From Dave_Touretzky at DST.BOLTZ.CS.CMU.EDU Thu Apr 1 20:56:03 1993 From: Dave_Touretzky at DST.BOLTZ.CS.CMU.EDU (Dave_Touretzky@DST.BOLTZ.CS.CMU.EDU) Date: Thu, 01 Apr 93 20:56:03 EST Subject: policy on posting talk announcements Message-ID: <17538.733715763@DST.BOLTZ.CS.CMU.EDU> A number of people have inquired recently about the propriety of posting local seminar announcements. Since CONNECTIONISTS is a world-wide mailing list, most readers will not be able to attend most talks. However, many folks find that a well-phrased talk abstract is a great way to learn about state-of-the-art work that hasn't yet made it into print. Reading talk abstracts is also a good way to keep track of what prominent people are working on these days. On the other hand, there are a lot of mundane neural net talks given every day. Some of these are introductory lectures, and thus not appropriate for readers of this list. Others describe preliminary research without significant results, or only incremental progress rather than really new ideas. Finally, some people may give decent talks but write boring abstracts. Here, then, is the policy on posting talk announcements to CONNECTIONISTS: 1. People are ENCOURAGED to post well-written abstracts describing exciting, state-of-the-art research. If possible, cite a paper or tech report so interested readers can follow up, or at least give the speaker's address so people can write for more information. 2. People are DISCOURAGED from posting abstracts that don't meet the above criteria. -- Dave Touretzky From UBTY003 at CCS.BBK.AC.UK Sat Apr 3 00:23:00 1993 From: UBTY003 at CCS.BBK.AC.UK (Martin Davies) Date: Sat, 3 Apr 93 0:23 BST Subject: European Society for Philosophy and Psychology Message-ID: ************************************************************************ ****** EUROPEAN SOCIETY FOR PHILOSOPHY AND PSYCHOLOGY ****** *********** SECOND ANNUAL MEETING *********** *****HANG SENG CENTRE FOR COGNITIVE STUDIES***** *****UNIVERSITY OF SHEFFIELD***** **** 3 - 6 JULY, 1993 **** The Second Annual Meeting of the European Society for Philosophy and Psychology will be held at the University of Sheffield, England, from the afternoon of Saturday 3 July to the morning of Tuesday 6 July, 1993. The meeting is sponsored by the Hang Seng Centre for Cognitive Studies, University of Sheffield. The goal of the Euro-SPP is: 'to promote interaction between philosophers and psychologists on issues of common concern'. ***** REGISTRATION ***** In order to register for the conference, you must fill out a Registration Form. Registration forms, along with information about accommodation and meals, can be obtained by writing to: Peter Carruthers, Hang Seng Centre for Cognitive Studies Department of Philosophy, University of Sheffield, Sheffield, S10 2TN UK or by sending email to: P.Carruthers at primea.sheffield.ac.uk THE REGISTRATION FEE (to include membership of the Euro-SPP) is 15 pounds sterling, or 10 pounds sterling for students. The cost of ACCOMMODATION AND MEALS (from dinner on Saturday to breakfast on Tuesday, including a visit to Chatsworth House - one of the great country houses of England - on Monday evening) is 120 pounds sterling. For those participants who do not require accommodation, the charge for MEALS is 70 pounds sterling. PAYMENT should be in *pounds sterling*, either by a cheque or draft drawn on a British bank or else by a EuroCheque. For all other methods of payment - whether foreign currency cheque, sterling cheque drawn on a non-UK bank, or electronic transfer - it will be necessary to make a surcharge of *seven pounds sterling* to cover clearance charges. Cheques must be made payable to *The University of Sheffield*. When registration is complete, you will be sent an information pack including maps and other touristic information along with a detailed programme. ************************************************************************ ***** PROVISIONAL PROGRAMME ***** SATURDAY 3 JULY Conference desk open from 12 noon 3.00 - 5.00 pm SYMPOSIUM 1: Body and Space 5.00 - 5.30 pm Tea 6.15 - 7.45pm INVITED LECTURE: Ruth Millikan 8.15 pm DINNER in Firth Hall, University of Sheffield SUNDAY 4 JULY 9.00 - 11.00 am SYMPOSIUM 2: Explanation by Intentional States 11.00 - 11.30 am Coffee 11.30 am - 1.00 pm SUBMITTED PAPERS 1.00 - 2.00 pm LUNCH 2.00 - 4.00 pm SYMPOSIUM 3: The Autonomy of Social Explanation 4.00 - 4.30 pm Tea 4.30 - 6.00 pm TUTORIAL LECTURE: Machine Vision 6.15 pm BUSINESS MEETING followed by a RECEPTION 8.00 pm DINNER MONDAY 5 JULY 9.00 - 11.00 am SYMPOSIUM 4: Mindblindness: Autism and Theory of Mind 11.00 - 11.30 am Coffee 11.30 am - 1.00 pm SUBMITTED PAPERS 1.00 - 2.00 pm Lunch 2.00 - 4.00 pm ROUND TABLE: Neuropsychological Approaches 4.00 - 4.30 pm Tea 4.30 - 6.00 pm INVITED LECTURE: tba 6.30 pm A visit to Chatsworth House,including DINNER TUESDAY 6 JULY Depart after breakfast Symposium speakers include: Simon Baron-Cohen, John Campbell, Pascal Engel, Juan Carlos Gomez, Pierre Jacob, Marcel Kinsbourne, Tony Marcel, Michael Martin, David Perrett, Gabriel Segal, Tim Shallice, Chris Sinha ************************************************************************ From lazzaro at boom.CS.Berkeley.EDU Sun Apr 4 16:42:27 1993 From: lazzaro at boom.CS.Berkeley.EDU (John Lazzaro) Date: Sun, 4 Apr 93 13:42:27 PDT Subject: New Release -- Chipmunk Analog VLSI CAD Tools Message-ID: <9304042042.AA07317@boom.CS.Berkeley.EDU> Caltech VLSI CAD Tool Distribution -- New Revision --------------------------------------------------- We are offering to the Internet community a new revision of the Caltech electronic CAD system for analog VLSI neural networks. This distribution contains tools for schematic capture, netlist creation, and analog and digital simulation (log), IC mask layout, extraction, and DRC (wol), simple chip compilation (wolcomp), MOSIS fabrication request generation (mosis), netlist comparison (netcmp), data plotting (view) and postscript graphics editing (until). These tools were used exclusively for the design and test of all the integrated circuits described in Carver Mead's book "Analog VLSI and Neural Systems". Until was used as the primary tool for figure creation for the book. The distribution also contains an example of an analog VLSI chip that was designed and fabricated with these tools, and an example of an Actel field-programmable gate array design that was simulated and converted to Actel format with these tools. These tools are distributed under a license very similar to the GNU license; the minor changes protect Caltech from liability. Highlights of the new revision includes: * Ports to new platforms (Supported platforms now include: Sun SPARC, Sun 3, HP Series 300/400/700/800, DEC MIPS-based Ultrix, Appple AU/X, linux, and IBM RS/6000 support). * Support for black and white displays, and resource database support for user preferences for sizing and placement of windows. New display modes in analog to support small screens. * Direct generation of SPICE netlists in analog, and new models for floating-well FET's, two-terminal devices with arbitrary i-v curves, and quantum-well tunnel diodes. * Many bug fixes for analog, wol, view, and until, and new features for view. If you are interested in some or all of these tools, 1) ftp to hobiecat.cs.caltech.edu on the Internet, 2) log in as anonymous and use your username as the password 3) cd pub/chipmunk 4) copy the file README, that contains more information. European researchers can access these files through anonymous ftp using the machine ifi.uio.no in Norway; the files are in the directory chipmunk. We are unable to help users who do not have Internet ftp access. From raina at max.ee.lsu.edu Mon Apr 5 16:18:00 1993 From: raina at max.ee.lsu.edu (Praveen Raina) Date: Mon, 5 Apr 93 15:18:00 CDT Subject: Generalization Comparison Message-ID: <9304052018.AA24266@max.ee.lsu.edu> The following report is available that examines the generalization performance of two feedforward learning techniques. ---- Technical Report ECE 93-03, LSU, March 31, 1993 ----- COMPARISON OF LEARNING AND GENERALIZATION CAPABILITIES OF THE KAK AND THE BACKPROPAGATION ALGORITHMS Praveen Raina Dept. of Electrical & Computer Engineering LSU, Baton Rouge, LA 70803-5901 E-mail: raina at max.ee.lsu.edu Abstract: This report compares the learning and generalization capabilities of the Backpropagation and the Kak algorithm. It is observed that the Backpropagation algorithm is much more computation intensive than the Kak algorithm. The generalization performance with respect to an error criterion is better for the Backpropagation algorithm for intermediate values of error. But when considered together with the number of extra iterations that the Backpropagation algorithm entails one concludes that the Kak algorithm has overall superior performance. From piero at dist.dist.unige.it Tue Apr 6 14:54:12 1993 From: piero at dist.dist.unige.it (Piero Morasso) Date: Tue, 6 Apr 93 14:54:12 MET DST Subject: ICANN'94 Preliminary Call for Papers Message-ID: <9304061254.AA02516@dist.dist.unige.it> -------------------------------------------------------------------- | ************************************************ | | * * | | * EUROPEAN NEURAL NETWORK SOCIETY * | | * PRELIMINARY CALL FOR PAPERS * | | * I C A N N ' 94 - SORRENTO * | | * * | | ************************************************ | | | | ICANN'94 (INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS)| | is the fourth Annual Conference of ENNS and it comes after | | ICANN'91(Helsinki), ICANN'92 (Brighton), ICANN'93 (Amsterdam). | | It is co-sponsored by INNS, IEEE-NC, JNNS. | | It will take place at the Sorrento Congress Center, near Naples, | | Italy, on May 26-29, 1994. | | There will be tutorials and invited talks by top-experts | | in the field who will also join the program committee. | | | | Interested authors are cordially invited to present their work | | in one of the following "Scientific Areas" (A-Cognitive Science; | | B-Mathematical Models; C- Neurobiology; D-Fuzzy Systems; | | E-Neurocomputing), indicating also an "Application domain" | | (1-Motor Control;2-Speech;3-Vision;4-Natural Language; | | 5-Process Control;6-Robotics;7-Signal Processing; | | 8-Pattern Recognition;9-Hybrid Systems;10-Implementation). | | | | DEADLINE for CAMERA-READY COPIES: December 15, 1993. | | ---------------------------------------------------- | | Detailed instructions will be given in a subsequent call. | | | | Conference Chair: Prof. Eduardo R. Caianiello, Univ. Salerno, | | Italy, Dept.Theoretic Physics; email: iiass at salerno.infn.it | | | | Conference Co-Chair: Prof. Pietro G. Morasso, Univ. Genova, | | Italy, Dept.Informatics, Systems,Telecommunication, | | email: morasso at dist.unige.it | | | | Tutorial Chair: Prof. John Taylor, Imperial College,London, UK, | | fax: +44 71 873 2017 | | | | Industrial Liaison Chair: Dr. Roberto Serra, Ferruzzi | | Finanziaria, Ravenna, fax: +39 544 35692/32358 | -------------------------------------------------------------------- From yves at netid.com Tue Apr 6 17:57:40 1993 From: yves at netid.com (Yves Chauvin) Date: Tue, 6 Apr 93 14:57:40 PDT Subject: Preprint available Message-ID: <9304062157.AA00259@netid.com> **DO NOT FORWARD TO OTHER GROUPS** The following paper, "Smooth On-Line Learning Algorithms for Hidden Markov Models" has been placed in the neuroprose archive. It is to be published in Neural Computation. Further information and retrieval instructions are given below. ___________________________________________________________________________ "Smooth On-Line Learning Algorithms for Hidden Markov Models" Pierre Baldi JPL, Caltech Yves Chauvin Net-ID, Inc. A simple learning algorithm for Hidden Markov Models (HMMs) is presented together with a number of variations. Unlike other classical algorithms such as the Baum-Welch algorithm, the algorithms described are smooth and can be used on-line (after each example presentation) or in batch mode, with or without the usual Viterbi most likely path approximation. The simple expression of the learning algorithms and several of their advantages result from using Boltzmann-Gibbs representations (normalizing exponentials) for the HMM parameters. All the algorithms presented are proved to be exact or approximate gradient optimization algorithms with respect to likelihood, log-likelihood or cross-entropy functions, and as such are usually convergent. These algorithms can also be casted in the more general EM (Expectation-Maximization) framework where they can be viewed as exact or approximate GEM (Generalized Expectation-Maximization) algorithms. The mathematical properties of the algorithms are derived in the appendix. ___________________________________________________________________________ Retrieval instructions: The paper is baldi.smoothhmm.ps.Z in the neuroprose archive. To retrieve this file from the neuroprose archives: unix> ftp cheops.cis.ohio-state.edu Name (cheops.cis.ohio-state.edu:becker): anonymous Password: (use your email address) ftp> cd pub/neuroprose ftp> binary ftp> get baldi.smoothhmm.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for baldi.compbiohmm.ps.Z . ftp> quit . unix> uncompress baldi.smoothhmm.ps.Z unix> lpr baldi.smoothhmm.ps From mike at psych.ualberta.ca Tue Apr 6 21:54:38 1993 From: mike at psych.ualberta.ca (Mike Dawson) Date: Tue, 6 Apr 93 19:54:38 MDT Subject: Positions at U. of A. Message-ID: The University of Alberta, Department of Psychology, is seeking applications from candidates who can contribute to the further development of a leading program in Cognitive Science. Individuals will be hired into tenure-track positions at the Assistant Professor level, salary range $40,035 to $57,003. Appointments take effect July 1, 1994; PhD should be completed by that date. Special consideration will be given to candidates who have expertise both in basic research and in applied, problem-oriented areas. Candidates should have significant interdisciplinary interests; the individuals hired will have the potential to further develop links across existing areas in the Department, as well as with other Departments and the extramural research community. The Department of Psychology has members within both the Faculties of Arts and Science and has outstanding infrastructure for research. Decisions will be made on the basis of demonstrated research capability, teaching ability, and the potential for interactions with colleagues. We encourage applicants from the following five areas; we currently have vacancies to fill in four of these areas: (1) COGNITION AND AGING: Expertise in memory, language, or cognition as they relate to normal aging or to age-related pathologies. (2) COGNITIVE NEUROSCIENCE: Expertise in the relation between neural processes and cognitive processes such as memory, language, perception, attention, visual cognition and/or psychophysiology. (3) COGNITIVE PSYCHOLOGY: Expertise in any area of cognition. Individuals with broad interests in language processing and cognitive science, and research expertise in psycholinguistics, discourse processing, speech comprehension and production, word perception and/or reading will be given special consideration. (4) COGNITIVE MODELING: Expertise in the computational modeling of cognitive, perceptual, and/or neural processes. Individuals with the demonstrated ability to relate these models to empirical observations are especially encouraged to apply. (5) SOCIAL COGNITION: Experts in such areas as social judgment and decision- making, social memory, beliefs and attitudes, affect, motivation, social psychophysiology, and/or interpersonal relations are especially encouraged to apply. In accordance with Canadian Immigration requirements, priority will be given to Canadian citizens and permanent residents of Canada. Applicants should include a curriculum vitae, statement of research interests, three letters of recommendation, and reprints or recent publications. These materials should be sent to the Chair of the appropriate search committee (e.g., Chair, Cognition and Aging Search Committee), Department of Psychology, University of Alberta, Edmonton, Alberta, CANADA T6G 2E9. To receive full consideration, all materials must be received by October 15, 1993. The University of Alberta is committed to the principle of equity in employment. The University encourages applications from aboriginal persons, disabled persons, members of visible minorities, and women. -- Michael R.W. Dawson email: mike at psych.ualberta.ca Biological Computation Project, Department of Psychology University of Alberta, Edmonton, AB CANADA T6G 2E9 Tel: +1 403 492 5175 Fax: +1 403 492 1768 From lpratt at franklinite.Mines.Colorado.EDU Wed Apr 7 12:57:52 1993 From: lpratt at franklinite.Mines.Colorado.EDU (Lorien Y. Pratt) Date: Wed, 7 Apr 93 09:57:52 -0700 Subject: David Cohn to speak in Colorado Machine Learning series Message-ID: <9304071657.AA15275@franklinite.Mines.Colorado.EDU> The spring, 1993 Colorado Machine Learning Colloquium Series presents: Dr. David Cohn Dept. of Brain & Cognitive Science Massachusetts Inst. of Technology Cambridge, MA 02139 Uncertainty-Based Queries in Neural Networks *Thursday*, April 15, 1993 Room 110, Stratton Hall, on the CSM campus 5:30 pm ABSTRACT In many interesting learning problems, it is practical for a learner to pick its own training data. Intuition and theory both suggest that by properly picking where one's training data comes from, one can greatly improve one's ability to generalize. I will consider the problem of attempting to learn a map from points in a domain, such as a geometric map or a set of state-action pairs, to some ``value,'' such as a classification or a next-state identifier. I will assume that training data may be obtained by querying. That is, we may specify a point x and call an oracle, or perform an experiment to determine f(x), the value of the map at that point. We wish to make queries that are ``optimally informative'' according to some criterion, but there are many criteria to choose from, and many are computationally intractible. I will discuss my current research studying the suitability of a querying criterion based on uncertainty in system parameters. Under certain reasonable assumptions, one may efficiently compute how much the uncertainty in system parameters will be reduced by knowing f(x) for a specified x, and thus the ``information gain'' of querying it. This approach was introduced by Fedorov in 1972; its utility for active data selection in neural networks was proposed by MacKay in 1991. I will discuss experiments performing gradient ascent on the information gain of a query, and discuss the problems that are involved in extending this approach to learning problems which only allow restricted querying, such as navigation, exploration and control. Suggested background readings: Training Connectionist Networks with Queries and Selective Sampling; Les Atlas, David Cohn and Richard Ladner. Advances in Neural Information Processing 2, D. Touretzky ed. Morgan Kaufmann, 1990, pp. 566-573. Constructing Hidden Units using Examples and Queries; Eric B. Baum and Kevin J. Lang. Advances in Neural Information Processing 3, R. Lippman, J. Moody and D. Touretzky, eds. Morgan Kaufmann, 1991, pp. 904- 910. The Evidence Framework applied to Classification Networks; David J. C. MacKay. Neural Computation, Volume 4, number 5, 1992, pages 698-714. These readings are available on reserve at the Arthur Lakes Library at CSM. Ask for the reserve package for MACS570, subject: Cohn. Non-students can check materials out on reserve by providing a driver's license. Open to the Public Refreshments to be served at 5:00pm, prior to talk For more information (including a schedule of all talks in this series), contact: Dr. L. Y. Pratt, CSM Dept. of Mathematical and Computer Sciences, lpratt at mines.colorado.edu, (303) 273-3878. The speaker may be contacted at cohn at psyche.mit.edu. Sponsored by: THE CSM DEPARTMENTS OF MATHEMATICAL AND COMPUTER SCIENCES, GEOPHYSICS, DIVISION OF ENGINEERING, AND CRIS The Center for Robotics and Intelligent Systems at the Colorado School of Mines From ronen at wisdom.weizmann.ac.il Wed Apr 7 10:34:16 1993 From: ronen at wisdom.weizmann.ac.il (Ronen Basri) Date: Wed, 7 Apr 93 17:34:16 +0300 Subject: CFP - Israeli Symposium on AI and Vision, Dec. 1993 Message-ID: <9304071434.AA17223@silver.wisdom.weizmann.ac.il> Call For Papers 10th Israeli Symposium on Artificial Intelligence and Computer Vision Tel-Aviv, December 27-28, 1993 The conference is the joint annual meeting of the Israeli Association for Artificial Intelligence, and the Israeli Association for Computer Vision and Pattern Recognition, which are affiliates of the Israeli Information Processing Association. Papers addressing all aspects of AI and Computer Vision, including, but not limited to, the following topics, are solicited: Image Processing and Analysis Computer Vision, Applications, Robotics Biological Vision, Visual Perception Cognitive Modeling Pattern Recognition and Neural Networks Natural Language Processing Inductive Inference, Automated Reasoning, Planning and Search Knowledge Acquisition, Knowledge Theory, Logics of Knowledge AI and Education, AI Languages and Methodology Submitted papers will be refereed by the program committee. Authors should submit 4 copies of the full paper (in English). Accepted papers will appear in the conference proceedings. Papers should be received by the conference co-chairmen at one of the following addresses by June 30th, 1993. Authors will be notified of acceptance by September 15th 1993. Vision: AI: Dr. Ronen Basri Dr. Uri J. Schild 10th IAICV 10th IAICV Dept. of Appl. Math. and Comp. Sci. Dept. of Math. and Comp. Sci. The Weizmann Institute of Science Bar Ilan University Rehovot 76100, Israel Ramat Gan 52900, Israel ronen at wisdom.weizmann.ac.il schild at bimacs.cs.biu.ac.il VISION Committee Members: ----------------------------------------------------------------------------- D. Weinshall Hebrew University daphna at cs.huji.ac.il N. Intrator Tel Aviv University nin at math.tau.ac.il N. Kiryati Technion kiryati at techunix.technion.ac.il Z. Smilansky Orbotec zeev at orbot.co.il Y. Halor Weizmann Institute toky at wisdom.weizmann.ac.il R. Basri (Chairman) Weizmann Institute ronen at wisdom.weizmann.ac.il AI Committee Members: ----------------------------------------------------------------------------- L. Manevitz Haifa University manevitz at mathcs2.haifa.ac.il M. Golumbic IBM Scientific center golumbic at haifasc3.vnet.ibm.com S. Kraus Bar-Ilan University sarit at bimacs.biu.ac.il Y. Davidor Weizmann Institute yuval at wisdom.weizmann.ac.il U. Ornan Technion ornan at techsel.technion.ac.il S. Markovitz Technion shaulm at cs.technion.ac.il J. Rosenschein Hebrew University jeff at cs.huji.ac.il E. Gudes Ben-Gurion University ehud at bengus.bgu.ac.il U. Schild (Chairman) Bar-Ilan University schild at bimacs.biu.ac.il From becker at cs.toronto.edu Wed Apr 7 10:05:41 1993 From: becker at cs.toronto.edu (becker@cs.toronto.edu) Date: Wed, 7 Apr 1993 10:05:41 -0400 Subject: job opening at McMaster Message-ID: <93Apr7.100550edt.786@neuron.ai.toronto.edu> McMaster University Department of Psychology McMaster University invites applications for a tenure track position at the Assistant Professor rank starting July 1, 1994, in the Department of Psychology with associate status in the De partment of Computer Science and Systems. This position is sub- ject to final budgetary approval. Candidates' interest should be in artificial intelligence, specifically in empirical studies and connectionist modelling of language abilities or language acquisition in normal and brain- damaged individuals. Candidates must have expert modelling and computational skills and be prepared to teach in both computer science and psychology. In accordance with Canadian Immigration requirements, priority will be given to Canadian citizens and permanent resi- dents. McMaster University is committed to Employment Equity and encourages applications from all qualified candidates, including aboriginal people, people with disabilities, members of visible minorities, and women. Please forward applications, consisting of c.v., publica- tions list, a short statement of research interests, and arrange to have three letters of reference sent to the Chair, Department of Psychology, McMaster University, Hamilton, Ontario, L8S 4K1, Canada. From wahba at stat.wisc.edu Thu Apr 8 15:03:51 1993 From: wahba at stat.wisc.edu (Grace Wahba) Date: Thu, 8 Apr 93 14:03:51 -0500 Subject: Uncertainty-Based Queries Message-ID: <9304081903.AA26851@hera.stat.wisc.edu> Re: Uncertainty Based Queries in Neural Networks: D. Cohn abstract of talk at Colorado State: ml-connectionists distribution Apr 7, 1993 Various forms of the interesting problem discussed in the above abstract have been studied in the statistics literature (in different language, naturally!) under the rubric `experimental design'- The Current Index to Statistics database here lists 5430 articles under `design', a non-trivial proportion of which are in the general context of allowing to choose x and observe f(x), or, a noise-corrupted version of f(x), in order to learn something about f. .see also: Sacks, Welch, Mitchell and Wynn, Design and analysis of computer experiments, with discussion Statistical Science, 4, 409-423, 1989. . Athavale and Wahba, Determination of an optimal mesh for a collocation-projection method for solving two-point boundary value problems, J. Approx. Theory, 25, 38-49, 1979. . Wahba, Parameter estimation in linear dynamic systems, IEEE Trans. Automatic Control, AC-25, 235-238, 1980 Grace Wahba wahba at stat.wisc.edu From soodakr at ROCKVAX.ROCKEFELLER.EDU Thu Apr 8 22:51:18 1993 From: soodakr at ROCKVAX.ROCKEFELLER.EDU (Robert Soodak) Date: Thu, 8 Apr 93 22:51:18 -0400 Subject: No subject Message-ID: <9304090251.AA20858@rocky8.ROCKEFELLER.EDU> Subject: Postdoc Position at Rockefeller U. April 8, 1993 A postdoctoral position in computational neuroscience is available immediately. Research will be concerned with pattern formation of orientation columns which result from the orderly mapping of the mosaic of retinal ganglion cells onto the cortical surface. Simulations constrained by published biological data are the primary means of investigation. The position will involve C programing in a UNIX environment, and some programing experience is essential. No formal training in neuroscience is required, although an interest in biological information processing would be an asset. Write, phone or email with questions or applications to: Robert Soodak Rockefeller University 1230 York Avenue New York, NY 10021 email: soodakr at rockvax.rockefeller.edu Tel: (212) 327-8603 Fax: (212) 327-8530 (Not Private) From David_Redish at GS17.SP.CS.CMU.EDU Fri Apr 9 10:08:25 1993 From: David_Redish at GS17.SP.CS.CMU.EDU (David Redish) Date: Fri, 09 Apr 93 10:08:25 -0400 Subject: Paper on Neuroprose Message-ID: <17467.734364505@GS17.SP.CS.CMU.EDU> The following paper has been placed in the Neuroprose archive. Comments and questions are welcome. ******************************************************************* Neural Representation of Space Using Sinusoidal Arrays David S. Touretzky A. David Redish Hank S. Wan School of Computer Science Computer Science Department Carnegie Mellon University Pittsburgh, PA 15213 O'Keefe (1991) has proposed that spatial information in rats might be represented as phasors: phase and amplitude of a sine wave encoding angle and distance to a landmark. We describe computer simulations showing that operations on phasors can be efficiently realized by arrays of spiking neurons that re-code the temporal dimension of the sine wave spatially. Some cells in motor and parietal cortex exhibit response properties compatible with this proposal. This paper will appear in Neural Computation. ******************************************************************* ---------------------------------------------------------------- FTP INSTRUCTIONS "Getps touretzky.sinusoidal-arrays.ps.Z" if you have the shell script, or unix% ftp archive.cis.ohio-state.edu (or 128.146.8.52) Name: anonymous Password: neuron ftp> cd pub/neuroprose ftp> binary ftp> get touretzky.sinusoidal-arrays.ps.Z ftp> bye unix% uncompress touretzky.sinusoidal-arrays.ps unix% lpr touretzky.sinusoidal-arrays.ps Note that the last figure does not print out correctly on all printers. If you have trouble printing it out, we have supplied a copy of the figure in its own postscript file. (We've never had a problem printing it out alone, just included into the document.) The extra file is called "touretzky.extra-fig.ps" and can be retrieved from the same directory in the same manner as "touretzky.sinusoidal-array.ps.Z". The extra figure is not compressed. ---------------------------------------------------------------- From dhw at santafe.edu Fri Apr 9 16:13:21 1993 From: dhw at santafe.edu (dhw@santafe.edu) Date: Fri, 9 Apr 93 14:13:21 MDT Subject: New paper in neuroprose Message-ID: <9304092013.AA07791@zia> *** DO NOT FORWARD TO ANY OTHER LISTS *** The following file has been placed in neuroprose. Part of it consists of a tutorial review, and part of it consists of novel material concerning extensions of stacked generalization. COMBINING GENERALIZERS USING PARTITIONS OF THE LEARNING SET by David H. Wolpert Abstract: For any real-world generalization problem, there are always many generalizers which could be applied to the problem. This paper discusses some algorithmic techniques for dealing with this multiplicity of possible generalizers. All of these techniques rely on partitioning the provided learning set in two, many different times. The first technique discussed is cross-validation, which is a winner-takes-all strategy (based on the behavior of the generalizers on the partitions of the learning set, it picks one single generalizer from amongst the set of candidate generalizers, and tells you to use that generalizer). The second technique discussed, the one this paper concentrates on, is an extension of cross-validation called stacked generalization. As opposed to cross-validation's winner-takes-all strategy, stacked generalization uses the partitions of the learning set to combine the generalizers, in a non-linear manner, via another generalizer (hence the term `stacked generalization'). After presenting a cursory review of stacked generalization, this paper discusses some possible extensions of stacked generalization. To retrieve the file: unix> ftp cheops.cis.ohio-state.edu Connected to cheops.cis.ohio-state.edu. 220 cheops.cis.ohio-state.edu FTP server ready. Name: anonymous 331 Guest login ok, send ident as password. Password:neuron 230 Guest login ok, access restrictions apply. ftp> binary 200 Type set to I. ftp> cd pub/neuroprose 250 CWD command successful. ftp> get wolpert.lecture92.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for rosenblatt.reborn.ps.Z 226 Transfer complete. 100000 bytes sent in 3.14159 seconds ftp> quit 221 Goodbye. unix> uncompress wolpert.lecture92.ps.Z unix lpr wolpert.lecture92.ps (or however you print out postscript) Many thanks to Jordan Pollack for maintaining this archive. From David_Redish at GS17.SP.CS.CMU.EDU Mon Apr 12 09:43:30 1993 From: David_Redish at GS17.SP.CS.CMU.EDU (David Redish) Date: Mon, 12 Apr 93 09:43:30 -0400 Subject: Sinusoidal arrays paper on Neuroprose (corrections/amplification) Message-ID: <10079.734622210@GS17.SP.CS.CMU.EDU> In referrence to: Neural Representation of Space Using Sinusoidal Arrays David S. Touretzky A. David Redish Hank S. Wan Some people have had trouble uncompressing the file. The problem should be fixed now. Some people have also noted that the name I gave for the extra figure was incorrect. The correct filenames are touretzky.sinusoidal-arrays.ps.Z touretzky.extra-fig.ps.Z Sorry for the inconvenience Dave Redish [I'm also including a more detailed version of the abstract. -- DST] EXTENDED ABSTRACT: Any vector in polar coordinates v=(r,phi) can be represented as a sine wave f(t) = r cos (omega t + phi), where r is amplitude, phi is phase, and omega is (constant) frequency. This is commonly known as a phasor. The advantage of phasor representation is that translation and rotation of a vector are both trivial operations. Translation is achieved by addition of sine waves, and rotation can be obtained by phase shifting or temporal delay. O'Keefe (1991) has suggested that rats might use phasors to encode angle and distance to landmarks. In his proposal, hippocampal theta provides the reference signal for determining phase. This temporal approach to encoding a sine wave has some drawbacks. The 7-12 Hz theta rhythm may be too slow to support real-time spatial reasoning tasks requiring rapid manipulation of phasors. Furthermore, maintaining even a modest angular resolution of 10 degrees relative to a roughly 10 Hz reference signal requires a temporal resolution of 3 msec. Although some specialized sensory systems are known to make much finer discriminations (e.g., acoustic imaging in bats and dolphins, or auditory localization in barn owls), we are reluctant to require this degree of temporal precision at the higher cognitive level associated with spatial reasoning. Instead, we suggest that phasor operations are more plausibly realized by re-coding the temporal dimension of the sine wave spatially, using populations of spiking neurons. We propose an architecture called the sinusoidal array for manipulating vectors in phasor form, and report the results of computer simulations. There is some experimental evidence that sinusoidal array representations may exist in rat parietal cortex and in rhesus motor or parietal cortex. We propose an experiment to test this hypothesis in rats. From ZENIOS at WILMA.WHARTON.UPENN.EDU Mon Apr 12 14:36:00 1993 From: ZENIOS at WILMA.WHARTON.UPENN.EDU (ZENIOS@WILMA.WHARTON.UPENN.EDU) Date: Mon, 12 Apr 93 14:36 EDT Subject: Cascade correlation learning algorithm to predict mortgage prepayments Message-ID: <9304121837.AA01667@noc2.dccs.upenn.edu> The March issue of The Journal of Fixed Income published a paper on the use of neural networks to predict mortgage prepayments. The precise reference is listed below, and copies of the article can be obtained from Marge Weiler, Decision Sciences Department, The Wharton School, University of Pennsylvania, Philadelphia, PA 19104 (215)898-5872 *************** Y. Yamamoto and S.A. Zenios, Predicting prepayment rates for mortgage-backed securities using the cascade-correlation learning algorithm, The Journal of Fixed Income, Vol. 2(4), pp.86--96, March 1993. From mel at cns.caltech.edu Mon Apr 12 14:59:49 1993 From: mel at cns.caltech.edu (Bartlett Mel) Date: Mon, 12 Apr 93 11:59:49 PDT Subject: Post-Doc Position Message-ID: <9304121859.AA09243@plato.cns.caltech.edu> --------- POSITION AVAILABLE ---------- Computation and Neural Systems Program California Institute of Technology A post-doctoral position will be available for Fall 1993 to work collaboratively on the development of a biologically-inspired system for 3-D visual object recognition. The position will be for one year with a possibility for renewal. The goal of the project is to construct an integrated software/hardware system for viewpoint invariant recognition of a large repertoire of real 3-D objects. The project will involve ideas and techniques from statistical pattern recognition and neural network learning, but with a strong emphasis on algorithms of relevance to biological vision, learning, and memory. Proficiency in a UNIX/C programming environment is necessary. Any of the following additional qualities is desirable: 1) knowledge of neurobiology and/or psychology of human and animal vision, 2) knowledge of classical computer vision techniques, and 3) experience in building large-scale software/hardware systems, particularly X-windows-based programming. Salary is $30,000/year. Interested applicants should send a letter describing their background and interests, a CV, a few relevant publications, and three letters of recommendation to: Dr. Bartlett Mel Division of Biology Caltech 216-76 Pasadena, CA 91125 (818)356-3643 mel at caltech.edu The California Institute of Technology is an equal opportunity/ affirmative action employer and encourages the applications of qualified women and minorities. From cohn at psyche.mit.edu Mon Apr 12 18:59:44 1993 From: cohn at psyche.mit.edu (David Cohn) Date: Mon, 12 Apr 93 18:59:44 EDT Subject: Uncertainty-based queries Message-ID: <9304122259.AA02257@psyche.mit.edu> Concerning the talk abstract "Uncertainty-Based Queries in Neural networks" which appeared here a few days ago: Quite a few people have pointed out that the use of measures of uncertainty to gather new data is not a new idea. I must apologize if my abstract made it appear that I thought it was. The idea can be traced back at least as far as the 40's (A. Wald, Ann. Math. Stat., Vol 14, 1943). The field of optimal experiment design, as it has become known to statisticians, is rather well developed. The most complete treatment of which I am aware is Fedorov (Theory of Optimal Experiments, Academic Press, 1972). Thanks also to Grace Wahba for providing additional references. It has been said, however, that the best new ideas in neural networks are coming from the 60's and 70's -- that people in the field are rediscovering the utility of tools (in statistics, control theory, etc.) that were developed "ahead of their time" and had only limited practical application before the advent of today's machine learning algorithms. My current research-in-progress, and the subject of the talk whose abstract appeared here earlier, is a practical examination of how we can take the techniques of optimal experiment design and apply them to the problems facing neural network researchers today. (D. MacKay addressed some aspects of this problem in his dissertation, and in a paper in Neural Computation 4(4)). As this *is* work in progress, I do not yet have a paper written on my results so far, but I will be happy to discuss them with any interested persons. Again, thank you all for your comments. Yes, I am aware of the body of results from optimal experiment design, and the point of my work is to see how these results can be applied to (excuse the expression) "practical problems" facing neural net researchers. I am sorry that my abstract did not make that clear. -David Cohn e-mail: cohn at psyche.mit.edu Dept. of Brain & Cognitive Science phone: (617) 253-8409 MIT, E10-243 Cambridge, MA 02139 From piero at dist.dist.unige.it Wed Apr 14 19:09:17 1993 From: piero at dist.dist.unige.it (Piero Morasso) Date: Wed, 14 Apr 93 19:09:17 MET DST Subject: ICANN'94 Preliminary Call for Papers Message-ID: <9304141709.AA26066@dist.dist.unige.it> -------------------------------------------------------------------- | ************************************************ | | * * | | * EUROPEAN NEURAL NETWORK SOCIETY * | | * PRELIMINARY CALL FOR PAPERS * | | * I C A N N ' 94 - SORRENTO * | | * * | | ************************************************ | | | | ICANN'94 (INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS)| | is the fourth Annual Conference of ENNS and it comes after | | ICANN'91(Helsinki), ICANN'92 (Brighton), ICANN'93 (Amsterdam). | | It is co-sponsored by INNS, IEEE-NC, JNNS. | | It will take place at the Sorrento Congress Center, near Naples, | | Italy, on May 26-29, 1994. | | There will be tutorials and invited talks by top-experts | | in the field who will also join the program committee. | | | | Interested authors are cordially invited to present their work | | in one of the following "Scientific Areas" (A-Cognitive Science; | | B-Mathematical Models; C- Neurobiology; D-Fuzzy Systems; | | E-Neurocomputing), indicating also an "Application domain" | | (1-Motor Control;2-Speech;3-Vision;4-Natural Language; | | 5-Process Control;6-Robotics;7-Signal Processing; | | 8-Pattern Recognition;9-Hybrid Systems;10-Implementation). | | | | DEADLINE for CAMERA-READY COPIES: December 15, 1993. | | ---------------------------------------------------- | | Detailed instructions will be given in a subsequent call. | | | | Conference Chair: Prof. Eduardo R. Caianiello, Univ. Salerno, | | Italy, Dept.Theoretic Physics; email: iiass at salerno.infn.it | | | | Conference Co-Chair: Prof. Pietro G. Morasso, Univ. Genova, | | Italy, Dept.Informatics, Systems,Telecommunication, | | email: morasso at dist.unige.it | | | | Tutorial Chair: Prof. John Taylor, Imperial College,London, UK, | | fax: +44 71 873 2017 | | | | Industrial Liaison Chair: Dr. Roberto Serra, Ferruzzi | | Finanziaria, Ravenna, fax: +39 544 35692/32358 | -------------------------------------------------------------------- From rob at comec4.mh.ua.edu Fri Apr 16 10:01:22 1993 From: rob at comec4.mh.ua.edu (Robert Elliott Smith) Date: Fri, 16 Apr 93 08:01:22 -0600 Subject: ICGA announcement and registration form Message-ID: <9304161301.AA16884@comec4.mh.ua.edu> Announcement and Registration Form: ICGA-93 The Fifth International Conference on Genetic Algorithms 17-21 July, 1993 University of Illinois at Urbana-Champaign The Fifth International Conference on Genetic Algorithms (ICGA-93), will be held on July 17-21, 1993 at the University of Illinois at Urbana-Champaign. This meeting brings together an international community from academia, government, and industry interested in algorithms suggested by the evolutionary process of natural selection. Topics of particular interest include: genetic algorithms and classifier systems, evolution strategies, and other forms of evolutionary computation; machine learning and optimization using these methods, their relations to other learning paradigms (e.g., neural networks and simulated annealing), and mathematical descriptions of their behavior. The meeting will include pre-conference tutorials, invited speakers, and workshops. A registration form is included below. For more ICGA-93 registration information, contact: Lori Costello Conferences & Institutes Univ. of Illinois 302 E. John St. Suite 202, Champaign, IL 61820 Telephone: (217) 333-2888 E-Mail: loric at ux1.cso.uiuc.edu Questions on the conference program should be directed to icga93 at unmvax.cs.unm.edu. Other questions should be directed to rob at comec4.mh.ua.edu. Tutorials--Levis Faculty Center ICGA '93 will begin with the presentation of three parallel tutorial sessions. Conference attendees may attend one of these sessions for a supplementary fee (see registration form). Tutorial 1: Introduction to Genetic Algorithms Overview of Genetic Algorithms (90 minutes), Melanie Mitchell-- What genetic algorithms are; how, why, and by whom they were invented; how and why they work; comparisons with other algorithms; how to find out more about the genetic algorithm field; foundations of GA theory; genetic algorithms and artificial life; partial bibliography. Genetic Algorithm Applications (90 minutes), Lawrence Davis-- What kind of real-world problems are appropriate for genetic algorithms; design choices that must be made when applying genetic algorithms to real problems; partial survey of existing applications; partial survey of existing tools; some case histories. Tutorial 2: Advanced Genetic Algorithm Topics Genetic Algorithm Theory (90 minutes), Darrell Whitley-- The schema theorem and its ramifications; deception; recent approaches to the study of genetic algorithm performance; recent approaches to the study of genetic algorithm failure. Classifier Systems and Modeling (90 minutes), Rob Smith-- Introduction to classifier systems; recent advances in classifier system theory and practice; classifier systems as modeling tools; genetic algorithms and neural networks; genetic algorithms and artificial life. Tutorial 3: Spotlighted Technologies Evolutionary Programming (45 minutes), David Fogel-- Description and overview of evolutionary programming; history of the field; relation of evolutionary programming to biological evolution; theoretical aspects of the field; survey of existing applications. Evolution Strategies (45 minutes), Thomas Back-- Description and overview of evolution strategies; comparison with other technologies; engineering solutions with evolution strategies; survey of existing applications. Genetic Programming (90 minutes), John Koza-- Description and overview of genetic programming; example applications; future directions; brief video demonstrations. TENTATIVE SCHEDULE: Saturday, July 17, 1993 12-3:00 pm Registration Levis Faculty Center 1-5:00 pm Tutorials Levis Faculty Center 7:00 pm Reception/Registration Levis Faculty Center Sunday, July 18, 1993 8am-5:00 pm Registration Krannert Center (KCPA) 8:30-9:00 am Coffee KCPA 9-10:15 am Invited Speaker KCPA 10:15-11 am Break KCPA 11-12:30 pm Technical Sessions KCPA/Levis 12:30-2 pm Lunch KCPA 2-3:30 pm Technical Sessions/ Registration Levis 3:30-4 pm Break Levis 4-5:30 pm Technical Sessions Levis 7:00 pm Banquet Chancellor Hotel 1501 S. Neil, Champaign Monday, July 19, 1993 8am-5:00 pm Registration KCPA 8:30-9:00 am Coffee KCPA 9-10:15 am Invited Speaker KCPA 10:15-11 am Break KCPA 11-12:30 pm Technical Sessions KCPA/Levis 12:30-2 pm Lunch KCPA 2-3:30 pm Technical Sessions/ Registration Levis 3:30-4 pm Break Levis 4-5:30 pm Technical Sessions Levis 7:00 pm Poster Session Levis Tuesday, July 20, 1993 8:30-9:00 am Coffee KCPA 9-10:15 am Invited Speaker KCPA 10:15-11 am Break KCPA 11-12:30 pm Technical Sessions KCPA/Levis 12:30-2 pm Lunch KCPA 2-3:30 pm Technical Sessions Levis 3:30-4 pm Break Levis 4-5:30 pm Technical Sessions Levis Wednesday, July 21, 1993 8:30-9:00 am Coffee Levis 9-10:30 am Technical Sessions Levis 10:30-11 am Break Levis 11-12:30 pm Technical Sessions Levis 12:30-2 pm Break Levis 2-3:30 pm Business Meeting Levis Invited Speakers David Campbell, Head, Dept. of Physics, University of Illinois. Topic: Dynamical Systems and Evolution John Holland, Professor, Dept. of Psychology, University of Michigan. Topic: Using The Schema Theorem To Counter Hitchhiking And Premature Convergence Gunter Wagner, Professor, Dept. of Biology, Yale University. Topic: Evolutionary Biology Papers (preliminary list) Erik R. Altman, "A Novel Methodology Using Genetic Algorithms for the Design of Caches and Cache Replacement Policy" Peter J. Angeline, "Competitive Environments Evolve Better Solutions for Complex Tasks" Thomas Back, "Optimal Mutation Rates in Genetic Search" Jerzy W. Bala, "Learning to Detect Targets Using Scale-Space and Genetic Search" David Beasley, "Reducing Epistasis in Combinatorial Problems by Expansive Coding" Pierre Bonelli, "A New Approach to Fuzzy Classifier Systems" Ralph Bruns, "Direct Chromosome Representation and Advanced Genetic Operators for Production Scheduling" Helen G. Cobb, "Genetic Algorithms for Tracking Changing Environments" Yuval Davidor, "The ECOlogical Framework II: Improving GA Performance With Virtually Zero Cost" Lawrence Davis, "A Genetic Algorithm for Survivable Network Design" Fred F. Easton, "A Distributed Genetic Algorithm for Employee Staffing and Scheduling Problems" Larry J. Eshelman, "Crossover's Niche" Andrew Fairley, "An Investigation into Possible Causes of, and Solutions to, Rule Strength Distortion in the Bucket Brigade" David S. Feldman, "Fuzzy Network Synthesis and Genetic Algorithms" Stuart J. Flockton, "Pole-Zero System Identification Using Genetic Algorithms" Carlos Fonseca, "Genetic Algorithms for Multiobjective Optimization: Formulation, Discussion and Generalization" David E. Goldberg, "Mixing in Genetic Algorithms" David E. Goldberg, "Rapid, Accurate Optimization of Difficult Problems Using Fast Messy Genetic Algorithms" V. Scott Gord, "Serial and Parallel Genetic Algorithms as Function Optimizers" Frederic Gruau, "Genetic Synthesis of Modular Neural Networks" H. Altay Guvenir, "A Genetic Algorithm for Classification by Feature Partitioning" Raphael T. Haftka, "Genetic Algorithms for Placing Actuators on Space Structures" Inman Harvey, "The Puzzle of the Persistent Question Marks: A Case Study of Genetic Drift" Abdollah Homaifar, "A New Approach on the Traveling Salesman Problem by the Genetic Algorithms" Jeffrey Horn, "Finite Markov Chain Analysis of Genetic Algorithms with Niching" Shu-Yuen Hwang, "A Genetic Algorithm with Disruptive Selection" Hitoshi Iba, "System Identification using Structured Genetic Algorithms" Terry Jones, "Reverse Hillclimbing, Genetic Algorithms and the Busy Beaver Problem" Kate Juliff, "A Multi-chromosome Genetic Algorithm for Pallet Loading" Bryant A. Julstrom, "A Genetic Algorithm for the Rectilinear Steiner Problem" Michelle D. Kidwell , "Using Genetic Algorithms to Schedule Distributed Tasks on a Bus-Based System" Kenneth E. Kinnear, Jr., "Generality and Difficulty in Genetic Programming: Evolving a Sort" Michael Lee, "Dynamic Control of Genetic Algorithms Using Fuzzy Logic Techniques" David M. Levine, "A Genetic Algorithm for the Set Partitioning Problem" Mauro Manela, "Fitting Spline Functions to Noisy Data Using a Genetic Algorithm" Raul San Martin, "Genetic Algorithms for the Optimization of Integrated Circuits Synthesis" Tsutomu Maruyama, "A Fine-Grained Parallel Genetic Algorithm for Distributed Parallel Systems" Laurence D. Merkle, "Comparison of Parallel Messy Genetic Algorithm Data Distribution Strategies" Robert R. Meyer, "A Genetic Algorithm for Diversity Minimization and Its Parallel Implementation" Byung R. Moon, "Hyperplane Synthesis for Genetic Algorithms" Toshinori Munakata, "A Genetic Algorithm Applied to the Maximum Flow Problem" Jim Oliver, "Discovering Individual Decision Rules: An Application of Genetic Algorithms" Norihiko Ono, "A Genetic Algorithm for Channel Routing Problem" Francesco Palmieri, "Diversification Role of Crossover in the Genetic Algorithms" L.M. Patnaik, "Binomially Distributed Populations for Modelling GAs" W.F. Punch, "Further Research on Feature Selection and Classification Using Genetic Algorithms" Nicholas J. Radcliffe, "A Study in Set Recombination" Connie Loggia Ramsey, "Case-Based Initialization of Genetic Algorithms" Colin Reeves, "Using Genetic Algorithms with Small Populations" Gary Roberts, "Dynamic Planning for Classifier Systems" Steve G. Romaniuk, "Evolutionary Growth Perceptions" Peter Ross, "A Promising GA Approach to Job-Shop Scheduling and Re-Scheduling Problems" J. David Schaffer, "Designing Multiplierless Digital Filters Using Genetic Algorithms" Michael J. Shaw, "Joint Lot Sizing and Sequencing with Genetic Algorithms for Scheduling: Evolving the Chromosome Structure" Man-Tak Shing, "Genetic Algorithms for the Development of Real-Time Multi-Heuristic Search Strategies" Marc Shoenauer, "Constrained GA Optimization" R. Shonkwiler, "Parallel Genetic Algorithms" Michael M. Skolnick, "Using Genetic Algorithms in Engineering Design Optimization with Non-Linear Constraints" Alice E. Smith, "Genetic Optimization Using A Penalty Function" William Spears, "On the State of Evolutionary Computation" Joe Suzuki, "A Markov Chain Analysis on A Genetic Algorithm" Walter Alden Tackett, "Genetic Programming for Feature Discovery and Image Discrimination" Dr. David M. Tate, "Expected Allele Coverage and the Role of Mutation" Sam R. Thangiah, "Vehicle Routing and Time Deadlines Using Genetic and Local Algorithms" Bruce Tidor, "An Analysis of Selection Procedures with Particular Attention Paid to Proportional and Boltzmann Selection" Shigeyoshi Tsutsui, "Forking Genetic Algorithm with Blocking and Shrinking Modes (FGA)" Kirk Twardowski, "Credit Assignment for Pole Balancing with Learning Classifier Systems" Ron Unger, "A Genetic Algorithm for 3D Protein Folding Simulations" Thomas Uthmann, "Training Kohonen Feature Maps in Different Topologies: an Analysis Using Genetic Algorithms" Benjamin W. Wah, "Scheduling of Genetic Algorithms in a Noisy Environment" Roger L. Wainwright, "Multiple Vehicle Routing with Time and Capacity Constraints Using Genetic Algorithms" Hirokazu Watabe, "A Study on Genetic Shape Design" Willfried Wienholt, "An Advanced Genetic Algorithm for Parameter Optimization Problems" Peter Willett, "Searching Databases of Two-Dimensional and Three-Dimensional Chemical Structures Using Genetic Algorithms" Jing-Jye Yang, "Query Optimization in Information Retrieval Using Genetic Algorithms" Xiaodong Yin, "A Fast Genetic Algorithm with Sharing Scheme Using Cluster Analysis Methods in Multimodal Function Optimization" Byoung-Tak Zhang, "Genetic Programming of Minimal Neural Nets Using Occam's Razor" Raed Abu Zitar, "Regulator Control via Genetic Search Assisted Reinforcement Learning" Posters (preliminary list) Fabrizio Baiardi, "Nested Hybrid Genetic Algorithms for System Configuration and Program Mapping in Massively Parallel Systems" Ellie Baker, "Evolving Line Drawings" Wolfgang Banzhaf, "Genetic Programming for Pedestrians" Rik Belew, "Evolving Aesthetic Sorting Networks Using Developmental Grammars" Susan E. Carlson, "A Comparative Evaluation of Search Methods Applied to Catalog Selection" Hugh M. Cartwright, "The Application of the Genetic Algorithm to Two-Dimensional Strings: The Source Apportionment Problem" Joseph C. Culberson, "Crossover Versus Mutation in the De Jong Functions: Fueling the Debate: TGA versus GIGA" Fikret Ercal, "Genetic Algorithms for Vertex Splitting in DAGs" David Fan, "GADELO: A Multi-Population Genetic Algorithm Based on Dynamic Exploration of Local Optima" Terence C. Fogarty, "Reproduction, Ranking, Replacement and Noisy Evaluations: Experimental Results" Takeshi Furuhashi, "A Proposal of Hierarchical Fuzzy Classifier Systems" Inman Harvey, "Genetic Convergence in a Species of Evolved Robot Control Architectures" Brynn Hibbert, "Display of Chemical Structures in Two Dimensions and the Evolution of Molecular Recognition" Akio Ishiguro, "A Genetic Algorithms' Application to Inverse Problems in Electromagnetics" Takashi Iwamoto, "Topological Aspects of Genetic Algorithms" Antonia J. Jones, "A Schemata Theorem for Trees" Hillol Kargupta, "Information Transmission in Genetic Algorithm and Shannon's Second Theorem" Hiroaki Kitano, "A Hybrid Search for Genetic Algorithms: Combining Genetic Algorithms, TABU Search, and Simulated Annealing" Luis R. Lopez, "Inverse Relationship Between Complexity and Probability of Full Deception in Trap Functions" Sushil J. Louis, "Pareto Optimality, GA-Easiness and Deception (Extended Abstract)" Heinz Muhlenbein, "Optimal Interaction of Mutation and Crossover in the Breeder Genetic Algorithm" R. Maenner, "Parallel Execution of Sequentially Coded Standard Genetic Algorithms on the NERV Multiprocessor" Samir W. Mahfoud, "Simple Analytical Models of Genetic Algorithms for Multimodal Function Optimization" Vittorio Maniezzo, "Granularity Evolution" Andras Markus, "Dual Insights into Genetic Algorithms" Melanie Mitchell, "When Will a Genetic Algorithm Outperform Hill-Climbing?" Masaharu Munetomo, "An Efficient Migration Scheme for Subpopulation-Based Asynchronously Parallel Genetic Algorithms" David Orvosh, "Shall We Repair? Genetic Algorithms, Combinatorial Optimization, and Feasibility Constraints" Kihong Park, "A Lower-Bound Result on the Power of Genetic Algorithms" Sandip Sen, "Improving Classification Accuracy through Performance History" Robert E. Smith, "Adaptively Resizing Populations: An Algorithm and Analysis" Graham Spencer, "Automatic Generation of Programs for Crawling and Walking" Chuen-Tsai Sun, "Using Genetic Algorithms in Structuring a Fuzzy Rulebase" Hans-Michael Voigt, "Multivalued Evolutionary Algorithms" Michael D. Vose, "The Genetic Algorithm Fractal" Darrell Whitley, "Toward Models of Island and Cellular Parallel Genetic Algorithms" Masayuki Yanagiya, "A Simple Mutation-Dependent Genetic Algorithm" Bernard P. Zeigler, "Asynchronous Genetic Algorithms on Parallel Computers" ICGA-93 Conference Committee: Conference Co-Chairs: David E. Goldberg, Univ. of Illinois at Urbana- Champaign; J. David Schaffer, Philips Labs Publicity: Robert E. Smith, Univ. of Alabama Program Chair: Stephanie Forrest, Univ. of New Mexico Financial Chair: Larry J. Eshelman, Philips Labs Local Arrangements: David E. Goldberg, Univ. of Illinois at Urbana- Champaign Financial supporters: Navy Center for Applied Research in Artificial Intelligence, Naval Research Laboratory; Philips Laboratories, North American Philips Corporation GENERAL INFORMATION Location: The conference will be held at two locations on the University of Illinois campus--the Krannert Center for the Performing Arts located at 500 South Goodwin, Urbana, and the Levis Faculty Center located at 919 West Illinois, Urbana (directly east of Krannert). ICGA '93 is a non-smoking conference. Smoking is allowed in designated areas only. Transportation: Champaign-Urbana is located 135 miles south of Chicago on Interstates 72, 74, and 57. By Car: >From Chicago: Take I-57 south to I-74 east which runs along the north edge of Champaign-Urbana. Take the Lincoln Avenue exit south. Once you reach campus, turn right on Illinois Street. Campus Parking: Pay parking is available in the lot adjacent to the Levis Faculty Center and under the Krannert Center (both accessible from Illinois Street). Do not park in any area marked "reserved" as campus parking is enforced and you will be towed. By Air: >From Champaign-Urbana's Willard Airport: Currently, American Airlines' American Eagle Service, Trans World Express, and US Air Express serve Willard Airport. Corky's Limousine Service is available and meets all incoming flights. The cost from Willard to most hotels in Champaign-Urbana is $8. If you need to contact Corky's, you may call 217/352-3121. By Train: AMTRAK service is also available from Chicago and points south. Weather: The weather in Illinois can vary to extremes. Please be prepared to dress in layered, cool clothing as July is normally hot (80 - 100 ) and very humid. Rain wear is also suggested. On-Campus Recreation: If you wish to take advantage of the recreation facilities on campus, you may purchase an IMPE (Intramural-Physical Education) pass for $5 per day upon showing your name badge at each recreation facility. Messages: If someone needs to reach you during the conference, they may call the Levis Faculty Center at 217/333-6241 and leave a message. A message board will be placed at this conference site. Lodging: Accommodations may be obtained at the following hotels/motels. A shuttle service will be available for transportation from your hotel to/from the conference sites. All hotel reservations should be made in advance by telephoning or writing the individual hotels. Be sure to mention that you are attending the Genetic Algorithms conference, as a block of rooms has been reserved for those attending this conference. We have listed the special conference rates beside the hotel/motel. Make your reservations early as the block of rooms will be released for "first come, first serve" reservations after June 16, 1993. Jumer's Castle Lodge 209 S. Broadway Urbana, IL 61801 Located about 1/4 mile from the campus. Within brisk walking distance. Toll free 800/285-8637 Single Double $60.00 $70.00 Plus tax Plus tax University Inn 302 E. John Street Champaign, IL 61820 Located about 1/2 mile from the campus. Within brisk walking distance. 217/384-2100; Toll free 800/252-1368 in Illinois; Toll free 800/322-8282 outside IL Single Double $54.00 $61.00 Plus tax Plus tax Travelodge 409 W. University Urbana, IL 61801 Located about 1 mile from the campus. Toll free 800/255-3050 Single Double $33.00 Plus tax Campus Inn-University (Days Inn) 1701 S. State Champaign, IL 61820 Located about 1 mile from the campus 217/359-8888 Single Double $30.00 $35.00 Plus tax Plus Tax King or Queen Busey-Evens Dormitory 1111 West Nevada Urbana, IL 61801 Located on campus 217/333-1766 $23.15 Plus tax Community Bath Registration Fee: Registrations received before 6/12/93 are $250 for participants and $100 for students. All registrations received on or after 6/12/93 and walk-in registrations at the conference will be $295 for participants and $125 for students. This includes entry to all technical sessions, 3 lunches, coffee breaks, reception Saturday evening, conference materials, and conference proceedings. Attendee and guest tickets for the banquet and guest tickets for the Sunday reception may be purchased at an additional cost (see attached registration form). Also, there is a separate fee for the tutorials. A limited fund has been set aside to assistant students and scientists with their travel expenses. Students should have their advisor certify their student status and that sufficient funds are not available. If you are interested in obtaining such assistance and need travel support, send a letter before May 22, 1993 describing your situation and needs to: Larry Eshelman, Philips Laboratories, 345 Scarborough Road, Briarcliff Manor, NY 10510. Address questions to: lje at philabs.philips.com. To Register: Early registration is recommended. There are four ways you may register. Complete and mail the attached form or phone (217)244-7659 to register. Please be sure to call our office if your registration may be late in arriving. You may also FAX your registration to (217)333-9561. You may receive an e-mail registration by contacting loric at ux1.cso.uiuc.edu If you register by phone, fax, or e-mail, please remember to send a copy of the registration form with your payment to the Accounting Business Office within one week. Should you have additional questions, please call Lori Costello at 217/333-2888 or e-mail loric at ux1.cso.uiuc.edu. ---------------------------------------------- REGISTRATION FORM: The 5th International Conference on Genetic Algorithms July 17-21, 1993 UFAS Acct. #1-3-63141-0660 Four Easy Ways To Register 1. Fill out the form and mail with payment to: University of Illinois at Urbana-Champaign Accounting Business Office, Room 162 Henry Administration Building, 506 South Wright Street, Urbana, IL 61801. 2. Call 217-244-7659 and the registration team will take your registration over the phone. 3. Call 217-333-9561 to FAX your registration. 4. E-mail: receive an e-mail form by contacting loric at ux1.cso.uiuc.edu. The deadline for e-mail registrations and to receive all e-mail registration fees is July 9, 1993. IF YOU REGISTER BY PHONE, FAX, OR E-MAIL: Please remember to send a hard copy of the registration form with your payment to the Accounting Business Office within one week of registration. Registration/Badge Information Please print or type __________________________________________________________________ Last Name First Name MI __________________________________________________________________ Affiliation/Business __________________________________________________________________ Address __________________________________________________________________ City State Zip __________________________________________________________________ Country __________________________________________________________________ Business Phone Home Phone REGISTRATION FEES: (all figures in US Dollars) Indicate your selection Conference Registration Fee Registration before 6/12/93 On or after 6/12/93 Participant $250 Participant $295 Student* $100 Student* $125 Tutorial for July 17 Before 6/12/93 On or after 6/12/93 Participant $75 Participant $95 Student $25 Student $50 Please specify choice: Tutorial I:__________ Tutorial II: __________ Tutorial III: __________ Banquet Tickets** Adult $30 # of tickets_______ amount_______ Child $10 # of tickets_______ amount_______ Additional Reception Tickets** Saturday $10 # of tickets_______ amount_______ Total Payment ________________________(U.S. Dollars) Method of Payment ______ Check enclosed (make payable to the University of Illinois, US banks only, send check with form to Accounting Business Office) ______ I prefer to charge on credit card Visa______ Mastercard______ American Express______ Card Number__________________________________ Exp. Date__________ Card Holder Signature______________________________________________ *Students must have university student ID at registration **Please purchase additional tickets now---you will be unable to buy them upon arrival PLEASE MAIL THIS FORM WITH YOUR PAYMENT TO: University of Illinois at Urbana-Champaign Accounting Business Office, Room 162 Henry Administration Building 506 South Wright Street Urbana, IL 61801 From mao at cps.msu.edu Thu Apr 15 22:08:43 1993 From: mao at cps.msu.edu (Jianchang Mao) Date: Thu, 15 Apr 93 22:08:43 EDT Subject: New Book Announcement Message-ID: <9304160208.AA08016@pixel.cps.msu.edu> Dear connectionists, A new book, "Markov Random Fields: Theory and Application", edited by Drs. Rama Chellappa and Anil Jain, has been published by Academic Press, Inc. recently. This book contains chapters written by many distinguished researchers in the field. It represents the work done by most of the leading researchers in the world and should be a good reference text for engineers, computer scientists, applied statisticians and mathematicians, and physicists who are interested in the basic research issues and state-of-the-art in MRF models. The link between Markov random field and neural network models has been investigated by a number of researchers. The inherent parallel nature of the MRF algorithms can be suitably mapped onto an artificial neural network architecture. Therefore, this book will be a good reference text for neural network researchers too. Best, Jianchang Mao Computer Science Department Michigan State University East Lansing, MI 48824, USA From soller at asylum.cs.utah.edu Fri Apr 16 15:47:30 1993 From: soller at asylum.cs.utah.edu (Jerome Soller) Date: Fri, 16 Apr 93 13:47:30 -0600 Subject: Utah Workshop on the Applications of Intelligent and Adaptive Systems Message-ID: <9304161947.AA06896@asylum.cs.utah.edu> The University of Utah Cognitive Science Group's Industrial Advisory Board presents the first Utah Workshop on the "Applications of Intelligent and Adaptive Systems." This will be held at the Salt Lake City VA Medical Center's multipurpose room, Building 8, on May 10th. This event is free and open to the public. A listing of speakers, titles, abstracts, e-mail addresses, phone numbers, parking information, etc.., is provided at the end of this notice. For listings of relevant publications, biographical sketches of the speakers, or a hard copy of a map of the VA campus and appropriate parking, contact Jerome Soller (soller at asylum.cs.utah.edu,582-1565, ext. 2469). Hopefully, we will have a videotape of this event available public domain at a later point. This workshop complements the yearly Psychology Department's William F. Prokasy Lecture by Dr. Irving Biederman, Head of the Cognitive and Behavioral Neuroscience Program at the University of Southern California. Dr. Biederman will speak on Tuesday, May 11, at 5:00 p.m. in BEH SCI 110 at the University of Utah. The title is "Shape Recognition in Mind and Brain." The official notice from Kim Poulson is included after the workshop description. Summary (abstracts and contact information are provided at the end of this notice): Talk 1: 10:00-10:45 The Utah State University Space Dynamics Laboratory, An Introduction Presented by J Steven Hansen, Ph.D. Director, Instrument and Data Evaluation Center Space Dynamics Laboratory Associate Research Professor, Department of Electrical and Computer Engineering Department of Physics Utah State University Talk 2: 10:45-11:30 Active Noise and Vibration Control: Structures, Algorithms, and Applications Scott C. Douglas, Ph.D. Department of Electrical Engineering University of Utah Talk 3: 11:30 - 12:15 A COMPUTERIZED DECISION SUPPORT SYSTEM FOR CRITICAL CARE: MANAGEMENT OF MECHANICAL VENTILATION IN PATIENTS WITH ARDS Thomas D. East, Ph.D.: Director of informatics research in the pulmonary division at LDS Hospital(Intermountain Health Care). Associate professor of anesthesiology, bioengineering and medical informatics at the University of Utah. Lunch break: 12:15-1:45 Talk 4: 1:45-2:30 "Neural Networks for Classification, Signal Processing, and Control in Patient Monitoring" Dwayne Westenskow, Ph.D. Acting Director of Institute of Life Support in Space and Professor, U. of Utah Department of Anesthesiology (additional appointments in Bioengineering, Surgery, and Medical Informatics). Talk 5: 2:30-3:15 Towards a General Self-Organizing Learning Model Tony Martinez, Ph.D., Director of the Neural Networks and Machine Intelligence Research Group, Brigham Young University Assistant Professor, Department of Computer Science and Department of Electrical and Computer Engineering, Brigham Young University. Talk 6: 3:15-4:00 Neil Cotter, Ph.D. Consulting Engineer, Geneva Steel Research Assistant Professor, Electrical Engineering, University of Utah "Neural Networks, Fuzzy Logic, and Triangulation in Process Control" (801-227-9865) Sincerely, Dick Burgess, U. of Utah Department of Physiology and Program Director, U. of Utah Cog. Sci. Group (801-581-4072) Dale Sanders, Chairman of Industrial Advisory Board to U. of Utah Cognitive Science Group and Senior Technical Member, TRW Corporation (dsanders at bmd.trw.com, 801-625-8343) Robert L. Angell, Principal, Applied Information and Management Systems and Small Business Representative to U. of Utah Cognitive Science Group (bangell at cs.utah.edu, 801-583-8544) Jerome B. Soller, VA GRECC and U. of Utah Department of Computer Science (soller at asylum.cs.utah.edu, 801-582-1565, ext. 2469) Abstracts: ---------------------------------------------------------------------- Active Noise and Vibration Control: Structures, Algorithms, and Applications Scott C. Douglas, Ph.D. Department of Electrical Engineering University of Utah Active noise and vibration control is a method for cancelling unwanted sound or vibration by generating and introducing an equal-but-opposite acoustic signal into the noise environment. Current research and application developments in this field include active mufflers for automobiles, active quieting of machine noise on factory floors, active vibration mounts for airplane engines, active noise suppressors for air ducts, and active suppression of wall vibration for apartment dwellings. In this talk, I will provide an overview of the technology needed for active noise control systems. In particular, I will discuss the digital signal processing hardware and multichannel adaptive control algorithms required for noise cancellation across large acoustic regions. Results from an active noise suppression system for quieting an air conditioner compressor will be presented. ------------------------------------------------------------------------ Neil Cotter, Ph.D. Consulting Engineer, Geneva Steel Research Assistant Professor, E.E. Department, University of Utah "Neural Networks, Fuzzy Logic, and Triangulation in Process Control" (801-227-9865) Many process control problems in industry require the approximation of nonlinear functions of several variables. This presentation will include a tutorial showing that the following approximation methods are structurally similar to Fourier series: linear regression, neural networks, radial basis functions, and fuzzy logic. The speaker will contrast these methods with a practical interpolation method called triangulation. -------------------------------------------------------------------------- "Neural Networks for Classification, Signal Processing, and Control in Patient Monitoring" Dwayne R. Westenskow, Ph.D. Department of Anesthesiology (801-581-6393, drw at cc.utah.edu) Artificial neural networks learn from examples to construct a function which maps input variables to a desired output. The mapping provides closed-loop control where the inputs are the variables to be controlled, and the output is the drive signal for an actuator. Neural network control will be illustrated with the truck backing up example, introducing the concept of supervised learning. The neural network mapping similarity provides for the classification of data, as will be illustrated with an intelligent anasthesia alaram system. Because the mapping function extrapolates between individual data points, the neural network provides signal processing, i.e., filtering and noise and artifact rejection. This will be illustrated by showing the neural network processing of oscillometric blood pressure curves and cardiac output by thermal dilution. In both of these examples, the neural network provides a nonlinear mapping which compensates for the overestimation at low values and underestimation at high values, which occurs with traditional linear algorithms. Success in processing Doppler signals for the detection of air embolism illustrates how the mapping function is constructed using training data rather than expert knowledge. --------------------------------------------------------------------- Dr. Tony Martinez, Director of the Neural Networks and Machine Intelligence Research Group, Brigham Young University Assistant Professor, Department of Computer Science and Department of Electrical and Computer Engineering, Brigham Young University, Provo, UT Towards a General Self-Organizing Learning Model (martinez at cs.byu.edu, 801-378-6464) A new class of connectionist architectures is presented called ASOCS (Adaptive Self-Organizing Concurrent Systems). ASOCS models support efficient computation through self-organized learning and parallel execution. Learning is done through the incremental presentation of rules and/or examples. Data types include Boolean and multi-state variables; recent models support analog variables. The model incorporates rules into an adaptive logic network in a parallel and self organizing fashion. The system itself resolves inconsistencies and generalizes as the rules are presented. After an introduction to the ASOCS paradigm, the talk introduces current research thrusts which significantly increase the power and applicability of ASOCS models. Current application targets include adaptive network routing, speech recognition, automated document updating, and general classification problems. ------------------------------------------------------------------------ Author Information: Thomas D. East, Ph.D., Pulmonary Division, LDS Hospital, 8th Ave and C St., Salt Lake City, UT, 84143, 801-321-3503 phone, 801-321-1671 fax, teast at fenta.med.utah.edu Audio Visual Media used: 35 mm slide projector and VHS video projector. A COMPUTERIZED DECISION SUPPORT SYSTEM FOR CRITICAL CARE: MANAGEMENT OF MECHANICAL VENTILATION IN PATIENTS WITH ARDS T.D. East, A.H. Morris, C.J. Wallace, A. T. Kinder, W.D. Littman*, J.S. Gochberg* Pulmonary Division, LDS Hospital,Salt Lake City, Utah 84143 * ACT/PC, 6501 Watts Road, Suite 115, Madison, WI 53719 Thomas D. East,Ph.D.: Associate professor of anesthesiology, bioengineering and medical informatics at the University of Utah. Director of informatics research in the pulmonary division at LDS Hospital. MEBE and Ph.D. in bioengineering from the U of U. My research interests are in the applications of computers to critical care. In particular much of my work has been in the area of rule based decision support systems and knowledge engineering. The care of critically ill patients is increasingly complex and clinicians frequently suffer from information overload. It is difficult, if not impossible to assess all this information and generate a systematic and reasonable therapy plan. Computerized decision support systems can assist the clinician with many of the tasks such as the iterative management of mechanical ventilation. This decision support not only standardizes care but may improve the quality of care by reducing mistakes. This standardization of care also makes it possible to thoroughly characterize the current treatment process in order to compare it to a proposed new therapy as part of an ongoing continuous quality improvement (CQI) program. A computerized decision support system for the management of mechanical ventilation (respiratory evaluation, oxygenation, ventilation, weaning and extubation) in patients with adult respiratory distress syndrome has already been developed and clinically validated at the LDS Hospital (1, 2) . The protocol logic was developed using our existing consensus generating physician group and was implemented on the HELP system (3) . The computerized decision support system was used for over 35,000 hours in 111 Adult Respiratory Distress Syndrome patients and has controlled decision making 95% of the 24 hour day. The survival rate was 67%, higher than the expected 31-33% from historical data (4, 5) , p < 0.05. These results have demonstrated that computerized decision support for critical care is feasible. We are in the process of conducting a prospective randomized clinical trial to test efficacy of computerized protocols in 400 patients with ARDS at two different clinical sites; KDMC a county hospital in the Watts district of Los Angeles, CA and Hermann Hospital, a private hospital in Houston affiliated with University of Texas Medical School (H0: There is no difference in efficacy between protocol and non-protocol controlled critical care). The knowledge base (set of protocol logic rules) was transferred from the HELP system at LDS Hospital to a PC based ICU computer system known as ARGUS Windows (ACT/PC, Madison , WI). ARGUS Windows runs under QNX V4.1 and QNX windows V2.03. The rules were implemented using a rule based decision support engine designed by ACT/PC. The engine is a finite state automata written in C for QNX and QNX Windows. The ARGUS Windows system has been installed at all 12 beds of the surgical ICU at KDMC. This system is now in routine use for respiratory care charting and the decision support system has been used to successfully care for 10 ARDS patients in a pilot study of feasibility. In the randomized trial, will define efficacy using a hierarchical four level approach; Efficacy F a)Survival, b) Length of ICU Stay, c) Morbidity, d) Incidence and severity of barotrauma. Generalizablity of the computerized decision support system will be determined by examining; 1) Percent of total time in the trial during which protocols controlled patient care. 2) Number of protocol instructions which were not followed. 3) Number of objections to protocol logic which, based on medical evidence, forced a change in the logic. To our knowledge this is the first prospective randomized clinical trial designed to test the impact of computerized critical care decision support on patient outcome. References: 1. East T, et al. Int J Clin Monit Comput 1992;8:263-269. 2. Morris AH, et al. Am Rev Respir Dis 1992;145(4):A184. 3. Pryor TA, et al. The HELP system development tools. In: Implementing health care information systems. New York: Springer-Verlag, 1989: 365-383. 4. Zapol WM, et al. The adult respiratory distress syndrome at Massachusetts General Hospital, Etiology progession and survival rates,1978-1988. In: Zapol WM, Lemaire F, ed. Adult Respiratory Distress Syndrome. New York: Marcel Dekker, Inc, 1991: 367-380. 5. Artigas A, et al. Clinical presentation, prognostic factors, and outcome of ARDS in the European Collaborative Study (1985-1987).In:Same book as ref 4, 1991: 37-63. Acknowledgements: This work was supported by NHLBI grant #HL36787, AHCPR grant HS06594, Siemens Ventilators, ACT/PC, the Respiratory Distress Syndrome Foundation and the Deseret Foundation (LDS Hospital). My biographical sketch: Thomas D. East,Ph.D.: Associate professor of anesthesiology, bioengineering and medical informatics at the University of Utah. Director of informatics research in the pulmonary division at LDS Hospital. MEBE and Ph.D. in bioengineering from the U of U. My research interests are in the applications of computers to critical care. In particular much of my work has been in the are of rule based decision support systems and knowledge engineering. ------------------------------------------------------------------------ The Utah State University Space Dynamics Laboratory, An Introduction Presented by Dr. J Steven Hansen (801-750-4850, jsh at sdl.usu.edu) Director, Instrument and Data Evaluation Center Space Dynamics Laboratory Associate Research Professor, Department of Electrical and Computer Engineering Department of Physics Utah State University, Logan, Utah Abstract This talk will provide description of the Space Dynamics Laboratory and its capabilities, particularly in the areas of data, signal, and image processing. The presentation will include a brief history of SDL over the past 30 years, an overview of the past and current projects at SDL and the Instrument and Data Evaluation Center (IDEC), a look at the current computing and image/signal processing capabilities IDEC. A look at the future and particular area of possible interest to the community will be addressed. ------------------------------------------------------------------------ Lunch: A group of us will go to lunch at a our own expense. If you wish to join that group, contact Jerome Soller to have a spot reserved. Directions to the VA Hospital: For directions, call 582-1565, and ask for learning resources. The address is 500 Foothill Boulevard Parking: The VA has limited parking for visitors behind building 8. If you come in the main entrance, make a right past building 1 and 14, continue through one of the staff parking lots. Make a right before reaching the staff parking lot between building 5 and 8. You should pass between buildings 8 and 9, and park behind building eight (not nine). Rough Map: Dash lines represent a desired path. Main Entrance:-- 1 | | 14 | 5 Don't Park | Don't Park Here Here | ----------| |---|Don't | Park | Here | 9 | 8 6 |___ Don't Park Don't Park Park Here Here Here It is advisable to have a map of the VA campus mailed to you, and that map and postage will be free of charge if Jerome Soller is notified within the next two weeks. If parking is tight, you may need to park nearby in Research Park (leave ample time for that). If you are at the University of Utah, you can catch a VA shuttle from the medical school or research park directly to the VA hospital. University shuttles run to university parking, which is across from the VA hospital, and to the LDS Insitute, which is also across the VA hospital. Registration: No registration is required. However, it would be greatly appreciated if you would rsvp by the end of April so we can estimate the attendance and set up the room accordingly. The room can comfortably seat 80 people with good workspace. Afterwards: We hope that speakers will provide some form of handouts. We hope to have a video tape record of this workshop, which will be public domain. *************************************************************************** From kainen at cs.UMD.EDU Tue Apr 13 21:02:48 1993 From: kainen at cs.UMD.EDU (Paul Kainen) Date: Tue, 13 Apr 93 21:02:48 -0400 Subject: Intelligent systems in Washington, DC (not an oxymoron!) Message-ID: <9304140102.AA21779@tove.cs.UMD.EDU> Public lectures on intelligent systems, to be given in Washington, DC, will include the topics of neural networks, fuzzy logic, robotics and expert systems. Speakers include Lotfi Zadeh, Thomas Saaty, Bernardo Huberman, Rodney Brooks and Marc Jeannerod. The series starts Apr. 21 and continues to June 9 at the Smithsonian's Campus on the Mall. All talks are scheduled Wednesdays from 8pm to 9:30pm. Call 202-357-3030 to register. More information is available from kainen at cs.umd.edu. From ncai at aaai.org Tue Apr 13 11:58:40 1993 From: ncai at aaai.org (NCAI) Date: Tue, 13 Apr 93 08:58:40 PDT Subject: No subject Message-ID: <9304131558.AA10733@aaai.org> Important addendum to AAAI-93 Conference Brochure regarding the Robot Building Event. Note that preregistration is mandatory for the Robot Building Event, and there is a $50 lab fee. In addition, student scholarships are available. From lpratt at franklinite.Mines.Colorado.EDU Tue Apr 13 17:17:09 1993 From: lpratt at franklinite.Mines.Colorado.EDU (Lorien Y. Pratt) Date: Tue, 13 Apr 93 14:17:09 -0700 Subject: Mike Mozer to speak in Colorado Machine Learning series Message-ID: <9304132117.AA06578@franklinite.Mines.Colorado.EDU> The spring, 1993 Colorado Machine Learning Colloquium Series presents: Dr. Michael C. Mozer Department of Computer Science University of Colorado, Boulder Neural network approaches to formal language induction Thursday, April 22, 1993 Room 110, Stratton Hall, on the CSM campus 5:30 pm ABSTRACT I will describe several recent approaches to formal language induction using neural networks. In contrast to 'connectoplasm' approaches that make use of generic network architectures, the work I'll advocate incorporates prior symbolic constraints to bias solutions learned by the network. One network I'll describe, the demon architecture (Mozer & Das, 1993), learns symbol rewrite operations that allow it to construct parse trees for strings in LR(0) context-free grammars. Another network, called SLUG (Mozer & Bachrach, 1991), processes regular languages and is based on an alternative and concise representation of some regular languages called an update graph. Both networks are trained on negative as well as positive examples, and, because of their specialized symbolically-constrained architectures, generalize extremely well. Additionally, their weights can often be interpreted in terms of symbolic rules. Suggested background readings: SLUG: A Connectionist Architecture for Inferring the Structure of Finite-State Elements; Michael C. Mozer and Jonathan Bachrach. Machine Learning, volume 7, 1991, pages 139-160; A Connectionist Symbol Manipulator that Discovers the Structure of Context-Free Languages. Michael C. Mozer and Sreerupa Das. To appear in: C. L. Giles and S. J. Hanson and J. D. Cowan (eds.) Advances in Neural Information Processing Systems V. San Mateo, CA: Morgan Kauffmann, 1993. These readings are available on reserve at the Arthur Lakes Library at CSM. Ask for the reserve package for MACS570, subject: Mozer. Non-students can check materials out on reserve by providing a driver's license. Open to the Public Refreshments to be served at 5:00pm, prior to talk For more information (including a schedule of all talks in this series), contact: Dr. L. Y. Pratt, CSM Dept. of Mathematical and Computer Sciences, lpratt at mines.colorado.edu, (303) 273-3878. The speaker may be contacted at: mozer at dendrite.cs.colorado.edu. Sponsored by: THE CSM DEPARTMENTS OF MATHEMATICAL AND COMPUTER SCIENCES, GEOPHYSICS, DIVISION OF ENGINEERING, AND CRIS* *The Center for Robotics and Intelligent Systems at the Colorado School of Mines From mathiak at sysc.PDX.EDU Tue Apr 20 00:27:57 1993 From: mathiak at sysc.PDX.EDU (mathiak@sysc.PDX.EDU) Date: Mon, 19 Apr 93 21:27:57 PDT Subject: 1993 World Congress on Neural Networks (Portland, Oregon, July 11-14) Message-ID: <9304200427.AA02064@orr.sysc.pdx.edu> -------------------------------------------------------------------- The World Congress on Neural Networks will be held in Portland, Oregon, July 11-14, 1993 (Oregon Convention Center). In this posting we provide: * the e-mail version of our registration form, * information about tutorials/sessions being planned, about housing and about WCNN'93 proceedings. More detailed information about WCNN'93 will be sent with the registration receipt. Quick information is available via e-mail regarding housing, papers, registration, sessions and tutorials at the following e-mail addresses: housing at wcnn93.ee.pdx.edu papers at wcnn93.ee.pdx.edu registration at wcnn93.ee.pdx.edu sessions at wcnn93.ee.pdx.edu tutorials at wcnn93.ee.pdx.edu . We are looking forward to seeing you at the conference! Sincerely, -------------------------------------------------------------------- Prof. George G. Lendaris email: lendarisg at wcnn93.ee.pdx.edu General Chair FAX: (503) 725-4882 Portland State University Portland, Oregon 97207 -------------------------------------------------------------------- - 1 - World Congress on Neural Networks 1993, Portland REGISTRATION FORM ================= Reg. Fee Reg. Fee Reg. Fee before before after Jan 15,93 Jun 15,93 Jun 15, 93 INNS or Cooperating Society Member $175.00 $270.00 $350.00 $ ........... Society Member Number: ................... Non-Members $275.00 $370.00 $450.00 $ ........... (Includes 1993 INNS membership and 1 year subscription of the INNS journal Neural Networks) Full-Time Student $50.00 $75.00 $95.00 $ ........... (Student registration and verification from department chairman required.) Spouse/Guest $50.00 $60.00 $70.00 $ ........... TUTORIAL REGISTRATION ===================== (Fee includes 4 tutorials, notes on all tutorials and lunch) (Please circle 4 preferences, see list below: A B C D E F G H I J K ) Members or Non-Members $225.00 $295.00 $345.00 $ ........... Student $50.00 $75.00 $95.00 $ ........... (Student registration and verification from department chairman required.) TOTAL $ ====================== Please print or type: Name: ............................................................... (As you would like to appear on badge) Title: ........................ Organization: ....................... (As you would like to appear on badge) Adress: ............................................................. City: ................... State: ..... Zip: ........ Country: ....... Bus.Tel: ....................... FAX: ............................... Spouse/Guest Name (if fee paid): .................................... (Complete only if paying the Spouse/Guest Registration fee - includes 2 receptions only) - 2 - IMPORTANT: Please indicate any disability for special assistance .................................................................... .................................................................... Unless the INNS is advised prior to the meeting of any special requirements, we cannot guarantee that service will be available. Please complete this form and return it with check or money order to: Attention: WCNN'93 Portland Meeting Registration 875 Kings Highway, Suite 200 West Deptford, NJ 08096 Tel: (609) 845-1720 FAX: (609) 853-0411 Checks must made payable in US Dollars and issued by a US correspon- dent bank. Each registrant is responsible for any bank charges. Check with your local bank before processing payment. Credit Card Information: .... I wish to pay for my fees by credit card. Circle one: Visa Master Card Account #: ............................ Expiration Date: ............ Signature: .......................................................... Tutorials will be offered on Sunday, July 11, 1993. Each two hour tutorial will be offered twice. A. Cognitive Neuroscience (Robert Desimone) B. Structural and Mathematical Approaches to Signal Processing (S.Y. Kung) C. Adaptive Resonance Theory (Gail Carpenter) D. Practical Applications of Neural Network Theory (Robert Hecht-Nielsen) E. Cognitive Science (David Rumelhart) F. Neural Fuzzy Systems (Fred Watkins) G. Neurobiology and Chaos (Walter Freeman) H. Neural Control and Robotics (Michael Kuperstein) I. Neural Computation and VLSI (Eric Schwartz) J. Biological Vision (V.S. Ramachandran) K. Supervised Learning (Hal White) !!! ATTENTION !!! If you must cancel your registration, all requests must be received in writing by Ms. Connie Rebert, Registration Supervisor, 875 Kings High- way, Suite 200, West Deptford, NJ 08096, no later than Monday, June 1, 1993. All fees paid will be refunded minus a $30.00 processing fee. THERE WILL BE NO REFUNDS AFTER THE JUNE 1ST DEADLINE. --------------------------------------------------------------------- You may make a hardcopy of this form and mail it to the above address. --------------------------------------------------------------------- -------------------------------------------------------------------- World Congress on Neural Networks 1993, WCNN'93 Portland, Oregon, Convention Center July 11-15, 1993 TUTORIALS ========= Tutorials will be offered on Sunday, July 11, 1993. Each two hour tutorial will be offered twice. A. Cognitive Neuroscience (Robert Desimone, National Instituteof Mental Health) B. Structural and Mathematical Approaches to Signal Processing (S.Y. Kung, Princeton University) C. Adaptive Resonance Theory (Gail Carpenter, Boston University) D. Practical Applications of Neural Network Theory (Robert Hecht-Nielsen, HNC Corporation) E. Cognitive Science (David Rumelhart, Stanford University) F. Neural Fuzzy Systems (Fred Watkins, HyperLogic Corporation) G. Neurobiology and Chaos (Walter Freeman, University of California) H. Neural Control and Robotics (Michael Kuperstein, Symbus Technology) I. Neural Computation and VLSI (Eric Schwartz, Vision Applications) J. Biological Vision (V.S. Ramachandran, University of California) K. Supervised Learning (Hal White, University of California) We are pleased to announce that in addition to the main program, we will be offering special tracks in conjunction with the Society of Manufacturing Engineers on Manufacturing (SME/INNS Track). -------------------------------------------------------------------- -------------------------------------------------------------------- World Congress on Neural Networks 1993, WCNN'93 Portland, Oregon, Convention Center July 11-15, 1993 SESSIONS ======== Plenary Speakers include: * Federico Faggin, Real-Time-On-Chip Learning in Analog VLSI Networks * Stephen Grossberg, 3-D Vision and Figure-Ground Pop-Out * Bart Kosko, Neural Fuzzy Systems * Kumpati Narendra, Intelligent Control Using Neural Networks * Wolf Singer, Coherence as an Organizing Principal of Cortical Function Session Topics | Session Chairs ----------------------------------------------------------------- - Applications | J. Dayhoff, R. Hecht-Nielsen - Associative Memory | J. Andersen, J. Taylor - Biological Sensory-Motor Control| A. Barto, S. Kelso - Biological Vision | C. Malsburg, V.S. Ramachandran - Cognitive Neuroscience | R. Desimone, L. Optician - Electro-Optical Neurocomputers | L. Giles, H. Szu - Intelligent Neural Systems | S. Grossberg, D. Levine - Local Circuit Neurobiology | J. Byrne, J. Houk - Machine Vision | R. Chellappa, K. Fukushima - Neural Fuzzy Systems | W. Daugherty, B. Kosko - Neurodynamics | S. Amari, H. White - Pattern Recognition | T. Kohonen, D. Specht - Robotics and Control | M. Kuperstein, K. Narendra - Signal Processing | S.Y. Kung, B. Widrow - Speech and Language | M. Cohen, D. Rumelhart - Supervised Learning | L. Cooper, P. Werbos - Unsupervised Learning | G. Carpenter, E. Oja (TENTATIVE) PROPOSED SESSION SCHEDULE ========================= The numbers associated with sessions refer to the list on the registration form. Sunday Monday Tuesday Wednesday Thursday 7/11/93 7/12/93 7/13/93 7/14/93 7/15/93 ---------------------------------------------------------------------- Morning Sessions, starting 8:00 am Tutorials (1) (10) (3) (8) Biological Cognitive Speech and Pattern Vision Neuro- Language Recognition science (17) (16) (5) (14) Applications Associative Robotics and Neurodynamics Memory Control SME/INNS (17) (6) (4) Track Applications Supervised Biological Learning Sensory Motor Afternoon Sessions, starting 1:30 pm (11) (7) (6) (13) Intelligent Unsupervised Supervised Signal Neural Learning Learning Processing Systems (12) (9) (2) (15) Neural Local Curcuit Machine E-O Neuro- Fuzzy Neurobiology Vision Computers Systems IFSA/INNS Track Plenary Talks Kosko Grossberg Reception Narendra Faggin Gov't Panel SIG Meeting -------------------------------------------------------------------- -------------------------------------------------------------------- World Congress on Neural Networks 1993, Portland HOUSING ======= Housing application forms will be sent to each registrant. In the mean time for your information the following are the room rates at the hotels that are holding blocks of rooms for the WCNN'93. 1) Conference Headquarter Hotel (walking distance to convention center): Red Lion/Lloyd Center $110.00 1-2 people, $15.00 each additional person 2) Other hotels within walking distance : Best Western/Convention Center $74.00 Flat Rate Holiday Inn/Downtown $72.00 1-2 people, $10 each additional person 3) Downtown Hotels (short ride on light rail train [called MAX]): Hilton Hotel $104.00 1-2 people, $20 each additional person Marriott Hotel $116.00 Flat Rate If you wish to reserve a room before you receive the registration, or if need further information about the Portland metropolitan area, please contact: Portland Oregon Visitor Association (POVA) Attention: Silvia Robles, Housing Department 26 SW Salmon Portland, OR 97204 STUDENT HOUSING =============== For July 11-14, 1993, there is still a limited number of rooms for students available: - Montgomery Hall, PSU Campus - single rooms - prices: $18.00 without meal $34.00 with meal (breakfast, lunch, dinner) - deposit: one night stay (send check in $US or VISA number to address below) ! PLEASE NOTE: ! ! All requests for student housing MUST BE PROCESSED BEFORE ! ! MAI 31, 1993. There is NO DEPOSIT REFUND for cancellations ! ! after MAI 31, 1993. ! For reservation and information please contact WCNN'93, Student Housing Systems Science PhD Program Portland State University Portland, OR 97201-0751 USA Phone : (503) 725-4961 FAX : (503) 725-4882 e-mail: housing at wcnn93.ee.pdx.edu -------------------------------------------------------------------- -------------------------------------------------------------------- World Congress on Neural Networks 1993, Portland PROCEEDINGS =========== 1) The WCNN`93 proceedings will be available to all WCNN'93 attendies at the Oregon Convention Center. 2) After the WCNN`93 the proceedings will be mailed to all who did register but could not attend. 3) The WCNN`93 proceedings will be available and mailed to requestors who did not register. The price has not been established yet. -------------------------------------------------------------------- From marwan at sedal.sedal.su.OZ.AU Wed Apr 21 13:52:14 1993 From: marwan at sedal.sedal.su.OZ.AU (Marwan Jabri) Date: Wed, 21 Apr 93 12:52:14 EST Subject: Research Fellowship position Message-ID: <9304210252.AA03798@sedal.sedal.su.OZ.AU> Research Fellowship (Fixed-term) Deadline 29 April 1993. Systems Engineering and Design Automation Laboratory Department of Electrical Engineering The University of Sydney Reference No: C14/12 The Fellow will work with the Systems Engineering and Design Automation Laboratory (SEDAL) at Sydney University Electrical Engineering. SEDAL currently groups 2 academic staff, 5 research staff and ten postgraduate students. It has projects in the areas of pattern recognition for implantable devices, VLSI systems and multi-chip modules, time series prediction, knowledge integration and continuous learning, and VLSI computer-aided design. The Research Fellow position is aimed at: contributing to the research program; helping with the supervision of postgraduate students; supporting some management aspects of SEDAL; providing occasional teaching support. The appointee should have a PhD or equivalent industry research and development experience. It is desirable that the appointee has a background in one or more of the following areas: machine intelligence and connectionist architectures; microelectronics; pattern recognition and classification. It is also desirable that the appointee be able to join the group before July 1993. Appointment will be for three years. Membership of a superannuation scheme is a condition of employment for new appointees. For further information, please contact Dr M Jabri on (61-2) 692 2240, fax (61-2) 660 1228, Email: marwan at sedal.su.oz.au. Salary: $41,000 - $48,688 per annum Applications, quoting Reference No, including curriculum vitae, list of publications, and the names, addresses, fax and phone nos of two referees to the Assistant Registrar (Appointments), Staff Office (K07), University of Sydney, NSW 2006 Australia by 29 April 1993. From cima at tce.ing.uniroma1.it Wed Apr 21 07:57:34 1993 From: cima at tce.ing.uniroma1.it (cima@tce.ing.uniroma1.it) Date: Wed, 21 Apr 1993 13:57:34 +0200 Subject: No subject Message-ID: <9304211157.AA06109@tce.ing.uniroma1.it> Dear Fellow Connectionists, I have been involved for some years in research about Cellular Neural Networks (CNNs), i.e., in the broadest sense, NNs where neurons are only connected to neighboring units. CNNs can be easily realized in IC technique by profiting of their spatially defined structure. Such networks, first introduced by Prof.L.O. Chua, of U.C. at Berkeley have been successfully applied to many image processing tasks. I have served in the scientific committees of the past IEEE International Workshops on CNNs and their Applications in Budapest in 1990, and in Munich in 1992. We would like to get in contact to other researchers working at similar topics, so as to establish a more specialistic mailing list to cooperate on CNN research. At present we are working on the following topics: - gradient descent and genetic learning for CNNs; - generalization and information storage in CNN learning; - simulation of physical systems governed by partial differential equations; - cellular networks of oscillators. Among our publications concerning CNNs are the following: 1) M. Balsi, "Generalized CNN: Potentials of a CNN with Non-Uniform Weights", Proceedings of IEEE Second International Workshop on Cellular Neural Networks and their Applications (CNNA-92), Munich, Germany, Oct. 14-16, 1992, 129-134 2) A. Barone, M. Balsi, V. Cimagalli, "Cellular Networks of Oscillators", Proceedings of CNNA-92, 246-251 3) T. Roska, C.W. Wu, M. Balsi, L.O. Chua, "Stability and Dynamics of Delay-Type General and Cellular Neural Networks", IEEE Trans. on Circuits and Systems 39(6), 487-490 (1992) 4) V. Cimagalli, M. Bobbi, M. Balsi, "MODA: Moving Object Detecting Architecture", IEEE Trans on Circuits and Systems, II, 40(3) (1993). 5) T. Roska, C.W. Wu, M. Balsi, L.O. Chua, "Stability of CNNs with Dominant Nonlinear and Delay-type Templates", IEEE Trans on Circuits and Systems, II, 40(3) (1993). 6) M. Balsi, "Stability of CNNs with One-Dimensional Templates", to be published in Intl. J. of Circ. Th. and Appl. (1993). We can provide hardcopies of these papers upon request. I shall be looking forward for your replies. Yours, Prof. Valerio Cimagalli Dept. of Electronic Engineering "La Sapienza" University of Rome via Eudossiana, 18 I-00184 Rome ITALY fax +39-6-4742647 From meeden at silver.ucs.indiana.edu Wed Apr 21 12:49:31 1993 From: meeden at silver.ucs.indiana.edu (Lisa Meeden) Date: Wed, 21 Apr 1993 11:49:31 -0500 Subject: Paper on connectionist robot control Message-ID: The following paper is available in the neuroprose archive. It will also appear in the "Proceedings of the Fifteenth Annual Conference of the Cognitive Science Society". Unfortunately for those unable to use FTP, we cannot provide hard copies. Emergent Control and Planning in an Autonomous Vehicle Lisa Meeden* Gary McGraw*+ Doug Blank* *Department of Computer Science +Center for Research on Concepts and Cognition Indiana University Abstract We use a connectionist network trained with reinforcement to control both an autonomous robot vehicle and a simulated robot. We show that given appopriate sensory data and architectural structutre, a network can learn to control the robot for a simple navigation problem. We then investigate a more complex, goal-based problem and examine the plan-like behavior that emerges. To obtain a copy: ftp cheops.cis.ohio-state.edu login: anonymous password: cd pub/neuroprose binary get meeden.robot.ps.Z bye Then at your system: uncompress meeden.robot.ps.Z lpr -P meeden.robot.ps From josh at faline.bellcore.com Thu Apr 22 16:01:12 1993 From: josh at faline.bellcore.com (Joshua Alspector) Date: Thu, 22 Apr 93 16:01:12 EDT Subject: telecom workshop paper summaries due May 14 Message-ID: <9304222001.AA15474@faline.bellcore.com> CALL FOR PAPERS International Workshop on Applications of Neural Networks to Telecommunications Princeton, NJ October 18-20, 1993 You are invited to submit a paper to an international workshop on applications of neural networks to problems in telecommunications. The workshop will be held in Princeton, New Jersey on October, 18-20 1993. This workshop will bring together active researchers in neural networks with potential users in the telecommunications industry in a forum for discussion of applications issues. Applications will be identified, experiences shared, and directions for future work explored. Suggested Topics: Application of Neural Networks in: Network Management Congestion Control Adaptive Equalization Speech Recognition Security Verification Language ID/Translation Information Filtering Dynamic Routing Software Reliability Fraud Detection Financial and Market Prediction Adaptive User Interfaces Fault Identification and Prediction Character Recognition Adaptive Control Data Compression Please submit 6 copies of both a 50 word abstract and a 1000 word summary of your paper by May 14, 1993. Mail papers to the conference administrator: Betty Greer, IWANNT*93 Bellcore, MRE 2P-295 445 South St. Morristown, NJ 07960 (201) 829-4993 (fax) 829-5888 bg1 at faline.bellcore.com Abstract and Summary Due: May 14 Author Notification of Acceptance: June 18 Camera-Ready Copy of Paper Due: August 13 Organizing Committee: General Chair Josh Alspector Bellcore, MRE 2P-396 445 South St. Morristown, NJ 07960-6438 (201) 829-4342 josh at bellcore.com Program Chair Rod Goodman Caltech 116-81 Pasadena, CA 91125 (818) 356-3677 rogo at micro.caltech.edu Publications Chair Timothy X Brown Bellcore, MRE 2E-378 445 South St. Morristown, NJ 07960-6438 (201) 829-4314 timxb at faline.bellcore.com Treasurer Anthony Jayakumar, Bellcore Events Coordinator Larry Jackel, AT&T Bell Laboratories Industry Liaisons Miklos Boda, Ellemtel Atul Chhabra, NYNEX Michael Gell, British Telecom Lee Giles, NEC Thomas John, Southwestern Bell Adam Kowalczyk, Telecom Australia Tadashi Sone, NTT University Liaisons S Y Kung, Princeton University Tzi-Dar Chiueh, National Taiwan University INNS Liaison Bernie Widrow, Stanford University IEEE Liaison Steve Weinstein, Bellcore Conference Administrator Betty Greer Bellcore, MRE 2P-295 445 South St. Morristown, NJ 07960 (201) 829-4993 (fax) 829-5888 bg1 at faline.bellcore.com ----------------------------------------------------------------------------- ----------------------------------------------------------------------------- International Workshop on Applications of Neural Networks to Telecommunications Princeton, NJ October 18-20, 1993 Registration Form Name: _____________________________________________________________ Institution: __________________________________________________________ Mailing Address: ___________________________________________________________________ ___________________________________________________________________ ___________________________________________________________________ ___________________________________________________________________ Telephone: ______________________________ Fax: ____________________________________ E-mail: _____________________________________________________________ I will attend | | Send more information | | Paper enclosed | | Registration Fee Enclosed | | ($350; $450 after Sept. 15; $150 students;) Please make sure your name is on the check (made out to IWANNT*93) Registration includes Monday night reception, Tuesday night banquet, refreshment breaks, AT&T tour, and proceedings available at the conference. Mail to: Betty Greer, IWANNT*93 Bellcore, MRE 2P-295 445 South St. Morristown, NJ 07960 (201) 829-4993 (fax) 829-5888 bg1 at faline.bellcore.com Deadline for submissions: May 14, 1993 Author Notification of Acceptance: June 18, 1993 Camera-Ready Copy of Paper Due: August 13, 1993 From john at dcs.rhbnc.ac.uk Fri Apr 23 05:25:32 1993 From: john at dcs.rhbnc.ac.uk (John Shawe-Taylor) Date: Fri, 23 Apr 1993 10:25:32 +0100 Subject: Paper on Neuroprose Message-ID: <12734.9304230925@csqx.cs.rhbnc.ac.uk> The following paper has recently been accepted to appear in IEEE Transactions on Neural Networks and has been placed in the Neuroprose archive as shawetaylor.symdisc.ps.Z. ----------------------------- Symmetries and Discriminability in Feedforward Network Architectures John Shawe-Taylor, Department of Computer Science, Royal Holloway, University of London Abstract: The paper investigates the effects of introducing symmetries into feedforward neural networks in what are termed Symmetry Networks. This technique allows more efficient training for problems in which we require the output of a network to be invariant under a set of transformations of the input. The particular problem of graph recognition is considered. In this case the network is designed to deliver the same output for isomorphic graphs. This leads to the question of which inputs can be distinguished by such architectures. A theorem characterising when two inputs can be distinguished by a Symmetry Network is given. As a consequence a particular network design is shown to be able to distinguish non-isomorphic graphs if and only if the graph reconstruction conjecture holds. To retrieve the file: unix> ftp cheops.cis.ohio-state.edu Connected to cheops.cis.ohio-state.edu. 220 cheops.cis.ohio-state.edu FTP server ready. Name: anonymous 331 Guest login ok, send ident as password. Password:neuron 230 Guest login ok, access restrictions apply. ftp> binary 200 Type set to I. ftp> cd pub/neuroprose 250 CWD command successful. ftp> get shawetaylor.symdisc.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for shawetaylor.symdisc.ps.Z 226 Transfer complete. 100000 bytes sent in 3.14159 seconds ftp> quit 221 Goodbye. unix> uncompress shawetaylor.symdisc.ps.Z unix> lpr shawetaylor.symdisc.ps (or however you print out postscript) From inmanh at cogs.sussex.ac.uk Fri Apr 23 05:01:10 1993 From: inmanh at cogs.sussex.ac.uk (Inman Harvey) Date: Fri, 23 Apr 93 10:01:10 +0100 Subject: CFP - SAB94 - Simulation of Adaptive Behavior Message-ID: <25560.9304230901@rsunr.crn.cogs.susx.ac.uk> ============================================================================== Conference Announcement and Call For Papers FROM ANIMALS TO ANIMATS Third International Conference on Simulation of Adaptive Behavior (SAB94) Brighton, UK, August 8-12, 1994 The object of the conference is to bring together researchers in ethology, psychology, ecology, cybernetics, artificial intelligence, robotics, and related fields so as to further our understanding of the behaviors and underlying mechanisms that allow animals and, potentially, robots to adapt and survive in uncertain environments. The conference will focus particularly on well-defined models, computer simulations, and built robots in order to help characterize and compare various organizational principles or architectures capable of inducing adaptive behavior in real or artificial animals. Contributions treating any of the following topics from the perspective of adaptive behavior will receive special emphasis. Individual and collective behavior Autonomous robots Neural correlates of behavior Hierarchical and parallel organizations Perception and motor control Emergent structures and behaviors Motivation and emotion Problem solving and planning Action selection and behavioral Goal directed behavior sequences Neural networks and evolutionary Ontogeny, learning and evolution computation Internal world models Characterization of environments and cognitive processes Applied adaptive behavior Authors should make every effort to suggest implications of their work for both natural and artificial animals. Papers which do not deal explicitly with adaptive behavior will be rejected. Submission Instructions Authors are requested to send five copies (hard copy only) of a full paper to the Program Chair (Dave Cliff). Papers should not exceed 10 pages (excluding the title page), with 1 inch margins all around, and no smaller than 10 pt (12 pitch) type (Times Roman preferred). Each paper must include a title page containing the following: (1) Full names, postal addresses, phone numbers, email addresses (if available), and fax numbers for each author, (2) A 100-200 word abstract, (3) The topic area(s) in which the paper could be reviewed (see list above). Camera ready versions of the papers, in two-column format, will be required after acceptance. Computer, video, and robotic demonstrations are also invited. Please contact Phil Husbands to make arrangements for demonstrations. Other program proposals will also be considered. Conference committee Conference Chair Philip HUSBANDS School of Cognitive and Computing Sciences University of Sussex Brighton BN1 9QN UK e-mail: philh at cogs.susx.ac.uk Jean-Arcady MEYER Groupe de Bioinformatique URA686.Ecole Normale Superieure 46 rue d'Ulm 75230 Paris Cedex 05 France e-mail: meyer at wotan.ens.fr Stewart WILSON The Rowland Institute for Science 100 Cambridge Parkway Cambridge, MA 02142 USA e-mail: wilson at smith.rowland.org Program Chair David CLIFF School of Cognitive and Computing Sciences University of Sussex Brighton BN1 9QN UK e-mail: davec at cogs.susx.ac.uk Financial Chair: P. Husbands, H. Roitblat Local Arrangements: I. Harvey, P. Husbands Program Committee M. Arbib, USA; R. Arkin, USA; R. Beer, USA; A. Berthoz, France; L. Booker, USA; R. Brooks, USA; P. Colgan, Canada; T. Collett, UK; H. Cruse, Germany; J. Daugman, UK; J. Delius, Germany; A. Dickinson, UK; J. Ferber, France; N. Franceschini, France; S. Goss, Belgium; I. Harvey, UK; I. Horswill, USA; L. Kaelbling, USA; H. Klopf, USA; L-J. Lin, USA; P. Maes, USA; M. Mataric, USA; D. McFarland, UK; G. Miller, UK; R. Pfeifer, Switzerland; H. Roitblat, USA; J. Slotine, USA; O. Sporns, USA; J. Staddon, USA; F. Toates, UK; P. Todd, USA; S. Tsuji, Japan; W. Uttal, USA; D. Waltz, USA. Official Language: English Publisher: MIT Press/Bradford Books Important Dates =============== JAN 5, 1994: Submission deadline MAR 10: Notification of acceptance or rejection APR 10: Camera ready revised versions due MAY 1: Early registration deadline JUL 8: Regular registration deadline AUG 8-12: Conference dates General queries to: sab94 at cogs.susx.ac.uk ============================================================================== From fcummins at cs.indiana.edu Fri Apr 23 15:29:21 1993 From: fcummins at cs.indiana.edu (fred cummins) Date: Fri, 23 Apr 1993 14:29:21 -0500 Subject: Neuroprose paper: Representation of Temporal patterns in RNNs Message-ID: *** DO NOT FORWARD TO OTHER GROUPS *** The following paper, to be presented as a poster at the 15th AGM of the Cognitive Science Society, has been placed in the neuroprose archive. FTP instructions follow the abstract. Fred Cummins fcummins at cs.indiana.edu __________________________________________________________________________ *** Representation of Temporal Patterns in Recurrent Neural Networks *** To be presented at the 15th Annual Conference of the Cognitive Science Society This paper investigates the way temporal patterns are represented by recurrent networks. Small sequence discrimination tasks were devised with the specific intention of requiring the network to base its discrimination on the temporal structure of the input sequences. The resulting solutions were then analyzed using elementary tools from dynamic systems theory. Our primary interest was to establish the relationship between the temporal characteristics of the training set and the representations developed by the network. Networks trained on a variety of simple sequence recognition tasks were examined. Analysis of the state space of unit activations allowed a direct view of the means employed by the network to solve a given problem, and provided insight both into the class of solutions these networks can produce and how these will generalize to sequences outside the training set. This intuitive approach may be of help in assessing the potential of simply recurrent networks for a variety of modelling problems. __________________________________________________________________________ The paper is cummins.temporal-patterns.ps.Z in the neuroprose archives. To retrieve this file from the neuroprose archives: unix> ftp archive.cis.ohio-state.edu Name (archive.cis.ohio-state.edu:whoever): anonymous Password: (use your email address) ftp> cd pub/neuroprose ftp> binary 200 type set to I ftp> get cummins.temporal-patterns.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for rosen.advsim.ps.Z . ftp> quit 221 Goodbye. unix> uncompress cummins.temporal-patterns.ps.Z unix> lpr cummins.temporal-patterns.ps From emark at cns.caltech.edu Fri Apr 23 19:26:07 1993 From: emark at cns.caltech.edu (Mark O'Dell) Date: Fri, 23 Apr 93 16:26:07 PDT Subject: The Giant Brain Museum Message-ID: The Giant Brain Museum The organizing committee members have gathered together to promote understanding of the brain. They hope to construct a giant walk-through brain museum to be useful to experts while appealing to everyone, including children. The committee members are: Marvin Adelson, Prof. of Architecture & Urban Planning, UCLA Joseph E. Bogen, Clin. Prof. of Neurological Surgery, USC Marian Diamond, Director, Lawrence Hall of Science, UCB Frank O. Gehry, Fellow, Amer. Instit. of Architecture John Hagar, Attorney at Law Robert B. Lewis, Project Director Arnold Scheibel, Director, Brain Research Instit., UCLA Anyone interested in this project, please send your paper mail address to: Giant Brain PO Box 50566 Pasadena, CA 91115 USA or email your paper mail address to me & I will deliver it to the organizers. Please do not send email without a paper mail address; I am only posting. Mark O'Dell emark at cns.caltech.edu From stefano at kant.irmkant.rm.cnr.it Fri Apr 23 05:03:13 1993 From: stefano at kant.irmkant.rm.cnr.it (stefano@kant.irmkant.rm.cnr.it) Date: Fri, 23 Apr 1993 04:03:13 -0500 Subject: No subject Message-ID: <9304230903.AA12012@kant.irmkant.rm.cnr.it> The following paper has been placed in the neuroprose archive as nolfi.growing.ps.Z Instructions for retrieving and printing follow the abstract. Growing Neural Networks Stefano Nolfi Domenico Parisi Institute of Psychology, CNR V.le Marx 15, 00137 Rome - Italy E-mail: stiva at irmkant.Bitnet domenico at irmkant.Bitnet Abstract Growing neural networks are networks which are constructed by executing genetic instructions contained in a genotype. These instructions and their products interacts non-linearly to eventually determine the mature structure. We present simulations in which the mapping from genotype to phenotype is instantaneous and simulations in which it develops in time during a segment of an individual's lifetime, i.e. the individual's developmental age, allowing us to study both neural evolution and neural development. The results shed some light on (a) why modular architectures are likely to emerge, (b) why similar successions of stages tend to appear in both evolution and development, and (c) why a developmental age is preserved evolutionarily although the mature state may appear to be more efficient from the point of view of fitness. The paper has been presented at the Artificial Life III Conference Sorry, no hard copies are available Comments are welcome. Stefano Nolfi Institute of Psychology, CNR V.le Marx, 15 00137 - Rome - Italy email stiva at irmkant.Bitnet _______________________________________________________________________ Here is an example of how to retrieve this file: gvax> ftp archive.cis.ohio-state.edu (or ftp 128.146.8.52) Connected to archive.cis.ohio-state.edu. 220 archive.cis.ohio-state.edu FTP server ready. Name: anonymous 331 Guest login ok, send ident as password. Password:neuron at wherever 230 Guest login ok, access restrictions apply. ftp> binary 200 Type set to I. ftp> cd pub/neuroprose 250 CWD command successful. ftp> get nolfi.growing.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for nolfi.growing.ps.Z 226 Transfer complete. ftp> quit 221 Goodbye. gvax> uncompress nolfi.growing.ps.Z gvax> lpr nolfi.growing.ps From efiesler at idiap.ch Fri Apr 23 10:28:18 1993 From: efiesler at idiap.ch (E. Fiesler) Date: Fri, 23 Apr 93 16:28:18 +0200 Subject: SimTec93 + WNN93 + FNN93; Call for papers. Message-ID: <9304231428.AA28613@idiap.ch> ------------------------------------------------------------------------ Please duplicate and post the following call for papers for the Interna- tional Simulation Technology MultiConference combining SimTec, WNN, and FNN. Thanks. E. Fiesler IDIAP C.P. 609 CH-1920 Martigny E-mail: EFiesler at IDIAP.CH (Internet) ------------------------------------------------------------------------ C A L L F O R P A P E R S 1993 INTERNATIONAL SIMULATION TECHNOLOGY MULTICONFERENCE SimTec93 * WNN93 * FNN93 SimTec: Computer Modeling Applications & Research - ALL Areas Applications * Aerospace * Emerging Technologies Mission Earth * Virtual Reality * Imaging WNN/FNN: Neural Networks * Fuzzy Logic * Computational AI Genetic Algorithms * Chaos & Fractals * Biological Models Virtual Reality * Implementations * Standards November 7-10, 1993 SAN FRANCISCO, CALIFORNIA Convenient. View of the beautiful bay. Near area attractions. ACADEMIC * INDUSTRIAL * GOVERNMENT TECHNOLOGY TRANSFER Awards Luncheon STANDARDS * Exhibits * Demonstrations * CONTESTS Tour NASA/Ames ------ SIMTEC93: INTERNATIONAL SIMULATION TECHNOLOGY CONFERENCE ------- Sponsor: SCS; CoSponsor: NASA; Cooperating: SPIE ----------------- WNN93: COMPUTATIONAL AI CONFERENCE ------------------ (Formerly Workshop on Neural Networks) Sponsor: SCS; CoSponsor: NASA; Cooperating: SPIE, INNS Participating: IEEE-NNC --------------- FNN93: TUTORIALS AND STANDARDS SEMINAR ---------------- PreConference Tutorials and Seminar Fuzzy Systems * Neural Networks * Computational AI Sponsor: SCS; Co-Sponsor: NASA Contact: Mary Lou Padgett, Associate VP for SimTec Auburn University, 1165 Owens Road, Auburn, AL 36830 (205) 821-2472/3488; Fax: (205) 844-1809; mpadgett at eng.auburn.edu [ S C S ] The Society for Computer Simulation P.O.Box 17900, San Diego, CA 92117 P: (619) 277-3888; F: (619) 277-3930 ======================================================================== INTERNATIONAL PROGRAM COMMITTEE General Chair: Ted Lambert - SCS General Program: Martin Dost - SCS Western Simulation Council: Barok Khoshnevis - USC Local Arrangements: Norm Pobanz - Bechtel NASA/Ames Tour Arrangements: Bill Cameron, H. Berenji, S. Columbano Commercial Exhibits: Ed Edwards, Motorola NASA / ESA Representatives: Robert Savely - NASA/JSC Hamid Berenji - NASA/Ames Sylvano Colombano - NASA/Ames Robert Shelton - NASA/JSC Joseph Mica - NASA/Goddard Tim Cleghorn - NASA/JSC Robert Lea - NASA/JSC Juan Miro - ESOC/ESA SimTec John McLeod - SCS Ben Clymer - SCS Norm Pobanz - Bechtel Stu Schlessinger - SCS Martin Wildberger - EPRI Ralph Huntsinger - CS Chico Abul Moaty Fayek - CS Chico Bill Cameron - NASA (ret.) Roy Latham - CGSD Dave O'Neil - SCS Kevin Reilly - UAB Ratan Guha - UCF V. Honovar - Iowa State U. Wartain Jemian - Auburn U. Chris Ward - Auburn U. C. F. Chen - Boston U. Hassan Farhat - U. Nebraska Omaha Keith Klukis - Martin Marietta John Murphy - Westinghouse Dale Whittaker - Texas A & M M. Obaidat - CUNY WNN * FNN Mary Lou Padgett - Auburn U. Walter J. Karplus - UCLA Lotfi Zadeh - Berkeley Paul Werbos - NSF Bart Kosko - USC Joe Brown - Thought Processes, Inc. E. Tzanakou - Rutgers U. David B. Hertz - U. Miami George Rogers - NSWC Ed Edwards - Motorola Louis Sheppard - UT Medical Branch Len Trejo - Navy, San Diego Holger Jaenisch - Nichols Research Bob Clapp - ORNL Rao Vemuri - LLNL T. A. Roppel - Auburn U. Emile Fiesler - IDIAP, Switzerland K. Ashenayi - U. Tulsa ======================================================================== SimTec Topics of Interest Include, but are Not Limited To: SIMULATION APPLICATIONS Chair: Martin Dost - SCS * Co-Chairs: M. Wildberger - EPRI & R. Guha UCF Power Systems Software Modeling Reliability and Quality Assurance Massively Parallel & Distributed Syst Robotics Ground Vehicle Simulation Automatic Control Systems Signal Processing and Analysis Simulation in ADA High Performance Computers/Computing Electronics/VLSI Model Validation Simulation Facilities Educ. for Simulation Professionals AEROSPACE Chair: Hamid Berenji - NASA/Ames * Co-Chair: Juan Miro - ESA Satellite Simulators Guidance, Navigation & Control Real Time Simulation Control Systems Space Avionics Display & Astronaut Training Control Systems Simulation Man-in-the-Loop Flight Remotely Piloted Vehicles Decision Support Systems Robotics & Manufacturing Facilities Planning and Change EMERGING TECHNOLOGIES Chair: Abul Moaty Fayek - CS Chico * Co-Chair T. A. Roppel - Auburn U. Automation & Robotics Training Intelligent Computer Aided Training Knowledge Based Systems Object Oriented Programming Intelligent Sensor Systems Biotechnology & Simulation Microelectronics Multimedia Advances in Simulation Intelligent Computer Environments VIRTUAL REALITY Chair: J. Murphy - Westinghouse Co-Chairs: R. Savely - NASA/JSC, Ben Delaney - CyberEdge Journal Applications Human Factors Hardware and Software Advances in Virtual Reality IMAGING Keith Klukis - Martin Marietta * Co-Chair: Bart Kosko - USC Computer Image Generation Robot & Machine Vision Image Processing & Analysis Biological Modeling of Vision Image Registration Advances in Imaging IR and MMW Image Techniques Automatic Target Recognition MISSION EARTH Chair: John McLeod - SCS * Co-Chair: Ben Clymer - SCS Dueling Methodologies Global Simulations for Education Trends in Mission Earth Global Modeling & Simulation Needs of Global Simulation for Global Planning Progress and Status of State of the Art Mission Earth Activity Organizational Session ======================================================================== W N N 9 3 / F N N 9 3 / S a n F r a n c i s c o November 7-10, 1993 * San Francisco, CA The WNN93 Conference on Computational AI is an extension of the Workshops on Neural Networks--Academic / Industrial / NASA / Defense: Tutorials and Technical Interchange. Monday, November 8 - Wednesday, November 10, 1993 Registration Covers Both SimTec93 and WNN93 sessions and one Proceedings KEYNOTE: "Soft Computing" Lotfi Zadeh - UC Berkeley OVERVIEWS * METHODOLOGY * APPLICATIONS * IMPLEMENTATIONS Academic - Industrial - Government Paper Contest * Awards Luncheon Exhibits * Demonstrations * Tutorials * Tour NASA/Ames STANDARDS: Performance Measure Paper Competition - R. Shelton,NASA/JSC STANDARDS: Comparative Paradigm Paper Competition - E. Tzanakou,Rutgers NASA Neural Networks User Group: Robert Shelton, NASA/JSC NEURAL NETWORKS Chair: Bob Shelton - NASA/JSC * Walter Karplus - UCLA Paul Werbos - NSF and Len Trejo, Navy, San Diego FUZZY LOGIC Chair: Hamid Berenji - NASA/Ames Co-Chairs: Joe Mica - NASA Goddard, Lotfi Zadeh - Berkeley GENETIC ALGORITHMS Chair: Joe Brown - Thought Processes, Inc. Co-Chair: Sylvano Colombano - NASA/Ames CHAOS and FRACTALS Chair: Holger Jaenisch - Nichols Research Co-Chair: Ned Clapp - ORNL * Rao Vemuri - LLNL BIOLOGICAL MODELS Chair: Louis Sheppard - UT Medical Branch Co-Chair: David Bendell Hertz - U. Miami VIRTUAL REALITY Chair: Bart Kosko, USC Co-Chairs: Robert Savely - NASA/JSC and Richard A. Blade - UCCS IMPLEMENTATIONS Chair: Ed Edwards - Motorola Co-Chairs: Bob Lea & Tim Cleghorn - NASA/JSC and T. A. Roppel - AU STANDARDS Chair: Walter J. Karplus - UCLA Co-Chair: Mary Lou Padgett - Auburn University Working Groups: IEEE-NNC Glossary, Performance, Interfaces, Fuzzy Systems, Virtual Reality SCS Neural Networks and Simulation ------------------------------- FNN ----------------------------------- Chair: Mary Lou Padgett Co-Chairs: Hamid Berenji - NASA/Ames Sylvano Colombano - NASA/Ames * Joseph Mica - NASA/Goddard Robert Savely - NASA/JSC * Lotfi Zadeh - Berkeley Sunday, November 7, 1993 - Separate Fee Fuzzy Systems * Neural Networks * Computational AI Basics * Applications * Examples * Standards * NETS Software Given ======================================================================== AUTHOR INSTRUCTIONS FOR SIMTEC AND WNN Papers containing original research contributions, tutorials, written and oral descriptions of company thrusts and government projects are of interest. Fully reviewed papers will be labeled such in the proceedings. Other presentations may be oral, or less formal, and require only an abstract submission by June 1. Prospective authors are invited to submit full papers (maximum of 20 pages double spaced) describing original or tutorial work for review. Four copies of the manuscript should be submitted by June 1. Late papers will be considered on a space available basis. Please include: full name, affiliation, address, phone and fax numbers, and e-mail address of each author and designate the author who is to be the contact. Authors must obtain employer, client or government releases prior to submission of the final manuscript. Accepted papers will be included in the conference proceedings, provided authors meet published deadlines and pay one registration fee ($315) per paper or presentation accepted. Suggestions for panel discussions and other conference activities are welcomed. Submit by June 1, for consideration and inclusion in the preliminary program of the conference. KEY DATES: Draft papers, proposals and/or abstracts Due: June 1, 1993 Camera-ready papers: June 30, 1993 CONTACT: Mary Lou Padgett, Associate VP for SimTec Auburn University, 1165 Owens Road, Auburn, AL 36830 (205) 821-2472/3488; Fax: (205) 844-1809; mpadgett at eng.auburn.edu (for SimTec submissions address to Martin Dost, c/o Padgett) ----------------------------- REGISTRATION ----------------------------- 1993 INTERNATIONAL SIMULATION TECHNOLOGY MULTICONFERENCE San Francisco Airport Marriott, California November 7-10, 1993 SimTec93 * WNN93 * FNN93 Registration fee for SimTec or WNN includes attendance at both conferenc es, speakers' breakfast (if applicable), one Proceedings and any planned social functions. Separate Sunday registration fee for FNN includes attendance at all Nov. 7 presentations, coffee breaks, handouts, executable copy of NASA NETS software. Make checks payable to SCS. Mail registration to SCS, P.O.Box 17900, San Diego, CA 92117-7900. Phone: (619) 277-3888. Fax: (619) 277-3930. Authors: This registration form must be completed and returned with your manuscript by June 30. Registration fee must be guaranteed by receipt of check or credit card number for paper inclusion in conference proceedings. Registration is not refundable. Others may preregister until Oct. 7, 1993. Commercial Exhibitors: Call for information! Name: _________________________________________________________________ Position: ____________________________________________________________ Organization: ________________________________________________________ Address: _____________________________________________________________ _____________________________________________________________ City: _____________________ State/Country_____________ Zip: __________ Business Phone: ___________________ Home Phone: ______________________ FAX: ___________________ Email: ______________________________________ Paper(1)# (if any): Paper(1) Title: Paper(2)# (if any): Paper(2) Title: * FNN Registration Fee ($185 before Oct 7, $265 after): $_______________ * SimTec ___ or WNN ___ Conference Fee: Attendees (Members $315 before Oct 7, $375 after; Non-members $375 before Oct 7, $435 after): . . . $_______________ Authors ($315 per paper or presentation, due July 30):$_______________ Extra Page Charges ($75 per extra page, if over 6 pages in a camera-ready paper):. $_______________ Membership: SCS___ NASA___ SPIE___ INNS___ IEEE-NNC___ Member Number: * SCS Membership Dues ($60 - enclose membership appl.):$_______________ * TOTAL: . . . . . . . . . . . . . . . . . . . . . . . $_______________ Method of Payment (No Cash Accepted): Visa___ Mastercard___ Am. Express___ Check___ Company PO___ Gov't Form 1556___ Card Number: Exp. Date: Authorizing Signature: - - - - - - - - MAKE HOTEL RESERVATIONS INDEPENDENTLY!!! - - - - - - - - Mention SOCIETY FOR COMPUTER SIMULATION for conference rates of $90. San Francisco Airport MARRIOTT 1800 Old Bayshore Hwy., Burlingame, CA 94010-1294 415-692-9100 Location: Bayside, 1 mile south of San Francisco International Airport at the Millbrae Avenue East exit. Guest Services: Complimentary Airport Shuttle Service * Auto Rental Valet and Free Parking * Gift Shop * Disco * Restaurants Luxury Rooms: $90 single or double. Reserve before October 7, 1993. Places to See/Things to Do: Fisherman's Wharf * Chinatown * Ghiradelli Square * The Cannery Golden Gate Bridge and Park * Whalewatching * Half Moon Bay Vineyard Tours in Napa and Sonoma Valley * Candlestick Park SimTec93 * WNN93 * FNN93 SEE YOU IN SAN FRANCISCO! From mm at sedal.sedal.su.OZ.AU Sat Apr 24 11:57:50 1993 From: mm at sedal.sedal.su.OZ.AU (Multi-Module Environment) Date: Sat, 24 Apr 93 10:57:50 EST Subject: MUME version 0.6 is available Message-ID: <9304240057.AA10348@sedal.sedal.su.OZ.AU> MUME 0.6 IS NOW AVAILABLE The Multi-Module Neural Computing Environment (MUME) version 0.6 (sources only) is now available. MUME-0.6 compiles on a variety of Unix machines as well on the Fujitsu VP2200 and PCs (MSDOS 5.0 or higher and using DJGCC). HOW TO GET IT ------------- It can be acquired by fetching the licence file: file license.ps (postrscript file) machine 129.78.13.39 directory: /pub login: anonymous password: your email address and getting it signed by an authorised person and then sending/faxing it to MUME 0.6 SEDAL Sydney University Electrical Engineering NSW 2006 Australia Fax: (+61-2) 660-1228 The machine/account/passwd where you can ftp the sources will then be communicated to you. *** PLEASE DO NOT FORGET TO WRITE YOUR EMAIL CONTACT ON THE FAXED LICENSE *** PC USERS -------- If you don't have the DJGCC compiler, you can write to the address above with a signed license and a cheque for A$150 (for media/doc/postage) and we will forward to you the software and binaries. Do not forget to clearly specify the media (3.5" or 5"1/4) and your surface mail address. Note MUME compiled under DJGCC will not run under Microsoft's Windows. MAILING LIST ------------ Once you have the software, you can ask to be include on a mailing list by sending your email address to mume-request at sedal.su.oz.au MORE INFO ABOUT MUME OR CHANGES ------------------------------- If you don't know what MUME is, you can fetch the file /pub/mume-overview.ps.Z from 129.78.13.39 (login as anonymous). Otherwise here is a copy of the CHANGES file (from version 0.5 to 0.6): o A detailled basic tutorial has been written (directory tutes/tut0) o To simplify interconnections statements between nets, MUME now generates default "iface"s. for example for an MLP called john, MUME automatically generates the interfaces john.in (input layer) and john.out (output layer). This applies to most nets. The enhancement of the interconnection semantic has been simplified even further by introducing "base" index which simplifies the neuron reference. All information about interfaces is now described in a separate manual page called IFACE.5. o The configuration files can make use of symbols which can be set in the file or on the command line of the front-end program (see man pages SYMBOLS.5 and MMN.5). Some nets now also define their own symbols (eg. "mlp" net). o The specification of neuron index for "nfun" keyword has been emhanced to allow easier indexing (see NET.5). o All front ends now default to a "test" mode. To train the switch "-train" is required. o Data reading routines of ENV net have been optimised o Data normalisation statements in ENV have been modified (see man pages ENV.5 and NORM.5) o MUME now supports the use of a validation set during training. The main purpose of a validation set is to prevent overtraining, as the error on both the training and validation sets can be tracked as training progresses. To use the validation set, set the optional "Validate" flag in the system definition section to 1 (using the statement "Validate 1;") and specify a validation data set in all ENV modules (using the statement "data Validate ;"). The error on the validation set will now be logged as a 3rd column along with the epoch number and training error. See the ENV.5 and MMN.5 man pages for more information. o MUME now catches more system signals when possible and exit after saving the net states upon receiving them. The signals are: SIGINT, SIGTERM, SIGXCPU, and SIGXFSZ. o Logging output is more consistent under the control of the "-verbose" switch. o the following learning algorithms have been added: stochastic error descent for limited precision training reinforcement learning conjugate gradient simplex based methods o the following net classes has been added: resource allocation nets (class RAN) NeTtalk postprocessing module (class N2K) o the class RBPTT has been renamed WPANG. o the WZ class (continuously running recurrent net) has now what is called pins which have 0 propagation delays o and of course, many bugs were fixed. The behaviour of the learning algorithms have not changed between 0.5 and 0.6. All configuration files should still run under 0.6 except for normalisation statements in the ENV class. We are sure that the new statements make declarations much easier. mume-request at sedal.su.OZ.AU From annette at cdu.ucl.ac.uk Thu Apr 22 13:10:33 1993 From: annette at cdu.ucl.ac.uk (Annette Karmiloff-Smith) Date: Thu, 22 Apr 93 13:10:33 BST Subject: Job possibility in London Message-ID: <9304221210.AA06205@cdu.ucl.ac.uk> MEDICAL RESEARCH COUNCIL, COGNITIVE DEVELOPMENT UNIT, LONDON A short term non-clinical scientific post is available at the CDU in London for 3 years, to work on the biological basis of cognitive development alongside Dr Mark Johnson. The successful candidate should have a PhD and solid experience in formal computational modelling of developmental processes. In addition, we would require experience in one or more biological techniques, such as event- related potentials, as well as interest in some area of cognitive development. The salary is on the non-clinical scientific scale Pounds Sterling 15,563 - 24,736 per annum, plus Pounds Sterling 2,134 London Weighting. Applications should be made in writing BY 15 MAY 1993, enclosing CV and names of three referees to: The Director, Professor John Morton, 17 Gordon Street, London WC1H OAH, UK (Fax 071-383-0398, E-mail: john at uk.ac.cdu.ucl) The Medical Research Council is an equal opportunities employer. -o0o- From P.Refenes at cs.ucl.ac.uk Mon Apr 26 07:04:38 1993 From: P.Refenes at cs.ucl.ac.uk (P.Refenes@cs.ucl.ac.uk) Date: Mon, 26 Apr 93 12:04:38 +0100 Subject: No subject Message-ID: ************* PLEASE DO NOT FORWARD TO OTHER LISTS ********** PROVISIONAL PROGRAMME Third International Conference on 'Artificial Neural Networks' Brighton Conference Centre, UK: 25 - 27 May 1993 SECRETARIAT: Sheila Griffiths, ANN'93 Secretariat, Conference Services, IEE, Savoy Place, London WC2R OBL, UK Tel: ++ 44 71 344 54 58 / 54 77 Fax: ++ 44 71 497 36 33 Monday, 24 May 16.00 - 18.00 hrs Registration Tuesday, 25 May 08.00 hrs Registration 09.30 hrs Formal Opening Address of Welcome: Dr R Voles Chairman, Electronics Division Institution of Electrical Engineers Keynote Address: Professor R M Goodman California Institute of Technology USA 10.30 hrs Close of Session and Coffee 11.00 hrs Session 1 - VISION I Session Chairman: A Wright 195 'BARTIN applied to visual inspection of axisymmetric engineering parts' D W McMichael DRA, UK 94 'A practical view based 3D object recognition system' A Evans, J E W Mayhew and N Thacker University of Sheffield, UK 55 'Neural network paradigm for visual pattern recognition' S J Bye Telecom Australia, Australia A Adams University of Tasmania, Australia 130 'Labelling images with a neural network' W P J Mackeown and B T Thomas University of Bristol, UK W A Wright and P Greenway British Aerospace PLC, UK 12.30 hrs Close of Session and Lunch 14.00 hrs Session 2 - ARCHITECTURE I Session Chairman: R Rohwer 188 'Neural network validation: An illustration from the monitoring of multi-phase flows' C M Bishop AEA Technology, UK 109 'Comparing parameters selection methods and weights rounding techniques to optimize the learning in neural networks' J-F Grandin, B Braban, A Halioua and C Ledoux Thomson CSF, France 108 'On recurrent neural networks and representing finite-state recognizers' M W Goudreau and C L Giles NEC Research Institute, Inc., USA 172 'Cascadability and in-situ learning for VLSI multi-layer networks' J Tombs, G Cairns and L Tarassenko University of Oxford, UK 15.30 hrs Close of Session and Tea 16.00 hrs Session 3 - ANALYSIS I Session Chairman: D Lowe 21 'An adaptive bayesian network for low-level image processing' Dr S P Luttrell Defence Research Agency, UK 185 'Neural computing: A new route to software reliability' Professor D Partridge and N Sharkey University of Exeter, UK 50 'Comparison of the performance of vector quantiser training algorithms' J V Black DRA Malvern, UK 173 'Improved generalization and network pruning using adaptive laplace regularization' P M Williams University of Sussex, UK 121 'Improving generalisation with Ockham's networks: Minimum description length networks' G D Kendall and T J Hall King's College London, UK 18.00 hrs Close of Session 18.15 - 19.00 hrs Civic Reception Wednesday, 26 May 08.30 hrs Session 4 - MEDICAL Session Chairman: P Refenes * 'Novelty, validation and classification of medical data: A unified approach using radar basis function architectures' L Tarassenko and S J Roberts University of Oxford, UK 65 'A comparison of neural network architectures for cervical cell classification' S J McKenna, A Y Cairns and I W Ricketts University of Dundee, UK 153 'Ultrasonic tissue characterization using neural networks' T E Schouten, M K Gebbinck, J M Thijssen and J T M Verhoeven Katholieke Universiteit Nijmegen, Netherlands 171 'Realization of physiological eye movements by automatic selection of control laws using artificial neural network' H Wakamatsu Tokyo Medical and Dental University, Japan H Suda and M Kuwano Fukui University, Japan 10.30 hrs Close of Session and Coffee 11.00 hrs Session 5 - APPLICATIONS Session Chairman: C Satchwell 191 'Neural network system for tactical asset allocation in the global bond markets' A N Refenes University College London C Diamond. M Azema-Barac and J Shadbolt ECONOSTAT Ltd, UK 19 'Experience with artificial neural network models for short-term load forecasting in electrical power systems: A proposed application of expert networks' A Asar and J R McDonald University of Strathclyde, UK W Rattray Scottish Power, UK 105 'Central auditory model for spectral processing' Y Gao and J-P Haton CRIN, France T Huang Chinese Acadmeny of Sciences, China 96 'Investigating the recognition of false patterns in backpropagation networks' Dr M C Fairhurst, D L Bisset and G C Vasconcelos University of Kent, UK 12.30 hrs Close of Session and Lunch 14.00 hrs Session 6 - POSTER SESSION AND SESSION ON THE INITIATIVES IN NEURAL NETWORKS IN THE UK Session Chairman: R Wiggins, DTI 'The Neural Computing Applications Forum' Simon Cummings British Airways, UK 'The Department of Trade and Industry programme' Ray Brown DTI, UK Representatives of DTI sponsored clubs will give presentations of their activities: A Furness Keel University, UK Derek Bunn London Business School, UK C Bishop AEA Technology, UK Vic Bevan EDS Scicon, UK Paul gregory Recognition Research Ltd, UK A Carr ERA Technology, UK 15.30 hrs Close of Session and Tea POSTER PAPERS 70 'Stochastic analysis and comparison of kohonen SOM with optimal filter' N M Allinson and H Yin University of York, UK 183 'Learning and prediction of nuclear radioactive properties with artificial neural networks' S Gazula University of Miami, USA 38 'An 'introspective' network that can learn to run its own weight change algorithm' J Schmidhuber Technische Universitat Munchen, Germany 91 'Using prototypes to solve problems in neural net classifiers' C Decaestecker IRIDIA - Universite Libre de Bruxelles, Belgium 161 'Scene segmentation of natural images using texture features and back-propagation' B Sridhar, G Chatterjee and A Phatak NASA Ames Research Center, USA 20 'On-line adaption in robot control' D A Fraser, K Althoefer and F Azhar King's College London, UK 59 'Neural network for modelling and control of fed batch fermentation process' N A Jalel, J R Leigh and D Tsaptsinos University of Westminster, UK 14 'Towards a neural network based system for skin cancer diagnosis' Dr E Claridge University of Birmingham, UK R T J Bostock and A J Harget Aston University, UK P N Hall Wardsley Hospital, UK 23 'Modelling of a fermentation process using a time-delay neural network' D Tsaptsinos and J R Leigh University of Westminster, UK 152 'Minimisation of torque ripple in a switched reluctance motor using a neural network' D S Reay, T C Green and B W Williams Heriot-Watt University, UK 137 'Neural network based fingerprint classification' K Moscinska and G Tyma Silesian Technical University, Poland 69 'Variable bit rate block truncation coding for image compression using hopfield neural networks' Dr M R Varley, G Qiu and T J Terrell University of Central Lancashire, UK 192 'Target classification using neural and classical techniques' A K Patel, P R Collins and W A Wright Sowerby Research Centre, UK 87 'A stochastic reverse interpolation algorithm for real-valued function learning' Dr T G Clarkson, D Gorse, Y Guan and J G Taylor King's College London, UK 119 'Dynamic DBP learning algorithm for real time applications' Y Jin, A G Pipe and A Winfield University of the West of England, UK 136 'A probabilistic approach which provides a modular and adaptive neural network architecture for discrimination' C Monrocq Thomson-CSF LCR, France 148 'Neural network based dynamic models' B Pataki Technical University of Budapest, Hungary 80 'External stimuli in optimised attractor neural networks for sparsely coded patterns' A N Burkitt Australian National University, Australia 103 'Parallel learning algorithms for principal component extraction' Dr B Freisleben University of Darmstadt, Germany 97 'Modular connectionist architectures for multi-patient ECG recognition' S Farrugia, P Nickolls and H Yee The University of Sydney, Australia 178 'Decentralized hopfield neural network applied to maintenance scheduling of generating units in power systems' K Yoshimoto, K Yasuda and R Yokoyama Tokyo Metropolitan University, Japan B J Cory Imperial College of Science, Technology and Medicine, UK 190 'Neural network processing of scattered light measurements in the detection of immiscible water pollutants' Dr P R Smith, D A Green, R Naimimohosses and H Thomason Loughborough University of Technology, UK 56 'A connectionist approach to SDH bandwidth management' S J Bye Telecom Australia, Australia 141 'LSP speech synthesis using backpropagation networks' P Noakes and G C Cawley University of Essex, UK 16.00 hrs Session 7 - CONTROL AND ROBOTICS Session Chairman: A J Morris 88 'Analysing recurrent dynamical networks evolved for robotic control' Dr D Cliff, I Harvey and P Husbands University of Sussex, UK 167 'Robot path planning using VLSI resistive grids' Ms G Marshall and L Tarassenko University of Oxford, UK 75 'Minimum variance control of a class of nonlinear plants with neural networks' Professor S Bittanti and L Piroddi Politecnico di Milano, Italy 159 'Neural networks performing system identification for control applications' O Sorensen Aalborg University, Denmark 131 'A neural network motion predictor' H Meng and P D Picton Open University, UK 18.00 hrs Close of Session 19.30 hrs Conference Dinner at Old Ship Hotel Thursday, 27 May 09.00 hrs Session 8 - ANALYSIS II Session Chairman: C Bishop 149 'A hebbian/anti-hebbian network which optimize information capacity by orthonormalizing the principal subspace' Dr M D Plumbley King's College London, UK 31 'A novel unsupervised classification method' J Schmidhuber and D Prelinger Technische Universitat Munchen, Germany 129 'Novel 'Topographic' nonlinear feature extraction using radial basis functions for concentration coding in the 'Artificial Nose'' D Lowe DRA Malvern, UK 117 'Valid generalization in radial basis function networks and modified kanerva models' S B Holden Cambridge University, UK 10.30 hrs Close of Session and Coffee 11.00 hrs Session 9 - APPLICATIONS II Session Chairman: L Tarassenko 133 'Speaker identification using radial basis functions' M W Mak, W G Allen and G G Sexton University of Northumbria at Newcastle, UK 99 'Nonlinear noise filtering with neural networks: Comparison with Wiener optimal filtering' T Fechner Dainler Benz AG Research Institute, Germany 41 'Complex-valued radial basis function networks' Dr S Chen, P M Grant, S McLaughlin and B Mulgrew The University of Edinburgh, UK 76 'Neural Nets for first break detection in seismic reflection data' J F Boyce and C H Dimitropoulos King's College London, UK 12.30 hrs Close of Session and Lunch 14.00 hrs Session 10: VISION II Session Chairman: S Lutterell 40 'Target recognition in infra-red imagery using neural networks and machine learning' A Crowe British Aerospace, UK W A Wright, M A Green, T M Banks and A D Hughes British Aerospace (Systems & Equipment) Limited, UK 170 'An original approach for the localization of objects in images' R Vaillant, Y Le Cun and C Monrocq Thomson-CSF, France 84 'Unsupervised feature extraction by hypothesis of feature centres' Ms M-Y Chan and T J Hall King's College London, UK 11 'A hardware polynomial feature net for handprinted digit recognition' A Rao Eastman Kodak Company, USA P G Anderson Rochester Institute of Technology, USA R S Gaborski and K Jaiswal Arizona State University, USA 16.30 hrs CLOSE OF CONFERENCE From ray at orthanc.cs.su.OZ.AU Mon Apr 26 22:40:19 1993 From: ray at orthanc.cs.su.OZ.AU (Raymond Lister) Date: Tue, 27 Apr 1993 12:40:19 +1000 Subject: Annealing Networks and Fractal Landscapes Message-ID: A postscript file containing the following paper has been placed in the neuroprose archive, as lister.anneal.ps.Z ... Annealing Networks and Fractal Landscapes Raymond Lister Dept. of Electrical Engineering, University of Queensland QLD 4072, Australia ray at s1.elec.uq.oz.au Abstract It is well known that Hopfield and Tank networks give poor solutions to the Traveling Salesman Problem; but we show that the popular explanation for the poor performance is either wrong, or at best incomplete. The popular explanation is that the network has difficulty in balancing the trade-off between the path length and the legality components of the energy function. We first describe an experiment which has an outcome that is not accounted for by this explanation. We then propose an alternative: these networks would scale better if their dynamics effectively implemented a "divide-and-conquer" strategy. That is, if they recursively decomposed the problem into smaller independent sub-problems. An annealing network can do so if the energy landscape has a self-similar "quasi-fractal" structure. We believe this proposition applies to both discrete and analog networks. We support our proposition by describing results from our work on the Traveling Salesman Problem. We then consider the implications for two other optimization problems: graph bisection and coloring. Here is an example of how to retrieve this file: > ftp archive.cis.ohio-state.edu (or ftp 128.146.8.52) Connected to archive.cis.ohio-state.edu. 220 archive.cis.ohio-state.edu FTP server ready. Name: anonymous 331 Guest login ok, send ident as password. Password: 230 Guest login ok, access restrictions apply. ftp> binary 200 Type set to I. ftp> cd pub/neuroprose 250 CWD command successful. ftp> get lister.anneal.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for lister.anneal.ps.Z 226 Transfer complete. ftp> quit 221 Goodbye. > uncompress lister.anneal.ps.Z > lpr lister.anneal.ps From terry at helmholtz.sdsc.edu Tue Apr 27 02:08:13 1993 From: terry at helmholtz.sdsc.edu (Terry Sejnowski) Date: Mon, 26 Apr 93 23:08:13 PDT Subject: NEURAL COMPUTATION: MAY 1993 Message-ID: <9304270608.AA03254@helmholtz.sdsc.edu> Neural Computation, Volume 5, Number 3 Article A Model for Motor Endplate Morphogenesis: Diffusible Morphogens, Transmembrane Signaling, and Compartmentalized Gene Expression Michel Kerszberg and Jean-Pierre Changeau Notes Universal Approximation by Phase Series and Fixed-Weight Networks Neil E. Cotter and Peter R. Conwell Backpropagation with Homotopy Liping Yang and Wanzhen Yu Improving Rejection Performance on Handwritten Digits by Training with "Rubbish" Jane Bromley and John S. Denker Vapnik-Chervonenkis Dimension Bounds for Two- and Three-Layer Networks Peter L. Bartlett Letters A Neural Network for the Processing of Optic Flow from Ego-Motion in Man and Higher Mammals Markus Lappe and losef P. Rauschecker Arbitrary Elastic Topologies and Ocular Dominance Peter Dayan Neural Networks for Fingerprint Recognition Pierre Baldi and Yves Chauvin Centered-Object Integrated Segmentation and Recognition of Overlapping Handprinted Characters Gale L. Martin Surface Interpolation Networks Alex P. Pentland Combining Exploratory Projection Pursuit and Projection Pursuit Regression with Application to Neural Networks Nathan Intrator A Simplified Gradient Algorithm for IIR Synapse Multilayer Perceptrons Andrew D. Back and Ah Chung Tsoi The Characteristics of the Convergence Time of Associative Neural Networks Toshiaki Tanaka and Miki Ynnlada Robustness in Multilayer Perceptrons P. Kerlirzin and F. Vallet Pattern Discrimination Using Feedforward Networks: A Benchmark Study of Scaling Behavior Thorsteinn Rognvaldsson A Neural Network That Learns to Interpret Myocardial Planar Thallium Scintigrams Charles Rosenberg, Jacob Erel, and Henri Atlan ----- SUBSCRIPTIONS - VOLUME 5 - BIMONTHLY (6 issues) ______ $40 Student ______ $65 Individual ______ $156 Institution Add $22 for postage and handling outside USA (+7% GST for Canada). (Back issues from Volumes 1-4 are regularly available for $28 each to institutions and $14 each for individuals Add $5 for postage per issue outside USA (+7% GST for Canada) MIT Press Journals, 55 Hayward Street, Cambridge, MA 02142. Tel: (617) 253-2889 FAX: (617) 258-6779 e-mail: hiscox at mitvma.mit.edu ----- From eric at research.nj.nec.com Tue Apr 27 10:25:23 1993 From: eric at research.nj.nec.com (Eric B. Baum) Date: Tue, 27 Apr 93 10:25:23 EDT Subject: Paper Announcement Message-ID: <9304271425.AA06945@yin> A revised draft of the following preprint is now available via the NEC Research Institute ftp archive external.nj.nec.com. Instructions for retrieval from the archive follow the summary. NOTE- This is NOT the Neuroprose directory. Thanks to those whose questions or comments regarding the first draft contributed to this revision. Any further comments are welcome. ----------------------------------------------------------------- Best Play for Imperfect Players and Game Tree Search Eric B. Baum and Warren D. Smith NEC Research Institute 4 Independence Way Princeton NJ 08540 ABSTRACT We propose a new approach to game tree search. We train up an evaluation function which returns, rather than a single number estimating the `value' of a position, a probability distribution $P_L(x)$. $P_L(x)$ is the probability that if we expanded leaf $L$ to some depth, the backed up value of leaf $L$ would then be found to be $x$. We describe how to propagate these distributions efficiently up the tree so that at any node n we compute without approximation the probability node n's negamax value is x given that a value is assigned to each leaf from its distribution. After we are done expanding the tree, the best move is the child of the root whose distribution has highest mean. Note that we take means at the child of the root {\it after} propagating, whereas the normal (Shannon) approach takes the mean at the leaves before propagating, which throws away information. Now we model the expansion of a leaf as selection of one value from its distribution. The total utility of all possible expansion is then by definition the ensemble sum over those possible leaf configurations for which the current favorite move is inferior to some alternate move, weighted by the probability of the leaf configuration and the amount the current favorite move is inferior. We propose as the natural measure of the expansion importance of leaf L, the expected absolute change in this utility when we expand leaf L. We support this proposal with several arguments including an approximation theorem valid in the limit that one expands until the remaining utility of expansion becomes small. In summary, we gather distributions at the leaves, propagate exactly all this information to the root, and incrementally grow a tree expanding approximately the most interesting leaf at each step. Under reasonable conditions, we accomplish all of this in time $O(N)$, where N is the number of leaves in the tree when we are done expanding. That is, we pay only a small constant factor overhead for all of our bookkeeping. ---------------------------------------------------------------------- FTP INSTRUCTIONS unix> ftp external.nj.nec.com (138.15.10.100) Name: anonymous Password: (your_userid at your_site) ftp> cd pub/eric/papers ftp> binary ftp> get game.ps.Z ftp> quit unix> uncompress game.ps.Z ----------------------------------------------------------------------- Eric Baum NEC Research Institute 4 Independence Way Princeton NJ 08540 Inet: eric at research.nj.nec.com UUCP: princeton!nec!eric MAIL: 4 Independence Way, Princeton NJ 08540 PHONE: (609) 951-2712 FAX: (609) 951-2482 From jls at computer-science.manchester.ac.uk Fri Apr 23 17:48:29 1993 From: jls at computer-science.manchester.ac.uk (Jon Shapiro) Date: Fri, 23 Apr 93 17:48:29 BST Subject: Research Posts Message-ID: <9304231648.AA10820@r8q.cs.man.ac.uk> Two Research Posts Department of Psychology, University of Lancaster Department of Computer Science, University of Manchester Short-term memory for verbal sequences: psychological experiments and connectionist modelling. Applications are invited for two posts on a research project investigating short-term memory mechanisms for processing verbal information. The first post is for a postdoctoral researcher to work with Dr. Jonathan Shapiro at Manchester on connectionist modelling and analysis. The second post is for a graduate researcher to assist Professor Graham Hitch with the psychological experiments. Both post can begin as soon as possible and run through December 1995. Applicants for the modelling post should have expertise in computational and mathematical aspects of connectionism and a Ph.D. in a relevant subject. The salary range is 15,221 - 16,629 U.K. pounds based on age and experience. Applicants for the experimental post should have a first degree in psychology, and interests in memory and cognition. The salary range is 13,632 - 15,221 U.K. pounds. To apply for either post, send curriculum vita and the names and addresses of two professional referees to the address below. For further information, you may also write to the address below. ------------------------------------------------------------------------- Jonathan Shapiro Computer Science Dept University of Manchester Oxford Road Manchester M13 9PL United Kingdom. Phone: 44-(0)61 275 6253 Fax: 44-(0)61 275 6236 E-mail: jls at cs.man.ac.uk From jab at GS116.SP.CS.CMU.EDU Tue Apr 27 15:48:30 1993 From: jab at GS116.SP.CS.CMU.EDU (Justin Boyan) Date: Tue, 27 Apr 93 15:48:30 EDT Subject: Modular Networks for Reinforcement Learning of Backgammon Strategies Message-ID: The file boyan.backgammon-thesis.ps.Z is now available in the neuroprose archive. _______________________ Modular Neural Networks for Learning Context-Dependent Game Strategies Justin A. Boyan Master's Thesis, University of Cambridge, Computer Speech and Language Processing Supervisor: Professor Frank Fallside 17 August 1992 Abstract: Recent results by Tesauro in the domain of backgammon indicate that a neural network, trained by temporal difference methods to evaluate positions generated by self-play, can reach an advanced level of backgammon skill. For my summer thesis project, I first implemented the TD/neural network learning algorithms and confirmed Tesauro's results, using the domains of tic-tac-toe and backgammon. Then, motivated by Waibel's success with modular neural networks for phoneme recognition, I experimented with using two modular architectures (DDD and Meta-Pi) in place of the monolithic networks. I found that using the modular networks significantly enhanced the ability of the backgammon evaluator to change its strategic priorities depending on the current game context. My best modular backgammon network was entered in the 1992 Computer Games Olympiad in London, where it finished in second place. _______________________ Here is an example of how to retrieve this paper: > ftp archive.cis.ohio-state.edu (or ftp 128.146.8.52) Connected to archive.cis.ohio-state.edu. 220 archive.cis.ohio-state.edu FTP server ready. Name: anonymous 331 Guest login ok, send ident as password. Password: 230 Guest login ok, access restrictions apply. ftp> binary 200 Type set to I. ftp> cd pub/neuroprose 250 CWD command successful. ftp> get boyan.backgammon-thesis.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for boyan.backgammon-thesis.ps.Z 226 Transfer complete. ftp> quit 221 Goodbye. > uncompress boyan.backgammon-thesis.ps.Z > lpr boyan.backgammon-thesis.ps From jordan at psyche.mit.edu Tue Apr 27 18:19:19 1993 From: jordan at psyche.mit.edu (Michael Jordan) Date: Tue, 27 Apr 93 18:19:19 EDT Subject: EM and hierarchies of experts Message-ID: The following technical report has been placed in the neuroprose directory, as jordan.hierarchies.ps.Z: Hierarchical mixtures of experts and the EM algorithm Michael I. Jordan MIT Robert A. Jacobs University of Rochester We present a tree-structured architecture for supervised learning. The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coefficients and the mixture components are generalized linear models (GLIM's). Learning is treated as a maximum likelihood problem; in particular, we present an Expectation-Maximization (EM) algorithm for adjusting the parameters of the architecture. We also develop an on-line learning algorithm in which the parameters are updated incrementally. Comparative simulation results are presented in the robot dynamics domain. ------------------------------------------------ Here is an example of how to retrieve this file: > ftp archive.cis.ohio-state.edu (or ftp 128.146.8.52) Connected to archive.cis.ohio-state.edu. 220 archive.cis.ohio-state.edu FTP server ready. Name: anonymous 331 Guest login ok, send ident as password. Password: 230 Guest login ok, access restrictions apply. ftp> binary 200 Type set to I. ftp> cd pub/neuroprose 250 CWD command successful. ftp> get jordan.hierarchies.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for jordan.hierarchies.ps.Z 226 Transfer complete. ftp> quit 221 Goodbye. > uncompress jordan.hierarchies.ps.Z > lpr jordan.hierarchies.ps From ray at orthanc.cs.su.OZ.AU Wed Apr 28 08:48:13 1993 From: ray at orthanc.cs.su.OZ.AU (Raymond Lister) Date: Wed, 28 Apr 1993 22:48:13 +1000 Subject: problems with "Annealing Networks and Fractal Landscapes" Message-ID: > From ray at orthanc.cs.su.OZ.AU Tue Apr 27 12:42:31 1993 > Subject: Annealing Networks and Fractal Landscapes > To: connectionists at cs.cmu.edu > > A postscript file containing the following paper has been placed in the > neuroprose archive, as lister.anneal.ps.Z ... > > > Annealing Networks and Fractal Landscapes A number of people have reported difficulty with printing the above non-standard postscript file. In most cases, the problem can be solved by inserting a line at the start of the file, containing the characters `%!'. (That is, the two characters between the `' characters.) The file may still not preview using certain tools, such as ghostview, but the paper is only 6 pages, so you won't be killing too many trees if you print it off. From rsun at athos.cs.ua.edu Wed Apr 28 11:30:55 1993 From: rsun at athos.cs.ua.edu (Ron Sun) Date: Wed, 28 Apr 1993 10:30:55 -0500 Subject: Bibliography available Message-ID: <9304281530.AA18716@athos.cs.ua.edu> ---------------------- Bibliography Available ---------------------- A compiled bibliography of connectionist models with symbolic processing is available in neuroprose now. This bibliography will be included in: R.Sun and L.Bookman. (eds.) Computational Architectures Integrating Neural and Symbolic Processes. Kluwer Academic Publishers. 1993. Thanks to all those who contributed. Any further suggestions and additions are also welcome. To get a copy of the bibliography, use FTP as follows: unix> ftp archive.cis.ohio-state.edu (or 128.146.8.52) Name: anonymous Password: ftp> cd pub/neuroprose ftp> binary ftp> get sun.nn-sp-bib.ps.Z ftp> quit unix> uncompress sun.nn-sp-bib.ps.Z unix> lpr sun.nn-sp-bib.ps (or however you print postscript) * As usual, no hardcopy available. Sorry. From rsun at athos.cs.ua.edu Thu Apr 29 09:33:59 1993 From: rsun at athos.cs.ua.edu (Ron Sun) Date: Thu, 29 Apr 1993 08:33:59 -0500 Subject: No subject Message-ID: <9304291333.AA14656@athos.cs.ua.edu> Regarding the bibliography I mentioned in a previous message: Plase send any suggestions or additions you might have to ================================================================ Ron Sun, Ph.D Assistant Professor Department of Computer Science phone: (205) 348-6363 The University of Alabama fax: (205) 348-8573 Tuscaloosa, AL 35487 rsun at athos.cs.ua.edu ================================================================ Your help is greatly appreciated. However, the decision whether to include a paper or not is solely the responsibility of the editors. --Ron From greiner at learning.siemens.com Thu Apr 29 14:26:26 1993 From: greiner at learning.siemens.com (Russell Greiner) Date: Thu, 29 Apr 93 14:26:26 EDT Subject: CFP: "Computational Learning and Natural Learning" workshop Message-ID: <9304291826.AA06060@learning.siemens.com> CLNL'93 -- Call for Submissions Computational Learning and Natural Learning Provincetown, Massachusetts 10-12 September 1993 CLNL'93 is the fourth of an ongoing series of workshops designed to bring together researchers from a diverse set of disciplines -- including computational learning theory, AI/machine learning, connectionist learning, statistics, and control theory -- to explore issues at the intersection of theoretical learning research and natural learning systems. Theme: To be useful, the learning methods used by our fields must be able to handle the complications inherent in real-world tasks. We therefore encourage researchers to submit papers that discuss extensions to learning systems that let them address issues such as: * handling many irrelevant features * dealing with large amounts of noise * inducing very complex concepts * mining enormous sets of data * learning over extended periods of time * exploiting large amounts of background knowledge We welcome theoretical analyses, comparative studies of existing algorithms, psychological models of learning in complex domains, and reports on relevant new techniques. Submissions: Authors should submit three copies of an abstract (100 words or less) and a summary (2000 words or less) of original research to: CLNL'93 Workshop Learning Systems Department Siemens Corporate Research 755 College Road East Princeton, NJ 08540-6632 by 30 June 1993. We will also accept plain-text, stand-alone LaTeX or Postscript submissions sent by electronic mail to clnl93 at learning.scr.siemens.com Each submission will be refereed by the workshop organizers and evaluated based on its relevance to the theme, originality, clarity, and significance. Copies of accepted abstracts will be distributed at the workshop, and MIT Press has agreed to publish an edited volume that incorporates papers from the meeting, subject to revisions and additional reviewing. Invited Talks: Tom Dietterich Oregon State University Ron Rivest Massachusetts Institute of Technology Leo Breiman University of California, Berkeley Yann le Cun Bell Laboratories Important Dates: Deadline for submissions: 30 June 1993 Notification of acceptance: 20 July 1993 CLNL'93 Workshop: 10-12 September 1993 Organizing Committee: Russell Greiner, Steve Hanson, Stephen Judd, Pat Langley, Thomas Petsche, Ron Rivest, Tomaso Poggio Registration Information is available from clnl93 at learning.scr.siemens.com or the above address. From shavlik at cs.wisc.edu Thu Apr 29 15:30:13 1993 From: shavlik at cs.wisc.edu (Jude Shavlik) Date: Thu, 29 Apr 93 14:30:13 -0500 Subject: Symbolic Knowledge and Neural Learning: MLj Special Issue CFP Message-ID: <9304291930.AA01035@steves.cs.wisc.edu> CALL FOR PAPERS for a Special Issue of the Journal MACHINE LEARNING on SYMBOLIC KNOWLEDGE AND NEURAL LEARNING (edited by C. L. Giles and J. W. Shavlik) This special issue will focus on novel and effective methods for acquiring and refining symbolic knowledge with neural learning. Particular topics of interest include insertion of prior knowledge into neural networks, alterations to standard neural training that are appropriate for the refinement of symbolic knowledge, and understanding trained neural networks. Submission deadline: November 1, 1993 (See a recent issue of Machine Learning for information for authors.) Send two (2) copies of submissions to: Jude Shavlik Computer Sciences Dept University of Wisconsin 1210 W. Dayton Street Madison, WI 53706 USA (608) 262-7784 shavlik at cs.wisc.edu Also mail four (4) copies of submitted papers to: Karen Cullen MACHINE LEARNING Editorial Office Kluwer Academic Publishers 101 Philip Drive Norwell, MA 02061 USA (617) 871-6300 karen at world.std.com Note: Machine Learning is now accepting submission of final copy in electronic form. There is a latex style file and related files available via anonymous ftp from world.std.com. Look in Kluwer/styles/journals for the files machl.sty, machl.doc, jpsfonts.sty, joursamp.tex, and jourtmpl.tex. From dario at cns.nyu.edu Fri Apr 30 09:31:34 1993 From: dario at cns.nyu.edu (Dario Ringach) Date: Fri, 30 Apr 93 09:31:34 EDT Subject: Brain Development Symposium in June Message-ID: <9304301331.AA20221@wotan.cns.nyu.edu> From tony at wotan.cns.nyu.edu Mon Apr 26 15:12:09 1993 From: tony at wotan.cns.nyu.edu (Tony Movshon) Date: Mon, 26 Apr 1993 15:12:09 -0400 Subject: Brain Development Symposium in June Message-ID: THE DEVELOPMENT OF BRAIN FUNCTION An International Symposium at New York University June 15 - 19, 1993 The Center for Neural Science at Scientific sessions will cover: New York University will hold its second International Symposium, o Cell-cell interactions The Development of Brain Function, at the Washington Square campus in o Migration and differentiation June, 1993. The symposium will begin on Tuesday afternoon, June o Neuroethological perspectives 15th, and end at lunchtime on Saturday, June 19th. The program o Activity-dependent processes will concentrate on areas of developmental neuroscience that o Visual and auditory function have seen substantial progress in recent years. The 40 distinguished o Connections and architecture invited speakers will cover topics of cortex that range from molecular and cel- lular mechanisms of brain develop- o Development of higher brain ment to analyses of infant function behavior. The symposium will be open to up to 400 attendees. The symposium is supported in part Registration cost is $75 ($40 for by an education grant from the students). Howard Hughes Medical Institute. Speakers Israel Abramov Darcy Kelley Chiye Aoki Lynne Kiorpes Jocelyn Bachevalier Eric Knudsen Martin Banks Patricia Kuhl Elizabeth Bates Arthur Lander Colin Blakemore Susan McConnell Tobias Bonhoeffer Kenneth Miller Sarah Bottjer David Moore Thomas Carew Anthony Movshon Connie Cepko Paul Patterson Martha Constantine-Paton Pasko Rakic Michael Friedlander Edwin Rubel Lincoln Gray Dan Sanes Ralph Greenspan Joshua Sanes Martin Grumet Carla Shatz Jeff Hall Nicholas Spitzer Mary Beth Hatten Michael Stryker Susan Hockfield Davida Teller Thomas Jessell Tim Tully Lawrence Katz Lynne Werner For further information, please contact: Jeanette Tacoronte Phone: 212 998-3949 Center for Neural Science New York University FAX: 212 995-4011 4 Washington Place, Room 809 New York, NY 10003 Email: symposium at cns.nyu.edu ************************************************************************ A complete program is available in electronic form. You can print the following page and use it as a registration form. ************************************************************************ THE DEVELOPMENT OF BRAIN FUNCTION An International Symposium at New York University June 15 - 19, 1993 REGISTRATION FORM Name: ______________________________________________________ Address: ______________________________________________________ ______________________________________________________ ______________________________________________________ Phone: ______________________________________________________ FAX: ______________________________________________________ E-mail: ______________________________________________________ REGISTRATION FEES Regular: $75, Student*: $40 *Students should document their status with a letter from their sponsor HOUSING Please check here to receive information about local hotels____________ PAYMENT Enclose a check or money order in US $ payable to New York University. Amount enclosed: $_______________ Return completed form to: The Development of Brain Function Center for Neural Science New York University 4 Washington Place, Room 809 New York, NY 10003 Phone: (212) 998-3949 FAX: (212) 995-4011 E-mail:symposium at cns.nyu.edu From annette at cdu.ucl.ac.uk Fri Apr 30 17:31:41 1993 From: annette at cdu.ucl.ac.uk (Annette Karmiloff-Smith) Date: Fri, 30 Apr 93 17:31:41 BST Subject: PhD in London Message-ID: <9304301631.AA06652@cdu.ucl.ac.uk> PhD STUDENTSHIP A Medical Research Council studentship for a PhD is available at the MRC Cognitive Development Unit in London (jointly with University College London), for three years from October 1993, for a student particularly interested in the cognitive aspects of abnormal development and how such studies also be used to further our understanding of the normal mind/brain. The CDU works on both normal and abnormal cognition (focal lesion infants, Down syndrome, autism, dyslexia, etc.) and has recently started a new project on Williams syndrome, a genetic disorder that leaves language, face processing and theory of mind relatively spared, in the face of severe deficits in number, spatial cognition and problem- solving. This offers exciting new possibilities for a bright, inquisitive scientific mind, in a relatively unchartered field of enquiry. Competence/interest in connectionist modelling would be an added advantage. The CDU is a small and very lively group of scientists with varied interests and common theoretical concerns. Students with or expecting a first class or upper second degree in cognitive science, psychology, or other related fields, should send CV and a brief outline of research interests, by 31st May latest, to: Professor Annette Karmiloff-Smith, Medical Research Council, Cognitive Development Unit, 17 Gordon Street, London, WC1H OAH. tel: 071 387 4692 fax: 071 383 0398 From DUDZIAK at vms.cis.pitt.edu Fri Apr 30 00:39:00 1993 From: DUDZIAK at vms.cis.pitt.edu (MARTIN DUDZIAK) Date: Thu, 29 Apr 1993 23:39 EST Subject: Announcement Message-ID: <01GXLNYZL448AIF6JQ@vms.cis.pitt.edu> Announcement Please Circulate to Faculty and Researchers in Physics, Computer Science, Economics, Mathematics, Business Schools There are some interesting opportunities for university/industry collaboration in the area of applying non-linear dynamical systems, including but not limited to connectionist networks, to problems in financial modeling within the banking sector. The projects for which I am responsible including modeling of fixed-income securities, forecasting of demand deposit accounts, improvments to traditional duration/market value models, forecasting select futures/commodities, and analysis of interest rate risks. We are somewhat less interested in the traditional stock-price forecasting applications for which there has been so much visibility of late and are more interested in the use of techniques such as NNs, fuzzy logic, chaos models and genetic algorithms for the identification and discrimination of useful features and parameters that can be applied to forecasting some rather indeterminate quantities. Our work is not a short-order task and we are looking for an academic partner with whom we might establish a long-term partnership. There are plenty of precedents for good collaborations of this sort on which we might model our joint effort. We envision building a set of tools that can be refined in the course of studying one or two particular problems from the above set and which as a toolset could be made available for use on other problems besides those of interest to those in finance and economics. Our problems are such that they are both real-world, down-to-earth applications in need of practical solutions and research-worthy in that not too much has been done in some of these topics. There is good thesis material, and good opportunity for breaking new ground. For instance, I see strong parallels between the currency balances and flows that we are trying to model and fluid dynamics... Cellular automata and parallel processing are two other methods that could be applied to some of these problems - it isn't just a matter of time series prediction (not to imply that the latter is trivial). A prior research track in the financial area is not as critical as an ability to work together on some practical problems (but without losing the spirit of scientific exploration and innovation). Being able to cooperatively show results and demonstrations of practical success is going to be very important. This is an introductory announcement of interest on our part and I welcome responses from individuals and groups that feel they have a common interest and something to contribute. I believe that a highly synergetic and mutually rewarding partnership is possible with the right team. For further information, please contact: Martin Dudziak (804) 782-5708 FAX (804) 782-5100 dudziak at vms.cis.pitt.edu From jls at computer-science.manchester.ac.uk Wed Apr 28 14:04:04 1993 From: jls at computer-science.manchester.ac.uk (Jon Shapiro) Date: Wed, 28 Apr 93 14:04:04 BST Subject: Research Posts Message-ID: <9304281304.AA12225@r8q.cs.man.ac.uk> Two Research Posts Department of Psychology, University of Lancaster Department of Computer Science, University of Manchester Short-term memory for verbal sequences: psychological experiments and connectionist modelling. Applications are invited for two posts on a research project investigating short-term memory mechanisms for processing verbal information. The first post is for a postdoctoral researcher to work with Dr. Jonathan Shapiro at Manchester on connectionist modelling and analysis. The second post is for a graduate researcher to assist Professor Graham Hitch with the psychological experiments. Both post can begin as soon as possible and run through December 1995. Applicants for the modelling post should have expertise in computational and mathematical aspects of connectionism and a Ph.D. in a relevant subject. The salary range is 15,221 - 16,629 U.K. pounds based on age and experience. Applicants for the experimental post should have a first degree in psychology, and interests in memory and cognition. The salary range is 13,632 - 15,221 U.K. pounds. To apply for either post, send curriculum vita and the names and addresses of two professional referees to the address below. Closing Date: 14th of May. ------------------------------------------------------------------------- Jonathan Shapiro Computer Science Dept University of Manchester Oxford Road Manchester M13 9PL United Kingdom. Phone: 44-(0)61 275 6253 Fax: 44-(0)61 275 6236 E-mail: jls at cs.man.ac.uk From DUDZIAK at vms.cis.pitt.edu Fri Apr 30 00:39:00 1993 From: DUDZIAK at vms.cis.pitt.edu (MARTIN DUDZIAK) Date: Thu, 29 Apr 1993 23:39 EST Subject: Announcement Message-ID: <01GXLO0HM58SAIF6JQ@vms.cis.pitt.edu> ANNOUNCEMENT Richmond VA Area SIG on NNs and NLDs Forming An informal special interest group on neural and non-linear dynamical systems is forming, oriented to people in the Richmond and east/central Virginia area. There is currently no organizational affiliation and what directions this group takes depends upon the response and participation of interested persons. The intent here is to bring together people who may otherwise be somewhat isolated by virtue of working in diverse industries or centers, academic or corporate, and who could benefit by reason of verbal and electronic exchanges. My initial sense is that there is more going on in this part of the country and state than appears at first glance, and while Richmond may seem so close to Baltimore/Washington D.C. as a major technology arena, it really isn't. If you are interested, please contact me and we will see where this goes. One idea is to have a monthly seminar with an invited talk; convenient facilities can be easily provided. Martin Dudziak Crestar Bank (804) 782-5708 dudziak at vms.cis.pitt.edu From cabestan at eel.upc.es Fri Apr 30 17:20:12 1993 From: cabestan at eel.upc.es (Joan Cabestany) Date: Fri, 30 Apr 1993 17:20:12 UTC+0100 Subject: registration and conference program: IWANN'93 Message-ID: INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORK IWANN'93 FINAL PROGRAMME Sitges (Barcelona), Spain June 9 - 11, 1993 SPONSORED BY IFIP (Working Group in Neural Computer Systems, WG10.6) IEEE Neural Networks Council UK&RI communication chapter of IEEE Spanish Computer Society chapter of IEEE AEIA (IEEE Affiliate society) ORGANISED BY Universidad Politecnica de Catalunya Universidad Autonoma de Barcelona Universidad de Barcelona UNED (Madrid) IWANN'91 (International Workshop on Artificial Neural Networks) was held in Granada (Spain) in September 1991. People from over 10 countries attended the Workshop, and over 50 oral presentations were given. IWANN'93 is schedules for next June, 1993 in Sitges (Spain) with the following final program. WELCOME TO DELEGATES It is a pleasure to invite you to attend the second edition of INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORKS (IWANN'93) to be held in Sitges (Barcelona, Spain) from June 9 to June 11, 1993, following the first edition done in Granada (Spain) during September, 1991. IWANN's main objective is to offer a forum for achieving a global, informative and advanced prespective on Artificial Neural Networks. In addition to conventional Neural Networks aspects, IWANN'93 will also be concerned with complementary topics such as neural computation theory and methodology, local computation models, organization and structures resembling biological systems. The actual Workshop will consist of 111 papers arranged into technical sessions addressing the topics of Learning, Models, Biological perspectives, Hardware implementations, Self-Organizing networks and Organizational principles, Artificial vision, Control, Communications, Software, Signal processing and Applications. A total of six Invited Conferences will open their respective sessions to be held in Room A, and their objective is to focus the State-of-the-Art, and motivate discussion and participation. The Workshop is organized in cooperation with the Spanish RIG of the IEEE Neural Networks Society, and the IFIP WG 10.6, and, is sponsored by the spanish "Comisin Interministerial de Ciencia y Tecnologa" (CICYT), the catalan "Comissi Interdepartamental per a la Recerca i Tecnologia" (CIRIT), and the organizing Universities. Welcome to the Workshop. We hope that IWANN'93 will be scientifically very rewarding and a good oportunity to get to know our country. Enjoy Sitges and Barcelona, one of the most dynamic towns in Europe, and meet people working in different topics of Neural Networks field. The IWANN'93 Committees look forward to seeing you there. Prof. Albert Prieto General Chaiman, IWANN'93 COMMITTEE OF HONOUR Chairman Molt Honorable Sr. Jordi Pujol i Soley President of the Catalan Government Excm. Sr. Jordi Serra i Villalb Mayor of Sitges Honorable Sr. Antoni Subir i Claus Minister of Industry and Energy Sr. Josep Laporte i Sala President of the CIRIT Sr. Alberto Prieto President of IWANN'93 Congress ORGANIZING COMMITTEE Chairman Jos Mira UNED. Madrid (E) Senn Barro Univ. de Santiago (E) Joan Cabestany Univ. Pltca. de Catalua (E) Trevor Clarkson King's College London (UK) Ana Delgado UNED. Madrid (E) Federico Morn Univ. Complutense. Madrid (E) Conrad Prez Univ. Autnoma de Catalua (E) Francisco Sandoval Univ. de Mlaga (E) Elena Valderrama CNM- Univ. Autnoma de Barcelona (E) LOCAL COMMITTEE Chairman Joan Cabestany Univ. Pltca. de Catalua (E) Jordi Carrabina CNM-Univ. Autnoma de Barcelona (E) Francisco Castillo Univ. Pltca. de Catalua (E) Andreu Catal Univ. Pltca. de Catalua (E) Gabriela Cembrano Inst. de Ciberntica. CSIC. Barcelona (E) Conrad Prez Univ. de Barcelona (E) Elena Valderrama CNM-UNIv. Autnoma de Barcelona (E) PROGRAMME COMMITTEE Chairman Jos Mira UNED. Madrid (E) Sanjeev B. Ahuja Nielsen A.I.Research & Development. Bannokburn (USA) Igor Aleksander Imperial College. London (UK) Lus B. Almeida INESC. Lisboa (P) Shun-ichi Amari Faculty of Engineering. Univ. Tokyo (Jp) Xavier Arreguit CSEM SA (CH) Franois Blayo LERI-EERIE. Nimes (F) Colin Campbell University of Bristol. (UK) Leon Chua Univ. of California. Berkeley (USA) Trevor Clarkson King's College London (UK) Michael Cosnard Ecole Normale Superieure de Lyon (F) Marie Cottrell Univ. Paris I (F) Dante Del Corso Politecnico di Torino (I) Gerard Dreyfus ESPCI. Paris (F) F.K. Fogelman-Soulie Mimetics. Chatenay Malabry (F) J. Simoes da Fonseca Univ. de Lisboa (P) Kunihiko Fukushima Faculty of Engineering Science. Osaka University (Jp) Karl Goser Univ. Dortmund (D) Hans Peter Graf AT&T Bell Lab., New Jersey (USA) Francesco Gregoretti Politecnico di Torino (I) Karl E. Grosspietsch Mathematik und Datenverarbeitung (GMD). St. Agustin (D) Mohamad H. Hassoun Wayne State University (USA) Jeanny Herault INPG Grenoble (F) Jaap Hoekstra Delft University of Technology (NL) P.T.W. Hudson Faculteit der Sociale Wetenschappen. Leiden University (NL) Jos Lus Huertas CNM- Universidad de Sevilla (E) Paul G.A. Jespers Universit Catholique de Louvain (B) Simon Jones IERI Loughborough Univ. of Technology (UK) Christian Jutten INPG Grenoble (F) H. Klar Inst. fr Mikroelektronik. Technische Universitt Berlin (D) Michael D. Lemmon Univ. of Notre Dame. Notre Dame (USA) Panos A. Ligomenides Univ. of Maryland (USA) Javier Lpez Aligu Univ. de Extremadura (E) Robert J. Marks II Univ. of Washington (USA) Anthony N. Michel Univ. of Notre Dame. Notre Dame (USA) Roberto Moreno Univ. Las Palmas de Gran Canaria (E) Josef A. Nossek Inst. of Network Theory and Circuit Design. Tech. Univ. of Munich (D) Francisco J. Pelayo Univ. de Granada (E) Franz Pichler Johannes Kepler Univ. (A) Ulrich Ramacher Siemens AG. Munich (D) Tmas Roska Comp. & Aut. Res. Inst. Hungarian Academy of Science. Budapest (H) Leonardo Reyneri Univ. di Pisa (I) Peter A. Rounce Dept. Computer Science. Univ. College London (UK) V.B. David Snchez German Aerospace Research Establishment. Wessling (G) E. Snchez-Sinencio Texas A&M University (USA) David Sherrington Dept. of Physics. Univ. of Oxford (UK) Renato Stefanelli Politecnico di Milano (I) T.J. Stonham Brunel-University of West London (UK) John G. Taylor Centre for Neural Networks. King's College London (UK) Carme Torras Inst. de Ciberntica. CSCI. Barcelona (E) Philip Treleaven Dept. Computer Science. Univ. College London (UK) Marley Vellasco Ponti. Univ. Catlica. Rio de Janeiro (BR) Michel Verleysen Univ. Catholique de Louvain (B) Michel Weinfeld Ecole Polytechnique Paris (F) WEDNESDAY, 9TH . JUNE 09:00 Hr. ROOM A Mathematical topics on Neural Learning. Prof S. Amari and Prof.N. Murata University of Tokyo. Moderator: E. Valderrama. Spain. 10:00 Hr. ROOM A Learning - I Chairman: Prof.S. Amari. Japan. * Self-organizing Grammar Induction using a Neural Network Model. C. Mannes. Boston University.(USA) * The role of forgetting in learning Strategies for Self-organizing Discriminator-based Systems. G. Tambouratzis and T.J. Stonham Brunel University.(UK) * Simulation of Stochastic Regular Grammars through simple recurrent Networks. M.A. Castao, E. Vidal and F. Casacuberta. Univ. Politcnica de Valencia.(E) * Local Stochastic Competition and Vector Quantization. M. Graa, A. D'Anjou, F.X. Albizuri, F.J. Torrealdea, M.C. Hernndez. CCIA Univ. del Pas Vasco.(E) ROOM B Signal processing - I Chairman:Prof.M.A.Lagunas. Spain. * Projectivity invariant Pattern Recognition with high-order Neural Networks. G. Joya and F. Sandoval. Universidad de Mlaga.(E) * Rejection of incorrect answer from a Neural net classifier. F.J. Smieja German National Research Centre for Computer Science (GMD) (D) * Nonlinear Time series modeling by Competitive Segmentation of State Space. C.J. Pantalen and A.R. Figueiras. Univ. Cantabria. UPM, Cdad. Univ.(E) * Identification and Prediction of Non-linear models with recurrant Neural Network. O. Adam, J.L. Zarader and M. Milgram Lab. Robotique de Paris(FR) ROOM C Biological Perspectives - I Chairman: Prof. J. Hoekstra. The Netherlands. * Integrated Learning in Rana Computatrix. F.J. Corbacho and M.A. Arbib. University of Southern California.(USA) * A model for visual stimuli centering through adaptive value learning. A. Murciano, J. Zamora and M. Reviriego. Univ. Complutense de Madrid.(E) * A model for the development of neurons selective to visual stimulus size. M.A. Andrade and F. Morn. Univ. Complutense de Madrid. 11:20 Hr. COFFEE BREAK 11:50 Hr. ROOM A Organizational Principles - I Chairman: Prof. M. Verleysen. Belgium. * Optimized learning for improving the evolution of piecewise linear separation incremental algorithms. J.M. Moreno, F. Castillo and J. Cabestany. Univ. Politcnica de Catalunya.(E) * A Method of Pruning Layered Feed-forward Neural Networks. M. Pelillo and A.M. Fanelli. Universit di Bari.(I) * MLP Modular versus YPREL Classifiers. Y. Lecourtier , B. Dorizzi 1, P. Sebire 1, and A. Ennaji. Univ. de Rouen, (1) Inst. Nac. des Tlcommunications.(FR) * Test of different regularization terms in small Networks. J.L. Crespo and E. Mora. Univ. de Cantabria.(E) * How many hidden neurons are needed to recognize a symmetrical pattern?. J. Patinel 1, G. Leone 2, and M. Maurice 3. (1) Lab. d'Intelligence Artificielle, (2) Lab. de Physiologie Neurosens., (3) Lab. de Robotique de Paris.(FR) ROOM B Communication Systems Chairman: Prof. T. Clarkson. United Kigdom. * Hopfield Neural Network for Routing. S. Cavalieri, A. Di Stefano and O. Mirabella. Universita' di Catania.(I) * Neural network Routing Controller for Communication parallel Multistage Interconnection Networks. A. Garca, A. Daz, F. Garca and F. Sandoval. Universidad de Mlaga.(E) * Adaptive Routing using Cellular Automata. J. Minot Lab. d'Electronique Philips.(FR) * Optimal blind Equalization of Gaussian channels. J. Cid 1, L. Weruaga and A.R. Figueiras. (1) Univ. de Valladolid. Univ. Politcnica de Madrid.(E) ROOM C Theoretical Models - I Chairman: Prof. F. Morn. Spain. * A Node Splitting Algorithm that reduces the number of connections in a hamming distance classifying Network. H. Hning. Aachen Univ. of Technology.(D) * A high order Neural Model. F.J. Lpez, M.I. Acevedo and M. Jaramillo. Univ. de Extremadura.(E) * Higher-order Networks for the optimization of Block Designs. P. Bofill and C. Torras. Univ. Politcnica de Catalunya.(E) * Region of influence (ROI) Networks. Model and Implementation. F. Castillo 1, J. Cabestany and J.M. Moreno. (1) E.U.P. E.T.S.E. Telecomunicacin.(E) 13:00 Hr. LUNCH 15:00 Hr. Hybrid Programming Environments: integrating neural networks, genetic algorithms and rule- based systems. Prof.P.C. Treleaven and P.V. Rocha. University College London. Moderator: Prof. A. Prieto. Spain. 16:00 Hr. ROOM A Software - I Chairman: Prof. P. Treleaven. United Kingdom. * Automatic Generation of C++ Code for Neural Network Simulation. S. Dreiseitl and D. Wang. Johannes Kepler University.(A) * Urano: an Object-oriented Artificial neural Network Simulation Tool. L. Fuentes, J.F. Aldana and J.M. Troya. Universidad de Mlaga.(E) * Realistic Simulation Tool for early visual Processing including Space, Time and Colour Data. W. Beaudot, P. Palagi and J. Hrault. Inst. National Polytechnique de Grenoble.(FR) ROOM B Hardware - I Chairman: Prof. K. Goser. Germany. * A Neural Network Chip using CPWM Modulation. M. Chiaberge, D. del Corso, F. Gregoretti and L.M. Reyneri. Politecnico di Torino.(I) * Hardware implementation of a Neural Network for High Energy Physics application. J. Carrabina, F. Lisa, V. Gaitan, L. Garrido and E. Valderrama. Univ. Autnoma de Barcelona.(E) * An array processor Architecture for Neural Networks. J. Ortega, F.J. Pelayo, A. Prieto, B. Pino and C.G. Puntonet. Univ. de Granada.(E) * Limitation of connectionism in MLP. C.V. Regueiro, S. Barro and A. Yez 1. Univ. de Santiago de Compostela.(1) Univ. de La Corua.(E) ROOM C Cognitive Science Chairman: Prof. S. Barro. Spain. * A Neural state machine for iconic language representation. I. Aleksander 1 and H. Morton 2. (1) Imperial College, London. (2) Brunel University.(UK) * Variable binding using serial order in recurrent Neural Networks. J. Lpez and J. Sopena. Univ. de Barcelona.(E) * Planlite: Adaptive planning using weightless systems. J. Mrsic. Imperial College, London.(UK) * An adaptive information retrieval system based on Neural Networks. F. Crestani. Univ. di Padova.(I) 17:20 Hr. COFFEE BREAK 17:50 Hr. ROOM A Organizational Principles - II Chairman: Prof. M. Cottrell. France. * Comparative Study of Self-organizing Neural Networks. C. Wann and S. Thomopoulos. The Pennsylvania State Univ.(USA) * GANNet: A Genetic Algorithm for optimizing Topology and weight in Neural Network design. D.W. White and P.A. Ligomenides. Univ. of Maryland.(USA) * Full automatic ann design: A Genetic approach. E. Alba, J.F. Aldana and J.M. Troya. Univ. de Mlaga.(E) ROOM B Software - II Chairman: Prof. J. Lpez. Spain. * Language supported Storage and Reuse of persistent Neural Network Objects. C. Burdorf. Univ. of Bath.(UK) * Flexible operating environment for Matrix Based Neurocomputers. J.C. Taylor, M.L. Recce and A.S. Mangat. Univ. College London.(UK) * A parallel Implementation of Kohonen's self-organizing Maps on the Smart Neurocomputer. E. Filippi 1, and J.C. Lawson 2. (1) Politecnico di Torino.(I) (2) INPG, Labo TIRF, Grenoble.(FR) ROOM C Theoretical Models - II Chairman: Prof. F. Castillo. Spain. * Neural bayesian Classifier. C. Jutten. INPG, Labo TIRF, Grenoble. P. Comon.(FR) * Constructive Methods for a new Classifier based on a Radial-Basis-Function Neural Network accelerated by a tree. P. Gentric and H. Withagen. Lab. d'Electronique Philips.(FR * Practical realization of a Radial Basis Function Network for handwritten digit recognition. B. Lemari. La Poste, Nantes.(FR) * Design of Fully and Partially connected Random Neural Networks fos Pattern Completion. C. Hubert. Univ. Ren Descartes.(FR) THURSDAY, 10TH. JUNE 09:00 Hr. ROOM A The Kolmogorov Signal processor. Prof. M.A. Lagunas, A. Prez, M. Najar, A. Pags. UPC TSC Department. Spain Moderator: Prof. C. Jutten. France. 10:00 Hr. ROOM A Signal Processing - II Chairman: Prof. C. Jutten. France. * Use of Unsupervised Neural Networks for classification of Blood Pressure Time Series. M.J. Rodrguez, F. del Pozo and M.T. Arredondo. Univ. Politcnica de Madrid.(E) * Aplication of Artificial Neural Networks to chest Image classification. J.J. Fernndez, A. Caas, E. Roca, F.J. Pelayo, J. Fernndez and A. Prieto. Univ. de Granada.(E) * Software Pattern EEG Recognition after a Wavelet transform by a Neural Network. P. Clochon, D. Clarencon, R. Caterini and V. Roman. INSERM.(FR) * Combination of Self-organizing Maps and Multilayer Perceptrons for Speaker Independent Isolated Word Recognition.J. Tuya, E. Arias, L. Snchez and J.A. Corrales. Univ. de Oviedo.(E) ROOM B Learning - II Chairman: Prof. F. Blayo. France. * MHC - An Evolutive Connectionist Model for Hybrid Training. J.M. Ramrez. Paradigma.(VEN) * Fast Convergenced Learning Algorithms for Multi-level and Binary Neurons and Solving of some Image Processing problems. N.N. Aizenberg, and I.N. Aizenberg 1. Univ. of Uzhgorod. (1) Joint Venture PGD.(UKR) * Invariant Object Recognition using Fahlman and Lebiere's Learning Algorithm. K. Ito, M. Hamamoto, J. Kamruzzaman and Y. Kumagai. Muroran Inst. of Technology.(JP) * Realization of Surjective Correspondence in Artificial Neural Network trained by Fahlman and Lebiere's Learning Algorithm. M. Hamamoto, K. Ito, J. Kamruzzaman and Y. Kumagai. Muroran Inst. of Technology.(JP) ROOM C Biological Perspectives - II Chairman: Prof. J. Mira. Spain. * An invariant Representation Mechanism after Presynaptic Inhibition. R. Moreno and O. Bolvar. Univ. de Las Palmas de Gran Canaria.(E) * The Pancreatic B-Cell as a Voltage-Controlles Oscillator. J.V. Snchez and B. Soria. Univ. de Alicante.(E) * Apprximation of the Solution of the Dendritic Cable Equation by a small series of Coupled Differential Equations. J. Hoekstra. Delft Univ. of Technology.(NL) * A Neural Network Model inspired in global appreciations about the Thalamic Reticular Nucleus and Cerebral Cortex Connectivity. J. Ropero. ICAI.(E) 11:20 Hr. COFFEE BREAK 11:50 Hr. ROOM A Applications - I Chairman: Prof. A. Prieto. Spain. * Noise Prediction in Urban Traffic by a Neural Approach. G.Cammarata, S. Cavalieri, A. Fichera and L. Marletta. Univ. di Catania.(I) * An industrial application of Neural Networks to Natural Textures classification. G. Yahiaoui and B. Borocco 2. cole Spciale de Mcanique et d'Electricit. (2) PSA Peugeot Citron.(FR) * Stock Prices and Volume in an Artificial adaptive Stock Market. S. Margarita and A. Beltratti. Univ. di Torino.(I) * Application of the Fuzzy Artmap Neural Network Architecture to Bank Failure Predictions. L.J. de Miguel, E. Revilla, J.M. Rodrguez and J.M. Cano. Univ. de Valladolid.(E) ROOM B Vector Quantizers Chairman: Prof. C. Prez. Spain. * Vector Quantization and Projection Neural Network. P. Demartines and J. Hrault. INPG, Labo. TIRF Grenoble.(FR) * Constructive Design of LVQ and DSM Classifiers. J.C. Prez and E. Vidal. Univ. Politcnica de Valencia.(E) * Linear Vector classification: an improvement on LVQ Algorithms to create classes of Patterns. M. Verleysen, P. Thissen and J.D. Legat. Univ. Catholique de Louvain.(B) * Non-Greedy adaptive Vector Quantizers. Z. Wang. Univ. of Waterloo.(CAN) ROOM C Theoretical Models - III Chairman: Prof. A. Catal. Spain. * Representation and Recognition of Regular Grammars by Means of Second-order recurrent Neural Networks. R. Alquzar and A. Sanfeliu. Inst. de Ciberntica (UPC-CSIC).(E) * Connectionist Models for Syllabic Recognition in the Time Domain. J. Santos and R.P. Otero. Univ. da Corua.(E) * Sparsely Interconnected Artificial Neural Networks for Associative Memories. D. Liu and A.N. Michel. Univ. of Notre Dame.(USA) * Dynamic Analysis of Networks of Neural Oscillators. A. Arenas and C.J. Prez. Univ. de Barcelona.(E) * Adaptive Models in Neural Networks. P.A. Ligomenides. Univ. of Maryland.(USA) 13:00 Hr. LUNCH 15:00 Hr. ROOM A Hardware Implementations of Artificial Neural Networks. Prof.D.Del Corso. Politecnico di Torino. Moderator: Prof. J. Cabestany. Spain. 16:00 Hr. ROOM A Hardware - II Chairman: Prof. D. Del Corso. Italy. * High Level Synthesis of Neural Network Chips. M.E. Nigri and P. Treleaven. Univ. College London.(UK) * Neural Network Simulations on massively parallel Computers: Applications in Chemical Physics. B.G. Sumpter, R.E. Guenther 1, C.Halloy 2, C. Getino and D.W. Noid. Oak Ride National Lab. (1) Univ. of Nebraska at Ohama. (2) Univ. of Tennessee.(USA) * A model based Approach to the Performance Analysis of Multi-Layer Networks realised in Linear Systolic Arrays. D. Naylor and S. Jones. Loughborough Univ. of Technology.(UK) * The temporal Noisy-Leaky Integrator Neuron with additional Inhibitory Inputs. G. Bugmann, C. Christodoulou, T.G. Clarkson and J.G. Taylor. King's College London.(UK) ROOM B Control & Robotics - I Chairman: Prof. C. Torras. Spain. * Neural Networks as Direct Adaptive Controllers. M. Bahrami. Univ. of New South Wales.(AUS) * A Neural Adaptive Controller for a Turbofan Exhaust Nozzle. C. Barret, M. Houkari, P. Meyne, J.M. Martnez 1, A. Garassino 2, and P. Tormo 2. Univ. Evry Val d'Essonne. (1) Commissariat l'Energie Atomique. (2) SNECMA Villaroche.(FR) * Feed-Forward Neural Networks for Bioreactor Control. A. Bulsari, B. Saxn and H. Saxn. bo Akademi.(FIN) ROOM C Artificial Vision - I Chairman: Prof. J. Herault. France. * A Connectionist Approach to the Correspondence Problem in Computer Vision. H. Sako and H.I. Avi-Itzhak 1. Hitachi Dublin Lab. (1) Stanford Univ.(IRE) * Self-Organizing Feature Maps for Image Segmentation. R. Natowicz and R. Sokol 1. E.S.I.E.E.. (1) Univ. de Paris.(FR) * Recognition of Fractal Images using a Network. B. Freisleben, J.H. Greve and J. Lber. Univ. of Darmstadt.(D) * Feed-Forward Network for Vehicle License Character Recognition. F. Lisa, J. Carrabina, C. Prez, N. Avellana and E. Valderrama. Univ. Autnoma de Barcelona.(E) END OF SESSIONS FRIDAY, 11TH. JUNE 09:00 Hr. ROOM A Biophysics of Neural Computation. Prof. K.N. Leibovic. Univ. of New York at Buffalo.USA Moderator: Prof. J. Mira. Spain. 10:00 Hr. ROOM A Biological Perspectives - III Chairman: Prof. K.N. Leibovic. U.S.A. * Towards more realistic Self Contained Models of Neurons: High-Order, Recurrence and Local Learning. J. Mira, A.E. Delgado, J.R. Alvarez, A.P. de Madrid and M. Santos. UNED.(E) * McCulloch's Neurons Revisited. R.J. Scott. Univ. of Maryland Baltimore County.(USA) * Biologically Motivated Approach to Face Recognition. N. Petkov, P. Kruizinga and T. Lourens.(NL) Rijksuniversiteit Groningen. * Learning by Reinforcement: a Psychobiological Model. F.J. Vico, F. Sandobal and J. Almaraz. Univ. de Mlaga.(E) ROOM B Learning - III Chairman: Prof. P. Ligomenides. U.S.A. * Bimodal Distribution Removal. P. Slade and T.D. Gedeon. Univ. of New South Wales.(AUS) * A simplified Artmap Architecture for Real-Time Learning. A. Guazzelli, D. Barone and E.C. de B. Carvalho Filho 1. Univ. Fed. do Rio Grande do Sul. (1) Univ. Fed. de Pernambuco.(BR) * B-Learning: a Reinforcement Learning Algorithm, Comparison with Dynamic Programming. T. Langlois and S. Canu. Lyonese des Eaux Dumez. Univ. de Technology de Compigne.(FR) * Increased Complexity Training. I. Cloete and J. Ludik. Univ. of Stellenbosch.(SA) ROOM C Artificial Vision - II Chairman: Prof. F. Sandoval. Spain. * Interpretation of Optical Flow through complex Neural Network. M. Miyauchi, M. Seki, A. Watanabe and A. Miyauchi. SANNO College, Musashi Inst. of Technology.(JP) * CT Image Segmentation by Self-Organizing Learning. D. Cabello, M.G. Penedo, S. Barro, J.M. Pardo and J. Heras. Univ. de Santiago de Compostela.(E) * Texture Image Segmentation using a modified Hopfield Network. A. Mosquera, D. Cabello, M.J. Carreira and M.G. Penedo. Univ. de Santiago de Compostela.(E) * Image Compression with Self-Organizing Networks. B. Freisleben and M. Mengel. Univ. of Darmstadt.(D) 11:20 Hr. COFFEE BREAK 11:50 Hr. ROOM A Applications - II Chairman: Prof. G. Cembrano. Spain. * Use of a Layered Neural Nets as a Display Method for N-Dimensional Distributions. L. Garrido 1-2, V. Gaitan 2, M. Serra 3 and X. Calbet 3. (E) (1) Univ. de Barcelona. (2) Univ. Autnoma de Barcelona. (3) Inst. de Astrofsica de Canarias. * Simulation of Neural Networks in a Distributed Computing Environment using NeuroGraph. P. Wilke. Univ. Erlangen-Nuernberg.(D) * Combination of Neural Network and Statistical Methods for Sensory Evaluation of Biological Products: on-line Beaty Selection of Flowers. F. Ros, A. Brons, f. Sevila, G. Rabatel and C. Touzet (1). CEMAGREF. (1) LERI-ERIEE.(FR) ROOM B Self-Organizing Networks Chairman: Prof. E. Valderrama. Spain. * On the Distribution of Feature Space in Self-Organizing Mapping and Convergence Accelerating by a Kalman Algorithm. H. Yin and N.M. Allinson. Univ. of York.(UK) * A learning Algorithm to Obtain Self-Organizing Maps using Fixed Neighbourhood Kohonen Networks. P. Martin, F.J. Pelayo, A. Daz, J. Ortega and A. Prieto. Univ. de Granada.(E) * Analysing a Contingency Table with Kohonen Maps: a Factorial Correspondence Analysis. M. Cottrell, P. Letremy and E. Roy. Univ. de Paris.(FR) * Dynamics of Self-Organized Feature Mapping. R. Der, T. Willmann. Univ. Leipzig.(D) ROOM C Theoretical Models - IV Chairman: F. Pelayo. Spain. * Optimised Attractor Neural Networks with External Inputs. A.N. Burkitt. Australian National Univ.(AUS) * Non-Orthogonal Bases and Metric Tensors: some Applications to Biology and Artificial Neural Networks. K. Weigl and M. Berthod. INRIA.(FR) * Genetic Synthesis of Discrete-Time Recurrent Neural Network. F.J. Marn and F. Sandoval. Univ. de Mlaga.(E) * Optimization of a Competitive Learning Neural Network by Genetic Algorithms. J.J. Merelo, M. Patn, A. Caas, A. Prieto and F. Morn 1. Univ. de Granada. (1) Univ. Complutense de Madrid.(E) 13:00 Hr. LUNCH 15:00 Hr. ROOM A Networks for Estimation, Control and Robotics. Prof. J.J.E. Slotine, RM Sanner MIT (USA) Moderator: Prof. C. Torras. Spain. 16:00 Hr. ROOM A Control & Robotics - II Chairman: Prof.J.J.E.Slotine. U.S.A. * Learning Networks for Process Identification and Associative Action. L. Borland and H. Haken. Univ. of Stuttgart.(D) * On-line Performance Enhancement of a Behavioral Neural Network Controller. J.R. Pimentel, D. Gachet, L. Moreno and M.A. Salichs. Univ. Politcnica de Madrid.(E) * An Architecture for Implementing Control and Signal Processing Neural Networks. R.P. Palmer and P.A. Rounce. Univ. College London.(UK) ROOM B Hardware - III Chairman: Prof. S. Jones. United Kingdom. * Architectures for Self-Learning Neural Network Modules. T.G. Clarkson and C.K. Ng. King's College London.(UK) * The Generic Neuron Architectural Framework for the Automatic Generation of ASICs. M.M.B.R. Vellasco and P.C. Treleaven 1. Pontificia Univ. Catlica do Rio de Janeiro.(BR) (1) Univ. College London.(UK) * A Risc Architecture to Support Neural Net Simulation. M. Pacheco and P.C. Treleaven 1. Pontificia Univ. Catlica do Rio de Janeiro.(BR). (1) Univ. College London.(UK) * Hardware Design for Self-Organizing Feature Maps with Binary Input Vestors. S. Rping, U. Rckert and K. Goser. Univ. of Dortmund.(D) ACCOMPANYING PERSONS PROGRAMME Tuesday, 8th. June 20:00 Hrs. Welcome Reception at "Maricel" Palace. Wednesday, 9th. June 09:30 Hrs. HISTORICAL AND ARTISTIC CITY TOUR OF BARCELONA. Including: The Gothic Quarter, the 14th Century Gothic Cathedral, the "Paseo de Gracia" where the most important Modernist buildings are placed, the Sagrada Familia, etc. Thursday, 10th. June 09:30 SITGES CITY TOUR AND MUSEUMS. Sitges is a summer and international tourism resort. The white washed houses, the seaside boulevard and the church on the sea create a beautiful and pleasant ensemble. Artists, such as Rusiol or Utrillo, already discovered its charm at the end of the XIXth century. The Cau Ferrat Museum and the Maricel Museum, display beautiful samples of the Catalan modern art. 21:00 Gala Dinner at Great Casino of Sitges. GENERAL INFORMATION CONGRESS VENUE The IWANN'93 Congress will be held in Sitges, a city located 35 Km. south of Barcelona. All sessions will take place at GRAN SITGES HOTEL: Gran Sitges Hotel Port d'Aiguadol 08870 Sitges (Barcelona) Spain TRANSPORTATION TO SITGES By air: The Barcelona-El Prat International Airport is linked to Barcelona by rail (Barcelona Sants Station) every 30 minutes, by bus (Aerobus) every 15 minutes, and by taxi. Sitges is also linked to the airport by rail, changing train in El Prat Station or through Barcelona Sants Station. By Rail: Internationals direct lines to Barcelona (Francia and Sants) Stations come from Geneva and Bern (Switzerland), Paris (France) and Milan (Italy). There are also many trains from Madrid, some of them overnight. Sitges is linked to Barcelona Sants Station by local trains every 15-30 minutes. By Road: Motorway A-17/7 from La Jonquera (at the French border) links up with the French motorway network; and thence, Great Britain and all northern and eastern countries. Motorway A-7 to the west and south connects Barcelona with the rest of Spain. Sitges is linked to Barcelona city and Airport by Motorway A-16 and country road C-246. HOTEL RESERVATIONS A number of rooms in different prices and categories have been booked in Sitges for the Congress attendants. Reservations made through the General Secretariat by registration form have a special price in all Hotels. Payment of a deposit per room will be necessary to confirm any hotel reservation. This amount will be deducted from your hotel invoice. See official list and map of the city attached in the back cover of this programme. Please consult special rates for consolidated groups (minimum 20 persons). OFFICIAL LANGUAGES AND SIMULTANEOUS TRANSLATION English will be the official language of IWANN'93. Simulaneous translation will not be provided. DOCUMENTATION AND INFORMATION Congress documents, personal budgets, and tickets will be handed over to attendants and accompanying persons at the Congres Secretariat from Tuesday 8th June to Friday 11th June. The Secretariat will be open every day from the begining to the end of the work sessions. REGISTRATION Registration and payment of fees will be absolutely necessary so as to attend the Workshop sessions and social events. On site registration is discouraged in order to avoid queueing. Registration Fees include: Attendants Accompanying Persons - Welcome reception - Welcome reception - Proccedings - Barcelona City Tour - Attendance to all Scientific Meetings - Sitges City Tour and Museums - Coffee Breaks - Gala Dinner - Gala Dinner Basic Inscription Economy Inscription - Proccedings - Attendance to all Scientific Meetings - Attendance to all Scientific Meetings - Coffee Breaks - Coffee Breaks SOCIAL EVENTS Tuesday 8th June 20:00 Hrs. Welcome Reception at "Maricel" Palace, the historical and cultural centre of Sitges which is overlooking the sea. This Palace, at present a museum, is a sample of the Catalan modern art ("Modernism"). Thursday 10th June 21:00 Hrs. Gala Dinner at Great Casino of Sitges located in Sant Pere de Ribes, 5Km. far from Sitges. This construction was built at the end of 19th. century in Catalan- Renaissance style. It's spacious halls are beautifully decorated and the access to the Casino is a long boulevard with cypresses and period street lamps. An unforgettable setting!.Free entrance to the Casino after the dinner showing the passport or D.N.I. OPTIONAL TOURS Optional Tours and Excursions will be organized on Saturday and Sunday for the attendants wishing to extend their stay after the Workshop. Caves and Montserrat (full day) Price : 7.500.- Ptas (Minimum 30 persons) We will visit a famous Caves of Sant Sadurn d'Anoia (placed on the most important wine- producing region of Catalonia). Lunch. Montserrat is a unique mountain located at a height of 1.235 mts.. In the Royal basilica is placed the famous Black Virgin. We will listen to the "Escolanets", the oldest child chorus in Europe. Modernism in Barcelona (half day) Price : 3.500.- Ptas (Minimum 30 persons) During this tour you can see the most important modernist works of Barcelona. Some houses located at the Paseo de Gracia, built with the particular imagination of the architects, painters and sculptors of the beginning of this century; the Holy Family Church, the still unfinished masterpiece of striking originality, begun in 1884 by A. Gaudi; the Gell Park, initially created as a Garden City and today a public park. Girona and Dal Museum (full day) Price : 8.000.- Ptas (Minimum 30 persons) Founded in ancient times, Girona preserves numerous vestiges of its Roman, Christian, Arab and Frankish past. From the 12th century to the present, it has witnessed the Catalonian War of Secession; the war against Louis XIV; the siege mounted by Philip V, and the defense against Napoleonic forces. The inner city is one of the most beautiful and best preserved in Spain. It consists of a number of steep, narrow streets, sometimes porticoed, that converge onto flights of stairs leading to different street levels and up to the Cathedral. Lunch. At Figueres, capital of Ampurdan region, we will visit the famous Dali Theater-Museum, the most visited one in Spain, after the Prado. Many works of this recently died genious artist are displayed in an original way. CANCELLATION OF REGISTRATION Notification of cancellation must be sent in writing to ULTRAMAR CONGRESS and will be accepted until April 30th., 1993 with refund of fees except a cancellation charge of 25%. No refunds can be made for cancellation received after April 30th., 1993. Refunds will be dealt with after the Congress. GENERAL SECRETARIAT For any matters related to correspondance, registration forms, payment of fees, hotel reservation, deposit, etc., please contact: ULTRAMAR CONGRESS Diputaci, 238 3 08007 Barcelona Tel. (34-3) 317.37.00 - Fax. (34-3) 412.03.19 __________________________________________________________________________________________________ REGISTRATION FORM **************************************************************************** IWANN'93 INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORKS SITGES (BARCELONA) Spain June 9-11, 1993 Name:______________________________________________________________________ Accompanying person:_______________________________________________________ Address:_______________________________ Tel:______________Fax:_____________ Z.C. __________ City ____________________ Country__________________________ Institution or Centre _____________________________________________________ REGISTRATION FEES Before April 31 After April 31 Full Inscription 60.000 ptas 70.000 ptas _______________ Basic Inscription (*) 40.000 ptas 50.000 ptas _______________ Economy Inscription (**) 30.000 ptas 35.000 ptas _______________ Accompanying Person Fees 40.000 ptas 50.000 ptas. _______________ (*) Only for students with accreditation and delegates from America (except USA and Canada), and East European Countries. (**)Without proceedings.Only for students. On site registration is discouraged. HOTEL RESERVATION Special Hotel rates per night (Breakfast included) Twin Room Single use room tax [] Gran Sitges Hotel **** 15,750 ptas 12,600 ptas 6% [] San Sebastian Htl **** 12,500 ptas 9,500 ptas 6% [] Sitges Park Hotel *** 8,000 ptas 6,500 ptas 6% [] Subur Hotel *** 8,300 ptas 6,200 ptas 6% [] Hotel Don Pancho ** 5,500 ptas 4,400 ptas 6% Please reserve ________ room(s) [] Twin(s) [] Single(s) at Hotel ______________________________________ Date of arrival ________________ Date of departure ___________________ HOTEL RESERVATION DEPOSIT Following deposit per room will be necessary to confirm any Hotel reservation: Hotel****:20.000 ptas Hotel***: 15.000 ptas Hotel**:10.000 ptas. Attached Hotel Deposit :____________________ ptas x _______ rooms= ___________ TOTAL ATTACHED PAYMENT _______________ Payment of Registration Fees will be necessary to attend the Workshop sessions and social events. Registration Fees include: For Attendants For Accompanying persons - Welcome Reception - Welcome Reception. - Proceedings - Barcelona City Tour - Attendence to all - Museums of Sitges Tour Scientific Meetings - Official Dinner - Coffee Breaks - Official Dinner Basic Inscription Economy Inscription - Proceedings - Attendance to all Scientific - Attendance to all Meetings Scientific Meetings - Coffee Breaks - Coffee Breaks METHODS OF PAYMENT [] By bank draft in Pesetas, payable to ULTRAMAR CONGRESS on a Spanish Bank. [] By bank transfer to: BANCO CENTRAL (c/o ULTRAMAR CONGRESS) Branch No.20 Paseo de Gracia, 3 08007 Barcelona Acct. No. 13575-70 Please attach copy of Bank transfer to this form. Transfer fees to be paid by the sender. [] By VISA Credit Card No._____________________ Expiration date ______________ Name of Card Holder ________________________________________________________ Please send this REGISTRATION FORM, together with payment, to ULTRAMAR CONGRESS Diputacio, 238, tercer 08007 BARCELONA Spain Tel. (34-3) 317.37.00 Fax. (34-3) 412.03.19 Date: ____________________ Signature: _______________________________ THE WORKSHOP VENUE Sitges is located 35 Km. south of Barcelona. The city is well known for its beaches and its promenade facing the Mediterranean sea. Sitges is also knownfor its cultural events, and interesting Museums (Maricel, Santiago Rusinol...) IWANN'93 will be held at one of the most modern Convention Centres of Mediterranean Coast, The Gran Sitges Hotel, an unique complex in which business and leisure go hand in hand. Opened in 1991, its Congress and Conventions facilities include 13 Meeting Rooms equipped with all the necessary means. The Mediterranean Sea can be seen from every balcony of its 307 guest rooms. All of them are designed to offer maximum comfort (TV, mini-bar, air-conditio- ning and a wall safe). Sitges can be easily accesed by train (every 30 minutes), and it is wellcommunicated by highway. OPTIONAL TOURS Optional tours and excursions will be organized on Saturday and Sunday for the attendants wishing to extend their stay after the Workshop. From vera at uivt.cas.cs Fri Apr 30 10:48:15 1993 From: vera at uivt.cas.cs (Vera Kurkova) Date: Fri, 30 Apr 93 10:48:15 CET Subject: Announcing Prague Conference Neuronet'93 Message-ID: <38900.vera@uivt1.uivt.cas.cs> Neuronet'93 will be held in Prague, Czechia, September 20-26, 1993 One-page abstracts of papers on both theory and applications of neural networks should be send by May 30, 1993 to: Mirko Novak Institute of Computer Sciences Czech Academy of Sciences P.O.Box 5, 18207 Prague 8, Czechia More detailed information abour Neuronet'93 can be obtained by e-mail: cvs15 at cspgcs11.bitnet by phone: (+422) 821639 by fax: (+422) 8585789 From Dave_Touretzky at DST.BOLTZ.CS.CMU.EDU Thu Apr 1 20:56:03 1993 From: Dave_Touretzky at DST.BOLTZ.CS.CMU.EDU (Dave_Touretzky@DST.BOLTZ.CS.CMU.EDU) Date: Thu, 01 Apr 93 20:56:03 EST Subject: policy on posting talk announcements Message-ID: <17538.733715763@DST.BOLTZ.CS.CMU.EDU> A number of people have inquired recently about the propriety of posting local seminar announcements. Since CONNECTIONISTS is a world-wide mailing list, most readers will not be able to attend most talks. However, many folks find that a well-phrased talk abstract is a great way to learn about state-of-the-art work that hasn't yet made it into print. Reading talk abstracts is also a good way to keep track of what prominent people are working on these days. On the other hand, there are a lot of mundane neural net talks given every day. Some of these are introductory lectures, and thus not appropriate for readers of this list. Others describe preliminary research without significant results, or only incremental progress rather than really new ideas. Finally, some people may give decent talks but write boring abstracts. Here, then, is the policy on posting talk announcements to CONNECTIONISTS: 1. People are ENCOURAGED to post well-written abstracts describing exciting, state-of-the-art research. If possible, cite a paper or tech report so interested readers can follow up, or at least give the speaker's address so people can write for more information. 2. People are DISCOURAGED from posting abstracts that don't meet the above criteria. -- Dave Touretzky From UBTY003 at CCS.BBK.AC.UK Sat Apr 3 00:23:00 1993 From: UBTY003 at CCS.BBK.AC.UK (Martin Davies) Date: Sat, 3 Apr 93 0:23 BST Subject: European Society for Philosophy and Psychology Message-ID: ************************************************************************ ****** EUROPEAN SOCIETY FOR PHILOSOPHY AND PSYCHOLOGY ****** *********** SECOND ANNUAL MEETING *********** *****HANG SENG CENTRE FOR COGNITIVE STUDIES***** *****UNIVERSITY OF SHEFFIELD***** **** 3 - 6 JULY, 1993 **** The Second Annual Meeting of the European Society for Philosophy and Psychology will be held at the University of Sheffield, England, from the afternoon of Saturday 3 July to the morning of Tuesday 6 July, 1993. The meeting is sponsored by the Hang Seng Centre for Cognitive Studies, University of Sheffield. The goal of the Euro-SPP is: 'to promote interaction between philosophers and psychologists on issues of common concern'. ***** REGISTRATION ***** In order to register for the conference, you must fill out a Registration Form. Registration forms, along with information about accommodation and meals, can be obtained by writing to: Peter Carruthers, Hang Seng Centre for Cognitive Studies Department of Philosophy, University of Sheffield, Sheffield, S10 2TN UK or by sending email to: P.Carruthers at primea.sheffield.ac.uk THE REGISTRATION FEE (to include membership of the Euro-SPP) is 15 pounds sterling, or 10 pounds sterling for students. The cost of ACCOMMODATION AND MEALS (from dinner on Saturday to breakfast on Tuesday, including a visit to Chatsworth House - one of the great country houses of England - on Monday evening) is 120 pounds sterling. For those participants who do not require accommodation, the charge for MEALS is 70 pounds sterling. PAYMENT should be in *pounds sterling*, either by a cheque or draft drawn on a British bank or else by a EuroCheque. For all other methods of payment - whether foreign currency cheque, sterling cheque drawn on a non-UK bank, or electronic transfer - it will be necessary to make a surcharge of *seven pounds sterling* to cover clearance charges. Cheques must be made payable to *The University of Sheffield*. When registration is complete, you will be sent an information pack including maps and other touristic information along with a detailed programme. ************************************************************************ ***** PROVISIONAL PROGRAMME ***** SATURDAY 3 JULY Conference desk open from 12 noon 3.00 - 5.00 pm SYMPOSIUM 1: Body and Space 5.00 - 5.30 pm Tea 6.15 - 7.45pm INVITED LECTURE: Ruth Millikan 8.15 pm DINNER in Firth Hall, University of Sheffield SUNDAY 4 JULY 9.00 - 11.00 am SYMPOSIUM 2: Explanation by Intentional States 11.00 - 11.30 am Coffee 11.30 am - 1.00 pm SUBMITTED PAPERS 1.00 - 2.00 pm LUNCH 2.00 - 4.00 pm SYMPOSIUM 3: The Autonomy of Social Explanation 4.00 - 4.30 pm Tea 4.30 - 6.00 pm TUTORIAL LECTURE: Machine Vision 6.15 pm BUSINESS MEETING followed by a RECEPTION 8.00 pm DINNER MONDAY 5 JULY 9.00 - 11.00 am SYMPOSIUM 4: Mindblindness: Autism and Theory of Mind 11.00 - 11.30 am Coffee 11.30 am - 1.00 pm SUBMITTED PAPERS 1.00 - 2.00 pm Lunch 2.00 - 4.00 pm ROUND TABLE: Neuropsychological Approaches 4.00 - 4.30 pm Tea 4.30 - 6.00 pm INVITED LECTURE: tba 6.30 pm A visit to Chatsworth House,including DINNER TUESDAY 6 JULY Depart after breakfast Symposium speakers include: Simon Baron-Cohen, John Campbell, Pascal Engel, Juan Carlos Gomez, Pierre Jacob, Marcel Kinsbourne, Tony Marcel, Michael Martin, David Perrett, Gabriel Segal, Tim Shallice, Chris Sinha ************************************************************************ From lazzaro at boom.CS.Berkeley.EDU Sun Apr 4 16:42:27 1993 From: lazzaro at boom.CS.Berkeley.EDU (John Lazzaro) Date: Sun, 4 Apr 93 13:42:27 PDT Subject: New Release -- Chipmunk Analog VLSI CAD Tools Message-ID: <9304042042.AA07317@boom.CS.Berkeley.EDU> Caltech VLSI CAD Tool Distribution -- New Revision --------------------------------------------------- We are offering to the Internet community a new revision of the Caltech electronic CAD system for analog VLSI neural networks. This distribution contains tools for schematic capture, netlist creation, and analog and digital simulation (log), IC mask layout, extraction, and DRC (wol), simple chip compilation (wolcomp), MOSIS fabrication request generation (mosis), netlist comparison (netcmp), data plotting (view) and postscript graphics editing (until). These tools were used exclusively for the design and test of all the integrated circuits described in Carver Mead's book "Analog VLSI and Neural Systems". Until was used as the primary tool for figure creation for the book. The distribution also contains an example of an analog VLSI chip that was designed and fabricated with these tools, and an example of an Actel field-programmable gate array design that was simulated and converted to Actel format with these tools. These tools are distributed under a license very similar to the GNU license; the minor changes protect Caltech from liability. Highlights of the new revision includes: * Ports to new platforms (Supported platforms now include: Sun SPARC, Sun 3, HP Series 300/400/700/800, DEC MIPS-based Ultrix, Appple AU/X, linux, and IBM RS/6000 support). * Support for black and white displays, and resource database support for user preferences for sizing and placement of windows. New display modes in analog to support small screens. * Direct generation of SPICE netlists in analog, and new models for floating-well FET's, two-terminal devices with arbitrary i-v curves, and quantum-well tunnel diodes. * Many bug fixes for analog, wol, view, and until, and new features for view. If you are interested in some or all of these tools, 1) ftp to hobiecat.cs.caltech.edu on the Internet, 2) log in as anonymous and use your username as the password 3) cd pub/chipmunk 4) copy the file README, that contains more information. European researchers can access these files through anonymous ftp using the machine ifi.uio.no in Norway; the files are in the directory chipmunk. We are unable to help users who do not have Internet ftp access. From raina at max.ee.lsu.edu Mon Apr 5 16:18:00 1993 From: raina at max.ee.lsu.edu (Praveen Raina) Date: Mon, 5 Apr 93 15:18:00 CDT Subject: Generalization Comparison Message-ID: <9304052018.AA24266@max.ee.lsu.edu> The following report is available that examines the generalization performance of two feedforward learning techniques. ---- Technical Report ECE 93-03, LSU, March 31, 1993 ----- COMPARISON OF LEARNING AND GENERALIZATION CAPABILITIES OF THE KAK AND THE BACKPROPAGATION ALGORITHMS Praveen Raina Dept. of Electrical & Computer Engineering LSU, Baton Rouge, LA 70803-5901 E-mail: raina at max.ee.lsu.edu Abstract: This report compares the learning and generalization capabilities of the Backpropagation and the Kak algorithm. It is observed that the Backpropagation algorithm is much more computation intensive than the Kak algorithm. The generalization performance with respect to an error criterion is better for the Backpropagation algorithm for intermediate values of error. But when considered together with the number of extra iterations that the Backpropagation algorithm entails one concludes that the Kak algorithm has overall superior performance. From piero at dist.dist.unige.it Tue Apr 6 14:54:12 1993 From: piero at dist.dist.unige.it (Piero Morasso) Date: Tue, 6 Apr 93 14:54:12 MET DST Subject: ICANN'94 Preliminary Call for Papers Message-ID: <9304061254.AA02516@dist.dist.unige.it> -------------------------------------------------------------------- | ************************************************ | | * * | | * EUROPEAN NEURAL NETWORK SOCIETY * | | * PRELIMINARY CALL FOR PAPERS * | | * I C A N N ' 94 - SORRENTO * | | * * | | ************************************************ | | | | ICANN'94 (INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS)| | is the fourth Annual Conference of ENNS and it comes after | | ICANN'91(Helsinki), ICANN'92 (Brighton), ICANN'93 (Amsterdam). | | It is co-sponsored by INNS, IEEE-NC, JNNS. | | It will take place at the Sorrento Congress Center, near Naples, | | Italy, on May 26-29, 1994. | | There will be tutorials and invited talks by top-experts | | in the field who will also join the program committee. | | | | Interested authors are cordially invited to present their work | | in one of the following "Scientific Areas" (A-Cognitive Science; | | B-Mathematical Models; C- Neurobiology; D-Fuzzy Systems; | | E-Neurocomputing), indicating also an "Application domain" | | (1-Motor Control;2-Speech;3-Vision;4-Natural Language; | | 5-Process Control;6-Robotics;7-Signal Processing; | | 8-Pattern Recognition;9-Hybrid Systems;10-Implementation). | | | | DEADLINE for CAMERA-READY COPIES: December 15, 1993. | | ---------------------------------------------------- | | Detailed instructions will be given in a subsequent call. | | | | Conference Chair: Prof. Eduardo R. Caianiello, Univ. Salerno, | | Italy, Dept.Theoretic Physics; email: iiass at salerno.infn.it | | | | Conference Co-Chair: Prof. Pietro G. Morasso, Univ. Genova, | | Italy, Dept.Informatics, Systems,Telecommunication, | | email: morasso at dist.unige.it | | | | Tutorial Chair: Prof. John Taylor, Imperial College,London, UK, | | fax: +44 71 873 2017 | | | | Industrial Liaison Chair: Dr. Roberto Serra, Ferruzzi | | Finanziaria, Ravenna, fax: +39 544 35692/32358 | -------------------------------------------------------------------- From yves at netid.com Tue Apr 6 17:57:40 1993 From: yves at netid.com (Yves Chauvin) Date: Tue, 6 Apr 93 14:57:40 PDT Subject: Preprint available Message-ID: <9304062157.AA00259@netid.com> **DO NOT FORWARD TO OTHER GROUPS** The following paper, "Smooth On-Line Learning Algorithms for Hidden Markov Models" has been placed in the neuroprose archive. It is to be published in Neural Computation. Further information and retrieval instructions are given below. ___________________________________________________________________________ "Smooth On-Line Learning Algorithms for Hidden Markov Models" Pierre Baldi JPL, Caltech Yves Chauvin Net-ID, Inc. A simple learning algorithm for Hidden Markov Models (HMMs) is presented together with a number of variations. Unlike other classical algorithms such as the Baum-Welch algorithm, the algorithms described are smooth and can be used on-line (after each example presentation) or in batch mode, with or without the usual Viterbi most likely path approximation. The simple expression of the learning algorithms and several of their advantages result from using Boltzmann-Gibbs representations (normalizing exponentials) for the HMM parameters. All the algorithms presented are proved to be exact or approximate gradient optimization algorithms with respect to likelihood, log-likelihood or cross-entropy functions, and as such are usually convergent. These algorithms can also be casted in the more general EM (Expectation-Maximization) framework where they can be viewed as exact or approximate GEM (Generalized Expectation-Maximization) algorithms. The mathematical properties of the algorithms are derived in the appendix. ___________________________________________________________________________ Retrieval instructions: The paper is baldi.smoothhmm.ps.Z in the neuroprose archive. To retrieve this file from the neuroprose archives: unix> ftp cheops.cis.ohio-state.edu Name (cheops.cis.ohio-state.edu:becker): anonymous Password: (use your email address) ftp> cd pub/neuroprose ftp> binary ftp> get baldi.smoothhmm.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for baldi.compbiohmm.ps.Z . ftp> quit . unix> uncompress baldi.smoothhmm.ps.Z unix> lpr baldi.smoothhmm.ps From mike at psych.ualberta.ca Tue Apr 6 21:54:38 1993 From: mike at psych.ualberta.ca (Mike Dawson) Date: Tue, 6 Apr 93 19:54:38 MDT Subject: Positions at U. of A. Message-ID: The University of Alberta, Department of Psychology, is seeking applications from candidates who can contribute to the further development of a leading program in Cognitive Science. Individuals will be hired into tenure-track positions at the Assistant Professor level, salary range $40,035 to $57,003. Appointments take effect July 1, 1994; PhD should be completed by that date. Special consideration will be given to candidates who have expertise both in basic research and in applied, problem-oriented areas. Candidates should have significant interdisciplinary interests; the individuals hired will have the potential to further develop links across existing areas in the Department, as well as with other Departments and the extramural research community. The Department of Psychology has members within both the Faculties of Arts and Science and has outstanding infrastructure for research. Decisions will be made on the basis of demonstrated research capability, teaching ability, and the potential for interactions with colleagues. We encourage applicants from the following five areas; we currently have vacancies to fill in four of these areas: (1) COGNITION AND AGING: Expertise in memory, language, or cognition as they relate to normal aging or to age-related pathologies. (2) COGNITIVE NEUROSCIENCE: Expertise in the relation between neural processes and cognitive processes such as memory, language, perception, attention, visual cognition and/or psychophysiology. (3) COGNITIVE PSYCHOLOGY: Expertise in any area of cognition. Individuals with broad interests in language processing and cognitive science, and research expertise in psycholinguistics, discourse processing, speech comprehension and production, word perception and/or reading will be given special consideration. (4) COGNITIVE MODELING: Expertise in the computational modeling of cognitive, perceptual, and/or neural processes. Individuals with the demonstrated ability to relate these models to empirical observations are especially encouraged to apply. (5) SOCIAL COGNITION: Experts in such areas as social judgment and decision- making, social memory, beliefs and attitudes, affect, motivation, social psychophysiology, and/or interpersonal relations are especially encouraged to apply. In accordance with Canadian Immigration requirements, priority will be given to Canadian citizens and permanent residents of Canada. Applicants should include a curriculum vitae, statement of research interests, three letters of recommendation, and reprints or recent publications. These materials should be sent to the Chair of the appropriate search committee (e.g., Chair, Cognition and Aging Search Committee), Department of Psychology, University of Alberta, Edmonton, Alberta, CANADA T6G 2E9. To receive full consideration, all materials must be received by October 15, 1993. The University of Alberta is committed to the principle of equity in employment. The University encourages applications from aboriginal persons, disabled persons, members of visible minorities, and women. -- Michael R.W. Dawson email: mike at psych.ualberta.ca Biological Computation Project, Department of Psychology University of Alberta, Edmonton, AB CANADA T6G 2E9 Tel: +1 403 492 5175 Fax: +1 403 492 1768 From lpratt at franklinite.Mines.Colorado.EDU Wed Apr 7 12:57:52 1993 From: lpratt at franklinite.Mines.Colorado.EDU (Lorien Y. Pratt) Date: Wed, 7 Apr 93 09:57:52 -0700 Subject: David Cohn to speak in Colorado Machine Learning series Message-ID: <9304071657.AA15275@franklinite.Mines.Colorado.EDU> The spring, 1993 Colorado Machine Learning Colloquium Series presents: Dr. David Cohn Dept. of Brain & Cognitive Science Massachusetts Inst. of Technology Cambridge, MA 02139 Uncertainty-Based Queries in Neural Networks *Thursday*, April 15, 1993 Room 110, Stratton Hall, on the CSM campus 5:30 pm ABSTRACT In many interesting learning problems, it is practical for a learner to pick its own training data. Intuition and theory both suggest that by properly picking where one's training data comes from, one can greatly improve one's ability to generalize. I will consider the problem of attempting to learn a map from points in a domain, such as a geometric map or a set of state-action pairs, to some ``value,'' such as a classification or a next-state identifier. I will assume that training data may be obtained by querying. That is, we may specify a point x and call an oracle, or perform an experiment to determine f(x), the value of the map at that point. We wish to make queries that are ``optimally informative'' according to some criterion, but there are many criteria to choose from, and many are computationally intractible. I will discuss my current research studying the suitability of a querying criterion based on uncertainty in system parameters. Under certain reasonable assumptions, one may efficiently compute how much the uncertainty in system parameters will be reduced by knowing f(x) for a specified x, and thus the ``information gain'' of querying it. This approach was introduced by Fedorov in 1972; its utility for active data selection in neural networks was proposed by MacKay in 1991. I will discuss experiments performing gradient ascent on the information gain of a query, and discuss the problems that are involved in extending this approach to learning problems which only allow restricted querying, such as navigation, exploration and control. Suggested background readings: Training Connectionist Networks with Queries and Selective Sampling; Les Atlas, David Cohn and Richard Ladner. Advances in Neural Information Processing 2, D. Touretzky ed. Morgan Kaufmann, 1990, pp. 566-573. Constructing Hidden Units using Examples and Queries; Eric B. Baum and Kevin J. Lang. Advances in Neural Information Processing 3, R. Lippman, J. Moody and D. Touretzky, eds. Morgan Kaufmann, 1991, pp. 904- 910. The Evidence Framework applied to Classification Networks; David J. C. MacKay. Neural Computation, Volume 4, number 5, 1992, pages 698-714. These readings are available on reserve at the Arthur Lakes Library at CSM. Ask for the reserve package for MACS570, subject: Cohn. Non-students can check materials out on reserve by providing a driver's license. Open to the Public Refreshments to be served at 5:00pm, prior to talk For more information (including a schedule of all talks in this series), contact: Dr. L. Y. Pratt, CSM Dept. of Mathematical and Computer Sciences, lpratt at mines.colorado.edu, (303) 273-3878. The speaker may be contacted at cohn at psyche.mit.edu. Sponsored by: THE CSM DEPARTMENTS OF MATHEMATICAL AND COMPUTER SCIENCES, GEOPHYSICS, DIVISION OF ENGINEERING, AND CRIS The Center for Robotics and Intelligent Systems at the Colorado School of Mines From ronen at wisdom.weizmann.ac.il Wed Apr 7 10:34:16 1993 From: ronen at wisdom.weizmann.ac.il (Ronen Basri) Date: Wed, 7 Apr 93 17:34:16 +0300 Subject: CFP - Israeli Symposium on AI and Vision, Dec. 1993 Message-ID: <9304071434.AA17223@silver.wisdom.weizmann.ac.il> Call For Papers 10th Israeli Symposium on Artificial Intelligence and Computer Vision Tel-Aviv, December 27-28, 1993 The conference is the joint annual meeting of the Israeli Association for Artificial Intelligence, and the Israeli Association for Computer Vision and Pattern Recognition, which are affiliates of the Israeli Information Processing Association. Papers addressing all aspects of AI and Computer Vision, including, but not limited to, the following topics, are solicited: Image Processing and Analysis Computer Vision, Applications, Robotics Biological Vision, Visual Perception Cognitive Modeling Pattern Recognition and Neural Networks Natural Language Processing Inductive Inference, Automated Reasoning, Planning and Search Knowledge Acquisition, Knowledge Theory, Logics of Knowledge AI and Education, AI Languages and Methodology Submitted papers will be refereed by the program committee. Authors should submit 4 copies of the full paper (in English). Accepted papers will appear in the conference proceedings. Papers should be received by the conference co-chairmen at one of the following addresses by June 30th, 1993. Authors will be notified of acceptance by September 15th 1993. Vision: AI: Dr. Ronen Basri Dr. Uri J. Schild 10th IAICV 10th IAICV Dept. of Appl. Math. and Comp. Sci. Dept. of Math. and Comp. Sci. The Weizmann Institute of Science Bar Ilan University Rehovot 76100, Israel Ramat Gan 52900, Israel ronen at wisdom.weizmann.ac.il schild at bimacs.cs.biu.ac.il VISION Committee Members: ----------------------------------------------------------------------------- D. Weinshall Hebrew University daphna at cs.huji.ac.il N. Intrator Tel Aviv University nin at math.tau.ac.il N. Kiryati Technion kiryati at techunix.technion.ac.il Z. Smilansky Orbotec zeev at orbot.co.il Y. Halor Weizmann Institute toky at wisdom.weizmann.ac.il R. Basri (Chairman) Weizmann Institute ronen at wisdom.weizmann.ac.il AI Committee Members: ----------------------------------------------------------------------------- L. Manevitz Haifa University manevitz at mathcs2.haifa.ac.il M. Golumbic IBM Scientific center golumbic at haifasc3.vnet.ibm.com S. Kraus Bar-Ilan University sarit at bimacs.biu.ac.il Y. Davidor Weizmann Institute yuval at wisdom.weizmann.ac.il U. Ornan Technion ornan at techsel.technion.ac.il S. Markovitz Technion shaulm at cs.technion.ac.il J. Rosenschein Hebrew University jeff at cs.huji.ac.il E. Gudes Ben-Gurion University ehud at bengus.bgu.ac.il U. Schild (Chairman) Bar-Ilan University schild at bimacs.biu.ac.il From becker at cs.toronto.edu Wed Apr 7 10:05:41 1993 From: becker at cs.toronto.edu (becker@cs.toronto.edu) Date: Wed, 7 Apr 1993 10:05:41 -0400 Subject: job opening at McMaster Message-ID: <93Apr7.100550edt.786@neuron.ai.toronto.edu> McMaster University Department of Psychology McMaster University invites applications for a tenure track position at the Assistant Professor rank starting July 1, 1994, in the Department of Psychology with associate status in the De partment of Computer Science and Systems. This position is sub- ject to final budgetary approval. Candidates' interest should be in artificial intelligence, specifically in empirical studies and connectionist modelling of language abilities or language acquisition in normal and brain- damaged individuals. Candidates must have expert modelling and computational skills and be prepared to teach in both computer science and psychology. In accordance with Canadian Immigration requirements, priority will be given to Canadian citizens and permanent resi- dents. McMaster University is committed to Employment Equity and encourages applications from all qualified candidates, including aboriginal people, people with disabilities, members of visible minorities, and women. Please forward applications, consisting of c.v., publica- tions list, a short statement of research interests, and arrange to have three letters of reference sent to the Chair, Department of Psychology, McMaster University, Hamilton, Ontario, L8S 4K1, Canada. From wahba at stat.wisc.edu Thu Apr 8 15:03:51 1993 From: wahba at stat.wisc.edu (Grace Wahba) Date: Thu, 8 Apr 93 14:03:51 -0500 Subject: Uncertainty-Based Queries Message-ID: <9304081903.AA26851@hera.stat.wisc.edu> Re: Uncertainty Based Queries in Neural Networks: D. Cohn abstract of talk at Colorado State: ml-connectionists distribution Apr 7, 1993 Various forms of the interesting problem discussed in the above abstract have been studied in the statistics literature (in different language, naturally!) under the rubric `experimental design'- The Current Index to Statistics database here lists 5430 articles under `design', a non-trivial proportion of which are in the general context of allowing to choose x and observe f(x), or, a noise-corrupted version of f(x), in order to learn something about f. .see also: Sacks, Welch, Mitchell and Wynn, Design and analysis of computer experiments, with discussion Statistical Science, 4, 409-423, 1989. . Athavale and Wahba, Determination of an optimal mesh for a collocation-projection method for solving two-point boundary value problems, J. Approx. Theory, 25, 38-49, 1979. . Wahba, Parameter estimation in linear dynamic systems, IEEE Trans. Automatic Control, AC-25, 235-238, 1980 Grace Wahba wahba at stat.wisc.edu From soodakr at ROCKVAX.ROCKEFELLER.EDU Thu Apr 8 22:51:18 1993 From: soodakr at ROCKVAX.ROCKEFELLER.EDU (Robert Soodak) Date: Thu, 8 Apr 93 22:51:18 -0400 Subject: No subject Message-ID: <9304090251.AA20858@rocky8.ROCKEFELLER.EDU> Subject: Postdoc Position at Rockefeller U. April 8, 1993 A postdoctoral position in computational neuroscience is available immediately. Research will be concerned with pattern formation of orientation columns which result from the orderly mapping of the mosaic of retinal ganglion cells onto the cortical surface. Simulations constrained by published biological data are the primary means of investigation. The position will involve C programing in a UNIX environment, and some programing experience is essential. No formal training in neuroscience is required, although an interest in biological information processing would be an asset. Write, phone or email with questions or applications to: Robert Soodak Rockefeller University 1230 York Avenue New York, NY 10021 email: soodakr at rockvax.rockefeller.edu Tel: (212) 327-8603 Fax: (212) 327-8530 (Not Private) From David_Redish at GS17.SP.CS.CMU.EDU Fri Apr 9 10:08:25 1993 From: David_Redish at GS17.SP.CS.CMU.EDU (David Redish) Date: Fri, 09 Apr 93 10:08:25 -0400 Subject: Paper on Neuroprose Message-ID: <17467.734364505@GS17.SP.CS.CMU.EDU> The following paper has been placed in the Neuroprose archive. Comments and questions are welcome. ******************************************************************* Neural Representation of Space Using Sinusoidal Arrays David S. Touretzky A. David Redish Hank S. Wan School of Computer Science Computer Science Department Carnegie Mellon University Pittsburgh, PA 15213 O'Keefe (1991) has proposed that spatial information in rats might be represented as phasors: phase and amplitude of a sine wave encoding angle and distance to a landmark. We describe computer simulations showing that operations on phasors can be efficiently realized by arrays of spiking neurons that re-code the temporal dimension of the sine wave spatially. Some cells in motor and parietal cortex exhibit response properties compatible with this proposal. This paper will appear in Neural Computation. ******************************************************************* ---------------------------------------------------------------- FTP INSTRUCTIONS "Getps touretzky.sinusoidal-arrays.ps.Z" if you have the shell script, or unix% ftp archive.cis.ohio-state.edu (or 128.146.8.52) Name: anonymous Password: neuron ftp> cd pub/neuroprose ftp> binary ftp> get touretzky.sinusoidal-arrays.ps.Z ftp> bye unix% uncompress touretzky.sinusoidal-arrays.ps unix% lpr touretzky.sinusoidal-arrays.ps Note that the last figure does not print out correctly on all printers. If you have trouble printing it out, we have supplied a copy of the figure in its own postscript file. (We've never had a problem printing it out alone, just included into the document.) The extra file is called "touretzky.extra-fig.ps" and can be retrieved from the same directory in the same manner as "touretzky.sinusoidal-array.ps.Z". The extra figure is not compressed. ---------------------------------------------------------------- From dhw at santafe.edu Fri Apr 9 16:13:21 1993 From: dhw at santafe.edu (dhw@santafe.edu) Date: Fri, 9 Apr 93 14:13:21 MDT Subject: New paper in neuroprose Message-ID: <9304092013.AA07791@zia> *** DO NOT FORWARD TO ANY OTHER LISTS *** The following file has been placed in neuroprose. Part of it consists of a tutorial review, and part of it consists of novel material concerning extensions of stacked generalization. COMBINING GENERALIZERS USING PARTITIONS OF THE LEARNING SET by David H. Wolpert Abstract: For any real-world generalization problem, there are always many generalizers which could be applied to the problem. This paper discusses some algorithmic techniques for dealing with this multiplicity of possible generalizers. All of these techniques rely on partitioning the provided learning set in two, many different times. The first technique discussed is cross-validation, which is a winner-takes-all strategy (based on the behavior of the generalizers on the partitions of the learning set, it picks one single generalizer from amongst the set of candidate generalizers, and tells you to use that generalizer). The second technique discussed, the one this paper concentrates on, is an extension of cross-validation called stacked generalization. As opposed to cross-validation's winner-takes-all strategy, stacked generalization uses the partitions of the learning set to combine the generalizers, in a non-linear manner, via another generalizer (hence the term `stacked generalization'). After presenting a cursory review of stacked generalization, this paper discusses some possible extensions of stacked generalization. To retrieve the file: unix> ftp cheops.cis.ohio-state.edu Connected to cheops.cis.ohio-state.edu. 220 cheops.cis.ohio-state.edu FTP server ready. Name: anonymous 331 Guest login ok, send ident as password. Password:neuron 230 Guest login ok, access restrictions apply. ftp> binary 200 Type set to I. ftp> cd pub/neuroprose 250 CWD command successful. ftp> get wolpert.lecture92.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for rosenblatt.reborn.ps.Z 226 Transfer complete. 100000 bytes sent in 3.14159 seconds ftp> quit 221 Goodbye. unix> uncompress wolpert.lecture92.ps.Z unix lpr wolpert.lecture92.ps (or however you print out postscript) Many thanks to Jordan Pollack for maintaining this archive. From David_Redish at GS17.SP.CS.CMU.EDU Mon Apr 12 09:43:30 1993 From: David_Redish at GS17.SP.CS.CMU.EDU (David Redish) Date: Mon, 12 Apr 93 09:43:30 -0400 Subject: Sinusoidal arrays paper on Neuroprose (corrections/amplification) Message-ID: <10079.734622210@GS17.SP.CS.CMU.EDU> In referrence to: Neural Representation of Space Using Sinusoidal Arrays David S. Touretzky A. David Redish Hank S. Wan Some people have had trouble uncompressing the file. The problem should be fixed now. Some people have also noted that the name I gave for the extra figure was incorrect. The correct filenames are touretzky.sinusoidal-arrays.ps.Z touretzky.extra-fig.ps.Z Sorry for the inconvenience Dave Redish [I'm also including a more detailed version of the abstract. -- DST] EXTENDED ABSTRACT: Any vector in polar coordinates v=(r,phi) can be represented as a sine wave f(t) = r cos (omega t + phi), where r is amplitude, phi is phase, and omega is (constant) frequency. This is commonly known as a phasor. The advantage of phasor representation is that translation and rotation of a vector are both trivial operations. Translation is achieved by addition of sine waves, and rotation can be obtained by phase shifting or temporal delay. O'Keefe (1991) has suggested that rats might use phasors to encode angle and distance to landmarks. In his proposal, hippocampal theta provides the reference signal for determining phase. This temporal approach to encoding a sine wave has some drawbacks. The 7-12 Hz theta rhythm may be too slow to support real-time spatial reasoning tasks requiring rapid manipulation of phasors. Furthermore, maintaining even a modest angular resolution of 10 degrees relative to a roughly 10 Hz reference signal requires a temporal resolution of 3 msec. Although some specialized sensory systems are known to make much finer discriminations (e.g., acoustic imaging in bats and dolphins, or auditory localization in barn owls), we are reluctant to require this degree of temporal precision at the higher cognitive level associated with spatial reasoning. Instead, we suggest that phasor operations are more plausibly realized by re-coding the temporal dimension of the sine wave spatially, using populations of spiking neurons. We propose an architecture called the sinusoidal array for manipulating vectors in phasor form, and report the results of computer simulations. There is some experimental evidence that sinusoidal array representations may exist in rat parietal cortex and in rhesus motor or parietal cortex. We propose an experiment to test this hypothesis in rats. From ZENIOS at WILMA.WHARTON.UPENN.EDU Mon Apr 12 14:36:00 1993 From: ZENIOS at WILMA.WHARTON.UPENN.EDU (ZENIOS@WILMA.WHARTON.UPENN.EDU) Date: Mon, 12 Apr 93 14:36 EDT Subject: Cascade correlation learning algorithm to predict mortgage prepayments Message-ID: <9304121837.AA01667@noc2.dccs.upenn.edu> The March issue of The Journal of Fixed Income published a paper on the use of neural networks to predict mortgage prepayments. The precise reference is listed below, and copies of the article can be obtained from Marge Weiler, Decision Sciences Department, The Wharton School, University of Pennsylvania, Philadelphia, PA 19104 (215)898-5872 *************** Y. Yamamoto and S.A. Zenios, Predicting prepayment rates for mortgage-backed securities using the cascade-correlation learning algorithm, The Journal of Fixed Income, Vol. 2(4), pp.86--96, March 1993. From mel at cns.caltech.edu Mon Apr 12 14:59:49 1993 From: mel at cns.caltech.edu (Bartlett Mel) Date: Mon, 12 Apr 93 11:59:49 PDT Subject: Post-Doc Position Message-ID: <9304121859.AA09243@plato.cns.caltech.edu> --------- POSITION AVAILABLE ---------- Computation and Neural Systems Program California Institute of Technology A post-doctoral position will be available for Fall 1993 to work collaboratively on the development of a biologically-inspired system for 3-D visual object recognition. The position will be for one year with a possibility for renewal. The goal of the project is to construct an integrated software/hardware system for viewpoint invariant recognition of a large repertoire of real 3-D objects. The project will involve ideas and techniques from statistical pattern recognition and neural network learning, but with a strong emphasis on algorithms of relevance to biological vision, learning, and memory. Proficiency in a UNIX/C programming environment is necessary. Any of the following additional qualities is desirable: 1) knowledge of neurobiology and/or psychology of human and animal vision, 2) knowledge of classical computer vision techniques, and 3) experience in building large-scale software/hardware systems, particularly X-windows-based programming. Salary is $30,000/year. Interested applicants should send a letter describing their background and interests, a CV, a few relevant publications, and three letters of recommendation to: Dr. Bartlett Mel Division of Biology Caltech 216-76 Pasadena, CA 91125 (818)356-3643 mel at caltech.edu The California Institute of Technology is an equal opportunity/ affirmative action employer and encourages the applications of qualified women and minorities. From cohn at psyche.mit.edu Mon Apr 12 18:59:44 1993 From: cohn at psyche.mit.edu (David Cohn) Date: Mon, 12 Apr 93 18:59:44 EDT Subject: Uncertainty-based queries Message-ID: <9304122259.AA02257@psyche.mit.edu> Concerning the talk abstract "Uncertainty-Based Queries in Neural networks" which appeared here a few days ago: Quite a few people have pointed out that the use of measures of uncertainty to gather new data is not a new idea. I must apologize if my abstract made it appear that I thought it was. The idea can be traced back at least as far as the 40's (A. Wald, Ann. Math. Stat., Vol 14, 1943). The field of optimal experiment design, as it has become known to statisticians, is rather well developed. The most complete treatment of which I am aware is Fedorov (Theory of Optimal Experiments, Academic Press, 1972). Thanks also to Grace Wahba for providing additional references. It has been said, however, that the best new ideas in neural networks are coming from the 60's and 70's -- that people in the field are rediscovering the utility of tools (in statistics, control theory, etc.) that were developed "ahead of their time" and had only limited practical application before the advent of today's machine learning algorithms. My current research-in-progress, and the subject of the talk whose abstract appeared here earlier, is a practical examination of how we can take the techniques of optimal experiment design and apply them to the problems facing neural network researchers today. (D. MacKay addressed some aspects of this problem in his dissertation, and in a paper in Neural Computation 4(4)). As this *is* work in progress, I do not yet have a paper written on my results so far, but I will be happy to discuss them with any interested persons. Again, thank you all for your comments. Yes, I am aware of the body of results from optimal experiment design, and the point of my work is to see how these results can be applied to (excuse the expression) "practical problems" facing neural net researchers. I am sorry that my abstract did not make that clear. -David Cohn e-mail: cohn at psyche.mit.edu Dept. of Brain & Cognitive Science phone: (617) 253-8409 MIT, E10-243 Cambridge, MA 02139 From piero at dist.dist.unige.it Wed Apr 14 19:09:17 1993 From: piero at dist.dist.unige.it (Piero Morasso) Date: Wed, 14 Apr 93 19:09:17 MET DST Subject: ICANN'94 Preliminary Call for Papers Message-ID: <9304141709.AA26066@dist.dist.unige.it> -------------------------------------------------------------------- | ************************************************ | | * * | | * EUROPEAN NEURAL NETWORK SOCIETY * | | * PRELIMINARY CALL FOR PAPERS * | | * I C A N N ' 94 - SORRENTO * | | * * | | ************************************************ | | | | ICANN'94 (INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS)| | is the fourth Annual Conference of ENNS and it comes after | | ICANN'91(Helsinki), ICANN'92 (Brighton), ICANN'93 (Amsterdam). | | It is co-sponsored by INNS, IEEE-NC, JNNS. | | It will take place at the Sorrento Congress Center, near Naples, | | Italy, on May 26-29, 1994. | | There will be tutorials and invited talks by top-experts | | in the field who will also join the program committee. | | | | Interested authors are cordially invited to present their work | | in one of the following "Scientific Areas" (A-Cognitive Science; | | B-Mathematical Models; C- Neurobiology; D-Fuzzy Systems; | | E-Neurocomputing), indicating also an "Application domain" | | (1-Motor Control;2-Speech;3-Vision;4-Natural Language; | | 5-Process Control;6-Robotics;7-Signal Processing; | | 8-Pattern Recognition;9-Hybrid Systems;10-Implementation). | | | | DEADLINE for CAMERA-READY COPIES: December 15, 1993. | | ---------------------------------------------------- | | Detailed instructions will be given in a subsequent call. | | | | Conference Chair: Prof. Eduardo R. Caianiello, Univ. Salerno, | | Italy, Dept.Theoretic Physics; email: iiass at salerno.infn.it | | | | Conference Co-Chair: Prof. Pietro G. Morasso, Univ. Genova, | | Italy, Dept.Informatics, Systems,Telecommunication, | | email: morasso at dist.unige.it | | | | Tutorial Chair: Prof. John Taylor, Imperial College,London, UK, | | fax: +44 71 873 2017 | | | | Industrial Liaison Chair: Dr. Roberto Serra, Ferruzzi | | Finanziaria, Ravenna, fax: +39 544 35692/32358 | -------------------------------------------------------------------- From rob at comec4.mh.ua.edu Fri Apr 16 10:01:22 1993 From: rob at comec4.mh.ua.edu (Robert Elliott Smith) Date: Fri, 16 Apr 93 08:01:22 -0600 Subject: ICGA announcement and registration form Message-ID: <9304161301.AA16884@comec4.mh.ua.edu> Announcement and Registration Form: ICGA-93 The Fifth International Conference on Genetic Algorithms 17-21 July, 1993 University of Illinois at Urbana-Champaign The Fifth International Conference on Genetic Algorithms (ICGA-93), will be held on July 17-21, 1993 at the University of Illinois at Urbana-Champaign. This meeting brings together an international community from academia, government, and industry interested in algorithms suggested by the evolutionary process of natural selection. Topics of particular interest include: genetic algorithms and classifier systems, evolution strategies, and other forms of evolutionary computation; machine learning and optimization using these methods, their relations to other learning paradigms (e.g., neural networks and simulated annealing), and mathematical descriptions of their behavior. The meeting will include pre-conference tutorials, invited speakers, and workshops. A registration form is included below. For more ICGA-93 registration information, contact: Lori Costello Conferences & Institutes Univ. of Illinois 302 E. John St. Suite 202, Champaign, IL 61820 Telephone: (217) 333-2888 E-Mail: loric at ux1.cso.uiuc.edu Questions on the conference program should be directed to icga93 at unmvax.cs.unm.edu. Other questions should be directed to rob at comec4.mh.ua.edu. Tutorials--Levis Faculty Center ICGA '93 will begin with the presentation of three parallel tutorial sessions. Conference attendees may attend one of these sessions for a supplementary fee (see registration form). Tutorial 1: Introduction to Genetic Algorithms Overview of Genetic Algorithms (90 minutes), Melanie Mitchell-- What genetic algorithms are; how, why, and by whom they were invented; how and why they work; comparisons with other algorithms; how to find out more about the genetic algorithm field; foundations of GA theory; genetic algorithms and artificial life; partial bibliography. Genetic Algorithm Applications (90 minutes), Lawrence Davis-- What kind of real-world problems are appropriate for genetic algorithms; design choices that must be made when applying genetic algorithms to real problems; partial survey of existing applications; partial survey of existing tools; some case histories. Tutorial 2: Advanced Genetic Algorithm Topics Genetic Algorithm Theory (90 minutes), Darrell Whitley-- The schema theorem and its ramifications; deception; recent approaches to the study of genetic algorithm performance; recent approaches to the study of genetic algorithm failure. Classifier Systems and Modeling (90 minutes), Rob Smith-- Introduction to classifier systems; recent advances in classifier system theory and practice; classifier systems as modeling tools; genetic algorithms and neural networks; genetic algorithms and artificial life. Tutorial 3: Spotlighted Technologies Evolutionary Programming (45 minutes), David Fogel-- Description and overview of evolutionary programming; history of the field; relation of evolutionary programming to biological evolution; theoretical aspects of the field; survey of existing applications. Evolution Strategies (45 minutes), Thomas Back-- Description and overview of evolution strategies; comparison with other technologies; engineering solutions with evolution strategies; survey of existing applications. Genetic Programming (90 minutes), John Koza-- Description and overview of genetic programming; example applications; future directions; brief video demonstrations. TENTATIVE SCHEDULE: Saturday, July 17, 1993 12-3:00 pm Registration Levis Faculty Center 1-5:00 pm Tutorials Levis Faculty Center 7:00 pm Reception/Registration Levis Faculty Center Sunday, July 18, 1993 8am-5:00 pm Registration Krannert Center (KCPA) 8:30-9:00 am Coffee KCPA 9-10:15 am Invited Speaker KCPA 10:15-11 am Break KCPA 11-12:30 pm Technical Sessions KCPA/Levis 12:30-2 pm Lunch KCPA 2-3:30 pm Technical Sessions/ Registration Levis 3:30-4 pm Break Levis 4-5:30 pm Technical Sessions Levis 7:00 pm Banquet Chancellor Hotel 1501 S. Neil, Champaign Monday, July 19, 1993 8am-5:00 pm Registration KCPA 8:30-9:00 am Coffee KCPA 9-10:15 am Invited Speaker KCPA 10:15-11 am Break KCPA 11-12:30 pm Technical Sessions KCPA/Levis 12:30-2 pm Lunch KCPA 2-3:30 pm Technical Sessions/ Registration Levis 3:30-4 pm Break Levis 4-5:30 pm Technical Sessions Levis 7:00 pm Poster Session Levis Tuesday, July 20, 1993 8:30-9:00 am Coffee KCPA 9-10:15 am Invited Speaker KCPA 10:15-11 am Break KCPA 11-12:30 pm Technical Sessions KCPA/Levis 12:30-2 pm Lunch KCPA 2-3:30 pm Technical Sessions Levis 3:30-4 pm Break Levis 4-5:30 pm Technical Sessions Levis Wednesday, July 21, 1993 8:30-9:00 am Coffee Levis 9-10:30 am Technical Sessions Levis 10:30-11 am Break Levis 11-12:30 pm Technical Sessions Levis 12:30-2 pm Break Levis 2-3:30 pm Business Meeting Levis Invited Speakers David Campbell, Head, Dept. of Physics, University of Illinois. Topic: Dynamical Systems and Evolution John Holland, Professor, Dept. of Psychology, University of Michigan. Topic: Using The Schema Theorem To Counter Hitchhiking And Premature Convergence Gunter Wagner, Professor, Dept. of Biology, Yale University. Topic: Evolutionary Biology Papers (preliminary list) Erik R. Altman, "A Novel Methodology Using Genetic Algorithms for the Design of Caches and Cache Replacement Policy" Peter J. Angeline, "Competitive Environments Evolve Better Solutions for Complex Tasks" Thomas Back, "Optimal Mutation Rates in Genetic Search" Jerzy W. Bala, "Learning to Detect Targets Using Scale-Space and Genetic Search" David Beasley, "Reducing Epistasis in Combinatorial Problems by Expansive Coding" Pierre Bonelli, "A New Approach to Fuzzy Classifier Systems" Ralph Bruns, "Direct Chromosome Representation and Advanced Genetic Operators for Production Scheduling" Helen G. Cobb, "Genetic Algorithms for Tracking Changing Environments" Yuval Davidor, "The ECOlogical Framework II: Improving GA Performance With Virtually Zero Cost" Lawrence Davis, "A Genetic Algorithm for Survivable Network Design" Fred F. Easton, "A Distributed Genetic Algorithm for Employee Staffing and Scheduling Problems" Larry J. Eshelman, "Crossover's Niche" Andrew Fairley, "An Investigation into Possible Causes of, and Solutions to, Rule Strength Distortion in the Bucket Brigade" David S. Feldman, "Fuzzy Network Synthesis and Genetic Algorithms" Stuart J. Flockton, "Pole-Zero System Identification Using Genetic Algorithms" Carlos Fonseca, "Genetic Algorithms for Multiobjective Optimization: Formulation, Discussion and Generalization" David E. Goldberg, "Mixing in Genetic Algorithms" David E. Goldberg, "Rapid, Accurate Optimization of Difficult Problems Using Fast Messy Genetic Algorithms" V. Scott Gord, "Serial and Parallel Genetic Algorithms as Function Optimizers" Frederic Gruau, "Genetic Synthesis of Modular Neural Networks" H. Altay Guvenir, "A Genetic Algorithm for Classification by Feature Partitioning" Raphael T. Haftka, "Genetic Algorithms for Placing Actuators on Space Structures" Inman Harvey, "The Puzzle of the Persistent Question Marks: A Case Study of Genetic Drift" Abdollah Homaifar, "A New Approach on the Traveling Salesman Problem by the Genetic Algorithms" Jeffrey Horn, "Finite Markov Chain Analysis of Genetic Algorithms with Niching" Shu-Yuen Hwang, "A Genetic Algorithm with Disruptive Selection" Hitoshi Iba, "System Identification using Structured Genetic Algorithms" Terry Jones, "Reverse Hillclimbing, Genetic Algorithms and the Busy Beaver Problem" Kate Juliff, "A Multi-chromosome Genetic Algorithm for Pallet Loading" Bryant A. Julstrom, "A Genetic Algorithm for the Rectilinear Steiner Problem" Michelle D. Kidwell , "Using Genetic Algorithms to Schedule Distributed Tasks on a Bus-Based System" Kenneth E. Kinnear, Jr., "Generality and Difficulty in Genetic Programming: Evolving a Sort" Michael Lee, "Dynamic Control of Genetic Algorithms Using Fuzzy Logic Techniques" David M. Levine, "A Genetic Algorithm for the Set Partitioning Problem" Mauro Manela, "Fitting Spline Functions to Noisy Data Using a Genetic Algorithm" Raul San Martin, "Genetic Algorithms for the Optimization of Integrated Circuits Synthesis" Tsutomu Maruyama, "A Fine-Grained Parallel Genetic Algorithm for Distributed Parallel Systems" Laurence D. Merkle, "Comparison of Parallel Messy Genetic Algorithm Data Distribution Strategies" Robert R. Meyer, "A Genetic Algorithm for Diversity Minimization and Its Parallel Implementation" Byung R. Moon, "Hyperplane Synthesis for Genetic Algorithms" Toshinori Munakata, "A Genetic Algorithm Applied to the Maximum Flow Problem" Jim Oliver, "Discovering Individual Decision Rules: An Application of Genetic Algorithms" Norihiko Ono, "A Genetic Algorithm for Channel Routing Problem" Francesco Palmieri, "Diversification Role of Crossover in the Genetic Algorithms" L.M. Patnaik, "Binomially Distributed Populations for Modelling GAs" W.F. Punch, "Further Research on Feature Selection and Classification Using Genetic Algorithms" Nicholas J. Radcliffe, "A Study in Set Recombination" Connie Loggia Ramsey, "Case-Based Initialization of Genetic Algorithms" Colin Reeves, "Using Genetic Algorithms with Small Populations" Gary Roberts, "Dynamic Planning for Classifier Systems" Steve G. Romaniuk, "Evolutionary Growth Perceptions" Peter Ross, "A Promising GA Approach to Job-Shop Scheduling and Re-Scheduling Problems" J. David Schaffer, "Designing Multiplierless Digital Filters Using Genetic Algorithms" Michael J. Shaw, "Joint Lot Sizing and Sequencing with Genetic Algorithms for Scheduling: Evolving the Chromosome Structure" Man-Tak Shing, "Genetic Algorithms for the Development of Real-Time Multi-Heuristic Search Strategies" Marc Shoenauer, "Constrained GA Optimization" R. Shonkwiler, "Parallel Genetic Algorithms" Michael M. Skolnick, "Using Genetic Algorithms in Engineering Design Optimization with Non-Linear Constraints" Alice E. Smith, "Genetic Optimization Using A Penalty Function" William Spears, "On the State of Evolutionary Computation" Joe Suzuki, "A Markov Chain Analysis on A Genetic Algorithm" Walter Alden Tackett, "Genetic Programming for Feature Discovery and Image Discrimination" Dr. David M. Tate, "Expected Allele Coverage and the Role of Mutation" Sam R. Thangiah, "Vehicle Routing and Time Deadlines Using Genetic and Local Algorithms" Bruce Tidor, "An Analysis of Selection Procedures with Particular Attention Paid to Proportional and Boltzmann Selection" Shigeyoshi Tsutsui, "Forking Genetic Algorithm with Blocking and Shrinking Modes (FGA)" Kirk Twardowski, "Credit Assignment for Pole Balancing with Learning Classifier Systems" Ron Unger, "A Genetic Algorithm for 3D Protein Folding Simulations" Thomas Uthmann, "Training Kohonen Feature Maps in Different Topologies: an Analysis Using Genetic Algorithms" Benjamin W. Wah, "Scheduling of Genetic Algorithms in a Noisy Environment" Roger L. Wainwright, "Multiple Vehicle Routing with Time and Capacity Constraints Using Genetic Algorithms" Hirokazu Watabe, "A Study on Genetic Shape Design" Willfried Wienholt, "An Advanced Genetic Algorithm for Parameter Optimization Problems" Peter Willett, "Searching Databases of Two-Dimensional and Three-Dimensional Chemical Structures Using Genetic Algorithms" Jing-Jye Yang, "Query Optimization in Information Retrieval Using Genetic Algorithms" Xiaodong Yin, "A Fast Genetic Algorithm with Sharing Scheme Using Cluster Analysis Methods in Multimodal Function Optimization" Byoung-Tak Zhang, "Genetic Programming of Minimal Neural Nets Using Occam's Razor" Raed Abu Zitar, "Regulator Control via Genetic Search Assisted Reinforcement Learning" Posters (preliminary list) Fabrizio Baiardi, "Nested Hybrid Genetic Algorithms for System Configuration and Program Mapping in Massively Parallel Systems" Ellie Baker, "Evolving Line Drawings" Wolfgang Banzhaf, "Genetic Programming for Pedestrians" Rik Belew, "Evolving Aesthetic Sorting Networks Using Developmental Grammars" Susan E. Carlson, "A Comparative Evaluation of Search Methods Applied to Catalog Selection" Hugh M. Cartwright, "The Application of the Genetic Algorithm to Two-Dimensional Strings: The Source Apportionment Problem" Joseph C. Culberson, "Crossover Versus Mutation in the De Jong Functions: Fueling the Debate: TGA versus GIGA" Fikret Ercal, "Genetic Algorithms for Vertex Splitting in DAGs" David Fan, "GADELO: A Multi-Population Genetic Algorithm Based on Dynamic Exploration of Local Optima" Terence C. Fogarty, "Reproduction, Ranking, Replacement and Noisy Evaluations: Experimental Results" Takeshi Furuhashi, "A Proposal of Hierarchical Fuzzy Classifier Systems" Inman Harvey, "Genetic Convergence in a Species of Evolved Robot Control Architectures" Brynn Hibbert, "Display of Chemical Structures in Two Dimensions and the Evolution of Molecular Recognition" Akio Ishiguro, "A Genetic Algorithms' Application to Inverse Problems in Electromagnetics" Takashi Iwamoto, "Topological Aspects of Genetic Algorithms" Antonia J. Jones, "A Schemata Theorem for Trees" Hillol Kargupta, "Information Transmission in Genetic Algorithm and Shannon's Second Theorem" Hiroaki Kitano, "A Hybrid Search for Genetic Algorithms: Combining Genetic Algorithms, TABU Search, and Simulated Annealing" Luis R. Lopez, "Inverse Relationship Between Complexity and Probability of Full Deception in Trap Functions" Sushil J. Louis, "Pareto Optimality, GA-Easiness and Deception (Extended Abstract)" Heinz Muhlenbein, "Optimal Interaction of Mutation and Crossover in the Breeder Genetic Algorithm" R. Maenner, "Parallel Execution of Sequentially Coded Standard Genetic Algorithms on the NERV Multiprocessor" Samir W. Mahfoud, "Simple Analytical Models of Genetic Algorithms for Multimodal Function Optimization" Vittorio Maniezzo, "Granularity Evolution" Andras Markus, "Dual Insights into Genetic Algorithms" Melanie Mitchell, "When Will a Genetic Algorithm Outperform Hill-Climbing?" Masaharu Munetomo, "An Efficient Migration Scheme for Subpopulation-Based Asynchronously Parallel Genetic Algorithms" David Orvosh, "Shall We Repair? Genetic Algorithms, Combinatorial Optimization, and Feasibility Constraints" Kihong Park, "A Lower-Bound Result on the Power of Genetic Algorithms" Sandip Sen, "Improving Classification Accuracy through Performance History" Robert E. Smith, "Adaptively Resizing Populations: An Algorithm and Analysis" Graham Spencer, "Automatic Generation of Programs for Crawling and Walking" Chuen-Tsai Sun, "Using Genetic Algorithms in Structuring a Fuzzy Rulebase" Hans-Michael Voigt, "Multivalued Evolutionary Algorithms" Michael D. Vose, "The Genetic Algorithm Fractal" Darrell Whitley, "Toward Models of Island and Cellular Parallel Genetic Algorithms" Masayuki Yanagiya, "A Simple Mutation-Dependent Genetic Algorithm" Bernard P. Zeigler, "Asynchronous Genetic Algorithms on Parallel Computers" ICGA-93 Conference Committee: Conference Co-Chairs: David E. Goldberg, Univ. of Illinois at Urbana- Champaign; J. David Schaffer, Philips Labs Publicity: Robert E. Smith, Univ. of Alabama Program Chair: Stephanie Forrest, Univ. of New Mexico Financial Chair: Larry J. Eshelman, Philips Labs Local Arrangements: David E. Goldberg, Univ. of Illinois at Urbana- Champaign Financial supporters: Navy Center for Applied Research in Artificial Intelligence, Naval Research Laboratory; Philips Laboratories, North American Philips Corporation GENERAL INFORMATION Location: The conference will be held at two locations on the University of Illinois campus--the Krannert Center for the Performing Arts located at 500 South Goodwin, Urbana, and the Levis Faculty Center located at 919 West Illinois, Urbana (directly east of Krannert). ICGA '93 is a non-smoking conference. Smoking is allowed in designated areas only. Transportation: Champaign-Urbana is located 135 miles south of Chicago on Interstates 72, 74, and 57. By Car: >From Chicago: Take I-57 south to I-74 east which runs along the north edge of Champaign-Urbana. Take the Lincoln Avenue exit south. Once you reach campus, turn right on Illinois Street. Campus Parking: Pay parking is available in the lot adjacent to the Levis Faculty Center and under the Krannert Center (both accessible from Illinois Street). Do not park in any area marked "reserved" as campus parking is enforced and you will be towed. By Air: >From Champaign-Urbana's Willard Airport: Currently, American Airlines' American Eagle Service, Trans World Express, and US Air Express serve Willard Airport. Corky's Limousine Service is available and meets all incoming flights. The cost from Willard to most hotels in Champaign-Urbana is $8. If you need to contact Corky's, you may call 217/352-3121. By Train: AMTRAK service is also available from Chicago and points south. Weather: The weather in Illinois can vary to extremes. Please be prepared to dress in layered, cool clothing as July is normally hot (80 - 100 ) and very humid. Rain wear is also suggested. On-Campus Recreation: If you wish to take advantage of the recreation facilities on campus, you may purchase an IMPE (Intramural-Physical Education) pass for $5 per day upon showing your name badge at each recreation facility. Messages: If someone needs to reach you during the conference, they may call the Levis Faculty Center at 217/333-6241 and leave a message. A message board will be placed at this conference site. Lodging: Accommodations may be obtained at the following hotels/motels. A shuttle service will be available for transportation from your hotel to/from the conference sites. All hotel reservations should be made in advance by telephoning or writing the individual hotels. Be sure to mention that you are attending the Genetic Algorithms conference, as a block of rooms has been reserved for those attending this conference. We have listed the special conference rates beside the hotel/motel. Make your reservations early as the block of rooms will be released for "first come, first serve" reservations after June 16, 1993. Jumer's Castle Lodge 209 S. Broadway Urbana, IL 61801 Located about 1/4 mile from the campus. Within brisk walking distance. Toll free 800/285-8637 Single Double $60.00 $70.00 Plus tax Plus tax University Inn 302 E. John Street Champaign, IL 61820 Located about 1/2 mile from the campus. Within brisk walking distance. 217/384-2100; Toll free 800/252-1368 in Illinois; Toll free 800/322-8282 outside IL Single Double $54.00 $61.00 Plus tax Plus tax Travelodge 409 W. University Urbana, IL 61801 Located about 1 mile from the campus. Toll free 800/255-3050 Single Double $33.00 Plus tax Campus Inn-University (Days Inn) 1701 S. State Champaign, IL 61820 Located about 1 mile from the campus 217/359-8888 Single Double $30.00 $35.00 Plus tax Plus Tax King or Queen Busey-Evens Dormitory 1111 West Nevada Urbana, IL 61801 Located on campus 217/333-1766 $23.15 Plus tax Community Bath Registration Fee: Registrations received before 6/12/93 are $250 for participants and $100 for students. All registrations received on or after 6/12/93 and walk-in registrations at the conference will be $295 for participants and $125 for students. This includes entry to all technical sessions, 3 lunches, coffee breaks, reception Saturday evening, conference materials, and conference proceedings. Attendee and guest tickets for the banquet and guest tickets for the Sunday reception may be purchased at an additional cost (see attached registration form). Also, there is a separate fee for the tutorials. A limited fund has been set aside to assistant students and scientists with their travel expenses. Students should have their advisor certify their student status and that sufficient funds are not available. If you are interested in obtaining such assistance and need travel support, send a letter before May 22, 1993 describing your situation and needs to: Larry Eshelman, Philips Laboratories, 345 Scarborough Road, Briarcliff Manor, NY 10510. Address questions to: lje at philabs.philips.com. To Register: Early registration is recommended. There are four ways you may register. Complete and mail the attached form or phone (217)244-7659 to register. Please be sure to call our office if your registration may be late in arriving. You may also FAX your registration to (217)333-9561. You may receive an e-mail registration by contacting loric at ux1.cso.uiuc.edu If you register by phone, fax, or e-mail, please remember to send a copy of the registration form with your payment to the Accounting Business Office within one week. Should you have additional questions, please call Lori Costello at 217/333-2888 or e-mail loric at ux1.cso.uiuc.edu. ---------------------------------------------- REGISTRATION FORM: The 5th International Conference on Genetic Algorithms July 17-21, 1993 UFAS Acct. #1-3-63141-0660 Four Easy Ways To Register 1. Fill out the form and mail with payment to: University of Illinois at Urbana-Champaign Accounting Business Office, Room 162 Henry Administration Building, 506 South Wright Street, Urbana, IL 61801. 2. Call 217-244-7659 and the registration team will take your registration over the phone. 3. Call 217-333-9561 to FAX your registration. 4. E-mail: receive an e-mail form by contacting loric at ux1.cso.uiuc.edu. The deadline for e-mail registrations and to receive all e-mail registration fees is July 9, 1993. IF YOU REGISTER BY PHONE, FAX, OR E-MAIL: Please remember to send a hard copy of the registration form with your payment to the Accounting Business Office within one week of registration. Registration/Badge Information Please print or type __________________________________________________________________ Last Name First Name MI __________________________________________________________________ Affiliation/Business __________________________________________________________________ Address __________________________________________________________________ City State Zip __________________________________________________________________ Country __________________________________________________________________ Business Phone Home Phone REGISTRATION FEES: (all figures in US Dollars) Indicate your selection Conference Registration Fee Registration before 6/12/93 On or after 6/12/93 Participant $250 Participant $295 Student* $100 Student* $125 Tutorial for July 17 Before 6/12/93 On or after 6/12/93 Participant $75 Participant $95 Student $25 Student $50 Please specify choice: Tutorial I:__________ Tutorial II: __________ Tutorial III: __________ Banquet Tickets** Adult $30 # of tickets_______ amount_______ Child $10 # of tickets_______ amount_______ Additional Reception Tickets** Saturday $10 # of tickets_______ amount_______ Total Payment ________________________(U.S. Dollars) Method of Payment ______ Check enclosed (make payable to the University of Illinois, US banks only, send check with form to Accounting Business Office) ______ I prefer to charge on credit card Visa______ Mastercard______ American Express______ Card Number__________________________________ Exp. Date__________ Card Holder Signature______________________________________________ *Students must have university student ID at registration **Please purchase additional tickets now---you will be unable to buy them upon arrival PLEASE MAIL THIS FORM WITH YOUR PAYMENT TO: University of Illinois at Urbana-Champaign Accounting Business Office, Room 162 Henry Administration Building 506 South Wright Street Urbana, IL 61801 From mao at cps.msu.edu Thu Apr 15 22:08:43 1993 From: mao at cps.msu.edu (Jianchang Mao) Date: Thu, 15 Apr 93 22:08:43 EDT Subject: New Book Announcement Message-ID: <9304160208.AA08016@pixel.cps.msu.edu> Dear connectionists, A new book, "Markov Random Fields: Theory and Application", edited by Drs. Rama Chellappa and Anil Jain, has been published by Academic Press, Inc. recently. This book contains chapters written by many distinguished researchers in the field. It represents the work done by most of the leading researchers in the world and should be a good reference text for engineers, computer scientists, applied statisticians and mathematicians, and physicists who are interested in the basic research issues and state-of-the-art in MRF models. The link between Markov random field and neural network models has been investigated by a number of researchers. The inherent parallel nature of the MRF algorithms can be suitably mapped onto an artificial neural network architecture. Therefore, this book will be a good reference text for neural network researchers too. Best, Jianchang Mao Computer Science Department Michigan State University East Lansing, MI 48824, USA From soller at asylum.cs.utah.edu Fri Apr 16 15:47:30 1993 From: soller at asylum.cs.utah.edu (Jerome Soller) Date: Fri, 16 Apr 93 13:47:30 -0600 Subject: Utah Workshop on the Applications of Intelligent and Adaptive Systems Message-ID: <9304161947.AA06896@asylum.cs.utah.edu> The University of Utah Cognitive Science Group's Industrial Advisory Board presents the first Utah Workshop on the "Applications of Intelligent and Adaptive Systems." This will be held at the Salt Lake City VA Medical Center's multipurpose room, Building 8, on May 10th. This event is free and open to the public. A listing of speakers, titles, abstracts, e-mail addresses, phone numbers, parking information, etc.., is provided at the end of this notice. For listings of relevant publications, biographical sketches of the speakers, or a hard copy of a map of the VA campus and appropriate parking, contact Jerome Soller (soller at asylum.cs.utah.edu,582-1565, ext. 2469). Hopefully, we will have a videotape of this event available public domain at a later point. This workshop complements the yearly Psychology Department's William F. Prokasy Lecture by Dr. Irving Biederman, Head of the Cognitive and Behavioral Neuroscience Program at the University of Southern California. Dr. Biederman will speak on Tuesday, May 11, at 5:00 p.m. in BEH SCI 110 at the University of Utah. The title is "Shape Recognition in Mind and Brain." The official notice from Kim Poulson is included after the workshop description. Summary (abstracts and contact information are provided at the end of this notice): Talk 1: 10:00-10:45 The Utah State University Space Dynamics Laboratory, An Introduction Presented by J Steven Hansen, Ph.D. Director, Instrument and Data Evaluation Center Space Dynamics Laboratory Associate Research Professor, Department of Electrical and Computer Engineering Department of Physics Utah State University Talk 2: 10:45-11:30 Active Noise and Vibration Control: Structures, Algorithms, and Applications Scott C. Douglas, Ph.D. Department of Electrical Engineering University of Utah Talk 3: 11:30 - 12:15 A COMPUTERIZED DECISION SUPPORT SYSTEM FOR CRITICAL CARE: MANAGEMENT OF MECHANICAL VENTILATION IN PATIENTS WITH ARDS Thomas D. East, Ph.D.: Director of informatics research in the pulmonary division at LDS Hospital(Intermountain Health Care). Associate professor of anesthesiology, bioengineering and medical informatics at the University of Utah. Lunch break: 12:15-1:45 Talk 4: 1:45-2:30 "Neural Networks for Classification, Signal Processing, and Control in Patient Monitoring" Dwayne Westenskow, Ph.D. Acting Director of Institute of Life Support in Space and Professor, U. of Utah Department of Anesthesiology (additional appointments in Bioengineering, Surgery, and Medical Informatics). Talk 5: 2:30-3:15 Towards a General Self-Organizing Learning Model Tony Martinez, Ph.D., Director of the Neural Networks and Machine Intelligence Research Group, Brigham Young University Assistant Professor, Department of Computer Science and Department of Electrical and Computer Engineering, Brigham Young University. Talk 6: 3:15-4:00 Neil Cotter, Ph.D. Consulting Engineer, Geneva Steel Research Assistant Professor, Electrical Engineering, University of Utah "Neural Networks, Fuzzy Logic, and Triangulation in Process Control" (801-227-9865) Sincerely, Dick Burgess, U. of Utah Department of Physiology and Program Director, U. of Utah Cog. Sci. Group (801-581-4072) Dale Sanders, Chairman of Industrial Advisory Board to U. of Utah Cognitive Science Group and Senior Technical Member, TRW Corporation (dsanders at bmd.trw.com, 801-625-8343) Robert L. Angell, Principal, Applied Information and Management Systems and Small Business Representative to U. of Utah Cognitive Science Group (bangell at cs.utah.edu, 801-583-8544) Jerome B. Soller, VA GRECC and U. of Utah Department of Computer Science (soller at asylum.cs.utah.edu, 801-582-1565, ext. 2469) Abstracts: ---------------------------------------------------------------------- Active Noise and Vibration Control: Structures, Algorithms, and Applications Scott C. Douglas, Ph.D. Department of Electrical Engineering University of Utah Active noise and vibration control is a method for cancelling unwanted sound or vibration by generating and introducing an equal-but-opposite acoustic signal into the noise environment. Current research and application developments in this field include active mufflers for automobiles, active quieting of machine noise on factory floors, active vibration mounts for airplane engines, active noise suppressors for air ducts, and active suppression of wall vibration for apartment dwellings. In this talk, I will provide an overview of the technology needed for active noise control systems. In particular, I will discuss the digital signal processing hardware and multichannel adaptive control algorithms required for noise cancellation across large acoustic regions. Results from an active noise suppression system for quieting an air conditioner compressor will be presented. ------------------------------------------------------------------------ Neil Cotter, Ph.D. Consulting Engineer, Geneva Steel Research Assistant Professor, E.E. Department, University of Utah "Neural Networks, Fuzzy Logic, and Triangulation in Process Control" (801-227-9865) Many process control problems in industry require the approximation of nonlinear functions of several variables. This presentation will include a tutorial showing that the following approximation methods are structurally similar to Fourier series: linear regression, neural networks, radial basis functions, and fuzzy logic. The speaker will contrast these methods with a practical interpolation method called triangulation. -------------------------------------------------------------------------- "Neural Networks for Classification, Signal Processing, and Control in Patient Monitoring" Dwayne R. Westenskow, Ph.D. Department of Anesthesiology (801-581-6393, drw at cc.utah.edu) Artificial neural networks learn from examples to construct a function which maps input variables to a desired output. The mapping provides closed-loop control where the inputs are the variables to be controlled, and the output is the drive signal for an actuator. Neural network control will be illustrated with the truck backing up example, introducing the concept of supervised learning. The neural network mapping similarity provides for the classification of data, as will be illustrated with an intelligent anasthesia alaram system. Because the mapping function extrapolates between individual data points, the neural network provides signal processing, i.e., filtering and noise and artifact rejection. This will be illustrated by showing the neural network processing of oscillometric blood pressure curves and cardiac output by thermal dilution. In both of these examples, the neural network provides a nonlinear mapping which compensates for the overestimation at low values and underestimation at high values, which occurs with traditional linear algorithms. Success in processing Doppler signals for the detection of air embolism illustrates how the mapping function is constructed using training data rather than expert knowledge. --------------------------------------------------------------------- Dr. Tony Martinez, Director of the Neural Networks and Machine Intelligence Research Group, Brigham Young University Assistant Professor, Department of Computer Science and Department of Electrical and Computer Engineering, Brigham Young University, Provo, UT Towards a General Self-Organizing Learning Model (martinez at cs.byu.edu, 801-378-6464) A new class of connectionist architectures is presented called ASOCS (Adaptive Self-Organizing Concurrent Systems). ASOCS models support efficient computation through self-organized learning and parallel execution. Learning is done through the incremental presentation of rules and/or examples. Data types include Boolean and multi-state variables; recent models support analog variables. The model incorporates rules into an adaptive logic network in a parallel and self organizing fashion. The system itself resolves inconsistencies and generalizes as the rules are presented. After an introduction to the ASOCS paradigm, the talk introduces current research thrusts which significantly increase the power and applicability of ASOCS models. Current application targets include adaptive network routing, speech recognition, automated document updating, and general classification problems. ------------------------------------------------------------------------ Author Information: Thomas D. East, Ph.D., Pulmonary Division, LDS Hospital, 8th Ave and C St., Salt Lake City, UT, 84143, 801-321-3503 phone, 801-321-1671 fax, teast at fenta.med.utah.edu Audio Visual Media used: 35 mm slide projector and VHS video projector. A COMPUTERIZED DECISION SUPPORT SYSTEM FOR CRITICAL CARE: MANAGEMENT OF MECHANICAL VENTILATION IN PATIENTS WITH ARDS T.D. East, A.H. Morris, C.J. Wallace, A. T. Kinder, W.D. Littman*, J.S. Gochberg* Pulmonary Division, LDS Hospital,Salt Lake City, Utah 84143 * ACT/PC, 6501 Watts Road, Suite 115, Madison, WI 53719 Thomas D. East,Ph.D.: Associate professor of anesthesiology, bioengineering and medical informatics at the University of Utah. Director of informatics research in the pulmonary division at LDS Hospital. MEBE and Ph.D. in bioengineering from the U of U. My research interests are in the applications of computers to critical care. In particular much of my work has been in the area of rule based decision support systems and knowledge engineering. The care of critically ill patients is increasingly complex and clinicians frequently suffer from information overload. It is difficult, if not impossible to assess all this information and generate a systematic and reasonable therapy plan. Computerized decision support systems can assist the clinician with many of the tasks such as the iterative management of mechanical ventilation. This decision support not only standardizes care but may improve the quality of care by reducing mistakes. This standardization of care also makes it possible to thoroughly characterize the current treatment process in order to compare it to a proposed new therapy as part of an ongoing continuous quality improvement (CQI) program. A computerized decision support system for the management of mechanical ventilation (respiratory evaluation, oxygenation, ventilation, weaning and extubation) in patients with adult respiratory distress syndrome has already been developed and clinically validated at the LDS Hospital (1, 2) . The protocol logic was developed using our existing consensus generating physician group and was implemented on the HELP system (3) . The computerized decision support system was used for over 35,000 hours in 111 Adult Respiratory Distress Syndrome patients and has controlled decision making 95% of the 24 hour day. The survival rate was 67%, higher than the expected 31-33% from historical data (4, 5) , p < 0.05. These results have demonstrated that computerized decision support for critical care is feasible. We are in the process of conducting a prospective randomized clinical trial to test efficacy of computerized protocols in 400 patients with ARDS at two different clinical sites; KDMC a county hospital in the Watts district of Los Angeles, CA and Hermann Hospital, a private hospital in Houston affiliated with University of Texas Medical School (H0: There is no difference in efficacy between protocol and non-protocol controlled critical care). The knowledge base (set of protocol logic rules) was transferred from the HELP system at LDS Hospital to a PC based ICU computer system known as ARGUS Windows (ACT/PC, Madison , WI). ARGUS Windows runs under QNX V4.1 and QNX windows V2.03. The rules were implemented using a rule based decision support engine designed by ACT/PC. The engine is a finite state automata written in C for QNX and QNX Windows. The ARGUS Windows system has been installed at all 12 beds of the surgical ICU at KDMC. This system is now in routine use for respiratory care charting and the decision support system has been used to successfully care for 10 ARDS patients in a pilot study of feasibility. In the randomized trial, will define efficacy using a hierarchical four level approach; Efficacy F a)Survival, b) Length of ICU Stay, c) Morbidity, d) Incidence and severity of barotrauma. Generalizablity of the computerized decision support system will be determined by examining; 1) Percent of total time in the trial during which protocols controlled patient care. 2) Number of protocol instructions which were not followed. 3) Number of objections to protocol logic which, based on medical evidence, forced a change in the logic. To our knowledge this is the first prospective randomized clinical trial designed to test the impact of computerized critical care decision support on patient outcome. References: 1. East T, et al. Int J Clin Monit Comput 1992;8:263-269. 2. Morris AH, et al. Am Rev Respir Dis 1992;145(4):A184. 3. Pryor TA, et al. The HELP system development tools. In: Implementing health care information systems. New York: Springer-Verlag, 1989: 365-383. 4. Zapol WM, et al. The adult respiratory distress syndrome at Massachusetts General Hospital, Etiology progession and survival rates,1978-1988. In: Zapol WM, Lemaire F, ed. Adult Respiratory Distress Syndrome. New York: Marcel Dekker, Inc, 1991: 367-380. 5. Artigas A, et al. Clinical presentation, prognostic factors, and outcome of ARDS in the European Collaborative Study (1985-1987).In:Same book as ref 4, 1991: 37-63. Acknowledgements: This work was supported by NHLBI grant #HL36787, AHCPR grant HS06594, Siemens Ventilators, ACT/PC, the Respiratory Distress Syndrome Foundation and the Deseret Foundation (LDS Hospital). My biographical sketch: Thomas D. East,Ph.D.: Associate professor of anesthesiology, bioengineering and medical informatics at the University of Utah. Director of informatics research in the pulmonary division at LDS Hospital. MEBE and Ph.D. in bioengineering from the U of U. My research interests are in the applications of computers to critical care. In particular much of my work has been in the are of rule based decision support systems and knowledge engineering. ------------------------------------------------------------------------ The Utah State University Space Dynamics Laboratory, An Introduction Presented by Dr. J Steven Hansen (801-750-4850, jsh at sdl.usu.edu) Director, Instrument and Data Evaluation Center Space Dynamics Laboratory Associate Research Professor, Department of Electrical and Computer Engineering Department of Physics Utah State University, Logan, Utah Abstract This talk will provide description of the Space Dynamics Laboratory and its capabilities, particularly in the areas of data, signal, and image processing. The presentation will include a brief history of SDL over the past 30 years, an overview of the past and current projects at SDL and the Instrument and Data Evaluation Center (IDEC), a look at the current computing and image/signal processing capabilities IDEC. A look at the future and particular area of possible interest to the community will be addressed. ------------------------------------------------------------------------ Lunch: A group of us will go to lunch at a our own expense. If you wish to join that group, contact Jerome Soller to have a spot reserved. Directions to the VA Hospital: For directions, call 582-1565, and ask for learning resources. The address is 500 Foothill Boulevard Parking: The VA has limited parking for visitors behind building 8. If you come in the main entrance, make a right past building 1 and 14, continue through one of the staff parking lots. Make a right before reaching the staff parking lot between building 5 and 8. You should pass between buildings 8 and 9, and park behind building eight (not nine). Rough Map: Dash lines represent a desired path. Main Entrance:-- 1 | | 14 | 5 Don't Park | Don't Park Here Here | ----------| |---|Don't | Park | Here | 9 | 8 6 |___ Don't Park Don't Park Park Here Here Here It is advisable to have a map of the VA campus mailed to you, and that map and postage will be free of charge if Jerome Soller is notified within the next two weeks. If parking is tight, you may need to park nearby in Research Park (leave ample time for that). If you are at the University of Utah, you can catch a VA shuttle from the medical school or research park directly to the VA hospital. University shuttles run to university parking, which is across from the VA hospital, and to the LDS Insitute, which is also across the VA hospital. Registration: No registration is required. However, it would be greatly appreciated if you would rsvp by the end of April so we can estimate the attendance and set up the room accordingly. The room can comfortably seat 80 people with good workspace. Afterwards: We hope that speakers will provide some form of handouts. We hope to have a video tape record of this workshop, which will be public domain. *************************************************************************** From kainen at cs.UMD.EDU Tue Apr 13 21:02:48 1993 From: kainen at cs.UMD.EDU (Paul Kainen) Date: Tue, 13 Apr 93 21:02:48 -0400 Subject: Intelligent systems in Washington, DC (not an oxymoron!) Message-ID: <9304140102.AA21779@tove.cs.UMD.EDU> Public lectures on intelligent systems, to be given in Washington, DC, will include the topics of neural networks, fuzzy logic, robotics and expert systems. Speakers include Lotfi Zadeh, Thomas Saaty, Bernardo Huberman, Rodney Brooks and Marc Jeannerod. The series starts Apr. 21 and continues to June 9 at the Smithsonian's Campus on the Mall. All talks are scheduled Wednesdays from 8pm to 9:30pm. Call 202-357-3030 to register. More information is available from kainen at cs.umd.edu. From ncai at aaai.org Tue Apr 13 11:58:40 1993 From: ncai at aaai.org (NCAI) Date: Tue, 13 Apr 93 08:58:40 PDT Subject: No subject Message-ID: <9304131558.AA10733@aaai.org> Important addendum to AAAI-93 Conference Brochure regarding the Robot Building Event. Note that preregistration is mandatory for the Robot Building Event, and there is a $50 lab fee. In addition, student scholarships are available. From lpratt at franklinite.Mines.Colorado.EDU Tue Apr 13 17:17:09 1993 From: lpratt at franklinite.Mines.Colorado.EDU (Lorien Y. Pratt) Date: Tue, 13 Apr 93 14:17:09 -0700 Subject: Mike Mozer to speak in Colorado Machine Learning series Message-ID: <9304132117.AA06578@franklinite.Mines.Colorado.EDU> The spring, 1993 Colorado Machine Learning Colloquium Series presents: Dr. Michael C. Mozer Department of Computer Science University of Colorado, Boulder Neural network approaches to formal language induction Thursday, April 22, 1993 Room 110, Stratton Hall, on the CSM campus 5:30 pm ABSTRACT I will describe several recent approaches to formal language induction using neural networks. In contrast to 'connectoplasm' approaches that make use of generic network architectures, the work I'll advocate incorporates prior symbolic constraints to bias solutions learned by the network. One network I'll describe, the demon architecture (Mozer & Das, 1993), learns symbol rewrite operations that allow it to construct parse trees for strings in LR(0) context-free grammars. Another network, called SLUG (Mozer & Bachrach, 1991), processes regular languages and is based on an alternative and concise representation of some regular languages called an update graph. Both networks are trained on negative as well as positive examples, and, because of their specialized symbolically-constrained architectures, generalize extremely well. Additionally, their weights can often be interpreted in terms of symbolic rules. Suggested background readings: SLUG: A Connectionist Architecture for Inferring the Structure of Finite-State Elements; Michael C. Mozer and Jonathan Bachrach. Machine Learning, volume 7, 1991, pages 139-160; A Connectionist Symbol Manipulator that Discovers the Structure of Context-Free Languages. Michael C. Mozer and Sreerupa Das. To appear in: C. L. Giles and S. J. Hanson and J. D. Cowan (eds.) Advances in Neural Information Processing Systems V. San Mateo, CA: Morgan Kauffmann, 1993. These readings are available on reserve at the Arthur Lakes Library at CSM. Ask for the reserve package for MACS570, subject: Mozer. Non-students can check materials out on reserve by providing a driver's license. Open to the Public Refreshments to be served at 5:00pm, prior to talk For more information (including a schedule of all talks in this series), contact: Dr. L. Y. Pratt, CSM Dept. of Mathematical and Computer Sciences, lpratt at mines.colorado.edu, (303) 273-3878. The speaker may be contacted at: mozer at dendrite.cs.colorado.edu. Sponsored by: THE CSM DEPARTMENTS OF MATHEMATICAL AND COMPUTER SCIENCES, GEOPHYSICS, DIVISION OF ENGINEERING, AND CRIS* *The Center for Robotics and Intelligent Systems at the Colorado School of Mines From mathiak at sysc.PDX.EDU Tue Apr 20 00:27:57 1993 From: mathiak at sysc.PDX.EDU (mathiak@sysc.PDX.EDU) Date: Mon, 19 Apr 93 21:27:57 PDT Subject: 1993 World Congress on Neural Networks (Portland, Oregon, July 11-14) Message-ID: <9304200427.AA02064@orr.sysc.pdx.edu> -------------------------------------------------------------------- The World Congress on Neural Networks will be held in Portland, Oregon, July 11-14, 1993 (Oregon Convention Center). In this posting we provide: * the e-mail version of our registration form, * information about tutorials/sessions being planned, about housing and about WCNN'93 proceedings. More detailed information about WCNN'93 will be sent with the registration receipt. Quick information is available via e-mail regarding housing, papers, registration, sessions and tutorials at the following e-mail addresses: housing at wcnn93.ee.pdx.edu papers at wcnn93.ee.pdx.edu registration at wcnn93.ee.pdx.edu sessions at wcnn93.ee.pdx.edu tutorials at wcnn93.ee.pdx.edu . We are looking forward to seeing you at the conference! Sincerely, -------------------------------------------------------------------- Prof. George G. Lendaris email: lendarisg at wcnn93.ee.pdx.edu General Chair FAX: (503) 725-4882 Portland State University Portland, Oregon 97207 -------------------------------------------------------------------- - 1 - World Congress on Neural Networks 1993, Portland REGISTRATION FORM ================= Reg. Fee Reg. Fee Reg. Fee before before after Jan 15,93 Jun 15,93 Jun 15, 93 INNS or Cooperating Society Member $175.00 $270.00 $350.00 $ ........... Society Member Number: ................... Non-Members $275.00 $370.00 $450.00 $ ........... (Includes 1993 INNS membership and 1 year subscription of the INNS journal Neural Networks) Full-Time Student $50.00 $75.00 $95.00 $ ........... (Student registration and verification from department chairman required.) Spouse/Guest $50.00 $60.00 $70.00 $ ........... TUTORIAL REGISTRATION ===================== (Fee includes 4 tutorials, notes on all tutorials and lunch) (Please circle 4 preferences, see list below: A B C D E F G H I J K ) Members or Non-Members $225.00 $295.00 $345.00 $ ........... Student $50.00 $75.00 $95.00 $ ........... (Student registration and verification from department chairman required.) TOTAL $ ====================== Please print or type: Name: ............................................................... (As you would like to appear on badge) Title: ........................ Organization: ....................... (As you would like to appear on badge) Adress: ............................................................. City: ................... State: ..... Zip: ........ Country: ....... Bus.Tel: ....................... FAX: ............................... Spouse/Guest Name (if fee paid): .................................... (Complete only if paying the Spouse/Guest Registration fee - includes 2 receptions only) - 2 - IMPORTANT: Please indicate any disability for special assistance .................................................................... .................................................................... Unless the INNS is advised prior to the meeting of any special requirements, we cannot guarantee that service will be available. Please complete this form and return it with check or money order to: Attention: WCNN'93 Portland Meeting Registration 875 Kings Highway, Suite 200 West Deptford, NJ 08096 Tel: (609) 845-1720 FAX: (609) 853-0411 Checks must made payable in US Dollars and issued by a US correspon- dent bank. Each registrant is responsible for any bank charges. Check with your local bank before processing payment. Credit Card Information: .... I wish to pay for my fees by credit card. Circle one: Visa Master Card Account #: ............................ Expiration Date: ............ Signature: .......................................................... Tutorials will be offered on Sunday, July 11, 1993. Each two hour tutorial will be offered twice. A. Cognitive Neuroscience (Robert Desimone) B. Structural and Mathematical Approaches to Signal Processing (S.Y. Kung) C. Adaptive Resonance Theory (Gail Carpenter) D. Practical Applications of Neural Network Theory (Robert Hecht-Nielsen) E. Cognitive Science (David Rumelhart) F. Neural Fuzzy Systems (Fred Watkins) G. Neurobiology and Chaos (Walter Freeman) H. Neural Control and Robotics (Michael Kuperstein) I. Neural Computation and VLSI (Eric Schwartz) J. Biological Vision (V.S. Ramachandran) K. Supervised Learning (Hal White) !!! ATTENTION !!! If you must cancel your registration, all requests must be received in writing by Ms. Connie Rebert, Registration Supervisor, 875 Kings High- way, Suite 200, West Deptford, NJ 08096, no later than Monday, June 1, 1993. All fees paid will be refunded minus a $30.00 processing fee. THERE WILL BE NO REFUNDS AFTER THE JUNE 1ST DEADLINE. --------------------------------------------------------------------- You may make a hardcopy of this form and mail it to the above address. --------------------------------------------------------------------- -------------------------------------------------------------------- World Congress on Neural Networks 1993, WCNN'93 Portland, Oregon, Convention Center July 11-15, 1993 TUTORIALS ========= Tutorials will be offered on Sunday, July 11, 1993. Each two hour tutorial will be offered twice. A. Cognitive Neuroscience (Robert Desimone, National Instituteof Mental Health) B. Structural and Mathematical Approaches to Signal Processing (S.Y. Kung, Princeton University) C. Adaptive Resonance Theory (Gail Carpenter, Boston University) D. Practical Applications of Neural Network Theory (Robert Hecht-Nielsen, HNC Corporation) E. Cognitive Science (David Rumelhart, Stanford University) F. Neural Fuzzy Systems (Fred Watkins, HyperLogic Corporation) G. Neurobiology and Chaos (Walter Freeman, University of California) H. Neural Control and Robotics (Michael Kuperstein, Symbus Technology) I. Neural Computation and VLSI (Eric Schwartz, Vision Applications) J. Biological Vision (V.S. Ramachandran, University of California) K. Supervised Learning (Hal White, University of California) We are pleased to announce that in addition to the main program, we will be offering special tracks in conjunction with the Society of Manufacturing Engineers on Manufacturing (SME/INNS Track). -------------------------------------------------------------------- -------------------------------------------------------------------- World Congress on Neural Networks 1993, WCNN'93 Portland, Oregon, Convention Center July 11-15, 1993 SESSIONS ======== Plenary Speakers include: * Federico Faggin, Real-Time-On-Chip Learning in Analog VLSI Networks * Stephen Grossberg, 3-D Vision and Figure-Ground Pop-Out * Bart Kosko, Neural Fuzzy Systems * Kumpati Narendra, Intelligent Control Using Neural Networks * Wolf Singer, Coherence as an Organizing Principal of Cortical Function Session Topics | Session Chairs ----------------------------------------------------------------- - Applications | J. Dayhoff, R. Hecht-Nielsen - Associative Memory | J. Andersen, J. Taylor - Biological Sensory-Motor Control| A. Barto, S. Kelso - Biological Vision | C. Malsburg, V.S. Ramachandran - Cognitive Neuroscience | R. Desimone, L. Optician - Electro-Optical Neurocomputers | L. Giles, H. Szu - Intelligent Neural Systems | S. Grossberg, D. Levine - Local Circuit Neurobiology | J. Byrne, J. Houk - Machine Vision | R. Chellappa, K. Fukushima - Neural Fuzzy Systems | W. Daugherty, B. Kosko - Neurodynamics | S. Amari, H. White - Pattern Recognition | T. Kohonen, D. Specht - Robotics and Control | M. Kuperstein, K. Narendra - Signal Processing | S.Y. Kung, B. Widrow - Speech and Language | M. Cohen, D. Rumelhart - Supervised Learning | L. Cooper, P. Werbos - Unsupervised Learning | G. Carpenter, E. Oja (TENTATIVE) PROPOSED SESSION SCHEDULE ========================= The numbers associated with sessions refer to the list on the registration form. Sunday Monday Tuesday Wednesday Thursday 7/11/93 7/12/93 7/13/93 7/14/93 7/15/93 ---------------------------------------------------------------------- Morning Sessions, starting 8:00 am Tutorials (1) (10) (3) (8) Biological Cognitive Speech and Pattern Vision Neuro- Language Recognition science (17) (16) (5) (14) Applications Associative Robotics and Neurodynamics Memory Control SME/INNS (17) (6) (4) Track Applications Supervised Biological Learning Sensory Motor Afternoon Sessions, starting 1:30 pm (11) (7) (6) (13) Intelligent Unsupervised Supervised Signal Neural Learning Learning Processing Systems (12) (9) (2) (15) Neural Local Curcuit Machine E-O Neuro- Fuzzy Neurobiology Vision Computers Systems IFSA/INNS Track Plenary Talks Kosko Grossberg Reception Narendra Faggin Gov't Panel SIG Meeting -------------------------------------------------------------------- -------------------------------------------------------------------- World Congress on Neural Networks 1993, Portland HOUSING ======= Housing application forms will be sent to each registrant. In the mean time for your information the following are the room rates at the hotels that are holding blocks of rooms for the WCNN'93. 1) Conference Headquarter Hotel (walking distance to convention center): Red Lion/Lloyd Center $110.00 1-2 people, $15.00 each additional person 2) Other hotels within walking distance : Best Western/Convention Center $74.00 Flat Rate Holiday Inn/Downtown $72.00 1-2 people, $10 each additional person 3) Downtown Hotels (short ride on light rail train [called MAX]): Hilton Hotel $104.00 1-2 people, $20 each additional person Marriott Hotel $116.00 Flat Rate If you wish to reserve a room before you receive the registration, or if need further information about the Portland metropolitan area, please contact: Portland Oregon Visitor Association (POVA) Attention: Silvia Robles, Housing Department 26 SW Salmon Portland, OR 97204 STUDENT HOUSING =============== For July 11-14, 1993, there is still a limited number of rooms for students available: - Montgomery Hall, PSU Campus - single rooms - prices: $18.00 without meal $34.00 with meal (breakfast, lunch, dinner) - deposit: one night stay (send check in $US or VISA number to address below) ! PLEASE NOTE: ! ! All requests for student housing MUST BE PROCESSED BEFORE ! ! MAI 31, 1993. There is NO DEPOSIT REFUND for cancellations ! ! after MAI 31, 1993. ! For reservation and information please contact WCNN'93, Student Housing Systems Science PhD Program Portland State University Portland, OR 97201-0751 USA Phone : (503) 725-4961 FAX : (503) 725-4882 e-mail: housing at wcnn93.ee.pdx.edu -------------------------------------------------------------------- -------------------------------------------------------------------- World Congress on Neural Networks 1993, Portland PROCEEDINGS =========== 1) The WCNN`93 proceedings will be available to all WCNN'93 attendies at the Oregon Convention Center. 2) After the WCNN`93 the proceedings will be mailed to all who did register but could not attend. 3) The WCNN`93 proceedings will be available and mailed to requestors who did not register. The price has not been established yet. -------------------------------------------------------------------- From marwan at sedal.sedal.su.OZ.AU Wed Apr 21 13:52:14 1993 From: marwan at sedal.sedal.su.OZ.AU (Marwan Jabri) Date: Wed, 21 Apr 93 12:52:14 EST Subject: Research Fellowship position Message-ID: <9304210252.AA03798@sedal.sedal.su.OZ.AU> Research Fellowship (Fixed-term) Deadline 29 April 1993. Systems Engineering and Design Automation Laboratory Department of Electrical Engineering The University of Sydney Reference No: C14/12 The Fellow will work with the Systems Engineering and Design Automation Laboratory (SEDAL) at Sydney University Electrical Engineering. SEDAL currently groups 2 academic staff, 5 research staff and ten postgraduate students. It has projects in the areas of pattern recognition for implantable devices, VLSI systems and multi-chip modules, time series prediction, knowledge integration and continuous learning, and VLSI computer-aided design. The Research Fellow position is aimed at: contributing to the research program; helping with the supervision of postgraduate students; supporting some management aspects of SEDAL; providing occasional teaching support. The appointee should have a PhD or equivalent industry research and development experience. It is desirable that the appointee has a background in one or more of the following areas: machine intelligence and connectionist architectures; microelectronics; pattern recognition and classification. It is also desirable that the appointee be able to join the group before July 1993. Appointment will be for three years. Membership of a superannuation scheme is a condition of employment for new appointees. For further information, please contact Dr M Jabri on (61-2) 692 2240, fax (61-2) 660 1228, Email: marwan at sedal.su.oz.au. Salary: $41,000 - $48,688 per annum Applications, quoting Reference No, including curriculum vitae, list of publications, and the names, addresses, fax and phone nos of two referees to the Assistant Registrar (Appointments), Staff Office (K07), University of Sydney, NSW 2006 Australia by 29 April 1993. From cima at tce.ing.uniroma1.it Wed Apr 21 07:57:34 1993 From: cima at tce.ing.uniroma1.it (cima@tce.ing.uniroma1.it) Date: Wed, 21 Apr 1993 13:57:34 +0200 Subject: No subject Message-ID: <9304211157.AA06109@tce.ing.uniroma1.it> Dear Fellow Connectionists, I have been involved for some years in research about Cellular Neural Networks (CNNs), i.e., in the broadest sense, NNs where neurons are only connected to neighboring units. CNNs can be easily realized in IC technique by profiting of their spatially defined structure. Such networks, first introduced by Prof.L.O. Chua, of U.C. at Berkeley have been successfully applied to many image processing tasks. I have served in the scientific committees of the past IEEE International Workshops on CNNs and their Applications in Budapest in 1990, and in Munich in 1992. We would like to get in contact to other researchers working at similar topics, so as to establish a more specialistic mailing list to cooperate on CNN research. At present we are working on the following topics: - gradient descent and genetic learning for CNNs; - generalization and information storage in CNN learning; - simulation of physical systems governed by partial differential equations; - cellular networks of oscillators. Among our publications concerning CNNs are the following: 1) M. Balsi, "Generalized CNN: Potentials of a CNN with Non-Uniform Weights", Proceedings of IEEE Second International Workshop on Cellular Neural Networks and their Applications (CNNA-92), Munich, Germany, Oct. 14-16, 1992, 129-134 2) A. Barone, M. Balsi, V. Cimagalli, "Cellular Networks of Oscillators", Proceedings of CNNA-92, 246-251 3) T. Roska, C.W. Wu, M. Balsi, L.O. Chua, "Stability and Dynamics of Delay-Type General and Cellular Neural Networks", IEEE Trans. on Circuits and Systems 39(6), 487-490 (1992) 4) V. Cimagalli, M. Bobbi, M. Balsi, "MODA: Moving Object Detecting Architecture", IEEE Trans on Circuits and Systems, II, 40(3) (1993). 5) T. Roska, C.W. Wu, M. Balsi, L.O. Chua, "Stability of CNNs with Dominant Nonlinear and Delay-type Templates", IEEE Trans on Circuits and Systems, II, 40(3) (1993). 6) M. Balsi, "Stability of CNNs with One-Dimensional Templates", to be published in Intl. J. of Circ. Th. and Appl. (1993). We can provide hardcopies of these papers upon request. I shall be looking forward for your replies. Yours, Prof. Valerio Cimagalli Dept. of Electronic Engineering "La Sapienza" University of Rome via Eudossiana, 18 I-00184 Rome ITALY fax +39-6-4742647 From meeden at silver.ucs.indiana.edu Wed Apr 21 12:49:31 1993 From: meeden at silver.ucs.indiana.edu (Lisa Meeden) Date: Wed, 21 Apr 1993 11:49:31 -0500 Subject: Paper on connectionist robot control Message-ID: The following paper is available in the neuroprose archive. It will also appear in the "Proceedings of the Fifteenth Annual Conference of the Cognitive Science Society". Unfortunately for those unable to use FTP, we cannot provide hard copies. Emergent Control and Planning in an Autonomous Vehicle Lisa Meeden* Gary McGraw*+ Doug Blank* *Department of Computer Science +Center for Research on Concepts and Cognition Indiana University Abstract We use a connectionist network trained with reinforcement to control both an autonomous robot vehicle and a simulated robot. We show that given appopriate sensory data and architectural structutre, a network can learn to control the robot for a simple navigation problem. We then investigate a more complex, goal-based problem and examine the plan-like behavior that emerges. To obtain a copy: ftp cheops.cis.ohio-state.edu login: anonymous password: cd pub/neuroprose binary get meeden.robot.ps.Z bye Then at your system: uncompress meeden.robot.ps.Z lpr -P meeden.robot.ps From josh at faline.bellcore.com Thu Apr 22 16:01:12 1993 From: josh at faline.bellcore.com (Joshua Alspector) Date: Thu, 22 Apr 93 16:01:12 EDT Subject: telecom workshop paper summaries due May 14 Message-ID: <9304222001.AA15474@faline.bellcore.com> CALL FOR PAPERS International Workshop on Applications of Neural Networks to Telecommunications Princeton, NJ October 18-20, 1993 You are invited to submit a paper to an international workshop on applications of neural networks to problems in telecommunications. The workshop will be held in Princeton, New Jersey on October, 18-20 1993. This workshop will bring together active researchers in neural networks with potential users in the telecommunications industry in a forum for discussion of applications issues. Applications will be identified, experiences shared, and directions for future work explored. Suggested Topics: Application of Neural Networks in: Network Management Congestion Control Adaptive Equalization Speech Recognition Security Verification Language ID/Translation Information Filtering Dynamic Routing Software Reliability Fraud Detection Financial and Market Prediction Adaptive User Interfaces Fault Identification and Prediction Character Recognition Adaptive Control Data Compression Please submit 6 copies of both a 50 word abstract and a 1000 word summary of your paper by May 14, 1993. Mail papers to the conference administrator: Betty Greer, IWANNT*93 Bellcore, MRE 2P-295 445 South St. Morristown, NJ 07960 (201) 829-4993 (fax) 829-5888 bg1 at faline.bellcore.com Abstract and Summary Due: May 14 Author Notification of Acceptance: June 18 Camera-Ready Copy of Paper Due: August 13 Organizing Committee: General Chair Josh Alspector Bellcore, MRE 2P-396 445 South St. Morristown, NJ 07960-6438 (201) 829-4342 josh at bellcore.com Program Chair Rod Goodman Caltech 116-81 Pasadena, CA 91125 (818) 356-3677 rogo at micro.caltech.edu Publications Chair Timothy X Brown Bellcore, MRE 2E-378 445 South St. Morristown, NJ 07960-6438 (201) 829-4314 timxb at faline.bellcore.com Treasurer Anthony Jayakumar, Bellcore Events Coordinator Larry Jackel, AT&T Bell Laboratories Industry Liaisons Miklos Boda, Ellemtel Atul Chhabra, NYNEX Michael Gell, British Telecom Lee Giles, NEC Thomas John, Southwestern Bell Adam Kowalczyk, Telecom Australia Tadashi Sone, NTT University Liaisons S Y Kung, Princeton University Tzi-Dar Chiueh, National Taiwan University INNS Liaison Bernie Widrow, Stanford University IEEE Liaison Steve Weinstein, Bellcore Conference Administrator Betty Greer Bellcore, MRE 2P-295 445 South St. Morristown, NJ 07960 (201) 829-4993 (fax) 829-5888 bg1 at faline.bellcore.com ----------------------------------------------------------------------------- ----------------------------------------------------------------------------- International Workshop on Applications of Neural Networks to Telecommunications Princeton, NJ October 18-20, 1993 Registration Form Name: _____________________________________________________________ Institution: __________________________________________________________ Mailing Address: ___________________________________________________________________ ___________________________________________________________________ ___________________________________________________________________ ___________________________________________________________________ Telephone: ______________________________ Fax: ____________________________________ E-mail: _____________________________________________________________ I will attend | | Send more information | | Paper enclosed | | Registration Fee Enclosed | | ($350; $450 after Sept. 15; $150 students;) Please make sure your name is on the check (made out to IWANNT*93) Registration includes Monday night reception, Tuesday night banquet, refreshment breaks, AT&T tour, and proceedings available at the conference. Mail to: Betty Greer, IWANNT*93 Bellcore, MRE 2P-295 445 South St. Morristown, NJ 07960 (201) 829-4993 (fax) 829-5888 bg1 at faline.bellcore.com Deadline for submissions: May 14, 1993 Author Notification of Acceptance: June 18, 1993 Camera-Ready Copy of Paper Due: August 13, 1993 From john at dcs.rhbnc.ac.uk Fri Apr 23 05:25:32 1993 From: john at dcs.rhbnc.ac.uk (John Shawe-Taylor) Date: Fri, 23 Apr 1993 10:25:32 +0100 Subject: Paper on Neuroprose Message-ID: <12734.9304230925@csqx.cs.rhbnc.ac.uk> The following paper has recently been accepted to appear in IEEE Transactions on Neural Networks and has been placed in the Neuroprose archive as shawetaylor.symdisc.ps.Z. ----------------------------- Symmetries and Discriminability in Feedforward Network Architectures John Shawe-Taylor, Department of Computer Science, Royal Holloway, University of London Abstract: The paper investigates the effects of introducing symmetries into feedforward neural networks in what are termed Symmetry Networks. This technique allows more efficient training for problems in which we require the output of a network to be invariant under a set of transformations of the input. The particular problem of graph recognition is considered. In this case the network is designed to deliver the same output for isomorphic graphs. This leads to the question of which inputs can be distinguished by such architectures. A theorem characterising when two inputs can be distinguished by a Symmetry Network is given. As a consequence a particular network design is shown to be able to distinguish non-isomorphic graphs if and only if the graph reconstruction conjecture holds. To retrieve the file: unix> ftp cheops.cis.ohio-state.edu Connected to cheops.cis.ohio-state.edu. 220 cheops.cis.ohio-state.edu FTP server ready. Name: anonymous 331 Guest login ok, send ident as password. Password:neuron 230 Guest login ok, access restrictions apply. ftp> binary 200 Type set to I. ftp> cd pub/neuroprose 250 CWD command successful. ftp> get shawetaylor.symdisc.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for shawetaylor.symdisc.ps.Z 226 Transfer complete. 100000 bytes sent in 3.14159 seconds ftp> quit 221 Goodbye. unix> uncompress shawetaylor.symdisc.ps.Z unix> lpr shawetaylor.symdisc.ps (or however you print out postscript) From inmanh at cogs.sussex.ac.uk Fri Apr 23 05:01:10 1993 From: inmanh at cogs.sussex.ac.uk (Inman Harvey) Date: Fri, 23 Apr 93 10:01:10 +0100 Subject: CFP - SAB94 - Simulation of Adaptive Behavior Message-ID: <25560.9304230901@rsunr.crn.cogs.susx.ac.uk> ============================================================================== Conference Announcement and Call For Papers FROM ANIMALS TO ANIMATS Third International Conference on Simulation of Adaptive Behavior (SAB94) Brighton, UK, August 8-12, 1994 The object of the conference is to bring together researchers in ethology, psychology, ecology, cybernetics, artificial intelligence, robotics, and related fields so as to further our understanding of the behaviors and underlying mechanisms that allow animals and, potentially, robots to adapt and survive in uncertain environments. The conference will focus particularly on well-defined models, computer simulations, and built robots in order to help characterize and compare various organizational principles or architectures capable of inducing adaptive behavior in real or artificial animals. Contributions treating any of the following topics from the perspective of adaptive behavior will receive special emphasis. Individual and collective behavior Autonomous robots Neural correlates of behavior Hierarchical and parallel organizations Perception and motor control Emergent structures and behaviors Motivation and emotion Problem solving and planning Action selection and behavioral Goal directed behavior sequences Neural networks and evolutionary Ontogeny, learning and evolution computation Internal world models Characterization of environments and cognitive processes Applied adaptive behavior Authors should make every effort to suggest implications of their work for both natural and artificial animals. Papers which do not deal explicitly with adaptive behavior will be rejected. Submission Instructions Authors are requested to send five copies (hard copy only) of a full paper to the Program Chair (Dave Cliff). Papers should not exceed 10 pages (excluding the title page), with 1 inch margins all around, and no smaller than 10 pt (12 pitch) type (Times Roman preferred). Each paper must include a title page containing the following: (1) Full names, postal addresses, phone numbers, email addresses (if available), and fax numbers for each author, (2) A 100-200 word abstract, (3) The topic area(s) in which the paper could be reviewed (see list above). Camera ready versions of the papers, in two-column format, will be required after acceptance. Computer, video, and robotic demonstrations are also invited. Please contact Phil Husbands to make arrangements for demonstrations. Other program proposals will also be considered. Conference committee Conference Chair Philip HUSBANDS School of Cognitive and Computing Sciences University of Sussex Brighton BN1 9QN UK e-mail: philh at cogs.susx.ac.uk Jean-Arcady MEYER Groupe de Bioinformatique URA686.Ecole Normale Superieure 46 rue d'Ulm 75230 Paris Cedex 05 France e-mail: meyer at wotan.ens.fr Stewart WILSON The Rowland Institute for Science 100 Cambridge Parkway Cambridge, MA 02142 USA e-mail: wilson at smith.rowland.org Program Chair David CLIFF School of Cognitive and Computing Sciences University of Sussex Brighton BN1 9QN UK e-mail: davec at cogs.susx.ac.uk Financial Chair: P. Husbands, H. Roitblat Local Arrangements: I. Harvey, P. Husbands Program Committee M. Arbib, USA; R. Arkin, USA; R. Beer, USA; A. Berthoz, France; L. Booker, USA; R. Brooks, USA; P. Colgan, Canada; T. Collett, UK; H. Cruse, Germany; J. Daugman, UK; J. Delius, Germany; A. Dickinson, UK; J. Ferber, France; N. Franceschini, France; S. Goss, Belgium; I. Harvey, UK; I. Horswill, USA; L. Kaelbling, USA; H. Klopf, USA; L-J. Lin, USA; P. Maes, USA; M. Mataric, USA; D. McFarland, UK; G. Miller, UK; R. Pfeifer, Switzerland; H. Roitblat, USA; J. Slotine, USA; O. Sporns, USA; J. Staddon, USA; F. Toates, UK; P. Todd, USA; S. Tsuji, Japan; W. Uttal, USA; D. Waltz, USA. Official Language: English Publisher: MIT Press/Bradford Books Important Dates =============== JAN 5, 1994: Submission deadline MAR 10: Notification of acceptance or rejection APR 10: Camera ready revised versions due MAY 1: Early registration deadline JUL 8: Regular registration deadline AUG 8-12: Conference dates General queries to: sab94 at cogs.susx.ac.uk ============================================================================== From fcummins at cs.indiana.edu Fri Apr 23 15:29:21 1993 From: fcummins at cs.indiana.edu (fred cummins) Date: Fri, 23 Apr 1993 14:29:21 -0500 Subject: Neuroprose paper: Representation of Temporal patterns in RNNs Message-ID: *** DO NOT FORWARD TO OTHER GROUPS *** The following paper, to be presented as a poster at the 15th AGM of the Cognitive Science Society, has been placed in the neuroprose archive. FTP instructions follow the abstract. Fred Cummins fcummins at cs.indiana.edu __________________________________________________________________________ *** Representation of Temporal Patterns in Recurrent Neural Networks *** To be presented at the 15th Annual Conference of the Cognitive Science Society This paper investigates the way temporal patterns are represented by recurrent networks. Small sequence discrimination tasks were devised with the specific intention of requiring the network to base its discrimination on the temporal structure of the input sequences. The resulting solutions were then analyzed using elementary tools from dynamic systems theory. Our primary interest was to establish the relationship between the temporal characteristics of the training set and the representations developed by the network. Networks trained on a variety of simple sequence recognition tasks were examined. Analysis of the state space of unit activations allowed a direct view of the means employed by the network to solve a given problem, and provided insight both into the class of solutions these networks can produce and how these will generalize to sequences outside the training set. This intuitive approach may be of help in assessing the potential of simply recurrent networks for a variety of modelling problems. __________________________________________________________________________ The paper is cummins.temporal-patterns.ps.Z in the neuroprose archives. To retrieve this file from the neuroprose archives: unix> ftp archive.cis.ohio-state.edu Name (archive.cis.ohio-state.edu:whoever): anonymous Password: (use your email address) ftp> cd pub/neuroprose ftp> binary 200 type set to I ftp> get cummins.temporal-patterns.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for rosen.advsim.ps.Z . ftp> quit 221 Goodbye. unix> uncompress cummins.temporal-patterns.ps.Z unix> lpr cummins.temporal-patterns.ps From emark at cns.caltech.edu Fri Apr 23 19:26:07 1993 From: emark at cns.caltech.edu (Mark O'Dell) Date: Fri, 23 Apr 93 16:26:07 PDT Subject: The Giant Brain Museum Message-ID: The Giant Brain Museum The organizing committee members have gathered together to promote understanding of the brain. They hope to construct a giant walk-through brain museum to be useful to experts while appealing to everyone, including children. The committee members are: Marvin Adelson, Prof. of Architecture & Urban Planning, UCLA Joseph E. Bogen, Clin. Prof. of Neurological Surgery, USC Marian Diamond, Director, Lawrence Hall of Science, UCB Frank O. Gehry, Fellow, Amer. Instit. of Architecture John Hagar, Attorney at Law Robert B. Lewis, Project Director Arnold Scheibel, Director, Brain Research Instit., UCLA Anyone interested in this project, please send your paper mail address to: Giant Brain PO Box 50566 Pasadena, CA 91115 USA or email your paper mail address to me & I will deliver it to the organizers. Please do not send email without a paper mail address; I am only posting. Mark O'Dell emark at cns.caltech.edu From stefano at kant.irmkant.rm.cnr.it Fri Apr 23 05:03:13 1993 From: stefano at kant.irmkant.rm.cnr.it (stefano@kant.irmkant.rm.cnr.it) Date: Fri, 23 Apr 1993 04:03:13 -0500 Subject: No subject Message-ID: <9304230903.AA12012@kant.irmkant.rm.cnr.it> The following paper has been placed in the neuroprose archive as nolfi.growing.ps.Z Instructions for retrieving and printing follow the abstract. Growing Neural Networks Stefano Nolfi Domenico Parisi Institute of Psychology, CNR V.le Marx 15, 00137 Rome - Italy E-mail: stiva at irmkant.Bitnet domenico at irmkant.Bitnet Abstract Growing neural networks are networks which are constructed by executing genetic instructions contained in a genotype. These instructions and their products interacts non-linearly to eventually determine the mature structure. We present simulations in which the mapping from genotype to phenotype is instantaneous and simulations in which it develops in time during a segment of an individual's lifetime, i.e. the individual's developmental age, allowing us to study both neural evolution and neural development. The results shed some light on (a) why modular architectures are likely to emerge, (b) why similar successions of stages tend to appear in both evolution and development, and (c) why a developmental age is preserved evolutionarily although the mature state may appear to be more efficient from the point of view of fitness. The paper has been presented at the Artificial Life III Conference Sorry, no hard copies are available Comments are welcome. Stefano Nolfi Institute of Psychology, CNR V.le Marx, 15 00137 - Rome - Italy email stiva at irmkant.Bitnet _______________________________________________________________________ Here is an example of how to retrieve this file: gvax> ftp archive.cis.ohio-state.edu (or ftp 128.146.8.52) Connected to archive.cis.ohio-state.edu. 220 archive.cis.ohio-state.edu FTP server ready. Name: anonymous 331 Guest login ok, send ident as password. Password:neuron at wherever 230 Guest login ok, access restrictions apply. ftp> binary 200 Type set to I. ftp> cd pub/neuroprose 250 CWD command successful. ftp> get nolfi.growing.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for nolfi.growing.ps.Z 226 Transfer complete. ftp> quit 221 Goodbye. gvax> uncompress nolfi.growing.ps.Z gvax> lpr nolfi.growing.ps From efiesler at idiap.ch Fri Apr 23 10:28:18 1993 From: efiesler at idiap.ch (E. Fiesler) Date: Fri, 23 Apr 93 16:28:18 +0200 Subject: SimTec93 + WNN93 + FNN93; Call for papers. Message-ID: <9304231428.AA28613@idiap.ch> ------------------------------------------------------------------------ Please duplicate and post the following call for papers for the Interna- tional Simulation Technology MultiConference combining SimTec, WNN, and FNN. Thanks. E. Fiesler IDIAP C.P. 609 CH-1920 Martigny E-mail: EFiesler at IDIAP.CH (Internet) ------------------------------------------------------------------------ C A L L F O R P A P E R S 1993 INTERNATIONAL SIMULATION TECHNOLOGY MULTICONFERENCE SimTec93 * WNN93 * FNN93 SimTec: Computer Modeling Applications & Research - ALL Areas Applications * Aerospace * Emerging Technologies Mission Earth * Virtual Reality * Imaging WNN/FNN: Neural Networks * Fuzzy Logic * Computational AI Genetic Algorithms * Chaos & Fractals * Biological Models Virtual Reality * Implementations * Standards November 7-10, 1993 SAN FRANCISCO, CALIFORNIA Convenient. View of the beautiful bay. Near area attractions. ACADEMIC * INDUSTRIAL * GOVERNMENT TECHNOLOGY TRANSFER Awards Luncheon STANDARDS * Exhibits * Demonstrations * CONTESTS Tour NASA/Ames ------ SIMTEC93: INTERNATIONAL SIMULATION TECHNOLOGY CONFERENCE ------- Sponsor: SCS; CoSponsor: NASA; Cooperating: SPIE ----------------- WNN93: COMPUTATIONAL AI CONFERENCE ------------------ (Formerly Workshop on Neural Networks) Sponsor: SCS; CoSponsor: NASA; Cooperating: SPIE, INNS Participating: IEEE-NNC --------------- FNN93: TUTORIALS AND STANDARDS SEMINAR ---------------- PreConference Tutorials and Seminar Fuzzy Systems * Neural Networks * Computational AI Sponsor: SCS; Co-Sponsor: NASA Contact: Mary Lou Padgett, Associate VP for SimTec Auburn University, 1165 Owens Road, Auburn, AL 36830 (205) 821-2472/3488; Fax: (205) 844-1809; mpadgett at eng.auburn.edu [ S C S ] The Society for Computer Simulation P.O.Box 17900, San Diego, CA 92117 P: (619) 277-3888; F: (619) 277-3930 ======================================================================== INTERNATIONAL PROGRAM COMMITTEE General Chair: Ted Lambert - SCS General Program: Martin Dost - SCS Western Simulation Council: Barok Khoshnevis - USC Local Arrangements: Norm Pobanz - Bechtel NASA/Ames Tour Arrangements: Bill Cameron, H. Berenji, S. Columbano Commercial Exhibits: Ed Edwards, Motorola NASA / ESA Representatives: Robert Savely - NASA/JSC Hamid Berenji - NASA/Ames Sylvano Colombano - NASA/Ames Robert Shelton - NASA/JSC Joseph Mica - NASA/Goddard Tim Cleghorn - NASA/JSC Robert Lea - NASA/JSC Juan Miro - ESOC/ESA SimTec John McLeod - SCS Ben Clymer - SCS Norm Pobanz - Bechtel Stu Schlessinger - SCS Martin Wildberger - EPRI Ralph Huntsinger - CS Chico Abul Moaty Fayek - CS Chico Bill Cameron - NASA (ret.) Roy Latham - CGSD Dave O'Neil - SCS Kevin Reilly - UAB Ratan Guha - UCF V. Honovar - Iowa State U. Wartain Jemian - Auburn U. Chris Ward - Auburn U. C. F. Chen - Boston U. Hassan Farhat - U. Nebraska Omaha Keith Klukis - Martin Marietta John Murphy - Westinghouse Dale Whittaker - Texas A & M M. Obaidat - CUNY WNN * FNN Mary Lou Padgett - Auburn U. Walter J. Karplus - UCLA Lotfi Zadeh - Berkeley Paul Werbos - NSF Bart Kosko - USC Joe Brown - Thought Processes, Inc. E. Tzanakou - Rutgers U. David B. Hertz - U. Miami George Rogers - NSWC Ed Edwards - Motorola Louis Sheppard - UT Medical Branch Len Trejo - Navy, San Diego Holger Jaenisch - Nichols Research Bob Clapp - ORNL Rao Vemuri - LLNL T. A. Roppel - Auburn U. Emile Fiesler - IDIAP, Switzerland K. Ashenayi - U. Tulsa ======================================================================== SimTec Topics of Interest Include, but are Not Limited To: SIMULATION APPLICATIONS Chair: Martin Dost - SCS * Co-Chairs: M. Wildberger - EPRI & R. Guha UCF Power Systems Software Modeling Reliability and Quality Assurance Massively Parallel & Distributed Syst Robotics Ground Vehicle Simulation Automatic Control Systems Signal Processing and Analysis Simulation in ADA High Performance Computers/Computing Electronics/VLSI Model Validation Simulation Facilities Educ. for Simulation Professionals AEROSPACE Chair: Hamid Berenji - NASA/Ames * Co-Chair: Juan Miro - ESA Satellite Simulators Guidance, Navigation & Control Real Time Simulation Control Systems Space Avionics Display & Astronaut Training Control Systems Simulation Man-in-the-Loop Flight Remotely Piloted Vehicles Decision Support Systems Robotics & Manufacturing Facilities Planning and Change EMERGING TECHNOLOGIES Chair: Abul Moaty Fayek - CS Chico * Co-Chair T. A. Roppel - Auburn U. Automation & Robotics Training Intelligent Computer Aided Training Knowledge Based Systems Object Oriented Programming Intelligent Sensor Systems Biotechnology & Simulation Microelectronics Multimedia Advances in Simulation Intelligent Computer Environments VIRTUAL REALITY Chair: J. Murphy - Westinghouse Co-Chairs: R. Savely - NASA/JSC, Ben Delaney - CyberEdge Journal Applications Human Factors Hardware and Software Advances in Virtual Reality IMAGING Keith Klukis - Martin Marietta * Co-Chair: Bart Kosko - USC Computer Image Generation Robot & Machine Vision Image Processing & Analysis Biological Modeling of Vision Image Registration Advances in Imaging IR and MMW Image Techniques Automatic Target Recognition MISSION EARTH Chair: John McLeod - SCS * Co-Chair: Ben Clymer - SCS Dueling Methodologies Global Simulations for Education Trends in Mission Earth Global Modeling & Simulation Needs of Global Simulation for Global Planning Progress and Status of State of the Art Mission Earth Activity Organizational Session ======================================================================== W N N 9 3 / F N N 9 3 / S a n F r a n c i s c o November 7-10, 1993 * San Francisco, CA The WNN93 Conference on Computational AI is an extension of the Workshops on Neural Networks--Academic / Industrial / NASA / Defense: Tutorials and Technical Interchange. Monday, November 8 - Wednesday, November 10, 1993 Registration Covers Both SimTec93 and WNN93 sessions and one Proceedings KEYNOTE: "Soft Computing" Lotfi Zadeh - UC Berkeley OVERVIEWS * METHODOLOGY * APPLICATIONS * IMPLEMENTATIONS Academic - Industrial - Government Paper Contest * Awards Luncheon Exhibits * Demonstrations * Tutorials * Tour NASA/Ames STANDARDS: Performance Measure Paper Competition - R. Shelton,NASA/JSC STANDARDS: Comparative Paradigm Paper Competition - E. Tzanakou,Rutgers NASA Neural Networks User Group: Robert Shelton, NASA/JSC NEURAL NETWORKS Chair: Bob Shelton - NASA/JSC * Walter Karplus - UCLA Paul Werbos - NSF and Len Trejo, Navy, San Diego FUZZY LOGIC Chair: Hamid Berenji - NASA/Ames Co-Chairs: Joe Mica - NASA Goddard, Lotfi Zadeh - Berkeley GENETIC ALGORITHMS Chair: Joe Brown - Thought Processes, Inc. Co-Chair: Sylvano Colombano - NASA/Ames CHAOS and FRACTALS Chair: Holger Jaenisch - Nichols Research Co-Chair: Ned Clapp - ORNL * Rao Vemuri - LLNL BIOLOGICAL MODELS Chair: Louis Sheppard - UT Medical Branch Co-Chair: David Bendell Hertz - U. Miami VIRTUAL REALITY Chair: Bart Kosko, USC Co-Chairs: Robert Savely - NASA/JSC and Richard A. Blade - UCCS IMPLEMENTATIONS Chair: Ed Edwards - Motorola Co-Chairs: Bob Lea & Tim Cleghorn - NASA/JSC and T. A. Roppel - AU STANDARDS Chair: Walter J. Karplus - UCLA Co-Chair: Mary Lou Padgett - Auburn University Working Groups: IEEE-NNC Glossary, Performance, Interfaces, Fuzzy Systems, Virtual Reality SCS Neural Networks and Simulation ------------------------------- FNN ----------------------------------- Chair: Mary Lou Padgett Co-Chairs: Hamid Berenji - NASA/Ames Sylvano Colombano - NASA/Ames * Joseph Mica - NASA/Goddard Robert Savely - NASA/JSC * Lotfi Zadeh - Berkeley Sunday, November 7, 1993 - Separate Fee Fuzzy Systems * Neural Networks * Computational AI Basics * Applications * Examples * Standards * NETS Software Given ======================================================================== AUTHOR INSTRUCTIONS FOR SIMTEC AND WNN Papers containing original research contributions, tutorials, written and oral descriptions of company thrusts and government projects are of interest. Fully reviewed papers will be labeled such in the proceedings. Other presentations may be oral, or less formal, and require only an abstract submission by June 1. Prospective authors are invited to submit full papers (maximum of 20 pages double spaced) describing original or tutorial work for review. Four copies of the manuscript should be submitted by June 1. Late papers will be considered on a space available basis. Please include: full name, affiliation, address, phone and fax numbers, and e-mail address of each author and designate the author who is to be the contact. Authors must obtain employer, client or government releases prior to submission of the final manuscript. Accepted papers will be included in the conference proceedings, provided authors meet published deadlines and pay one registration fee ($315) per paper or presentation accepted. Suggestions for panel discussions and other conference activities are welcomed. Submit by June 1, for consideration and inclusion in the preliminary program of the conference. KEY DATES: Draft papers, proposals and/or abstracts Due: June 1, 1993 Camera-ready papers: June 30, 1993 CONTACT: Mary Lou Padgett, Associate VP for SimTec Auburn University, 1165 Owens Road, Auburn, AL 36830 (205) 821-2472/3488; Fax: (205) 844-1809; mpadgett at eng.auburn.edu (for SimTec submissions address to Martin Dost, c/o Padgett) ----------------------------- REGISTRATION ----------------------------- 1993 INTERNATIONAL SIMULATION TECHNOLOGY MULTICONFERENCE San Francisco Airport Marriott, California November 7-10, 1993 SimTec93 * WNN93 * FNN93 Registration fee for SimTec or WNN includes attendance at both conferenc es, speakers' breakfast (if applicable), one Proceedings and any planned social functions. Separate Sunday registration fee for FNN includes attendance at all Nov. 7 presentations, coffee breaks, handouts, executable copy of NASA NETS software. Make checks payable to SCS. Mail registration to SCS, P.O.Box 17900, San Diego, CA 92117-7900. Phone: (619) 277-3888. Fax: (619) 277-3930. Authors: This registration form must be completed and returned with your manuscript by June 30. Registration fee must be guaranteed by receipt of check or credit card number for paper inclusion in conference proceedings. Registration is not refundable. Others may preregister until Oct. 7, 1993. Commercial Exhibitors: Call for information! Name: _________________________________________________________________ Position: ____________________________________________________________ Organization: ________________________________________________________ Address: _____________________________________________________________ _____________________________________________________________ City: _____________________ State/Country_____________ Zip: __________ Business Phone: ___________________ Home Phone: ______________________ FAX: ___________________ Email: ______________________________________ Paper(1)# (if any): Paper(1) Title: Paper(2)# (if any): Paper(2) Title: * FNN Registration Fee ($185 before Oct 7, $265 after): $_______________ * SimTec ___ or WNN ___ Conference Fee: Attendees (Members $315 before Oct 7, $375 after; Non-members $375 before Oct 7, $435 after): . . . $_______________ Authors ($315 per paper or presentation, due July 30):$_______________ Extra Page Charges ($75 per extra page, if over 6 pages in a camera-ready paper):. $_______________ Membership: SCS___ NASA___ SPIE___ INNS___ IEEE-NNC___ Member Number: * SCS Membership Dues ($60 - enclose membership appl.):$_______________ * TOTAL: . . . . . . . . . . . . . . . . . . . . . . . $_______________ Method of Payment (No Cash Accepted): Visa___ Mastercard___ Am. Express___ Check___ Company PO___ Gov't Form 1556___ Card Number: Exp. Date: Authorizing Signature: - - - - - - - - MAKE HOTEL RESERVATIONS INDEPENDENTLY!!! - - - - - - - - Mention SOCIETY FOR COMPUTER SIMULATION for conference rates of $90. San Francisco Airport MARRIOTT 1800 Old Bayshore Hwy., Burlingame, CA 94010-1294 415-692-9100 Location: Bayside, 1 mile south of San Francisco International Airport at the Millbrae Avenue East exit. Guest Services: Complimentary Airport Shuttle Service * Auto Rental Valet and Free Parking * Gift Shop * Disco * Restaurants Luxury Rooms: $90 single or double. Reserve before October 7, 1993. Places to See/Things to Do: Fisherman's Wharf * Chinatown * Ghiradelli Square * The Cannery Golden Gate Bridge and Park * Whalewatching * Half Moon Bay Vineyard Tours in Napa and Sonoma Valley * Candlestick Park SimTec93 * WNN93 * FNN93 SEE YOU IN SAN FRANCISCO! From mm at sedal.sedal.su.OZ.AU Sat Apr 24 11:57:50 1993 From: mm at sedal.sedal.su.OZ.AU (Multi-Module Environment) Date: Sat, 24 Apr 93 10:57:50 EST Subject: MUME version 0.6 is available Message-ID: <9304240057.AA10348@sedal.sedal.su.OZ.AU> MUME 0.6 IS NOW AVAILABLE The Multi-Module Neural Computing Environment (MUME) version 0.6 (sources only) is now available. MUME-0.6 compiles on a variety of Unix machines as well on the Fujitsu VP2200 and PCs (MSDOS 5.0 or higher and using DJGCC). HOW TO GET IT ------------- It can be acquired by fetching the licence file: file license.ps (postrscript file) machine 129.78.13.39 directory: /pub login: anonymous password: your email address and getting it signed by an authorised person and then sending/faxing it to MUME 0.6 SEDAL Sydney University Electrical Engineering NSW 2006 Australia Fax: (+61-2) 660-1228 The machine/account/passwd where you can ftp the sources will then be communicated to you. *** PLEASE DO NOT FORGET TO WRITE YOUR EMAIL CONTACT ON THE FAXED LICENSE *** PC USERS -------- If you don't have the DJGCC compiler, you can write to the address above with a signed license and a cheque for A$150 (for media/doc/postage) and we will forward to you the software and binaries. Do not forget to clearly specify the media (3.5" or 5"1/4) and your surface mail address. Note MUME compiled under DJGCC will not run under Microsoft's Windows. MAILING LIST ------------ Once you have the software, you can ask to be include on a mailing list by sending your email address to mume-request at sedal.su.oz.au MORE INFO ABOUT MUME OR CHANGES ------------------------------- If you don't know what MUME is, you can fetch the file /pub/mume-overview.ps.Z from 129.78.13.39 (login as anonymous). Otherwise here is a copy of the CHANGES file (from version 0.5 to 0.6): o A detailled basic tutorial has been written (directory tutes/tut0) o To simplify interconnections statements between nets, MUME now generates default "iface"s. for example for an MLP called john, MUME automatically generates the interfaces john.in (input layer) and john.out (output layer). This applies to most nets. The enhancement of the interconnection semantic has been simplified even further by introducing "base" index which simplifies the neuron reference. All information about interfaces is now described in a separate manual page called IFACE.5. o The configuration files can make use of symbols which can be set in the file or on the command line of the front-end program (see man pages SYMBOLS.5 and MMN.5). Some nets now also define their own symbols (eg. "mlp" net). o The specification of neuron index for "nfun" keyword has been emhanced to allow easier indexing (see NET.5). o All front ends now default to a "test" mode. To train the switch "-train" is required. o Data reading routines of ENV net have been optimised o Data normalisation statements in ENV have been modified (see man pages ENV.5 and NORM.5) o MUME now supports the use of a validation set during training. The main purpose of a validation set is to prevent overtraining, as the error on both the training and validation sets can be tracked as training progresses. To use the validation set, set the optional "Validate" flag in the system definition section to 1 (using the statement "Validate 1;") and specify a validation data set in all ENV modules (using the statement "data Validate ;"). The error on the validation set will now be logged as a 3rd column along with the epoch number and training error. See the ENV.5 and MMN.5 man pages for more information. o MUME now catches more system signals when possible and exit after saving the net states upon receiving them. The signals are: SIGINT, SIGTERM, SIGXCPU, and SIGXFSZ. o Logging output is more consistent under the control of the "-verbose" switch. o the following learning algorithms have been added: stochastic error descent for limited precision training reinforcement learning conjugate gradient simplex based methods o the following net classes has been added: resource allocation nets (class RAN) NeTtalk postprocessing module (class N2K) o the class RBPTT has been renamed WPANG. o the WZ class (continuously running recurrent net) has now what is called pins which have 0 propagation delays o and of course, many bugs were fixed. The behaviour of the learning algorithms have not changed between 0.5 and 0.6. All configuration files should still run under 0.6 except for normalisation statements in the ENV class. We are sure that the new statements make declarations much easier. mume-request at sedal.su.OZ.AU From annette at cdu.ucl.ac.uk Thu Apr 22 13:10:33 1993 From: annette at cdu.ucl.ac.uk (Annette Karmiloff-Smith) Date: Thu, 22 Apr 93 13:10:33 BST Subject: Job possibility in London Message-ID: <9304221210.AA06205@cdu.ucl.ac.uk> MEDICAL RESEARCH COUNCIL, COGNITIVE DEVELOPMENT UNIT, LONDON A short term non-clinical scientific post is available at the CDU in London for 3 years, to work on the biological basis of cognitive development alongside Dr Mark Johnson. The successful candidate should have a PhD and solid experience in formal computational modelling of developmental processes. In addition, we would require experience in one or more biological techniques, such as event- related potentials, as well as interest in some area of cognitive development. The salary is on the non-clinical scientific scale Pounds Sterling 15,563 - 24,736 per annum, plus Pounds Sterling 2,134 London Weighting. Applications should be made in writing BY 15 MAY 1993, enclosing CV and names of three referees to: The Director, Professor John Morton, 17 Gordon Street, London WC1H OAH, UK (Fax 071-383-0398, E-mail: john at uk.ac.cdu.ucl) The Medical Research Council is an equal opportunities employer. -o0o- From P.Refenes at cs.ucl.ac.uk Mon Apr 26 07:04:38 1993 From: P.Refenes at cs.ucl.ac.uk (P.Refenes@cs.ucl.ac.uk) Date: Mon, 26 Apr 93 12:04:38 +0100 Subject: No subject Message-ID: ************* PLEASE DO NOT FORWARD TO OTHER LISTS ********** PROVISIONAL PROGRAMME Third International Conference on 'Artificial Neural Networks' Brighton Conference Centre, UK: 25 - 27 May 1993 SECRETARIAT: Sheila Griffiths, ANN'93 Secretariat, Conference Services, IEE, Savoy Place, London WC2R OBL, UK Tel: ++ 44 71 344 54 58 / 54 77 Fax: ++ 44 71 497 36 33 Monday, 24 May 16.00 - 18.00 hrs Registration Tuesday, 25 May 08.00 hrs Registration 09.30 hrs Formal Opening Address of Welcome: Dr R Voles Chairman, Electronics Division Institution of Electrical Engineers Keynote Address: Professor R M Goodman California Institute of Technology USA 10.30 hrs Close of Session and Coffee 11.00 hrs Session 1 - VISION I Session Chairman: A Wright 195 'BARTIN applied to visual inspection of axisymmetric engineering parts' D W McMichael DRA, UK 94 'A practical view based 3D object recognition system' A Evans, J E W Mayhew and N Thacker University of Sheffield, UK 55 'Neural network paradigm for visual pattern recognition' S J Bye Telecom Australia, Australia A Adams University of Tasmania, Australia 130 'Labelling images with a neural network' W P J Mackeown and B T Thomas University of Bristol, UK W A Wright and P Greenway British Aerospace PLC, UK 12.30 hrs Close of Session and Lunch 14.00 hrs Session 2 - ARCHITECTURE I Session Chairman: R Rohwer 188 'Neural network validation: An illustration from the monitoring of multi-phase flows' C M Bishop AEA Technology, UK 109 'Comparing parameters selection methods and weights rounding techniques to optimize the learning in neural networks' J-F Grandin, B Braban, A Halioua and C Ledoux Thomson CSF, France 108 'On recurrent neural networks and representing finite-state recognizers' M W Goudreau and C L Giles NEC Research Institute, Inc., USA 172 'Cascadability and in-situ learning for VLSI multi-layer networks' J Tombs, G Cairns and L Tarassenko University of Oxford, UK 15.30 hrs Close of Session and Tea 16.00 hrs Session 3 - ANALYSIS I Session Chairman: D Lowe 21 'An adaptive bayesian network for low-level image processing' Dr S P Luttrell Defence Research Agency, UK 185 'Neural computing: A new route to software reliability' Professor D Partridge and N Sharkey University of Exeter, UK 50 'Comparison of the performance of vector quantiser training algorithms' J V Black DRA Malvern, UK 173 'Improved generalization and network pruning using adaptive laplace regularization' P M Williams University of Sussex, UK 121 'Improving generalisation with Ockham's networks: Minimum description length networks' G D Kendall and T J Hall King's College London, UK 18.00 hrs Close of Session 18.15 - 19.00 hrs Civic Reception Wednesday, 26 May 08.30 hrs Session 4 - MEDICAL Session Chairman: P Refenes * 'Novelty, validation and classification of medical data: A unified approach using radar basis function architectures' L Tarassenko and S J Roberts University of Oxford, UK 65 'A comparison of neural network architectures for cervical cell classification' S J McKenna, A Y Cairns and I W Ricketts University of Dundee, UK 153 'Ultrasonic tissue characterization using neural networks' T E Schouten, M K Gebbinck, J M Thijssen and J T M Verhoeven Katholieke Universiteit Nijmegen, Netherlands 171 'Realization of physiological eye movements by automatic selection of control laws using artificial neural network' H Wakamatsu Tokyo Medical and Dental University, Japan H Suda and M Kuwano Fukui University, Japan 10.30 hrs Close of Session and Coffee 11.00 hrs Session 5 - APPLICATIONS Session Chairman: C Satchwell 191 'Neural network system for tactical asset allocation in the global bond markets' A N Refenes University College London C Diamond. M Azema-Barac and J Shadbolt ECONOSTAT Ltd, UK 19 'Experience with artificial neural network models for short-term load forecasting in electrical power systems: A proposed application of expert networks' A Asar and J R McDonald University of Strathclyde, UK W Rattray Scottish Power, UK 105 'Central auditory model for spectral processing' Y Gao and J-P Haton CRIN, France T Huang Chinese Acadmeny of Sciences, China 96 'Investigating the recognition of false patterns in backpropagation networks' Dr M C Fairhurst, D L Bisset and G C Vasconcelos University of Kent, UK 12.30 hrs Close of Session and Lunch 14.00 hrs Session 6 - POSTER SESSION AND SESSION ON THE INITIATIVES IN NEURAL NETWORKS IN THE UK Session Chairman: R Wiggins, DTI 'The Neural Computing Applications Forum' Simon Cummings British Airways, UK 'The Department of Trade and Industry programme' Ray Brown DTI, UK Representatives of DTI sponsored clubs will give presentations of their activities: A Furness Keel University, UK Derek Bunn London Business School, UK C Bishop AEA Technology, UK Vic Bevan EDS Scicon, UK Paul gregory Recognition Research Ltd, UK A Carr ERA Technology, UK 15.30 hrs Close of Session and Tea POSTER PAPERS 70 'Stochastic analysis and comparison of kohonen SOM with optimal filter' N M Allinson and H Yin University of York, UK 183 'Learning and prediction of nuclear radioactive properties with artificial neural networks' S Gazula University of Miami, USA 38 'An 'introspective' network that can learn to run its own weight change algorithm' J Schmidhuber Technische Universitat Munchen, Germany 91 'Using prototypes to solve problems in neural net classifiers' C Decaestecker IRIDIA - Universite Libre de Bruxelles, Belgium 161 'Scene segmentation of natural images using texture features and back-propagation' B Sridhar, G Chatterjee and A Phatak NASA Ames Research Center, USA 20 'On-line adaption in robot control' D A Fraser, K Althoefer and F Azhar King's College London, UK 59 'Neural network for modelling and control of fed batch fermentation process' N A Jalel, J R Leigh and D Tsaptsinos University of Westminster, UK 14 'Towards a neural network based system for skin cancer diagnosis' Dr E Claridge University of Birmingham, UK R T J Bostock and A J Harget Aston University, UK P N Hall Wardsley Hospital, UK 23 'Modelling of a fermentation process using a time-delay neural network' D Tsaptsinos and J R Leigh University of Westminster, UK 152 'Minimisation of torque ripple in a switched reluctance motor using a neural network' D S Reay, T C Green and B W Williams Heriot-Watt University, UK 137 'Neural network based fingerprint classification' K Moscinska and G Tyma Silesian Technical University, Poland 69 'Variable bit rate block truncation coding for image compression using hopfield neural networks' Dr M R Varley, G Qiu and T J Terrell University of Central Lancashire, UK 192 'Target classification using neural and classical techniques' A K Patel, P R Collins and W A Wright Sowerby Research Centre, UK 87 'A stochastic reverse interpolation algorithm for real-valued function learning' Dr T G Clarkson, D Gorse, Y Guan and J G Taylor King's College London, UK 119 'Dynamic DBP learning algorithm for real time applications' Y Jin, A G Pipe and A Winfield University of the West of England, UK 136 'A probabilistic approach which provides a modular and adaptive neural network architecture for discrimination' C Monrocq Thomson-CSF LCR, France 148 'Neural network based dynamic models' B Pataki Technical University of Budapest, Hungary 80 'External stimuli in optimised attractor neural networks for sparsely coded patterns' A N Burkitt Australian National University, Australia 103 'Parallel learning algorithms for principal component extraction' Dr B Freisleben University of Darmstadt, Germany 97 'Modular connectionist architectures for multi-patient ECG recognition' S Farrugia, P Nickolls and H Yee The University of Sydney, Australia 178 'Decentralized hopfield neural network applied to maintenance scheduling of generating units in power systems' K Yoshimoto, K Yasuda and R Yokoyama Tokyo Metropolitan University, Japan B J Cory Imperial College of Science, Technology and Medicine, UK 190 'Neural network processing of scattered light measurements in the detection of immiscible water pollutants' Dr P R Smith, D A Green, R Naimimohosses and H Thomason Loughborough University of Technology, UK 56 'A connectionist approach to SDH bandwidth management' S J Bye Telecom Australia, Australia 141 'LSP speech synthesis using backpropagation networks' P Noakes and G C Cawley University of Essex, UK 16.00 hrs Session 7 - CONTROL AND ROBOTICS Session Chairman: A J Morris 88 'Analysing recurrent dynamical networks evolved for robotic control' Dr D Cliff, I Harvey and P Husbands University of Sussex, UK 167 'Robot path planning using VLSI resistive grids' Ms G Marshall and L Tarassenko University of Oxford, UK 75 'Minimum variance control of a class of nonlinear plants with neural networks' Professor S Bittanti and L Piroddi Politecnico di Milano, Italy 159 'Neural networks performing system identification for control applications' O Sorensen Aalborg University, Denmark 131 'A neural network motion predictor' H Meng and P D Picton Open University, UK 18.00 hrs Close of Session 19.30 hrs Conference Dinner at Old Ship Hotel Thursday, 27 May 09.00 hrs Session 8 - ANALYSIS II Session Chairman: C Bishop 149 'A hebbian/anti-hebbian network which optimize information capacity by orthonormalizing the principal subspace' Dr M D Plumbley King's College London, UK 31 'A novel unsupervised classification method' J Schmidhuber and D Prelinger Technische Universitat Munchen, Germany 129 'Novel 'Topographic' nonlinear feature extraction using radial basis functions for concentration coding in the 'Artificial Nose'' D Lowe DRA Malvern, UK 117 'Valid generalization in radial basis function networks and modified kanerva models' S B Holden Cambridge University, UK 10.30 hrs Close of Session and Coffee 11.00 hrs Session 9 - APPLICATIONS II Session Chairman: L Tarassenko 133 'Speaker identification using radial basis functions' M W Mak, W G Allen and G G Sexton University of Northumbria at Newcastle, UK 99 'Nonlinear noise filtering with neural networks: Comparison with Wiener optimal filtering' T Fechner Dainler Benz AG Research Institute, Germany 41 'Complex-valued radial basis function networks' Dr S Chen, P M Grant, S McLaughlin and B Mulgrew The University of Edinburgh, UK 76 'Neural Nets for first break detection in seismic reflection data' J F Boyce and C H Dimitropoulos King's College London, UK 12.30 hrs Close of Session and Lunch 14.00 hrs Session 10: VISION II Session Chairman: S Lutterell 40 'Target recognition in infra-red imagery using neural networks and machine learning' A Crowe British Aerospace, UK W A Wright, M A Green, T M Banks and A D Hughes British Aerospace (Systems & Equipment) Limited, UK 170 'An original approach for the localization of objects in images' R Vaillant, Y Le Cun and C Monrocq Thomson-CSF, France 84 'Unsupervised feature extraction by hypothesis of feature centres' Ms M-Y Chan and T J Hall King's College London, UK 11 'A hardware polynomial feature net for handprinted digit recognition' A Rao Eastman Kodak Company, USA P G Anderson Rochester Institute of Technology, USA R S Gaborski and K Jaiswal Arizona State University, USA 16.30 hrs CLOSE OF CONFERENCE From ray at orthanc.cs.su.OZ.AU Mon Apr 26 22:40:19 1993 From: ray at orthanc.cs.su.OZ.AU (Raymond Lister) Date: Tue, 27 Apr 1993 12:40:19 +1000 Subject: Annealing Networks and Fractal Landscapes Message-ID: A postscript file containing the following paper has been placed in the neuroprose archive, as lister.anneal.ps.Z ... Annealing Networks and Fractal Landscapes Raymond Lister Dept. of Electrical Engineering, University of Queensland QLD 4072, Australia ray at s1.elec.uq.oz.au Abstract It is well known that Hopfield and Tank networks give poor solutions to the Traveling Salesman Problem; but we show that the popular explanation for the poor performance is either wrong, or at best incomplete. The popular explanation is that the network has difficulty in balancing the trade-off between the path length and the legality components of the energy function. We first describe an experiment which has an outcome that is not accounted for by this explanation. We then propose an alternative: these networks would scale better if their dynamics effectively implemented a "divide-and-conquer" strategy. That is, if they recursively decomposed the problem into smaller independent sub-problems. An annealing network can do so if the energy landscape has a self-similar "quasi-fractal" structure. We believe this proposition applies to both discrete and analog networks. We support our proposition by describing results from our work on the Traveling Salesman Problem. We then consider the implications for two other optimization problems: graph bisection and coloring. Here is an example of how to retrieve this file: > ftp archive.cis.ohio-state.edu (or ftp 128.146.8.52) Connected to archive.cis.ohio-state.edu. 220 archive.cis.ohio-state.edu FTP server ready. Name: anonymous 331 Guest login ok, send ident as password. Password: 230 Guest login ok, access restrictions apply. ftp> binary 200 Type set to I. ftp> cd pub/neuroprose 250 CWD command successful. ftp> get lister.anneal.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for lister.anneal.ps.Z 226 Transfer complete. ftp> quit 221 Goodbye. > uncompress lister.anneal.ps.Z > lpr lister.anneal.ps From terry at helmholtz.sdsc.edu Tue Apr 27 02:08:13 1993 From: terry at helmholtz.sdsc.edu (Terry Sejnowski) Date: Mon, 26 Apr 93 23:08:13 PDT Subject: NEURAL COMPUTATION: MAY 1993 Message-ID: <9304270608.AA03254@helmholtz.sdsc.edu> Neural Computation, Volume 5, Number 3 Article A Model for Motor Endplate Morphogenesis: Diffusible Morphogens, Transmembrane Signaling, and Compartmentalized Gene Expression Michel Kerszberg and Jean-Pierre Changeau Notes Universal Approximation by Phase Series and Fixed-Weight Networks Neil E. Cotter and Peter R. Conwell Backpropagation with Homotopy Liping Yang and Wanzhen Yu Improving Rejection Performance on Handwritten Digits by Training with "Rubbish" Jane Bromley and John S. Denker Vapnik-Chervonenkis Dimension Bounds for Two- and Three-Layer Networks Peter L. Bartlett Letters A Neural Network for the Processing of Optic Flow from Ego-Motion in Man and Higher Mammals Markus Lappe and losef P. Rauschecker Arbitrary Elastic Topologies and Ocular Dominance Peter Dayan Neural Networks for Fingerprint Recognition Pierre Baldi and Yves Chauvin Centered-Object Integrated Segmentation and Recognition of Overlapping Handprinted Characters Gale L. Martin Surface Interpolation Networks Alex P. Pentland Combining Exploratory Projection Pursuit and Projection Pursuit Regression with Application to Neural Networks Nathan Intrator A Simplified Gradient Algorithm for IIR Synapse Multilayer Perceptrons Andrew D. Back and Ah Chung Tsoi The Characteristics of the Convergence Time of Associative Neural Networks Toshiaki Tanaka and Miki Ynnlada Robustness in Multilayer Perceptrons P. Kerlirzin and F. Vallet Pattern Discrimination Using Feedforward Networks: A Benchmark Study of Scaling Behavior Thorsteinn Rognvaldsson A Neural Network That Learns to Interpret Myocardial Planar Thallium Scintigrams Charles Rosenberg, Jacob Erel, and Henri Atlan ----- SUBSCRIPTIONS - VOLUME 5 - BIMONTHLY (6 issues) ______ $40 Student ______ $65 Individual ______ $156 Institution Add $22 for postage and handling outside USA (+7% GST for Canada). (Back issues from Volumes 1-4 are regularly available for $28 each to institutions and $14 each for individuals Add $5 for postage per issue outside USA (+7% GST for Canada) MIT Press Journals, 55 Hayward Street, Cambridge, MA 02142. Tel: (617) 253-2889 FAX: (617) 258-6779 e-mail: hiscox at mitvma.mit.edu ----- From eric at research.nj.nec.com Tue Apr 27 10:25:23 1993 From: eric at research.nj.nec.com (Eric B. Baum) Date: Tue, 27 Apr 93 10:25:23 EDT Subject: Paper Announcement Message-ID: <9304271425.AA06945@yin> A revised draft of the following preprint is now available via the NEC Research Institute ftp archive external.nj.nec.com. Instructions for retrieval from the archive follow the summary. NOTE- This is NOT the Neuroprose directory. Thanks to those whose questions or comments regarding the first draft contributed to this revision. Any further comments are welcome. ----------------------------------------------------------------- Best Play for Imperfect Players and Game Tree Search Eric B. Baum and Warren D. Smith NEC Research Institute 4 Independence Way Princeton NJ 08540 ABSTRACT We propose a new approach to game tree search. We train up an evaluation function which returns, rather than a single number estimating the `value' of a position, a probability distribution $P_L(x)$. $P_L(x)$ is the probability that if we expanded leaf $L$ to some depth, the backed up value of leaf $L$ would then be found to be $x$. We describe how to propagate these distributions efficiently up the tree so that at any node n we compute without approximation the probability node n's negamax value is x given that a value is assigned to each leaf from its distribution. After we are done expanding the tree, the best move is the child of the root whose distribution has highest mean. Note that we take means at the child of the root {\it after} propagating, whereas the normal (Shannon) approach takes the mean at the leaves before propagating, which throws away information. Now we model the expansion of a leaf as selection of one value from its distribution. The total utility of all possible expansion is then by definition the ensemble sum over those possible leaf configurations for which the current favorite move is inferior to some alternate move, weighted by the probability of the leaf configuration and the amount the current favorite move is inferior. We propose as the natural measure of the expansion importance of leaf L, the expected absolute change in this utility when we expand leaf L. We support this proposal with several arguments including an approximation theorem valid in the limit that one expands until the remaining utility of expansion becomes small. In summary, we gather distributions at the leaves, propagate exactly all this information to the root, and incrementally grow a tree expanding approximately the most interesting leaf at each step. Under reasonable conditions, we accomplish all of this in time $O(N)$, where N is the number of leaves in the tree when we are done expanding. That is, we pay only a small constant factor overhead for all of our bookkeeping. ---------------------------------------------------------------------- FTP INSTRUCTIONS unix> ftp external.nj.nec.com (138.15.10.100) Name: anonymous Password: (your_userid at your_site) ftp> cd pub/eric/papers ftp> binary ftp> get game.ps.Z ftp> quit unix> uncompress game.ps.Z ----------------------------------------------------------------------- Eric Baum NEC Research Institute 4 Independence Way Princeton NJ 08540 Inet: eric at research.nj.nec.com UUCP: princeton!nec!eric MAIL: 4 Independence Way, Princeton NJ 08540 PHONE: (609) 951-2712 FAX: (609) 951-2482 From jls at computer-science.manchester.ac.uk Fri Apr 23 17:48:29 1993 From: jls at computer-science.manchester.ac.uk (Jon Shapiro) Date: Fri, 23 Apr 93 17:48:29 BST Subject: Research Posts Message-ID: <9304231648.AA10820@r8q.cs.man.ac.uk> Two Research Posts Department of Psychology, University of Lancaster Department of Computer Science, University of Manchester Short-term memory for verbal sequences: psychological experiments and connectionist modelling. Applications are invited for two posts on a research project investigating short-term memory mechanisms for processing verbal information. The first post is for a postdoctoral researcher to work with Dr. Jonathan Shapiro at Manchester on connectionist modelling and analysis. The second post is for a graduate researcher to assist Professor Graham Hitch with the psychological experiments. Both post can begin as soon as possible and run through December 1995. Applicants for the modelling post should have expertise in computational and mathematical aspects of connectionism and a Ph.D. in a relevant subject. The salary range is 15,221 - 16,629 U.K. pounds based on age and experience. Applicants for the experimental post should have a first degree in psychology, and interests in memory and cognition. The salary range is 13,632 - 15,221 U.K. pounds. To apply for either post, send curriculum vita and the names and addresses of two professional referees to the address below. For further information, you may also write to the address below. ------------------------------------------------------------------------- Jonathan Shapiro Computer Science Dept University of Manchester Oxford Road Manchester M13 9PL United Kingdom. Phone: 44-(0)61 275 6253 Fax: 44-(0)61 275 6236 E-mail: jls at cs.man.ac.uk From jab at GS116.SP.CS.CMU.EDU Tue Apr 27 15:48:30 1993 From: jab at GS116.SP.CS.CMU.EDU (Justin Boyan) Date: Tue, 27 Apr 93 15:48:30 EDT Subject: Modular Networks for Reinforcement Learning of Backgammon Strategies Message-ID: The file boyan.backgammon-thesis.ps.Z is now available in the neuroprose archive. _______________________ Modular Neural Networks for Learning Context-Dependent Game Strategies Justin A. Boyan Master's Thesis, University of Cambridge, Computer Speech and Language Processing Supervisor: Professor Frank Fallside 17 August 1992 Abstract: Recent results by Tesauro in the domain of backgammon indicate that a neural network, trained by temporal difference methods to evaluate positions generated by self-play, can reach an advanced level of backgammon skill. For my summer thesis project, I first implemented the TD/neural network learning algorithms and confirmed Tesauro's results, using the domains of tic-tac-toe and backgammon. Then, motivated by Waibel's success with modular neural networks for phoneme recognition, I experimented with using two modular architectures (DDD and Meta-Pi) in place of the monolithic networks. I found that using the modular networks significantly enhanced the ability of the backgammon evaluator to change its strategic priorities depending on the current game context. My best modular backgammon network was entered in the 1992 Computer Games Olympiad in London, where it finished in second place. _______________________ Here is an example of how to retrieve this paper: > ftp archive.cis.ohio-state.edu (or ftp 128.146.8.52) Connected to archive.cis.ohio-state.edu. 220 archive.cis.ohio-state.edu FTP server ready. Name: anonymous 331 Guest login ok, send ident as password. Password: 230 Guest login ok, access restrictions apply. ftp> binary 200 Type set to I. ftp> cd pub/neuroprose 250 CWD command successful. ftp> get boyan.backgammon-thesis.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for boyan.backgammon-thesis.ps.Z 226 Transfer complete. ftp> quit 221 Goodbye. > uncompress boyan.backgammon-thesis.ps.Z > lpr boyan.backgammon-thesis.ps From jordan at psyche.mit.edu Tue Apr 27 18:19:19 1993 From: jordan at psyche.mit.edu (Michael Jordan) Date: Tue, 27 Apr 93 18:19:19 EDT Subject: EM and hierarchies of experts Message-ID: The following technical report has been placed in the neuroprose directory, as jordan.hierarchies.ps.Z: Hierarchical mixtures of experts and the EM algorithm Michael I. Jordan MIT Robert A. Jacobs University of Rochester We present a tree-structured architecture for supervised learning. The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coefficients and the mixture components are generalized linear models (GLIM's). Learning is treated as a maximum likelihood problem; in particular, we present an Expectation-Maximization (EM) algorithm for adjusting the parameters of the architecture. We also develop an on-line learning algorithm in which the parameters are updated incrementally. Comparative simulation results are presented in the robot dynamics domain. ------------------------------------------------ Here is an example of how to retrieve this file: > ftp archive.cis.ohio-state.edu (or ftp 128.146.8.52) Connected to archive.cis.ohio-state.edu. 220 archive.cis.ohio-state.edu FTP server ready. Name: anonymous 331 Guest login ok, send ident as password. Password: 230 Guest login ok, access restrictions apply. ftp> binary 200 Type set to I. ftp> cd pub/neuroprose 250 CWD command successful. ftp> get jordan.hierarchies.ps.Z 200 PORT command successful. 150 Opening BINARY mode data connection for jordan.hierarchies.ps.Z 226 Transfer complete. ftp> quit 221 Goodbye. > uncompress jordan.hierarchies.ps.Z > lpr jordan.hierarchies.ps From ray at orthanc.cs.su.OZ.AU Wed Apr 28 08:48:13 1993 From: ray at orthanc.cs.su.OZ.AU (Raymond Lister) Date: Wed, 28 Apr 1993 22:48:13 +1000 Subject: problems with "Annealing Networks and Fractal Landscapes" Message-ID: > From ray at orthanc.cs.su.OZ.AU Tue Apr 27 12:42:31 1993 > Subject: Annealing Networks and Fractal Landscapes > To: connectionists at cs.cmu.edu > > A postscript file containing the following paper has been placed in the > neuroprose archive, as lister.anneal.ps.Z ... > > > Annealing Networks and Fractal Landscapes A number of people have reported difficulty with printing the above non-standard postscript file. In most cases, the problem can be solved by inserting a line at the start of the file, containing the characters `%!'. (That is, the two characters between the `' characters.) The file may still not preview using certain tools, such as ghostview, but the paper is only 6 pages, so you won't be killing too many trees if you print it off. From rsun at athos.cs.ua.edu Wed Apr 28 11:30:55 1993 From: rsun at athos.cs.ua.edu (Ron Sun) Date: Wed, 28 Apr 1993 10:30:55 -0500 Subject: Bibliography available Message-ID: <9304281530.AA18716@athos.cs.ua.edu> ---------------------- Bibliography Available ---------------------- A compiled bibliography of connectionist models with symbolic processing is available in neuroprose now. This bibliography will be included in: R.Sun and L.Bookman. (eds.) Computational Architectures Integrating Neural and Symbolic Processes. Kluwer Academic Publishers. 1993. Thanks to all those who contributed. Any further suggestions and additions are also welcome. To get a copy of the bibliography, use FTP as follows: unix> ftp archive.cis.ohio-state.edu (or 128.146.8.52) Name: anonymous Password: ftp> cd pub/neuroprose ftp> binary ftp> get sun.nn-sp-bib.ps.Z ftp> quit unix> uncompress sun.nn-sp-bib.ps.Z unix> lpr sun.nn-sp-bib.ps (or however you print postscript) * As usual, no hardcopy available. Sorry. From rsun at athos.cs.ua.edu Thu Apr 29 09:33:59 1993 From: rsun at athos.cs.ua.edu (Ron Sun) Date: Thu, 29 Apr 1993 08:33:59 -0500 Subject: No subject Message-ID: <9304291333.AA14656@athos.cs.ua.edu> Regarding the bibliography I mentioned in a previous message: Plase send any suggestions or additions you might have to ================================================================ Ron Sun, Ph.D Assistant Professor Department of Computer Science phone: (205) 348-6363 The University of Alabama fax: (205) 348-8573 Tuscaloosa, AL 35487 rsun at athos.cs.ua.edu ================================================================ Your help is greatly appreciated. However, the decision whether to include a paper or not is solely the responsibility of the editors. --Ron From greiner at learning.siemens.com Thu Apr 29 14:26:26 1993 From: greiner at learning.siemens.com (Russell Greiner) Date: Thu, 29 Apr 93 14:26:26 EDT Subject: CFP: "Computational Learning and Natural Learning" workshop Message-ID: <9304291826.AA06060@learning.siemens.com> CLNL'93 -- Call for Submissions Computational Learning and Natural Learning Provincetown, Massachusetts 10-12 September 1993 CLNL'93 is the fourth of an ongoing series of workshops designed to bring together researchers from a diverse set of disciplines -- including computational learning theory, AI/machine learning, connectionist learning, statistics, and control theory -- to explore issues at the intersection of theoretical learning research and natural learning systems. Theme: To be useful, the learning methods used by our fields must be able to handle the complications inherent in real-world tasks. We therefore encourage researchers to submit papers that discuss extensions to learning systems that let them address issues such as: * handling many irrelevant features * dealing with large amounts of noise * inducing very complex concepts * mining enormous sets of data * learning over extended periods of time * exploiting large amounts of background knowledge We welcome theoretical analyses, comparative studies of existing algorithms, psychological models of learning in complex domains, and reports on relevant new techniques. Submissions: Authors should submit three copies of an abstract (100 words or less) and a summary (2000 words or less) of original research to: CLNL'93 Workshop Learning Systems Department Siemens Corporate Research 755 College Road East Princeton, NJ 08540-6632 by 30 June 1993. We will also accept plain-text, stand-alone LaTeX or Postscript submissions sent by electronic mail to clnl93 at learning.scr.siemens.com Each submission will be refereed by the workshop organizers and evaluated based on its relevance to the theme, originality, clarity, and significance. Copies of accepted abstracts will be distributed at the workshop, and MIT Press has agreed to publish an edited volume that incorporates papers from the meeting, subject to revisions and additional reviewing. Invited Talks: Tom Dietterich Oregon State University Ron Rivest Massachusetts Institute of Technology Leo Breiman University of California, Berkeley Yann le Cun Bell Laboratories Important Dates: Deadline for submissions: 30 June 1993 Notification of acceptance: 20 July 1993 CLNL'93 Workshop: 10-12 September 1993 Organizing Committee: Russell Greiner, Steve Hanson, Stephen Judd, Pat Langley, Thomas Petsche, Ron Rivest, Tomaso Poggio Registration Information is available from clnl93 at learning.scr.siemens.com or the above address. From shavlik at cs.wisc.edu Thu Apr 29 15:30:13 1993 From: shavlik at cs.wisc.edu (Jude Shavlik) Date: Thu, 29 Apr 93 14:30:13 -0500 Subject: Symbolic Knowledge and Neural Learning: MLj Special Issue CFP Message-ID: <9304291930.AA01035@steves.cs.wisc.edu> CALL FOR PAPERS for a Special Issue of the Journal MACHINE LEARNING on SYMBOLIC KNOWLEDGE AND NEURAL LEARNING (edited by C. L. Giles and J. W. Shavlik) This special issue will focus on novel and effective methods for acquiring and refining symbolic knowledge with neural learning. Particular topics of interest include insertion of prior knowledge into neural networks, alterations to standard neural training that are appropriate for the refinement of symbolic knowledge, and understanding trained neural networks. Submission deadline: November 1, 1993 (See a recent issue of Machine Learning for information for authors.) Send two (2) copies of submissions to: Jude Shavlik Computer Sciences Dept University of Wisconsin 1210 W. Dayton Street Madison, WI 53706 USA (608) 262-7784 shavlik at cs.wisc.edu Also mail four (4) copies of submitted papers to: Karen Cullen MACHINE LEARNING Editorial Office Kluwer Academic Publishers 101 Philip Drive Norwell, MA 02061 USA (617) 871-6300 karen at world.std.com Note: Machine Learning is now accepting submission of final copy in electronic form. There is a latex style file and related files available via anonymous ftp from world.std.com. Look in Kluwer/styles/journals for the files machl.sty, machl.doc, jpsfonts.sty, joursamp.tex, and jourtmpl.tex. From dario at cns.nyu.edu Fri Apr 30 09:31:34 1993 From: dario at cns.nyu.edu (Dario Ringach) Date: Fri, 30 Apr 93 09:31:34 EDT Subject: Brain Development Symposium in June Message-ID: <9304301331.AA20221@wotan.cns.nyu.edu> From tony at wotan.cns.nyu.edu Mon Apr 26 15:12:09 1993 From: tony at wotan.cns.nyu.edu (Tony Movshon) Date: Mon, 26 Apr 1993 15:12:09 -0400 Subject: Brain Development Symposium in June Message-ID: THE DEVELOPMENT OF BRAIN FUNCTION An International Symposium at New York University June 15 - 19, 1993 The Center for Neural Science at Scientific sessions will cover: New York University will hold its second International Symposium, o Cell-cell interactions The Development of Brain Function, at the Washington Square campus in o Migration and differentiation June, 1993. The symposium will begin on Tuesday afternoon, June o Neuroethological perspectives 15th, and end at lunchtime on Saturday, June 19th. The program o Activity-dependent processes will concentrate on areas of developmental neuroscience that o Visual and auditory function have seen substantial progress in recent years. The 40 distinguished o Connections and architecture invited speakers will cover topics of cortex that range from molecular and cel- lular mechanisms of brain develop- o Development of higher brain ment to analyses of infant function behavior. The symposium will be open to up to 400 attendees. The symposium is supported in part Registration cost is $75 ($40 for by an education grant from the students). Howard Hughes Medical Institute. Speakers Israel Abramov Darcy Kelley Chiye Aoki Lynne Kiorpes Jocelyn Bachevalier Eric Knudsen Martin Banks Patricia Kuhl Elizabeth Bates Arthur Lander Colin Blakemore Susan McConnell Tobias Bonhoeffer Kenneth Miller Sarah Bottjer David Moore Thomas Carew Anthony Movshon Connie Cepko Paul Patterson Martha Constantine-Paton Pasko Rakic Michael Friedlander Edwin Rubel Lincoln Gray Dan Sanes Ralph Greenspan Joshua Sanes Martin Grumet Carla Shatz Jeff Hall Nicholas Spitzer Mary Beth Hatten Michael Stryker Susan Hockfield Davida Teller Thomas Jessell Tim Tully Lawrence Katz Lynne Werner For further information, please contact: Jeanette Tacoronte Phone: 212 998-3949 Center for Neural Science New York University FAX: 212 995-4011 4 Washington Place, Room 809 New York, NY 10003 Email: symposium at cns.nyu.edu ************************************************************************ A complete program is available in electronic form. You can print the following page and use it as a registration form. ************************************************************************ THE DEVELOPMENT OF BRAIN FUNCTION An International Symposium at New York University June 15 - 19, 1993 REGISTRATION FORM Name: ______________________________________________________ Address: ______________________________________________________ ______________________________________________________ ______________________________________________________ Phone: ______________________________________________________ FAX: ______________________________________________________ E-mail: ______________________________________________________ REGISTRATION FEES Regular: $75, Student*: $40 *Students should document their status with a letter from their sponsor HOUSING Please check here to receive information about local hotels____________ PAYMENT Enclose a check or money order in US $ payable to New York University. Amount enclosed: $_______________ Return completed form to: The Development of Brain Function Center for Neural Science New York University 4 Washington Place, Room 809 New York, NY 10003 Phone: (212) 998-3949 FAX: (212) 995-4011 E-mail:symposium at cns.nyu.edu From annette at cdu.ucl.ac.uk Fri Apr 30 17:31:41 1993 From: annette at cdu.ucl.ac.uk (Annette Karmiloff-Smith) Date: Fri, 30 Apr 93 17:31:41 BST Subject: PhD in London Message-ID: <9304301631.AA06652@cdu.ucl.ac.uk> PhD STUDENTSHIP A Medical Research Council studentship for a PhD is available at the MRC Cognitive Development Unit in London (jointly with University College London), for three years from October 1993, for a student particularly interested in the cognitive aspects of abnormal development and how such studies also be used to further our understanding of the normal mind/brain. The CDU works on both normal and abnormal cognition (focal lesion infants, Down syndrome, autism, dyslexia, etc.) and has recently started a new project on Williams syndrome, a genetic disorder that leaves language, face processing and theory of mind relatively spared, in the face of severe deficits in number, spatial cognition and problem- solving. This offers exciting new possibilities for a bright, inquisitive scientific mind, in a relatively unchartered field of enquiry. Competence/interest in connectionist modelling would be an added advantage. The CDU is a small and very lively group of scientists with varied interests and common theoretical concerns. Students with or expecting a first class or upper second degree in cognitive science, psychology, or other related fields, should send CV and a brief outline of research interests, by 31st May latest, to: Professor Annette Karmiloff-Smith, Medical Research Council, Cognitive Development Unit, 17 Gordon Street, London, WC1H OAH. tel: 071 387 4692 fax: 071 383 0398 From DUDZIAK at vms.cis.pitt.edu Fri Apr 30 00:39:00 1993 From: DUDZIAK at vms.cis.pitt.edu (MARTIN DUDZIAK) Date: Thu, 29 Apr 1993 23:39 EST Subject: Announcement Message-ID: <01GXLNYZL448AIF6JQ@vms.cis.pitt.edu> Announcement Please Circulate to Faculty and Researchers in Physics, Computer Science, Economics, Mathematics, Business Schools There are some interesting opportunities for university/industry collaboration in the area of applying non-linear dynamical systems, including but not limited to connectionist networks, to problems in financial modeling within the banking sector. The projects for which I am responsible including modeling of fixed-income securities, forecasting of demand deposit accounts, improvments to traditional duration/market value models, forecasting select futures/commodities, and analysis of interest rate risks. We are somewhat less interested in the traditional stock-price forecasting applications for which there has been so much visibility of late and are more interested in the use of techniques such as NNs, fuzzy logic, chaos models and genetic algorithms for the identification and discrimination of useful features and parameters that can be applied to forecasting some rather indeterminate quantities. Our work is not a short-order task and we are looking for an academic partner with whom we might establish a long-term partnership. There are plenty of precedents for good collaborations of this sort on which we might model our joint effort. We envision building a set of tools that can be refined in the course of studying one or two particular problems from the above set and which as a toolset could be made available for use on other problems besides those of interest to those in finance and economics. Our problems are such that they are both real-world, down-to-earth applications in need of practical solutions and research-worthy in that not too much has been done in some of these topics. There is good thesis material, and good opportunity for breaking new ground. For instance, I see strong parallels between the currency balances and flows that we are trying to model and fluid dynamics... Cellular automata and parallel processing are two other methods that could be applied to some of these problems - it isn't just a matter of time series prediction (not to imply that the latter is trivial). A prior research track in the financial area is not as critical as an ability to work together on some practical problems (but without losing the spirit of scientific exploration and innovation). Being able to cooperatively show results and demonstrations of practical success is going to be very important. This is an introductory announcement of interest on our part and I welcome responses from individuals and groups that feel they have a common interest and something to contribute. I believe that a highly synergetic and mutually rewarding partnership is possible with the right team. For further information, please contact: Martin Dudziak (804) 782-5708 FAX (804) 782-5100 dudziak at vms.cis.pitt.edu From jls at computer-science.manchester.ac.uk Wed Apr 28 14:04:04 1993 From: jls at computer-science.manchester.ac.uk (Jon Shapiro) Date: Wed, 28 Apr 93 14:04:04 BST Subject: Research Posts Message-ID: <9304281304.AA12225@r8q.cs.man.ac.uk> Two Research Posts Department of Psychology, University of Lancaster Department of Computer Science, University of Manchester Short-term memory for verbal sequences: psychological experiments and connectionist modelling. Applications are invited for two posts on a research project investigating short-term memory mechanisms for processing verbal information. The first post is for a postdoctoral researcher to work with Dr. Jonathan Shapiro at Manchester on connectionist modelling and analysis. The second post is for a graduate researcher to assist Professor Graham Hitch with the psychological experiments. Both post can begin as soon as possible and run through December 1995. Applicants for the modelling post should have expertise in computational and mathematical aspects of connectionism and a Ph.D. in a relevant subject. The salary range is 15,221 - 16,629 U.K. pounds based on age and experience. Applicants for the experimental post should have a first degree in psychology, and interests in memory and cognition. The salary range is 13,632 - 15,221 U.K. pounds. To apply for either post, send curriculum vita and the names and addresses of two professional referees to the address below. Closing Date: 14th of May. ------------------------------------------------------------------------- Jonathan Shapiro Computer Science Dept University of Manchester Oxford Road Manchester M13 9PL United Kingdom. Phone: 44-(0)61 275 6253 Fax: 44-(0)61 275 6236 E-mail: jls at cs.man.ac.uk From DUDZIAK at vms.cis.pitt.edu Fri Apr 30 00:39:00 1993 From: DUDZIAK at vms.cis.pitt.edu (MARTIN DUDZIAK) Date: Thu, 29 Apr 1993 23:39 EST Subject: Announcement Message-ID: <01GXLO0HM58SAIF6JQ@vms.cis.pitt.edu> ANNOUNCEMENT Richmond VA Area SIG on NNs and NLDs Forming An informal special interest group on neural and non-linear dynamical systems is forming, oriented to people in the Richmond and east/central Virginia area. There is currently no organizational affiliation and what directions this group takes depends upon the response and participation of interested persons. The intent here is to bring together people who may otherwise be somewhat isolated by virtue of working in diverse industries or centers, academic or corporate, and who could benefit by reason of verbal and electronic exchanges. My initial sense is that there is more going on in this part of the country and state than appears at first glance, and while Richmond may seem so close to Baltimore/Washington D.C. as a major technology arena, it really isn't. If you are interested, please contact me and we will see where this goes. One idea is to have a monthly seminar with an invited talk; convenient facilities can be easily provided. Martin Dudziak Crestar Bank (804) 782-5708 dudziak at vms.cis.pitt.edu From cabestan at eel.upc.es Fri Apr 30 17:20:12 1993 From: cabestan at eel.upc.es (Joan Cabestany) Date: Fri, 30 Apr 1993 17:20:12 UTC+0100 Subject: registration and conference program: IWANN'93 Message-ID: INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORK IWANN'93 FINAL PROGRAMME Sitges (Barcelona), Spain June 9 - 11, 1993 SPONSORED BY IFIP (Working Group in Neural Computer Systems, WG10.6) IEEE Neural Networks Council UK&RI communication chapter of IEEE Spanish Computer Society chapter of IEEE AEIA (IEEE Affiliate society) ORGANISED BY Universidad Politecnica de Catalunya Universidad Autonoma de Barcelona Universidad de Barcelona UNED (Madrid) IWANN'91 (International Workshop on Artificial Neural Networks) was held in Granada (Spain) in September 1991. People from over 10 countries attended the Workshop, and over 50 oral presentations were given. IWANN'93 is schedules for next June, 1993 in Sitges (Spain) with the following final program. WELCOME TO DELEGATES It is a pleasure to invite you to attend the second edition of INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORKS (IWANN'93) to be held in Sitges (Barcelona, Spain) from June 9 to June 11, 1993, following the first edition done in Granada (Spain) during September, 1991. IWANN's main objective is to offer a forum for achieving a global, informative and advanced prespective on Artificial Neural Networks. In addition to conventional Neural Networks aspects, IWANN'93 will also be concerned with complementary topics such as neural computation theory and methodology, local computation models, organization and structures resembling biological systems. The actual Workshop will consist of 111 papers arranged into technical sessions addressing the topics of Learning, Models, Biological perspectives, Hardware implementations, Self-Organizing networks and Organizational principles, Artificial vision, Control, Communications, Software, Signal processing and Applications. A total of six Invited Conferences will open their respective sessions to be held in Room A, and their objective is to focus the State-of-the-Art, and motivate discussion and participation. The Workshop is organized in cooperation with the Spanish RIG of the IEEE Neural Networks Society, and the IFIP WG 10.6, and, is sponsored by the spanish "Comisin Interministerial de Ciencia y Tecnologa" (CICYT), the catalan "Comissi Interdepartamental per a la Recerca i Tecnologia" (CIRIT), and the organizing Universities. Welcome to the Workshop. We hope that IWANN'93 will be scientifically very rewarding and a good oportunity to get to know our country. Enjoy Sitges and Barcelona, one of the most dynamic towns in Europe, and meet people working in different topics of Neural Networks field. The IWANN'93 Committees look forward to seeing you there. Prof. Albert Prieto General Chaiman, IWANN'93 COMMITTEE OF HONOUR Chairman Molt Honorable Sr. Jordi Pujol i Soley President of the Catalan Government Excm. Sr. Jordi Serra i Villalb Mayor of Sitges Honorable Sr. Antoni Subir i Claus Minister of Industry and Energy Sr. Josep Laporte i Sala President of the CIRIT Sr. Alberto Prieto President of IWANN'93 Congress ORGANIZING COMMITTEE Chairman Jos Mira UNED. Madrid (E) Senn Barro Univ. de Santiago (E) Joan Cabestany Univ. Pltca. de Catalua (E) Trevor Clarkson King's College London (UK) Ana Delgado UNED. Madrid (E) Federico Morn Univ. Complutense. Madrid (E) Conrad Prez Univ. Autnoma de Catalua (E) Francisco Sandoval Univ. de Mlaga (E) Elena Valderrama CNM- Univ. Autnoma de Barcelona (E) LOCAL COMMITTEE Chairman Joan Cabestany Univ. Pltca. de Catalua (E) Jordi Carrabina CNM-Univ. Autnoma de Barcelona (E) Francisco Castillo Univ. Pltca. de Catalua (E) Andreu Catal Univ. Pltca. de Catalua (E) Gabriela Cembrano Inst. de Ciberntica. CSIC. Barcelona (E) Conrad Prez Univ. de Barcelona (E) Elena Valderrama CNM-UNIv. Autnoma de Barcelona (E) PROGRAMME COMMITTEE Chairman Jos Mira UNED. Madrid (E) Sanjeev B. Ahuja Nielsen A.I.Research & Development. Bannokburn (USA) Igor Aleksander Imperial College. London (UK) Lus B. Almeida INESC. Lisboa (P) Shun-ichi Amari Faculty of Engineering. Univ. Tokyo (Jp) Xavier Arreguit CSEM SA (CH) Franois Blayo LERI-EERIE. Nimes (F) Colin Campbell University of Bristol. (UK) Leon Chua Univ. of California. Berkeley (USA) Trevor Clarkson King's College London (UK) Michael Cosnard Ecole Normale Superieure de Lyon (F) Marie Cottrell Univ. Paris I (F) Dante Del Corso Politecnico di Torino (I) Gerard Dreyfus ESPCI. Paris (F) F.K. Fogelman-Soulie Mimetics. Chatenay Malabry (F) J. Simoes da Fonseca Univ. de Lisboa (P) Kunihiko Fukushima Faculty of Engineering Science. Osaka University (Jp) Karl Goser Univ. Dortmund (D) Hans Peter Graf AT&T Bell Lab., New Jersey (USA) Francesco Gregoretti Politecnico di Torino (I) Karl E. Grosspietsch Mathematik und Datenverarbeitung (GMD). St. Agustin (D) Mohamad H. Hassoun Wayne State University (USA) Jeanny Herault INPG Grenoble (F) Jaap Hoekstra Delft University of Technology (NL) P.T.W. Hudson Faculteit der Sociale Wetenschappen. Leiden University (NL) Jos Lus Huertas CNM- Universidad de Sevilla (E) Paul G.A. Jespers Universit Catholique de Louvain (B) Simon Jones IERI Loughborough Univ. of Technology (UK) Christian Jutten INPG Grenoble (F) H. Klar Inst. fr Mikroelektronik. Technische Universitt Berlin (D) Michael D. Lemmon Univ. of Notre Dame. Notre Dame (USA) Panos A. Ligomenides Univ. of Maryland (USA) Javier Lpez Aligu Univ. de Extremadura (E) Robert J. Marks II Univ. of Washington (USA) Anthony N. Michel Univ. of Notre Dame. Notre Dame (USA) Roberto Moreno Univ. Las Palmas de Gran Canaria (E) Josef A. Nossek Inst. of Network Theory and Circuit Design. Tech. Univ. of Munich (D) Francisco J. Pelayo Univ. de Granada (E) Franz Pichler Johannes Kepler Univ. (A) Ulrich Ramacher Siemens AG. Munich (D) Tmas Roska Comp. & Aut. Res. Inst. Hungarian Academy of Science. Budapest (H) Leonardo Reyneri Univ. di Pisa (I) Peter A. Rounce Dept. Computer Science. Univ. College London (UK) V.B. David Snchez German Aerospace Research Establishment. Wessling (G) E. Snchez-Sinencio Texas A&M University (USA) David Sherrington Dept. of Physics. Univ. of Oxford (UK) Renato Stefanelli Politecnico di Milano (I) T.J. Stonham Brunel-University of West London (UK) John G. Taylor Centre for Neural Networks. King's College London (UK) Carme Torras Inst. de Ciberntica. CSCI. Barcelona (E) Philip Treleaven Dept. Computer Science. Univ. College London (UK) Marley Vellasco Ponti. Univ. Catlica. Rio de Janeiro (BR) Michel Verleysen Univ. Catholique de Louvain (B) Michel Weinfeld Ecole Polytechnique Paris (F) WEDNESDAY, 9TH . JUNE 09:00 Hr. ROOM A Mathematical topics on Neural Learning. Prof S. Amari and Prof.N. Murata University of Tokyo. Moderator: E. Valderrama. Spain. 10:00 Hr. ROOM A Learning - I Chairman: Prof.S. Amari. Japan. * Self-organizing Grammar Induction using a Neural Network Model. C. Mannes. Boston University.(USA) * The role of forgetting in learning Strategies for Self-organizing Discriminator-based Systems. G. Tambouratzis and T.J. Stonham Brunel University.(UK) * Simulation of Stochastic Regular Grammars through simple recurrent Networks. M.A. Castao, E. Vidal and F. Casacuberta. Univ. Politcnica de Valencia.(E) * Local Stochastic Competition and Vector Quantization. M. Graa, A. D'Anjou, F.X. Albizuri, F.J. Torrealdea, M.C. Hernndez. CCIA Univ. del Pas Vasco.(E) ROOM B Signal processing - I Chairman:Prof.M.A.Lagunas. Spain. * Projectivity invariant Pattern Recognition with high-order Neural Networks. G. Joya and F. Sandoval. Universidad de Mlaga.(E) * Rejection of incorrect answer from a Neural net classifier. F.J. Smieja German National Research Centre for Computer Science (GMD) (D) * Nonlinear Time series modeling by Competitive Segmentation of State Space. C.J. Pantalen and A.R. Figueiras. Univ. Cantabria. UPM, Cdad. Univ.(E) * Identification and Prediction of Non-linear models with recurrant Neural Network. O. Adam, J.L. Zarader and M. Milgram Lab. Robotique de Paris(FR) ROOM C Biological Perspectives - I Chairman: Prof. J. Hoekstra. The Netherlands. * Integrated Learning in Rana Computatrix. F.J. Corbacho and M.A. Arbib. University of Southern California.(USA) * A model for visual stimuli centering through adaptive value learning. A. Murciano, J. Zamora and M. Reviriego. Univ. Complutense de Madrid.(E) * A model for the development of neurons selective to visual stimulus size. M.A. Andrade and F. Morn. Univ. Complutense de Madrid. 11:20 Hr. COFFEE BREAK 11:50 Hr. ROOM A Organizational Principles - I Chairman: Prof. M. Verleysen. Belgium. * Optimized learning for improving the evolution of piecewise linear separation incremental algorithms. J.M. Moreno, F. Castillo and J. Cabestany. Univ. Politcnica de Catalunya.(E) * A Method of Pruning Layered Feed-forward Neural Networks. M. Pelillo and A.M. Fanelli. Universit di Bari.(I) * MLP Modular versus YPREL Classifiers. Y. Lecourtier , B. Dorizzi 1, P. Sebire 1, and A. Ennaji. Univ. de Rouen, (1) Inst. Nac. des Tlcommunications.(FR) * Test of different regularization terms in small Networks. J.L. Crespo and E. Mora. Univ. de Cantabria.(E) * How many hidden neurons are needed to recognize a symmetrical pattern?. J. Patinel 1, G. Leone 2, and M. Maurice 3. (1) Lab. d'Intelligence Artificielle, (2) Lab. de Physiologie Neurosens., (3) Lab. de Robotique de Paris.(FR) ROOM B Communication Systems Chairman: Prof. T. Clarkson. United Kigdom. * Hopfield Neural Network for Routing. S. Cavalieri, A. Di Stefano and O. Mirabella. Universita' di Catania.(I) * Neural network Routing Controller for Communication parallel Multistage Interconnection Networks. A. Garca, A. Daz, F. Garca and F. Sandoval. Universidad de Mlaga.(E) * Adaptive Routing using Cellular Automata. J. Minot Lab. d'Electronique Philips.(FR) * Optimal blind Equalization of Gaussian channels. J. Cid 1, L. Weruaga and A.R. Figueiras. (1) Univ. de Valladolid. Univ. Politcnica de Madrid.(E) ROOM C Theoretical Models - I Chairman: Prof. F. Morn. Spain. * A Node Splitting Algorithm that reduces the number of connections in a hamming distance classifying Network. H. Hning. Aachen Univ. of Technology.(D) * A high order Neural Model. F.J. Lpez, M.I. Acevedo and M. Jaramillo. Univ. de Extremadura.(E) * Higher-order Networks for the optimization of Block Designs. P. Bofill and C. Torras. Univ. Politcnica de Catalunya.(E) * Region of influence (ROI) Networks. Model and Implementation. F. Castillo 1, J. Cabestany and J.M. Moreno. (1) E.U.P. E.T.S.E. Telecomunicacin.(E) 13:00 Hr. LUNCH 15:00 Hr. Hybrid Programming Environments: integrating neural networks, genetic algorithms and rule- based systems. Prof.P.C. Treleaven and P.V. Rocha. University College London. Moderator: Prof. A. Prieto. Spain. 16:00 Hr. ROOM A Software - I Chairman: Prof. P. Treleaven. United Kingdom. * Automatic Generation of C++ Code for Neural Network Simulation. S. Dreiseitl and D. Wang. Johannes Kepler University.(A) * Urano: an Object-oriented Artificial neural Network Simulation Tool. L. Fuentes, J.F. Aldana and J.M. Troya. Universidad de Mlaga.(E) * Realistic Simulation Tool for early visual Processing including Space, Time and Colour Data. W. Beaudot, P. Palagi and J. Hrault. Inst. National Polytechnique de Grenoble.(FR) ROOM B Hardware - I Chairman: Prof. K. Goser. Germany. * A Neural Network Chip using CPWM Modulation. M. Chiaberge, D. del Corso, F. Gregoretti and L.M. Reyneri. Politecnico di Torino.(I) * Hardware implementation of a Neural Network for High Energy Physics application. J. Carrabina, F. Lisa, V. Gaitan, L. Garrido and E. Valderrama. Univ. Autnoma de Barcelona.(E) * An array processor Architecture for Neural Networks. J. Ortega, F.J. Pelayo, A. Prieto, B. Pino and C.G. Puntonet. Univ. de Granada.(E) * Limitation of connectionism in MLP. C.V. Regueiro, S. Barro and A. Yez 1. Univ. de Santiago de Compostela.(1) Univ. de La Corua.(E) ROOM C Cognitive Science Chairman: Prof. S. Barro. Spain. * A Neural state machine for iconic language representation. I. Aleksander 1 and H. Morton 2. (1) Imperial College, London. (2) Brunel University.(UK) * Variable binding using serial order in recurrent Neural Networks. J. Lpez and J. Sopena. Univ. de Barcelona.(E) * Planlite: Adaptive planning using weightless systems. J. Mrsic. Imperial College, London.(UK) * An adaptive information retrieval system based on Neural Networks. F. Crestani. Univ. di Padova.(I) 17:20 Hr. COFFEE BREAK 17:50 Hr. ROOM A Organizational Principles - II Chairman: Prof. M. Cottrell. France. * Comparative Study of Self-organizing Neural Networks. C. Wann and S. Thomopoulos. The Pennsylvania State Univ.(USA) * GANNet: A Genetic Algorithm for optimizing Topology and weight in Neural Network design. D.W. White and P.A. Ligomenides. Univ. of Maryland.(USA) * Full automatic ann design: A Genetic approach. E. Alba, J.F. Aldana and J.M. Troya. Univ. de Mlaga.(E) ROOM B Software - II Chairman: Prof. J. Lpez. Spain. * Language supported Storage and Reuse of persistent Neural Network Objects. C. Burdorf. Univ. of Bath.(UK) * Flexible operating environment for Matrix Based Neurocomputers. J.C. Taylor, M.L. Recce and A.S. Mangat. Univ. College London.(UK) * A parallel Implementation of Kohonen's self-organizing Maps on the Smart Neurocomputer. E. Filippi 1, and J.C. Lawson 2. (1) Politecnico di Torino.(I) (2) INPG, Labo TIRF, Grenoble.(FR) ROOM C Theoretical Models - II Chairman: Prof. F. Castillo. Spain. * Neural bayesian Classifier. C. Jutten. INPG, Labo TIRF, Grenoble. P. Comon.(FR) * Constructive Methods for a new Classifier based on a Radial-Basis-Function Neural Network accelerated by a tree. P. Gentric and H. Withagen. Lab. d'Electronique Philips.(FR * Practical realization of a Radial Basis Function Network for handwritten digit recognition. B. Lemari. La Poste, Nantes.(FR) * Design of Fully and Partially connected Random Neural Networks fos Pattern Completion. C. Hubert. Univ. Ren Descartes.(FR) THURSDAY, 10TH. JUNE 09:00 Hr. ROOM A The Kolmogorov Signal processor. Prof. M.A. Lagunas, A. Prez, M. Najar, A. Pags. UPC TSC Department. Spain Moderator: Prof. C. Jutten. France. 10:00 Hr. ROOM A Signal Processing - II Chairman: Prof. C. Jutten. France. * Use of Unsupervised Neural Networks for classification of Blood Pressure Time Series. M.J. Rodrguez, F. del Pozo and M.T. Arredondo. Univ. Politcnica de Madrid.(E) * Aplication of Artificial Neural Networks to chest Image classification. J.J. Fernndez, A. Caas, E. Roca, F.J. Pelayo, J. Fernndez and A. Prieto. Univ. de Granada.(E) * Software Pattern EEG Recognition after a Wavelet transform by a Neural Network. P. Clochon, D. Clarencon, R. Caterini and V. Roman. INSERM.(FR) * Combination of Self-organizing Maps and Multilayer Perceptrons for Speaker Independent Isolated Word Recognition.J. Tuya, E. Arias, L. Snchez and J.A. Corrales. Univ. de Oviedo.(E) ROOM B Learning - II Chairman: Prof. F. Blayo. France. * MHC - An Evolutive Connectionist Model for Hybrid Training. J.M. Ramrez. Paradigma.(VEN) * Fast Convergenced Learning Algorithms for Multi-level and Binary Neurons and Solving of some Image Processing problems. N.N. Aizenberg, and I.N. Aizenberg 1. Univ. of Uzhgorod. (1) Joint Venture PGD.(UKR) * Invariant Object Recognition using Fahlman and Lebiere's Learning Algorithm. K. Ito, M. Hamamoto, J. Kamruzzaman and Y. Kumagai. Muroran Inst. of Technology.(JP) * Realization of Surjective Correspondence in Artificial Neural Network trained by Fahlman and Lebiere's Learning Algorithm. M. Hamamoto, K. Ito, J. Kamruzzaman and Y. Kumagai. Muroran Inst. of Technology.(JP) ROOM C Biological Perspectives - II Chairman: Prof. J. Mira. Spain. * An invariant Representation Mechanism after Presynaptic Inhibition. R. Moreno and O. Bolvar. Univ. de Las Palmas de Gran Canaria.(E) * The Pancreatic B-Cell as a Voltage-Controlles Oscillator. J.V. Snchez and B. Soria. Univ. de Alicante.(E) * Apprximation of the Solution of the Dendritic Cable Equation by a small series of Coupled Differential Equations. J. Hoekstra. Delft Univ. of Technology.(NL) * A Neural Network Model inspired in global appreciations about the Thalamic Reticular Nucleus and Cerebral Cortex Connectivity. J. Ropero. ICAI.(E) 11:20 Hr. COFFEE BREAK 11:50 Hr. ROOM A Applications - I Chairman: Prof. A. Prieto. Spain. * Noise Prediction in Urban Traffic by a Neural Approach. G.Cammarata, S. Cavalieri, A. Fichera and L. Marletta. Univ. di Catania.(I) * An industrial application of Neural Networks to Natural Textures classification. G. Yahiaoui and B. Borocco 2. cole Spciale de Mcanique et d'Electricit. (2) PSA Peugeot Citron.(FR) * Stock Prices and Volume in an Artificial adaptive Stock Market. S. Margarita and A. Beltratti. Univ. di Torino.(I) * Application of the Fuzzy Artmap Neural Network Architecture to Bank Failure Predictions. L.J. de Miguel, E. Revilla, J.M. Rodrguez and J.M. Cano. Univ. de Valladolid.(E) ROOM B Vector Quantizers Chairman: Prof. C. Prez. Spain. * Vector Quantization and Projection Neural Network. P. Demartines and J. Hrault. INPG, Labo. TIRF Grenoble.(FR) * Constructive Design of LVQ and DSM Classifiers. J.C. Prez and E. Vidal. Univ. Politcnica de Valencia.(E) * Linear Vector classification: an improvement on LVQ Algorithms to create classes of Patterns. M. Verleysen, P. Thissen and J.D. Legat. Univ. Catholique de Louvain.(B) * Non-Greedy adaptive Vector Quantizers. Z. Wang. Univ. of Waterloo.(CAN) ROOM C Theoretical Models - III Chairman: Prof. A. Catal. Spain. * Representation and Recognition of Regular Grammars by Means of Second-order recurrent Neural Networks. R. Alquzar and A. Sanfeliu. Inst. de Ciberntica (UPC-CSIC).(E) * Connectionist Models for Syllabic Recognition in the Time Domain. J. Santos and R.P. Otero. Univ. da Corua.(E) * Sparsely Interconnected Artificial Neural Networks for Associative Memories. D. Liu and A.N. Michel. Univ. of Notre Dame.(USA) * Dynamic Analysis of Networks of Neural Oscillators. A. Arenas and C.J. Prez. Univ. de Barcelona.(E) * Adaptive Models in Neural Networks. P.A. Ligomenides. Univ. of Maryland.(USA) 13:00 Hr. LUNCH 15:00 Hr. ROOM A Hardware Implementations of Artificial Neural Networks. Prof.D.Del Corso. Politecnico di Torino. Moderator: Prof. J. Cabestany. Spain. 16:00 Hr. ROOM A Hardware - II Chairman: Prof. D. Del Corso. Italy. * High Level Synthesis of Neural Network Chips. M.E. Nigri and P. Treleaven. Univ. College London.(UK) * Neural Network Simulations on massively parallel Computers: Applications in Chemical Physics. B.G. Sumpter, R.E. Guenther 1, C.Halloy 2, C. Getino and D.W. Noid. Oak Ride National Lab. (1) Univ. of Nebraska at Ohama. (2) Univ. of Tennessee.(USA) * A model based Approach to the Performance Analysis of Multi-Layer Networks realised in Linear Systolic Arrays. D. Naylor and S. Jones. Loughborough Univ. of Technology.(UK) * The temporal Noisy-Leaky Integrator Neuron with additional Inhibitory Inputs. G. Bugmann, C. Christodoulou, T.G. Clarkson and J.G. Taylor. King's College London.(UK) ROOM B Control & Robotics - I Chairman: Prof. C. Torras. Spain. * Neural Networks as Direct Adaptive Controllers. M. Bahrami. Univ. of New South Wales.(AUS) * A Neural Adaptive Controller for a Turbofan Exhaust Nozzle. C. Barret, M. Houkari, P. Meyne, J.M. Martnez 1, A. Garassino 2, and P. Tormo 2. Univ. Evry Val d'Essonne. (1) Commissariat l'Energie Atomique. (2) SNECMA Villaroche.(FR) * Feed-Forward Neural Networks for Bioreactor Control. A. Bulsari, B. Saxn and H. Saxn. bo Akademi.(FIN) ROOM C Artificial Vision - I Chairman: Prof. J. Herault. France. * A Connectionist Approach to the Correspondence Problem in Computer Vision. H. Sako and H.I. Avi-Itzhak 1. Hitachi Dublin Lab. (1) Stanford Univ.(IRE) * Self-Organizing Feature Maps for Image Segmentation. R. Natowicz and R. Sokol 1. E.S.I.E.E.. (1) Univ. de Paris.(FR) * Recognition of Fractal Images using a Network. B. Freisleben, J.H. Greve and J. Lber. Univ. of Darmstadt.(D) * Feed-Forward Network for Vehicle License Character Recognition. F. Lisa, J. Carrabina, C. Prez, N. Avellana and E. Valderrama. Univ. Autnoma de Barcelona.(E) END OF SESSIONS FRIDAY, 11TH. JUNE 09:00 Hr. ROOM A Biophysics of Neural Computation. Prof. K.N. Leibovic. Univ. of New York at Buffalo.USA Moderator: Prof. J. Mira. Spain. 10:00 Hr. ROOM A Biological Perspectives - III Chairman: Prof. K.N. Leibovic. U.S.A. * Towards more realistic Self Contained Models of Neurons: High-Order, Recurrence and Local Learning. J. Mira, A.E. Delgado, J.R. Alvarez, A.P. de Madrid and M. Santos. UNED.(E) * McCulloch's Neurons Revisited. R.J. Scott. Univ. of Maryland Baltimore County.(USA) * Biologically Motivated Approach to Face Recognition. N. Petkov, P. Kruizinga and T. Lourens.(NL) Rijksuniversiteit Groningen. * Learning by Reinforcement: a Psychobiological Model. F.J. Vico, F. Sandobal and J. Almaraz. Univ. de Mlaga.(E) ROOM B Learning - III Chairman: Prof. P. Ligomenides. U.S.A. * Bimodal Distribution Removal. P. Slade and T.D. Gedeon. Univ. of New South Wales.(AUS) * A simplified Artmap Architecture for Real-Time Learning. A. Guazzelli, D. Barone and E.C. de B. Carvalho Filho 1. Univ. Fed. do Rio Grande do Sul. (1) Univ. Fed. de Pernambuco.(BR) * B-Learning: a Reinforcement Learning Algorithm, Comparison with Dynamic Programming. T. Langlois and S. Canu. Lyonese des Eaux Dumez. Univ. de Technology de Compigne.(FR) * Increased Complexity Training. I. Cloete and J. Ludik. Univ. of Stellenbosch.(SA) ROOM C Artificial Vision - II Chairman: Prof. F. Sandoval. Spain. * Interpretation of Optical Flow through complex Neural Network. M. Miyauchi, M. Seki, A. Watanabe and A. Miyauchi. SANNO College, Musashi Inst. of Technology.(JP) * CT Image Segmentation by Self-Organizing Learning. D. Cabello, M.G. Penedo, S. Barro, J.M. Pardo and J. Heras. Univ. de Santiago de Compostela.(E) * Texture Image Segmentation using a modified Hopfield Network. A. Mosquera, D. Cabello, M.J. Carreira and M.G. Penedo. Univ. de Santiago de Compostela.(E) * Image Compression with Self-Organizing Networks. B. Freisleben and M. Mengel. Univ. of Darmstadt.(D) 11:20 Hr. COFFEE BREAK 11:50 Hr. ROOM A Applications - II Chairman: Prof. G. Cembrano. Spain. * Use of a Layered Neural Nets as a Display Method for N-Dimensional Distributions. L. Garrido 1-2, V. Gaitan 2, M. Serra 3 and X. Calbet 3. (E) (1) Univ. de Barcelona. (2) Univ. Autnoma de Barcelona. (3) Inst. de Astrofsica de Canarias. * Simulation of Neural Networks in a Distributed Computing Environment using NeuroGraph. P. Wilke. Univ. Erlangen-Nuernberg.(D) * Combination of Neural Network and Statistical Methods for Sensory Evaluation of Biological Products: on-line Beaty Selection of Flowers. F. Ros, A. Brons, f. Sevila, G. Rabatel and C. Touzet (1). CEMAGREF. (1) LERI-ERIEE.(FR) ROOM B Self-Organizing Networks Chairman: Prof. E. Valderrama. Spain. * On the Distribution of Feature Space in Self-Organizing Mapping and Convergence Accelerating by a Kalman Algorithm. H. Yin and N.M. Allinson. Univ. of York.(UK) * A learning Algorithm to Obtain Self-Organizing Maps using Fixed Neighbourhood Kohonen Networks. P. Martin, F.J. Pelayo, A. Daz, J. Ortega and A. Prieto. Univ. de Granada.(E) * Analysing a Contingency Table with Kohonen Maps: a Factorial Correspondence Analysis. M. Cottrell, P. Letremy and E. Roy. Univ. de Paris.(FR) * Dynamics of Self-Organized Feature Mapping. R. Der, T. Willmann. Univ. Leipzig.(D) ROOM C Theoretical Models - IV Chairman: F. Pelayo. Spain. * Optimised Attractor Neural Networks with External Inputs. A.N. Burkitt. Australian National Univ.(AUS) * Non-Orthogonal Bases and Metric Tensors: some Applications to Biology and Artificial Neural Networks. K. Weigl and M. Berthod. INRIA.(FR) * Genetic Synthesis of Discrete-Time Recurrent Neural Network. F.J. Marn and F. Sandoval. Univ. de Mlaga.(E) * Optimization of a Competitive Learning Neural Network by Genetic Algorithms. J.J. Merelo, M. Patn, A. Caas, A. Prieto and F. Morn 1. Univ. de Granada. (1) Univ. Complutense de Madrid.(E) 13:00 Hr. LUNCH 15:00 Hr. ROOM A Networks for Estimation, Control and Robotics. Prof. J.J.E. Slotine, RM Sanner MIT (USA) Moderator: Prof. C. Torras. Spain. 16:00 Hr. ROOM A Control & Robotics - II Chairman: Prof.J.J.E.Slotine. U.S.A. * Learning Networks for Process Identification and Associative Action. L. Borland and H. Haken. Univ. of Stuttgart.(D) * On-line Performance Enhancement of a Behavioral Neural Network Controller. J.R. Pimentel, D. Gachet, L. Moreno and M.A. Salichs. Univ. Politcnica de Madrid.(E) * An Architecture for Implementing Control and Signal Processing Neural Networks. R.P. Palmer and P.A. Rounce. Univ. College London.(UK) ROOM B Hardware - III Chairman: Prof. S. Jones. United Kingdom. * Architectures for Self-Learning Neural Network Modules. T.G. Clarkson and C.K. Ng. King's College London.(UK) * The Generic Neuron Architectural Framework for the Automatic Generation of ASICs. M.M.B.R. Vellasco and P.C. Treleaven 1. Pontificia Univ. Catlica do Rio de Janeiro.(BR) (1) Univ. College London.(UK) * A Risc Architecture to Support Neural Net Simulation. M. Pacheco and P.C. Treleaven 1. Pontificia Univ. Catlica do Rio de Janeiro.(BR). (1) Univ. College London.(UK) * Hardware Design for Self-Organizing Feature Maps with Binary Input Vestors. S. Rping, U. Rckert and K. Goser. Univ. of Dortmund.(D) ACCOMPANYING PERSONS PROGRAMME Tuesday, 8th. June 20:00 Hrs. Welcome Reception at "Maricel" Palace. Wednesday, 9th. June 09:30 Hrs. HISTORICAL AND ARTISTIC CITY TOUR OF BARCELONA. Including: The Gothic Quarter, the 14th Century Gothic Cathedral, the "Paseo de Gracia" where the most important Modernist buildings are placed, the Sagrada Familia, etc. Thursday, 10th. June 09:30 SITGES CITY TOUR AND MUSEUMS. Sitges is a summer and international tourism resort. The white washed houses, the seaside boulevard and the church on the sea create a beautiful and pleasant ensemble. Artists, such as Rusiol or Utrillo, already discovered its charm at the end of the XIXth century. The Cau Ferrat Museum and the Maricel Museum, display beautiful samples of the Catalan modern art. 21:00 Gala Dinner at Great Casino of Sitges. GENERAL INFORMATION CONGRESS VENUE The IWANN'93 Congress will be held in Sitges, a city located 35 Km. south of Barcelona. All sessions will take place at GRAN SITGES HOTEL: Gran Sitges Hotel Port d'Aiguadol 08870 Sitges (Barcelona) Spain TRANSPORTATION TO SITGES By air: The Barcelona-El Prat International Airport is linked to Barcelona by rail (Barcelona Sants Station) every 30 minutes, by bus (Aerobus) every 15 minutes, and by taxi. Sitges is also linked to the airport by rail, changing train in El Prat Station or through Barcelona Sants Station. By Rail: Internationals direct lines to Barcelona (Francia and Sants) Stations come from Geneva and Bern (Switzerland), Paris (France) and Milan (Italy). There are also many trains from Madrid, some of them overnight. Sitges is linked to Barcelona Sants Station by local trains every 15-30 minutes. By Road: Motorway A-17/7 from La Jonquera (at the French border) links up with the French motorway network; and thence, Great Britain and all northern and eastern countries. Motorway A-7 to the west and south connects Barcelona with the rest of Spain. Sitges is linked to Barcelona city and Airport by Motorway A-16 and country road C-246. HOTEL RESERVATIONS A number of rooms in different prices and categories have been booked in Sitges for the Congress attendants. Reservations made through the General Secretariat by registration form have a special price in all Hotels. Payment of a deposit per room will be necessary to confirm any hotel reservation. This amount will be deducted from your hotel invoice. See official list and map of the city attached in the back cover of this programme. Please consult special rates for consolidated groups (minimum 20 persons). OFFICIAL LANGUAGES AND SIMULTANEOUS TRANSLATION English will be the official language of IWANN'93. Simulaneous translation will not be provided. DOCUMENTATION AND INFORMATION Congress documents, personal budgets, and tickets will be handed over to attendants and accompanying persons at the Congres Secretariat from Tuesday 8th June to Friday 11th June. The Secretariat will be open every day from the begining to the end of the work sessions. REGISTRATION Registration and payment of fees will be absolutely necessary so as to attend the Workshop sessions and social events. On site registration is discouraged in order to avoid queueing. Registration Fees include: Attendants Accompanying Persons - Welcome reception - Welcome reception - Proccedings - Barcelona City Tour - Attendance to all Scientific Meetings - Sitges City Tour and Museums - Coffee Breaks - Gala Dinner - Gala Dinner Basic Inscription Economy Inscription - Proccedings - Attendance to all Scientific Meetings - Attendance to all Scientific Meetings - Coffee Breaks - Coffee Breaks SOCIAL EVENTS Tuesday 8th June 20:00 Hrs. Welcome Reception at "Maricel" Palace, the historical and cultural centre of Sitges which is overlooking the sea. This Palace, at present a museum, is a sample of the Catalan modern art ("Modernism"). Thursday 10th June 21:00 Hrs. Gala Dinner at Great Casino of Sitges located in Sant Pere de Ribes, 5Km. far from Sitges. This construction was built at the end of 19th. century in Catalan- Renaissance style. It's spacious halls are beautifully decorated and the access to the Casino is a long boulevard with cypresses and period street lamps. An unforgettable setting!.Free entrance to the Casino after the dinner showing the passport or D.N.I. OPTIONAL TOURS Optional Tours and Excursions will be organized on Saturday and Sunday for the attendants wishing to extend their stay after the Workshop. Caves and Montserrat (full day) Price : 7.500.- Ptas (Minimum 30 persons) We will visit a famous Caves of Sant Sadurn d'Anoia (placed on the most important wine- producing region of Catalonia). Lunch. Montserrat is a unique mountain located at a height of 1.235 mts.. In the Royal basilica is placed the famous Black Virgin. We will listen to the "Escolanets", the oldest child chorus in Europe. Modernism in Barcelona (half day) Price : 3.500.- Ptas (Minimum 30 persons) During this tour you can see the most important modernist works of Barcelona. Some houses located at the Paseo de Gracia, built with the particular imagination of the architects, painters and sculptors of the beginning of this century; the Holy Family Church, the still unfinished masterpiece of striking originality, begun in 1884 by A. Gaudi; the Gell Park, initially created as a Garden City and today a public park. Girona and Dal Museum (full day) Price : 8.000.- Ptas (Minimum 30 persons) Founded in ancient times, Girona preserves numerous vestiges of its Roman, Christian, Arab and Frankish past. From the 12th century to the present, it has witnessed the Catalonian War of Secession; the war against Louis XIV; the siege mounted by Philip V, and the defense against Napoleonic forces. The inner city is one of the most beautiful and best preserved in Spain. It consists of a number of steep, narrow streets, sometimes porticoed, that converge onto flights of stairs leading to different street levels and up to the Cathedral. Lunch. At Figueres, capital of Ampurdan region, we will visit the famous Dali Theater-Museum, the most visited one in Spain, after the Prado. Many works of this recently died genious artist are displayed in an original way. CANCELLATION OF REGISTRATION Notification of cancellation must be sent in writing to ULTRAMAR CONGRESS and will be accepted until April 30th., 1993 with refund of fees except a cancellation charge of 25%. No refunds can be made for cancellation received after April 30th., 1993. Refunds will be dealt with after the Congress. GENERAL SECRETARIAT For any matters related to correspondance, registration forms, payment of fees, hotel reservation, deposit, etc., please contact: ULTRAMAR CONGRESS Diputaci, 238 3 08007 Barcelona Tel. (34-3) 317.37.00 - Fax. (34-3) 412.03.19 __________________________________________________________________________________________________ REGISTRATION FORM **************************************************************************** IWANN'93 INTERNATIONAL WORKSHOP ON ARTIFICIAL NEURAL NETWORKS SITGES (BARCELONA) Spain June 9-11, 1993 Name:______________________________________________________________________ Accompanying person:_______________________________________________________ Address:_______________________________ Tel:______________Fax:_____________ Z.C. __________ City ____________________ Country__________________________ Institution or Centre _____________________________________________________ REGISTRATION FEES Before April 31 After April 31 Full Inscription 60.000 ptas 70.000 ptas _______________ Basic Inscription (*) 40.000 ptas 50.000 ptas _______________ Economy Inscription (**) 30.000 ptas 35.000 ptas _______________ Accompanying Person Fees 40.000 ptas 50.000 ptas. _______________ (*) Only for students with accreditation and delegates from America (except USA and Canada), and East European Countries. (**)Without proceedings.Only for students. On site registration is discouraged. HOTEL RESERVATION Special Hotel rates per night (Breakfast included) Twin Room Single use room tax [] Gran Sitges Hotel **** 15,750 ptas 12,600 ptas 6% [] San Sebastian Htl **** 12,500 ptas 9,500 ptas 6% [] Sitges Park Hotel *** 8,000 ptas 6,500 ptas 6% [] Subur Hotel *** 8,300 ptas 6,200 ptas 6% [] Hotel Don Pancho ** 5,500 ptas 4,400 ptas 6% Please reserve ________ room(s) [] Twin(s) [] Single(s) at Hotel ______________________________________ Date of arrival ________________ Date of departure ___________________ HOTEL RESERVATION DEPOSIT Following deposit per room will be necessary to confirm any Hotel reservation: Hotel****:20.000 ptas Hotel***: 15.000 ptas Hotel**:10.000 ptas. Attached Hotel Deposit :____________________ ptas x _______ rooms= ___________ TOTAL ATTACHED PAYMENT _______________ Payment of Registration Fees will be necessary to attend the Workshop sessions and social events. Registration Fees include: For Attendants For Accompanying persons - Welcome Reception - Welcome Reception. - Proceedings - Barcelona City Tour - Attendence to all - Museums of Sitges Tour Scientific Meetings - Official Dinner - Coffee Breaks - Official Dinner Basic Inscription Economy Inscription - Proceedings - Attendance to all Scientific - Attendance to all Meetings Scientific Meetings - Coffee Breaks - Coffee Breaks METHODS OF PAYMENT [] By bank draft in Pesetas, payable to ULTRAMAR CONGRESS on a Spanish Bank. [] By bank transfer to: BANCO CENTRAL (c/o ULTRAMAR CONGRESS) Branch No.20 Paseo de Gracia, 3 08007 Barcelona Acct. No. 13575-70 Please attach copy of Bank transfer to this form. Transfer fees to be paid by the sender. [] By VISA Credit Card No._____________________ Expiration date ______________ Name of Card Holder ________________________________________________________ Please send this REGISTRATION FORM, together with payment, to ULTRAMAR CONGRESS Diputacio, 238, tercer 08007 BARCELONA Spain Tel. (34-3) 317.37.00 Fax. (34-3) 412.03.19 Date: ____________________ Signature: _______________________________ THE WORKSHOP VENUE Sitges is located 35 Km. south of Barcelona. The city is well known for its beaches and its promenade facing the Mediterranean sea. Sitges is also knownfor its cultural events, and interesting Museums (Maricel, Santiago Rusinol...) IWANN'93 will be held at one of the most modern Convention Centres of Mediterranean Coast, The Gran Sitges Hotel, an unique complex in which business and leisure go hand in hand. Opened in 1991, its Congress and Conventions facilities include 13 Meeting Rooms equipped with all the necessary means. The Mediterranean Sea can be seen from every balcony of its 307 guest rooms. All of them are designed to offer maximum comfort (TV, mini-bar, air-conditio- ning and a wall safe). Sitges can be easily accesed by train (every 30 minutes), and it is wellcommunicated by highway. OPTIONAL TOURS Optional tours and excursions will be organized on Saturday and Sunday for the attendants wishing to extend their stay after the Workshop. From vera at uivt.cas.cs Fri Apr 30 10:48:15 1993 From: vera at uivt.cas.cs (Vera Kurkova) Date: Fri, 30 Apr 93 10:48:15 CET Subject: Announcing Prague Conference Neuronet'93 Message-ID: <38900.vera@uivt1.uivt.cas.cs> Neuronet'93 will be held in Prague, Czechia, September 20-26, 1993 One-page abstracts of papers on both theory and applications of neural networks should be send by May 30, 1993 to: Mirko Novak Institute of Computer Sciences Czech Academy of Sciences P.O.Box 5, 18207 Prague 8, Czechia More detailed information abour Neuronet'93 can be obtained by e-mail: cvs15 at cspgcs11.bitnet by phone: (+422) 821639 by fax: (+422) 8585789