From piero@matilde.laboratorium.dist.unige.it Tue Apr 22 20:09:31 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id UAA22888 for ; Tue, 22 Apr 1997 20:09:27 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id UAA18878 for ; Tue, 22 Apr 1997 20:09:26 -0500 (CDT) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa13863; 22 Apr 97 19:06:37 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa13861; 22 Apr 97 18:38:57 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa01050; 22 Apr 97 18:38:33 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa12629; 22 Apr 97 13:56:50 EDT Received: from dist.dist.unige.it by CS.CMU.EDU id aa22465; 22 Apr 97 13:54:38 EDT Received: from matilde.laboratorium.dist.unige.it (matilde.laboratorium.dist.unige.it [130.251.13.1]) by dist.dist.unige.it (8.6.12/8.6.12) with SMTP id TAA10563; Tue, 22 Apr 1997 19:55:48 +0200 Received: by matilde.laboratorium.dist.unige.it (4.1/SMI-4.1) id AA12961; Tue, 22 Apr 97 19:52:50 +0200 From: Piero Morasso Message-Id: <9704221752.AA12961@matilde.laboratorium.dist.unige.it> Subject: Book announcement To: Connectionists@cs.cmu.edu, SCRIB-L@NIC.SURFNET.NL Date: Tue, 22 Apr 97 19:52:50 MET DST X-Mailer: ELM [version 2.3 PL0] ========================================================================= ANNOUNCEMENT OF A NEW BOOK OF COMPUTATIONAL NEUROSCIENCE SELF-ORGANIZATION, COMPUTATIONAL MAPS, AND MOTOR CONTROL edited by Pietro Morasso and Vittorio SanguinetI North Holland Elsevier - Advances in Psychology vol. 119 ISBN 0 444 823239, 1997, 635 pages In the study of the computational structure of biological/robotic sensorimotor systems, distributed models have gained center stage in recent years, with a range of issues including self-organization, non-linear dynamics, field computing, etc. This multidisciplinary research area is addressed by a multidisciplinary team of contributors, who provide a balanced set of articulated presentations which include reviews, computational models, simulation studies, psychophysical and neurophysiological experiments. For convenience, the book is divided into three parts, without a clearcut boundary but a slightly different focus. The reader can find different approaches on controversial issues, such as the role and nature of force fields, the need of internal representations, the nature of invariant commands, the vexing question about coordinate transformations, the distinction between hierarchical and bidirectional modelling, and the influence of muscle stiffness. In Part I, the major theme concerns computational maps which typically model cortical areas, according to a view of the sensorimotor cortex as a "geometric engine" and the site of "internal models" of external spaces. Part II also addresses problems of self-organization and field-computing but in a simpler computational architecture which, although lacking a specialized cortical machinery, can still behave in a very adaptive and surprising way by exploiting the interaction with the real world. Finally, Part III is focused on the motor control issues related to the physical properties of muscular actuators and the dynamic interactions with the world, attempting to complete the picture from planning to control. PART I Cortical Maps of Sensorimotor Spaces V. Sanguineti, P. Morasso, and F. Frisone Field Computation in Motor Control B. MacLennan A Probability Interpretation of Neural Population Coding for Movement T.D. Sanger Computational Models of Sensorimotor integration Z. Ghahramani, D.M. Wolpert, and M.I. Jordan How Relevant are Subcortical Maps for the Cortical Machinery? An Hypothesis Based on Parametric Study of Extra-Relay Afferents to Primary Sensory Areas D. Minciacchi and A. Granato PART II Artificial Force-Field Based Methods in Robotics T. Tsuji, P. Morasso, V. Sanguineti, and M. Kaneko Learning Newtonian Mechanics F.A. Mussa Ivaldi and E. Bizzi Motor Intelligence in a Simple Distributed Control System: Walking Machines and Stick Insects H. Cruse and J. Dean The Dynamic Neural Field Theory of Motor Programming: Arm and Eye Movements G. Schner, K. Kopecz, and W. Erlhagen Network Models in Motor Control and Music A. Camurri PART III Human Arm Impedance in Multi-Joint Movement T. Tsuji Neural Models for Flexible Control of Redundant Systems F.H. Guenther and D. Micci Barreca Models of Motor Adaptation and Impedance Control in Human Arm Movements T. Flash and I. Gurevich Control of Human Arm and Jaw Motion: Issues Related to Musculo-Skeletal Geometry P.L. Gribble, R. Laboissire, and D.J. Ostry Computational Maps and Target Fields for Reaching Movements V. Sanguineti and P. Morasso >From Cortical Maps to the Control of Muscles P. Morasso and V. Sanguineti Learning to Speak: Speech Production and Sensori-motor representations G. Bailly, R. Laboissire, and A. Galvn ========================================================================= Pietro G. Morasso - University of Genova, DIST Via Opera Pia, 13, I-16145 Genova (Italy) V:+39 10 3532749; F:+39 10 3532154/3532948; E: morasso@dist.unige.it W: http://www.laboratorium.dist.unige.it/STAFF/Morasso.html - Center of Bioengineering - Hospital Colletta di Arenzano Via Giappone 3, I-16011 Arenzano (Genova) V:+39 10 9134805; F:+39 10 9134122; E: colletta@csita.unige.it ---------------------------------------------------------------------- From Uwe.Zimmer@GMD.de Wed Apr 23 04:12:08 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id EAA24714 for ; Wed, 23 Apr 1997 04:12:02 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id EAA24377 for ; Wed, 23 Apr 1997 04:12:01 -0500 (CDT) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa14187; 23 Apr 97 0:31:05 EDT Received: from SKINNER.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa14184; 23 Apr 97 0:21:49 EDT Received: from skinner.boltz.cs.cmu.edu by skinner.boltz.cs.cmu.edu id aa14151; 23 Apr 97 0:21 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa16316; 22 Apr 97 18:42:56 EDT Received: from mail.gmd.de by EDRC.CMU.EDU id aa07796; 22 Apr 97 18:41:14 EDT Received: from 129.26.128.163 (k9mac29.gmd.de) by mail.gmd.de with SMTP id AA03713 (5.67b8/IDA-1.5 for ); Wed, 23 Apr 1997 00:39:06 +0200 Message-Id: <335D3E30.77C@GMD.de> Date: Wed, 23 Apr 1997 00:39:45 +0200 From: "Uwe R. Zimmer" Reply-To: Uwe.Zimmer@GMD.de X-Mailer: Mozilla 3.0 (Macintosh; I; 68K) Mime-Version: 1.0 To: connectionists@cs.cmu.edu Subject: Japanese Robotics Research - a report and more Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Dear all, a report discussing outstanding research topics in Japanese robotics laboratories as well as governmental issues is just released. Some of the discussed groups deal with neural (biological) sensory-motor control, others are involved in biologically plausible sensory systems or redundant (humanoid) kinematics. Even creatures combining mechatronic and biological structures are investigated. ---------------------------------------------------------------------- Recent Developments in Japanese Robotics Research - Notes of a Japan Tour - Uwe R. Zimmer, Thomas Christaller, Christfried Webers ---------------------------------------------------------------------- http://www.gmd.de/People/Uwe.Zimmer/Publications/abs.Japan-Report.html ---------------------------------------------------------------------- (containing links to .pdf, .ps.gz, and ps.Z formats of the report) Abstract: Robotics appears to be a very lively and fruitful field of research in Japan. Some of the research topics cannot be found elsewhere at all, and some are significantly advanced. Discussing this impression, a collection of laboratories is introduced with their most outstanding topics. Moreover some background information about research plans, politics, and organisations are given. ---------------------------------------------------------------------- For an extensive web-presentation of robotics in Japan see also: ---------------------------------------------------------------------- http://www.gmd.de/People/Uwe.Zimmer/Lists/Robotics.in.Japan.html ---------------------------------------------------------------------- For more publications on robotics from GMD, please refer to: ---------------------------------------------------------------------- http://www.gmd.de/FIT/KI/CogRob/Publications/CogRob.Publications.html ---------------------------------------------------------------------- And for general information about scientific activities in Japan: ---------------------------------------------------------------------- http://www.gmd.de/Japan/ ---------------------------------------------------------------------- ,,,,, ___________________________________________ (o o) _____| ________oOO__( )__OOo_______| Uwe R. Zimmer GMD - FIT-KI ___| Schloss Birlinghoven | 53754 St. Augustin, Germany | _______________________________________________________________. Voice: +49 2241 14 2373 - Fax: +49 2241 14 2384 | http://www.gmd.de/People/Uwe.Zimmer/ | From meyer@wotan.ens.fr Wed Apr 23 15:43:16 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id PAA03068 for ; Wed, 23 Apr 1997 15:42:59 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id PAA05694 for ; Wed, 23 Apr 1997 15:42:57 -0500 (CDT) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa15120; 23 Apr 97 12:02:38 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa15118; 23 Apr 97 11:46:34 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa01733; 23 Apr 97 11:44:48 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa25827; 23 Apr 97 8:58:24 EDT Received: from nef.ens.fr by CS.CMU.EDU id aa00335; 23 Apr 97 8:57:31 EDT Received: from eole.ens.fr (eole.ens.fr [129.199.17.12]) by nef.ens.fr (8.8.5/jtpda-5.1) with ESMTP id OAA17834 ; Wed, 23 Apr 1997 14:57:15 +0200 (MET DST) From: Jean-Arcady MEYER Date: Wed, 23 Apr 1997 14:57:09 +0200 (MET DST) Received: from (meyer@localhost) by eole.ens.fr (8.8.5/jb-1.1) Message-Id: <199704231257.OAA00763@eole.ens.fr> To: animat@ens.fr, echos@dmi.ens.FR, gann@cs.iastate.edu, hybrid-list@cs.ua.edu, alife@cognet.ucla.edu, Reinforce@cs.uwa.edu.au, cogni-info@univ-lyon1.fr, cogpsy@neuro.psy.soton.ac.uk, Connectionists@cs.cmu.edu Subject: MODELS OF SPATIAL NAVIGATION X-Sun-Charset: US-ASCII ================================================================== CALL FOR PAPERS ADAPTIVE BEHAVIOR Journal (The MIT Press) Special Issue on BIOLOGICALLY INSPIRED MODELS OF SPATIAL NAVIGATION Guest editor: Nestor Schmajuk Submission Deadline: August 31, 1997. In the last decades, computational models of animal and human spatial navigation have received increasing attention from computer scientists, engineers, psychologists, and neurophysiologists. At the same time, roboticists have applied enormous efforts to the design of robots capable of spatial navigation. The combined contribution of these fields to the study of spatial navigation promises a rapid progress in this area. This special issue of Adaptive Behavior will focus on models of spatial navigation in both animals and robots. We are soliciting papers describing finished work on models and technology applied to maze navigation, search behavior, and exploration. Also models of brain areas involved in navigation are welcome. We encourage submissions that address the following topics: -spatial learning in animals or robots -maze navigation in animals or robots -exploratory and searching behavior by individual animals or robots -exploratory behavior by groups of animals or robots -learning from incremental and delayed feedback Submitted papers should be delivered by August 31, 1997. Authors intending to submit a manuscript should contact the guest editor as soon as possible to discuss paper ideas and suitability for this issue. Use nestor@acpub.duke.edu or tel: (919) 660-5695 or fax: (919) 660-5726. Manuscripts should be typed or laser-printed in English (with American spelling preferred) and double-spaced. Copies of the complete Adaptive Behavior Instructions to Contributors are available on request--also see the Adaptive Behavior journal's home page at: http://www.biologie.ens.fr/AnimatLab/AB.html For paper submissions, send five (5) copies of submitted papers (hard-copy only) to: Dr. Nestor Schmajuk Department of Psychology Duke University Durham, NC 27708 ================================================================== From mel@quake.usc.edu Wed Apr 23 22:50:17 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id WAA04313 for ; Wed, 23 Apr 1997 22:50:12 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id WAA12301 for ; Wed, 23 Apr 1997 22:50:11 -0500 (CDT) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa15664; 23 Apr 97 20:05:43 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa15662; 23 Apr 97 19:45:53 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa01924; 23 Apr 97 19:45:34 EDT Date: Wed, 23 Apr 1997 14:04:19 +0800 Message-Id: <9704232104.AA12648@quake.usc.edu> From: Bartlett Mel Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit To: connectionists@cs.cmu.edu Subject: Joint Symposium Registration and Program X-Mailer: VM 6.24 under Emacs 19.34.1 Please find REGISTRATION INFORMATION and PRELIMINARY PROGRAM for the upcoming 4th Annual Southern California JSNC: ----------------------------- --- 4th Annual Joint Symposium on Neural Computation --- Co-sponsored by Institute for Neural Computation University of California, San Diego and Biomedical Engineering Department and Neuroscience Program University of Southern California to be hosted at The University of Southern California University Park Campus Rm. 124, Seeley G. Mudd Building Saturday, May 17, 1997 8:00 a.m. to 5:30 p.m. 8:00 am Registration/Coffee 8:50 am Opening Remarks Session 1: "VISION" - Bartlett Mel, Chair 9:00 am Peter Kalocsai, USC "Using Extension Fields to Improve Proformance of a Biologically Inspired Recognition Model" 9:15 am Kechen Zhang, The Salk Institute "A Conjugate Neural Representation of Visual Objects in Three Dimensions" 9:30 am Alexander Grunewald, Caltech "Detection of First and Second Order Motion" 9:45 am Zhong-Lin Lu, USC "Extracting Characteristic Structures from Natural Images Through Statistically Certified Unsupervised Learning" 10:00 am Don McCleod, UC San Diego "Optimal Nonlinear Codes" 10:15 am Lisa J. Croner, The Salk Institute "Segmentation by Color Influences Response of Motion-Sensitive Neurons in Cortical Area MT" 10:15 am - 10:30 am *** BREAK *** Session 2: "CODING in NEURAL SYSTEMS" - Christof Koch, Chair 10:30 am Dawei Dong, Caltech "How Efficient is Temporal Coding in the Early Visual System?" 10:45 am Martin Stemmler, Caltech "Entropy Maximization in Hodgkin-Huxley Models" 11:00 am Michael Wehr, Caltech "Temporal coding with Oscillatory Sequences of Firing" 11:15 am Martin J. McKeown, The Salk Institutde "Functional Magnetic Resonance Imaging Data Interpreted as Spatially Independent Mixtures" 11:30 am KEYNOTE SPEAKER: Prof. Irving Biederman, William M. Keck Professor of Cognitive Neuroscience Departments of Psychology and Computer Science and the Neuroscience Program, USC "Shape Representation in Mind and Brain" ------------- 12:30 pm - 2:30 pm *** LUNCH/POSTERS *** P1. Konstantinos Alataris, USC "Modeling of Neuronal Ensemble Dynamics" P2. George Barbastathis, Caltech "Awareness-Based Computation" P3. Marian Stewart Bartlett, UC San Diego "What are the Independent Components of Face Images?" P4. Maxim Bazhenov,The Salk Institute "A Computational Model of Intrathalamic Augmenting Responses" P5. Alan Bond, Caltech "A Computational Model for the Primate Brain Based on its Functional Architecture" P6. Glen Brown, The Salk Institute "Output Sign Switching by Neurons is Mediated by a Novel Voltage-Dependent Sodium Current" P7. Martin Chian, USC "Characterization of Unobservable Neural Circuitry in the Hippocampus with Nonlinear Systems Analysis" P8. Carl Chiang, The Neuroscience Institute "Visual and Sensorimotor Intra- and Intercolumnar Synchronization in Awake Behaving Cat" P9. Matthew Dailey, UC San Diego "Learning a Specializtion for Face Recognition" P10. Emmanuel Gillissen, Caltech "Comparative Studies of Callosal Specification in M ammals" P11. Micheal Gray, The Salk Institute "Infomative Features for Visual Speechreading" P12. Alex Guazzelli, USC "A Taxon-Affordances Model of Rat Navigation" P13. Marwan Jabri, The Salk Instutute/Sydney University "A Neural Network Model for Saccades and Fixation on Superior Colliculus" P14. Mathew Lamb, USC "Depth Based Prey Capture in Frogs and Salamanders" P15. Te-Won Lee, The Salk Instutute "Independent Component Analysis for Mixed Sub-Gaussian and Super-Gaussian Sources" P16. George Marnellos, The Salk Institute "A Gene Network of Early Neurogenesis in Drosophila" P17. Steve Potter, Caltech "Animat in a Petri Dish: Cultured Neural Networks for Studying Neural Computation" P18. James Prechtl, UC San Diego "Visual Stimuli Induce Propagating Waves of Electrical Activity in Turtle Cortex" P19. Raphael Ritz, The Salk Institute "Multiple Synfire Chains in Simultaneous Action Lead to Poisson-Like Neuronal Firing" P20. Adrian Robert, UC San Diego "A Model of the Effects of Lamination and Celltype Specialization in the Neocortex" P21. Joseph Sirosh, HNC Software Inc. "Large-Scale Neural Network Simulations Suggest a Single Mechanism for the Self-Organization of Orientation Maps, Lateral Connections and Dynamic Receptive Fields in the Primary Visual Cortex" P22. George Sperling, UC Irvine "A Proposed Architecture for Visual Motion Perception" P23. Adam Taylor, UC San Diego "Dynamics of a Recurrent Network of Two Bipolar Units" P24. Laurenz Wiskott, The Salk Institute "Objective Functions for Neural Map Formation" ------------------------------------------- Session 3: "HARDWARE" - Michael Arbib, Chair 2:30 pm Christof Born, Caltech "Real Time Ego-Motion Estimation with Neuromorphic Analog VLSI Sensors" 2:45 pm Anil Thakoor, JPL "High Speed Image Computation with 3D Analog Neural Hardware" Session 4: "VISUOMOTOR COORDINATION" - Michael Arbib, Chair 3:00 pm Marwan Jabri, The Salk Institute/Sydney University "A Computational Model of Auditory Space Neural Coding in the Superior Colliculus" 3:15 pm Amanda Bischoff, USC "Modeling the Basal Ganglia in a Reciprocal Aiming Task" 3:30 pm Jacob Spoelstra, USC "A Computational Model of the Role of the Cerebellum in Adapting to Throwing While Wearing Wedge Prism Glasses" 3:45 pm - 4:00 pm *** BREAK *** Session 5: "CHANNELS, SYNAPSES, and DENDRITES" - Terry Sejnowski, Chair 4:00 pm Akaysha C. Tang, The Salk Institute "Modeling the Effect of Neuromodulation of Spike Timing in Neocortical Neurons" 4:15 pm Michael Eisele, The Salk Institute "Reinforcement Learning by Pyramidal Neurons" 4:30 pm Sunil S. Dalal, USC "A Nonlinear Prositive Feedback Model of Glutamatergic Synaptic Transmission in Dentate Gyrus" 4:45 pm Venkatesh Murthy, The Salk Institute "Are Neighboring Synapses Independent?" 5:00 pm Gary Holt, Caltech "Shunting Inhibition Does Not Have a Divisive Effect on Firing Rates" 5:15 pm Kevin Archie, USC "Binocular Disparity Tuning in Cortical 'Complex' Cells: Yet Another Role for Intradendritic Computation?" 5:30 pm Closing Remarks *** Adjourn for DINNER *** ------------------------------------------- ORGANIZERS Bartlett Mel, USC (Chair) Michael Arbib, USC Terry Sejnowski, Salk/UCSD PROGRAM COMMITTEE Michael Arbib, USC Bartlett Mel, USC (Chair) Christof Koch, Caltech Terry Sejnowski, UCSD ------------------------------------------- REGISTRATION INFORMATION If you have not already registered, you still have 10 days to do so before the Pre-Registration DEADLINE: Pre-Registration: $25 Late/On-site Registration: $35 (received after Friday, May 2) Registration fee includes coffee, snacks, lunch, and proceedings. Registration form and checks payable to the "Department of Biomedical Engineering, USC" should be mailed to: Joint Symposium, attn: Linda Yokote Biomedical Engineering Department USC, MC 1451 Los Angeles, CA 90089 Administrative questions can be addressed to Linda at: yokote@bmsrs.usc.edu (213)740-0840, (213)740-0343 fax ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 1997 JSNC Attendees Registration Form Name: ________________________________________________________________________ Affiliation: _________________________________________________________________ Address: _____________________________________________________________________ _____________________________________________________________________ _____________________________________________________________________ Phone: _________________ Fax: ____________________ E-mail: __________________ Special Dietary Preference: __________________________________________________ Registration fee enclosed: _________ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ DIRECTIONS TO THE SYMPOSIUM >From PASADENA, or parts North Take the 110 south past downtown LA to Exposition; at the exit, bend soft right to hop through a quick light at Flowers St. Continue straight one block, turn right on Figueroa. The USC campus is now on your left, but do not enter. Continue the length of the campus, turn left on Jefferson, and continue 2/3 of the length of the campus heading west, past Hoover. At the light at McClintock, turn left into the campus. This is the weekend entrance. See instructions for "EVERYBODY" below for the final details. Expected drive time on Saturday: 25 minutes. >From the WEST SIDE Take the 10 west, exit Vermont, turn right (south) and proceed a half mile, turn left on Jefferson and continue to McClintock. The weekend entrance to the USC campus will be on your right. See instructions for "EVERYBODY" below for the final details. Expected drive time on Saturday: 5 minutes from Vermont exit. >From the SOUTH Take the (5 N to the) 405 N to the 110 N, exit Exposition. Proceed straight through the light and the next light at the DMV entrance. Bend hard left past the DMV to cross under the freeway. Proceed through the light at Flowers, continue 1 block, and turn right on Figueroa. The USC campus is now on your left, but do not enter. Continue the length of the campus, turn left on Jefferson, and continue 2/3 of the length of the campus heading west, past Hoover. At the light at McClintock, turn left into the campus. This is the weekend entrance. See instructions for "EVERYBODY" below for the final details. Expected drive time on Saturday: 25 minutes. EVERYBODY Enter the USC campus and purchase an all-day parking pass ($6) at the guard booth. Proceed straight south on McClintock past the pool (on right), and playing field (on left) to the corner of 36th Place/Downey. You may park in lot 6 on your right or the large parking structure just ahead on the right. Seeley Mudd (SGM) is a tall brick and concrete building on the NE corner of Downey and McClintock. SGM 124 is a large auditorium on the ground floor. Look for coffee-drinking computational neuroscientists. From meyer@wotan.ens.fr Thu Apr 24 11:39:41 1997 Received: from cs.wisc.edu (cs.wisc.edu [128.105.2.6]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id LAA07686 for ; Thu, 24 Apr 1997 11:39:29 -0500 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by cs.wisc.edu (8.7.6/8.7.3) with SMTP id LAA11783 for ; Thu, 24 Apr 1997 11:39:25 -0500 (CDT) Received: from (parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id VAA02214; Thu, 24 Apr 1997 21:15:33 +0800 Message-Id: <199704241315.VAA02214@cs.uwa.oz.au> From: meyer@wotan.ens.fr (Jean-Arcady MEYER) To: animat@ens.fr, echos@dmi.ens.fr, gann@cs.iastate.edu, hybrid-list@cs.ua.edu, alife@cognet.ucla.edu, Reinforce@cs.uwa.edu.au, cogni-info@univ-lyon1.fr, cogpsy@neuro.psy.soton.ac.uk, Connectionists@cs.cmu.edu Subject: MODELS OF SPATIAL NAVIGATION [connectionists] Date: Wed, 23 Apr 1997 14:57:09 +0200 (MET DST) ================================================================== CALL FOR PAPERS ADAPTIVE BEHAVIOR Journal (The MIT Press) Special Issue on BIOLOGICALLY INSPIRED MODELS OF SPATIAL NAVIGATION Guest editor: Nestor Schmajuk Submission Deadline: August 31, 1997. In the last decades, computational models of animal and human spatial navigation have received increasing attention from computer scientists, engineers, psychologists, and neurophysiologists. At the same time, roboticists have applied enormous efforts to the design of robots capable of spatial navigation. The combined contribution of these fields to the study of spatial navigation promises a rapid progress in this area. This special issue of Adaptive Behavior will focus on models of spatial navigation in both animals and robots. We are soliciting papers describing finished work on models and technology applied to maze navigation, search behavior, and exploration. Also models of brain areas involved in navigation are welcome. We encourage submissions that address the following topics: -spatial learning in animals or robots -maze navigation in animals or robots -exploratory and searching behavior by individual animals or robots -exploratory behavior by groups of animals or robots -learning from incremental and delayed feedback Submitted papers should be delivered by August 31, 1997. Authors intending to submit a manuscript should contact the guest editor as soon as possible to discuss paper ideas and suitability for this issue. Use nestor@acpub.duke.edu or tel: (919) 660-5695 or fax: (919) 660-5726. Manuscripts should be typed or laser-printed in English (with American spelling preferred) and double-spaced. Copies of the complete Adaptive Behavior Instructions to Contributors are available on request--also see the Adaptive Behavior journal's home page at: http://www.biologie.ens.fr/AnimatLab/AB.html For paper submissions, send five (5) copies of submitted papers (hard-copy only) to: Dr. Nestor Schmajuk Department of Psychology Duke University Durham, NC 27708 ================================================================== From ataxr@IMAP1.ASU.EDU Thu Apr 24 14:22:05 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id OAA08440 for ; Thu, 24 Apr 1997 14:22:01 -0500 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id OAA24380 for ; Thu, 24 Apr 1997 14:21:54 -0500 (CDT) Received: from (parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id VAA02228; Thu, 24 Apr 1997 21:17:30 +0800 Message-Id: <199704241317.VAA02228@cs.uwa.oz.au> From: Asim Roy To: reinforce@cs.uwa.edu.au Subject: CONNECTIONIST LEARNING: IS IT TIME TO RECONSIDER THE FOUNDATIONS? [connectionists] Date: Wed, 23 Apr 1997 21:12:46 -0400 (EDT) =091997 International Conference on Neural Networks (ICNN'97) =09=09Houston, Texas (June 8 -12, 1997) ---------------------------------------------------------------- Further information on the conference is available on the=20 conference web page: =09http://www.eng.auburn.edu/department/ee/ICNN97 ------------------------------------------------------------------ =09=09=09PANEL DISCUSSION ON "CONNECTIONIST LEARNING: IS IT TIME TO RECONSIDER THE FOUNDATIONS?" ------------------------------------------------------------------- This is to announce that a panel will discuss the above question at=20 ICNN'97 on Monday afternoon (June 9). Below is the abstract for the=20 panel discussion broadly outlining the questions to be addressed. I=20 am also attaching a slightly modified version of a subsequent note=20 sent to the panelist. I think the issues are very broad and the=20 questions are simple. The questions are not tied to any specific=20 "algorithm" or "network architecture" or "task to be performed." However, the answers to these simple questions may have an enormous=20 effect on the "nature of algorithms" that we would call=20 "brain-like" and for the design and construction of autonomous=20 learning systems and robots. I believe these questions also have a=20 bearing on other brain related sciences such as neuroscience,=20 neurobiology and cognitive science. Please send any comments on these issues directly to me=20 (asim.roy@asu.edu). I will post the collection of responses to the=20 newsgroups in a few weeks. All comments/criticisms/suggestions are=20 welcome. All good science depends on vigorous debate. Asim Roy Arizona State University =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D PANEL MEMBERS 1. Igor Aleksander 2. Shunichi Amari 3. Eric Baum=20 4. Jim Bezdek 5. Rolf Eckmiller 6. Lee Giles 7. Geoffrey Hinton 8. Dan Levine 9. Robert Marks 10. Jean Jacques Slotine 11. John G. Taylor 12. David Waltz 13. Paul Werbos 14. Nicolaos Karayiannis (Panel Moderator, ICNN'97 General Chair) 15. Asim Roy Six of the above members are plenary speakers at the meeting. =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =09=09=09PANEL TITLE: =20 "CONNECTIONIST LEARNING: IS IT TIME TO RECONSIDER THE FOUNDATIONS?" =09=09=09ABSTRACT Classical connectionist learning is based on two key ideas. First,=20 no training examples are to be stored by the learning algorithm in=20 its memory (memoryless learning). It can use and perform whatever=20 computations are needed on any particular training example, but=20 must forget that example before examining others. The idea is to=20 obviate the need for large amounts of memory to store a large=20 number of training examples. The second key idea is that of local=20 learning - that the nodes of a network are autonomous learners.=20 Local learning embodies the viewpoint that simple, autonomous=20 learners, such as the single nodes of a network, can in fact=20 produce complex behavior in a collective fashion. This second idea,=20 in its purest form, implies a predefined net being provided to the=20 algorithm for learning, such as in multilayer perceptrons.=20 Recently, some questions have been raised about the validity of=20 these classical ideas. The arguments against classical ideas are=20 simple and compelling. For example, it is a common fact that humans=20 do remember and recall information that is provided to them as part=20 of learning. And the task of learning is considerably easier when=20 one remembers relevant facts and information than when one doesn=92t.=20 Second, strict local learning (e.g. back propagation type learning)=20 is not a feasible idea for any system, biological or otherwise. It=20 implies predefining a network "by the system" without having seen a=20 single training example and without having any knowledge at all of=20 the complexity of the problem. Again, there is no system that can=20 do that in a meaningful way. The other fallacy of the local=20 learning idea is that it acknowledges the existence of a "master"=20 system that provides the design so that autonomous learners can=20 learn. Recent work has shown that much better learning algorithms, in=20 terms of computational properties (e.g. designing and training a=20 network in polynomial time complexity, etc.) can be developed if=20 we don=92t constrain them with the restrictions of classical=20 learning. It is, therefore, perhaps time to reexamine the ideas of=20 what we call "brain-like learning." This panel will attempt to address some of the following questions=20 on classical connectionists learning: 1. Should memory be used for learning? Is memoryless learning an=20 unnecessary restriction on learning algorithms? 2. Is local learning a sensible idea? Can better learning=20 algorithms be developed without this restriction?=20 3. Who designs the network inside an autonomous learning system=20 such as the brain?=20 =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =09A SUBSEQUENT NOTE SENT TO THE PANELIST The panel abstract was written to question the two pillars of=20 classical connectionist learning - memoryless learning and pure=20 local learning. With regards to memoryless learning, the basic=20 argument against it is that humans do store information (remember=20 facts/information) in order to learn. So memoryless learning, as=20 far I understand, cannot be justified by any behavioral or=20 biological observations/facts. That does not mean that humans store=20 any and all information provided to them. They are definitely=20 selective and parsimonious in the choice of information/facts to=20 collect and store.=20 We have been arguing that it is the "combination" of memoryless=20 learning and pure local learning that is not feasible for any=20 system, biological or otherwise. Pure local learning, in this=20 context, implies that the system somehow puts together a set of=20 "local learners" that start learning with each learning example=20 given to it (e.g. in back propagation) without having seen a single=20 training example before and without knowing anything about the=20 complexity of the problem. Such a system can be demonstrated to do=20 well in some cases, but would not work in general. Note that not all existing neural network algorithms are of this=20 pure local learning type. For example, if I understand correctly,=20 in constructive algorithms such as ART, RBF, RCE/hypersphere and=20 others, a "decision" to create a new node is made by a "global=20 decision-maker" based on evidence on performance of the existing=20 system. So there is quite a bit of global coordination and=20 "decision-making" in those algorithms beyond the simple "local=20 learning".=20 Anyway, if we "accept" the idea that memory can indeed be used for=20 the purpose of learning (Paul Werbos indicated so in one of his=20 notes), the terms of the debate/discussion change dramatically. We=20 then open the door to the development of far more robust and=20 reliable learning algorithms with much nicer properties than=20 before. We can then start to develop algorithms that are closer to=20 "normal human learning processes". Normal human learning includes=20 processes such as (1) collection and storage of information about a=20 problem, (2) examination of the information at hand to determine=20 the complexity of the problem, (3) development of trial solutions=20 (nets)for the problem, (4) testing of trial solutions (nets), (5)=20 discarding such trial solutions (nets) if they are not good enough,=20 and (6) repetition of these processes until an acceptable solution=20 is found. And these learning processes are implemented within the=20 brain, without doubt, using local computing mechanisms of different=20 types. But these learning processes cannot exist without allowing=20 for storage of information about the problem.=20 One of the "large" missing pieces in the neural network field is=20 the definition or characterization of an autonomous learning system=20 such as the brain. We have never defined the external behavioral=20 characteristics of our learning algorithms. We have largely pursued=20 algorithm development from an "internal mechanisms" point of view=20 (local learning, memoryless learning) rather than from the point of=20 view of "external behavior or characteristics" of these resulting=20 algorithms. Some of these external characteristics of our learning=20 algorithms might be:(1) the capability to design the net on their=20 own, (2) polynomial time complexity of the algorithm in design and=20 training of the net, (3) generalization capability, and (4)=20 learning from as few examples as possible (quickness in learning).=20 It is perhaps time to define a set of desirable external=20 characteristics for our learning algorithms. We need to define=20 characteristics that are "independent of": (1) a particular=20 architecture, (2) the problem to be solved (function approximation,=20 classification, memory, etc.), (3)local/global learning issues, and=20 (4) issues of whether to use memory or not to learn. We should=20 rather argue about these external properties than issues of=20 global/local learning and of memoryless learning.=20 With best regards, Asim Roy Arizona State University From juergen@idsia.ch Thu Apr 24 14:59:11 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id OAA08584 for ; Thu, 24 Apr 1997 14:59:05 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id OAA25124 for ; Thu, 24 Apr 1997 14:59:03 -0500 (CDT) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa16836; 24 Apr 97 13:05:25 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa16834; 24 Apr 97 12:49:31 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa02571; 24 Apr 97 12:48:44 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa13197; 24 Apr 97 4:15:20 EDT Received: from fava.idsia.ch by CS.CMU.EDU id aa10171; 24 Apr 97 4:14:14 EDT Received: from ruebe.idsia.ch by fava.idsia.ch (4.1/SMI-4.1) id AA21548; Thu, 24 Apr 97 10:13:10 +0200 Received: by ruebe.idsia.ch (SMI-8.6/SMI-SVR4) id KAA01923; Thu, 24 Apr 1997 10:06:39 +0200 Date: Thu, 24 Apr 1997 10:06:39 +0200 From: Juergen Schmidhuber Message-Id: <199704240806.KAA01923@ruebe.idsia.ch> To: connectionists@cs.cmu.edu Subject: IDSIA job interviews Concerning the recent IDSIA job openings in http://www.idsia.ch/~juergen/lstm.html : Between May 25 and June 1 I'll be in Hong Kong (for TANC-97). Candidates from Southeast Asia may be interested in arranging job interviews there. Juergen Schmidhuber, IDSIA From terry@salk.edu Thu Apr 24 22:24:55 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id WAA10367 for ; Thu, 24 Apr 1997 22:24:45 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id WAA01862 for ; Thu, 24 Apr 1997 22:24:44 -0500 (CDT) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa17271; 24 Apr 97 22:03:19 EDT Received: from SKINNER.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa17269; 24 Apr 97 21:42:48 EDT Received: from skinner.boltz.cs.cmu.edu by skinner.boltz.cs.cmu.edu id aa24300; 24 Apr 97 21:42 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa10182; 24 Apr 97 21:32:15 EDT Received: from helmholtz.salk.edu by RI.CMU.EDU id aa16329; 24 Apr 97 21:32:01 EDT Received: (from terry@localhost) by helmholtz.salk.edu (8.7.5/8.7.3) id SAA04124; Thu, 24 Apr 1997 18:31:57 -0700 (PDT) Date: Thu, 24 Apr 1997 18:31:57 -0700 (PDT) From: Terry Sejnowski Message-Id: <199704250131.SAA04124@helmholtz.salk.edu> To: connectionists@cs.cmu.edu Subject: NEURAL COMPUTATION 9:4 Cc: leslie@helmholtz.salk.edu, terry@helmholtz.salk.edu Neural Computation - Contents Volume 9, Number 4 - May 15, 1997 Review Similarity, Connectionism, and the Problem of Representation in Vision Shimon Edelman and Sharon Duvdevani-Bar Article Dynamic Model of Visual Recognition Predicts Neural Response Properties in the Visual Cortex Rajesh P. N. Rao and Dana H. Ballard Notes Correction to "Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes Wee Sun Lee, Peter L. Bartlett and Robert C. Williamson Lower Bound on VC-Dimension by Local Shattering Yossi Erlich, Dan Chazan, Scott Petrack, and Avi Levi Letters SEEMORE: Combining Color, Shape and Texture Histogramming in a Neurally-Inspired Approach to Visual Object Recognition Bartlett Mel Image Segmentation Based on Oscillatory Correlation DeLiang Wang and David Terman Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience Lance R. Williams and David W. Jacobs Local Parallel Computation of Stochastic Completion Fields Lance R. Williams and David W. Jacobs Optimal, Unsupervised Learning in Invariant Object Recognition Guy Wallis and Roland Baddeley Activation Functions, Computational Goals and Learning Rules for Local Processors with Contextual Guidance Jim Kay and W. A. Phillips Marr's Theory of the Neocortex as a Self-Organizing Neural Network David Willshaw, John Hallam, Sarah Gingell and Soo Leng Lau ----- ABSTRACTS - http://www-mitpress.mit.edu/jrnls-catalog/neural.html SUBSCRIPTIONS - 1997 - VOLUME 9 - 8 ISSUES ______ $50 Student and Retired ______ $78 Individual ______ $250 Institution Add $28 for postage and handling outside USA (+7% GST for Canada). (Back issues from Volumes 1-8 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) mitpress-orders@mit.edu MIT Press Journals, 55 Hayward Street, Cambridge, MA 02142. Tel: (617) 253-2889 FAX: (617) 258-6779 ----- From ataxr@IMAP1.ASU.EDU Fri Apr 25 06:43:01 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id GAA12133 for ; Fri, 25 Apr 1997 06:42:56 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id GAA06144 for ; Fri, 25 Apr 1997 06:42:55 -0500 (CDT) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa17312; 24 Apr 97 22:14:21 EDT Received: from SKINNER.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa17288; 24 Apr 97 21:50:29 EDT Received: from skinner.boltz.cs.cmu.edu by skinner.boltz.cs.cmu.edu id aa24335; 24 Apr 97 21:49 EDT Date: Wed, 23 Apr 1997 21:12:46 -0400 (EDT) From: Asim Roy Subject: CONNECTIONIST LEARNING: IS IT TIME TO RECONSIDER THE FOUNDATIONS? To: connectionists@cs.cmu.edu Message-id: MIME-version: 1.0 X-Mailer: Simeon for Windows Content-type: TEXT/PLAIN; CHARSET=US-ASCII Content-transfer-encoding: QUOTED-PRINTABLE Priority: NORMAL X-Authentication: IMSP 1997 International Conference on Neural Networks (ICNN'97) Houston, Texas (June 8 -12, 1997) ---------------------------------------------------------------- Further information on the conference is available on the conference web page: http://www.eng.auburn.edu/department/ee/ICNN97 ------------------------------------------------------------------ PANEL DISCUSSION ON "CONNECTIONIST LEARNING: IS IT TIME TO RECONSIDER THE FOUNDATIONS?" ------------------------------------------------------------------- This is to announce that a panel will discuss the above question at ICNN'97 on Monday afternoon (June 9). Below is the abstract for the panel discussion broadly outlining the questions to be addressed. I am also attaching a slightly modified version of a subsequent note sent to the panelist. I think the issues are very broad and the questions are simple. The questions are not tied to any specific "algorithm" or "network architecture" or "task to be performed." However, the answers to these simple questions may have an enormous effect on the "nature of algorithms" that we would call "brain-like" and for the design and construction of autonomous learning systems and robots. I believe these questions also have a bearing on other brain related sciences such as neuroscience, neurobiology and cognitive science. Please send any comments on these issues directly to me (asim.roy@asu.edu). I will post the collection of responses to the newsgroups in a few weeks. All comments/criticisms/suggestions are welcome. All good science depends on vigorous debate. Asim Roy Arizona State University -------------------------= PANEL MEMBERS 1. Igor Aleksander 2. Shunichi Amari 3. Eric Baum 4. Jim Bezdek 5. Rolf Eckmiller 6. Lee Giles 7. Geoffrey Hinton 8. Dan Levine 9. Robert Marks 10. Jean Jacques Slotine 11. John G. Taylor 12. David Waltz 13. Paul Werbos 14. Nicolaos Karayiannis (Panel Moderator, ICNN'97 General Chair) 15. Asim Roy Six of the above members are plenary speakers at the meeting. ------------------------- PANEL TITLE: "CONNECTIONIST LEARNING: IS IT TIME TO RECONSIDER THE FOUNDATIONS?" ABSTRACT Classical connectionist learning is based on two key ideas. First, no training examples are to be stored by the learning algorithm in its memory (memoryless learning). It can use and perform whatever computations are needed on any particular training example, but must forget that example before examining others. The idea is to obviate the need for large amounts of memory to store a large number of training examples. The second key idea is that of local learning - that the nodes of a network are autonomous learners. Local learning embodies the viewpoint that simple, autonomous learners, such as the single nodes of a network, can in fact produce complex behavior in a collective fashion. This second idea, in its purest form, implies a predefined net being provided to the algorithm for learning, such as in multilayer perceptrons. Recently, some questions have been raised about the validity of these classical ideas. The arguments against classical ideas are simple and compelling. For example, it is a common fact that humans do remember and recall information that is provided to them as part of learning. And the task of learning is considerably easier when one remembers relevant facts and information than when one doesn=92t. Second, strict local learning (e.g. back propagation type learning) is not a feasible idea for any system, biological or otherwise. It implies predefining a network "by the system" without having seen a single training example and without having any knowledge at all of the complexity of the problem. Again, there is no system that can do that in a meaningful way. The other fallacy of the local learning idea is that it acknowledges the existence of a "master" system that provides the design so that autonomous learners can learn. Recent work has shown that much better learning algorithms, in terms of computational properties (e.g. designing and training a network in polynomial time complexity, etc.) can be developed if we don=92t constrain them with the restrictions of classical learning. It is, therefore, perhaps time to reexamine the ideas of what we call "brain-like learning." This panel will attempt to address some of the following questions on classical connectionists learning: 1. Should memory be used for learning? Is memoryless learning an unnecessary restriction on learning algorithms? 2. Is local learning a sensible idea? Can better learning algorithms be developed without this restriction? 3. Who designs the network inside an autonomous learning system such as the brain? ------------------------- A SUBSEQUENT NOTE SENT TO THE PANELIST The panel abstract was written to question the two pillars of classical connectionist learning - memoryless learning and pure local learning. With regards to memoryless learning, the basic argument against it is that humans do store information (remember facts/information) in order to learn. So memoryless learning, as far I understand, cannot be justified by any behavioral or biological observations/facts. That does not mean that humans store any and all information provided to them. They are definitely selective and parsimonious in the choice of information/facts to collect and store. We have been arguing that it is the "combination" of memoryless learning and pure local learning that is not feasible for any system, biological or otherwise. Pure local learning, in this context, implies that the system somehow puts together a set of "local learners" that start learning with each learning example given to it (e.g. in back propagation) without having seen a single training example before and without knowing anything about the complexity of the problem. Such a system can be demonstrated to do well in some cases, but would not work in general. Note that not all existing neural network algorithms are of this pure local learning type. For example, if I understand correctly, in constructive algorithms such as ART, RBF, RCE/hypersphere and others, a "decision" to create a new node is made by a "global decision-maker" based on evidence on performance of the existing system. So there is quite a bit of global coordination and "decision-making" in those algorithms beyond the simple "local learning". Anyway, if we "accept" the idea that memory can indeed be used for the purpose of learning (Paul Werbos indicated so in one of his notes), the terms of the debate/discussion change dramatically. We then open the door to the development of far more robust and reliable learning algorithms with much nicer properties than before. We can then start to develop algorithms that are closer to "normal human learning processes". Normal human learning includes processes such as (1) collection and storage of information about a problem, (2) examination of the information at hand to determine the complexity of the problem, (3) development of trial solutions (nets)for the problem, (4) testing of trial solutions (nets), (5) discarding such trial solutions (nets) if they are not good enough, and (6) repetition of these processes until an acceptable solution is found. And these learning processes are implemented within the brain, without doubt, using local computing mechanisms of different types. But these learning processes cannot exist without allowing for storage of information about the problem. One of the "large" missing pieces in the neural network field is the definition or characterization of an autonomous learning system such as the brain. We have never defined the external behavioral characteristics of our learning algorithms. We have largely pursued algorithm development from an "internal mechanisms" point of view (local learning, memoryless learning) rather than from the point of view of "external behavior or characteristics" of these resulting algorithms. Some of these external characteristics of our learning algorithms might be:(1) the capability to design the net on their own, (2) polynomial time complexity of the algorithm in design and training of the net, (3) generalization capability, and (4) learning from as few examples as possible (quickness in learning). It is perhaps time to define a set of desirable external characteristics for our learning algorithms. We need to define characteristics that are "independent of": (1) a particular architecture, (2) the problem to be solved (function approximation, classification, memory, etc.), (3)local/global learning issues, and (4) issues of whether to use memory or not to learn. We should rather argue about these external properties than issues of global/local learning and of memoryless learning. With best regards, Asim Roy Arizona State University