From smyth@galway.ICS.UCI.EDU Mon Sep 23 09:41:58 1996 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 JAA19756 for ; Mon, 23 Sep 1996 09:41:49 -0500 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id JAA18478 for ; Mon, 23 Sep 1996 09:41:45 -0500 Received: from (parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id TAA13012; Mon, 23 Sep 1996 19:16:36 +0800 Message-Id: <199609231116.TAA13012@cs.uwa.oz.au> From: Padhraic Smyth To: ml@ics.uci.edu, ai-stats@watstat.uwaterloo.ca, mlnet@swi.psy.uva.nl, news-announce-conferences@uunet.uu.net, Connectionists@cs.cmu.edu, uai@maillist.cs.orst.edu, bayes-news@stat.cmu.edu, nl-kr@cs.rpi.edu, colt@cs.uiuc.edu, ilpnet@IJS.si, kdd@gte.com, reinforce@cs.uwa.edu.au, comp-finance@teleport.com, sigart@vaxa.isi.edu, genetic-programming@cs.stanford.edu, CLASS-L@ccvm.sunysb.edu, ai-medicine@mednet.stanford.edu Subject: Call for Participation for AISTATS-97 [connectionists] Date: Fri, 20 Sep 1996 13:53:19 -0700 Call for Participation SIXTH INTERNATIONAL WORKSHOP ON ARTIFICIAL INTELLIGENCE AND STATISTICS January 4-7, 1997 Ft. Lauderdale, Florida REGISTRATION AND CONFERENCE INFORMATION Conference and tutorial registration forms, hotel information, and descriptions of the technical program and tutorials are all now available from the conference Web site: http://www.stat.washington.edu/aistats97/ The workshop will be held at the Radisson Bahia Mar Beach Resort in Fort Lauderdale. The workshop will consist of 20 plenary talks and 38 poster presentations over 2 1/2 days (January 5th to 7th). Preceding the workshop, January 4th, will be a day of tutorials by A. P. Dawid (University College London), Mike Jordan (MIT), Tom Mitchell (CMU), and Mike West (Duke University). Attendance at the workshop is open to all and is *not* limited to presenters of papers. Register early by December 2nd to take advantage of reduced registration fees. MORE INFORMATION: Visit the website directly for online information. For further details write to David Madigan (Program Chair) at aistats@stat.washington.edu for inquiries concerning the technical program or Padhraic Smyth (General Chair) at aistats@aig.jpl.nasa.gov for other inquiries about the workshop. From ghosh@zach.wustl.edu Mon Sep 23 09:53:14 1996 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 JAA19939 for ; Mon, 23 Sep 1996 09:53:03 -0500 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id JAA18686 for ; Mon, 23 Sep 1996 09:52:57 -0500 Received: from (parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id TAA12960; Mon, 23 Sep 1996 19:13:01 +0800 Message-Id: <199609231113.TAA12960@cs.uwa.oz.au> From: ghosh@zach.wustl.edu (Bijoy Ghosh) To: connect-bb@ed.eusip Cc: reinforce@cs.uwa.edu.au, gann-list@cs.iastate.edu, neuron-request@CATTELL.psych.upenn.edu, alife@cognet.ucla.edu, connectionists@cs.cmu.edu, hybrid-list@cs.ua.edu, LearningRobots@kimo.informatik.uni-dortmund.de, enns-list@dcs.kcl.ac.uk, echos@dmi.ens.fr, comp-neuro@smaug.bbb.caltech.edu, neuropl@plearn.edu.pl, neuras-list@etsiig.uniovi.es, aep-list@dsic.upv.es, acia@lsi.upc.es Subject: CIRA, 1997 [connectionists] Date: Wed, 18 Sep 1996 12:14:02 -0600 I am sending the following ad for inclusion in the mailing list. Please let me know if there is any questions. Bijoy K. Ghosh Department of Systems Science and Mathematics Washington University Saint Louis, MO 63130 XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX XXXXXXXX Call for Papers 1997 IEEE International Symposium on COMPUTATIONAL INTELLIGENCE IN ROBOTICS AND AUTOMATION (CIRA'97) Hyatt Regency, Monterey, California July 10-11, 1997 In conjunction with the 8th International Conference on Advanced Robotics, ICAR'97, July 5 - 9, 1997 Sponsored by the IEEE Robotics & Automation Society and the IEEE Neural Network Council The theme of CIRA'97 will be "Towards new computational principles for Robotics and Automation". Neural and fuzzy information processing, evolutionary computation, artificial life, chaos, etc., referred often collectively as computational intelligence, have by nature a strong connection to robotics and automation. During the past decade, numerous applications of computational intelligence to robotics and automation have appeared as partial or full alternatives to conventional approaches. A potentially explosive growth of applications is expected in the near future with many practical as well theoretical contributions, as research and practice of computational intelligence mature. Researchers are paying close attention to the emergence of new computational principles as they are applied in particular to robotics and automation. Indeed, the computational intelligence enables real-time and robust connections between sensing and action through learning. However, many research results as well as the growing level of interest in computational intelligence by the robotics and automation community have been scattered around various conferences and symposiums of more general themes. CIRA'97 will provide an international forum which draws together researchers and practitioners working on different aspects of computational intelligence in robotics and automation to exchange their ideas, concepts, and results. Participants will enjoy high quality, focused, and in-depth discussions on the subject matters of their interest. Papers are solicited for all aspect of theories, applications, and case studies related to computational intelligence in robotics and automation. DEADLINES: Submission of papers: Feb. 14, 1997 Acceptance notification: April 1, 1997 Camera-ready copy due: April 21, 1997 Submit four copies of completed paper in either single column or double column format to the address given below for peer review. Upon acceptance, authors will be requested to prepare a photoready copy. Send papers to Dr. Sukhan Lee, Dept. of Computer Science, SAL 204 University of Southern California, Los Angeles, CA 90089-0781, Email: shlee@pollux.usc.edu, Tel: (213)740-7230, Fax:(213) 740-7285 GENERAL CHAIR Antti Koivo, Purdue University PROGRAM CHAIR Sukhan Lee, JPL/Caltech and USC CO-CHAIRS Toshio Fukuda, Nagoya University, George Lee, Purdue University Carme Torras, Univ. Politechnica de Barcelona ORGANIZING COMMITTEE Publicity: Bijoy Ghosh, Washington University Kimon Valavanis, Southwestern Louisiana Univ. Publications: Yangsheng Xu, Carnegie Mellon Univ. Local Arrangements Xiaoping Yun, Naval Postgraduate School Finance: Richard Klafter, Temple University Panels/Tutorials/ Workshops William Gruver, Simon Fraser University Exhibits Fei-Yue Wang, University of Arizona International Liaison Angel P. del Pobil (Spain), Takanori Shibata (Japan), S. K. Cho (Hong Kong), Hyung-Suk Cho (Korea) STEERING COMMITTEE Michael Arbib (USC), George Bekey (USC), Zengnam Bien (KAIST), Paolo Dario (Univ. Pisa), Steve Hsia (UC-Davis), Antti Koivo (Purdue Univ.), Paul Werbos (NSF), Sukhan Lee (JPL/USC, Chair), T. J. Tarn (Washington University) SECRETARIES Fumihito Arai (Japan), Il-Hong Suh (Korea), Andrew Fagg (Univ. of Massachusetts), Seul Jung (UC-Davis) Topics include but are not limited to Robot control with neural networks, fuzzy systems, and neuro-fuzzy systems, Neural net based hand-eye coordination, Mobile robot navigation, Sensor referenced planning and control, Applications to man-machine systems and telerobotics, Skill acquisition, learning, and transfer, Behavior based control, Sensor planning and intelligent sensor placement, Society of robots with artificial life, Visual servoing, Pattern recognition, Recurrent nets and dynamics, Neuro-fuzzy systems, Automatic target recognition, Reactive and interactive task planning, Sensor integration and fusion with neural and fuzzy information processing, Neural networks for legged locomotion, Visual information processing, Computational intelligence in assembly, Scheduling and optimization with neural, fuzzy, and evolutionary computation, Biologically inspired robotics, Active vision, Robot-human communication and coordination, Multiple cooperative robots, Reinforcement learning over time, Virtual and visualized reality, Learning for planning and scheduling, Mobile robot localization and planning, Automatic programming by demonstration. For general information please contact Prof. Antti Koivo, School of Electrical Engineering Purdue University, West Lafayette, IN 47907-1285 Email: koivo@ecn.purdue.edu, Tel:(317) 494-3436, Fax:(317) 494-0880 or browse through our web site at http://www.cs.cmu.edu/afs/cs/project/space/www/cira97/conference.html From arbib@pollux.usc.edu Mon Sep 23 10:38:19 1996 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 KAA20577 for ; Mon, 23 Sep 1996 10:37:39 -0500 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id KAA19454 for ; Mon, 23 Sep 1996 10:37:32 -0500 Received: from (parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id TAA12974; Mon, 23 Sep 1996 19:14:52 +0800 Message-Id: <199609231114.TAA12974@cs.uwa.oz.au> From: "Michael A. Arbib" To: alife@cognet.ucla.edu, comp-neuro@smaug.bbb.caltech.edu, connectionists@cs.cmu.edu, cvnet@skivs.ski.org, doll@magnum.cog.brown.edu, list@cogsci.soton.ac.uk, neuron@cattell.psych.upenn.edu, reinforce@cs.uwa.edu.au, simulation@bikini.cis.ufl.edu Cc: giorgio@sssup.it Subject: An Interesting Conference - Mechatronics, Perception, and Action. [connectionists] Date: Fri, 20 Sep 1996 10:11:42 -0700 (PDT) ---------------------------------------------------------------- _ _ __ ___ __ , __ ___ |\/| | |__| |__| |__| / | |. |__. | . | |. __| | 2nd INTERNATIONAL WORKSHOP ON MECHATRONICAL COMPUTER SYSTEMS FOR PERCEPTION AND ACTION February 10-12, 1997 Scuola Superiore S. Anna Pisa, Italy MCPA'97 on Internet: http://www.sssup.it/www/eventi/mcpa.html ---------------------------------------------------------------- C A L L F O R P A P E R S Mechatronical computer systems, which we will see in advanced products and production equipment of tomorrow, are designed to do much more than calculate. The interaction with the environment and the integration of computational modules in every part of the equipment put new, and conceptually different, demands on the computer system. A development towards a complete integration between the mechanical system, advanced sensors and actuators, and a multitude of processing modules can be foreseen. At the system level, powerful algorithms for perceptual integration, goal-direction and action planning in real-time will be critical components. The resulting "action-oriented systems" may be able to learn and adapt to different circumstances and environments. Perceiving the objects and events of the external world and acting upon the situation in accordance with an appropriate behaviour, whether programmed, trained, or learned, are key functions of these next generation computer systems. The aim of this Workshop is to gather researchers and industrial development engineers to a fruitful exchange of ideas and results and, often interdisciplinary, discussions. ---------------------------------------------------------------- WORKSHOP FORM One day of the workshop will be devoted to "true workshop activities". The objective is to identify and propose research directions and key problem areas in mechatronical computing systems for perception and action. In the morning session, invited speakers, as well as other workshop delegates, will give their perspectives on the theme of the workshop. The work will proceed in smaller groups during the afternoon, and the conclusions will be presented in a plenary session. The scientific programme will also include presentation of research results in oral and poster form. Demonstrations of devices, sensors, software tools or methodologies for developing real-time autonomous systems are very welcome. ---------------------------------------------------------------- SUBJECT AREAS - Real-Time Systems - Dependable Computer Systems - Real-Time Decision Making and Action Planning - Parallel Processor Architectures for Embedded Systems - Development Tools and Support Systems for Mechatronics - Robotics - Sensory Systems - Sensory-Motor Coordination - Man-Machine Advanced Interfaces - Real-Time Control Applications - Adaptive and Learning Systems - Biologically Inspired Systems - Autonomous Systems ---------------------------------------------------------------- SUBMISSIONS Papers on the workshop topics should be 20 double-spaced pages (5,000 words) or less in length. Extended abstract (10 double- spaced pages or less in length) should contain enough information for the program committee to understand the scope of the project and evaluate the work. All accepted submissions will appear in the proceedings. Please send 4 copies of the manuscript to Giorgio Buttazzo Scuola Superiore S. Anna Via Carducci, 40 56100 Pisa, Italy Fax: +39 - 50 - 883.215 Email: giorgio@sssup.it A single cover page should be included which contains: paper title, full name, affiliations, complete addresses, phone and fax numbers, and email addresses of the authors, as well as a 100 to 150 words abstract. ---------------------------------------------------------------- IMPORTANT DATES Deadline for papers: September 30, 1996 Notification of acceptance: December 10, 1996 Deadline for camera-ready paper: January 15, 1997 Workshop days: February 10-12, 1997 ---------------------------------------------------------------- WORKSHOP LOCATION: Scuola Superiore S. Anna Via Carducci, 40 Pisa - Italy WORKSHOP LANGUAGE: English MCPA'97 ON INTERNET: http://www.sssup.it/www/eventi/mcpa.html ---------------------------------------------------------------- INVITED SPEAKERS - Michael Arbib University of Southern California, Los Angeles, USA "Visual Control of Grasp: From Monkey Brains to Dextrous Robots" - John Stankovic University of Massachusetts, Amherst, USA "Novel Uses of Reflection and Composability Concepts In Mechatronic Systems" - Paolo Dario Scuola Superiore S. Anna, Italy "Mechatronics in Medical Applications" ---------------------------------------------------------------- GENERAL CHAIR Paolo Ancilotti Scuola Superiore S.Anna 56100 Pisa, Italy Fax: +39 - 50 - 883.215 E-mail: paolo@sssup2.sssup.it PROGRAM CHAIR Giorgio Buttazzo Scuola Superiore S.Anna 56100 Pisa, Italy Fax: +39 - 50 - 883.215 E-mail: giorgio@sssup.it LOCAL ARRANGEMENT and FINANCE CHAIR Ettore Ricciardi Istituto Elaborazione Informazione 56100 Pisa, Italy Fax: +39 - 50 - 554.342 E-mail: ricciardi@iei.pi.cnr.it ---------------------------------------------------------------- ORGANIZATION Scuola Superiore S. Anna (Italy) and IEI Institute of CNR (Italy) ---------------------------------------------------------------- PROGRAMME COMMITTEE Benedetto Allotta (Italy) Paolo Ancilotti (Italy) Michael Arbib (USA) Albert-Jan Baerveldt (Sweden) George Bekey (USA) Lars Bengtsson (Sweden) Giorgio Buttazzo (Italy) Dave Cliff (UK) Paolo Dario (Italy) Felicita Di Giandomenico (Italy) Jan-Olof Eklundh (Sweden) Gerhard Fohler (Austria) Manfred Glesner (Germany) John Hallam (UK) Anders Lansner (Sweden) Tony Lewis (USA) Jean-Daniel Nicoud (Switzerland) Petri Pulli (Finland) John Stankovic (USA) Bertil Svensson (Sweden) Jan Torin (Sweden) Per-Arne Wiberg (Sweden) Jan Wikander (Sweden) ---------------------------------------------------------------- EVENTS The workshop will be held during the Carnival of Viareggio (20 Km from Pisa), a big event in Italy that could be of interest to some participants. This event is during the second week of February, and February 8-9-10-11 will be the most intensive days, when they organize a lot of parades in the streets. A social dinner will be organized in Viareggio on February 11. ---------------------------------------------------------------- From James_Morgan@brown.edu Mon Sep 23 19:53:52 1996 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 TAA09272 for ; Mon, 23 Sep 1996 19:53:41 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id TAA02297 for ; Mon, 23 Sep 1996 19:53:39 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa17308; 23 Sep 96 19:40:47 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa17306; 23 Sep 96 19:15:51 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa19581; 23 Sep 96 19:15:46 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa26859; 23 Sep 96 15:03:18 EDT Received: from golden.brown.edu by EDRC.CMU.EDU id aa10192; 23 Sep 96 15:02:21 EDT Received: from cog.brown.edu ([128.148.208.59]) by golden.brown.edu (8.7.3/8.7.3) with SMTP id PAA02867 for ; Mon, 23 Sep 1996 15:02:11 -0400 (EDT) Message-Id: <199609231902.PAA02867@golden.brown.edu> X-Sender: James_Morgan@postoffice.brown.edu X-Mailer: Windows Eudora Pro Version 2.1.2 Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Date: Mon, 23 Sep 1996 15:01:45 -0400 To: Connectionists@cs.cmu.edu From: Jim Morgan Subject: Position Announcement: Language & Cognitive Processing, Brown University LANGUAGE AND COGNITIVE PROCESSING, Brown University: The Department of Cognitive and Linguistic Sciences invites applications for a three year renewable tenure-track position at the Assistant Professor level beginning July 1, 1997. Areas of interest include but are not limited to phonology or phonological processing, syntax or sentence processing, and lexical access or lexical semantics, using experimental, formal, developmental, neurological, or computational methods. Expertise in two or more areas and/or application of multiple paradigms is preferred. Applicants should have a strong research program and a broad teaching ability in cognitive science and/or linguistics at both the undergraduate and graduate levels. Interest in contributing curricular innovations in keeping with Brown's university-college tradition is desirable. Applicants should have completed all Ph.D. requirements no later than July 1, 1997. Women and minorities are especially encouraged to apply. Send curriculum vitae, three letters of reference, reprints and preprints of publications, and a one page statement of research interests to Dr. Sheila E. Blumstein, Chair, Search Committee, Department of Cognitive and Linguistic Sciences, Brown University, Box 1978, Providence, RI 02912 by January 1, 1997. Brown University is an Equal Opportunity/Affirmative Action Employer. From terry@salk.edu Tue Sep 24 19:06:50 1996 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 TAA13165 for ; Tue, 24 Sep 1996 19:06:35 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id TAA20803 for ; Tue, 24 Sep 1996 19:06:33 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa18682; 24 Sep 96 18:48:05 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa18680; 24 Sep 96 18:35:26 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa21118; 24 Sep 96 18:35:07 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa17741; 24 Sep 96 16:22:23 EDT Received: from helmholtz.salk.edu by CS.CMU.EDU id aa28053; 24 Sep 96 14:18:07 EDT Received: (from terry@localhost) by helmholtz.salk.edu (8.7.5/8.7.3) id LAA06146; Tue, 24 Sep 1996 11:17:50 -0700 (PDT) Date: Tue, 24 Sep 1996 11:17:50 -0700 (PDT) From: Terry Sejnowski Message-Id: <199609241817.LAA06146@helmholtz.salk.edu> To: connectionists@cs.cmu.edu Subject: Neural Computation 8:7 Cc: terry@helmholtz.salk.edu Neural Computation - Contents Volume 8, Number 7 - October 1, 1996 The Lack of a Priori Distinctions Between Learning Algorithms David H. Wolpert The Existence of a Priori Distinctions Between Learning Algorithms David H. Wolpert Note No Free Lunch for Cross Validation Huaiyu Zhu and Richard Rohwer Letter A Self-Organizing Model of "Color Blob" Formation Harry G. Barrow, Alistair J. Bray and Julian M. L. Budd Functional Consequences of an Integration of Motion and Stereopsis in Area MT of Monkey Extrastriate Visual Cortex Markus Lappe Learning Perceptually Salient Visual Parameters Using Spatiotemporal Smoothness Constraints James V. Stone Using Visual Latencies to Improve Image Segmentation Ralf Opara and Florentin Worgotter Learning and Generalization in Cascade Network Architectures Enno Littmann and Helge Ritter Hybrid Modeling, HMM/NN Architectures, and Protein Applications Pierre Baldi and Yves Chauvin ----- ABSTRACTS - http://www-mitpress.mit.edu/jrnls-catalog/neural.html SUBSCRIPTIONS - 1996 - VOLUME 8 - 8 ISSUES ______ $50 Student and Retired ______ $78 Individual ______ $220 Institution Add $28 for postage and handling outside USA (+7% GST for Canada). (Back issues from Volumes 1-7 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 pfbaldi@cco.caltech.edu Wed Sep 25 23:59:33 1996 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 XAA07941 for ; Wed, 25 Sep 1996 23:59:27 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id XAA13401 for ; Wed, 25 Sep 1996 23:59:18 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa20011; 25 Sep 96 23:18:17 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa19996; 25 Sep 96 22:50:13 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa22115; 25 Sep 96 22:49:16 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id an07232; 25 Sep 96 17:35:58 EDT Received: from accord.cco.caltech.edu by CS.CMU.EDU id aa05205; 25 Sep 96 8:42:42 EDT Received: from localhost by accord.cco.caltech.edu with SMTP (8.6.12/DEI:4.45) id FAA14998; Wed, 25 Sep 1996 05:41:03 -0700 Date: Wed, 25 Sep 1996 05:40:58 -0700 (PDT) From: Pierre Baldi X-Sender: pfbaldi@accord To: Connectionists@cs.cmu.edu Subject: TR available: Bayesian Methods and Compartmental Modeling Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII FTP-host: archive.cis.ohio-state.edu FTP-filename: /pub/neuroprose/baldi.comp.tar.Z The file baldi.comp.tar.Z is now available for copying from the Neuroprose repository: ON THE USE OF BAYESIAN METHODS FOR EVALUATING COMPARTMENTAL NEURAL MODELS (40 pages = 35 pages + 5 figures) (one figure is in color but should print OK in black and white) P. Baldi, M. C. Vanier, and J. M. Bower Department of Computation and Neural Systems Caltech ABSTRACT: In this TR, we provide a tutorial on Bayesian methods for neurobiologists, as well an application of the methods to compartmental modeling. We first derive prior and likelihood functions for compartmental neural models and for spike trains. We then apply the full Bayesian inference machinery to parameter estimation, and model comparison in the case of simple classes of compartmental models, with three and four conductances. We also perform class comparison by approximating integrals over the entire parameter space. Advantages and drawbacks are discussed. Postscript and other problems reported to us have been corrected. From sverker.sikstrom@psy.umu.se Wed Sep 25 23:59:41 1996 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 XAA07944 for ; Wed, 25 Sep 1996 23:59:32 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id XAA13403 for ; Wed, 25 Sep 1996 23:59:27 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab20011; 25 Sep 96 23:19:05 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa20002; 25 Sep 96 22:56:33 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa22132; 25 Sep 96 22:55:44 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id bg07232; 25 Sep 96 17:38:38 EDT Received: from psycho.psy.umu.se by CS.CMU.EDU id aa06443; 25 Sep 96 10:44:50 EDT Received: from [130.239.155.31] (bomlc.psy.umu.se) by psy.umu.se (5.0/SMI-SVR4) id AA07064; Wed, 25 Sep 1996 16:37:22 --100 X-Sender: sverker@psycho.psy.umu.se Message-Id: Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Date: Wed, 25 Sep 1996 16:44:16 +0100 To: Connectionists@cs.cmu.edu From: Sverker Sikstrom Subject: PhD THESIS AVAILABLE: A Connectionist Model for Episodic Tests content-length: 3603 THESIS AVAILABLE My (Sverker Sikstr=F6m) thesis "TECO: A connectionist Model for Dependency in Successive Episodic Tests" is now available for anonymous download in postscript format at the following url-site: http://www.psy.umu.se/personal/thesis.ps.gz The file is approximately 1MB and unfolds to 3MB. The thesis includes 180 pages. You may also download it from my homepage: http://www.psy.umu.se/personal/Sverker.html The ABSTRACT is as follows: Sikstr=F6m, P. S. TECO: A connectionist Model for Dependency in Successive Episodic Tests. Doctoral dissertation, Department of Psychology, Ume University, S-90187 Ume, Sweden, 1996; ISBN 91-7191-155-3 Data from a large number of experimental conditions in published studies have shown that recognition and cued recall exhibit a moderate dependency described by the Tulving-Wiseman function. Exceptions from this lawfulness, in the form of higher dependency, are found when the recall test lacks effective cues (i.e., free recall exceptions) or when the recognition test is cued (i.e., cued recognition exceptions). In Study I, the TECO (Target, Event, Cue & Object) theory for dependency in successive tests, is proposed to account for the dependence between recognition and cued recall through the fact that both tests are cued with the instruction to retrieve from the learning episode (i.e., the event). Independence is accounted by differences in cueing; the recall test is cued by a contextual cue, whereas the recognition test is cued by the target. A quantitative degree of dependence, measured by =DF, is predicted to be one-third by counting the number of shared cues divided by the total number of cues. Free recall exceptions are predicted to reveal a dependency of one-half because the recall test lacks effective cues. Cued recognition exceptions are predicted to reveal a dependency of two-thirds because both tests are cued with the cue word. A function is derived to predict the conditional probabilities and the results show a reasonable fit with the predictions. In, Study II, the predictions of TECO on successive tests of cued recall and cued recognition, free recall and cued recognition, recognition, free recall and cued recall, recognition and cued recognition is tested. A database is presented for successive episodic tests. In, Study III the lawfulness of recognition failure is discussed. Hintzman claimed that the conditional probability of recognition given recall is constrained by the P(Rn)/P(Rc) boundary and that the phenomenon of recognition failure is, thus, a mathematical artefact. It is argued that this boundary is due to a psychological process and that this boundary carries important information regarding the underlying system. Furthermore, half of the deviation from the predictive function of recognition given cued recall is shown to arise from the lack of statistical power. In Study IV, TECO is simulated in a neural network of a Hopfield type. A theoretical analysis is proposed and nine sets of simulations are conducted. The results show that the theory can be simulated with reasonable agreement to empirical data. Keywords. Episodic memory, recognition failure, successive tests, lawfulness, connectionism. Feel free to contact me on the following address Email:sverker.sikstrom@psy.umu.se ---------------------------------------------------- PhD Sverker Sikstrom, Department of Psychology s90187 Ume University, Sweden Tel: ++46-90-166759, Fax: ++46-90-166695 Homepage:http://www.psy.umu.se/personal/Sverker.html ---------------------------------------------------- From ken@phy.ucsf.edu Wed Sep 25 23:59:42 1996 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 XAA07947 for ; Wed, 25 Sep 1996 23:59:34 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id XAA13405 for ; Wed, 25 Sep 1996 23:59:32 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ac20011; 25 Sep 96 23:19:48 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab20002; 25 Sep 96 22:56:35 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa22136; 25 Sep 96 22:55:49 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa07854; 25 Sep 96 17:52:51 EDT Received: from coltrane.ucsf.EDU by EDRC.CMU.EDU id aa24528; 25 Sep 96 17:50:50 EDT Received: by coltrane.ucsf.edu (5.65v3.2/GSC4.24) id AA09350 for Connectionists@CS.CMU.EDU; Wed, 25 Sep 1996 14:52:47 -0700 Date: Wed, 25 Sep 1996 14:52:47 -0700 From: Ken Miller Message-Id: <9609252152.AA09350@coltrane.ucsf.edu> To: Connectionists@cs.cmu.edu, cneuro@smaug.bbb.caltech.edu Subject: Hertz Fellowships for graduate studies [ Moderator's note: Carnegie Mellon, Stanford, and MIT are also on the list of approved schools for Hertz fellowships. -- DST] I wanted to bring to the attention of prospective and current Ph.D. students something I just ran across, the Fannie and John Hertz Foundation fellowship for studies in Applied Physical Sciences. They define applied physical sciences to explicitly include computational neuroscience, artificial intelligence, and robotics. The deadline is quite soon -- Oct. 18. It's a generous fellowship -- 5 yrs, stipend of $20K per year. Info is at http://www.hertzfndn.org Please don't ask me for more info about this fellowship -- go to the foundation and/or its web page. The fellowships are only tenable at a short list of eligible schools, but applicants can also include in their application the desire that other schools be added to that list. In particular, three of the existing schools with Sloan Centers for Theoretical Neurobiology -- Caltech, UCSD, and NYU -- are on the list, but the other two -- UCSF and Brandeis -- are not. As a member of the faculty at UCSF, I'd certainly like to encourage applicants in computational neuroscience to include UCSF and/or Brandeis on your list of desired schools and to check us out in months to come. More info on UCSF can be found at: Neuroscience Program: http://www.neuroscience.ucsf.edu/neuroscience/ Sloan Center: http://www.sloan.ucsf.edu/sloan/ (links to Brandeis and the other Sloan centers can be found on our Sloan page). Ken Kenneth D. Miller telephone: (415) 476-8217 Dept. of Physiology fax: (415) 476-4929 UCSF internet: ken@phy.ucsf.edu 513 Parnassus www: http://www.keck.ucsf.edu/~ken San Francisco, CA 94143-0444 From jordan@psyche.mit.edu Thu Sep 26 08:25:06 1996 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 IAA11265 for ; Thu, 26 Sep 1996 08:25:00 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id IAA16292 for ; Thu, 26 Sep 1996 08:24:57 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa19994; 25 Sep 96 23:09:18 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa19992; 25 Sep 96 22:49:22 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa22108; 25 Sep 96 22:48:57 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa07232; 25 Sep 96 17:34:02 EDT Received: from PSYCHE.MIT.EDU by CS.CMU.EDU id aa04078; 25 Sep 96 3:15:10 EDT Received: by psyche.mit.edu (4.1/DA1.0.4) id AA23535; Wed, 25 Sep 96 03:15:04 EDT From: Michael Jordan Message-Id: <9609250715.AA23535@psyche.mit.edu> Subject: NIPS Conference Program To: connectionists@cs.cmu.edu Date: Wed, 25 Sep 96 3:15:03 EDT Cc: Michael Jordan X-Mailer: ELM [version 2.3 PL0] The NIPS*96 conference program is now available. It can be retrieved via anonymous ftp from: ftp://psyche.mit.edu/pub/NIPS96/nips96-program It will also be available soon from the NIPS*96 homepage. NIPS*96 begins on December 2 with a tutorial program and banquet. The NIPS*96 invited speakers are as follows: MON DEC 2 --------- Computer graphics for film: Automatic versus manual techniques (Banquet talk) E. Enderton Industrial Light and Magic TUE DEC 3 --------- The CONDENSATION algorithm---conditional density propagation and applications to visual tracking (Invited) A. Blake University of Oxford Compositionality, MDL priors, and object recognition (Invited) S. Geman, E. Bienenstock Brown University WED DEC 4 --------- Plasticity of dynamics as opposed to absolute strength of synapse (Invited) H. Markram Weizmann Institute Transition between rate and temporal coding in neocortex as determined by synaptic depression (Invited) M. Tsodyks Weizmann Institute THU DEC 5 --------- Wavelets, wavelet packets, and beyond: Applications of new adaptive signal representations (Invited) D. Donoho Stanford University and University of California Berkeley Michael Jordan NIPS*96 Program Chair From jordan@psyche.mit.edu Thu Sep 26 19:12:37 1996 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 TAA03730 for ; Thu, 26 Sep 1996 19:12:26 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id TAA00715 for ; Thu, 26 Sep 1996 19:12:19 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa21529; 26 Sep 96 16:05:59 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa21527; 26 Sep 96 15:50:04 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa22784; 26 Sep 96 15:49:23 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id av26089; 26 Sep 96 14:14:00 EDT Received: from PSYCHE.MIT.EDU by CS.CMU.EDU id aa10758; 25 Sep 96 16:56:42 EDT Received: by psyche.mit.edu (4.1/DA1.0.4) id AA05917; Wed, 25 Sep 96 16:56:32 EDT From: Michael Jordan Message-Id: <9609252056.AA05917@psyche.mit.edu> Subject: NIPS program committee notes To: connectionists@cs.cmu.edu Date: Wed, 25 Sep 96 16:56:32 EDT Cc: Michael Jordan X-Mailer: ELM [version 2.3 PL0] Dear connectionists colleagues, I enclose below some notes on this year's NIPS reviewing and decision process. These notes will hopefully be of interest not only to contributors to NIPS*96, but to anyone else who has an ongoing interest in the conference. Note also that there is a "feedback session with the NIPS board" scheduled for Wednesday, December 4th at the conference venue; this would be a good opportunity for public discussion of NIPS reviewing and decision policies. In my experience NIPS has worked hard to earn its role as a flagship conference serving a diverse technical community, particularly through its revolving program committees, and further public discussion of NIPS decision- making procedures can only help to improve the conference. The notes include lists of all of this year's area chairs and reviewers. Mike Jordan NIPS*96 program chair ----------------------------------------------------------- The area chairs for NIPS*96 were as follows: Algorithms and Architectures Chris Bishop, Aston University Steve Omohundro, NEC Research Institute Rob Tibshirani, University of Toronto Theory Michael Kearns, AT&T Research Sara Solla, AT&T Research Vision David Mumford, Harvard University Control Andrew Moore, Carnegie Mellon University Applications Anders Krogh, The Sanger Centre Speech and Signals Eric Wan, Oregon Graduate Institute Neuroscience Bill Bialek, NEC Research Institute Artificial Intelligence/Cognitive Science Stuart Russell, University of California, Berkeley Implementations Fernando Pineda, Johns Hopkins University The area chairs were responsible for recruiting reviewers. All told, 160 reviewers were recruited, from 17 countries. 104 reviewers were from institutions in the US, and 56 reviewers were from institutions outside the US. The breakdown of the submissions by areas was as follows: 1995 1996 ---------------------------------------- Alg & Arch 133 173 Theory 89 79 Neuroscience 43 61 Control & Nav 40 43 Applications 36 42 Vision 46 40 Speech & Sig Proc 20 25 Implementations 25 24 AI & Cog Sci 30 22 ---------------------------------------- Total 462 509 Area chairs assigned papers to reviewers. For cases in which an area chair was an author of a paper the program chair made the selection of reviewers. For cases in which the program chair was an author of a submission the appropriate area chair made the selection of reviewers. Code letters were used for all such reviewers, and neither the area chairs nor the program chair knew (or know) who reviewed their papers. Each paper was reviewed by three reviewers. In most cases all three reviewers were from the same area, but some papers that were particularly interdisciplinary in flavor were reviewed by reviewers from different areas. After the reviews were received and processed the program committee met at MIT in August to make decisions. A few comments on the meeting way the meeting was run: (1) It was agreed that the overriding goal of the program committee's decision process should be to select the best papers, i.e., those exhibiting the most significant thinking and the most thorough development of ideas. All other issues were considered secondary. (2) To achieve (1), the program committee agreed that one of its principal roles was to help eliminate bias in the reviewing process. This took several forms: (a) Close attention was paid to cases in which the reviewers disagreed among themselves. In such cases the area chair often read the paper him/herself to help come to a decision. (b) The area chairs studied histograms of scores to help identify cases where reviewers seemed to be using different scales. (c) The committee tried to identify reviewers who were not as strong or as devoted as others and tried to weight their reviews accordingly. (3) It was agreed that authors who were members of the program committee would be held to higher standards than other authors. That is, if a paper by a program committee author was near a borderline (acceptance, spotlight, oral), it would be demoted. This was considered to be another form of bias minimization, given that the committee was aware that some reviewers might favor program committee members. Also, program committee members who were authors of a paper left the room when their paper was being discussed; they played no role in the decision-making process for their own papers. (4) Other criteria that were utilized in the decision-making process included: junior status of authors (younger authors were favored), new-to-NIPS criteria (outsiders were favored), novelty (new ideas were favored). These criteria also figured in decisions for oral presentations and spotlights, along with additional criteria that favored authors who had not had an oral presentation in recent years and favored presentations of general interest to the NIPS audience. All such criteria, however, were considered secondary, in that they were used to distinguish papers that were gauged to be of roughly equal quality by the reviewers. As stated above, the primary criterion was to select the best papers, and to give oral presentations to papers receiving the most laudatory reviews. (5) Generally speaking, it turned out that the program committee decisions followed the reviewers' scores. A rough guess would be that 1 paper in 10 was moved up or down from where the reviewers' scores placed the paper. (6) The entire program committee participated in the discussions of individual papers for all of the areas. (7) The decision making was seldom easy. It was the overall sense of the program committee that the submissions were exceptionally strong this year. There were many papers near the borderline that were of NIPS quality, but could not be accepted because of size constraints (the conference is limited in size by a number of factors, including the scheduling and the size of the proceedings volume). We hope that authors of these papers will strengthen them a notch and resubmit next year. The process was as fair and as intellectually rigorous as the program committee could make it. It can of course stand improvement, however, and I would hope that people with ideas in this regard will attend the feedback session in Denver. One improvement that I personally think is worth considering, having now seen the reviewing process in such detail, is to allow reviewers to consult among themselves. In this model, reviewers exchange their reviews and discuss them before sending final reviews to the program chair. I review for other conferences where this is done, and I think that it has the substantial advantage of helping to reduce cases where a reviewer just didn't understand something and thus gave a paper an unreasonably low score. Such is my opinion at any case. Perhaps this idea and other such ideas could be discussed in Denver. Mike Jordan ------------------------------------------------------------------- Reviewers for NIPS*96: --------------------- Larry Abbott David Lowe Naoki Abe David Madigan Subutai Ahmad Marina Meila Ethem Alpaydin Bartlett Mel Chuck Anderson David Miller James Anderson Kenneth Miller Chris Atkeson Martin Moller Pierre Baldi Read Montague Naama Barkai Tony Movshon Etienne Barnard Klaus Mueller Andy Barto Alan Murray Francoise Beaufays Ian Nabney Sue Becker Jean-Pierre Nadal Yoshua Bengio Ken Nakayama Michael Biehl Ralph Neuneier Leon Bottou Mahesan Niranjan Herve Bourlard Peter Norvig Timothy Brown Klaus Obermayer Nader Bshouty Erkki Oja Joachim Buhmann Genevieve Orr Carmen Canavier Art Owen Claire Cardie Barak Pearlmutter Ted Carnevale Jing Peng Nestor Caticha Fernando Pereira Gert Cauwenberghs Pietro Perona David Cohn Carsten Peterson Greg Cooper Jay Pittman Corinna Cortes Tony Plate Gary Cottrell John Platt Marie Cottrell Jordan Pollack Bob Crites Alexandre Pouget Christian Darken Jose Principe Peter Dayan Adam Prugel-Bennett Virginia de Sa Anand Rangarajan Alain Destexhe Carl Rasmussen Thomas Dietterich Steve Renals Dawei Dong Barry Richmond Charles Elkan Peter Riegler Ralph Etienne-Cummings Brian Ripley Gary Flake David Rohwer Paolo Frasconi David Saad Bill Freeman Philip Sabes Yoav Freund Lawrence Saul Jerry Friedman Stefan Schaal Patrick Gallinari Jeff Schneider Stuart Geman Terrence Sejnowski Zoubin Ghahramani Robert Shapley Federico Girosi Patrice Simard Mirta Gordon Tai Sing Russ Greiner Yoram Singer Vijaykumar Gullapalli Satinder Singh Isabelle Guyon Padhraic Smyth Lars Hansen Bill Softky John Harris David Somers Michael Hasselmo Devika Subramanian Simon Haykin Richard Sutton David Heckerman Josh Tenenbaum John Hertz Michael Thielscher Andreas Herz Sebastian Thrun Tom Heskes Mike Titterington Geoffrey Hinton Geoffrey Towell Sean Holden Todd Troyer Don Hush Ah Chung Tsoi Nathan Intrator Michael Turmon Tommi Jaakkola Joachim Utans Marwan Jabri Benjamin VanRoy Jeff Jackson Kelvin Wagner Robbie Jacobs Raymond Watrous Chuanyi Ji Yair Weiss Ido Kanter Christopher Williams Bert Kappen Ronald Williams Dan Kersten Robert Williamson Ronny Kohavi David Willshaw Alan Lapedes Ole Winther John Lazzaro David Wolpert Todd Leen Lei Xu Zhaoping Li Alan Yuille Christiane Linster Tony Zador Richard Lippmann Steven Zucker Michael Littman From levy@xws.com Thu Sep 26 19:12:47 1996 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 TAA03735 for ; Thu, 26 Sep 1996 19:12:34 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id TAA00719 for ; Thu, 26 Sep 1996 19:12:31 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab21553; 26 Sep 96 16:18:40 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab21533; 26 Sep 96 15:51:41 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa22797; 26 Sep 96 15:50:43 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa28275; 26 Sep 96 15:39:31 EDT Received: from sawtooth.xws.com by CS.CMU.EDU id aa20247; 26 Sep 96 15:38:20 EDT Received: from kenyma (ppp76.xws.com [205.162.198.76]) by sawtooth.xws.com (8.6.12/8.6.9) with SMTP id LAA07447 for ; Thu, 26 Sep 1996 11:39:40 -0700 Message-Id: <1.5.4.32.19960926193609.0069a4ec@mail.xws.com> X-Sender: levy@mail.xws.com X-Mailer: Windows Eudora Light Version 1.5.4 (32) Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Date: Thu, 26 Sep 1996 12:36:09 -0700 To: Connectionists@cs.cmu.edu From: "Kenneth L. Levy" Subject: Dissertation Available: The Transformation of Acoustic Information by Cochlear Nucleus Octopus Cells: A Modeling Study Hello, My (Ken Levy) dissertation is available as a compressed postscript file for DOS/Win and Unix (downloading directions below). The dissertation is entitled "The Transformation of Acoustic Information by Cochlear Nucleus Octopus Cells: A Modeling Study." The cochlear nucleus is the first nuclei of the mammalian auditory brainstem, and the octopus cell type is one of the principlal cell types. Octopus cells respond only at the onset of a toneburst. The dissertation presents an analysis of a compartmental model using GENESIS that led to a description of the underlying mechanism of the onset response of the octopus cell. It also includes the development, analysis and verification of the novel, biologically-plausible model, labeled the intrinsic membrane model (IMM), that produces accurate spike times 100-to-1000 time more efficiently than a compartmental model. Finally, the document covers the utilization of the IMM to demonstrate the enhancement of the encoding of the fundamental frequency of the vowel [i] in background noise by single-cell and ensemble models of octopus cells. Comments and suggestions are welcome and encouraged! Thank you for your time and consideration. --Ken Downloading Information: ------------------------ Homepage URL => http://www.eas.asu.edu/~neurolab or Homepage URL => http://www.xws.com/levy/levypub.html or Anonymous FTP site => ftp.eas.asu.edu (login:anonymous passwd:your email) FTP directory => pub/neurolab Dissertation file => Diss.ps.Z or DissPS.exe IMM => IMMdemo.tar.Z or IMMdemo.exe =============================================================== Kenneth L. Levy, Ph.D. levy@xws.com Acoustic Information Processing Lab http://www.xws.com/levy 31 Skamania Coves Drive Voice: (509) 427-5374 Stevenson, WA 98648 FAX: (509) 427-7131 =============================================================== From rao@cs.rochester.edu Thu Sep 26 19:12:48 1996 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 TAA03732 for ; Thu, 26 Sep 1996 19:12:31 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id TAA00717 for ; Thu, 26 Sep 1996 19:12:26 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa21553; 26 Sep 96 16:17:54 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa21533; 26 Sep 96 15:51:40 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa22792; 26 Sep 96 15:50:17 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id ac27873; 26 Sep 96 15:15:23 EDT Received: from cayuga.cs.rochester.edu by RI.CMU.EDU id aa25231; 26 Sep 96 15:12:24 EDT Received: from skunk.cs.rochester.edu (skunk.cs.rochester.edu [192.5.53.143]) by cayuga.cs.rochester.edu (8.6.9/H) with ESMTP id PAA17521; Thu, 26 Sep 1996 15:08:47 -0400 Received: (from rao@localhost) by skunk.cs.rochester.edu (8.6.9/K) id PAA19545; Thu, 26 Sep 1996 15:07:05 -0400 Date: Thu, 26 Sep 1996 15:07:05 -0400 Message-Id: <199609261907.PAA19545@skunk.cs.rochester.edu> From: Rajesh Rao To: connectionists@cs.cmu.edu, comp-neuro@smaug.bbb.caltech.edu, neuron@cattell.psych.upenn.edu, psyc@pucc.princeton.edu, vision-list@teleosresearch.com, cvnet@skivs.ski.org, cogneuro@ptolemy-ethernet.arc.nasa.gov, neuronet@tutkie.tut.ac.jp, cogpsy@phil.ruu.nl, cogpsych@ripken.oit.unc.edu CC: rao@cs.rochester.edu Subject: Tech Report: Visual Cortex as a Hierarchical Predictor The following technical report on a hierarchical predictor model of the visual cortex and the complex cell phenomenon of "endstopping" is available for retrieval via ftp. Comments and suggestions welcome (This message has been cross-posted - my apologies to those who received it more than once). -- Rajesh Rao Internet: rao@cs.rochester.edu Dept. of Computer Science VOX: (716) 275-2527 University of Rochester FAX: (716) 461-2018 Rochester NY 14627-0226 WWW: http://www.cs.rochester.edu/u/rao/ =========================================================================== The Visual Cortex as a Hierarchical Predictor Rajesh P.N. Rao and Dana H. Ballard Technical Report 96.4 National Resource Laboratory for the Study of Brain and Behavior Department of Computer Science, University of Rochester September, 1996 Abstract A characteristic feature of the mammalian visual cortex is the reciprocity of connections between cortical areas [1]. While corticocortical feedforward connections have been well studied, the computational function of the corresponding feedback projections has remained relatively unclear. We have modelled the visual cortex as a hierarchical predictor wherein feedback projections carry predictions for lower areas and feedforward projections carry the difference between the predictions and the actual internal state. The activities of model neurons and their synaptic strength are continually adapted using a hierarchical Kalman filter [2] that minimizes errors in prediction. The model generalizes several previously proposed encoding schemes [3,4,5,6,7,8] and allows functional interpretations of a number of well-known psychophysical and neurophysiological phenomena [9]. Here, we present simulation results suggesting that the classical phenomenon of endstopping [10,11] in cortical neurons may be viewed as an emergent property of the cortex implementing a hierarchical Kalman filter-like prediction mechanism for efficient encoding and recognition. Retrieval information: FTP-host: ftp.cs.rochester.edu FTP-pathname: /pub/u/rao/papers/endstop.ps.Z WWW URL: ftp://ftp.cs.rochester.edu/pub/u/rao/papers/endstop.ps.Z 20 pages; 302K compressed. The following related papers are also available via ftp: ------------------------------------------------------------------------- Dynamic Model of Visual Recognition Predicts Neural Response Properties In The Visual Cortex Rajesh P.N. Rao and Dana H. Ballard (Neural Computation - in press) Abstract The responses of visual cortical neurons during fixation tasks can be significantly modulated by stimuli from beyond the classical receptive field. Modulatory effects in neural responses have also been recently reported in a task where a monkey freely views a natural scene. In this paper, we describe a hierarchical network model of visual recognition that explains these experimental observations by using a form of the extended Kalman filter as given by the Minimum Description Length (MDL) principle. The model dynamically combines input-driven bottom-up signals with expectation-driven top-down signals to predict current recognition state. Synaptic weights in the model are adapted in a Hebbian manner according to a learning rule also derived from the MDL principle. The resulting prediction/learning scheme can be viewed as implementing a form of the Expectation-Maximization (EM) algorithm. The architecture of the model posits an active computational role for the reciprocal connections between adjoining visual cortical areas in determining neural response properties. In particular, the model demonstrates the possible role of feedback from higher cortical areas in mediating neurophysiological effects due to stimuli from beyond the classical receptive field. Simulations of the model are provided that help explain the experimental observations regarding neural responses in both free viewing and fixating conditions. Retrieval information: FTP-host: ftp.cs.rochester.edu FTP-pathname: /pub/u/rao/papers/dynmem.ps.Z WWW URL: ftp://ftp.cs.rochester.edu/pub/u/rao/papers/dynmem.ps.Z 43 pages; 569K compressed. -------------------------------------------------------------------------- A Class of Stochastic Models for Invariant Recognition, Motion, and Stereo Rajesh P.N. Rao and Dana H. Ballard Technical Report 96.1 Abstract We describe a general framework for modeling transformations in the image plane using a stochastic generative model. Algorithms that resemble the well-known Kalman filter are derived from the MDL principle for estimating both the generative weights and the current transformation state. The generative model is assumed to be implemented in cortical feedback pathways while the feedforward pathways implement an approximate inverse model to facilitate the estimation of current state. Using the above framework, we derive models for invariant recognition, motion estimation, and stereopsis, and present preliminary simulation results demonstrating recognition of objects in the presence of translations, rotations and scale changes. Retrieval information: FTP-host: ftp.cs.rochester.edu FTP-pathname: /pub/u/rao/papers/invar.ps.Z URL: ftp://ftp.cs.rochester.edu/pub/u/rao/papers/invar.ps.Z 7 pages; 430K compressed. ========================================================================== Anonymous ftp instructions: >ftp ftp.cs.rochester.edu Connected to anon.cs.rochester.edu. 220 anon.cs.rochester.edu FTP server (Version wu-2.4(3)) ready. Name: [type 'anonymous' here] 331 Guest login ok, send your complete e-mail address as password. Password: [type your e-mail address here] ftp> cd /pub/u/rao/papers/ ftp> get endstop.ps ftp> get dynmem.ps ftp> get invar.ps ftp> bye From es2029@eng.warwick.ac.uk Fri Sep 27 10:03:30 1996 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 KAA11820 for ; Fri, 27 Sep 1996 10:02:59 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id KAA08901 for ; Fri, 27 Sep 1996 10:02:52 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa22725; 27 Sep 96 4:20:23 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa22723; 27 Sep 96 4:06:43 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa23567; 27 Sep 96 4:06:36 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa10359; 27 Sep 96 4:01:03 EDT Received: from eagle.eng.warwick.ac.uk by RI.CMU.EDU id aa28524; 27 Sep 96 4:00:56 EDT Received: from eng.warwick.ac.uk by eagle.eng.warwick.ac.uk with SMTP id JAA13810; Fri, 27 Sep 1996 09:00:34 +0100 From: es2029@eng.warwick.ac.uk Message-Id: <25868.9609270800@eng.warwick.ac.uk> Subject: Thesis available: Constrained weight nets To: Connectionists@cs.cmu.edu Date: Fri, 27 Sep 96 9:00:32 BST X-Mailer: ELM [version 2.3 PL8] The following PhD Thesis is available on the web: ---------------------------------------------------- Feedforward Neural Networks with Constrained Weights ---------------------------------------------------- Altaf H. Khan (Email address effective 7 Oct 96 a.h.khan@ieee.org) Department of Engineering, University of Warwick, Coventry, CV4 7AL, England August 1996 218 pages - gzipped postscript version available as http://www.eng.warwick.ac.uk/~es2029/thesis.ps.gz This thesis will also be made available on Neuropose in the near future. ---------------------------------------------------- Thesis Summary The conventional multilayer feedforward network having continuous-weights is expensive to implement in digital hardware. Two new types of networks are proposed which lend themselves to cost-effective implementations in hardware and have a fast forward-pass capability. These two differ from the conventional model in having extra constraints on their weights: the first allows its weights to take integer values in the range [-3, 3] only, whereas the second restricts its synapses to the set {-1,0,1} while allowing unrestricted offsets. The benefits of the first configuration are in having weights which are only 3-bits deep and a multiplication operation requiring a maximum of one shift, one add, and one sign-change instruction. The advantages of the second are in having 1-bit synapses and a multiplication operation which consists of a single sign-change instruction. The procedure proposed for training these networks starts like the conventional error backpropagation procedure, but becomes more and more discretised in its behaviour as the network gets closer to an error minimum. Mainly based on steepest descent, it also has a perturbation mechanism to avoid getting trapped in local minima, and a novel mechanism for rounding off `near integers'. It incorporates weight elimination implicitly, which simplifies the choice of the start-up network configuration for training. It is shown that the integer-weight network, although lacking the universal approximation capability, can implement learning tasks, especially classification tasks, to acceptable accuracies. A new theoretical result is presented which shows that the multiplier-free network is a universal approximator over the space of continuous functions of one variable. In light of experimental results it is conjectured that the same is true for functions of many variables. Decision and error surfaces are used to explore the discrete-weight approximation of continuous-weight networks using discretisation schemes other than integer weights. The results suggest that provided a suitable discretisation interval is chosen, a discrete-weight network can be found which performs as well as a continuous-weight networks, but that it may require more hidden neurons than its conventional counterpart. Experiments are performed to compare the generalisation performances of the new networks with that of the conventional one using three very different benchmarks: the MONK's benchmark, a set of artificial tasks designed to compare the capabilities of learning algorithms, the `onset of diabetes mellitus' prediction data set, a realistic set with very noisy attributes, and finally the handwritten numeral recognition database, a realistic but very structured data set. The results indicate that the new networks, despite having strong constraints on their weights, have generalisation performances similar to that of their conventional counterparts. -- Altaf. From marney@ai.mit.edu Fri Sep 27 10:03:35 1996 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 KAA11829 for ; Fri, 27 Sep 1996 10:03:11 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id KAA08906 for ; Fri, 27 Sep 1996 10:02:59 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa22768; 27 Sep 96 4:43:36 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa22766; 27 Sep 96 4:35:52 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa23627; 27 Sep 96 4:35:39 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aj26290; 26 Sep 96 14:18:35 EDT Received: from life.ai.mit.edu by CS.CMU.EDU id aa12920; 25 Sep 96 21:32:39 EDT Received: from carpentras.ai.mit.edu (CARPENTRAS.MIT.EDU [18.42.0.101]) by life.ai.mit.edu (8.7.5/8.7.5AI/life.ai.mit.edu:1.6) with SMTP id VAA14649; Wed, 25 Sep 1996 21:32:34 -0400 (EDT) From: Marney Smyth Received: by carpentras.ai.mit.edu (4.1/AI-4.10) id AA05378; Wed, 25 Sep 96 21:32:31 EDT Message-Id: <9609260132.AA05378@carpentras.ai.mit.edu> Subject: Modern Regression and Classification Course in Boston To: connectionists@cs.cmu.edu Date: Wed, 25 Sep 1996 21:32:31 -0400 (EDT) Cc: Marney Smyth X-Mailer: ELM [version 2.4 PL25] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ +++ +++ +++ Modern Regression and Classification +++ +++ Widely Applicable Statistical Methods for +++ +++ Modeling and Prediction +++ +++ +++ +++ Cambridge, MA, December 9 - 10, 1996 +++ +++ +++ +++ Trevor Hastie, Stanford University +++ +++ Rob Tibshirani, University of Toronto +++ +++ +++ ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ This two-day course will give a detailed overview of statistical models for regression and classification. Known as machine-learning in computer science and artificial intelligence, and pattern recognition in engineering, this is a hot field with powerful applications in science, industry and finance. The course covers a wide range of models, from linear regression through various classes of more flexible models, to fully nonparametric regression models, both for the regression problem and for classification. Although a firm theoretical motivation will be presented, the emphasis will be on practical applications and implementations. The course will include many examples and case studies, and participants should leave the course well-armed to tackle real problems with realistic tools. The instructors are at the forefront in research in this area. After a brief overview of linear regression tools, methods for one-dimensional and multi-dimensional smoothing are presented, as well as techniques that assume a specific structure for the regression function. These include splines, wavelets, additive models, MARS (multivariate adaptive regression splines), projection pursuit regression, neural networks and regression trees. The same hierarchy of techniques is available for classification problems. Classical tools such as linear discriminant analysis and logistic regression can be enriched to account for nonlinearities and interactions. Generalized additive models and flexible discriminant analysis, neural networks and radial basis functions, classification trees and kernel estimates are all such generalizations. Other specialized techniques for classification including nearest-neighbor rules and learning vector quantization will also be covered. Apart from describing these techniques and their applications to a wide range of problems, the course will also cover model selection techniques, such as cross-validation and the bootstrap, and diagnostic techniques for model assessment. Software for these techniques will be illustrated, and a comprehensive set of course notes will be provided to each attendee. Additional information is available at the Website: http://playfair.stanford.edu/~trevor/mrc.html COURSE OUTLINE DAY ONE: Overview of regression methods: Linear regression models and least squares. Ridge regression and the lasso. Flexible linear models and basis function methods. linear and nonlinear smoothers; kernels, splines, and wavelets. Bias/variance tradeoff- cross-validation and bootstrap. Smoothing parameters and effective number of parameters. Surface smoothers. ++++++++ Structured Nonparametric Regression: Problems with high dimensional smoothing. Structured high-dimensional regression: additive models. project pursuit regression. CART, MARS. radial basis functions. neural networks. applications to time series forecasting. DAY TWO: Classification: Statistical decision theory and classification rules. Linear procedures: Discriminant Analysis. Logistics regression. Quadratic discriminant analysis, parametric models. Nearest neighbor classification, K-means and LVQ. Adaptive nearest neighbor methods. ++++++++ Nonparametric classification: Classification trees: CART. Flexible/penalized discriminant analysis. Multiple logistic regression models and neural networks. Kernel methods. THE INSTRUCTORS Professor Trevor Hastie of the Statistics and Biostatistics Departments at Stanford University was formerly a member of the Statistics and Data Analysis Research group AT & T Bell Laboratories. He co-authored with Tibshirani the monograph Generalized Additive Models (1990) published by Chapman and Hall, and has many research articles in the area of nonparametric regression and classification. He also co-edited the Wadsworth book Statistical Models in S (1991) with John Chambers. Professor Robert Tibshirani of the Statistics and Biostatistics departments at University of Toronto is the most recent recipient of the COPSS award - an award given jointly by all the leading statistical societies to the most outstanding statistician under the age of 40. He also has many research articles on nonparametric regression and classification. With Bradley Efron he co-authored the best-selling text An Introduction to the Bootstrap in 1993, and has been an active researcher on bootstrap technology for the past 11 years. Quotes from previous participants: "... the best presentation by professional statisticians I have ever had the pleasure of attending" ".. superior to most courses in all respects." Both Prof. Hastie and Prof. Tibshirani are actively involved in research in modern regression and classification and are well-known not only in the statistics community but in the machine-learning and neural network fields as well. The have given many short courses together on classification and regression procedures to a wide variety of academic, government and industrial audiences. These include the American Statistical Association and Interface meetings, NATO ASI Neural Networks and Statistics workshop, AI and Statistics, and the Canadian Statistical Society meetings. BOSTON COURSE: December 9-10, 1996 at the HYATT REGENCY HOTEL, CAMBRIDGE, MASSACHUSETTS. PRICE: $750 per attendee before November 11, 1996. Full time registered students receive a 40% discount (i.e. $450). Cancellation fee is $100 after October 29, 1996. Registration fee after November 11, 1996 is $950 (Students $530). Attendance is limited to the first 60 applicants, so sign up soon! These courses fill up quickly. HOTEL ACCOMMODATION The Hyatt Regency Hotel offers special accommodation rates for course participants ($139 per night). Contact the hotel directly - The Hyatt Regency Hotel, 575 Memorial Drive, Cambridge, MA 02139. Phone : 617 4912-1234 Alternative hotel accommodation information at MRC WebSite: http://playfair.stanford.edu/~trevor/mrc.html COURSE REGISTRATION TO REGISTER: Detach and fill in the Registration Form below: Modern Regression and Classification Widely applicable methods for modeling and prediction December 9 - December 10, 1996 Cambridge, Massachusetts USA Please complete this form (type or print) Name ___________________________________________________ Last First Middle Firm or Institution ______________________________________ Mailing Address (for receipt) _________________________ __________________________________________________________ __________________________________________________________ __________________________________________________________ Country Phone FAX __________________________________________________________ email address __________________________________________________________ Credit card # (if payment by credit card) Expiration Date (Lunch Menu - tick as appropriate): ___ Vegetarian ___ Non-Vegetarian Fee payment must be made by MONEY ORDER, PERSONAL CHECK, VISA or MASTERCARD. All amounts must in US dollar figures. Make fee payable to Prof. Trevor Hastie. Mail it, together with this completed Registration Form to: Marney Smyth, MIT Press E39-311 55 Hayward Street, Cambridge, MA 02142 USA ALL CREDIT CARD REGISTRATIONS MUST INCLUDE BOTH CARD NUMBER AND EXPIRATION DATE. DEADLINE: Registration before December 2, 1996. DO NOT SEND CASH. Registration fee includes Course Materials, coffee breaks, and lunch both days. If you have further questions, email to marney@ai.mit.edu