sg/~liuh/dmkd.html Due date: 18 Sept 1999, electronic submission INTRODUCTION Knowledge discovery and data mining (KDD) is growing rapidly as computer technologies advance. However, no matter how powerful computers are now or will be in the future, KDD researchers and practitioners must consider how to manage ever-growing data which is, ironically, due to the extensive use of computers and ease of data collection with computers. Many different approaches have been used to address the data explosion issue. Algorithm scale-up is one and data reduction is another. Instance, example, or tuple selection is about algorithms that select or search for a representative portion of data that can fulfill a KDD task as if the whole data is used. Instance selection is directly related to data reduction and becomes increasingly important in many KDD applications due to the need for processing efficiency and/or storage efficiency. One of the major means of instance selection is sampling whereby a sample is selected for testing and analysis, and randomness is a key element in the process. Instance selection also covers other methods that require search. Examples can be found in density estimation - finding the representative instances (data points) for each cluster, and boundary hunting - finding the critical instances to form boundaries to differentiate data points of different classes. Other important issues related to instance selection extend to unwanted precision, focusing, concept drifts, noise/outlier removal, data smoothing, etc. OBJECTIVES This special issue on instance selection brings researchers and practitioners together to report new developments and applications, share hard-learned experiences to avoid similar pitfalls, and shed light on the future development of instance selection. Several critical questions are interesting to practitioners in KDD, and practically useful in real-life applications: * What are the existing methods? * Are they the same or just different names coined by researchers in different fields? * Are they application dependent or stand-alone? * Are new methods needed? * If there is no generic selection algorithm, are these algorithms specific to tasks such as classification, clustering, association, parallelization? * Are there common and reusable components in instance selection methods? * How can we reconfigure some components of instance selection for a particular task/application? * What are the new challenging issues of instance selection in the context of KDD? Sensible answers to these questions can greatly advance the field of KDD in handling large databases. This special issue hopes to answer these questions and to provide an easy reference point for further research and development. COVERAGE All aspects of instance selection will be considered: theories, methodologies, algorithms, and applications. Also studied are issues such as costs of selection, the gains and losses due to the selection, how to balance the gains and losses, and when to use what. Researchers and practitioners in KDD-related fields (Statistics, Databases, Machine Learning, etc.) are encouraged to submit their work to this special issue to share and exchange ideas and problems in any forms: survey, research manuscript, experimental comparison, theoretical study, or report on applications. IMPORTANT DATES 18 September, 1999 - Submissions due 15 November, 1999 - Reviews due (mainly peer review and the guest editors will review all the submissions) 22 Janurary, 2000 - Revised papers due 13 February, 2000 - To Editor-in-Chief FORMAT and PAGE LIMIT Each submission should be no more than 25 pages, have a line spacing of 1.5, use no smaller than a 12pt font, and have at least a 1 inch margin on each side. CONTACT INFORMATION Please direct any enquiries to the guest editors: Huan Liu, liuh at comp.nus.edu.sg, National University of Singapore Hiroshi Motoda, motoda at sanken.osaka-u.ac.jp, Osaka University, Japan. Please submit your work electronically (postscript file) to either guest editor. If you have to submit it in hard copy, please discuss it with the guest editors first. INFORMATION about the JOURNAL Data Mining and Knowledge Discovery, Kluwer Academic Publishers. http://www.wkap.nl/journalhome.htm/1384-5810 Editors-in-Chief: Usama Fayyad, Gregory Piatetsky-Shapiro, Heikki Mannila. From rknott at cup.cam.ac.uk Tue Aug 17 06:47:06 1999 From: rknott at cup.cam.ac.uk (Richard Knott) Date: Tue, 17 Aug 1999 10:47:06 +0000 Subject: book announcement: Neural Network Learning Message-ID: Neural Network Learning Theoretical Foundations Martin Anthony London School of Economics and Political Science and Peter Bartlett Australian National University This book describes recent theoretical advances in the study of artificial neural networks. It explores probabilistic models of supervised learning problems, and addresses the key statistical and computational questions. Research on pattern classification with binary-output networks is surveyed, including a discussion of the relevance of the Vapnik-Chervonenkis dimension, and calculating estimates of the dimension for several neural network models. A model of classification by real-output networks is developed, and the usefulness of classification with a 'large margin' is demonstrated. The authors explain the role of scale-sensitive versions of the Vapnik-Chervonenkis dimension in large margin classification, and in real prediction. They also discuss the computational complexity of neural network learning, describing a variety of hardness results, and outlining two efficient constructive learning algorithms. The book is self-contained and is intended to be accessible to researchers and graduate students in computer science, engineering, and mathematics. Contents: 1. Introduction; Part I. Pattern Recognition with Binary-output Neural Networks: 2. The pattern recognition problem; 3. The growth function and VC-dimension; 4. General upper bounds on sample complexity; 5. General lower bounds; 6. The VC-dimension of linear threshold networks; 7. Bounding the VC-dimension using geometric techniques; 8. VC-dimension bounds for neural networks; Part II. Pattern Recognition with Real-output Neural Networks: 9. Classification with real values; 10. Covering numbers and uniform convergence; 11. The pseudo-dimension and fat-shattering dimension; 12. Bounding covering numbers with dimensions; 13. The sample complexity of classification learning; 14. The dimensions of neural networks; 15. Model selection; Part III. Learning Real-Valued Functions: 16. Learning classes of real functions; 17. Uniform convergence results for real function classes; 18. Bounding covering numbers; 19. The sample complexity of learning function classes; 20. Convex classes; 21. Other learning problems; Part IV. Algorithmics: 22. Efficient learning; 23. Learning as optimisation; 24. The Boolean perceptron; 25. Hardness results for feed-forward networks; 26. Constructive learning algorithms for two-layered networks. 1999 228 x 152 mm 416pp 0 521 57353 X Hardback For further information see http://www.cup.cam.ac.uk or http://www.cup.org **************************************************************************** Richard Knott STM Marketing Dept. Cambridge University Press The Edinburgh Building Cambridge CB2 2RU, UK email:rknott at cup.cam.ac.uk tel: ++44 (0)1223 325916 fax: ++44 (0)1223 315052 Web: http://www.cup.cam.ac.uk **************************************************************************** From saadd at aston.ac.uk Wed Aug 18 06:31:27 1999 From: saadd at aston.ac.uk (David Saad) Date: Wed, 18 Aug 1999 11:31:27 +0100 (BST) Subject: Post-doc positions Message-ID: Neural Computing Research Group ------------------------------- School of Engineering and Applied Sciences Aston University, Birmingham, UK TWO POSTDOCTORAL RESEARCH FELLOWSHIPS ------------------------------------- There are two postdoctoral research fellowships at the NCRG available for October 1999 or as soon as possible thereafter. *** Full details at http://www.ncrg.aston.ac.uk/ *** 1. Analysis of Learning in Support Vector Machines ----------------------------------------------- The Neural Computing Research Group at Aston is looking for a highly motivated individual for a 2 year postdoctoral research position in the area of `Analysis of Learning in Support Vector Machines'. The emphasis of the research will be on applying a theoretically well-founded approach based on methods adopted from statistical mechanics to analyse learning in support vector machines. Potential candidates should have strong mathematical and computational skills, with a background in statistical mechanics and support vector machines. Conditions of Service --------------------- Salaries will be up to point 11 on the RA 1A scale, currently 21,815 UK pounds. The salary scale is subject to annual increments. How to Apply ------------ If you wish to be considered for this Fellowship, please send a full CV and publications list, including full details and grades of academic qualifications, together with the names of 3 referees, to: Dr. Manfred Opper Neural Computing Research Group School of Engineering and Applied Sciences Aston University Birmingham B4 7ET, U.K. Tel: 0121 333 4631 Fax: 0121 333 4586 e-mail: opperm at aston.ac.uk e-mail submission of postscript files is welcome. Closing date: 13 September, 1999. =========================================================================== 2. Searching for Patterns in Activity across Multiple Targets ---------------------------------------------------------- This 3 year post aims to develop novel data visualisation and modelling techniques for analysing large biological activity databases. The work will be carried out together with a PhD student funded by Pfizer. Candidates should have strong mathematical and computational skills; a background in biological sciences would be an advantage. Conditions of Service --------------------- Salaries will be up to point 6 on the RA 1A scale, currently 17,570 UK pounds per annum. The salary scale is subject to annual increments. How to Apply ------------ If you wish to be considered for this Fellowship, please send a full CV and publications list, including full details and grades of academic qualifications, together with the names of 3 referees, to: Dr. Ian Nabney Neural Computing Research Group School of Engineering and Applied Sciences Aston University Birmingham B4 7ET, U.K. Tel: 0121 333 4631 Fax: 0121 333 4586 e-mail: i.t.nabney at aston.ac.uk e-mail submission of postscript or pdf files is welcome. Closing date: 13 September, 1999. From rod at dcs.gla.ac.uk Wed Aug 18 11:53:52 1999 From: rod at dcs.gla.ac.uk (Roderick Murray-Smith) Date: Wed, 18 Aug 1999 16:53:52 +0100 Subject: Post-doc position at University of Glasgow Message-ID: <37BAD710.F449D98@dcs.gla.ac.uk> Vacancy: Post-doctoral research assistant at University of Glasgow, Dept. of Computing Science Applications are invited for a Post-doctoral Research Assistantship (RA-1A, salary range 16,286-18,185, depending on experience, up to a maximum of scale point 6) at the University of Glasgow. The appointee will be based in the Department of Computing Science. The work will be directed by R. Murray-Smith (Computing Science), D. M. Titterington (Statistics) and K. J. Hunt (Mechanical Engineering). The appointment is for three years, funded by an EPSRC project "Modern Statistical Approaches to off-equilibrium modelling for nonlinear system control", which starts on 1st January 2000, or as soon as possible thereafter. This project aims to develop modern statistical theory and methodology to improve the performance and interpretability of the multiple-model approach to modelling and control of dynamic systems in engineering. The primary application will be in rehabilitation engineering, where improved modelling and control methods are needed. Candidates should ideally have a strong statistics background. Skills in the following areas will be advantageous: Markov-Chain Monte Carlo methods, Bayesian inference, time series modelling and control. The candidate should also be keen on applying leading-edge techniques to challenging problems, and dealing with the concrete programming work needed to produce successful results. The work will involve algorithm implementation, application and some system development in MATLAB. Further details available at: http://www.dcs.gla.ac.uk/~rod/vacancy.htm http://www.dcs.gla.ac.uk/~rod/MSAFCproject.htm Please send a letter of application and c.v. to Roderick Murray-Smith, rod at dcs.gla.ac.uk (informal enquiries by e-mail welcome) before the end of September 1999. Please note that because of work permit restrictions, non European Union/European Economic Area nationals can only be considered if no suitably qualified EU/EEA national can be found. Postal address: Roderick Murray-Smith, Department of Computing Science, Glasgow University Glasgow G12 8QQ Scotland UK Fax. +44 141 330 4913 http://www.dcs.gla.ac.uk/~rod From allinson at umist.ac.uk Thu Aug 12 13:04:25 1999 From: allinson at umist.ac.uk (Nigel M. Allinson) Date: Thu, 12 Aug 1999 18:04:25 +0100 (BST) Subject: Workshop on Self-Organising Systems Message-ID: Dear All, Emergent Behaviour Computing - one of EPSRCs Emerging Computing networks- is holding its first two-day workshop on "Self-Organising Systems - Future Prospects for Computing" at UMIST, Manchester, England on 28/29 October, 1999 The Workshop covers divers aspects of self-organising systems - both natural and artificial, and aims to present the best of international and UK activity. The overall focus is the current and future application of self-organisation as an alternate paradigm for "intelligent" computation. The Workshop represents an important opportunity for those active, or just interested, in self-organising system research and application to hear about current work, discuss future directions and priorities, and form research contacts. There are several leading overseas speakers, and contributions from the UK community are invited. Details of submission and registration can be obtained from http://images.ee.umist.ac.uk/emergent. -- | Prof. Nigel M. Allinson |______________________________________ Dept. of Electrical Engineering and Electronics UMIST, Manchester, M60 1QD, England ________ | | allinson at umist.ac.uk | Office Phone: (+44) (0) 161 200 4641 | Office Fax: (+44) (0) 161 200 4784 | Home Phone: (+44) (0) 1904 626756 |______________________________________ | http://images.ee.umist.ac.uk |______________________________________ From isahara at crl.go.jp Sat Aug 21 00:10:38 1999 From: isahara at crl.go.jp (Isahara Hitoshi) Date: Sat, 21 Aug 1999 13:10:38 +0900 Subject: NLPRS'99 Workshop -- Natural Language Processing and Neural Networks Message-ID: <9908210410.AA19824@margaux.crl.go.jp> Dear Colleagues, Attached is the call for papers for the NLPRS'99 workshop of Natural Language Processing and Neural Networks. Please help us to distribute this to people who will be interested in. --------------------------------------------------------------------------- Call for Papers NLPRS'99 Workshop Natural Language Processing and Neural Networks Beijing, China, November 5, 1999 http://korterm.kaist.ac.kr/~nlprs99/ The artificial neural networks (ANN) began to be an attract approach to natural language processing (NLP) since several works on parsing were done using ANN techniques in 1985. Since then, with the boom of NLP research based on very large corpora, the ANN, as a powerful parallel and distributed learning/processing machine, attract a more great deal of attention from both the ANN and NLP researchers and have been successfully used in many areas of NLP. This workshop will provide a forum for researchers in both the areas of ANN and NLP who are interested in advancing the state in developing NLP techniques by using ANN approach. Submissions are invited on all NLP topics in the context of using ANN techniques. The workshop review and acceptance will be based on a two-page extended summary (2000 words or less). The summary must be accompanied by paper title and author information including full names, affiliations of all authors and the postal mailing address and email of the corresponding author. Submit by email to qma at crl.go.jp IMPORTANT DATES Summary submission deadline: September 15 Notification of acceptance: September 30 Camera ready papers due: October 15 Inquiries concerning the workshop can be sent to one of the organisers either by email to qma at crl.go.jp or by post to the following address: Dr. Qing Ma Intelligent Processing Section Kansai Advanced Research Center Communications Research Laborotory Ministry of Posts and Telecommunications 588-2, Iwaoka, Nishi-ku, Kobe, 651-2401, Japan --------------------------------------------------------------------------- Dr. Hitoshi Isahara Dr. Qing Ma Intelligent Processing Section Kansai Advanced Research Center Communications Research Laborotory Ministry of Posts and Telecommunications 588-2, Iwaoka, Nishi-ku, Kobe, 651-2401, Japan From kenm at sunrae.sscl.uwo.ca Sat Aug 21 00:37:09 1999 From: kenm at sunrae.sscl.uwo.ca (kenm@sunrae.sscl.uwo.ca) Date: Sat, 21 Aug 1999 00:37:09 -0400 (EDT) Subject: Faculty Position in Cognition at Western Ontario Message-ID: FACULTY POSITION IN COGNITION. The University of Western Ontario, Department of Psychology invites applications for a tenure-track position for a Cognitive Psychologist at the Assistant Professor level. Individuals with research interests in any area of Cognition, including memory, language, computational modelling, concepts and categorization, cognitive development, or animal cognition are invited to apply. Duties will include maintaining an active research program, graduate student supervision, and graduate and undergraduate teaching. The Cognition Program at the University of Western Ontario emphasizes a multidisciplinary approach to research in the cognitive sciences, featuring close ties with researchers in artificial intelligence, linguistics, visual neuroscience, neuroimaging, and evolutionary psychology. Applicants should submit a vita, copies of representative publications and arrange to have three letters of recommendation sent to Dr. Jim Olson, Chair, Department of Psychology, The University of Western Ontario, London, Ontario, Canada N6A 5C2 by January 1, 2000. This position is subject to budgetary approval. The scheduled starting date is July 1, 2000. In accordance with Canadian Immigration requirements, first priority will be given to applicants who are Canadian Citizens or 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 tommi at ai.mit.edu Sat Aug 21 14:45:27 1999 From: tommi at ai.mit.edu (Tommi Jaakkola) Date: Sat, 21 Aug 1999 14:45:27 -0400 Subject: paper available: maximum entropy discrimination Message-ID: The following technical report (MIT AITR-1668) is now available on-line Maximum entropy discrimination Jaakkola T., Meila M., Jebara T. We present a general framework for discriminative estimation based on the maximum entropy principle and its extensions. All calculations involve distributions over structures and/or parameters rather than specific settings and reduce to relative entropy projections. This holds even when the data is not separable within the chosen parametric class, in the context of anomaly detection rather than classification, or when the labels in the training set are uncertain or incomplete. Support vector machines are naturally subsumed under this class and we provide several extensions. We are also able to estimate exactly and efficiently discriminative distributions over tree structures of class-conditional models within this framework. Preliminary experimental results are indicative of the potential in these techniques. http://www.ai.mit.edu/~tommi/publications/maxent.ps.gz 26 pages, about 400KB compressed. Tommi - ====================================================== Tommi Jaakkola MIT Artificial Intelligence Laboratory 545 Technology Square, NE43-735 Cambridge, MA 02139 Tel: (617) 253 0440 Fax: (617) 253 5060 http://www.ai.mit.edu/~tommi ====================================================== From ingber at ingber.com Mon Aug 23 08:21:21 1999 From: ingber at ingber.com (Lester Ingber) Date: Mon, 23 Aug 1999 07:21:21 -0500 Subject: PAPER: ... EEG eigenfunctions of short-term memory Message-ID: <19990823072121.A4177@ingber.com> The draft paper, %A L. Ingber %T Statistical mechanics of neocortical interactions: EEG eigenfunctions of short-term memory %J Behavioral and Brain Sciences %D 2000 %O URL http://www.ingber.com/smni00_eeg_stm.ps.gz is now available at www.ingber.com. Instructions for retrieval are given below. Behavioral and Brain Sciences Commentary on Toward a Quantitative Description of Large-Scale Neo-Cortical Dynamic Function and EEG by Paul Nunez ABSTRACT: This paper focuses on how bottom-up neocortical models can be developed into eigenfunction expansions of probability distributions appropriate to describe short-term memory in the context of scalp EEG. The mathematics of eigenfunctions are similar to the top-down eigenfunctions developed by Nunez, albeit they have different physical manifestations. The bottom-up eigenfunctions are at the local mesocolumnar scale, whereas the top-down eigenfunctions are at the global regional scale. However, as described in several joint papers, our approaches have regions of substantial overlap, and future studies may expand top-down eigenfunctions into the bottom-up eigenfunctions, yielding a model of scalp EEG that is ultimately expressed in terms of columnar states of neocortical processing of attention and short-term memory. Links to informations and utilities for compression/expansion and for viewing and printing PostScript are in http://www.ingber.com/Z_gz_ps_tar_shar.txt Lester ======================================================================== Instructions for Retrieval of Code and Reprints Interactively Via WWW The archive can be accessed via WWW path http://www.ingber.com/ http://www.alumni.caltech.edu/~ingber/ where the last address is a mirror homepage for the full archive. Interactively Via Anonymous FTP Code and reprints can be retrieved via anonymous ftp from ftp.ingber.com. Interactively [brackets signify machine prompts]: [your_machine%] ftp ftp.ingber.com [Name (...):] anonymous [Password:] your_e-mail_address [ftp>] binary [ftp>] ls [ftp>] get file_of_interest [ftp>] quit The 00index file contains an index of the other files. Files have the same WWW and FTP paths under the main / directory; e.g., http://www.ingber.com/MISC.DIR/00index_misc and ftp://ftp.ingber.com/MISC.DIR/00index_misc reference the same file. Electronic Mail If you do not have WWW or FTP access, get the Guide to Offline Internet Access, returned by sending an e-mail to mail-server at rtfm.mit.edu with only the words send usenet/news.answers/internet-services/access-via-email in the body of the message. The guide gives information on using e-mail to access just about all InterNet information and documents. Additional Information Lester Ingber Research (LIR) develops projects in areas of expertise documented in the ingber.com InterNet archive. Limited help assisting people with queries on my codes and papers is available only by electronic mail correspondence. Sorry, I cannot mail out hardcopies of code or papers. Lester ======================================================================== -- Lester Ingber http://www.ingber.com/ http://www.alumni.caltech.edu/~ingber/ From magnus at cs.man.ac.uk Mon Aug 23 10:31:55 1999 From: magnus at cs.man.ac.uk (Magnus Rattray) Date: Mon, 23 Aug 1999 15:31:55 +0100 Subject: Post-doctoral position Message-ID: <37C15B5A.377B33D3@cs.man.ac.uk> Readers of the list may be interested in the following post-doc position, which is jointly offered by the University of Manchester and Rh?ne-Poulenc Rorer. Candidates with experience in neural networks and related machine-learning/visualisation techniques are particularly encouraged to apply. Magnus Rattray, Dept. of Computer Science, University of Manchester, Manchester M13 9PL. -------------------------------------------------------------------- Post-doctoral research associate for gene expression analysis (Rh?ne-Poulenc Rorer and University of Manchester) We are looking for a post-doctoral research associate to work on a 2 year project on the analysis of gene expression patterns from DNA arrays. The work would be done in a collaboration between Rh?ne-Poulenc Rorer and the University of Manchester. The post would provide an ideal opportunity for a mathematically trained scientist to apply their skills to one of the fastest growing and most exciting areas of modern biology. The successful candidate will work primarily at Rh?ne-Poulenc Rorer's site near London and liaise extensively with experimentalists. He/she will be part of a large multidisciplinary team involving biologists and bioinformaticians that is applying and developing state of the art mathematical and computational methods for biologically relevant problems. The ideal candidate would have excellent communication skills, a mathematical background, preferably in areas such as multivariate statistical analysis and pattern recognition, and a strong interest in molecular biology. As an Equal Opportunities Employer, we welcome applications from suitably qualified people from all sections of the community regardless of race, religion, gender or disability. For further details please contact: Dr Burkhard Morgenstern, Rh?ne-Poulenc Rorer Limited, JA3-3 Rainham Road South, Dagenham, Essex. RM10 7XS UK. Email: burkhard.morgenstern at rp-rorer.co.uk From mondada at k-team.com Tue Aug 24 03:20:41 1999 From: mondada at k-team.com (Francesco Mondada) Date: Tue, 24 Aug 1999 09:20:41 +0200 Subject: IKW99 call for participation Message-ID: CALL FOR PARTICIPATION The Heinz Nixdorf Institute, with support from K-Team, organizes the 1ST International KHEPERA Workshop http://ikw99.k-team.com 10th and 11th December 1999, Paderborn, Germany. This workshop aims to bring together researchers from many different fields who utilize the mini-robot Khepera as an experimental platform. The intention is to give a comprehensive overview of the Khepera related work done so far and to provide a forum for scientific exchange. For KHEPERA USERS: The best opportunity to exchange ideas, experience, hardware, software and tips on Khepera. The latest research results and developments will be shown. ******** BRING YOUR KHEPERA ROBOTS for the big clustering demo ******** ******** AND GET A CHANCE TO REPRODUCE ONE OF THEM !!! ******** One of the Khepera robots participating to the demo will be selected and his owner will win a Khepera robot kit offered by K-Team. For NON KHEPERA USERS: The best opportunity to see how to implement real robotics experiences with the standard mobile robot, Khepera, used by more than 350 research groups. Exchange experience and tips with the best Khepera users and developers. This is the only conference where only papers using real robots are accepted! *** PAPERS *** DEMOS *** ROBOTIC NIGHT *** COLLECTIVE ROBOT SHOW *** From d.mareschal at bbk.ac.uk Tue Aug 24 04:47:02 1999 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Tue, 24 Aug 1999 09:47:02 +0100 Subject: models of cognitive development Message-ID: Dear all, The following book chapter may be of interest to readers of this list. It reviews current connectionist modelling efforts with regards to modelling cognitive development. The chapter situates normal and abnormal development within the same framework and illustrates how differences in boundary conditions (constraints) can lead to the emergence of behaviours classified as normal or abnormal. Special attention is paid to models of development in autistic children. Copies of this chapter can be obtained from the following web page: http://www.psyc.bbk.ac.uk/staff/dm.html Self-organization in Normal and Abnormal Cognitive Development Denis Mareschal & Michael S. C. Thomas To appear in: Kalverboer, A. F. & Gramsbergen, A. (2000). Brain and Behaviour in Human Development A source book. Dordecht. Kluwer Academic Publishers. ABSTRACT This chapter discusses self-organization as a motor for cognitive development. Self-organization occurs in systems with many degrees of freedom and is ubiquitous in the brain. The principal means of investigating the role of self-organization in cognitive development is through connectionist computational modeling. Connectionist models are computer models loosely based on neural information processing. We survey a range of models of cognitive development in infants and children and identify the constraints on self-organization that lead to the emergence of target behaviors. A survey of connectionist models of abnormal cognitive development illustrates how deviations in these constraints can lead to the development of abnormal behaviors. Special attention is paid to models of development in autistic children. ================================================= Dr. Denis Mareschal Centre for Brain and Cognitive Development Department of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 171 631-6582/6207 fax +44 171 631-6312 http://www.psyc.bbk.ac.uk/staff/dm.html ================================================= From triesch at cs.rochester.edu Wed Aug 25 09:58:32 1999 From: triesch at cs.rochester.edu (Jochen Triesch) Date: Wed, 25 Aug 1999 09:58:32 -0400 Subject: Thesis on Robotic Gesture Recognition / Sensory Integration available Message-ID: <199908251358.JAA01357@tbird.cs.rochester.edu> Dear connectionists, the following thesis is available from my homepage at http://www.cs.rochester.edu/u/triesch/home.html The thesis was prepared under the supervision of Prof. C. von der Malsburg at the Institut fuer Neuroinformatik, Ruhr-Universitaet Bochum, Germany. http://www.neuroinformatik.ruhr-uni-bochum.de Best Regards, Jochen Triesch Titel: Vision-Based Robotic Gesture Recognition Abstract: Vision in complex environments is a big scientific challenge for two reasons. First, in complex environments it is not possible to segment a scene into the constituent objects on the basis of simple cues. Second, unpredictable changes in the environment must be tolerated. A proper domain for investigating these problems is robotic gesture recognition, since the two problems arise there naturally. Furthermore, gesture recognition holds the promise of making man-machine interaction more natural and intuitive. The principal idea for tackling the first problem is the integration of information stemming from different cues. In the first part of this thesis, methods for tracking human hands, finding fingertips and recognizing hand postures despite complex backgrounds are presented, which owe their robustness to the integration of different complementary cues. The components have been integrated into a user-independent gesture interface implemented on an anthropomorphic robot. The second part is concerned with the adaptive integration of different cues, aimed at addressing the second problem. A model of adaptive sensory integration in the brain is proposed, which relates the psychophysical phenomena of suppression and recalibration of discordant sensory information to a self-organized adaptation employing fast synaptic plasticity mechanisms. Finally, the idea of self-organized adaptation is applied to the tracking of human faces in a scene. To this end, an adaptive tracking scheme is proposed which combines different cues in a "democratic" manner. _______________________________________________________________________________ Jochen Triesch Computer Science Department, University of Rochester RC PO Box 270226, Rochester, NY 14627-0226, USA phone : +1 (716) 275-2957, fax: +1 (716) 461-2018 email : triesch at cs.rochester.edu URL : www.cs.rochester.edu/u/triesch/ _______________________________________________________________________________ From lemm at lorentz.uni-muenster.de Wed Aug 25 05:37:42 1999 From: lemm at lorentz.uni-muenster.de (Joerg_Lemm) Date: Wed, 25 Aug 1999 11:37:42 +0200 (MEST) Subject: New Papers on Bayesian Inverse Quantum Theorie Message-ID: Connectionists at cs.cmu.edu Two papers (MS-TP1-99-6 and MS-TP1-99-10) applying Bayesian methods to inverse problems in quantum mechanics ("empirical learning of potentials") are now available on-line at http://pauli.uni-muenster.de/~lemm/ Joerg ---------------------------------------------------------------------------- 1. A Bayesian Approach to Inverse Quantum Statistics. (MS-TP1-99-6) J. C. Lemm, J. Uhlig, A. Weiguny A nonparametric Bayesian approach is developed to determine quantum potentials from empirical data for quantum systems at finite temperature. The approach combines the likelihood model of quantum mechanics with a priori information on potentials implemented in form of stochastic processes. Its specific advantages are the possibilities to deal with heterogeneous data and to express a priori information explicitly in terms of the potential of interest. A numerical solution in maximum a posteriori approximation is obtained for one--dimensional problems. The results depend strongly on the implemented a priori information. http://xxx.lanl.gov/ps/cond-mat/9907013 or http://pauli.uni-muenster.de/~lemm/papers/iqs.ps.gz 4 pages, 6 figures ---------------------------------------------------------------------------- 2. Hartree-Fock Approximation for Inverse Many-Body Problems. (MS-TP1-99-10) J. C. Lemm, J. Uhlig A new method is presented to reconstruct the potential of a quantum mechanical many--body system from observational data, combining a nonparametric Bayesian approach with a Hartree--Fock approximation. A priori information is implemented as a stochastic process, defined on the space of potentials. The method is computationally feasible and provides a general framework to treat inverse problems for quantum mechanical many--body systems. http://xxx.lanl.gov/ps/nucl-th/9908056 or http://pauli.uni-muenster.de/~lemm/papers/ihf.ps.gz 4 pages, 2 figures ======================================================================== Joerg Lemm Universitaet Muenster Email: lemm at uni-muenster.de Institut fuer Theoretische Physik I Phone: +49(251)83-34922 Wilhelm-Klemm-Str.9 Fax: +49(251)83-36328 D-48149 Muenster, Germany http://pauli.uni-muenster.de/~lemm ======================================================================== From riedml at ira.uka.de Thu Aug 26 18:23:48 1999 From: riedml at ira.uka.de (Martin Riedmiller) Date: Thu, 26 Aug 99 18:23:48 EDT Subject: Job announcement: University of Karlsruhe Message-ID: <"i11s5.ira..851:26.08.99.16.23.51"@ira.uka.de> The following announces a job opportunity for a postdoc or a PhD candidate at the University of Karlsruhe, Germany. Since we are looking for a German speaking applicant, a German version is attached. The University of Karlsruhe, Computer Science Department, is looking for a (post-doc) research assistant in the domain Computability and Complexity Theory of adaptive Systems (Prof.\ W.\ Menzel) The salary is BAT II a. We are looking for a highly qualified mathematician or computer scientist with experience in at least one of the following domains: - Computability and Complexity - Theory of adaptive Systems - Probability Theory Please send your application to Prof. Dr. W. Menzel Institut f\"ur Logik, Komplexit\"at und Deduktionssysteme Universit\"at Karlsruhe 76128 Karlsruhe ------------------------- An der Fakult\"at Informatik, Universit\"at Karlsruhe, ist im Bereich Berechenbarkeit und Komplexit\"at,\\ Theorie adaptiver Systeme\\ (Prof.\ W.\ Menzel) eine Stelle BAT IIa eines wissenschaftlichen Mitarbeiters/einer wissenschaftlichen Mitarbeiterin zu besetzen. Bewerber/Bewerberinnen sollten einen sehr guten Hochschulabschlu\ss{} in Informatik oder in Mathematik mit starkem Informatikbezug besitzen. Vorteilhaft sind vertiefte Kenntnisse in mindestens einem der Gebiete - Berechenbarkeit/Komplexit\"at - Adaptive Systeme, wie etwa neuronale Netze, Support Vector Machines, Evolution\"are Algorithmen - Stochastik. F\"ur promovierte Bewerber/Bewerberinnen besteht die M\"oglichkeit einer Einstellung als wissenschaftliche(r) Assistent(in) (C1). Ansonsten ist die M\"oglichkeit zur Promotion gegeben. Bitte richten Sie Ihre Bewerbung an Prof. Dr. W. Menzel Institut f\"ur Logik, Komplexit\"at und Deduktionssysteme Universit\"at Karlsruhe 76128 Karlsruhe From rn519343 at exchange.UnitedKingdom.NCR.COM Thu Aug 26 07:45:40 1999 From: rn519343 at exchange.UnitedKingdom.NCR.COM (Nakisa, Ramin) Date: Thu, 26 Aug 1999 12:45:40 +0100 Subject: Research Fellowship at NCR Knowledge Lab Message-ID: Reminder: Closing date is in five days. NCR's Knowledge Lab conducts leading-edge research in the areas of data mining, consumer behaviour, emerging technologies and electronic commerce. Research is carried out in close collaboration with a group of banking and academic research partners. Our research interests are wide-ranging and interdisciplinary within the financial services industry. In the area of data mining the Knowledge Lab is investigating the potential of Bayesian statistics applied to very large data sets. The Knowledge Lab invites applicants for a Knowledge Lab Research Fellowship. The fellowship will be awarded to conduct innovative research in developing and applying new machine learning methods to banking problems. Candidates will have a Ph.D. in a numerate discipline and sound knowledge of the theory and computational practice of analysing large data sets. The ability to code fluently in C/C++ is a prerequisite. Fellows are expected to carry out research of an exceptionally high standard and to publish in leading international journals. The fellowship will be for an initial period of one year with the possibility of a permanent position. The fellow will be based in the Knowledge Lab in central London. Salaries will be above the post-doctoral level (which ranges from ?21,293 to ?28,919). The fellowship offers a unique opportunity to both conduct leading-edge research and to also gain experience of the application of research with a world-leading technology company. NCR is the world's leading provider of electronic banking solutions and massively parallel computing for data warehousing. Applicants should send a full CV, indicating their research interests, to Dr. Ramin Nakisa, The Knowledge Lab, NCR Financial Solutions Limited, 206 Marylebone Road, London NW1 6LY. Closing date for applications September 1st, 1999 with a starting date of October 1st, 1999. Informal inquiries may be made by phone to 0171 725 8144 or email ramin.nakisa at unitedkingdom.ncr.com. For more information on the Knowledge Lab, please visit our web site at http://www.knowledgelab.com. From grb at neuralt.com Fri Aug 27 05:06:49 1999 From: grb at neuralt.com (George Bolt) Date: Fri, 27 Aug 1999 10:06:49 +0100 Subject: Neural Scientist Position at Neural Technologies Limited Message-ID: Neural Scientists Wanted! Do you want to apply your neural computing skills to solve real-world problems? Neural Technologies can offer you this opportunity - just some of the areas we work in are: * Telecommunications - fraud, churn, etc. * Finance - credit scoring, risk management, instrument trading, etc. * Marketing - modelling and analysis * Data Analysis and Visualisation - virtual reality Neural Technologies Limited is the leading UK company working in the application and exploitation of neural computing across a wide range of industrial and commercial environments. We are looking not only for high standards of professionalism but also technical innovation second to none. Self confidence, adaptability and communication skills are as important as the technical skills. You will be working within a highly motivated team in our offices in Petersfield, Hampshire. Required skills are: * Well versed in neural network and other advanced algorithm development and their practical application, should have at least 2 years applied knowledge of at least 2 of the following: * MLP, RBF, Decision Trees, etc. * Kohonen/SOM, LVQ, etc. * Rule induction and inferencing, case-based reasoning, etc. * Evolution, GA's, etc. * Optimisation * Experienced using MATLAB * Proven problem solving abilities and system design * Good mathematical background * Able to code in C or C++ within the PC environment Experience of the following would also be an advantage: * Knowledge of conventional statistics * Signal processing techniques (e.g. speech) * Application domains (credit scoring, fraud analysis, telecommunications, banking and finance) All candidates should be working at a practical research level or have extensive industrial experience. A keen view to the commercial realities of working within a small, but fast growing, company is required. Neural Technologies Limited operate a non-smoking policy. Contact: Kirsten Tait Human Resources Executive Neural Technologies Limited Bedford Road PETERSFIELD Hampshire GU32 3QA Phone: +44 (0) 1730 260256 Fax: +44 (0) 1730 260466 Email: kdt at neuralt.com Website: http://www.neuralt.com George Bolt Director of Product Innovation Neural Technologies Cafe Neural: http://www.neuralt.com Tel: +44 (0) 1730 260 256 Fax: +44 (0) 1730 260 466 > ********** NOTE > Any views expressed in this message are those of the individual > sender, > except where the sender specifically states them to be the views of > Neural Technologies Limited > ********** > From John.Carney at cs.tcd.ie Fri Aug 27 09:44:25 1999 From: John.Carney at cs.tcd.ie (John Carney) Date: Fri, 27 Aug 1999 14:44:25 +0100 Subject: TECH-REPORT on bagging neural networks Message-ID: <3.0.1.32.19990827144425.009dbcd0@mail.cs.tcd.ie> Dear Connectionists, The following technical report is available for download from: http://www.cs.tcd.ie/publications/tech-reports/tr-index.99.html REPORT NUMBER: TCD-CS-1999-44 TITLE: Tuning diversity in bagged neural network ensembles ABSTRACT: In this paper we address the issue of how to optimize the generalization performance of bagged neural network ensembles. We investigate how diversity amongst networks in bagged ensembles can signifcantly influence ensemble generalization performance and propose a new early-stopping technique that effectively tunes this diversity so that overall ensemble generalization performance is optimized. Experiments performed on benchmark regression data-sets demonstrate the potential of the technique. KEYWORDS: Bagging, diversity, ensemble, generalization, early-stopping Any comments or feedback welcome. Regards, John Carney. __________________________________________________________ John Carney Department of Computer Science University of Dublin Trinity College Ireland http://www.cs.tcd.ie/John.Carney ______________________________________________________ From harnad at coglit.ecs.soton.ac.uk Fri Aug 27 16:00:52 1999 From: harnad at coglit.ecs.soton.ac.uk (Stevan Harnad) Date: Fri, 27 Aug 1999 21:00:52 +0100 (BST) Subject: Individual Differences in Reasoning: BBS Call for Commentators Message-ID: Below is the abstract of a forthcoming BBS target article INDIVIDUAL DIFFERENCES IN REASONING: IMPLICATIONS FOR THE RATIONALITY DEBATE? by Keith E. Stanovich and Richard F. West *** please see also 5 important announcements about new BBS policies and address change at the bottom of this message) *** 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 BBS Associates or nominated by a 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 reply by EMAIL by September 20th to: bbs at cogsci.soton.ac.uk or write to: Behavioral and Brain Sciences ECS: New Zepler Building University of Southampton Highfield, Southampton SO17 1BJ UNITED KINGDOM http://www.princeton.edu/~harnad/bbs/ http://www.cogsci.soton.ac.uk/bbs/ If you are not a BBS Associate, please send your CV and the name of a BBS Associate (there are currently over 10,000 worldwide) who is familiar with your work. All past BBS authors, referees and commentators are eligible to become BBS Associates. 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 with a WWW browser according to the instructions that follow after the abstract. _____________________________________________________________ INDIVIDUAL DIFFERENCES IN REASONING: IMPLICATIONS FOR THE RATIONALITY DEBATE? Keith E. Stanovich Department of Human Development and Applied Psychology University of Toronto 252 Bloor Street West Toronto, ON Canada M5S 1V6 kstanovich at oise.utoronto.ca Richard F. West School of Psychology James Madison University Harrisonburg, VA 22807 USA westrf at jmu.edu ABSTRACT: Much research in the last two decades has demonstrated that human responses deviate from the performance deemed normative according to various models of decision making and rational judgment (e.g., the basic axioms of utility theory). This gap between the normative and the descriptive can be interpreted as indicating systematic irrationalities in human cognition. However, four alternative interpretations preserve the assumption that human behavior and cognition is largely rational. According to these explanations, the gap is due to (1) performance errors, (2) computational limitations, (3) the wrong norm being applied by the experimenter and (4) a different construal of the task by the subject. In the debates about the viability of these alternative explanations, attention has been focused too narrowly on the modal response. In a series of experiments involving most of the classic tasks in the heuristics and biases literature, we have examined the implications of individual differences in performance for each of the four explanations of the normative and descriptive gap. Performance errors are a minor factor in the gap, computational limitations underlie non-normative responding on several tasks, particularly those that involve some type of cognitive decontextualization. Unexpected patterns of covariance can suggest when the wrong norm is being applied to a task or when an alternative construal of the task is called for. KEYWORDS: rationality, normative models, descriptive models, heuristics, biases, reasoning, individual differences ___________________________________________________________ To help you decide whether you would be an appropriate commentator for this article, an electronic draft is retrievable from the World Wide Web or by anonymous ftp from the US or UK BBS Archive. Ftp instructions follow below. 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. The URLs you can use to get to the BBS Archive: http://www.princeton.edu/~harnad/bbs/ http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.stanovich.html ____________________________________________________________ *** FIVE IMPORTANT ANNOUNCEMENTS *** ------------------------------------------------------------------ (1) There have been some very important developments in the area of Web archiving of scientific papers very recently. Please see: Science: http://www.cogsci.soton.ac.uk/~harnad/science.html Nature: http://www.cogsci.soton.ac.uk/~harnad/nature.html American Scientist: http://www.cogsci.soton.ac.uk/~harnad/amlet.html Chronicle of Higher Education: http://www.chronicle.com/free/v45/i04/04a02901.htm --------------------------------------------------------------------- (2) All authors in the biobehavioral and cognitive sciences are strongly encouraged to archive all their papers (on their Home-Servers as well as) on CogPrints: http://cogprints.soton.ac.uk/ It is extremely simple to do so and will make all of our papers available to all of us everywhere at no cost to anyone. --------------------------------------------------------------------- (3) BBS has a new policy of accepting submissions electronically. Authors can specify whether they would like their submissions archived publicly during refereeing in the BBS under-refereeing Archive, or in a referees-only, non-public archive. Upon acceptance, preprints of final drafts are moved to the public BBS Archive: ftp://ftp.princeton.edu/pub/harnad/BBS/.WWW/index.html http://www.cogsci.soton.ac.uk/bbs/Archive/ -------------------------------------------------------------------- (4) BBS has expanded its annual page quota and is now appearing bimonthly, so the service of Open Peer Commentary can now be be offered to more target articles. The BBS refereeing procedure is also going to be considerably faster with the new electronic submission and processing procedures. Authors are invited to submit papers to: Email: bbs at cogsci.soton.ac.uk Web: http://cogprints.soton.ac.uk http://bbs.cogsci.soton.ac.uk/ INSTRUCTIONS FOR AUTHORS: http://www.princeton.edu/~harnad/bbs/instructions.for.authors.html http://www.cogsci.soton.ac.uk/bbs/instructions.for.authors.html --------------------------------------------------------------------- (5) Call for Book Nominations for BBS Multiple Book Review In the past, Behavioral and Brain Sciences (BBS) journal had only been able to do 1-2 BBS multiple book treatments per year, because of our limited annual page quota. BBS's new expanded page quota will make it possible for us to increase the number of books we treat per year, so this is an excellent time for BBS Associates and biobehavioral/cognitive scientists in general to nominate books you would like to see accorded BBS multiple book review. (Authors may self-nominate, but books can only be selected on the basis of multiple nominations.) It would be very helpful if you indicated in what way a BBS Multiple Book Review of the book(s) you nominate would be useful to the field (and of course a rich list of potential reviewers would be the best evidence of its potential impact!). From harnad at coglit.ecs.soton.ac.uk Fri Aug 27 16:08:16 1999 From: harnad at coglit.ecs.soton.ac.uk (Stevan Harnad) Date: Fri, 27 Aug 1999 21:08:16 +0100 (BST) Subject: SIMPLE HEURISTICS: BBS Call for Multiple Book Review Message-ID: Below is the abstract of the Precis of a book that will shortly be circulated for Multiple Book Review in Behavioral and Brain Sciences (BBS): SIMPLE HEURISTICS THAT MAKE US SMART: BBS MULTIPLE BOOK REVIEW Gerd Gigerenzer, Peter M. Todd, and the ABC Research Group, This book has been accepted for a muliple book review to be published 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. Reviewers must be BBS Associates or nominated by a BBS Associate. (All prior BBS referees, editors, authors, and commentators are also equivalent to Associates.) To be considered as a reviewer for this article, to suggest other appropriate reviewers, or for information about how to become a BBS Associate, please send EMAIL to, BEFORE September 20, 1999: bbs at cogsci.soton.ac.uk or write to [PLEASE NOTE SLIGHTLY CHANGED ADDRESS]: Behavioral and Brain Sciences ECS: New Zepler Building University of Southampton Highfield, Southampton SO17 1BJ UNITED KINGDOM http://www.princeton.edu/~harnad/bbs/ http://www.cogsci.soton.ac.uk/bbs/ If you are not a BBS Associate, please send your CV and the name of a BBS Associate (there are currently over 10,000 worldwide) who is familiar with your work. All past BBS authors, referees and commentators are eligible to become BBS Associates. To help us put together a balanced list of reviewers, 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 reviewer. An electronic draft of the full text is available for inspection with a WWW browser according to the instructions that follow after the abstract. Please also specify (1) If you need the book (2) whether you can make it by the deadline of December 10, 1999. Please note that it is the book, not the Precis, that is to be reviewed. It would be helpful if you indicated in your reply whether you already have the book or would require a copy. _____________________________________________________________ Precis of Simple Heuristics That Make Us Smart BBS MULTIPLE BOOK REVIEW Simple Heuristics That Make Us Smart, was published by Oxford University Press 1999. Peter M. Todd & Gerd Gigerenzer Center for Adaptive Behavior and Cognition Max Planck Institute for Human Development Lentzeallee 94, 14195 Berlin, Germany ptodd at mpib-berlin.mpg.de gigerenzer at mpib-berlin.mpg.de http://www.mpib-berlin.mpg.de/abc ABSTRACT: How can anyone be rational in a world where knowledge is limited, time is pressing, and deep thought is often an unattainable luxury? Traditional models of unbounded rationality and optimization in cognitive science, economics, and animal behavior have tended to view decision-makers as possessing supernatural powers of reason, limitless knowledge, and endless time. But understanding decisions in the real world requires a more psychologically plausible notion of bounded rationality. In "Simple heuristics that make us smart", we explore fast and frugal heuristics--simple rules in the mind's adaptive toolbox for making decisions with realistic mental resources. These heuristics can enable both living organisms and artificial systems to make smart choices quickly and with a minimum of information by exploiting the way that information is structured in particular environments. In this precis, we show how simple building blocks that control information search, stop search, and make decisions can be put together to form classes of heuristics, including: ignorance-based and one-reason decision making for choice, elimination models for categorization, and satisficing heuristics for sequential search. These simple heuristics perform comparably to more complex algorithms, particularly when generalizing to new data--that is, simplicity leads to robustness. We present evidence regarding when people use simple heuristics and describe the challenges to be addressed by this research program. KEYWORDS: Bounded rationality, heuristics, decision making, simplicity, robustness, limited information search, satisficing, ignorance-based reasoning, elimination models, environment structure, adaptive toolbox ____________________________________________________________ To help you decide whether you would be an appropriate commentator for this article, an electronic draft is retrievable from the World Wide Web or by anonymous ftp from the US or UK BBS Archive. Ftp instructions follow below. 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. The URLs you can use to get to the BBS Archive: http://www.princeton.edu/~harnad/bbs/ http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.todd.html *** FIVE IMPORTANT ANNOUNCEMENTS *** ------------------------------------------------------------------ (1) There have been some very important developments in the area of Web archiving of scientific papers very recently. Please see: Science: http://www.cogsci.soton.ac.uk/~harnad/science.html Nature: http://www.cogsci.soton.ac.uk/~harnad/nature.html American Scientist: http://www.cogsci.soton.ac.uk/~harnad/amlet.html Chronicle of Higher Education: http://www.chronicle.com/free/v45/i04/04a02901.htm --------------------------------------------------------------------- (2) All authors in the biobehavioral and cognitive sciences are strongly encouraged to archive all their papers (on their Home-Servers as well as) on CogPrints: http://cogprints.soton.ac.uk/ It is extremely simple to do so and will make all of our papers available to all of us everywhere at no cost to anyone. --------------------------------------------------------------------- (3) BBS has a new policy of accepting submissions electronically. Authors can specify whether they would like their submissions archived publicly during refereeing in the BBS under-refereeing Archive, or in a referees-only, non-public archive. Upon acceptance, preprints of final drafts are moved to the public BBS Archive: ftp://ftp.princeton.edu/pub/harnad/BBS/.WWW/index.html http://www.cogsci.soton.ac.uk/bbs/Archive/ -------------------------------------------------------------------- (4) BBS has expanded its annual page quota and is now appearing bimonthly, so the service of Open Peer Commentary can now be be offered to more target articles. The BBS refereeing procedure is also going to be considerably faster with the new electronic submission and processing procedures. Authors are invited to submit papers to: Email: bbs at cogsci.soton.ac.uk Web: http://cogprints.soton.ac.uk http://bbs.cogsci.soton.ac.uk/ INSTRUCTIONS FOR AUTHORS: http://www.princeton.edu/~harnad/bbs/instructions.for.authors.html http://www.cogsci.soton.ac.uk/bbs/instructions.for.authors.html --------------------------------------------------------------------- (5) Call for Book Nominations for BBS Multiple Book Review In the past, Behavioral and Brain Sciences (BBS) journal had only been able to do 1-2 BBS multiple book treatments per year, because of our limited annual page quota. BBS's new expanded page quota will make it possible for us to increase the number of books we treat per year, so this is an excellent time for BBS Associates and biobehavioral/cognitive scientists in general to nominate books you would like to see accorded BBS multiple book review. (Authors may self-nominate, but books can only be selected on the basis of multiple nominations.) It would be very helpful if you indicated in what way a BBS Multiple Book Review of the book(s) you nominate would be useful to the field (and of course a rich list of potential reviewers would be the best evidence of its potential impact!). From georgiou at csusb.edu Fri Aug 27 17:15:54 1999 From: georgiou at csusb.edu (georgiou@csusb.edu) Date: 27 Aug 1999 14:15:54 -0700 Subject: CFP: 4th ICCIN (Feb. 27-Mar. 3, 2000) Message-ID: Call for Papers 4th International Conference on COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE http://www.csci.csusb.edu/iccin Trump Taj Mahal Casino and Resort]], Atlantic City, NJ USA February 27 -- March 3, 2000 Summary Submission Deadline: September 1, 1999 Conference Co-chairs: Subhash C. Kak, Louisiana State University Jeffrey P. Sutton, Harvard University This conference is part of the Fourth Joint Conference Information Sciences. http://www.ee.duke.edu/JCIS/ ***Added plenary speakers***: Marvin Minsky and Brian Josephson Plenary Speakers include the following: +------------------------------------------------------------------------+ |James Anderson |Wolfgang Banzhaf |B. Chandrasekaran|Lawrence J. Fogel| |-----------------+------------------+-----------------+-----------------| |Walter J. Freeman|David E. Goldberg |Irwin Goodman |Stephen Grossberg| |-----------------+------------------+-----------------+-----------------| |Thomas S.Huang |Janusz Kacprzyk |A. C. Kak |Subhash C. Kak | |-----------------+------------------+-----------------+-----------------| |John Mordeson |Kumpati S. Narenda|Anil Nerode |Huang T. Nguyen | |-----------------+------------------+-----------------+-----------------| |Jeffrey P. Sutton|Ron Yager | | | +------------------------------------------------------------------------+ Special Sessions on Quantum Computation. More to be added. Areas for which papers are sought include: o Artificial Life o Artificially Intelligent NNs o Associative Memory o Cognitive Science o Computational Intelligence o DNA Computing o Efficiency/Robustness Comparisons o Evaluationary Computation for Neural Networks o Feature Extraction & Pattern Recognition o Implementations (electronic, Optical, Biochips) o Intelligent Control o Learning and Memory o Neural Network Architectures o Neurocognition o Neurodynamics o Optimization o Parallel Computer Applications o Theory of Evolutionary Computation Summary Submission Deadline: September 1, 1999 Notification of authors upon review: November 1, 1999 December 1, 1999 - Deadline for invited sessions and exhibition proposals Papers will be accepted based on summaries. A summary shall not exceed 4 pages of 10-point font, double-column, single-spaced text, with figures and tables included. For the Fourth ICCIN, send 3 copies of summaries to: George M. Georgiou Computer Science Department California State University San Bernardino, CA 92407-2397 U.S.A. georgiou at csci.csusb.edu From terry at salk.edu Fri Aug 27 21:03:23 1999 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 27 Aug 1999 18:03:23 -0700 (PDT) Subject: NEURAL COMPUTATION 11:7 Message-ID: <199908280103.SAA10599@tesla-e0.salk.edu> NEURAL COMPUTATION 11:7 Neural Computation - Contents - Volume 11, Number 7 - October 1, 1999 ARTICLE Prediction Games and Arcing Algorithms Leo Breiman NOTES Can Hebbian Volume Learning Explain Discontinuities In Cortical Maps? Graeme J. Mitchison and Nicholas V. Swindale Disambiguating Different Covariation Types Carlos Brody LETTER Correlations Without Synchrony Carlos Brody On Decoding The Responses Of A Population of Neurons From geoff at giccs.georgetown.edu Sun Aug 29 10:08:34 1999 From: geoff at giccs.georgetown.edu (Geoff Goodhill) Date: Sun, 29 Aug 1999 10:08:34 -0400 Subject: Postdoc position available Message-ID: <199908291408.KAA13562@brecker.giccs.georgetown.edu> POSTDOCTORAL POSITION IN AXON GUIDANCE A postdoctoral position in now available to join a small team of physicists, biologists and computational neuroscientists investigating mechanisms of axon guidance in the developing nervous system. We are combining mathematical modeling with the development of a novel bioengineering technology for complementary quantitative experiments. We are looking for someone with skills in mathematical biological modeling, dynamics of complex systems, or quantitative imaging and data acquisition. For more details see http://www.giccs.georgetown.edu/labs/cns/axon.html Send a CV and contact information for at least two referees, preferably be email, to Geoffrey J Goodhill Georgetown Institute for Cognitive and Computational Sciences Georgetown University Medical Center 3970 Reservoir Road NW Washington DC 20007 Tel: (202) 687 6889 Fax: (202) 687 0617 Email: geoff at giccs.georgetown.edu Homepage: www.giccs.georgetown.edu/labs/cns From juergen at idsia.ch Mon Aug 30 03:34:44 1999 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Mon, 30 Aug 1999 09:34:44 +0200 Subject: job opening Message-ID: <199908300734.JAA13770@ruebe.idsia.ch> POSTDOC JOB OPENING The Swiss machine learning research institute IDSIA offers a 1-year postdoc position with possibility of renewal for 2 additional years. It is the position currently held by Fred Cummins who recently accepted a professorship at the University of Ireland, Dublin. The position is funded by an SNF research grant on recurrent neural networks. Ideal candidates have strong mathematical and programming skills, outstanding research potential, excellent ability to communicate research results, interest in recurrent network research, experience in one or more of the following fields: speech processing, neural nets, prediction (e.g., finance), control, music, program evolution. For more information, please see http://www.idsia.ch/~juergen/lstm99.html Juergen Schmidhuber IDSIA http://www.idsia.ch/~juergen From smagt at dlr.de Mon Aug 30 07:11:19 1999 From: smagt at dlr.de (Patrick van der Smagt) Date: Mon, 30 Aug 1999 13:11:19 +0200 (MET DST) Subject: CFP: Scalable Robotic Applications of Neural Networks Message-ID: <199908301111.NAA29171@ilz.robotic> Scalable Robotic Applications of Neural Networks ================================================ Special Issue of "Applied Intelligence" Editors: Patrick van der Smagt and Daniel Bullock http://www.robotic.dlr.de/Smagt/CFP/ In this special issue, we want to address the question of whether there are real robotic problems that can be better solved using existing neuro-computational principles than by using other standard engineering techniques. Where sensory-motor systems cannot be explicitly modeled, the brain's success leads us to expect that approaches based on adaptive neural control will someday provide a technically sound alternative. However, today's robotic engineers are appropriately skeptical regarding use of neural network principles because of the apparent scarcity of published research that demonstrates scalability of solutions to complex robotic control tasks. For example, like many traditional approaches, many neural network control strategies do not scale well from a two-degree-of-freedom robot arm to a seven degree-of-freedom system. For this special issue, papers are sought that: 1. introduce or review biologically plausible models of sensory-motor control that truly integrate action and perception; 2. newly apply such models to the control of realistic robots, especially manipulators; 3. describe hybrid robot control methodologies that incorporate cerebellar or other neuro-computational models (e.g., vision); 4. provide a case history that clearly defines, or illustrates overcoming of, barriers to successful competition by neural network models for robot control. The scalability of applications of biological models can only be fully assessed in the context of demonstrations that are representative of real-world complexities. Therefore, results on real hardware will generally be preferred. However, results on well-simulated complex problems will be preferred to results with hardware (e.g., 2 DoF robot arms) that can already be optimally controlled with conventional, non-neural techniques. Special Issue Editors: ---------------------- Patrick van der Smagt Institute of Robotics and System Dynamics DLR (German Aerospace Research Center) Oberpfaffenhofen, Germany smagt at dlr.de http://www.robotic.dlr.de/Smagt/ Daniel Bullock Cognitive and Neural Systems Department Boston University danb at cns.bu.edu http://cns-web.bu.edu/faculty.html#bullock Editor in Chief: ---------------- Moonis Ali Department of Computer Science Southwest Texas State University ma04 at swt.edu http://www.cs.swt.edu Submission ========== Deadline for submitting papers: Jan 15, 2000. The journal's instructions to authors can be read at http://www.robotic.dlr.de/Smagt/CFP/ifa.html. For this special issue, *all* papers must be submitted by the above date in Postscript or PDF format via email to smagt at dlr.de. Hardcopy submissions will not be accepted. To the extent that time permits, the editors will invite short external commentaries (to be published in the same issue) on the accepted papers. Submitters should inform the editors if they do *not* want their paper treated in an invited commentary. Suggestions of expert reviewers and commentators are welcome. About the journal ================= The objective of Applied Intelligence (IJAI) is to provide a medium for exchanging applied research on intelligent systems and technological achievements. IJAI is currently in its eighth year of publication. In order to meet the demand, the publication frequency has been increased from four to six issues per year effective 1998. IJAI is abstracted and/or indexed by twenty indexing publications. See http://www.wkap.nl/journals/apin -- Dr Patrick van der Smagt phone +49 8153 281152, fax -34 DLR/Institute of Robotics and System Dynamics smagt at dlr.de P.O.Box 1116, 82230 Wessling, Germany http://www.robotic.de/Smagt/ From georg at ai.univie.ac.at Mon Aug 30 12:32:26 1999 From: georg at ai.univie.ac.at (Georg Dorffner) Date: Mon, 30 Aug 1999 18:32:26 +0200 Subject: Workshop: Future and Prospects of Neural Networks Message-ID: <37CAB21A.4C1FA72C@ai.univie.ac.at> The following workshop is open to everyone. Your input to the discussion is needed! Since the workshop will take place during ICANN'99 at the conference venue, it will be of particular interest to conference participants. ============================================================= The Future and Prospects of Neural Networks ============================================================= a workshop Edinburgh University Appleton Tower, Lecture Theatre 2 Wednesday, Sep. 8, 1999, 6-8 p.m. Purpose The purpose of the workshop is to consolidate views and discuss perspectives of where the field of neural networks will be heading in the near and medium-term future. The ultimate goal of NEuroNet - the organiser of this workshop - is to compile a so-called "technological roadmap" of neural networks and related methodologies, that presents a visionary overview of the current trends in neural networks, as well as likely future developments, foci and prospects of both basic and applied research. For this, the opinions from neural network researchers are solicited. Format A number of panellists will present their short position papers about the future of neural networks. This will be followed by an open discussion, where everybody is invited to contribute their own view about the prospects of the field. Refreshments will be served to enable a continuation of the discussion over a glass of wine. Panellists: Georg Dorffner, OFAI Vienna Geoffrey Hinton, Univ. College London Erkki Oja, Helsinki Univ. of Technology Nic Schraudolph, IDSIA Lugano John Taylor, King's College London David Willshaw, Edinburgh Univ. Moderation: Mark Plumbley, NEuroNet The organizer This workshop is organised by NEuroNet - the network of excellence on neural networks, sponsored by the EU commission (http://www.kcl.ac.uk/neuronet). More information about the workshop can be found at http://www.ai.univie.ac.at/oefai/nn/neuronet/workshop.html From jknierim at nba19.med.uth.tmc.edu Mon Aug 30 11:48:54 1999 From: jknierim at nba19.med.uth.tmc.edu (James Knierim) Date: Mon, 30 Aug 1999 10:48:54 -0500 Subject: postdoctoral position available Message-ID: <37CAA7E6.4459CBAC@nba19.med.uth.tmc.edu> Postdoctoral position available in behavioral/cognitive neuroscience We use state-of the-art multi-electrode technology to record single-unit activity from neuronal ensembles in the hippocampus and related structures of freely moving animals. Current projects include studies of the interactions between place cells in the hippocampus and head direction cells of the thalamus, and the processing of information through the different areas of the hippocampal formation (entorhinal cortex, dentate gyrus, CA fields, and subiculum). Expertise in single-unit physiology, behavioral neuroscience, or computational neuroscience is preferred. Please send a CV, statement of research interests, and references to: James J. Knierim, Ph.D. Department of Neurobiology and Anatomy University of Texas-Houston Medical School P.O. Box 20708 Houston, TX 77225 E0E/AA/SSP/Smoke-free Environment From ted.carnevale at yale.edu Tue Aug 31 08:26:47 1999 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Tue, 31 Aug 1999 08:26:47 -0400 Subject: SFN 1999 NEURON course Message-ID: <37CBCA07.F2E22E68@yale.edu> This year, the Society for Neuroscience meeting is earlier than in 1997 or 19998, so the deadline to sign up for the NEURON short course is approaching rapidly. Seats are still available, but quick action is needed to take advantage of the early registration fee. Among the new features that will be covered, I should mention: The Cell Builder, which will be of particular interest to experimentalists and others whose models are closely linked to empirical observations. The Cell Builder makes it easy to construct new models, but its greatest strength may be in the management of anatomically complex models based on quantitative morphometric data. The Multiple Run Fitter, a powerful and flexible new tool for optimizing models with high-dimensional data sets. This tool is useful for experimentalists and theoreticians alike. Further information about the course and an electronic registration form are posted at http://www.neuron.yale.edu/miami99.html --Ted From ucganlb at ucl.ac.uk Tue Aug 31 14:51:45 1999 From: ucganlb at ucl.ac.uk (Neil Burgess - Anatomy UCL London) Date: Tue, 31 Aug 1999 19:51:45 +0100 Subject: C code available for model of STM for serial order. Message-ID: <2099.199908311851@socrates-a.ucl.ac.uk> The C code for the simulations in the following paper is available on: http://behemoth.maze.ucl.ac.uk/neil/PL_sim/ code and executables for running under MS windows/DOS can be found on: http://behemoth.maze.ucl.ac.uk/neil/PL_simPC/ MEMORY FOR SERIAL ORDER: A NETWORK MODEL OF THE PHONOLOGICAL LOOP AND ITS TIMING. N Burgess & GJ Hitch (1999) Psychological Review 106 551-581. Abstract: A connectionist model of human short-term memory is presented that extends the `phonological loop' (A. D. Baddeley, 1986) to encompass serial order and learning. Psychological and neuropsychological data motivate separate layers of lexical, timing and input and output phonemic information. Connection weights between layers show Hebbian learning and decay over short and long time scales. At recall, the timing signal is rerun, phonemic information feeds back from output to input and lexical nodes compete to be selected. The selected node then receives decaying inhibition. The model provides an explanatory mechanism for the phonological loop, and for the effects of serial position, presentation modality, lexicality, grouping and Hebb repetition. It makes new psychological and neuropsychological predictions and is a starting point for understanding the role of the phonological loop in vocabulary acquisition and for interpreting data from functional neuroimaging. Best wishes, Neil