From jbower@bbb.caltech.edu Sun Aug 11 21:45:56 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 VAA08210 for ; Sun, 11 Aug 1996 21:45:50 -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 VAA01801 for ; Sun, 11 Aug 1996 21:45:48 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa18035; 11 Aug 96 21:40:32 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa18033; 11 Aug 96 21:20:39 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa03618; 11 Aug 96 21:20:10 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa18509; 11 Aug 96 15:16:05 EDT Received: from smaug-gw.caltech.edu by CS.CMU.EDU id aa26331; 11 Aug 96 15:15:35 EDT Received: from bbb.caltech.edu (smaug.bbb.caltech.edu) by gateway.bbb.caltech.edu (4.1/SMI-4.0) id AA04521; Sun, 11 Aug 96 12:26:22 PDT Received: from [131.215.137.84] (gatorbox4.bbb.caltech.edu) by bbb.caltech.edu (4.1/SMI-4.1) id AA04684; Sun, 11 Aug 96 12:25:57 PDT Message-Id: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Date: Sun, 11 Aug 1996 12:16:15 -0800 To: Connectionists@cs.cmu.edu From: "James M. Bower" Subject: J. Comput. Neurosci. Journal of Computational Neuroscience Volume 3, Number 2, July 1996 Paul Blush and Terrence Sejnowski, Inhibition Synchronizes Sparsely Connected Cortical Neurons Within and Between Columns in Realistic Network Models 91 Gary Strangman, Searching for Cell Assemblies: How Many Electrodes Do I Need? 111 Usula Fuentes, Raphael Ritz, Wulfram Gerstner, and J. Leo VanHemmen, Vertical Signal Flow and Oscillations in a Three-Layer Model of the Cortex 125 Joshua W. Fost and Gregory A. Clark, Modeling Hermissenda: I. Differential Contributions of IA and IC to Type-B Cell Plasticity 137 Joshua W. Fost and Gregory A. Clark, Modeling Hermissenda: II. Effects of Variations in Type-B Cell Excitability, Synaptic Strength, and Network Architecture 155 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Journal of Computational Neuroscience Volume 3, Number 3, September 1996 A.E. Sauer, R.B. Driesang, A. Buschges, and U. Bassler, Distributed Processing on the Basis of Parallel and Antagonistic Pathways Simulation of the Femur-Tibia Control System in the Stick Insect 179 R. J. Butera, Jr., J.W. Clark, Jr., and J.H. Byrne, Dissection and Reduction of a Modeled Bursting Neuron 199 Christiane Linster and Remi Gervais, Investigation of the Role of Interneurons and Their Modulation by Centrifugal Fibers in a Neural Model of the Olfactory Bulb 225 David J. Pinto, Joshua C. Brumberg, Daniel J. Simons, and G. Bard Ermentrout, A Quantitative Population Model of Whisker Barrels: Re-Examining the Wilson-Cowan Equations 247 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Information about the Journal of Computational Neuroscience is available from: http://www.bbb.caltech.edu/JCNS *************************************** James M. Bower Division of Biology Mail code: 216-76 Caltech Pasadena, CA 91125 (818) 395-6817 (818) 795-2088 FAX NCSA Mosaic addresses for: laboratory http://www.bbb.caltech.edu/bowerlab GENESIS: http://www.bbb.caltech.edu/GENESIS science education reform http://www.caltech.edu/~capsi From geoff@salk.edu Mon Aug 12 03:25:51 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 DAA11426 for ; Mon, 12 Aug 1996 03:25:37 -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 DAA03783 for ; Mon, 12 Aug 1996 03:25:35 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa18055; 11 Aug 96 21:48:16 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa18045; 11 Aug 96 21:24:39 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa03639; 11 Aug 96 21:24:08 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa20065; 11 Aug 96 20:26:29 EDT Received: from tesla-e0.salk.edu by CS.CMU.EDU id aa27398; 11 Aug 96 20:25:58 EDT Received: from gauss.salk.edu (gauss.salk.edu [198.202.70.10]) by tesla-e0.salk.edu (8.7.5/8.7.3) with ESMTP id RAA18697 for ; Sun, 11 Aug 1996 17:25:55 -0700 (PDT) From: geoff@salk.edu Received: (from geoff@localhost) by gauss.salk.edu (8.7.5/8.7.3) id RAA00613 for connectionists@cs.cmu.edu; Sun, 11 Aug 1996 17:25:53 -0700 (PDT) Date: Sun, 11 Aug 1996 17:25:53 -0700 (PDT) Message-Id: <199608120025.RAA00613@gauss.salk.edu> To: connectionists@cs.cmu.edu Subject: Postdoc position GEORGETOWN INSTITUTE FOR COGNITIVE AND COMPUTATIONAL SCIENCES Georgetown University, Washington DC Postdoctoral position in Theoretical / Computational Neuroscience Georgetown University has recently established an interdisciplinary research institute consisting of 16 full-time faculty. The major focus areas are neuroplasticity in development, higher auditory processing and language, and injury and aging. Experimental, computational and brain imaging approaches are all well represented. A postdoctoral position in theoretical / computational neuroscience is available from October 1996 in the lab of Dr Geoffrey J. Goodhill. The lab focuses on neural development and self-organization; particularly the development and plasticity of cortical mappings, areal specification of the cortex, and mechanisms of axon guidance (for more details see http://www.cnl.salk.edu/~geoff). The ideal candidate will have an initial training in a quantitative discipline plus knowledge and experience of neuroscience. Please send a CV, summary of relevant research experience and at least 2 letters of recommendation by post or email to: Dr Geoffrey J. Goodhill The Salk Institute 10010 North Torrey Pines Road La Jolla, CA 92037 Email: geoff@salk.edu From weissg@informatik.tu-muenchen.de Mon Aug 12 07:00:39 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 HAA13651 for ; Mon, 12 Aug 1996 07:00:05 -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 GAA04936 for ; Mon, 12 Aug 1996 06:59:59 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id QAA26054; Mon, 12 Aug 1996 16:03:36 +0800 Message-Id: <199608120803.QAA26054@cs.uwa.oz.au> From: Gerhard Weiss Sender: Gerhard Weiss To: DAI-List@ece.sc.edu, agentnews-owner@cs.umbc.edu, maamaw@cosmos.imag.fr, reinforce@cs.uwa.edu.au, genetic-programming@cs.stanford.edu Subject: CFP: ICMAS-96 Workshop on LIOME Date: Fri, 9 Aug 1996 11:20:57 +0200 (MET DST) Please distribute the following 2nd CFP through your mailing list. Thanks a lot, Gerhard Weiss. **************************************************************************** ICMAS'96 WORKSHOP - 2nd CALL FOR PAPERS Learning, Interaction and Organizations in Multiagent Environments December 10th, 1996 - http://www.lab7.kuis.kyoto-u.ac.jp/icmas96-liome/ - ABSTRACT: This workshop FOCUSES on the relationships between learning, interaction and organizations in multiagent environments. The need for studying these relationships is twofold. On the one hand, the efficiency and the success of a multiagent system largely depends on how efficient and successful the individual agents interact. On the other hand, even in simplified application domains it is almost impossible to correctly specify appropriate interactions between the individual agents a priori, and it is therefore desirable that the agents themselves are capable of learning to inter- act appropriately. The workshop is INTENDED to cover the whole range of open questions and problems concerning these relationships in all types of multiagent systems (e.g., robots interacting with dynamic environments, multiple robot systems, systems com- posed of interacting software agents, hybrid systems com- posed of both interacting humans and machines). A major GOAL of the workshop is to get a better understanding of how learning can improve the interactivity between agents em- bedded in multiagent environments. Among others, the following ISSUES are of interest: - concepts, methods and algorithms for learning in multiagent environments - design of multiagent systems - requirements for and principles of learning in multiagent environments - learning and communication - learning and negotiation - learning, cooperation and competition - collaborative and adversarial learning - learning and modeling of agents and users - learning and organizational design - learning and planning - acquiring internal representations - attention control in dynamic or multiagent environments We would like to stress that not only papers describing completed work, but also papers on novel ideas and of exploratory nature are welcome. ORGANIZERS: - Organizing Committee: . Toru Ishida Kyoto University, Japan . Yukinori Kakazu Hokkaido University, Japan . Gerhard Weiss TU Muenchen, Germany - Program Committee: . Minoru Asada Osaka University, Japan . Tatsuo Unemi Soka University, Japan . Yves Demazeau LEIBNIZ Laboratory, France . Ed Durfee University of Michigan, USA . Thomas Haynes University of Tulsa, USA . Hiroshi Ishiguro Kyoto University, Japan . Michael Huhns University of South Carolina, USA . Keiji Suzuki Hokkaido University, Japan . Victor Lesser University of Massachusetts, USA . Jeffrey Rosenschein The Hebrew University, Israel . Sandip Sen University of Tulsa, USA - Submission Handling: . Hiroshi Ishiguro Kyoto University, Japan CONTACT PERSON: Gerhard Weiss Institut fuer Informatik Technische Universitaet Muenchen D-80290 Muenchen, Germany EMAIL: weissg@informatik.tu-muenchen.de TEL: +49 89 289 22390, FAX: +49 89 289 28207 SUBMISSION: Four copies of each submitted extended abstract (written in English, at least 6 and at most 12 A4 pages with 12pt fonts including figures and tables) should be received no later than August 25th, 1996 by Hiroshi Ishiguro Department of Information Science Kyoto University Sakyo-ku, Kyoto 606-01, JAPAN Fax or email submissions will be ignored. The first page should include the full coordinates of at least one author. Extended abstracts are submitted to rigorous refereeing by the workshop program committee. In addition to the paper submission, authors need to submit an ascii abstract for each paper by email(ishiguro@kuis.kyoto-u.ac.jp). The abstract should use the following format: [Header] To: ishiguro@kuis.kyoto-u.ac.jp Subject: ICMAS96 Workshop on LIOME [Description] Title: Author: Address:
Email address: Key words: <3 or 4 key words> Abstract: PUBLICATION: Authors will be advised as to the acceptance status of their paper around October 8th, 1996 by email. Camera ready copies (hard copy only), are due no later than October 30th, 1996. These papers will be made available at the workshop. For the preparation of the camera ready papers, authors are strongly recommended to use LATEX with a style file included in the acceptance notification letter. Printed proceedings from Springer or other publishers is currently considered. IMPORTANT DATES: August 25th, 1996: Paper Submission October 8th, 1996: Notification of Acceptance October 30th, 1996: Camera Ready Paper December 10th, 1996: Workshop December 11-13th, 1996: ICMAS-96 Main Conference REMARKS: The workshop will be jointly held by ICMAS and GAL (Research Group on Adaptive and Reinforcement Learning/Research Project on System Theory of Function Emergence). The GAL project started in April 1995 under the Grant-in-Aid for Scientific Research on the Priority Area from the Ministry of Education, Science, Sports and Culture of Japan. So far, 31 researchers in various Japanese universities have joined in this project. **************************************************************************** From moeller@informatik.uni-bonn.de Mon Aug 12 07:46:17 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 HAA15657 for ; Mon, 12 Aug 1996 07:46:11 -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 HAA05305 for ; Mon, 12 Aug 1996 07:46:08 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id QAA26081; Mon, 12 Aug 1996 16:05:53 +0800 Message-Id: <199608120805.QAA26081@cs.uwa.oz.au> From: Knut Moeller To: colt@cs.uiuc.edu, connectionists@cs.cmu.edu, mafm@cs.uwa.oz.au, neuron-request@CATTELL.PSYCH.UPENN.EDU, alife@cognet.ucla.edu, cogpsy@neuro.psy.soton.ac.uk, hybrid-list@cs.ua.edu, annrules@fit.qut.edu.au, ml@ics.uci.edu, Reinforce@cs.uwa.edu.au, nonlin-l@list.nih.gov, comp-finance@teleport.com, ai-stats@watstat.uwaterloo.ca, genetic-programming@cs.stanford.edu Subject: CfParticipation HeKoNN86: Deadline extended [connectionists] Date: Fri, 9 Aug 1996 17:39:20 +0200 (MET DST) There are a limited number of spaces left. Therefore the application deadline was extended. ATTENTION: EXTENDED DEADLINE UNTIL Aug. 31, 1996 CALL FOR PARTICIPATION ================================================================= = = = H e K o N N 9 6 = = = Autumn School in C o n n e c t i o n i s m and N e u r a l N e t w o r k s October 2-6, 1996 Muenster, Germany Conference Language: German ---------------------------------------------------------------- A comprehensive description of the Autumn School together with abstracts of the courses can be found at the following address: WWW: http://set.gmd.de/AS/fg1.1.2/hekonn = = = O V E R V I E W = = = Artificial neural networks (ANN's) have been discussed in many diverse areas, ranging from models of cortical learning to the control of industrial processes. The goal of the Autumn School in Connectionionism and Neural Networks is to give a comprehensive introduction to connectionism and artificial neural networks (ANN's) and to provide an overview of the current state of the art. Courses will be offered in five thematic tracks. (The conference language is German.) The FOUNDATION track will introduce basic concepts (A. Zell, Univ. Stuttgart) and theoretical issues. Hardwareaspects (U. Rueckert, Univ. Paderborn), Lifelong Learning (G. Paass, GMD St.Augustin), algorithmic complexity of learning procedures (M. Schmitt, TU Graz) and convergence properties of ANN's (K. Hornik, TU Vienna) are presented in further lectures. This year, a special track was devoted to BRAIN RESEARCH. Courses are offered about the simulation of biological neurons (R. Rojas, Univ. Halle), theoretical neurobiology (H. Gluender, LMU Munich), learning and memory (A. Bibbig, Univ. Ulm) and dynamical aspects of cortical information processing (H. Dinse, Univ. Bochum). In the track on SYMBOLIC CONNECTIONISM and COGNITIVE MODELLING, consists of courses on: procedures for extracting rules from ANN's (J. Diederich, QUT Brisbane). representation and cognitive models (G. Peschl, Univ. Vienna), autonomous agents and ANN's (R. Pfeiffer, ETH Zuerich) and hybrid systems (A. Ultsch, Univ. Marburg). APPLICATIONS of ANN's are covered by courses on image processing (H.Bischof, TU Vienna), evolution strategies and ANN's (J. Born, FU Berlin), ANN's and fuzzy logic (R. Kruse, Univ. Braunschweig), and on medical applications (T. Waschulzik, Univ. Bremen). In addition, there will be courses on PROGRAMMING and SIMULATORS. Participants will have the opportunity to work with the SNNS simulator (G. Mamier, A. Zell, Univ. Stuttgart, Univ. Tuebingen) and the VieNet2/ECANSE simulation tool (G. Linhart, Univ. Vienna). ========================================================================= Participants are encouraged to present posters of their own work related to any of the above mentioned subjects. ========================================================================= From johkim@vivaldi.kaist.ac.kr Mon Aug 12 08:12:01 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 IAA16094 for ; Mon, 12 Aug 1996 08:11:47 -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 IAA05577 for ; Mon, 12 Aug 1996 08:11:43 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id QAA26100; Mon, 12 Aug 1996 16:07:15 +0800 Message-Id: <199608120807.QAA26100@cs.uwa.oz.au> From: Jong-Hwan Kim To: reinforce@cs.uwa.edu.au Subject: MIROSOT NEWSLETTER Date: Sat, 10 Aug 1996 13:08:55 +1000 (KDT) ==================================================================== MICRO-ROBOT WORLD CUP SOCCER TOURNAMENT MIROSOT NEWSLETTER W E L C O M E T O M I R O S O T ' 9 6 No. 3, August 10, 1996 -------------------------------------------------------------------- November 9-12, 1996, KAIST, Taejon, Korea Organized by KAIST Sponsored by IEEE Robotics and Automation Society Supported by LG Semicon Co., Ltd. ==================================================================== Publisher : Jong-Hwan Kim Editor : Bok-Kyung Kim MIROSOT'96 Secretariat Dept. of Electrical Engineering, KAIST 373-1 Kusong-dong, Yusong-gu, Taejon 305-701, Korea Tel: +82-42-869-8048 Fax: +82-42-869-8010 WWW: http://www.mirosot.org Email: mirosot@vivaldi.kaist.ac.kr <<<<<<<<<<<<<<<<<<<<<<<< C O N T E N T S >>>>>>>>>>>>>>>>>>>>>>>>>> 1. International Summer Camp 2. Updated Rules 3. Discussions on Robots 4. ICRA'97 Special Session 5. Special Issue RAS Journal 6. TROUW, Newspaper, in the Netherlands 7. New Committee Members <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 1. International Summer Camp (Workshop proceedings available) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ International Summer Camp as a pre-meeting for the November competition was held at KAIST during July 29 - August 2, 1996. More than fifty people attended the summer camp including the fifteen participants from ten overseas countries - Australia, Brazil, Bulgaria, Canada, France Italy, Japan, Spain, Netherlands and USA (three teams). The summer camp schedule was as follows: - July 29 * Opening Ceremony & Orientation & Team Introduction * Mini-workshop I: 10 teams presented their robots and strategies. - July 30 * Mini-workshop II: 13 teams presented their robots and strategies. * LG Semicon Co., Ltd. Tour. - July 31 * Rule Discussion: The participants discussed and updated the rules more clearly. * Collaboration: The international Joint Teams had the cooperation time to participate in MIROSOT'96 in November with the partner team. Robot systems (hardware) were provided by KAIST team and strategies for soccer(software) was provided by the foreign team. * Lab. Tours: The participants visited some laboratories in the department of Electrical Engineering, KAIST. * Real Soccer Game: The participants played and enjoyed the soccer game in playground. There were two teams, international team and KAIST IC (Intelligent Control) lab (Prof. J.-H. Kim's lab) team. The international team won over the IC lab team by 3:1 (Peter Stone: two goals, M.-T. Han: one goal, and H.-S. Shim: one goal). - August 1 * Micro-robot Soccer Demonstration: The participants looked around the auditorium where MIROSOT'96 will be held and collected the necessary information on MIROSOT. The MIRO team showed the demonstration of the robots. * Discussions on Robots: The participants discussed on robot specifications such as carrier frequencies for communication and also on robot uniform problems. - August 2 * One-day Tour: KAIST - Puyo Nak'waam - Puyo Museum - Donghak Temple - KAIST * Farewell Dinner MIROSOT'96 published the proceedings of the mini-workshop of the International Summer Camp. If you are interested, please contact the MIROSOT Secretariat (e-mail: mirosot@vivaldi.kaist.ac.kr). ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2. Updated Rules (Summarized by Peter Stone, CMU, USA) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Rule discussion was held at the International Summer Camp on July 31, 1996. All participants should abide by an unwritten code analogous to "sportsmanship". This code is named as "sportsrobotship" by Prof. J.-H. Kim. A general comment was made that the field is too small for the number of robots being used. However the change will not be made for this coming competition. It was agreed that the eventual aim of MIROSOT should be to move towards fully autonomous robots with no external vision camera and no external processing. Some participants also argued for prohibiting any robot control from the remote host. Although these eventual aims should be publicized as the future goals of MIROSOT, the rules will not be changed at this time. Each team can decide to use 3, 4, or 5 robots. The decision of each team is independent, so a game might be played with 3 robots on one team and 5 robots on the other. For the updated rules of MIROSOT, please refer to www.mirosot.org. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 3. Discussions on Robots (Summarized by Peter Stone, CMU, USA) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The participants discussed the IR frequency problem and the team uniform problems on August 1, 1996. It is recommended that each team be able to use 2 different frequencies. Frequencies that are used should be published on the MIROLIST and new teams should choose previously unreserved frequencies. A potential interference problem was also pointed out. Brushed DC motors tend to cause RF interference. So brushless motors were recommended, and teams should attempt to shield their motors also that they don't cause RF interference. They had a long discussion about the colors of the robot tops. They decided upon a variation to Oller's (from Spain) code that leaves room for IR sensors. There will be 2 team colors (pure blue and yellow) and at the beginning of the game, each team will be assigned one of the two colors. Each robot in the team must have a solid 3.5 cm x 3.5 cm patch of its team color visible on top. It must avoid wearing any of the other team color. They decided that robots should have a light color on their sides to enable IR sensor obstacle detection. Exceptions can be made for sensors, wheels, and ball-handling mechanisms. It was noted that the lighting in the auditorium was very "warm", meaning that it was yellowish rather than pure white light. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 4. ICRA'97 Special Session ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Considering the number of participating teams in the November competition, at least two special sessions should be organized. Each session will consist of four papers so eight papers are needed. If you are interested in this special session, please send the manuscript by August 31, 1996 to Prof. J.-H. Kim as the session organization due date is September 15th. Regarding ICRA special session, please refer to the following web site: http://www.sandia.gov/cc_at/ieee/1ieee.html ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 5. Special Issue RAS Journal ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The Journal on Robotics and Autonomous Systems will have a special issue on MIROSOT. As soon as the November tournament is over, some papers of the winning teams will be collected and published in RAS by the special issue. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 6. TROUW, Newspaper, in the Netherlands ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ TROUW, newspaper in the Netherlands, published an article on the MIROSOT on June 12, 1996. The contents occupied the whole page of No. 15. There are interviews of Prof. Nicoud (EPFL) and Prof. Groen (Univ. of Amsterdam) on MIROSOT with Bas den Hond, Science Editor of the TROUW. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 7. New Committee Members ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - Advisory Committee Members * Prof. J.-D. Nicoud, EPFL, Swizterland * Prof. A. C. Sanderson, RPI, U.S.A. * D.-R. Kim, Korean National Assembly * B.-R. Lee, KAERI - Organizing Committee Members * J. Wang, Univ. of California, Riverside, U.S.A. * R. C. Luo, North Carolina State Univ., U.S.A. * R. F. T. Filho, CTI, Brazil * K.-C. Koh, LG Industrial Systems Co., Ltd. ===================================================================== From jhf@playfair.Stanford.EDU Tue Aug 13 05:10:43 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 FAA02777 for ; Tue, 13 Aug 1996 05:10:30 -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 FAA19000 for ; Tue, 13 Aug 1996 05:10:28 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa20809; 13 Aug 96 5:03:07 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa20805; 13 Aug 96 4:44:48 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa06291; 13 Aug 96 4:34:50 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa03835; 12 Aug 96 16:01:40 EDT Received: from Playfair.Stanford.EDU by RI.CMU.EDU id aa21567; 12 Aug 96 16:00:59 EDT Received: from tukey.Stanford.EDU (tukey.Stanford.EDU [36.137.0.70]) by playfair.Stanford.EDU (8.7.1/8.6.10) with ESMTP id NAA18854; Mon, 12 Aug 1996 13:00:46 -0700 From: "Jerome H. Friedman" Received: (jhf@localhost) by tukey.Stanford.EDU (8.7.1/8.6.10) id NAA01577; Mon, 12 Aug 1996 13:00:26 -0700 Date: Mon, 12 Aug 1996 13:00:26 -0700 Message-Id: <199608122000.NAA01577@tukey.Stanford.EDU> To: connectionists@cs.cmu.edu Subject: Technical Report Available. Cc: jhf@playfair.Stanford.EDU *** Technical Report Available *** LOCAL LEARNING BASED ON RECURSIVE COVERING Jerome H. Friedman Stanford University (jhf@playfair.stanford.edu) ABSTRACT Local learning methods approximate a global relationship between an output (response) variable and a set of input (predictor) variables by establishing a set of "local" regions that collectively cover the input space, and modeling a different (usually simple) input-output relationship in each one. Predictions are made by using the model associated with the particular region in which the prediction point is most centered. Two widely applied local learning procedures are K - nearest neighbor methods, and decision tree induction algorithms (CART, C4.5). The former induce a large number of highly overlapping regions based only on the distribution of training input values. By contrast, the latter (recursively) partition the input space into a relatively small number of highly customized (disjoint) regions using the training output values as well. Recursive covering unifies these two approaches in an attempt to combine the strengths of both. A large number of highly customized overlapping regions are produced based on both the training input and output values. Moreover, the data structure representing this cover permits rapid search for the prediction region given a set of (future) input values. Available by ftp from: "ftp://playfair.stanford.edu/pub/friedman/dart.ps.Z" Note: this postscript does not view properly on some ghostviews. It seems to print OK on nearly all postscript printers. From listerrj@helios.aston.ac.uk Tue Aug 13 15:56:44 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 PAA16602 for ; Tue, 13 Aug 1996 15:56:30 -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 PAA26245 for ; Tue, 13 Aug 1996 15:08:36 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id BAA09602; Wed, 14 Aug 1996 01:25:33 +0800 Message-Id: <199608131725.BAA09602@cs.uwa.oz.au> From: Richard Lister To: Connectionists@cs.cmu.edu, reinforce@cs.uwa.edu.au, gann-list@cs.iastate.edu, neuron-request@CATTELL.psych.upenn.edu, cogpsy@neuro.psy.soton.ac.uk, hybrid-list@cs.ua.edu, colt@cs.uiuc.edu, cphc-jobs@ukc.ac.uk Subject: Lectureships available [connectionists] Date: Tue, 13 Aug 1996 17:00:31 +0100 ---------------------------------------------------------------------- LECTURESHIPS ------------ Aston University, Birmingham, UK * Full details at http://www.ncrg.aston.ac.uk/ * We are seeking highly motivated academic staff to contribute to research in the general areas of neural computing, pattern recognition, time series analysis, image processing, machine vision or a closely related field. Candidates are expected to have excellent academic qualifications, a strong mathematical background and a proven record of research. Two posts are available. The successful candidates will also be expected to make innovative contributions to graduate-level and undergraduate teaching programmes, and ideally also contribute to industrially funded research programmes and industrial courses. They will join the Neural Computing Research Group which currently comprises the following members: Professors: Christopher Bishop David Lowe Visiting Professors: Geoffrey Hinton Edward Feigenbaum David Bounds Lecturers: Richard Rohwer Ian Nabney David Saad Chris Williams Postdoctoral Research Fellows: David Barber Paul Goldberg Neep Hazarika Alan McLachlan Mike Tipping Huaiyu Zhu (5 further posts currently being advertised) Personal Assistant: Hanni Sondermann System Administrator: Richard Lister Research Programmer: Andrew Weaver 20 Research Students Conditions of Service --------------------- The appointment will be for an initial period of three years, with the possibility of subsequent renewal or transfer to a continuing appointment. Initial salary will be within the lecturer A and B range 15,154 to 26,430, and exceptionally up to 29,532 (UK pounds; these salary scales are currently under review). How to Apply ------------ If you wish to be considered for one of these positions, please send a full CV and publications list, together with the names and addresses of 4 referees, to: Hanni Sondermann Neural Computing Research Group Aston University Birmingham B4 7ET, U.K. Tel: +44/0 121 333 4631 Fax: +44/0 121 333 4586 e-mail: H.E.Sondermann@aston.ac.uk Applications may be submitted as postscript files using e-mail, or as hard copy by post. Closing date: 30 August 1996. ---------------------------------------------------------------------- From rsun@cs.ua.edu Tue Aug 13 17:51:51 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 RAA19787 for ; Tue, 13 Aug 1996 17:51:29 -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 RAA29016 for ; Tue, 13 Aug 1996 17:51:26 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa21518; 13 Aug 96 16:38:00 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa21516; 13 Aug 96 16:24:54 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa06765; 13 Aug 96 13:09:38 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa15054; 13 Aug 96 11:58:26 EDT Received: from [130.160.44.2] by EDRC.CMU.EDU id aa09458; 13 Aug 96 11:58:00 EDT Received: by athos.cs.ua.edu (AIX 3.2/UCB 5.64/4.03) id AA18781; Tue, 13 Aug 1996 10:58:11 -0500 Date: Tue, 13 Aug 1996 10:58:11 -0500 From: Ron Sun Message-Id: <9608131558.AA18781@athos.cs.ua.edu> To: connectionists@cs.cmu.edu Subject: IEEE TNN special issue on hybrid systems Call For Papers special issue of IEEE Transaction on Neural Networks on ``Neural Networks and Hybrid Intelligent Models: Foundations, Theory, and Applications'' Guest Editors: C. Lee Giles, Ron Sun, Jacek M. Zurada Hybrid systems, the use of other intelligence paradigms with neural networks, are becoming more common and useful. In fact it can be argued that the success of neural networks has been from its ready incorporation of other information processing approaches, including pattern recognition, statistical inference, as well as symbolic processing. Some systems (especially those incorporating symbolic processing) have been known to some segments of the scientific community as high-level connectionist models. Other systems have been referred to as knowledge insertion and extraction. However, for the many applications, there exists little (1) theoretical foundation and (2) engineering methodology for effectively developing hybrid approaches. These two aspects are the topic of this special issue. Manuscripts are solicited in neural networks and hybrid models in the following areas - Theorectical foundations of hybrid models. Mathematical analysis, theories, critiques, case studies. - Models incorporating other paradigms such as AI symbolic processing, machine learning, fuzzy systems, genetic algorithms, and other intelligent paradigms within neural networks. Techniques, methodologies, and analyses. - Methodology of engineering design of hybrid systems. - Innovative and non-trivial applications of hybrid models (for example, in natural language processing, signal and image processing, pattern recognition, and cognitive modeling). Papers will undergo the standard review procedure of the IEEE Transactions on Neural Netwoks. The special issue will appear around November 1997. Prospective authors should submit six (6) copies of the completed manuscript, on or before February 28, 1997, to one of the following three guest editors: Dr. C. Lee Giles NEC Research Institute 4 Independence Way Princeton, NJ 08540, USA Phone: 609-951-2642 Fax 609-951-2482 Email: giles@research.nj.nec.com Web: http://www.neci.nj.nec.com/homepages/giles.html Prof. Ron Sun Department of Computer Science The University of Alabama Tuscaloosa, AL 35487 Phone: (205) 348-6363 Fax: (205) 348-0219 Email: rsun@cs.ua.edu Web: http://cs.ua.edu/faculty/sun/sun.html Prof. Jacek M. Zurada Electrical Engineering Department University of Louisville Louisville, KY 40292, USA Phone: (502) 852-6314 Fax: (502) 852-6807 Email: j.zurada@ieee.org Web: under construction From fil@cs.ucsd.edu Wed Aug 14 13:27:48 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 NAA17455 for ; Wed, 14 Aug 1996 13:27:42 -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 NAA10181 for ; Wed, 14 Aug 1996 13:27:35 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id XAA10402; Wed, 14 Aug 1996 23:47:27 +0800 Message-Id: <199608141547.XAA10402@cs.uwa.oz.au> From: fil@cs.ucsd.edu (Filippo Menczer) To: reinforce@cs.uwa.edu.au Subject: Latent Energy Environments 2.0 Software available Date: Tue, 13 Aug 1996 13:47:35 -0700 --============_-1372153241==_============ Content-Type: text/plain; charset="us-ascii" --============_-1372153241==_============ Content-Type: text/plain; name="announce"; charset="us-ascii" Content-Disposition: attachment; filename="announce" ========================== Software announcement LEE release 2.0 Latent Energy Environments ========================== Release 2.0 of the LEE artificial life simulator is now available via FTP/WWW. Changes from previous versions include, among others, an option for reinforcement learning, a new motor type, a new and improved user interface, and a fat binary application for the Macintosh. You may download the software (Unix sources and/or Mac source and fat application, documentation, and a technical report) as follows: World Wide Web: http://www.cs.ucsd.edu/users/fil/lee/lee.html Anonymous FTP: ftp://cs.ucsd.edu/pub/LEE Authors: Richard Belew and Filippo Menczer. LEE is (c) 1993-1996 University of California, San Diego. You may freely copy/distribute the software, except for commercial purposes, and as long and the notices in the source headers are preserved. Filename Format Content ----------------------------------------------------------------- README ASCII general info lee.doc ASCII documentation pinep.ps.Z compressed PostScript paper about LEE model lee2.0.tar.Z compressed tar file LEE 2.0 Unix source lee2.0.sit.hqx binhexed stuffit archive LEE 2.0 for the Mac ----------------------------------------------------------------- Please see README file for a general introduction, and lee.doc for specific information on how to compile and/or run the program. For a complete list of related papers please see Filippo Menczer's homepage (URL below). =============================================== Filippo Menczer Dept. of Computer Science and Engineering, 0114 University of California, San Diego La Jolla, CA 92093-0114 USA Fax: +1 619 534-7029 Email: fil@cs.ucsd.edu Homepage: http://www.cs.ucsd.edu/users/fil/ =============================================== --============_-1372153241==_============ Content-Type: text/plain; charset="us-ascii" ========================================================= Filippo Menczer fil@cs.ucsd.edu http://www.cs.ucsd.edu/users/fil/ Lab: (619) 534-8187 CSE Dept., 0114 Fax: (619) 534-7029 U. C. San Diego Home: (619) 587-7005 La Jolla, CA 92093-0114, U.S.A. ========================================================= --============_-1372153241==_============-- From dwang@cis.ohio-state.edu Wed Aug 14 18:34:45 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 SAA22849 for ; Wed, 14 Aug 1996 18:34:39 -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 SAA14523 for ; Wed, 14 Aug 1996 18:34:34 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa23119; 14 Aug 96 18:25:48 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa23117; 14 Aug 96 18:01:01 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa08335; 14 Aug 96 15:35:01 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa04048; 14 Aug 96 15:00:02 EDT Received: from mail.cis.ohio-state.edu by EDRC.CMU.EDU id aa15401; 14 Aug 96 14:59:16 EDT Received: from shirt.cis.ohio-state.edu (shirt.cis.ohio-state.edu [164.107.47.4]) by mail.cis.ohio-state.edu (8.6.7/8.6.4) with ESMTP id OAA19806; Wed, 14 Aug 1996 14:59:00 -0400 From: DeLiang Wang Received: (dwang@localhost) by shirt.cis.ohio-state.edu (8.6.7/8.6.4) id OAA20887; Wed, 14 Aug 1996 14:59:00 -0400 Date: Wed, 14 Aug 1996 14:59:00 -0400 Message-Id: <199608141859.OAA20887@shirt.cis.ohio-state.edu> To: Connectionists@cs.cmu.edu Subject: Neurocomputing Best Paper Award Cc: Y.CAMPFENS@elsevier.nl, ds@cs.miami.edu Presenting the Neurocomputing best paper award, Vols. 7-9 (1995) As a form to express our thanks to the support by all contributors to the journal for a concluded volume our Editorial Board elects one representative contribution and grants the author(s) of an outstanding contribution the "Neurocomputing Best Paper Award". Originality, clarity of result presentation, depth, and novelty are some of the properties we are looking for. >From 1995 (Vol. 7-9) on, the award has been granted on the basis of all contributions of one year. The winner(s) obtain(s) a corresponding certificate and a publication of free-choice from our publisher, Elsevier Science B.V. M. Cannon and J.-J.E. Slotine were granted the Neurocomputing Best Paper Award for their contribution Space-frequency localized basis function networks for nonlinear systems estimation and control in Vol. 9(3) (1995), pp. 293-342. Again thanks for your support. V. David Sanchez A. Editor-in-Chief From otavioc@cogs.susx.ac.uk Thu Aug 15 19:23:58 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 TAA18446 for ; Thu, 15 Aug 1996 19:23:53 -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 TAA02589 for ; Thu, 15 Aug 1996 19:23:52 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab24754; 15 Aug 96 19:06:14 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab24752; 15 Aug 96 18:47:09 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa09810; 15 Aug 96 16:38:21 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa16429; 15 Aug 96 14:27:14 EDT Received: from rsuna-gw.susx.ac.uk by RI.CMU.EDU id aa06493; 15 Aug 96 14:26:32 EDT Received: by rsuna.crn.cogs.susx.ac.uk (Smail3.1.29.1 #3) id m0ur76p-00003BC; Thu, 15 Aug 96 19:25 BST Message-Id: Subject: Thesis available To: connectionists@cs.cmu.edu Date: Thu, 15 Aug 1996 19:25:30 +0100 (BST) From: Otavio Augusto Salgado Carpinteiro Cc: Otavio Carpinteiro MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Content-Length: 3912 FTP-host: ftp.cogs.susx.ac.uk FTP-filename: /pub/reports/csrp/csrp426.ps.Z The following thesis is available via anonymous ftp. A CONNECTIONIST APPROACH IN MUSIC PERCEPTION Otavio A. S. Carpinteiro email: otavioc@cogs.susx.ac.uk Cognitive Science Research Paper CSRP-426 School of Cognitive & Computing Sciences University of Sussex, Brighton, UK FTP instructions: unix> ftp ftp.cogs.susx.ac.uk [ or ftp 192.33.16.70] login: anonymous password: ftp> cd pub/reports/csrp ftp> binary ftp> get csrp426.ps.Z ftp> bye 117 pages. 422107 bytes compressed, 1195561 bytes uncompressed Paper copies can be ordered from: Celia McInnes (celiam@cogs.susx.ac.uk) School of Cognitive & Computing Sciences University of Sussex Falmer, Brighton, UK. ------------------------------------------------------------------------ ABSTRACT: Little research has been carried out in order to understand the mechanisms underlying the perception of polyphonic music. Perception of polyphonic music involves thematic recognition, that is, recognition of instances of theme through polyphonic voices, whether they appear unaccompanied, transposed, altered or not. There are many questions still open to debate concerning thematic recognition in the polyphonic domain. One of them, in particular, is the question of whether or not cognitive mechanisms of segmentation and thematic reinforcement facilitate thematic recognition in polyphonic music. This dissertation proposes a connectionist model to investigate the role of segmentation and thematic reinforcement in thematic recognition in polyphonic music. The model comprises two stages. The first stage consists of a supervised artificial neural model to segment musical pieces in accordance with three cases of rhythmic segmentation. The supervised model is trained and tested on sets of contrived patterns, and successfully applied to six musical pieces from J. S. Bach. The second stage consists of an original unsupervised artificial neural model to perform thematic recognition. The unsupervised model is trained and assessed on a four-part fugue from J. S. Bach. The research carried out in this dissertation contributes into two distinct fields. Firstly, it contributes to the field of artificial neural networks. The original unsupervised model encodes and manipulates context information effectively, and that enables it to perform sequence classification and discrimination efficiently. It has application in cognitive domains which demand classifying either a set of sequences of vectors in time or sub-sequences within a unique and large sequence of vectors in time. Secondly, the research contributes to the field of music perception. The results obtained by the connectionist model suggest, along with other important conclusions, that thematic recognition in polyphony is not facilitated by segmentation, but otherwise, facilitated by thematic reinforcement. -- Otavio. +===========================================================================+ | | | | Otavio Augusto Salgado Carpinteiro | Phone: +44 (0) 1273 606755 | | Postgraduate Pigeonholes | ext. 2385 | | School of Cognitive & Computing Sciences | | | University of Sussex | Fax: +44 (0) 1273 671320 | | FALMER - East Sussex | | | BN1 9QH | E-mail: | | England | otavioc@cogs.sussex.ac.uk | | | | +===========================================================================+ From giles@research.nj.nec.com Fri Aug 16 00:15:22 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 AAA22094 for ; Fri, 16 Aug 1996 00:15:18 -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 AAA05143 for ; Fri, 16 Aug 1996 00:15:16 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa24754; 15 Aug 96 19:05:04 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa24752; 15 Aug 96 18:47:07 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa09651; 15 Aug 96 12:32:56 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id ae13488; 15 Aug 96 10:02:17 EDT Received: by CS.CMU.EDU id bh26101; 15 Aug 96 10:01:58 EDT Received: from zingo.nj.nec.com by CS.CMU.EDU id aa25978; 15 Aug 96 9:50:09 EDT Received: from alta (alta [138.15.158.81]) by zingo.nj.nec.com (8.7.4/8.7.3) with SMTP id JAA10895 for ; Thu, 15 Aug 1996 09:50:05 -0400 (EDT) Received: by alta (5.52/cliff's joyful mailer #2) id AA03234(alta); Thu, 15 Aug 96 09:49:00 EDT Date: Thu, 15 Aug 96 09:49:00 EDT From: Lee Giles Message-Id: <9608151349.AA03234@alta> To: connectionists@cs.cmu.edu Subject: TR on recurrent networks and long-term dependenices The following Technical Report is available via the University of Maryland Department of Computer Science and the NEC Research Institute archives: ____________________________________________________________________ HOW EMBEDDED MEMORY IN RECURRENT NEURAL NETWORK ARCHITECTURES HELPS LEARNING LONG-TERM DEPENDENCIES Technical Report CS-TR-3626 and UMIACS-TR-96-28, Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20742 Tsungnan Lin{1,2}, Bill G. Horne{1}, C. Lee Giles{1,3} {1}NEC Research Institute, 4 Independence Way, Princeton, NJ 08540 {2}Department of Electrical Engineering, Princeton University, Princeton, NJ 08540 {3}UMIACS, University of Maryland, College Park, MD 20742 ABSTRACT Learning long-term temporal dependencies with recurrent neural networks can be a difficult problem. It has recently been shown that a class of recurrent neural networks called NARX networks perform much better than conventional recurrent neural networks for learning certain simple long-term dependency problems. The intuitive explanation for this behavior is that the output memories of a NARX network can be manifested as jump-ahead connections in the time-unfolded network. These jump-ahead connections can propagate gradient information more efficiently, thus reducing the sensitivity of the network to long-term dependencies. This work gives empirical justification to our hypothesis that similar improvements in learning long-term dependencies can be achieved with other classes of recurrent neural network architectures simply by increasing the order of the embedded memory. In particular we explore the impact of learning simple long-term dependency problems on three classes of recurrent neural networks architectures: globally recurrent networks, locally recurrent networks, and NARX (output feedback) networks. Comparing the performance of these architectures with different orders of embedded memory on two simple long-term dependences problems shows that all of these classes of networks architectures demonstrate significant improvement on learning long-term dependencies when the orders of embedded memory are increased. These results can be important to a user comfortable to a specific recurrent neural network architecture because simply increasing the embedding memory order will make the architecture more robust to the problem of long-term dependency learning. ------------------------------------------------------------------- KEYWORDS: discrete-time, memory, long-term dependencies, recurrent neural networks, training, gradient-descent PAGES: 15 FIGURES: 7 TABLES: 2 ------------------------------------------------------------------- http://www.neci.nj.nec.com/homepages/giles.html http://www.cs.umd.edu/TRs/TR-no-abs.html or ftp://ftp.nj.nec.com/pub/giles/papers/UMD-CS-TR-3626.recurrent.arch.long.term.ps.Z ------------------------------------------------------------------------------------ -- C. Lee Giles / Computer Sciences / NEC Research Institute / 4 Independence Way / Princeton, NJ 08540, USA / 609-951-2642 / Fax 2482 www.neci.nj.nec.com/homepages/giles.html == From pazzani@super-pan.ICS.UCI.EDU Fri Aug 16 07:44:51 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 HAA27130 for ; Fri, 16 Aug 1996 07:44:30 -0500 Received: from paris.ics.uci.edu (paris.ics.uci.edu [128.195.1.50]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id HAA07704; Fri, 16 Aug 1996 07:44:22 -0500 Received: from super-pan.ics.uci.edu by paris.ics.uci.edu id aa26199; 15 Aug 96 22:17 PDT To: ML-LIST:; Subject: Machine Learning List: Vol. 8, No. 14 Reply-to: ml@ics.uci.edu Date: Thu, 15 Aug 1996 22:08:05 -0700 From: Michael Pazzani Message-ID: <9608152217.aa26199@paris.ics.uci.edu> Machine Learning List: Vol. 8, No. 14 Thursday, Auguts 15, 1996 Contents: postdoctoral positions at ISLE postdoctoral positions in learning and intelligent agents Videotapes of Genetic Programming 96 Conference Available MLJ Table of Contents Recent JAIR ML-related articles Job opportunity at IRST Programmer/R.A. Position at Rutgers Univ. in Computational Neuroscience Intensive Tutorial: Learning Methods for Prediction, Classification Special Issue CFP - final call spline/ai paper ancts REGISTRATION FOR NIPS*96 Announcing a New Book... Data-Mining jobs at IBM San Jose FIRST Call for Papers: NNSP*97 CfParticipation HeKoNN86: Deadline extended CfP EPIA'97 (Preliminary) 3rd Brazilian Symposium on Neural Networks Workshop on IMMUNITY-BASED SYSTEMS The Machine Learning List is moderated. Contributions should be relevant to the scientific study of machine learning. Mail contributions to ml@ics.uci.edu. Mail requests to be added or deleted to ml-request@ics.uci.edu. Back issues may be obtained from http://www.ics.uci.edu/AI/ML/Machine-Learning.html ---------------------------------------------------------------------- Date: Thu, 25 Jul 1996 21:07:18 -0700 From: Pat Langley Subject: postdoctoral positions at ISLE The Institute for the Study of Learning and Expertise (ISLE) has openings for postdoctoral researchers in three projects: - use of machine learning in analysis of aerial images (e.g., inducing the conditions for applying vision operators); - use of machine learning in large-scale crisis planning (e.g., inducing conditions for applying plan adaptation operators); - use of machine learning in robotic localization/navigation (e.g., acquiring place knowledge in terms of evidence grids). All three efforts focus on adapting existing learning algorithms to complex task environments. Thus, the ideal candidates will have experience with a variety of induction methods and have detailed knowledge of computer vision, planning, or robotics. In addition, the vision and planning positions (available this fall) will involve the development of adaptive interfaces that personalize themselves to individual users, so experience in this area would also be an asset. The robotics project is contingent on renewal funding, with a starting date in late 1996 or early 1997. ISLE is a nonprofit corporation that specializes in basic and applied research on machine learning. The Institute is located in Palo Alto, adjacent to Stanford University, and all three projects will involve interaction with university researchers. For more information about the positions or ISLE, contact Pat Langley (langley@cs.stanford.edu). ------------------------------ Date: Mon, 29 Jul 1996 14:01:01 -0700 From: Pat Langley Subject: postdoctoral positions in learning and intelligent agents Dear Colleagues, I have accepted a position at the new Daimler-Benz Research and Technology Center in Palo Alto, California, starting this September. I will be heading a laboratory that carries out basic and applied research on learning and intelligent agents, with a focus on mobile systems. The laboratory's projects will emphasize: - adaptive interfaces and personalization - data fusion and decision support - distributed agents and cooperation We have two postdoctoral positions to fill in these areas this fall, so I hope you will pass on this note to near or recent PhD's who would be appropriate for the positions. Candidates should contact me by electronic mail at langley@cs.stanford.edu. My new address will be: Pat Langley Daimler-Benz Research and Technology Center 1510 Page Mill Road Palo Alto, CA 94304 Although I will be moving to Daimler-Benz, I intend to keep my close ties with colleagues at Stanford University, and members of the lab will participate in joint projects that involve Stanford faculty and students. Also, I will continue to spend part of my time as director of ISLE, a nonprofit corporation that specializes in research on machine learning. ------------------------------ Date: Mon, 5 Aug 96 13:18:42 -0700 (PDT) From: Creon Levit Subject: Videotapes of Genetic Programming 96 Conference Available VIDEO TAPES AND AUDIO TAPES OF THE GENETIC PROGRAMMING 96 CONFERENCE NOW AVAILABLE FOR ORDERING Sound Photosynthesis is pleased to announce that video and audio cassette recordings of (almost) the entire GP96 conference, held earlier this week at Stanford University are available for ordering. (NTSC VHS) Videotapes are $35 each, plus shipping ($3 domestic, and approx. $10 international per tape depending on country), plus California sales tax if applicable. Most videotapes hold about two hours of material. Audio tapes (1 hour each) are $10, plus shipping ($3 per two tapes rounded up, approx $10 per two tapes international depending on destination). Purchasers of the entire set will receive a 10% discount. Please allow 6-8 weeks for delivery. You can order by calling 415-383-6712, or emailing soundphoto@aol.com or using the web at http://photosynthesis.com/space/gp96.html When ordering, please have the title(s) and catalog number(s) ready, along with your name, shipping address, and VISA/MasterCard information. The list of GP96 tapes is as follows: ================================================================= Sunday July 28 Video V569BT-96 Machine Language Genetic Programming - Peter Nordin, University of Dortmund, Germany. Video V569CT-96 Genetic Programming using Mathematica - Robert Nachbar - Merck Research Laboratories. Video V569DT-96 Introduction to Genetic Programming - John Koza. Video V569ET-96 Classifier Systems- Robert Elliott Smith, University of Alabama. Video V569FT-96 Evolutionary Computation for Constraint Optimization - Zbigniew Michalewicz, University of North Carolina. Video V569GT-96 Advanced Genetic Programming - Koza. Video V569HT-96 Evolutionary Programming and Evolution Strategies - David Fogel, University of California, San Diego. Video V569IT-96 Cellular Encoding - Gruau, Stanford University (via videotape) and Andre, Stanford University (in person). Video V569JT-96 Genetic Programming with Linear Genomes (one hour) - Wolfgang Banzhaf, University of Dortmund, Germany. Video V569KT-96 ECHO - Simon Fraser, Santa Fe Institute. Monday, July 29, 1996 Video V569A-96 Introduction and Administrative Announcements - John Koza, GP-96 General Chair Invited Speech - Hidden Order, John Holland Video V569B-96 Discovery by GP of a Cellular Automata Rule that is Better than any Known Rule for the Majority Classification Problem, Andre, Bennett , and Koza. discussant: Ehrenburg Solving Facility Layout Problems Using Genetic Programming, Garces-Perez, Schoenefeld, and Wainwright Silicon Evolution, Thompson, discussant: BennettIII G P of Near-Minimum-Time Spacecraft Attitude Maneuvers, Howley, discussant: Oakley Video V569C-96 Automated WYWIWYG Design of Both the Topology and Component Values of Electrical Circuits Using GP, Koza, Bennett , Andre, and Keane, discussant: Rosca Evolving Fractal Movies, Angeline, discussant: Fogel Preliminary Experiments on Discriminating between Chaotic Signals and Noise Using Evolutionary Programming, Fogel and Fogel, discussant: Angeline Discovering Patterns in Spatial Data using Evolutionary Programming, Ghozeil and Fogel, discussant: Angeline Evolving Reduced Parameter Bilinear Models for Time Series Prediction using Fast Evolutionary Programming, Rao and Chellapilla, discussant: Fogel Video V569D-96 Robustness of Robot Programs Generated by GP Ito, Iba, and Kimura, discussant: Lohnert Toward Simulated Evolution of Machine Language Iteration, Huelsbergen, discussant: Balakrishnan A New Class of Function Sets for Solving Sequence Problems, Handley, discussant: Abramson The Evolution of Memory and Mental Models Using GP, Brave, discussant: Spector Video V569E-96 Learning Recursive Functions from Noisy Examples using Generic GP, Wong and Leung discussant: McPhee Dynamics of GP and Chaotic Time Series Prediction, Mulloy, Riolo, and Savit, discussant: Oakley Waveform Recognition Using GP: The Myoelectric Signal Recognition Problem, Fernandez, Farry, and Cheatham, discussant: Poli Video V569F-96 Bargaining by Artificial Agents in Two Coalition Games: A Study in GP for Electronic Commerce, Dworman, Kimbrough, and Laing, discussant: Gessler GP and the Efficient Market Hypothesis, Chen and Yeh, discussant: Milne Parallel GP: An Application to Trading Models Evolution, Oussaidene, Chopard, Pictet, and Tomassini, discussant: Ikram Improved Direct Acyclic Graph Evaluation and the Combine Operator in GP, Ehrenburg, discussant: Dracopoulos Video V569G-96 Distributed GP: Empirical Study and Analysis, Niwa and Iba, discussant: Ikram Paragen: A Novel Technique for the Autoparallelisation of Sequential Programs using GP, Walsh and Ryan, discussant: Ikram Motion Planning and Design of CAM Mechanisms by Means of a Genetic Algorithm, Faglia and Vetturi, discussant: Oakley An Adverse Interaction between Crossover and Restricted Tree Depth in GP, Gathercole and Ross, discussant: Rosca Video V569H-96 Evolving Event Driven Programs, Crosbie and Spafford, discussant: McPhee Entailment for Specification Refinement, Haynes, Gamble, Knight, and Wainwright, discussant: Teller MASSON: Discovering Commonalities in Collection of Objects using GP, Ryu and Eick Dis: Handley Evolving Strategies Based on the Nearest Neighbor Rule and a Genetic Algorithm, Fuchs, discussant: Gelenbe Tuesday, July 30, 1996 Video V569I-96 Introduction and Administrative Announcements, Koza, GP-96 General Chair Using Data Structures within GP,. Langdon,discussant: Andre >From Competence to Efficiency and Beyond: Lessons from GAs, Lessons for GP, Goldberg Video V569J-96 Evolving Evolution Programs: GP and L-Systems, Jacob, discussant: Fuchs A Comparison between Cellular Encoding and Direct Encoding for Genetic Neural Networks, Gruau, Whitley, and Pyeatt, discussant: Bennett Code Growth in GP, Soule, Foster, and Dickinson, discussant: Rosca Cultural Transmission of Information in GP, Spector and Luke, discussant: Gessler Video V569K-96 Use of Automatically Defined Functions and Architecture-Altering Operations in Automated Circuit Synthesis with GP, Koza, Andre, Bennett , and Keane, discussant: Poli Investigating the Generality of Automatically Defined Functions, O'Reilly, discussant: Gathercole Evolving Deterministic Finite Automata Using Cellular Encoding, Brave Variations in Evolution of Subsumption Architectures Using GP: The Wall Following Robot Revisited, Ross, Daida, Doan, Bersano-Begey, McClain, discussant: Maxwell Video V569L-96 A Study in Program Response and the Negative Effects of Introns in GP, Andre and Teller, discussant: Rosca Ontogenetic Programming, Spector & Stoffel, discussant: Haynes Generality Versus Size in GP, Rosca, discussant: Haynes The Benefits of Computing with Introns, Wineberg and Oppacher, discussant: Abramson Video V569M-96 Computer-Assisted Design of Image Classification Algorithms: Dynamic and Static Fitness Evaluations in a Scaffolded GP Environment, Daida, Bersano-Begey, Ross, and Vesecky, discussant: Poli Programmatic Compression of Images and Sound, Nordin and Banzhaf, discussant: Oakley GP for Image Analysis, Poli, discussant: Lohnert Evolving Edge Detectors with GP, Harris and Buxton, discussant: Poli Video V569LT-96 Tutorial 12 - Neural Networks - David E. Rumelhart, Stanford University Video V569MT-96 Tutorial 13 - Machine Learning - Pat Langley, Stanford University Video V569NT-96 Tutorial 14 - Molecular Biology for Computer Scientist - Russ B. Altman, M. D., Ph.D , Stanford University Video V569oT-96 Tutorial 15 - Evolvable Hardware Tutorial, Hugo De Garis, ATR, Kyoto, Japan, Adrian Thompson, University of Sussex, UK This is on 2 video tapes for $50. Wednesday, July 31, 1996 Video V569N-96 Introduction and Administrative Announcements, Koza, GP-96 general chair An Investigation into the Sensitivity of GP to the Frequency of Leaf Selection During Subtree Crossover, Angeline, discussant: McPhee Benchmarking the Generalization Capabilities of A Compiling GP System using Sparse Data Sets, Francone, Nordin, and Banzhaf, discussant: Dracopoulos GP using Genotype-Phenotype Mapping from Linear Genomes into Linear Phenotypes, Keller and Banzhaf, discussant: Spector GP, the Reflection of Chaos, and the Bootstrap: Towards a useful Test for Chaos, Oakley, discussant: Video V569o-96 Search Bias, Language Bias, and GP, Whigham, discussant: Rosca Using GP to Develop Inferential Estimation Algorithms, McKay, Willis, Montague, and Barton Evolving Teamwork and Coordination with GP, Luke and Spector Automatic Creation of an Efficient Multi-Agent Architecture Using GP with Architecture- Altering Operations, Bennett , discussant: Poli Video V569P-96 Classifier System Renaissance: New Analogies, New Directions, Cribbs and Smith, discussant: Riolo Three-Dimensional Shape Optimization Utilizing a Learning Classifier System, Richards and Sheppard, discussant: Smith Natural Niching for Evolving Cooperative Classifiers, Horn and Goldberg, discussant: Smith Genetic Algorithms with Analytical Solution, Gelenbe Video V569Q-96 Evolving Control Laws for a Network of Traffic Signals, Montana and Czerwinski, discussant: McPhee Evolving Agents, Qureshi, discussant: Horn Signal Path Oriented Approach for Generation of Dynamic Process Models, Marenbach, Bettenhausen, and Freyer discussant: Teller High-Performance, Parallel, Stack-Based GP, Stoffel and Spector, discussant: Ikram Video V569R-96 GP for Improved Data Mining: An Application to the Biochemistry of Protein Interactions, Raymer, Punch, Goodman, and Kuhn, discussant: Handley The Prediction of the Degree of Exposure to Solvent of Amino Acid Residues via GP, Handley Using GP to Approximate Maximum Clique, Soule, Foster, and Dickinson Evolving Recurrent Neural Network Architectures by GP, Esparcia-Alcazar and Sharman Video V569S-96 On Sensor Evolution in Robotics, Balakrishnan and Honavar Testing Software using Order-Based Genetic Algorithms Boden and Martino, discussant: Balakrishnan A Genetic Algorithm for the Construction of Small and Highly Testable OKFDD Circuits, Drechsler, Becker, and Gockel, discussant: Gelenbe Video V569T-96 Automatic Generation of Object-Oriented Programs Using GP, Bruce, discussant: Dracopoulos Recognition and Reconstruction of Visibility Graphs Using a Genetic Algorithm, Veach, discussant: Gelenbe Evolutionary Algorithms for Natural Language Processing, Dunning and Davis, discussant: Noorthoek Video V569U-96 GP in Database Query Optimization, Stillger and Spiliopoulou Classification using Cultural Co-Evolution and GP, Abramson and Hunter, discussant: Horn Type-Constrained GP for Rule-Base Definition in Fuzzy Logic Controllers, Alba, Cotta, and Troyo You can order by calling 415-383-6712, or emailing soundphoto@aol.com or using the web at http://photosynthesis.com/space/order.html ------------------------------ Date: Sat, 3 Aug 1996 13:45:38 -0700 From: "Jeffrey C. Schlimmer" Subject: MLJ Table of Contents Machine Learning Journal Table of Contents Vol. 24, No. 2 (August 1996) A Lattice Conceptual Clustering System and Its Application to Browsing Retrieval, Claudio Carpineto and Giovanni Romano, Page 95. Bagging Predictors, Leo Breiman, Page 123. Unifying Instance-Based and Rule-Based Induction, Pedro Domingos, Page 141. Jeffrey C. Schlimmer, Asst. Prof., School of EE & CS, Washington State University, PO Box 642752, Pullman, WA 99164-2752, (509) 335-2399, (509) 335-3818 FAX http://www.eecs.wsu.edu/~schlimme/ PGP key: ftp://ftp.eecs.wsu.edu/pub/pgp/schlimmer.hqx, .txt powerPen Faculty Advisor, powerPen@eecs.wsu.edu http://www.eecs.wsu.edu/~schlimme/newton/index.shtml ftp://ftp.eecs.wsu.edu/pub/newton/ ------------------------------ Date: Wed, 14 Aug 96 09:31:45 PDT From: Steve Minton Subject: Recent JAIR ML-related articles Here is a list of ML-related articles that have appeared in JAIR (since March, the last time I sent an update). JAIR's URL is http://www.cs.washington.edu/research/jair/home.html. Regards, - Steve Minton Cohn, D.A., Ghahramani, Z., and Jordan, M.I. (1996) "Active Learning with Statistical Models", Volume 4, pages 129-145. PostScript and HTML See http://www.cs.washington.edu/research/jair/abstracts/yip96a.html Abstract: For many types of machine learning algorithms, one can compute the statistically `optimal' way to select training data. In this paper, we review how optimal data selection techniques have been used with feedforward neural networks. We then show how the same principles may be used to select data for two alternative, statistically-based learning architectures: mixtures of Gaussians and locally weighted regression. While the techniques for neural networks are computationally expensive and approximate, the techniques for mixtures of Gaussians and locally weighted regression are both efficient and accurate. Empirically, we observe that the optimality criterion sharply decreases the number of training examples the learner needs in order to achieve good performance. Fisher, D. (1996) "Iterative Optimization and Simplification of Hierarchical Clusterings", Volume 4, pages 147-178. PostScript and HTML See http://www.cs.washington.edu/research/jair/abstracts/fisher96a.html Abstract: Clustering is often used for discovering structure in data. Clustering systems differ in the objective function used to evaluate clustering quality and the control strategy used to search the space of clusterings. Ideally, the search strategy should consistently construct clusterings of high quality, but be computationally inexpensive as well. In general, we cannot have it both ways, but we can partition the search so that a system inexpensively constructs a `tentative' clustering for initial examination, followed by iterative optimization, which continues to search in background for improved clusterings. Given this motivation, we evaluate an inexpensive strategy for creating initial clusterings, coupled with several control strategies for iterative optimization, each of which repeatedly modifies an initial clustering in search of a better one. One of these methods appears novel as an iterative optimization strategy in clustering contexts. Once a clustering has been constructed it is judged by analysts -- often according to task-specific criteria. Several authors have abstracted these criteria and posited a generic performance task akin to pattern completion, where the error rate over completed patterns is used to `externally' judge clustering utility. Given this performance task, we adapt resampling-based pruning strategies used by supervised learning systems to the task of simplifying hierarchical clusterings, thus promising to ease post-clustering analysis. Finally, we propose a number of objective functions, based on attribute-selection measures for decision-tree induction, that might perform well on the error rate and simplicity dimensions. Kaelbling, L.P., Littman, M.L., and Moore, A.W. (1996) "Reinforcement Learning: A Survey", Volume 4, pages 237-285. PostScript and HTML See http://www.cs.washington.edu/research/jair/abstracts/kaelbling96a.html Abstract: This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word ``reinforcement.'' The paper discusses central issues of reinforcement learning, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning. Nienhuys-Cheng, S.-H. and de Wolf, R. (1996) "Least Generalizations and Greatest Specializations of Sets of Clauses", Volume 4, pages 341-363. See http://www.cs.washington.edu/research/jair/abstracts/cheng96a.html Abstract: The main operations in Inductive Logic Programming (ILP) are generalization and specialization, which only make sense in a generality order. In ILP, the three most important generality orders are subsumption, implication and implication relative to background knowledge. The two languages used most often are languages of clauses and languages of only Horn clauses. This gives a total of six different ordered languages. In this paper, we give a systematic treatment of the existence or non-existence of least generalizations and greatest specializations of finite sets of clauses in each of these six ordered sets. We survey results already obtained by others and also contribute some answers of our own. Our main new results are, firstly, the existence of a computable least generalization under implication of every finite set of clauses containing at least one non-tautologous function-free clause (among other, not necessarily function-free clauses). Secondly, we show that such a least generalization need not exist under relative implication, not even if both the set that is to be generalized and the background knowledge are function-free. Thirdly, we give a complete discussion of existence and non-existence of greatest specializations in each of the six ordered languages. Gratch, J. and Chien, S. (1996) "Adaptive Problem-solving for Large-scale Scheduling Problems: A Case Study", Volume 4, pages 365-396. See http://www.cs.washington.edu/research/jair/abstracts/gratch96a.html Abstract: Although most scheduling problems are NP-hard, domain specific techniques perform well in practice but are quite expensive to construct. In adaptive problem-solving solving, domain specific knowledge is acquired automatically for a general problem solver with a flexible control architecture. In this approach, a learning system explores a space of possible heuristic methods for one well-suited to the eccentricities of the given domain and problem distribution. In this article, we discuss an application of the approach to scheduling satellite communications. Using problem distributions based on actual mission requirements, our approach identifies strategies that not only decrease the amount of CPU time required to produce schedules, but also increase the percentage of problems that are solvable within computational resource limitations. Webb, G.I. (1996) "Further Experimental Evidence against the Utility of Occam's Razor", Volume 4, pages 397-417. PostScript plus online appendix containing source code. See http://www.cs.washington.edu/research/jair/abstracts/webb96a.html Abstract: This paper presents new experimental evidence against the utility of Occam's razor. A~systematic procedure is presented for post-processing decision trees produced by C4.5. This procedure was derived by rejecting Occam's razor and instead attending to the assumption that similar objects are likely to belong to the same class. It increases a decision tree's complexity without altering the performance of that tree on the training data from which it is inferred. The resulting more complex decision trees are demonstrated to have, on average, for a variety of common learning tasks, higher predictive accuracy than the less complex original decision trees. This result raises considerable doubt about the utility of Occam's razor as it is commonly applied in modern machine learning. Tadepalli, P. and Natarajan, B.K. (1996) "A Formal Framework for Speedup Learning from Problems and Solutions", Volume 4, pages 445-475. See http://www.cs.washington.edu/research/jair/abstracts/tadepalli96a.html Abstract: Speedup learning seeks to improve the computational efficiency of problem solving with experience. In this paper, we develop a formal framework for learning efficient problem solving from random problems and their solutions. We apply this framework to two different representations of learned knowledge, namely control rules and macro-operators, and prove theorems that identify sufficient conditions for learning in each representation. Our proofs are constructive in that they are accompanied with learning algorithms. Our framework captures both empirical and explanation-based speedup learning in a unified fashion. We illustrate our framework with implementations in two domains: symbolic integration and Eight Puzzle. This work integrates many strands of experimental and theoretical work in machine learning, including empirical learning of control rules, macro-operator learning, Explanation-Based Learning (EBL), and Probably Approximately Correct (PAC) Learning. Brafman, R.I. and Tennenholtz, M. (1996) "On Partially Controlled Multi-Agent Systems", Volume 4, pages 477-507. See http://www.cs.washington.edu/research/jair/abstracts/brafman96a.html Abstract: Motivated by the control theoretic distinction between controllable and uncontrollable events, we distinguish between two types of agents within a multi-agent system: controllable agents, which are directly controlled by the system's designer, and uncontrollable agents, which are not under the designer's direct control. We refer to such systems as partially controlled multi-agent systems, and we investigate how one might influence the behavior of the uncontrolled agents through appropriate design of the controlled agents. In particular, we wish to understand which problems are naturally described in these terms, what methods can be applied to influence the uncontrollable agents, the effectiveness of such methods, and whether similar methods work across different domains. Using a game-theoretic framework, this paper studies the design of partially controlled multi-agent systems in two contexts: in one context, the uncontrollable agents are expected utility maximizers, while in the other they are reinforcement learners. We suggest different techniques for controlling agents' behavior in each domain, assess their success, and examine their relationship. Yip, K. and Zhao, F. (1996) "Spatial Aggregation: Theory and Applications", Volume 5, pages 1-26. See http://www.cs.washington.edu/research/jair/abstracts/yip96a.html Abstract: Visual thinking plays an important role in scientific reasoning. Based on the research in automating diverse reasoning tasks about dynamical systems, nonlinear controllers, kinematic mechanisms, and fluid motion, we have identified a style of visual thinking, imagistic reasoning. Imagistic reasoning organizes computations around image-like, analogue representations so that perceptual and symbolic operations can be brought to bear to infer structure and behavior. Programs incorporating imagistic reasoning have been shown to perform at an expert level in domains that defy current analytic or numerical methods. We have developed a computational paradigm, spatial aggregation, to unify the description of a class of imagistic problem solvers. A program written in this paradigm has the following properties. It takes a continuous field and optional objective functions as input, and produces high-level descriptions of structure, behavior, or control actions. It computes a multi-layer of intermediate representations, called spatial aggregates, by forming equivalence classes and adjacency relations. It employs a small set of generic operators such as aggregation, classification, and localization to perform bidirectional mapping between the information-rich field and successively more abstract spatial aggregates. It uses a data structure, the neighborhood graph, as a common interface to modularize computations. To illustrate our theory, we describe the computational structure of three implemented problem solvers -- KAM, MAPS, and HIPAIR --- in terms of the spatial aggregation generic operators by mixing and matching a library of commonly used routines. ------------------------------ From: Francesco Ricci Subject: Job opportunity at IRST Date: Mon, 22 Jul 1996 11:07:27 +0200 (MET DST) Istituto Trentino di Cultura Istituto per la Ricerca Scientifica e Tecnologica The Istituto per la Ricerca Scientifica e Tecnologica (IRST) is seeking a person for a research position in case based reasoning (CBR) and machine learning. The position is advertised as part of a long term plan whose goal is to strengthen the IRST group working in the area of Reasoning and CBR in particular. The position requires highly motivated outstanding individuals capable of working in a research group including researchers, programmers, and students. The successful candidate will be responsible for the development and deployment of advanced case-based reasoning software. The position will involve working on research and technology transfer projects, as defined by IRST's research plan. The work will involve close collaboration with industry. Publishing is encouraged. Istituto Trentino di Cultura (ITC) is a regional research organisation created in 1962, in order to promote research activities in the Trentino area. ITC has currently a staff of 200 full-time researchers (plus several fellows, consultants and visiting scholars) and a 1996 provisional budget of more than 13,100,000 ECU. IRST is the main research centre of ITC. Its organisation and planning are directed to pursue both basic and applied research, through a co-ordinated design that integrates objectives of research excellence and responsiveness to local, national, and international development needs. IRST's main efforts are concentrated in interactive sensorial systems, cognitive and communication technologies and in the design, fabrication and testing of intelligent smart optical and bio-sensors. The successful candidate will be in the Cognitive and Communication Technologies division, working in a group of people concerned with Automated Reasoning and Knowledge Representation. This group at the moment has nine full time researchers, some post-docs, and various PhD and Master students. More specifically, he or she will closely collaborate with the people developing a state of the art CBR tool to be applied in a number of different applications (Natural Resource Management, Fraud Detection, DSS in the Banking environment). More information can be found at the following Web addresses: ITC: http://www.itc.it/ IRST: http://artemide.itc.it:80/irst/ Reasoning Area groups: Reasoning for Decision Support: http://mnemosyne.itc.it:1024/rds/ Mechanized Reasoning: http://afrodite.itc.it:1024/ Knowledge Representation and Reasoning: http://mnemosyne.itc.it:1024/ REQUIRED: -MS/PhD in Computer Science, Mathematics, Engineering or related field -Min 3 years of experience developing and maintaining complex large-scale R&D software applications either in industry or academia -Excellent working knowledge of LISP or C++. -Familiarity with UNIX -Some mathematical sophistication -Good problem solving and communication skills (both written and verbal) DESIRED: - International experience - Earlier work on case-based reasoning or machine learning applications - Experience with any of the following: Relational DBs, SQL, HTML, Data Visualization, Data Mining; - Some familiarity with probability theory and statistics. HOW TO APPLY The interested candidate should send a resume plus names and addresses (including email addresses when possible) of three people who can recommend them. The resume should make clear under which circumstances these people have known the candidate. This position is advertised for three years, to be renewed each year. This position can be further extended at the end of the three years. This will depend on the scientific results obtained and the industrial projects acquired. The salary is competive. The deadline for submission is September 15th. We would like to fill this position by November 1st. Inquiries and requests for further information should be directed to: Francesco Ricci IRST Loc. Pante' di Povo 38050 Trento, Italy Tel: ++39-461-314334, Fax: ++39-461-302040 email: ricci@irst.itc.it WWW http://mnemosyne.itc.it:1024/ricci Applications should be sent to: Fausto Giunchiglia IRST Loc. Pante' di Povo 38050 Trento, Italy Tel: ++39-461-314-436 (517), Fax: ++39-461-302040 email: fausto@irst.itc.it WWW http://afrodite.itc.it:1024/~fausto ------------------------------ Date: Wed, 24 Jul 1996 08:57:09 -0400 From: Mark Gluck Subject: Programmer/R.A. Position at Rutgers Univ. in Computational Neuroscience SEEKING A PROGRAMMER/RESEARCH ASSISTANT TO WORK ON NEURAL-NETWORK BRAIN MODELS AT RUTGERS-NEWARK NEUROSCIENCE CENTER (GLUCK LAB). We are looking for a programmer/research assistant to work with us on testing computational models of cortico-hippocampal function in animal and human learning. The applicant must be able to work independently -- given a set of specifications, he/she should be able to optimize program performance to generate results, and also analyze system behavior. The ideal applicant would be someone recently out of college, who would like some research experience prior to future graduate work in psychology, neuroscience, cognitive science, or computer science. Required Skills: Strong C (or C++) programming Knowledge of Unix Commitment to at least 15 hours/week, for at least one year. Could also be a full time position. Preferrred But Not Required Skills: Knowledge of Sun workstations Background in neural networks Background in premed, biology, or psychology. Salary: Commensurate with skill level and experience. For more information on our research, see our lab WWW page noted below. Contact Mark Gluck below with a cover letter and resume (preferably sent by email) to apply. ========================================================== Dr. Mark A. Gluck Center for Molecular & Behavioral Neuroscience Rutgers University 197 University Ave. Newark, New Jersey 07102 Phone: (201) 648-1080 (Ext. 3221) Fax: (201) 648-1272 Email: gluck@pavlov.rutgers.edu WWW Homepage: http://www.cmbn.rutgers.edu/cmbn/faculty/gluck.html ====================================================================== ------------------------------ From: Marney Smyth Subject: Intensive Tutorial: Learning Methods for Prediction, Classification Date: Thu, 25 Jul 1996 07:40:41 -0400 (EDT) ************************************************************** *** *** *** Learning Methods for Prediction, Classification, *** *** Novelty Detection and Time Series Analysis *** *** *** *** Cambridge, MA, September 20-21, 1996 *** *** Los Angeles, CA, December 14-15, 1996 *** *** *** *** Geoffrey Hinton, University of Toronto *** *** Michael Jordan, Massachusetts Inst. of Tech. *** *** *** ************************************************************** A two-day intensive Tutorial on Advanced Learning Methods will be held on September 20 and 21, 1996, at the Royal Sonesta Hotel, Cambridge, MA, and on December 14 and 15, 1996, at Lowe's Hotel, Santa Monica, CA. Space is available for up to 50 participants for each course. The course will provide an in-depth discussion of the large collection of new tools that have become available in recent years for developing autonomous learning systems and for aiding in the analysis of complex multivariate data. These tools include neural networks, hidden Markov models, belief networks, decision trees, memory-based methods, as well as increasingly sophisticated combinations of these architectures. Applications include prediction, classification, fault detection, time series analysis, diagnosis, optimization, system identification and control, exploratory data analysis and many other problems in statistics, machine learning and data mining. The course will be devoted equally to the conceptual foundations of recent developments in machine learning and to the deployment of these tools in applied settings. Case studies will be described to show how learning systems can be developed in real-world settings. Architectures and algorithms will be presented in some detail, but with a minimum of mathematical formalism and with a focus on intuitive understanding. Emphasis will be placed on using machine methods as tools that can be combined to solve the problem at hand. WHO SHOULD ATTEND THIS COURSE? The course is intended for engineers, data analysts, scientists, managers and others who would like to understand the basic principles underlying learning systems. The focus will be on neural network models and related graphical models such as mixture models, hidden Markov models, Kalman filters and belief networks. No previous exposure to machine learning algorithms is necessary although a degree in engineering or science (or equivalent experience) is desirable. Those attending can expect to gain an understanding of the current state-of-the-art in machine learning and be in a position to make informed decisions about whether this technology is relevant to specific problems in their area of interest. COURSE OUTLINE Overview of learning systems; LMS, perceptrons and support vectors; generalized linear models; multilayer networks; recurrent networks; weight decay, regularization and committees; optimization methods; active learning; applications to prediction, classification and control Graphical models: Markov random fields and Bayesian belief networks; junction trees and probabilistic message passing; calculating most probable configurations; Boltzmann machines; influence diagrams; structure learning algorithms; applications to diagnosis, density estimation, novelty detection and sensitivity analysis Clustering; mixture models; mixtures of experts models; the EM algorithm; decision trees; hidden Markov models; variations on hidden Markov models; applications to prediction, classification and time series modeling Subspace methods; mixtures of principal component modules; factor analysis and its relation to PCA; Kalman filtering; switching mixtures of Kalman filters; tree-structured Kalman filters; applications to novelty detection and system identification Approximate methods: sampling methods, variational methods; graphical models with sigmoid units and noisy-OR units; factorial HMMs; the Helmholtz machine; computationally efficient upper and lower bounds for graphical models REGISTRATION Standard Registration: $700 Student Registration: $400 Registration fee includes course materials, breakfast, coffee breaks, and lunch on Saturday. Those interested in participating should return the completed Registration Form and Fee as soon as possible, as the total number of places is limited by the size of the venue. ADDITIONAL INFORMATION A registration form is available from the course's WWW page at http://www.ai.mit.edu/projects/cbcl/web-pis/jordan/course/index.html Marney Smyth CBCL at MIT E25-201 45 Carleton Street Cambridge, MA 02142 USA Phone: 617 253-0547 Fax: 617 253-2964 E-mail: marney@ai.mit.edu ------------------------------ From: Zoran Obradovic - Faculty Subject: Special Issue CFP - final call Date: Sun, 28 Jul 1996 11:33:56 -0700 (PDT) FINAL CALL FOR PAPERS Special Issue of the NeuroVe$t Journal Special Issue Theme: Hybrid Neural Networks for Financial Forecasting Submission Deadline: September 3, 1996 Publication Date: January 1997 Finance & Technology Publishing is seeking papers reporting original research for review and publication in the NeuroVe$t Journal special issue on HYBRID NEURAL NETWORKS FOR FINANCIAL FORECASTING scheduled for publication in January 1997. Aims and Scope: Current machine learning prediction systems are very limited in the type of knowledge they can use for learning. This design limitation is particularly serious when applied to financial domains where sample data is very noisy and non-stationary. Although potentially better results are achievable using learning systems that integrate two or more types of knowledge representation and/or multiple inference underlying a learning process, to date little has been published on such hybrid approaches to financial modeling. Potential subjects of interest to this special issue include systems in which neural networks are integrated with other prediction techniques (e.g. trading rules, stochastic analysis, nonlinear dynamics, genetic algorithms, fuzzy logic, etc.) to complement limited training data information into more accurate prediction systems. Submission Procedure: Prospective authors are invited to submit three hardcopies and a softcopy of a complete manuscript by SEPTEMBER 3, 1996 to either the Guest Editor or to the Editor-in-Chief. Papers should be double-spaced, single-sided and the text should be 4000 to 5000 words in length, contain no more than 10 references. Authors should provide a brief biographic sketch of themselves. Each copy submitted should include a page that contains the title of the paper, the full name(s) and affiliation(s) of the author(s), complete mailing address and telephone numbers of all authors, and a 150 to 300 word abstract. Text citations must use the following format: last name(s) of author(s), publication date and suffix (as necessary) in brackets. Example: [Watkins and McCoy 1993a]. References must be listed alphabetically by the last name of the first author. The preferred file format for a softcopy is Word for Windows. All formating details are available at the NeuroVeSt WWW location http://ourworld.compuserve.com/homepages/FTPub/nvj.htm Guest Editor: Editor-in-Chief: Zoran Obradovic Randall B. Caldwell School of Electrical Engineering NeuroVe$t Journal and Computer Science P.O. Box 764 Washington State University Haymarket, VA 22069-0764, USA Pullman, WA 99164-2752, USA Tel/Fax: (703) 754-0696 Tel: (509) 335-6601 email: RBCALDWELL@delphi.com Fax: (509) 335-3818 email: zoran@eecs.wsu.edu http://www.eecs.wsu.edu/~zoran ------------------------------ Date: Mon, 29 Jul 96 22:54:06 -0500 From: Grace Wahba Subject: spline/ai paper ancts Announcing some new/revised manuscripts available on the web .... URL http://www.stat.wisc.edu/~wahba click on `TRLIST' ============================================================================ Luo, Z. " Backfitting in Smoothing Spline ANOVA, With Application to Historical Global Temperature Data " TR 964, July 1996. PhD. Thesis Xiang, D. " Model Fitting and Testing for Non-Gaussian Data with a Large Data Set " TR 957, January 1996. PhD. Thesis Wang, Y., Wahba, G., Gu, C., Klein, R. and Klein, B. " Using Smoothing Spline ANOVA to Examine the Relation of Risk Factors to the Incidence and Progression of Diabetic Retinopathy " TR 956, December 1995, provisionally accepted, Statistics in Medicine, some revisions in preparation. Luo, Z. and Wahba, G. " Hybrid Adaptive Splines" TR 947, June 1995, to appear, J. A. S. A. Xiang, D. and Wahba, G. " A Generalized Approximate Cross Validation for Smoothing Splines with Non-Gaussian Data." TR 930, September 1994, to appear, Statistica Sinica. ------------------------------ Date: Tue, 30 Jul 1996 20:27:19 -0500 From: Ron Sun Call For Papers special issue of IEEE Transaction on Neural Networks on ``Neural Networks and Hybrid Intelligent Models: Foundations, Theory, and Applications'' Guest Editors: C. Lee Giles, Ron Sun, Jacek M. Zurada Hybrid systems, the use of other intelligence paradigms with neural networks, are becoming more common and useful. In fact it can be argued that the success of neural networks has been from its ready incorporation of other information processing approaches, including pattern recognition, statistical inference, as well as symbolic processing. Some systems (especially those incorporating symbolic processing) have been known to some segments of the scientific community as high-level connectionist models. Other systems have been referred to as knowledge insertion and extraction. However, for the many applications, there exists little (1) theoretical foundation and (2) engineering methodology for effectively developing hybrid approaches. These two aspects are the topic of this special issue. Manuscripts are solicited in neural networks and hybrid models in the following areas - Theorectical foundations of hybrid models. Mathematical analysis, theories, critiques, case studies. - Models incorporating other paradigms such as AI symbolic processing, machine learning, fuzzy systems, genetic algorithms, and other intelligent paradigms within neural networks. Techniques, methodologies, and analyses. - Methodology of engineering design of hybrid systems. - Innovative and non-trivial applications of hybrid models (for example, in natural language processing, signal and image processing, pattern recognition, and cognitive modeling). Papers will undergo the standard review procedure of the IEEE Transactions on Neural Netwoks. The special issue will appear around November 1997. Prospective authors should submit six (6) copies of the completed manuscript, on or before February 28, 1997, to one of the following three guest editors: Dr. C. Lee Giles NEC Research Institute 4 Independence Way Princeton, NJ 08540, USA Phone: 609-951-2642 Fax 609-951-2482 Email: giles@research.nj.nec.com Web: http://www.neci.nj.nec.com/homepages/giles.html Prof. Ron Sun Department of Computer Science The University of Alabama Tuscaloosa, AL 35487 Phone: (205) 348-6363 Fax: (205) 348-0219 Email: rsun@cs.ua.edu Web: http://cs.ua.edu/faculty/sun/sun.html Prof. Jacek M. Zurada Electrical Engineering Department University of Louisville Louisville, KY 40292, USA Phone: (502) 852-6314 Fax: (502) 852-6807 Email: j.zurada@ieee.org Web: under construction ------------------------------ Date: Thu, 1 Aug 1996 22:29:05 -0400 (EDT) From: Sue Becker Subject: REGISTRATION FOR NIPS*96 REGISTRATION FOR NIPS*96 Neural Information Processing Systems Tenth Annual Conference Monday December 2 - Saturday December 7, 1996 Denver, Colorado The NIPS*96 registration brochure is now available online. NIPS*96 is the tenth meeting of an interdisciplinary conference which brings together cognitive scientists, computer scientists, engineers, neuroscientists, physicists, and mathematicians interested in all aspects of neural processing and computation. The conference will include invited talks and oral and poster presentations of refereed papers. The conference is single track and is highly selective. Preceding the main session (Dec. 3-5), there will be one day of tutorial presentations (Dec. 2), both in Denver, Colorado. Following will be two days of focused workshops on topical issues at Snowmass, Colorado, a world class ski resort (Dec. 6-7). The registration brochure and other conference information may be retrieved via the World Wide Web at http://www.cs.cmu.edu/Web/Groups/NIPS We expect to offer online registration soon from the NIPS web site. Registration material and other information may also be obtained by writing to: NIPS*96 Registration Conference Consulting Associates 451 N. Sycamore Monticello, IA 52310 fax: (319) 465-6709 (attn: Denise Prull) e-mail: nipsinfo@salk.edu REGISTRATION FEES: Conference (includes Proceedings, Reception, Banquet and 3 Continental Breakfasts) Regular $285.00 ($360.00 after Oct. 31, 1996) Full-time students, with I.D. $100.00 ($150.00 after Oct. 31, 1996) Workshops Regular $150.00 ($200.00 after Oct. 31, 1996) Full-time students, with I.D. $75.00 ($125.00 after Oct. 31, 1996) Tutorials Regular $150.00 Full-time students, with I.D. $50.00 TUTORIAL PROGRAM December 2, 1996 Session I: 09:30-11:30 Mostly statistical methods for language processing Dan Jurafsky, University of Colorado at Boulder >From traditional statistical models to neural networks Trevor Hastie, Stanford University Session II: 13:00-15:00 Practical pattern recognition via neural networks Brian Ripley, University of Oxford Reinforcement learning Richard S. Sutton, University of Massachusetts Session III: 15:30-17:30 Neural networks for the human genome project and beyond Frank Eeckman, Lawrence Berkeley National Laboratory Challenges of time series prediction John Moody, Oregon Graduate Institute CONFERENCE: INVITED TALKS December 3-5, 1996 Computer graphics for film: Automatic versus manual techniques Eric Enderton (Banquet Speaker), Industrial Light and Magic Wavelets, wavelet packets, and beyond: Applications of new adaptive signal representations David Donoho, Stanford University and UC Berkeley Plasticity of dynamics as opposed to absolute strength of synapses Henry Markram, Weizmann Institute Transition between rate and temporal coding in neocortex as determined by synaptic depression Misha Tsodyks, Weizmann Institute The CONDENSATION algorithm - Conditional density propagation and applications to visual tracking Andrew Blake, University of Oxford Compositionality, MDL priors and object recognition Stuart Geman and Elie Bienenstock, Brown University WORKSHOPS: PRELIMINARY SCHEDULE December 6-7, 1996 Friday, December 6 Neural modulation and neural information processing A. Tang and C. Linster Population coding: Interpreting the responses of neuronal populations A. Pouget, R. Zemel, P. Dayan Model complexity C. Williams & J. Utans ANNs and continuous optimization: Local minima, sub-optimality and computational complexity M. Gori and M. Protasi The structure of natural images and efficient image coding D. Ruderman and B. Olshausen Dynamical recurrent networks Day 1: J. Kolen and S. Kremer Connectionist modelling of auditory scene analysis G. Brown and D. Wang Rule extraction from ANNs R. Andrews Saturday, December 7 Cortical magnification G. Blasdell Synaptic transmission: Reliability and variability V. Murthy and T. Zador Tricks of the trade: How to really make algorithms work G. Orr, K. Mueller, & R. Caruana What does accuracy really mean? H. Burke and A. Hoang Modelling error surfaces S. Mukherjee and T. Fine Learning vision A. Yuille and A. Blake Dynamical recurrent networks Day 2: James Howse and Bill Horne Nature inspired algorithms for combinatorial optimization A. Jagota Blind signal processing A. Cichocki and A. Back NIPS*96 is sponsored by the NEURAL INFORMATION PROCESSING SYSTEMS Foundation, Inc. with additional sponsorship of student and young investigator travel awards from the Office of Naval Research. NIPS*96 Organizing Committee: General Chair, Michael Mozer, U. Colorado; Program Chair, Michael Jordan, MIT; Publications Chair, Thomas Petsche, Siemens; Tutorial Chair, John Lazzaro, Berkeley; Workshops Co-Chairs, Michael Perrone, IBM, and Steven Nowlan, Lexicus; Publicity Chair, Suzanna Becker, McMaster; Local Arrangements, Marijke Augusteijn, U. Colorado; Treasurer, Eric Mjolsness, UCSD; Government/Corporate Liaison, John Moody, OGI; Contracts, Steve Hanson, Siemens, Scott Kirkpatrick, IBM, Gerry Tesauro, IBM. Conference arrangements by Conference Consulting Associates, Monticello, IA. ------------------------------ Date: Fri, 2 Aug 1996 16:07:16 -0600 (MDT) From: Melanie Mitchell Subject: Announcing a New Book... ADAPTIVE INDIVIDUALS IN EVOLVING POPULATIONS: MODELS AND ALGORITHMS edited by Richard K. Belew and Melanie Mitchell Proceedings Volume XXVI, Santa Fe Institute Studies in the Sciences of Complexity Addison-Wesley, Reading, MA, 1996 ABOUT THE BOOK The theory of evolution has been most successful explaining the emergence of new species in terms of their morphological traits. Ethologists teach that behaviors, too, qualify as first-class phenotypic features, but evolutionary accounts of behaviors have been much less satisfactory. In part this is because maturational "programs" transforming genotype to phenotype are "open" to environmental influences affected by behaviors. Further, many organisms are able to continue to modify their behavior, i.e., learn, even after fully mature. This creates an even more complex relationship between the genotypic features underlying the mechanisms of maturation and learning and the adapted behaviors ultimately selected. A meeting held at the Santa Fe Institute during the summer of 1993 brought together a small group of biologists, psychologists, and computer scientists with shared interests in questions such as these. This volume consists of approximately two dozen papers that explore interacting adaptive systems from a range of interdisciplinary perspectives. About half the articles are classic, seminal references on the subject, ranging from biologists like Lamarck and Waddington to psychologists like Piaget and Skinner. The other papers represent new work by the workshop participants. The role played by mathematical and computational tools, both as models of natural phenomena and as algorithms useful in their own right, is particularly emphasized in these new papers. In all cases the chapters have been augmented by specially written prefaces. In the case of the reprinted classics, the prefaces help to put the older papers in a modern context. For the new papers, the prefaces have been written by colleagues from a discipline other than the paper's authors, and highligh, for example, what a computer scientist can learn from a biologist's model, or vice versa. Through these cross-disciplinary "dialogues" and a glossary collecting multidisciplinary connotations of pivotal terms, the process of interdisciplinary investigation itself becomes a central theme. ORDERING INFORMATION This series is published by The Advanced Book Program, Addison-Wesley Publishing Company, One Jacob Way, Reading, MA 01867. Please contact your local bookstore or, for credit card orders, call Addison-Wesley Publishing Company at (800)447-2226. For more information on this book, visit the web page: http://www.santafe.edu/sfi/publications/Bookinfo/aiineptofc.html ======================================================================= ADAPTIVE INDIVIDUALS IN EVOLVING POPULATIONS: MODELS AND ALGORITHMS TABLE OF CONTENTS Chapter 1: Introduction - R. K. Belew & M. Mitchell BIOLOGY OVERVIEW Chapter 2: Adaptive Computation in Ecology and Evolution: A Guide to Future Research - J. Roughgarden, A. Bergman, S. Shafir, and C. Taylor REPRINTED CLASSICS Chapter 3: The Classics in Their Context, and in Ours - J. Schull Chapter 4: Of the Influence of the Environment on the Activities and Habits of Animals, and the Influence of the Activities and Habits of These Living Bodies in Modifying Their Organisation and Structure - J. B. Lamarck Chapter 5: A New Factor in Evolution - J. M. Baldwin Chapter 6: On Modification and Variation - C. Lloyd Morgan Chapter 7: Canalization of Development and the Inheritance of Acquired Characters - C. H. Waddington Chapter 8: The Baldwin Effect - G. G. Simpson Chapter 9: The Role of Somatic Change in Evolution - G. Bateson NEW WORK Chapter 10: A Model of Individual Adaptive Behavior in a Fluctuating Environment - L. A. Zhivotovsky, A. Bergman, and M. W. Feldman (Preface by R. K. Belew) Chapter 11: The Baldwin Effect in the Immune System: Learning by Somatic Hypermutation - R. Hightower, S. Forrest, and A. S. Perelson (Preface by W. Hart) Chapter 12: The Effect of Memory Length on Individual Fitness in a Lizard - S. Shafir and J. Roughgarden (Preface by M. L. Littman and F. Menczer; Appendix by F. Menczer, W. E. Hart, and M. L. Littman) Chapter 13: Latent Energy Environments - F. Menczer and R. K. Belew (Preface by J. Roughgarden) PSYCHOLOGY OVERVIEW Chapter 14: The Causes and Effects of Evolutionary Simulation in the Behavioral Sciences - P. M. Todd REPRINTED CLASSICS Chapter 15: Excerpts from "Principles of Biology" - H. Spencer (Preface by P. G. Godfrey-Smith) Chapter 16: Excerpts from "Principles of Psychology" - H. Spencer (Preface by P. G. Godfrey-Smith) Chapter 17: William James and the Broader Implications of a Multilevel Selectionism - J. Schull Chapter 18: Excerpts from "The Phylogeny and Ontogeny of Behavior" - B. F. Skinner Chapter 19: Excerpts from "Adaptation and Intelligence: Organic Selection and Phenocopy" - J. Piaget (Preface by O. Miglino & R. K. Belew) Chapter 20: Selective Costs and Benefits of Learning - T. D. Johnston (Preface by P. M. Todd) NEW WORK Chapter 21: Sexual Selection and the Evolution of Learning - P. M. Todd (Preface by S. Shafir) Chapter 22: Discontinuity in Evolution: How Different Levels of Organization Imply Preadaptation - O. Miglino, S. Nolfi, and D. Parisi (Preface by M. Mitchell) Chapter 23: The Influence of Learning on Evolution - D. Parisi and S. Nolfi (Preface by W. Hart) COMPUTER SCIENCE OVERVIEW Chapter 24: Computation and the Natural Sciences - R. K. Belew, M. Mitchell, and D. Ackley REPRINTED CLASSICS Chapter 25: How Learning Can Guide Evolution - G. Hinton & S. Nowlan (Preface by M. Mitchell and R. K. Belew) Natural Selection: When Learning Guides Evolution - J. Maynard Smith NEW WORK Chapter 26: Simulations Combining Evolution and Learning - M. L. Littman (Preface by M. Mitchell) Chapter 27: Optimization with Genetic Algorithm Hybrids that Use Local Search - W. Hart & R. K. Belew (Preface by C. Taylor) GLOSSARY INDEX ------------------------------ Date: Tue, 6 Aug 1996 14:54:35 -0700 From: ali@almaden.ibm.com Subject: Data-Mining jobs at IBM San Jose IBM DATA MINING POSITIONS Join the team! We are an entrepreneurial organization within IBM developing Data Mining solutions. We have three groups, a consulting services group, research & development group, and software application development group. Currently, we are looking for qualified individuals in the rapidly expanding consulting services group. DATA MINING ANALYSTS/CONSULTANTS Analysts will be responsible for performing consulting engagements in any of the following areas: finance, insurance, retail, tele- communications, media, and health care. There will also be opportunities for teaching business data-mining classes and a few opportunities for applied research for the kinds of problems that arise from our data-mining engagements. Familiarity with databases, statistics, data preparation, and high-end data mining techniques and tools required. Familiarity with SAS and previous experience in applying data-mining in a commercial context are big pluses. Applicants must have advanced degrees in CS, Statistics, or Mathematics - PhD preferred. Applicants should have good communication skills, like working with people in a team environment, be willing to travel and be application oriented. These positions provide excellent customer contact with high level executives in FORTUNE 500 companies. These positions will be located at our world class research lab - Almaden Research Center - in sunny San Jose, CA. Almaden is located in beautifully situated rolling hills in Silicon Valley affording close contact with top universities such as Stanford University and UC Berkeley. For further information, please email your resume to myself (ali@almaden.ibm.com) preferably in ASCII or Postscript format. I've been working as an Analyst in IBM's data mining group since December and it's been a great experience. Feel free to contact me with questions. (408) 927-1354. US citizenship or permanent residency required. Also check out our web pages, which give some detailed examples of how we've used our tools to build and visualize models and give information on previous engagements we have had. http://www.almaden.ibm.com/stss (click on "Data Mining") Kamal Mahmood Ali, Ph.D. Phone: 408 927 1354 Consultant and data mining analyst, Fax: 408 927 3025 Data Mining Solutions, Office: ARC D3-250 IBM http://www.almaden.ibm.com/stss/ ------------------------------ Date: Thu, 8 Aug 96 15:05:49 EDT From: Aalbert De Vries x2456 Subject: FIRST Call for Papers: NNSP*97 1997 IEEE Workshop on Neural Networks for Signal Processing 24-26 September 1997 Amelia Island Plantation Amelia Island, Florida FIRST ANNOUNCEMENT AND CALL FOR PAPERS Thanks to the sponsorship of the IEEE Signal Processing Society and the co-sponsorship of the IEEE Neural Network Council, we are proud to announce the seventh of a series of IEEE Workshops on Neural Networks for Signal Processing. Papers are solicited for, but not limited to, the following topics: * Paradigms artificial neural networks, Markov models, fuzzy logic, inference net, evolutionary computation, nonlinear signal processing, and wavelets * Application areas speech processing, image processing, OCR, robotics, adaptive filtering, communications, sensors, system identification, issues related to RWC, and other general signal processing and pattern recognition * Theories generalization, design algorithms, optimization, parameter estimation, and network architectures * Implementations parallel and distributed implementation, hardware design, and other general implementation technologies Instructions for sumbitting papers Prospective authors are invited to submit 5 copies of extended summaries of no more than 6 pages. The top of the first page of the summary should include a title, authors' names, affiliations, address, telephone and fax numbers and email address, if any. Camera-ready full papers of accepted proposals will be published in a hard-bound volume by IEEE and distributed at the workshop. Submissions should be sent to: Dr. Jose C. Principe IEEE NNSP'97 444 CSE Bldg #42 P.O. Box 116130 University of Florida Gainesville, FL 32611 Important Dates: * Submission of extended summary: January 27, 1997 * Notification of acceptance: March 31, 1997 * Submission of photo-ready accepted paper: April 26, 1997 * Advanced registration: before July 1, 1997 Further Information Local Organizer Ms. Sharon Bosarge Telephone: 352-392-2585 Fax: 352-392-0044 e-mail: sharon@ee1.ee.ufl.edu World Wide Web http://www.cnel.ufl.edu/nnsp97/ Organization General Chairs Lee Giles (giles@research.nj.nec.com), NEC Research Nelson Morgan (morgan@icsi.berkeley.edu), UC Berkeley Proceeding Chair Elizabeth J. Wilson (bwilson@ed.ray.com), Raytheon Co. Publicity Chair Bert DeVries (bdevries@sarnoff.com), David Sarnoff Research Center Program Chair Jose Principe (principe@synapse.ee.ufl.edu), University of Florida Program Committee Les ATLAS Andrew BACK A. CONSTANTINIDES Federico GIROSI Lars Kai HANSEN Allen GORIN Yu-Hen HU Jenq-Neng HWANG Biing-Hwang JUANG Shigeru KATAGIRI Gary KUHN Sun-Yuan KUNG Richard LIPPMANN John MAKHOUL Elias MANOLAKOS Erkki OJA Tomaso POGGIO Mahesan NIRANJAN Volker TRESP John SORENSEN Takao WATANABE Raymond WATROUS Andreas WEIGEND Christian WELLEKENS About Amelia Island Amelia Island is in the extreme northeast Florida, across the St. Mary's river. The island is just 29 miles from Jacksonville International Airport, which is served by all major airlines. About Amelia Island Plantation Amelia Island Plantation is a 1,250 acre resort/paradise that offers something for every traveler. The Plantation offers 33,000 square feet of workable meeting space and a staff dedicated to providing an efficient, yet relaxed atmosphere. The many amenities of the Plantation include 45 holes of championship golf, 23 Har-Tru tennis courts, modern fitness facilities, an award winning children's program, more than 7 miles of flora-filled bike and jogging trails, 21 swimming pools, diverse accommodations, exquisite dining opportunities, and of course, miles of glistening Atlantic beach front. ------------------------------ From: Knut Moeller Date: Fri, 9 Aug 1996 17:39:20 +0200 (MET DST) Subject: CfParticipation HeKoNN86: Deadline extended There are a limited number of spaces left. Therefore the application deadline was extended. ATTENTION: EXTENDED DEADLINE UNTIL Aug. 31, 1996 CALL FOR PARTICIPATION = = = H e K o N N 9 6 = = = Autumn School in C o n n e c t i o n i s m and N e u r a l N e t w o r k s October 2-6, 1996 Muenster, Germany Conference Language: German ------------------------------ Date: Thu, 25 Jul 1996 00:09:04 +0200 From: Amilcar Cardoso Subject: CfP EPIA'97 (Preliminary) EPIA'97 8th Portuguese Conference on Artificial Intelligence Coimbra, Portugal October 6-9, 1997 Under the auspices of the Portuguese Association for Artificial Intelligence The EPIA'97 Program Committee invites submissions of technical papers for the 8th Portuguese Conference on Artificial Intelligence which is to be held in Coimbra, Portugal, by October 6-9, 1997. As in previous issues ('89, '91, '93 and '95), EPIA'97 will be run as an international conference, English being the official language. The scientific program encompasses tutorials, invited lectures, parallel workshops, and paper presentations. Four well-known researchers will present invited lectures. The conference is devoted to all areas of Artificial Intelligence and will cover both theoretical and foundational issues and applications as well. ********************************************** INVITED LECTURES Francisco Varela (CNRS - France) Luis Moniz Pereira (UNL - Portugal) Orkar Dressler (OCC'M Software GmbH - Germany) Tom Mitchell (CMU - USA) ********************************************** CONTENT AREAS Original papers are solicited in all areas of Artificial Intelligence, including but not limited to: o Agent-Oriented Programming o Automated Reasoning o Artificial Life o Belief Revision o Case-Based Reasoning o Common Sense Reasoning o Constraint Programming o Distributed AI o Expert Systems o Genetic Algorithms o Hybrid Systems o Intelligent Tutoring Systems o Knowledge Representation o Logic Programming o Machine Learning o Model-Based Reasoning o Natural Language Understanding o Neural Networks o Nonmonotonic Reasoning o Planning and Scheduling o Qualitative Reasoning o Robotics o Spatial Reasoning o Temporal Reasoning o Theorem Proving o Theory of Computation TIMETABLE Official call for papers: September 16, 1996 (including technical details for paper submissions) Submission Deadline: March 17, 1997 Notification of Acceptance or Rejection: May 19, 1997 Camera-Ready Copy: June 16, 1997 REVIEW OF PAPERS Submissions will be judged on significance, originality, quality and clarity. Each paper will be cross-reviewed by three referees. Papers will be subject to blind peer review: reviewers will not be aware of the identities of the authors. Submitted papers must report original and previously unpublished work. WORKSHOPS A Call For Workshops Proposals will be available at September 23, 1996. CONFERENCE CO-CHAIRS, PROGRAM CO-CHAIRS Ernesto Costa (ernesto@dei.uc.pt) Amilcar Cardoso (amilcar@dei.uc.pt) Universidade de Coimbra - Portugal PROGRAM COMMITTEE Bernardete Ribeiro (Portugal) Carlos Bento (Portugal) Carlos Pinto-Ferreira (Portugal) Ernesto Morgado (Portugal) Eugenio Oliveira (Portugal) Gabriel Pereira Lopes (Portugal) Helder Araujo (Portugal) Helder Coelho (Portugal) Luis Moniz Pereira (Portugal) Luis Monteiro (Portugal) Manuela Veloso (USA) Miguel Filgueiras (Portugal) Nuno Mamede (Portugal) Oskar Dressler (Germany) Pavel Brazdil (Portugal) Pedro Barahona (Portugal) Ramon de Mantaras (Spain) Rosa Vicari (Brazil) Stuart Shapiro (USA) Takeo Kanade (USA) Xue Mei Wang (USA) LOCAL CHAIR Jose Luis Ferreira (jlf@dei.uc.pt) Universidade de Coimbra - Portugal INQUIRES ADDRESS EPIA'97 Dep. Eng. Informatica Universidade de Coimbra - Polo II Pinhal de Marrocos 3030 Coimbra, Portugal Voice: +351 (39) 7000004 Fax: +351 (39) 701266 Email: epia97@alma.uc.pt URL: http://alma.uc.pt:80/~epia97 OFFICIAL LANGUAGE English ------------------------------ Date: Mon, 5 Aug 1996 13:31:19 -0300 From: " M. Carolina Monard " Subject: 3rd Brazilian Symposium on Neural Networks 3rd Brazilian Symposium on Neural Networks Recife, November 12 - 14, 1996 Sponsored by the Brazilian Computer Society (SBC) Second Call for Papers The Third Brazilian Symposium on Neural Networks will be held at the Federal University of Pernambuco, in Recife (Brazil), from the 12nd to the 14th of November, 1996. The SBRN symposia, as they were initially named, are organized by the interest group in Neural Networks of the Brazilian Computer Society since 1994. The third version of the meeting follows a very successfull organization of the previous events which brought together the main developments of the area in Brazil and had the participation of many national and international researchers both as invited speakers and as authors of papers presented at the symposium. Recife is a very pleasant city (photos) in the northeast of Brazil, known by its good climate and beautiful beaches, with sunshine throughout almost the whole year. The city, whose name originated from the coral formations in the seaside port and beaches, is in a strategic touristic situation in the region and offers a good variety of hotels both in the city historic center and at the seaside resort. Scientific papers will be analyzed by the program committee. This analysis will take into account originality, significance to the area, and clarity. Accepted papers will be fully published in the conference proceedings. MAJOR TOPICS: The major topics of interest include, but are not limited to: * Biological Perspectives * Theoretical Models * Algorithms and Architectures * Learning Models * Hardware Implementation * Signal Processing * Robotics and Control * Parallel and Distributed Implementations * Pattern Recognition * Image Processing * Optimization * Cognitive Science * Hybrid Systems * Dynamic Systems * Genetic Algorithms * Fuzzy Logic * Applications INTERNATIONAL INVITED SPEAKERS: * "Adaptive Wavelets for Pattern Recognition" by Professor Harold Szu , Director of the Center for Advanced Computer Studies, University of Southwestern Louisiana * "Recurrent Neural Networks: El Dorado or Fort Knox?" by Professor C. Lee Giles , NEC Research Institute and University of Maryland, College Park * "Case-based Reasoning and Neural Networks - a Fruitful Breed?" by Professor Agnar Aamodt , Department of Informatics, University of Trondheim - Norway PROGRAM COMMITTEE: (Tentative) * Teresa Bernarda Ludermir - DI/UFPE * Andri C. P. L. F. de Carvalho - ICMSC/USP (Chair) * Germano C. Vasconcelos - DI/UFPE * Anttnio de Padua Braga - DELT/UFMG * Dmbio Leandro Borges - CEFET/PR * Paulo Martins Engel - II/UFRGS * Ricardo Machado - PUC/Rio * Valmir Barbosa - COPPE/UFRJ * Weber Martins - EEE/UFG ORGANISING COMMITTEE: * Teresa Bernarda Ludermir - DI/UFPE (Chair) * Edson Costa de Barros Carvalho Filho - DI/UFPE * Germano C. Vasconcelos - DI/UFPE * Paulo Jorge Leitco Adeodato - DI/UFPE SUBMISSION PROCEDURE: The symposium seeks contributions to the state of the art and future perspectives of Neural Networks research. Submitted papers must be in Portuguese, English or Spanish. The submissions must include the original and three copies of the paper and must follow the format below (Electronic mail and FAX submissions are NOT accepted). The paper must be printed using a laser printer, in two-column format, not numbered, 8.5 X 11.0 inch (21,7 X 28.0 cm). It must not exceed eight pages, including all figures and diagrams. The font size should be 10 pts, such as Times-Roman or equivalent, with the following margins: right and left 2.5 cm, top 3.5 cm, and bottom 2.0 cm. The first page should contain the paper's title, the complete author(s) name(s), affiliation(s), and mailing address(es), followed by a short (150 words) abstract and a list of descriptive key words. The submission should also include an accompanying letter containing the following information : * Manuscript title * First author's name, mailing address and e-mail * Technical area of the paper Authors may use the Latex files sbrn.tex and sbrn.sty for preparing their manuscripts. The postscript file sbrn.ps is also available. Alternately, all those files, together with an equivalent file in WORD, can be retrieved by anonymous ftp following the instructions given below : ftp ftp.di.ufpe.br (LOGIN :) anonymous (PASSWORD :) (your email address) cd pub/events/IIISBRN bin get sbrn.tex (or sbrn.doc) get sbrn.sty bye SUBMISSION ADDRESS: Four copies (one original and three copies) must be submitted to: Prof. Andri Carlos Ponce de Leon Ferreira de Carvalho Coordenador do Comitj de Programa - III SBRN Departamento de Cijncias de Computagco e Estatmstica ICMSC - Universidade de Sco Paulo Caixa Postal 668 CEP 13560.070 Sco Carlos, SP Phone: +55 162 726222 FAX: +55 162 749150 E-mail: IIISBRN@di.ufpe.br IMPORTANT DATES: August 16, 1996 (mailing date): Deadline for paper submission September 16, 1996 : Notification of acceptance/rejection November, 12-14 1996 : III SBRN ADDITIONAL INFORMATION: * Up-to-minute information about the symposium is available on the World Wide Web (WWW) at http://www.di.ufpe.br/~IIISBRN/web_sbrn * Questions can be sent by E-mail to IIISBRN@di.ufpe.br Profa. Teresa Bernarda Ludermir Coordenadora Geral do III SBRN Laboratory of Intelligent Computing (LCI) Departamento de Informatica Universidade Federal de Pernambuco Caixa Postal 7851 CEP 50.732-970 Recife-PE Fone : +55 81 271-8430 FAX: +55 81 271-8438 E-mail: IIISBRN@di.ufpe.br We look forward to seeing you in Recife ! ------------------------------ Date: Thu, 8 Aug 1996 12:14:26 +0100 From: jjh Subject: Workshop on IMMUNITY-BASED SYSTEMS ICMAS Workshop on IMMUNITY-BASED SYSTEMS **************************************** ICMAS Workshop on Immunity-Based Systems will be held on December 10, Keihanna Plaza, Kyoto, Japan; in conjunction with Second International Conference on Multiagent Systems ICMAS '96 December 10 (Tue) - 13 (Fri), 1996 DESCRIPTION ~~~~~~~~~~~ Biologically inspired approach has been paid attention. Recently, the immune system have provided an important paradigm in adaptive complex systems, autonomous decentralized systems and multiagent systems. The immunity-based system consisting of agents may have adaptation and learning capability, similar to neural networks, but it is based on dynamic cooperation of agents. The immunity-based system may have an evolutionary mechanism similar to genetic algorithm, but it has a sophisticated control of diversity and specificity of populations. Although many immunity-based systems have been proposed and studied, it seems there is no agreement yet on the common and important element of immunity-based systems. It is the time for researchers from many fields to define and clarify the immunity-based systems, study the immunity-based models and explore the possible applications. Specific topics of interest include but not limited to: * Immunity-based system as a multiagent system * Multiagent approach for modeling and simulating immune systems * Immunity-based systems for self-diagnosis and self-organization * Immunity-based approach for collective intelligence * Immunity-based systems for optimization and search * The immune system as a prototype of Autonomous Decentralized Systems * Immunity-based approach for Artificial Life * Immunity-based approach for security of information systems * Immunological approach against computer viruses and internet worms * The immune system as a metaphor for computer based learning systems * Immunity-based systems as a distributed learning system SUBMISSION INFORMATION ~~~~~~~~~~~~~~~~~~~~~~ Persons wishing to make presentations at the workshop should submit papers (up to 12 pages, 12pt font, single column). Papers must include in the first page: the title, author's name(s), affiliation, mailing address, phone number, fax number, e-mail, an abstract of 300 words maximum and up to five keywords. Four copies should be sent to the workshop chair. Attendees are required to register for the main ICMAS 96 conference. TIMETABLE ~~~~~~~~~ October 1, 1996 Submission deadline. November 1, 1996 Submitters will be informed of decisions December 10, 1996 Workshop ORGANIZING COMMITTEE (in Alphabetical Order) Hugues Bersini (Universite Libre de Bruxelles, Belgium) Hiroyuki Fujita (University of Tokyo, Japan) Toyoo Fukuda (Kansei Gakuin University, Japan) John Hunt (University of Wales, United Kingdom) Yoshiteru Ishida (Nara Institute of Science and Technology, Japan) Akio Ishiguro (Nagoya University, Japan) Kazuyuki Mori (Mitsubishi Electric Corporation, Japan) WORKSHOP CHAIR Yoshiteru ISHIDA Graduate School of Information Science,Nara Institute of Science and Technology 8916-5 Takayama, Ikoma, Nara 630-01, Japan Voice:+81-7437-2-5351 Fax:+81-7437-2-5359 Email:ishida@is.aist-nara.ac.jp Updated version of this CFP can be seen at: http://genesis.aist-nara.ac.jp/IMBS96.html ================================================================= Dr. John Hunt Email: jjh@aber.ac.uk Centre for Intelligent Systems, Tel: [+44] (0)1970-622537 Department of Computer Science, Fax: [+44] (0)1970-622455 University of Wales, Aberystwyth, WWW: http://www.aber.ac.uk/~jjh Dyfed, SY23 3DB, United Kingdom ------------------------------ End of ML-LIST (Digest format) **************************************** From twilson@afit.af.mil Fri Aug 16 23:48:21 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 XAA12651 for ; Fri, 16 Aug 1996 23:48:15 -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 XAA00745 for ; Fri, 16 Aug 1996 23:48:13 -0500 Received: by TELNET-1.SRV.CS.CMU.EDU id aa27474; 17 Aug 96 0:11:03 EDT Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa26906; 16 Aug 96 19:12:04 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa26903; 16 Aug 96 18:54:02 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa11331; 16 Aug 96 13:12:21 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa02114; 16 Aug 96 13:11:12 EDT Received: from [129.92.2.1] by CS.CMU.EDU id aa08311; 16 Aug 96 13:11:01 EDT Received: from hawkeye.afit.af.mil (moss.afit.af.mil [129.92.100.150]) by stealth.afit.af.mil (8.7.5/8.7.3) with ESMTP id NAA04773 for ; Fri, 16 Aug 1996 13:10:48 -0400 (EDT) Received: from euclid.afit.af.mil (euclid.afit.af.mil [129.92.141.26]) by hawkeye.afit.af.mil (8.6.12/8.6.12) with SMTP id NAA24579 for ; Fri, 16 Aug 1996 13:10:48 -0400 Received: by euclid.afit.af.mil (NX5.67f2/NX3.0S) id AA05694; Fri, 16 Aug 96 13:15:28 -0400 Message-Id: <9608161715.AA05694@euclid.afit.af.mil> Content-Type: text/plain Mime-Version: 1.0 (NeXT Mail 3.3risc v118.3) Received: by NeXT.Mailer (1.118.3) From: Terry Wilson Date: Fri, 16 Aug 96 13:15:25 -0400 To: Connectionists@cs.cmu.edu Subject: call for papers Applications and Science of Artificial Neural Networks ****************************************************** Call for Papers and Announcement Applications and Science of Artificial Neural Networks Part of SPIE's 1997 International Symposium on Aerospace/Defense Sensing and Controls 21-25 April 1997 Marriott's Orlando World Center Resort and Convention Center (Orlando, Florida USA) The focus of this conference is on real-world applications of artificial neural networks and on recent theoretical developments applicable to current applications. The goal of this conference is to provide a forum for interaction between researchers and industrial/government agencies with information processing requirements. Papers that investigate advantages/disadvantages of artificial neural networks in specific real-world applications will be presented. Papers that clearly state existing problems in information processing that could potentially be solved by artificial neural networks will also be considered. Sessions will concentrate on: --- innovative applications of artificial neural networks to solve real-world problems --- comparative performance in applications of target recognition, object recognition, speech processing, speaker identification, speaker normalization, cochannel processing, signal processing in realistic environments, robotics, process control, and image processing --- demonstrations of properties and limitations of existing or new artificial neural networks as shown by or related to an application --- hardware implementation technologies that are either general purpose or application specific --- knowledge acquisition and representation --- biologically inspired visual representation techniques --- decision support systems --- artificial life --- cognitive science --- hybrid systems (fuzzy, neural, genetic) --- neurobiology --- optimization --- sensation and perception --- system identification --- financial applications --- time series analysis and prediction --- pattern recognition --- medical applications --- intelligent control --- robotics --- information warfare applications --- sensation, perception and cognitive neuropsychology. Conference Chair: - Steven K. Rogers, Air Force Institute of Technology Program Committee: - Stanley C. Ahalt, The Ohio State Univ.; - John Franco Basti, Pontifical Gregorian Univ.; - James C. Bezdek, Univ. of West Florida; - Joe R. Brown, Berkom USA; - John Colombi, Dept. of Defense; - Laurene V. Fausett, Florida Institute of Technology; - Michael Georgiopoulos, Univ. of Central Florida; - Joydeep Ghosh, Univ. of Texas/Austin; - Charles W. Glover, Oak Ridge National Lab.; - John B. Hampshire II, Jet Propulsion Lab.; - Richard P. Lippmann, MIT Lincoln Lab.; - Murali Menon, MIT/Lincoln Lab.; - Harley R. Myler, Univ. of Central Florida; - Mary Lou Padgett, Auburn Univ.; - Kevin L. Priddy, Accurate Automation Corp.; - Dennis W. Ruck, Information Warfare Ctr.; - Gregory L. Tarr, Air Force Phillips Lab.; - Gary Whittington, Global Web Ltd.; - Rodney G. Winter, Dept of Defense; - Yinglin Yu, South China Univ. IMPORTANT DATES: Abstract Due Date: 9 September 1996 Manuscript Due Date: 24 January 1997 Proceedings of this conference will be published and available at the symposium. ADDITIONAL INFORMATION: * Up-to-minute information about the conference is available on the World Wide Web (WWW) at http://www.afit.af.mil/Schools/EN/ENG/LABS/PatternRec/aero97.html * Questions can be sent by E-mail to rogers@afit.af.mil