From erol@ee.duke.edu Thu Feb 1 09:42:44 1996 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 1 Feb 96 09:42:29 -0600; AB01269 Received: from bilby.cs.uwa.oz.au by lucy.cs.wisc.edu; Thu, 1 Feb 96 05:35:00 -0600 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 KAA06019; Thu, 1 Feb 1996 10:24:23 +0800 Message-Id: <199602010224.KAA06019@cs.uwa.oz.au> From: Erol Gelenbe Subject: BIOLOGICALLY INSPIRED AUTONOMOUS SYSTEMS To: muehlenbein@gmd.de Cc: cogneuro@ptolemy-ethernet.arc.nasa.gov, cogni-info@univ-lyon1.fr, cogpsy@phil.ruu.nl, cogpsych@ripken.oit.unc.edu, comp-math@bbn.com, comp-neuro@smaug.bbb.caltech.edu, connectionists@cs.cmu.edu, cvnet@skivs.ski.org, cybsys-l@bingvaxu.cc.binghamton.edu, eyemov-l@spcvxa.spc.edu, inns-l%umdd.bitnet@pucc.princeton.edu, intcon@phoenix.ee.unsw.edu.au, mark.ring@gmd.de, ml@ics.uci.edu, mpsych-l@brownvm.brown.edu, neuro-evolution@cse.ogi.edu, neuron@cattell.psych.upenn.edu, neuronet@tutkie.tut.ac.jp, psyc@pucc.princeton.edu, psygrd-j@acadvm1.uottawa.ca, reinforce@cs.uwa.edu.au, simulation@bikini.cis.ufl.edu, vision-list@teleosresearch.com Date: Wed, 31 Jan 1996 11:40:17 -0500 (EST) BIOLOGICALLY INSPIRED AUTONOMOUS SYSTEMS Computation, Cognition and Control Duke University -- March 4 and 5, 1996 Departments of Electrical and Computer Engineering, Psychology Experimental, Biomedical Engineering, Neurobiology, and NSF-ERC Preliminary Program March 4 -- 8:00- 8:45 Registration 8:45- 9:00 Erol Gelenbe and Nestor Schmajuk -- Welcome 9:00- 9:30 Jean-Arcady Meyer (ENS, Paris) >From Natural to Artificial Life 9:30- 10:00 Heinz Muehlenbein (GMD, Bonn) Inspiration from Nature vs. Copying nature. Lessons Learned from Genetic Algorithms 10:00- 10:50 Stephen Grossberg (Boston U) Are there Universal Principles of Brain Computation? 10:50-11:30 Discussion and Coffee 11:30-12:00 Anil Nerode (Cornell, Ithaca) Hybrid Systems as a Modelling Substrate for Biological and Cognitive Systems 12:00- 12:30 Daniel Mange (EPFL, Lausanne) Von Neumann Revisited: a Turing Machine with Self-Repair and Self-Reproduction Properties 12:30- 1:30 Lunch Robotics and Autonomous Systems 1:30- 1:50 Lynne Parker (ORNL, Oak Ridge) >From Social Animals to Teams of Cooperating Robots 1:50-2:10 Akira Ito (Kansai Res. Ctr., Kobe) How Selfish Agents Learn to Cooperate 2:10-2:30 Bengt Carlsson (Karlskrona U, Sweden) The War of Attrition Strategy in Multi-Agent Systems 2:30-2:50 Claudio Cesar de Sa (IMA, Brasil) Architecture for a Mobile Agent 2:50-3:10 A.N. Stafylopatis (NTU, Athens) Autonomous Vehicle Navigation Using Evolutionary Reinforcement Learning 3:10-3:30 Jun Tani (Sony, Tokyo) Cognition from Dynamical Systems Perspective: Robot Navigation Learning 3:00-3:30 Discussion and Coffee Mathematical Models 3:30-3:50 Erol Gelenbe (Duke, NC) Genetic Algorithms which Learn 3:50-4:10 Petr Lansky (CTS, Prague University), Jean-Pierre Rospars (INRA) Stochastic Models of the Olfactory System 4:10-4:30 Vladimir Protopopescu (ORNL, Oak Ridge, Tenn.) Learning Algorithms Based on Finite Samples 4:30-5:00 Ivan Havel (CTS, Prague University) Interaction of Processes at Different Time Scales 5:00-5:30 Boris Stilman (Univ. of Colorado, Denver) Linguistic Geometry: A Cognitive Model for Autonomous Agents 7:00 Dinner Second Day: March 5, 1996 Neural Control 9:00- 9:30 Kumpati Narendra (Yale, New Haven) Neural Networks and Control 9:30- 10:00 John G. Taylor (King's College, London) Global Control Systems of the Brain 10:00- 10:30 Paul Werbos (NSF) Brain-like Control 10:30- 11:00 Discussion and Coffee 11:00-11:20 Shahid Habib and Mona Zaghloul (NASA and GWU) Concurrent System Identification and Control 11:30-12:00 Harry Klopf (Wright-Patterson AFB) Drive-Reinforcement Learning and Hierarchical Networks of Control Systems as Models of Nervous System Function 12:00-1:00 Lunch Learning 1:00- 1:20 Nestor Schmajuk (Duke, NC) The Psychology of Robots 1:20- 1:40 John Staddon (Duke, NC) Habituation: A Non-Associative Learning Process 1:40-2:00 David Rubin (Duke, NC) A Biologically Inspired Model of Autobiographical Memory 2:00-2:20 Ugur Halici (METU, Ankara) Reward, Punishment and Expectation in Reinforcement Learning for the RNN 2:20-2:40 Daniel Levine (Univ. of Texas, Arlington) Analyzing the Executive: Modeling the Functions of Prefrontal Subcortical Loops 2:40-3:00 Discussion and Coffee Autonomous Systems 3:00-3:15 E. Koerner, U. Koerner (Honda R \& D, Japan) Selforganization of Semantic Constraints for Knowledge Representation in Autonomous Systems: A Model of the Role of an Emotional System in Brains 3:15-3:30 Tetsuya Higuchi et al. (Tsukuba, Japan) Hardware Evolution at Gate and Function Levels 3:30-3:45 Christopher Landauer (The Aerospace Corp., Virginia) Constructing Autonomous Software Systems 3:45-4:00 Robert E. Smith Combined Biological Paradigms: A Neural, Genetics-Based Autonomous Systems Strategy Vision and Imaging 4:00-4:15 Jonathan Marshall (UNC, NC) Self-organization of Triadic Neural Circuits for Anticipatory Visual Receptive Field Shifts under Intended Eye Movements 4:15-4:30 Didem Gokcay, LiMin Fu (Univ. of Florida, Gainesville) Visualization of Functional Magnetic Resonance Images through Self-Organizing Maps 4:30-4:45 S. Guberman, W. Wojtkowski (Paragraph International, California) DD algorithm and Automated Image Comprehension 4:45-5:00 E. Koerner, U. Koerner (Honda R \& D, Japan) Neocortex-like Neural Network Architecture for Autonomous Image Understanding 5:00-5:15 E. Oztop (METU, Ankara) Baseline Extraction on Document Images by Repulsive/Attractive Network 5:15-5:30 Y. Feng, E. Gelenbe (Duke, NC) Detecting Faint Targets in Strong Clutter: A Neural Approach Networking Applications 5:30-5:45 Christopher Cramer et al. (Duke, NC) Adaptive Neural Video Compression 5:45-6:00 Thomas John, Scott Toborg (Southwestern Bel, Austin, Texas) Neural Network Techniques for Fault and Performance Diagnosis of Broadband Networks 6:15-6:30 Philippe de Wilde (Imperial College, London) Equilibria of a Communication Network 6:30-6:45 Jonathan W. Mills (Indiana University) Implementing the McCulloch-Kilmer RETIC Architecture with an Analog VLSI Neural Field Computer End of the Workshop ------------------------------------------------------------------ For further information contact: Margrid Krueger Dept. of Electrical and Computer Engineering Duke University email: mak@ee.duke.edu Fax: (919) 660 5293 Tel: (919) 660 5253 From weissg@informatik.tu-muenchen.de Thu Feb 1 09:43:22 1996 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 1 Feb 96 09:43:10 -0600; AA01330 Received: from bilby.cs.uwa.oz.au by lucy.cs.wisc.edu; Thu, 1 Feb 96 02:55:34 -0600 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 KAA06045; Thu, 1 Feb 1996 10:26:11 +0800 Message-Id: <199602010226.KAA06045@cs.uwa.oz.au> From: Gerhard Weiss Sender: Gerhard Weiss To: DAI-List@ece.sc.edu, agentnews-owner@cs.umbc.edu, ckbs-int@cs.keele.ac.uk, maamaw@cosmos.imag.fr, vki-request@dfki.uni-sb.de, reinforce@cs.uwa.edu.au, gi-fgml@gmd.de Subject: CFP: JETAI Special Issue on Learning in DAI Systems Date: Wed, 31 Jan 1996 16:57:28 +0100 (MET) Please announce the following CFP in your mailing list. Thank you very much, Gerhard Weiss. *********************************************************************** C A L L F O R P A P E R S ( http://www7.informatik.tu-muenchen.de/~weissg/si-jetai ) JOURNAL OF EXPERIMENTAL AND THEORETICAL ARTIFICIAL INTELLIGENCE (JETAI) Special Issue on LEARNING IN DISTRIBUTED ARTIFICIAL INTELLIGENCE SYSTEMS Guest Editor: Gerhard Weiss JETAI is an international journal published by Taylor & Francis ( http://turing.pacss.binghamton.edu/jetai/index.html ); Editor-in-Chief: Eric Dietrich, State University of New York, Binghamton Focus and Purpose ----------------- Distributed Artificial Intelligence (DAI) is concerned with the study and design of systems composed of several interacting entities which are logically and often spatially distributed and in some sense can be called intelligent. The two principal types of DAI systems that are usually distinguised are distributed problem solving systems and multi-agent systems. DAI systems typically are very complex and hard to specify in their dynamics and behavior. It is therefore commonly agreed that these systems should be able to learn, that is, to self-improve their performance. For this issue high-quality papers are invited that describe work done at the intersection of Machine Learning and DAI. The focus of this issue is on all aspects of learning in all kinds of DAI systems. The purpose of this issue is to draw together experimental, theoretical, and methodological key research being within this focus. Relevant topics for this issue include, but are not limited to, the following: - concepts and models of learning in DAI systems - requirements for and principles of learning in DAI systems - applicability and limitations of traditional machine learning approaches in the context of DAI systems - parallel and distributed (inductive, multistrategy, etc) learning in DAI systems - learning in DAI systems by knowledge acquisition/discovery/refinement, by advice taking, by negotiation, by observation, etc - relationships between learning on the one hand and communication, cooperation, coordination, etc on the other - self-organization in DAI systems - learning in robot teams - adaptive distributed planning systems - formal models of learning in DAI systems. Papers describing research on learning in DAI systems carried out in other disciplines than AI are also particularly welcome. Submission Information ---------------------- All prospective authors should contact the guest editor (preferably via E-mail) prior to submission and in any case not later than April 7, 1996, in order to discuss contribution ideas and suitablity for this issue. Submissions should be send to the guest editor. For general information on the submission format, consult the inside back cover of a recent JETAI issue or visit JETAI's home page at the URL address provided above. Important Dates --------------- April 7, 1996 contact guest editor November 1, 1996 submission deadline February 16, 1997 notification of acceptance June 1, 1997 final manuscript + send to publisher (issue 9/4 publication) Contact Address --------------- Dr. Gerhard Weiss Institut fuer Informatik Technische Universitaet Muenchen D-80290 Muenchen, Germany Email: weissg@informatik.tu-muenchen.de Tel: +49 89 2105 2407 Fax: +49 89 2105 8207 URL: http://www7.informatik.tu-muenchen.de/~weissg *********************************************************************** From jan@uran.informatik.uni-bonn.de Thu Feb 1 09:47:07 1996 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 1 Feb 96 09:47:04 -0600; AA01853 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 31 Jan 96 21:18:42 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa06087; 31 Jan 96 17:49:26 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa06083; 31 Jan 96 17:35:47 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa07469; 31 Jan 96 17:32:37 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa05119; 31 Jan 96 10:12:41 EST Received: from uran.informatik.uni-bonn.de by CS.CMU.EDU id aa05493; 31 Jan 96 10:12:21 EST Received: from thalia.informatik.uni-bonn.de (jan@thalia.informatik.uni-bonn.de [131.220.10.27]) by uran.informatik.uni-bonn.de (8.7.3-ws3/8.7.1-ws3) with ESMTP id QAA12242 for ; Wed, 31 Jan 1996 16:11:38 +0100 (MET) From: Jan Puzicha Received: (jan@localhost) by thalia.informatik.uni-bonn.de (8.6.9-ws5/8.6.9) id QAA13190 for Connectionists@CS.CMU.EDU; Wed, 31 Jan 1996 16:11:36 +0100 Date: Wed, 31 Jan 1996 16:11:36 +0100 Message-Id: <199601311511.QAA13190@thalia.informatik.uni-bonn.de> To: Connectionists@cs.cmu.edu Subject: Publications and Abstracts available online The following Publications are now available as abstracts and compressed postscript online via the WWW-Home-Page of the Computer Vision and Pattern Recognition Group of the University of Bonn, Germany: http://www-dbv.cs.uni-bonn.de/ This page also contains information about peoble, scientific projects (segmentation, stereo, compression, data clustering, vector quantization, multidimensional scaling, autonomous robotics, associative memories) and new results in textured image segmentation of the group as well as links to related sites, conferences and jounals. Data Clustering J. Buhmann, Data clustering and learning, in Handbook of Brain Theory and Neural Networks, M. Arbib, ed., Bradfort Books/MIT Press, 1995. J. Buhmann, Vector Quantization with Complexity Costs, IEEE Transactions on Information Theory, 39, pp.1133-1145, 1993. J. Buhmann and T. Hofmann, A Maximum Entropy Approach to Pairwise Data Clustering, in Proceedings of the International Conference on Pattern Recognition, Hebrew University, Jerusalem, vol.II, IEEE Computer Society Press, pp.207-212, 1994. J. Buhmann and T. Hofmann, Pairwise data clustering by deterministic Annealing, Tech. Rep. IAI-TR-95-7, Institut fr Informatik III, Universit"at Bonn. T. Hofmann and J. Buhmann, Multidimensional scaling and data clustering, in Advances in Neural Information Processing Systems 7, Morgan Kaufmann Publishers, 1995. T. Hofmann and J. Buhmann, Hierarchical pairwise data clustering by mean-field annealing. ICANN 1995. Robotics J. Buhmann, W. Burgard, A.B. Cremers, D. Fox, T. Hofmann, F. Schneider, J. Strikos and S. Thrun. The Mobile Robot Rhino. AI Magazin, 16:1, 1995. Face Recognition J. Buhmann, M. Lades and F. Eeckmann. Illumination-Invariant Face Recognition with a Contrast Sensitive Silicon Retina. In: Advances in Neural Information Processing Systems (NIPS) 6, Morgan Kaufmann Publishers, pp 769-776, 1994. H. Aurisch, J. Strikos and J. Buhmann. A Real-Time Face Recognition System with a Retina camera. Internal report, summerizes the results of our face regognition research accomplished in summer 1993. Associative Memories J. Buhmann, Oscillatory Associative Memories, in Handbook of Brain Theory & Neural Networks, M. Arbib (ed.), Bradfort Books, MIT Press, 1995. Greeting Jan Puzicha -------------------------------------------------------------------- Jan Puzicha | email: jan@uran.cs.uni-bonn.de Institute f. Informatics III | jan@cs.uni-bonn.de University of Bonn | WWW : http://www.cs.uni-bonn.de/~jan | Roemerstrasse 164 | Tel. : +49 228 550-383 D-53117 Bonn | Fax : +49 228 550-382 From moody@chianti.cse.ogi.edu Thu Feb 1 12:19:10 1996 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 1 Feb 96 12:19:02 -0600; AA05424 Received: from bilby.cs.uwa.oz.au by lucy.cs.wisc.edu; Thu, 1 Feb 96 12:18:58 -0600 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 TAA16675; Thu, 1 Feb 1996 19:16:12 +0800 Message-Id: <199602011116.TAA16675@cs.uwa.oz.au> From: John Moody To: connectionists@cs.cmu.edu, ml@ics.uci.edu, Reinforce@cs.uwa.edu.au, gannout@cs.iastate.edu, corryfee%hasara11.BITNET@bitnet.mailgate.cs.mu.oz.au, csemlist%hasara11.BITNET@bitnet.mailgate.cs.mu.oz.au, nonlin-l@list.nih.gov, comp-finance@teleport.com Cc: moody@cs.uwa.oz.au, yaser@cs.caltech.edu Subject: CFP: NEURAL NETWORKS in the CAPITAL MARKETS 1996 Date: Wed, 31 Jan 96 19:27:19 -0800 -- Preliminary Announcement and Call for Papers -- NNCM-96 FOURTH INTERNATIONAL CONFERENCE NEURAL NETWORKS in the CAPITAL MARKETS Wednesday-Friday, November 20-22, 1996 The Ritz-Carlton Hotel, Pasadena, California, U.S.A. Sponsored by Caltech and London Business School Neural networks have been applied to a number of live systems in the capital markets, and in many cases have demonstrated better performance than competing approaches. Because of the increasing interest in the NNCM conferences held in the U.K. and the U.S., the fourth annual NNCM is planned for November 20-22, 1996, in Pasadena, California. This is a research meeting where original and significant contributions to the field are presented. In addition, introductory tutorials will be included to familiarize audiences of different backgrounds with the financial and the mathematical aspects of the field. Areas of Interest: Price forecasting for stocks, bonds, commodities, and foreign exchange; asset allocation and risk management; volatility analysis and pricing of derivatives; cointegration, correlation, and multivariate data analysis; credit assessment and economic forecasting; statistical methods, learning techniques, and hybrid systems. Organizing Committee: Dr. Y. Abu-Mostafa, Caltech (Chairman) Dr. A. Atiya, Cairo University Dr. N. Biggs, London School of Economics Dr. D. Bunn, London Business School Dr. M. Jabri, Sydney University Dr. B. LeBaron, University of Wisconsin Dr. A. Lo, MIT Sloan School Dr. I. Matsuba, Chiba University Dr. J. Moody, Oregon Graduate Institute Dr. C. Pedreira, Catholic Univ. PUC-Rio Dr. A. Refenes, London Business School Dr. M. Steiner, Universitaet Munster Dr. A. Timermann, UC San Diego Dr. A. Weigend, University of Colorado Dr. H. White, UC San Diego Dr. L. Xu, Chinese University of Hong Kong Submission of Papers: Original contributions representing new and significant research, development, and applications in the above areas of interest are invited. Authors should send 5 copies of a 1000-word summary clearly stating their results to Dr. Y. Abu-Mostafa, Caltech 136-93, Pasadena, CA 91125, U.S.A. All submissions must be received before May 1, 1996. There will be a rigorous refereeing process to select the high-quality papers to be presented at the conference. Location: The conference will be held at the Ritz-Carlton Huntington Hotel in Pasadena, within two miles from the Caltech campus. The hotel is a 35-minute drive from Los Angeles International Airport (LAX) with nonstop flights from most major cities in North America, Europe, the Far East, Australia, and South America. Mailing List: If you wish to be added to the mailing list of NNCM-96, please send your postal address, e-mail address, and fax number to Dr. Y. Abu-Mostafa, Caltech 136-93, Pasadena, CA 91125, U.S.A. e-mail: yaser@caltech.edu , fax (818) 795-0326 Home Page: http://www.cs.caltech.edu/~learn/nncm.html From moody@chianti.cse.ogi.edu Thu Feb 1 13:31:16 1996 Received: from cs.wisc.edu by sea.cs.wisc.edu; Thu, 1 Feb 96 13:30:54 -0600; AA07405 Received: from bilby.cs.uwa.oz.au by cs.wisc.edu; Thu, 1 Feb 96 13:30:22 -0600 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 TAA16632; Thu, 1 Feb 1996 19:14:32 +0800 Message-Id: <199602011114.TAA16632@cs.uwa.oz.au> From: John Moody To: connectionists@cs.cmu.edu, Vision-List-Request@TELEOS.COM, ml@ics.uci.edu, Reinforce@cs.uwa.edu.au, gannout@cs.iastate.edu, corryfee%hasara11.BITNET@bitnet.mailgate.cs.mu.oz.au, csemlist%hasara11.BITNET@bitnet.mailgate.cs.mu.oz.au, nonlin-l@list.nih.gov, comp-finance@teleport.com Cc: moody@cs.uwa.oz.au Subject: Graduate Study at the Oregon Graduate Institute Date: Wed, 31 Jan 96 18:45:49 -0800 OGI (Oregon Graduate Institute of Science and Technology) has openings for a few outstanding students in its Computer Science and Electrical Engineering Masters and Ph.D programs in the areas of Neural Networks, Learning, Signal Processing, Time Series, Control, Speech, Language, Vision, and Computational Finance. OGI has 14 faculty, senior research staff, and postdocs in these areas. Short descriptions of our research interests are appended below. The primary purposes of this message are: 1) To invite inquiries and applications from prospective students interested in studying for a Masters or PhD Degree in the above areas. 2) To notify prospective PhD students who are U.S. Citizens or U.S. Nationals of various fellowship opportunities at OGI. Fellowships provide full or partial financial support while studying for the PhD. OGI is a young, but rapidly growing, private research institute located in the Silicon Forest area west of downtown Portland, Oregon. OGI offers Masters and PhD programs in Computer Science and Engineering, Electrical Engineering, Applied Physics, Materials Science and Engineering, Environmental Science and Engineering, Chemistry, Biochemistry, Molecular Biology, and Management. The Portland area has a high concentration of high tech companies that includes major firms like Intel, Hewlett Packard, Tektronix, Sequent Computer, Mentor Graphics, Wacker Siltronics, and numerous smaller companies like Planar Systems, FLIR Systems, Flight Dynamics, and Adaptive Solutions (an OGI spin-off that manufactures high performance parallel computers for neural network and signal processing applications). The admissions deadline for the OGI PhD programs is March 1. Masters program applications are accepted year-round. Inquiries about these programs and admissions for either Computer Science or Electrical Engineering should be addressed to: Office of Admissions and Records Oregon Graduate Institute PO Box 91000 Portland, OR 97291 Phone: (503)690-1028, or (800)685-2423 (toll-free in the US and Canada) Worldwide Web: http://www.ogi.edu/webtest/admissions.html Internet: admissions@admin.ogi.edu Due to the late time in the PhD applications season, though, informal applications should be sent directly to the CSE Department. For these informal applications, please include a letter specifying your research interests, photocopies of your GRE Scores, TOEFL Scores, and College transcripts, and indicate your interest in either the PhD or Masters programs. Please send these materials to: Betty Shannon, Academic Coordinator Department of Computer Science and Engineering Oregon Graduate Institute PO Box 91000 Portland, OR 97291-1000 Phone: (503)690-1255 Internet: bettys@cse.ogi.edu +++++++++++++++++++++++++++++++++++++++++++++++++++++++ Oregon Graduate Institute of Science & Technology Department of Computer Science and Engineering & Department of Electrical Engineering and Applied Physics Research Interests of Faculty, Research Staff, and Postdocs in Neural Networks, Signal Processing, Control, Speech, Language, Vision, Time Series, and Computational Finance (Note: Additional information is available on the Web at http://www.ogi.edu/ ) Etienne Barnard (Associate Professor, EEAP): Etienne Barnard is interested in the theory, design and implementation of pattern-recognition systems, classifiers, and neural networks. He is also interested in adaptive control systems -- specifically, the design of near-optimal controllers for real- world problems such as robotics. Ron Cole (Professor, CSE): Ron Cole is director of the Center for Spoken Language Understanding at OGI. Research in the Center currently focuses on speaker- independent recognition of continuous speech over the telephone and automatic language identification for English and ten other languages. The approach combines knowledge of hearing, speech perception, acoustic phonetics, prosody and linguistics with neural networks to produce systems that work in the real world. Mark Fanty (Research Assistant Professor, CSE): Mark Fanty's research interests include continuous speech recognition for the telephone; natural language and dialog for spoken language systems; neural networks for speech recognition; and voice control of computers. Dan Hammerstrom (Associate Professor, CSE): Based on research performed at the Institute, Dan Hammerstrom and several of his students have spun out a company, Adaptive Solutions Inc., which is creating massively parallel computer hardware for the acceleration of neural network and pattern recognition applications. There are close ties between OGI and Adaptive Solutions. Dan is still on the faculty of the Oregon Graduate Institute and continues to study next generation VLSI neurocomputer architectures. Hynek Hermansky (Associate Professor, EEAP); Hynek Hermansky is interested in speech processing by humans and machines with engineering applications in speech and speaker recognition, speech coding, enhancement, and synthesis. His main research interest is in practical engineering models of human information processing. Todd K. Leen (Associate Professor, CSE): Todd Leen's research spans theory of neural network models, architecture and algorithm design and applications to speech recognition. His theoretical work is currently focused on the foundations of stochastic learning, while his work on Algorithm design is focused on fast algorithms for non-linear data modeling. John Moody (Associate Professor, CSE): John Moody does research on the design and analysis of learning algorithms, statistical learning theory (including generalization and model selection), optimization methods (both deterministic and stochastic), and applications to signal processing, time series, economics, and computational finance. David Novick (Associate Professor, CSE): David Novick conducts research in interactive systems, including computational models of conversation, technologically mediated communication, and human-computer interaction. A central theme of this research is the role of meta-acts in the control of interaction. Current projects include dialogue models for telephone-based information systems. Misha Pavel (Associate Professor, EEAP): Misha Pavel does mathematical and neural modeling of adaptive behaviors including visual processing, pattern recognition, visually guided motor control, categorization, and decision making. He is also interested in the application of these models to sensor fusion, visually guided vehicular control, and human-computer interfaces. Hong Pi (Senior Research Associate, CSE) Hong Pi's research interests include neural network models, time series analysis, and dynamical systems theory. He currently works on the applications of nonlinear modeling and analysis techniques to time series prediction problems and financial market analysis. Thorsteinn S. Rognvaldsson (Post-Doctoral Research Associate, CSE): Thorsteinn Rognvaldsson studies both applications and theory of neural networks and other non-linear methods for function fitting and classification. He is currently working on methods for choosing regularization parameters and also comparing the performance of neural networks with the performance of other techniques for time series prediction and financial markets. Pieter Vermeulen (Senior Research Associate, CSE): Pieter Vermeulen is interested in the theory, design and implementation of pattern-recognition systems, neural networks and telephone based speech systems. He currently works on the realization of speaker independent, small vocabulary interfaces to the public telephone network. Current projects include voice dialing, a system to collect the year 2000 census information and the rapid prototyping of such systems. Eric A. Wan (Assistant Professor, EEAP): Eric Wan's research interests include learning algorithms and architectures for neural networks and adaptive signal processing. He is particularly interested in neural applications to time series prediction, adaptive control, active noise cancellation, and telecommunications. Lizhong Wu (Senior Research Associate, CSE): Lizhong Wu's research interests include neural network theory and modeling, time series analysis and prediction, pattern classification and recognition, signal processing, vector quantization, source coding and data compression. He is now working on the application of neural networks and nonparametric statistical paradigms to finance. From chentouf@kepler.inpg.fr Thu Feb 1 17:12:16 1996 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 1 Feb 96 17:12:12 -0600; AA12817 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Thu, 1 Feb 96 17:12:08 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa06076; 31 Jan 96 17:41:43 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa06074; 31 Jan 96 17:31:10 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa07451; 31 Jan 96 17:30:21 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id ac03131; 31 Jan 96 7:21:28 EST Received: from adminpg.inpg.fr by EDRC.CMU.EDU id aa06963; 31 Jan 96 6:44:45 EST Received: from kepler.inpg.fr (kepler.inpg.fr [192.70.29.43]) by adminpg.inpg.fr (8.6.11/8.6.11) with ESMTP id MAA04868 for ; Wed, 31 Jan 1996 12:38:48 +0100 Received: (from chentouf@localhost) by kepler.inpg.fr (8.6.11/8.6.11) id MAA00665 for connectionists@cs.cmu.edu; Wed, 31 Jan 1996 12:44:33 +0100 Date: Wed, 31 Jan 1996 12:44:33 +0100 From: rachida Message-Id: <199601311144.MAA00665@kepler.inpg.fr> To: connectionists@cs.cmu.edu Subject: new paper available "Combining Sigmoids and RBFs" The following paper: Combining Sigmoids and Radial Basis Functions in Evolutive Neural Architectures. is available at: ftp://tirf.inpg.fr/pub/HTML/chentouf/esann96_chentouf.ps.gz ABSTRACT An incremental algorithm for supervised learning of noisy data using two layers neural networks with linear output units and a mixture of sigmoids and radial basis functions in the hidden layer (2-[S,RBF]NN) is proposed. Each time the network has to be extended, we compare different estimations of the residual error: the one provided by a sigmoidal unit responding to the overall input space, and those provided by a number of RBFs responding to localized regions. The unit which provides the best estimation is selected and installed in the existing network. The procedure is repeated until the error reduces to the noise in the data. Experimental results show that the incremental algorithm using 2-[S,RBF]NN is considerably faster than the one using only sigmoidal hidden units. It also leads to a less complex final network and avoids being trapped in spurious minima. ========= This paper has been accepted for publication in the European Symposium on Artificial Neural Networks, Bruges, Belgium , April, 96. __ ______ __ ________ _______ __ __ __ ________ ______ / / /_ __/ / / / ____ / / _____/ / // /\ / // ____ // ____/ / / / / / / / /___/ / / /___ ____ / // /\ \ / // /___/ // / ____ / /_____ / / / / / ___/ / _____/ /___/ / // / \ \/ // /_____// /_/ __/ /_______/ /_/ /_/ /_/\__\ /_/ /_//_/ \_\//_/ /_____/ -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= || Mrs Rachida CHENTOUF || || LTIRF-INPG || || 46, AV Felix Viallet || || 38031 Grenoble - FRANCE || || Tel : (+33) 76.57.43.64 || || Fax : (+33) 76.57.47.90 || || || || WWW: ftp://tirf.inpg.fr/pub/HTML/chentouf/rachida.html || -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= From joerg@informatik.uni-kl.de Fri Feb 2 04:54:47 1996 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 2 Feb 96 04:54:43 -0600; AB04802 Received: from bilby.cs.uwa.oz.au by lucy.cs.wisc.edu; Fri, 2 Feb 96 04:54:27 -0600 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 LAA07221; Fri, 2 Feb 1996 11:48:03 +0800 Message-Id: <199602020348.LAA07221@cs.uwa.oz.au> From: joerg@informatik.uni-kl.de To: reinforce@cs.uwa.edu.au Subject: EUROBOT '96 - 2nd Call for Papers Date: Thu, 1 Feb 96 17:18:23 +0100 Dear Colleague, please distribute the information on Eurobot '96 to prospective authors and potential participants of the workshop. Best regards Klaus Werner Joerg PS I apologize if you receive this note more than once. Please let me know if that happens, or if you wish to be taken off this mailing list. ---------------------------------------------------------------------------- EUROBOT '96 1st EUROMICRO WORKSHOP ON ADVANCED MOBILE ROBOTS Kaiserslautern, Germany October 9-11th, 1996 CALL FOR PAPERS Robotics has undergone a profound transformation during the past decade. Many robotics researcher who started their work on industrial manipulators have now progressed to more advanced robots, particularly to Mobile robots which are often intended for use outside the manufacturing arena. While methods developed for industrial manipulators are being transferred to the field of advanced robots, it is also recognised that these methods cannot alone fulfil the needs of machines designed to perform useful and complex tasks in poorly known environments. To meet these needs, connections with other computer- and non- computer science disciplines, such as real-time computing, connectionist architectures, artificial intelligence, psicology, neuro-physiology are being established. This massive research effort has led to many interesting scientific results and the large number of big conferences being held world-wide demonstrates the importance of the field. However, the need for dialogue between researchers working in widely dispersed fields results in a strong demand for narrow- focus, high-level workshops. EUROBOT, in 1996 at its first issue, aims to establish an international open forum for the discussion of up-to-date topics related to advanced mobile robots. The workshop will be held annually at different European locations. To keep disussions focused, papers to be presented should concentrate on a particular topic which will be selected an a yearly basis. This policy, which is derived from the one foolwed by the other EUROMICRO workshops, has proven valid, allowing fruitful discussions on outstanding research topics. The central topic of EUROBOT '96 is "Perception in mobile robots". Within this topic, many subjects can be perceived, such as advanced self localisation techniques, non-traditional sensors, sensor data fusion, world modelling, sensor planning, connectionnnist approaches, symbolic and sub-symbolic reasoning, etc. SUBMISSION OF PAPERS Prospective authors are encouraged to send a PostScript version of their full paper (not exceeding 4000 words in length and including a 150-200 word abstract) by anonymous ftp to ftp.ing.unibs.it and put it in the eurobot directory. In addition, they should send by e-mail to cassinis@bsing.ing.unibs.it the title of the paper, full names, affiliations, postal and e-mail addresses, fax and telephone numbers. Alternatively, they can send the paper by postal mail. In this case, they should send 5 copies of all the above items to the program chairman. The following information should be included in the submission: All necessary clearances have been obtained for the publication of this paper. If accepted, the author(s) will prepare the final camera-ready manuscript in time for inclusion in the proceedings, and will personally present the paper at the workshop. The closing date for submissions is March 1st, 1996. Authors will be notified of acceptance by May 15th, 1996. Camera-ready versions will be required by June 30th,1996. The proceedings will be published by IEEE Computer Society. SPECIAL SESSIONS Sessions on special topics proposed by delegates will be welcome. Please send suggestions to the program chairman before the closing date for submissions. REFERENCE ADDRESSES General Chairman: Klaus Werner Joerg University of Kaiserslautern Robotics Research Group P.O. Box 3049 D-67653 Kaiserslautern, Germany Phone: +49-631-205 2621 Fax: +49-631-205 2803 e-mail: joerg@informatik.uni-kl.de Deputy General Chairman: Ewald von Puttkamer University of Kaiserslautern Robotics Research Group P.O. Box 3049 D-67653 Kaiserslautern, Germany Phone: +49-631-205 2276 Fax: +49-631-205 2803 e-mail: puttkam@informatik.uni-kl.de Program Chairman: Riccardo Cassinis University of Brescia Dept. of Electronics for Automation Via Branze, 38 I-25123 Brescia, Italy Phone: +39-30-3715.453 Fax: +39-30-380014 e-mail: cassinis@bsing.ing.unibs.it Deputy Program Chairman: Enrico Pagello LADSEB - CNR C.so Stati Uniti,4 I-35100 Padova, Italy Phone: +39-49-829.5784 Fax: +39-49-8295649 e-mail: pagello@ladseb.pd.cnr.it Euromicro Manager: Chiquita Snippe-Marlisa P.O. Box 2346 7301 EA Apeldoorn, The Netherlands Tel. +31 - 55 355 73 72 Fax +31 - 55 355 73 93 e-mail chiquita@info.vub.ac.be IMPORTANT DATES Submission of papers Submission of session proposal March 1st, 1996 Notification of Acceptance May 15th, 1996 Camera-ready Papers Due June 30th, 1996 AUTOMATIC INFORMATION Information on the workshop is available through WWW starting from URL http://info.vub.ac.be:8080/euromicro/emhomepg.html GENERAL INFORMATION Kaiserslautern lies in the state of Rhineland-Palatinate and is the economical and cultural centre of the Palatinate. Kaiserslautern's surroundings offer a unique landscape which is part of the "Pfalzerwald Natural Reserve", Germany's largest forrest. In general, the Palatinate has a mild climate - the average temperature in October is approx. 18o Celsius. The eastern part of the area is famous for numerous vineyards and excellent vines. There are a number of attractions to be visited, e.g. Palatinate Gallery of Art, Valley Karlstal, Lichtemberg Castle, River Rhine, Roman Cathedral in Speyer and the world's largest wine barrel, a unique restaurant in Bad Durkheim. For local arrangements and tourist information, please contact Mrs. Claudia Pregernig, Tourist Information Office, Willy Brandt-Platz 1, 67653 Kaiserslautern, Germany, Phone: +49-631-365-4019, Fax: +49-631-365-2723 or the General Chairman. *************************************** Dr. Klaus Werner Joerg University of Kaiserslautern Robotics Research Group P.O. Box 3049 67653 Kaiserslautern Germany Tel. +49 631 205 2621 Fax. +49 631 205 2803 email joerg@uklirb.informatik.uni-kl.de From marks@u.washington.edu Fri Feb 2 11:02:18 1996 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 2 Feb 96 11:02:16 -0600; AA11596 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 2 Feb 96 11:02:12 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa06521; 31 Jan 96 22:09:33 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa06511; 31 Jan 96 22:00:54 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa07871; 31 Jan 96 22:00:37 EST Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa16565; 31 Jan 96 21:11:54 EST Received: from carson.u.washington.edu by RI.CMU.EDU id aa11080; 31 Jan 96 21:11:05 EST Received: by carson.u.washington.edu (5.65+UW96.01/UW-NDC Revision: 2.33 ) id AA19936; Wed, 31 Jan 96 18:11:01 -0800 Date: Wed, 31 Jan 96 18:11:01 -0800 From: Robert Marks Message-Id: <9602010211.AA19936@carson.u.washington.edu> X-Sender: marks@carson.u.washington.edu To: Connectionists@cs.cmu.edu Subject: NNC Home Page Erratum ERRATUM In a previous message, I wrote "the IEEE Neural Networks Council home page (http://www.ieee.org.nnc)" It should be http://www.ieee.org/nnc Robert J. Marks II From janet@psy.uq.oz.au Fri Feb 2 18:16:20 1996 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 2 Feb 96 18:16:17 -0600; AA21348 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 2 Feb 96 18:16:14 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa08117; 1 Feb 96 17:46:06 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa08100; 1 Feb 96 17:19:59 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa08749; 1 Feb 96 17:18:36 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa20563; 1 Feb 96 2:47:25 EST Received: from psych.psy.uq.oz.au by EDRC.CMU.EDU id aa12164; 1 Feb 96 2:46:51 EST Received: (from janet@localhost) by psych.psy.uq.edu.au (8.7.1/8.7.1) id RAA18083; Thu, 1 Feb 1996 17:46:38 +1000 (EST) Date: Thu, 1 Feb 1996 17:46:37 +1000 (EST) From: Janet Wiles To: connectionists@cs.cmu.edu Subject: Cognitive Modelling Workshop (Virtual and Physical) Message-Id: Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII CALL FOR PAPERS We are pleased to announce a COGNITIVE MODELLING WORKSHOP in conjunction with the Australian Conference on Neural Networks (ACNN'96) and the electronic cognitive science journal Noetica This announcement can be accessed on the WWW at URL: http://psy.uq.edu.au/CogPsych/acnn96/cfp.html -------------------------------------------------------------------- Noetica/ACNN'96 Cognitive Modelling Workshop: Call For Papers VIRTUAL WORKSHOP February 1 to March 26, 1996 PHYSICAL WORKSHOP Canberra Australia April 9, 1996 Memory, time, change and structure in ANNs: Distilling cognitive models into their functional components Organisers: Janet Wiles and J. Devin McAuley Departments of Computer Science and Psychology University of Queensland QLD 4072 Australia janet@psy.uq.edu.au devin@psy.uq.edu.au Call For Papers Web Page http://psy.uq.edu.au/CogPsych/acnn96/cfp.html Workshop Web Page http://psy.uq.edu.au/CogPsych/acnn96/workshop.html Aim The Workshop aim is to identify the functional roles of artificial neural network (ANN) components and to understand how they combine to explain cognitive phenomena. Existing ANN models will be distilled into their functional components through case study analysis, targeting three traditional strengths of ANNs - mechanisms for memory, time and change; and one area of weakness - mechanisms for structure (see below for details of these four areas). Workshop Format The Workshop will be held in two parts: a virtual workshop via the World Wide Web followed by the physical workshop at ACNN'96. February - March 1996 (Part 1 - Virtual Workshop): All members of the cognitive modelling and ANN research communities are invited to submit case studies of neural-network-based cognitive models (their own or established models from the literature) and commentaries on the workshop issues and case studies. Submissions judged appropriate for the workshop will be posted to the Workshop Web Page as they arrive, and will be collated into a Special Issue of the electronic journal Noetica. Multiple case studies of an ANN model may be accepted if they address different cognitive phenomena. It is OK to participate in the virtual workshop without attending the physical workshop. April 9, 1996 (Part 2 - Physical Workshop): A physical workshop will be held as part of the 1996 Australian Conference on Neural Networks (ACNN'96) in Canberra Australia. At the workshop, the collection of case studies and commentaries will be available in hard copy form. The physical workshop will be 90 minutes long, beginning with an introduction (review of the issues); then presentation of submitted and invited Case Studies; and closing with a discussion of what's missing from the list of available mechanisms. A summary of the issues raised in the discussion will be compiled afterwards, and made available via the workshop web page. Further details on presentations will be announced closer to the date of the workshop. Rationale For many ANN models of cognitive phenomena, interesting behaviour appears to arise from the model as a total package, and it is often a challenge to understand how aspects of the behaviour are supported by components of the ANN. The goal of this workshop is to further such understanding: Specifically, to identify the functional roles of ANN components, the link from the component to the overall behaviour and how they combine to explain cognitive phenomena. The four target areas (memory, time, change and structure) are not disjoint, but rather, provide overlapping viewpoints from which to examine models. In essence, we believe these target areas are where to look for the ``sources of power'' in a model. We use the term "distillation" to refer to the process of identifying the functional components of a model with respect to the four target areas. The task of distillation requires exploring the details of a model in order to clarify its source of power, stripping away other aspects. It focuses on the computational properties of the model formalism, providing a method for: (1) understanding the computational components of a newly presented model, and how they give rise to its behavior, (2) discerning novel computational components that may prove useful in model development, and (3) comparing ANN models that target similar cognitive tasks. The workshop is specifically intended for cognitive modellers who use ANNs, but we anticipate that it will be of interest to the wider ANN community. The case study format grounds the analysis of the functional components of ANNs in the cognitive modelling literature, and focuses on phenomena that do admit a computational explanation. The workshop is intended as much as a learning experience as a communicative one. ---------------------------------------------------------------------------- Submission Details Each Case Study should be based on a published ANN simulation in an area of cognitive science. It should address all four target areas of memory, time, change and structure, with the order of sections and choice of sub-headings up to the individual. Some models may have little to say about one or more of these areas - make this explicit. Include simulation details relevant to understanding the functional components of the model but complete replication details are not necessary. Issues beyond the scope of the functional components and the behaviour they support should not be included in the case study itself, but may be appropriate as commentary. Maximum length is 2500 words including references. Where possible, papers should be submitted in html format (but ascii and postscript will also be accepted). The URL for each submission or the source document can be emailed to the organisers at janet@psy.uq.edu.au or devin@psy.uq.edu.au between Feb 1 and March 26, 1996. Case Study Format See Case Study #1 , "Elman's SRN and the discovery of lexical classes" as a guide: http://psych.psy.uq.oz.au/CogPsych/acnn96/case1.html Target paper: Give the full reference to the original paper and relevant simulation. Introduction: In this section introduce the task addressed by the model and the ANN used. Distinguish between the cognitive task of the model and its instantiation in the input/output task of the network. Is there a gap between the the cognitive task and the input/output task of the ANN? For some studies this mismatch may be intentional, as the cognitive task can be viewed as a by-product of another process (e.g., discovery of lexical classes via the prediction task in Elman's SRN). In others, the mismatch between cognitive task and input/output task may be less benign, obscuring the contribution of the model towards understanding the phenomenon. For the ANN task, consider the following questions: What are the inputs and outputs of the model? How is the task information encoded in the input representation? How is the model's response encoded by the output representation? How does the network address the cognitive task? Memory: Identify the information to be stored in memory, then describe the mechanisms. There have been a range of mechanisms proposed for storing and retrieving memories in neural networks: such as implicit long-term coding of memories distributed in the weights; memory as an attractor; short-term memory as transient decay of activations; limit-cycle encoding of memories with synchrony as a method of retrieval. Consider the what and how of memory storage and retrieval: What information needs memory? How is it stored and retrieved? Time: Describe how time is treated in the data, processing and parameters of the network. For example, does the network consider time as an absolute measure in which events in the input are time-stamped with reference to an external clock, as a sequence in which only the order of events is specified, or as a relative measure in which durations are ratios of one another? Methods for processing temporal information with neural networks have included: using a fixed or sliding time window which maps time into space; learning of time delays in the network weights; sequential processing of time slices; and encoding time as the phase angle of an oscillator. What measures of time are used by the network? How are they represented and what are the underlying mechanisms? Change: In this section, consider the types of changes that occur in the neural network, parameters, data, etc, over a range of timescales: * evolutionary change such as a genetic algorithm operating over network parameters; * generational change such as networks training the next generation of networks; * development and aging such as adding or removing units; * learning such as changing weights based on training data; * transient behavior such as activation equation dynamics What types of changes occur in the selected model and how are they implemented in the network's mechanisms? (Note that few of these aspects are expected to apply to any one model, with many case studies focusing on change as learning.) Structure: In this section, consider how structured information in the environment is represented as structured information in the network (e.g., an implicit grammar in training data can be encoded in the hidden-unit space of a recurrent net; and higher-order bindings can be stored using tensors or phase synchrony). What structure is coded directly into the architecture of the network? Is the network partitioned into modules to directly encode structure? What generalization is the network capable of? Is the generalization due to direct coding of structure or does it learn it from the training data? There has been an ongoing debate in the ANN literature on the generalization abilities of networks. Are there important aspects of structure that cannot be represented, learned or generalized by the network? Where possible, identify structure in the environment that may be expected to be reflected in the ANN model but is not. Discussion and Conclusions: In the final section, discuss how the functional components reviewed in the previous sections combine to explain the cognitive phenomena targeted by the case study. Commentary Format The commentary section of the workshop is provided as an outlet for interpretation, elaboration, and substantive criticism of case studies. It is included as part of the workshop format to complement the case studies, which are intended to be compact and focussed on the workshop aim of distilling ANN models into their functional components. Each commentary should discuss one or more case studies and have a maximum length of 1000 words including references. ---------------------------------------------------------------------------- From pjs@aig.jpl.nasa.gov Fri Feb 2 18:16:22 1996 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 2 Feb 96 18:16:20 -0600; AA21354 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 2 Feb 96 18:16:17 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab08117; 1 Feb 96 17:46:47 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa08103; 1 Feb 96 17:21:01 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa08761; 1 Feb 96 17:20:18 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa29507; 1 Feb 96 12:30:56 EST Received: from aig.jpl.nasa.gov by CS.CMU.EDU id aa18012; 1 Feb 96 12:29:27 EST Received: from amorgos.jpl.nasa.gov by aig.jpl.nasa.gov (4.1/JPL-AIG-1.0) id AA25029; Thu, 1 Feb 96 09:29:19 PST Received: (from pjs@localhost) by amorgos.jpl.nasa.gov (8.7.1/8.7.1) id JAA08415 for Connectionists@cs.cmu.edu; Thu, 1 Feb 1996 09:29:16 -0800 (PST) Date: Thu, 1 Feb 1996 09:29:16 -0800 (PST) From: "Padhraic J. Smyth" Message-Id: <199602011729.JAA08415@amorgos.jpl.nasa.gov> To: Connectionists@cs.cmu.edu Subject: CFP for special issue of Machine Learning Journal CALL FOR PAPERS SPECIAL ISSUE OF THE MACHINE LEARNING JOURNAL ON LEARNING WITH PROBABILISTIC REPRESENTATIONS Guest editors: Pat Langley (ISLE/Stanford University) Gregory Provan (Rockwell Science Center/ISLE) Padhraic Smyth (JPL/University of California, Irvine) In recent years, probabilistic formalisms for representing knowledge and inference techniques for using such knowledge have come to play an important role in artificial intelligence. The further development of algorithms for inducing such probabilistic knowledge from experience has resulted in novel approaches to machine learning. To increase awareness of such probabilistic methods, including their relation to each other and to other induction techniques, Machine Learning will publish a special issue on this topic. We encourage submission of papers that address all aspects of learning with probabilistic representations, including but not limited to: Bayesian networks, probabilistic concept hierarchies, naive Bayesian classifiers, mixture models, (hidden) Markov models, and stochastic context-free grammars. We consider any work on learning over representations with explicit probabilistic semantics to fall within the scope of this issue. Submissions should describe clearly the learning task, the representation of data and learned knowledge, the performance element that uses this knowledge, and the induction algorithm itself. Moreover, we encourage authors to decompose their characterization of learning into the processes of (i) selecting a model (or family of models): what are the properties of the model representation ? (ii) selecting a method for evaluating the quality of a fitted model: given a particular parametrization of the model what is the performance criterion by which one can judge its quality ? and (iii) the algorithmic specification of how to search over parameter and model space. An ideal paper will specify these three items clearly and relatively independently. Papers should also evaluate the proposed methods using techniques acknowledged in the machine learning literature, including but not limited to: experimental studies of algorithm behavior on natural and synthetic data (but not the latter alone), theoretical analyses of algorithm behavior, ability to model psychological phenomena, and evidence of successful application in real-world contexts. We especially encourage comparisons that clarify relations among different probabilistic methods or to nonprobabilistic techniques. Papers should meet the standard submission requirements given in the Machine Learning instructions to authors, including having length between 8,000 and 12,000 words. Hardcopies of each submission should be mailed to: Karen Cullen (5 copies) Pat Langley (1 copy) Kluwer Academic Publishers Institute for the Study 101 Philip Drive of Learning and Expertise Assinippi Park 2164 Staunton Court Norwell, MA 02061 Palo Alto, CA 94306 by the submission deadline, July 1, 1996. The review process will take into account the usual criteria, including clarity of presentation, originality of the contribution, and quality of evaluation. We encourage potential authors to contact Pat Langley (langley@cs.stanford.edu), Gregory Provan (provan@jupiter.risc.rockwell.com), or Padhraic Smyth (pjs@aig.jpl.nasa.gov) prior to submission if they have questions. From lawrence@s4.elec.uq.edu.au Fri Feb 2 18:16:26 1996 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 2 Feb 96 18:16:13 -0600; AA21346 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 2 Feb 96 18:16:10 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab08098; 1 Feb 96 17:36:04 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab08095; 1 Feb 96 17:19:09 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa08743; 1 Feb 96 17:18:09 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa18734; 31 Jan 96 23:48:16 EST Received: from s4.elec.uq.edu.au by EDRC.CMU.EDU id aa11484; 31 Jan 96 23:47:03 EST Received: (from lawrence@localhost) by s4.elec.uq.edu.au (8.7.1/8.6.12) id OAA00201; Thu, 1 Feb 1996 14:45:34 +1000 (EST) From: Steve Lawrence Message-Id: <199602010445.OAA00201@s4.elec.uq.edu.au> Subject: Paper available: Function Approximation with Neural Networks and Local Methods To: Connectionists@cs.cmu.edu, neuron@CATTELL20.psych.upenn.edu Date: Thu, 1 Feb 1996 14:45:34 +1000 (EST) X-Mailer: ELM [version 2.4 PL25] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit The following paper presents an overview of global MLP approximation and local approximation. It is known that MLPs can respond poorly to isolated data points and we demonstrate that considering histograms of k-NN density estimates of the data can help in prior determination of the best method. http://www.elec.uq.edu.au/~lawrence - Australia http://www.neci.nj.nec.com/homepages/lawrence - USA We welcome your comments Function Approximation with Neural Networks and Local Methods: Bias, Variance and Smoothness Steve Lawrence, Ah Chung Tsoi, Andrew Back Electrical and Computer Engineering University of Queensland, St. Lucia 4072, Australia ABSTRACT We review the use of global and local methods for estimating a function mapping $\mathcal{R}\mathnormal{^m} \Rightarrow \mathcal{R}\mathnormal{^n}$ from samples of the function containing noise. The relationship between the methods is examined and an empirical comparison is performed using the multi-layer perceptron (MLP) global neural network model, the single nearest-neighbour model, a linear local approximation (LA) model, and the following commonly used datasets: the Mackey-Glass chaotic time series, the Sunspot time series, British English Vowel data, TIMIT speech phonemes, building energy prediction data, and the sonar dataset. We find that the simple local approximation models often outperform the MLP. No criteria such as classification/prediction, size of the training set, dimensionality of the training set, etc. can be used to distinguish whether the MLP or the local approximation method will be superior. However, we find that if we consider histograms of the $k$-NN density estimates for the training datasets then we can choose the best performing method {\em a priori} by selecting local approximation when the spread of the density histogram is large and choosing the MLP otherwise. This result correlates with the hypothesis that the global MLP model is less appropriate when the characteristics of the function to be approximated varies throughout the input space. We discuss the results, the smoothness assumption often made in function approximation, and the bias/variance dilemma. From pazzani@super-pan.ICS.UCI.EDU Fri Feb 2 19:32:45 1996 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 2 Feb 96 19:32:39 -0600; AA22457 Received: from paris.ics.uci.edu by lucy.cs.wisc.edu; Fri, 2 Feb 96 19:31:59 -0600 Received: from super-pan.ics.uci.edu by paris.ics.uci.edu id aa12746; 2 Feb 96 15:12 PST To: ML-LIST:; Subject: Machine Learning List: Vol. 8, No. 2 Reply-To: ml@ics.uci.edu Date: Fri, 02 Feb 1996 14:56:17 -0800 From: Michael Pazzani Message-Id: <9602021512.aa12746@paris.ics.uci.edu> Machine Learning List: Vol. 8, No. 2 Friday, February 2 1996 Contents: WWW Page -- Santa Cruz ML Research MSL'96 workshop FOGA96 - last call Strategic Task Force KDD of MLnet MODERN REGRESSION AND CLASSIFICATION CFP: NEURAL NETWORKS in the CAPITAL MARKETS 1996 MSc MACHINE LEARNING AND ADAPTIVE COMPUTING Graduate Study at the Oregon Graduate Institute UAI 96: Updated CFP Job Posting CFP: Mathematical Psychology conference -- August 1996 Call For Papers: Conf. on Empirical NLP SDAIR'96 - Advance Program 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 FTP'd from ics.uci.edu in pub/ml-list/V/ or N.Z where X and N are the volume and number of the issue; ID: anonymous PASSWORD: URL- http://www.ics.uci.edu/AI/ML/Machine-Learning.html ---------------------------------------------------------------------- From: Mark Herbster Subject: WWW Page -- Santa Cruz ML Research Date: Thu, 1 Feb 1996 03:37:04 -0800 (PST) The following papers are available via the following web page of the Machine Learning group at the University of California at Santa Cruz: http://www.cse.ucsc.edu/research/ml/research.html "Exponentially many local minima for single neurons" Peter Auer, Mark Herbster and Manfred Warmuth, Neural Information Processing Systems 1996. "Tracking the Best Expert" Mark Herbster and Manfred Warmuth, Proceeding of Machine Learning 1995. "Mutual Information, Metric Entropy, and Risk in Estimation of Probability Distributions." David Haussler and Manfred Opper. "Exponentiated Gradient versus Gradient Descent for Linear Predictors" Jyrki Kivenen and Manfred K. Warmuth. "The Perceptron algorithm vs. Winnow: linear vs. logarithmic mistake bounds when few input variables are relevant" Jyrki Kivenen and Manfred K. Warmuth. "Efficient Learning with Virtual Threshold Gates," By Wolfgang Maass and Manfred K. Warmuth. "How to Use Expert Advice" Nicolo Cesa-Bianchi, Yoav Freund, David P. Helmbold, David Haussler, Robert E. Schapire, and Manfred K. Warmuth. "Bounds for Predictive Errors in the Statistical Mechanics of Supervised Learning" Manfred Opper and David Haussler, published in Physical Review Letters, number 20, volume 75, 1995, pp. 3772-3775. "General Bounds on the Mutual Information between a parameter and n conditionally independent observations" David Haussler and Manfred Opper, Proceedings of the 8th Conference on Computational Learning Theory, Santa Cruz, July, 1995, Published by ACM Press. "A General Minimax Result for Relative Entropy" David Haussler, Submitted to IEEE Transactions on Information Theory. "Rigorous Learning Curve Bounds from Statistical Mechanics" David Haussler, Michael Kearns, and H. Sebastian Seung, Submitted to Machine Learning. ------------------------------ From: Janusz Wnek Subject: MSL'96 workshop Date: Mon, 29 Jan 96 13:48:28 EST CALL FOR PAPERS The Third International Workshop on Multistrategy Learning (MSL'96) May 23-25, 1996 Hilltop Inn, Harpers Ferry, West Virginia http://www.mli.gmu.edu/msl96.html Submission deadline: February 10, 1996. Please note: Since MSL'96 is a small, limited-attendance workshop, a paper submitted to an open conference, including ML, AAAI or KDD, can also be submitted to MSL'96. Each submitted paper will be evaluated independently, and accepted for presentation solely on the basis of its merit for the workshop. ------------------------------ From: "Richard K. Belew" Subject: FOGA96 - last call Date: Mon, 29 Jan 96 21:20:24 -0800 There have been a number of recent queries concerning manuscripts being submitted to the 1996 Foundations of Genetic Algorithms (FOGA4) workshop, to be held August 3-5 in San Diego, California. (Complete information about the meeting is available at: http://www.aic.nrl.navy.mil/galist/foga/ ). The deadline for submissions remains this Thursday, 1 February. However, due to the large number of related conferences with similar deadlines, difficulties for foreign authors, etc., we will continue to accept manuscripts for a couple of days beyond this deadline. HOWEVER, if you intend to submit a paper but will not have it to us (either as hardcopy or Postscript) by the deadline PLEASE SEND US A BRIEF MESSAGE NOW. Be sure to include the title, authors and abstract of the paper. This will help us to begin the process of assigning reviewers. Paper submissions and further questions may be directed to: Richard K. Belew Computer Science & Engr. Dept. (0114) Univ. California -- San Diego La Jolla, CA 92093-0114 rik@cs.ucsd.edu Michael D. Vose C.S. Dept., 107 Ayres Hall The University of Tennessee Knoxville, TN 37996 vose@cs.utk.edu ------------------------------ From: Ramon Lopez de Mantaras Date: Thu, 25 Jan 1996 12:52:42 +0100 Subject: Strategic Task Force KDD of MLnet Strategic Task Force KDD of MLnet (European Network of Excellence in ML) In view of the great interest of ML in KDD and regarding the expertise that members of MLnet can offer to this new field, it is proposed that a general discussion on KDD takes place via e-mail. The e-mail discussion can extend beyond MLnet, in particular it should be coordinated with the KDD nuggets, the Machine Learning list and the AI-stats lists. The purpose of this email discussion is to identify the most crucial issue in KDD that the ML community can contribute to. Below, some topics for discussion are proposed. The e-mail discussion should run for less than 2 months. On the basis of the contributions, people may apply to become one of the 7 experts that will write a document, based on the e-mail discussion and additional discussions among themselves. The coordinator of MLnet (Ramon Lopez de Mantaras : mantaras@iiia.csic.es) will decide on the applications for becoming a member of the expert group. Possible TOPICS FOR DISCUSSION: 1) Who will be the users of KDD tools? AI has often claimed to offer information directly to managers or experts. It then turned out, that even AI products are used and maintained by the computer experts. Concerning KDD, some (e.g. Tej Anand from AT & T) perceive the business user as using and maintaining a KDD system. What is your experience? For whom do you design your tool? Are there any real users out there? 2) What are the goals of KDD? A variety of goals has been put forward in KDD literature: - allowing for better answers of a database system (e.g.: the query "who are the customers of product X" will not be answered by a table listing the customers but by a characterization of the customers). - supporting data quality maintenance (the KDD tool will deliver dependencies or rules hidden in the data; if these contradict the domain expert's knowledge, the data must be incomplete or wrong). - database query optimization (e.g., the KDD tool discovers queries that cannot have a positive answer - the database system need not look-up any entry). - overview of database content - prediction of new data. 3) What is the relation between statistics and ML techniques in KDD? Statistics might play the role of a pre-processor for a learning algorithm. It may also be part of the kernel of a KDD system. Or it may be considered an ancestor of KDD - now overcome by ML techniques! 4) What is the role of a knowledge base in KDD? It is often claimed that a KB can be exploited in order to guide KDD. What are the restrictions and constraints this imposes on the KB? Another claim is that the KB can (partly) be constructed by KDD. What does this mean for the relation between KA and KDD? In particular, does KDD re-describe a given KB? Alternatively a KB can be used to redescribe a dataset before KDD techniques are applied. 5) Which prerequisites of DBMS technology are required by KDD? The demand of KDD is to some extent based on the behind-the-state-of-art state of data handling. It is hoped that KDD will give insight into data that have been managed poorly. On the other hand, a data warehouse is stated as a prerequisite for KDD applications. 6) The KDD search space is very large: many techniques can be applied and application of one technique may yield a large number of clusters, rules, classes etc. How can a user be supported in navigating this large space? 7) Clever data preparation of often a key to success in ML. This works when one knows what one is looking for. In KDD one may not know what one is looking for and hence data preparation has to be performed in the dark. How to solve this? 8) Currently there is no clear framework or methodology for KDD and its application in an industrial context. Is such a methodology (Life Cycle, set of methods, guidelines) needed and what would industrial users expect from them? ========================================================================= _________________________________________________________________________ _/ _/ _/_| Ramon Lopez de Mantaras / _/ _/ _| IIIA - Artificial Intelligence Research Institute _/ _/___| CSIC - Spanish Scientific Research Council _/ _/____| Campus Universitat Autonoma de Barcelona / _/ _| 08193 Bellaterra, Spain voice: +34-3-580 95 70 fax: +34-3-580 96 61 mantaras@iiia.csic.es http://www.iiia.csic.es _________________________________________________________________________ ------------------------------ Date: Fri, 19 Jan 1996 17:15:56 -0800 (PST) From: Trevor Hastie Subject: MODERN REGRESSION AND CLASSIFICATION MODERN REGRESSION AND CLASSIFICATION May 9-10, 1996 Stanford Park Hotel, Menlo Park A two-day course on widely applicable statistical methods for modelling and prediction, featuring Professor Trevor Hastie and Professor Robert Tibshirani Stanford University University of Toronto This two day course covers modern tools for statistical prediction and classification. We start from square one, with a review of linear techniques for regression and classification, and then take attendees through a tour of: o Flexible regression techniques o Classification and regression trees o Neural networks o Projection pursuit regression o Nearest Neighbor methods o Learning vector quantization o Wavelets o Bootstrap and cross-validation We will also illustrate software tools for implementing the methods. Our objective is to provide attendees with the background and knowledge necessary to apply these modern tools to solve their own real-world problems. The course is geared for: o Statisticians o Financial analysts o Industrial managers o Medical and Quantitative researchers o Scientists o others interested in prediction and classification Attendees should have an undergraduate degree in a quantitative field, or have knowledge and experience working in such a field. For more details on the course, how to register, price etc: o point your web browser to: http://playfair.stanford.edu/~trevor/mrc.html OR send a request by o FAX to Prof. T. Hastie at (415) 326-0854, OR o email to trevor@playfair.stanford.edu ------------------------------ From: John Moody Subject: CFP: NEURAL NETWORKS in the CAPITAL MARKETS 1996 Date: Wed, 31 Jan 96 19:27:19 -0800 -- Preliminary Announcement and Call for Papers -- NNCM-96 FOURTH INTERNATIONAL CONFERENCE NEURAL NETWORKS in the CAPITAL MARKETS Wednesday-Friday, November 20-22, 1996 The Ritz-Carlton Hotel, Pasadena, California, U.S.A. Sponsored by Caltech and London Business School Neural networks have been applied to a number of live systems in the capital markets, and in many cases have demonstrated better performance than competing approaches. Because of the increasing interest in the NNCM conferences held in the U.K. and the U.S., the fourth annual NNCM is planned for November 20-22, 1996, in Pasadena, California. This is a research meeting where original and significant contributions to the field are presented. In addition, introductory tutorials will be included to familiarize audiences of different backgrounds with the financial and the mathematical aspects of the field. Areas of Interest: Price forecasting for stocks, bonds, commodities, and foreign exchange; asset allocation and risk management; volatility analysis and pricing of derivatives; cointegration, correlation, and multivariate data analysis; credit assessment and economic forecasting; statistical methods, learning techniques, and hybrid systems. Organizing Committee: Dr. Y. Abu-Mostafa, Caltech (Chairman) Dr. A. Atiya, Cairo University Dr. N. Biggs, London School of Economics Dr. D. Bunn, London Business School Dr. M. Jabri, Sydney University Dr. B. LeBaron, University of Wisconsin Dr. A. Lo, MIT Sloan School Dr. I. Matsuba, Chiba University Dr. J. Moody, Oregon Graduate Institute Dr. C. Pedreira, Catholic Univ. PUC-Rio Dr. A. Refenes, London Business School Dr. M. Steiner, Universitaet Munster Dr. A. Timermann, UC San Diego Dr. A. Weigend, University of Colorado Dr. H. White, UC San Diego Dr. L. Xu, Chinese University of Hong Kong Submission of Papers: Original contributions representing new and significant research, development, and applications in the above areas of interest are invited. Authors should send 5 copies of a 1000-word summary clearly stating their results to Dr. Y. Abu-Mostafa, Caltech 136-93, Pasadena, CA 91125, U.S.A. All submissions must be received before May 1, 1996. There will be a rigorous refereeing process to select the high-quality papers to be presented at the conference. Location: The conference will be held at the Ritz-Carlton Huntington Hotel in Pasadena, within two miles from the Caltech campus. The hotel is a 35-minute drive from Los Angeles International Airport (LAX) with nonstop flights from most major cities in North America, Europe, the Far East, Australia, and South America. Mailing List: If you wish to be added to the mailing list of NNCM-96, please send your postal address, e-mail address, and fax number to Dr. Y. Abu-Mostafa, Caltech 136-93, Pasadena, CA 91125, U.S.A. e-mail: yaser@caltech.edu , fax (818) 795-0326 Home Page: http://www.cs.caltech.edu/~learn/nncm.html ------------------------------ Subject: MSc MACHINE LEARNING AND ADAPTIVE COMPUTING From: tcf@btc.uwe.ac.uk Date: Fri, 2 Feb 96 16:28:57 GMT University of the West of England, Bristol Intelligent Computer Systems Centre MSc MACHINE LEARNING AND ADAPTIVE COMPUTING Applications are invited for entry in October 1996 to the Master of Science (MSc) Degree in Machine Learning and Adaptive Computing. The degree can be taken in one year full-time or two years part-time. Students will follow compulsory taught courses in core techniques, options in application areas and a project leading to a Masters Thesis. INTRODUCTION Over the next few years the new technologies of machine learning and adaptive computing will enhance established computing technologies to provide a new class of intelligent computer systems. This one year full-time MSc is aimed at good graduates in computing, mathematics and engineering who wish to be involved in the research, development and exploitation of machine learning and adaptive computing. UWE has acknowledged expertise in the areas of evolutionary computing, machine learning, neural networks, case-based reasoning and knowledge acquisition and their application to problems in business, science and engineering. AIMS To develop an understanding of machine learning and adaptive computing. To demonstrate the applicability of these fields to current computing and engineering problems To provide the stimulus and opportunity for students to make a significant contribution to reasearch and/or development in these fields. OBJECTIVES To produce students who know the range of applicability of machine learning and adaptive computing and which technique and which tool to use for a particular problem. To provide students with experience in the development and use of one technique on a range of problems or the solution of one problem using a mix of techniques. ORGANISATION 1st TERM Two weeks induction and introduction including a 2-3 day off-site residential course. Five compulsory core modules in: Machine Learning. Case-Based Reasoning. Evolutionary Computing. Neural Networks. Knowledge Acquisition. 2nd TERM A Case Study module. Students will work in groups of three/four and will specify, design, implement, test, and document a small system or research study. A compulsory module on Organisational and Business Aspects of IT Innovation Six applications modules (subject to demand) chosen from the following: Expert Databases Image Processing Distributed and Parallel Computing Smart Buildings Communication Systems Intelligent Control Multi-robot Cooperation Manufacturing Systems Computer Aided Design Examinations 3rd TERM A substantial project will be undertaken, as part of an industrial placement or in one of the University's research groups, leading to the submission of a masters thesis. STAFF INVOLVED Brian Carse, Dr. Nouhman Chalabi, Dr. Stephen Drewer, Dr. Terence Fogarty, Terry Hill, Owen Holland, Dr. Ye Huang, Ian Johnson, Dr. Wei Zhong Liu, Dr. Richard McClatchey, Dr. Roger Miles, Tony Pipe, Dr. Peter Sharpe, Rob Stevens, Prof. Sam Waters COMPANIES INVOLVED Quadstone, British Aerospace, Hewlett Packard, British Telecom, PACT Bristol, Integral Solutions Limited APPLICATION PROCEDURE Application forms are available from the course secretary: Mrs. Fay Coleman Intelligent Computer Systems Centre Faculty of Computer Studies and Mathematics University of the West of England Bristol BS16 1QY, UK Tel: +44 (0)1179 656261 x3183 Email: fay@btc.uwe.ac.uk Further information is available from the course director: Dr. Terry Fogarty at the same address Tel: +44 (0)1179 656261 x3179 Email: tcf@btc.uwe.ac.uk ------------------------------ From: John Moody Subject: Graduate Study at the Oregon Graduate Institute Date: Wed, 31 Jan 96 18:45:49 -0800 OGI (Oregon Graduate Institute of Science and Technology) has openings for a few outstanding students in its Computer Science and Electrical Engineering Masters and Ph.D programs in the areas of Neural Networks, Learning, Signal Processing, Time Series, Control, Speech, Language, Vision, and Computational Finance. OGI has 14 faculty, senior research staff, and postdocs in these areas. Short descriptions of our research interests are appended below. The primary purposes of this message are: 1) To invite inquiries and applications from prospective students interested in studying for a Masters or PhD Degree in the above areas. 2) To notify prospective PhD students who are U.S. Citizens or U.S. Nationals of various fellowship opportunities at OGI. Fellowships provide full or partial financial support while studying for the PhD. OGI is a young, but rapidly growing, private research institute located in the Silicon Forest area west of downtown Portland, Oregon. OGI offers Masters and PhD programs in Computer Science and Engineering, Electrical Engineering, Applied Physics, Materials Science and Engineering, Environmental Science and Engineering, Chemistry, Biochemistry, Molecular Biology, and Management. The Portland area has a high concentration of high tech companies that includes major firms like Intel, Hewlett Packard, Tektronix, Sequent Computer, Mentor Graphics, Wacker Siltronics, and numerous smaller companies like Planar Systems, FLIR Systems, Flight Dynamics, and Adaptive Solutions (an OGI spin-off that manufactures high performance parallel computers for neural network and signal processing applications). The admissions deadline for the OGI PhD programs is March 1. Masters program applications are accepted year-round. Inquiries about these programs and admissions for either Computer Science or Electrical Engineering should be addressed to: Office of Admissions and Records Oregon Graduate Institute PO Box 91000 Portland, OR 97291 Phone: (503)690-1028, or (800)685-2423 (toll-free in the US and Canada) Worldwide Web: http://www.ogi.edu/webtest/admissions.html Internet: admissions@admin.ogi.edu Due to the late time in the PhD applications season, though, informal applications should be sent directly to the CSE Department. For these informal applications, please include a letter specifying your research interests, photocopies of your GRE Scores, TOEFL Scores, and College transcripts, and indicate your interest in either the PhD or Masters programs. Please send these materials to: Betty Shannon, Academic Coordinator Department of Computer Science and Engineering Oregon Graduate Institute PO Box 91000 Portland, OR 97291-1000 Phone: (503)690-1255 Internet: bettys@cse.ogi.edu +++++++++++++++++++++++++++++++++++++++++++++++++++++++ Oregon Graduate Institute of Science & Technology Department of Computer Science and Engineering & Department of Electrical Engineering and Applied Physics Research Interests of Faculty, Research Staff, and Postdocs in Neural Networks, Signal Processing, Control, Speech, Language, Vision, Time Series, and Computational Finance (Note: Additional information is available on the Web at http://www.ogi.edu/ ) Etienne Barnard (Associate Professor, EEAP): Etienne Barnard is interested in the theory, design and implementation of pattern-recognition systems, classifiers, and neural networks. He is also interested in adaptive control systems -- specifically, the design of near-optimal controllers for real- world problems such as robotics. Ron Cole (Professor, CSE): Ron Cole is director of the Center for Spoken Language Understanding at OGI. Research in the Center currently focuses on speaker- independent recognition of continuous speech over the telephone and automatic language identification for English and ten other languages. The approach combines knowledge of hearing, speech perception, acoustic phonetics, prosody and linguistics with neural networks to produce systems that work in the real world. Mark Fanty (Research Assistant Professor, CSE): Mark Fanty's research interests include continuous speech recognition for the telephone; natural language and dialog for spoken language systems; neural networks for speech recognition; and voice control of computers. Dan Hammerstrom (Associate Professor, CSE): Based on research performed at the Institute, Dan Hammerstrom and several of his students have spun out a company, Adaptive Solutions Inc., which is creating massively parallel computer hardware for the acceleration of neural network and pattern recognition applications. There are close ties between OGI and Adaptive Solutions. Dan is still on the faculty of the Oregon Graduate Institute and continues to study next generation VLSI neurocomputer architectures. Hynek Hermansky (Associate Professor, EEAP); Hynek Hermansky is interested in speech processing by humans and machines with engineering applications in speech and speaker recognition, speech coding, enhancement, and synthesis. His main research interest is in practical engineering models of human information processing. Todd K. Leen (Associate Professor, CSE): Todd Leen's research spans theory of neural network models, architecture and algorithm design and applications to speech recognition. His theoretical work is currently focused on the foundations of stochastic learning, while his work on Algorithm design is focused on fast algorithms for non-linear data modeling. John Moody (Associate Professor, CSE): John Moody does research on the design and analysis of learning algorithms, statistical learning theory (including generalization and model selection), optimization methods (both deterministic and stochastic), and applications to signal processing, time series, economics, and computational finance. David Novick (Associate Professor, CSE): David Novick conducts research in interactive systems, including computational models of conversation, technologically mediated communication, and human-computer interaction. A central theme of this research is the role of meta-acts in the control of interaction. Current projects include dialogue models for telephone-based information systems. Misha Pavel (Associate Professor, EEAP): Misha Pavel does mathematical and neural modeling of adaptive behaviors including visual processing, pattern recognition, visually guided motor control, categorization, and decision making. He is also interested in the application of these models to sensor fusion, visually guided vehicular control, and human-computer interfaces. Hong Pi (Senior Research Associate, CSE) Hong Pi's research interests include neural network models, time series analysis, and dynamical systems theory. He currently works on the applications of nonlinear modeling and analysis techniques to time series prediction problems and financial market analysis. Thorsteinn S. Rognvaldsson (Post-Doctoral Research Associate, CSE): Thorsteinn Rognvaldsson studies both applications and theory of neural networks and other non-linear methods for function fitting and classification. He is currently working on methods for choosing regularization parameters and also comparing the performance of neural networks with the performance of other techniques for time series prediction and financial markets. Pieter Vermeulen (Senior Research Associate, CSE): Pieter Vermeulen is interested in the theory, design and implementation of pattern-recognition systems, neural networks and telephone based speech systems. He currently works on the realization of speaker independent, small vocabulary interfaces to the public telephone network. Current projects include voice dialing, a system to collect the year 2000 census information and the rapid prototyping of such systems. Eric A. Wan (Assistant Professor, EEAP): Eric Wan's research interests include learning algorithms and architectures for neural networks and adaptive signal processing. He is particularly interested in neural applications to time series prediction, adaptive control, active noise cancellation, and telecommunications. Lizhong Wu (Senior Research Associate, CSE): Lizhong Wu's research interests include neural network theory and modeling, time series analysis and prediction, pattern classification and recognition, signal processing, vector quantization, source coding and data compression. He is now working on the application of neural networks and nonparametric statistical paradigms to finance. ------------------------------ From: Eric Horvitz Subject: UAI 96: Updated CFP Date: Wed, 31 Jan 1996 14:11:55 -0800 ========================================================= S E C O N D C A L L F O R P A P E R S ========================================================= ** U A I 96 ** THE TWELFTH ANNUAL CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE August 1-3, 1996 Reed College Portland, Oregon, USA ======================================= See the UAI-96 WWW page at http://cuai-96.microsoft.com/ CALL FOR PAPERS The effective handling of uncertainty is critical in designing, understanding, and evaluating computational systems tasked with making intelligent decisions. For over a decade, the Conference on Uncertainty in Artificial Intelligence (UAI) has served as the central meeting on advances in methods for reasoning under uncertainty in computer-based systems. The conference is the annual international forum for exchanging results on the use of principled uncertain-reasoning methods to solve difficult challenges in AI. Theoretical and empirical contributions first presented at UAI have continued to have significant influence on the direction and focus of the larger community of AI researchers. The scope of UAI covers a broad spectrum of approaches to automated reasoning and decision making under uncertainty. Contributions to the proceedings address topics that advance theoretical principles or provide insights through empirical study of applications. Interests include quantitative and qualitative approaches, and traditional as well as alternative paradigms of uncertain reasoning. Innovative applications of automated uncertain reasoning have spanned a broad spectrum of tasks and domains, including systems that make autonomous decisions and those designed to support human decision making through interactive use. We encourage submissions of papers for UAI-96 that report on advances in the core areas of representation, inference, learning, and knowledge acquisition, as well as on insights derived from building or using applications of uncertain reasoning. Topics of interest include (but are not limited to): >> Foundations * Theoretical foundations of uncertain belief and decision * Uncertainty and models of causality * Representation of uncertainty and preference * Generalization of semantics of belief * Conceptual relationships among alternative calculi * Models of confidence in model structure and belief >> Principles and Methods * Planning under uncertainty * Temporal reasoning * Markov processes and decisions under uncertainty * Qualitative methods and models * Automated construction of decision models * Abstraction in representation and inference * Representing intervention and persistence * Uncertainty and methods for learning and datamining * Computation and action under limited resources * Control of computational processes under uncertainty * Time-dependent utility and time-critical decisions * Uncertainty and economic models of problem solving * Integration of logical and probabilistic inference * Statistical methods for automated uncertain reasoning * Synthesis of Bayesian and neural net techniques * Algorithms for uncertain reasoning * Advances in diagnosis, troubleshooting, and test selection >> Empirical Study and Applications * Empirical validation of methods for planning, learning, and diagnosis * Enhancing the human--computer interface with uncertain reasoning * Uncertain reasoning in embedded, situated systems (e.g., softbots) * Automated explanation of results of uncertain reasoning * Nature and performance of architectures for real-time reasoning * Experimental studies of inference strategies * Experience with knowledge-acquisition methods * Comparison of repres. and inferential adequacy of different calculi * Uncertain reasoning and information retrieval For papers focused on applications in specific domains, we suggest that the following issues be addressed in the submission: - Why was it necessary to represent uncertainty in your domain? - What are the distinguishing properties of the domain and problem? - What kind of uncertainties does your application address? - Why did you decide to use your particular uncertainty formalism? - What theoretical problems, if any, did you encounter? - What practical problems did you encounter? - Did users/clients of your system find the results useful? - Did your system lead to improvements in decision making? - What approaches were effective (ineffective) in your domain? - What methods were used to validate the effectiveness of the systems? ================================= SUBMISSION AND REVIEW OF PAPERS ================================= Papers submitted for review should represent original, previously unpublished work (details on policy on submission uniqueness are available at the UAI 96 www homepage). Submitted papers will be evaluated on the basis of originality, significance, technical soundness, and clarity of exposition. Papers may be accepted for presentation in plenary or poster sessions. All accepted papers will be included in the Proceedings of the Twelfth Conference on Uncertainty in Artificial Intelligence, published by Morgan Kaufmann Publishers. Outstanding student papers will be selected for special distinction. Submitted papers must be at most 20 pages of 12pt Latex article style or equivalent (about 4500 words). See the UAI-96 homepage for additional details about UAI submission policies. We strongly encourage the electronic submission of papers. To submit a paper electronically, send an email message to uai@microsoft.com that includes the following information (in this order): * Paper title (plain text) * Author names, including student status (plain text) * Surface mail and email address for a contact author (plain text) * A short abstract including keywords or topic indicators (plain text) An electronic version of the paper (Postscript format) should be submitted simultaneously via ftp to: cuai-96.microsoft.com/incoming. Files should be named $.ps, where $ is an identifier created from the first five letters of the last name of the first author, followed by the first initial of the author's first name. Multiple submissions by the same first author should be indicated by adding a number (e.g., pearlj2.ps) to the end of the identifier. Authors will receive electronic confirmation of the successful receipt of their articles. Authors unable to access ftp should electronically mail the first four items and the Postscript file of their paper to uai@microsoft.com. Authors unable to submit Postscript versions of their paper should send the first four items in email and 5 copies of the complete paper to one of the Program Chairs at the addresses listed below. ++++++++++++++++++++++++++++++ Important Dates (Note revisions) ++++++++++++++++++++++++++++++ >> Submissions must be received by 5PM local time: March 1, 1996 >> Notification of acceptance on or before: April 19, 1996 >> Camera-ready copy due: May 15, 1996 ========================== Program Cochairs: ================= Eric Horvitz Microsoft Research, 9S Redmond, WA 98052 Phone: (206) 936 2127 Fax: (206) 936 0502 Email: horvitz@microsoft.com WWW: http://www.research.microsoft.com/research/dtg/horvitz/ Finn Jensen Department of Mathematics and Computer Science Aalborg University Fredrik Bajers Vej 7,E DK-9220 Aalborg OE Denmark Phone: +45 98 15 85 22 (ext. 5024) Fax: +45 98 15 81 29 Email: fvj@iesd.auc.dk WWW: http://www.iesd.auc.dk/cgi-bin/photofinger?fvj General Conference Chair (General conference inquiries): ======================== Steve Hanks Department of Computer Science and Engineering, FR-35 University of Washington Seattle, WA 98195 Tel: (206) 543 4784 Fax: (206) 543 2969 Email: hanks@cs.washington.edu Program Committee =================== Fahiem Bacchus (U Waterloo) * Salem Benferhat (U Paul Sabatier) * Mark Boddy (Honeywell) * Piero Bonissone (GE) * Craig Boutilier (U Brit Columbia) * Jack Breese (Microsoft) * Wray Buntine (Thinkbank) * Luis M. de Campos * (U Granada) * Enrique Castillo (U Cantabria) * Eugene Charniak (Brown) * Greg Cooper (U Pittsburgh) * Bruce D'Ambrosio (Oregon State) * Paul Dagum (Stanford) * Adnan Darwiche (Rockwell) * Tom Dean (Brown) * Denise Draper (Rockwell) * Marek Druzdzel (U Pittsburgh) * Didier Dubois (Paul Sabatier) * Ward Edwards (USC) * Kazuo Ezawa (ATT Labs) * Robert Fung (Prevision) * Linda van der Gaag (Utrecht U) * Hector Geffner (Simon Bolivar) * Dan Geiger (Technion) * Lluis Godo (Barcelona) * Robert Goldman (Honeywell) * Moises Goldszmidt (Rockwell) * Adam Grove (NEC) * Peter Haddawy (U Wisc-Milwaukee) * Petr Hajek (Czech Acad Sci) * Joseph Halpern (IBM) * Steve Hanks (U Wash) * Othar Hansson (Berkeley) * Peter Hart (Ricoh) * David Heckerman (Microsoft) * Max Henrion (Lumina) * Frank Jensen (Hugin) * Michael Jordan (MIT) * Leslie Pack Kaelbling (Brown) * Keiji Kanazawa (Microsoft) * Uffe Kjaerulff (U Aalborg) * Daphne Koller (Stanford) * Paul Krause (Imp. Cancer Rsch Fund) * Rudolf Kruse (U Braunschweig) * Henry Kyburg (U Rochester) * Jerome Lang (U Paul Sabatier) * Kathryn Laskey (George Mason) * Paul Lehner (George Mason) * John Lemmer (Rome Lab) * Tod Levitt (IET) * Ramon Lopez de Mantaras (Spanish Sci. Rsch Council) * David Madigan (U Wash) * Eric Neufeld (U Saskatchewan) * Ann Nicholson (Monash U) * Nir Friedman (Stanford) * Judea Pearl (UCLA) * Mark Peot (Stanford) * Kim Leng Poh, (Natl U Singapore) * David Poole (U Brit Columbia) * Henri Prade (U Paul Sabatier) * Greg Provan (Inst. Learning Sys) * Enrique Ruspini (SRI) * Romano Scozzafava (Dip. Mo. Met., Rome) * Ross Shachter (Stanford) * Prakash Shenoy (U Kansas) * Philippe Smets (U Bruxelles) * David Spiegelhalter (Cambridge U) * Peter Spirtes (CMU) * Milan Studeny (Czech Acad Sci) * Sampath Srinivas (Microsoft) * Jaap Suermondt (HP Labs) * Marco Valtorta (U S.Carolina) * Michael Wellman (U Michigan) * Nic Wilson (Oxford Brookes U) * Y. Xiang (U Regina) * Hong Xu (U Bruxelles) * John Yen (Texas A&M) * Lian Wen Zhang, (Hong Kong U) * --------------- UAI-96 will occur right before KDD-96, AAAI-96, and the AAAI workshops, and will be in close proximity to these meetings. * * * UAI 96 will include a full-day tutorial program on uncertain reasoning on the day before the main UAI 96 conference (Wednesday, July 31) at Reed College. Details on the tutorials are available on the UAI 96 www homepage. * * * Refer to the UAI-96 WWW home page for late-breaking information: http://cuai-96.microsoft.com/ ------------------------------ From: Janice Colby Subject: Job Posting Date: Tue, 23 Jan 96 11:38 EST The Army Research Laboratory (ARL), Ft. Belvoir, VA is looking for researchers in the fields of computer science, engineering and mathematics to work on fundamental problems in the areas of object recognition and scene generation. This includes both work on open theoretical problems and the development of efficient algorithms. Our research is primarily directed toward problems in computer vision and computer graphics that arise in processing images in a number of different viewing domains including visual, infrared/thermal, and newer technologies as they become available. Several levels of research positions exist at ARL and applicants are being sought for a number of them. These include senior level research scientist, entry level doctoral position, postdoctoral fellowship, and graduate student internship. One of the positions dealing with object recognition would favor an applicant with a doctoral degree in optimization, whereas the remaining positions would primarily be suited for PhD's who have demonstrated a strong potential for original research in computer vision and/or computer graphics. Applicants for the graduate student positions should have, at a minimum, a masters degree or equivalent in one of the areas listed above. A knowledge of C or C++ would be considered a strong positive for all of the positions because of the extensive interactions between the research staff and the development staff here at ARL. These positions are available at two distinct sites in the Washington, DC area. To apply, send your curriculum vitae or resume in ascii, postscript, or latex format to colby@nvl.army.mil. Please remember to include a phone number where you can be reached as well as an e-mail address if available. Applications may also be faxed to (703)704-3196 or sent via U.S. mail to the address below. DEPARTMENT OF THE ARMY ARMY RESEARCH LABORATORY AMSRL SE RS (COLBY) 10235 BURBECK RD STE 110 FT. BELVOIR, VA 22060-5838 ------------------------------ From: Jonathan Marshall Subject: CFP: Mathematical Psychology conference -- August 1996 Date: Sun, 28 Jan 1996 15:00:12 -0400 CALL FOR PAPERS 29th Annual MATHEMATICAL PSYCHOLOGY Meeting 1-4 August 1996 Sponsored by the University of North Carolina at Chapel Hill The 29th Annual Mathematical Psychology Meeting will be held at the Univ. of North Carolina at Chapel Hill. The meetings will follow the usual format with paper sessions over two and a half days (2-4 August) with a banquet after the first day of papers. The Organizing Committee consists of Christina A. Burbeck, Elliot L. Hirshman, Jonathan A. Marshall (Co-Chair), Nestor A. Schmajuk, Thomas S. Wallsten (Co-Chair), and Yiu-Fai Yung. Papers for the Mathematical Psychology Meeting may be submitted by regular members, student members, and nonmembers. Any one person may present only one paper but may be a coauthor of other papers, or may be an invited speaker or symposium participant. Papers will be limited to those in which mathematical, statistical, and simulation methods play a significant role in the development of psychological ideas or in the interpretation of results. Purely theoretical developments should clearly relate to some psychological issue or contribute to methodologies of obvious use in psychology. Experimental results should bear directly on some mathematical or simulation model. Programs of past meetings appear in the Journal of Mathematical Psychology and may be consulted for ideas concerning symposia as well as for ideas about areas that have not recently been covered. All members of the Society for Mathematical Psychology are welcome to make suggestions for symposia and invited speakers, to the Program Committee as soon as possible. Abstracts of papers must be received by 30 April 1996. Papers are accepted on the basis of their quality and suitability and not according to the author's affiliation with the Society. For oral papers, presentation time will be limited to 25 minutes including five minutes for discussion. Sessions will be strictly timed. This year, we are considering adding a poster session. If there are sufficient submissions, we will do so. Poster presentations have the advantage of longer discussion time, less formality, and closer audience contact. The "status" associated with poster presentations will be equal to that associated with oral presentations. Submissions must include the following information: 1. For all authors and co-authors: - Names - Institutional affiliations - Mailing addresses - E-mail addresses - Telephone and fax numbers - Membership status in the Society for Mathematical Psychology (member, student member, or nonmember) 2. A specification of which co-author will present the paper at the meeting 3. Your preference for spoken/poster presentation: (a) Only wish to present a spoken paper (b) Prefer spoken paper, willing to give a poster (c) No preference; either spoken or poster is fine (d) Prefer poster, willing to give a spoken paper (e) Only willing to present a poster 4. Title of paper 5. Category of the paper. Choose the most appropriate category: (a) categorization (b) cognition and language (c) judgment, decision, and choice (d) information processing and performance (e) learning and memory (f) measurement and scaling (g) methodology and statistics (h) neural/neurophysiological modeling (i) physiology (j) psychophysics (k) sensation and perception (l) social psychology (m) other (please specify) 6. An abstract of 150-250 words E-mail submission of abstracts is greatly preferred, since this will facilitate compiling (without retyping) of an abstract book to be distributed at the meeting. Send abstracts to: Professor Jonathan A. Marshall Math Psych '96 Program Committee Department of Computer Science CB 3175, Sitterson Hall University of North Carolina Chapel Hill, NC 27599-3175, U.S.A. E-mail marshall@cs.unc.edu Tel +1-919-962-1887, fax +1-919-962-1799 Address symposium outlines, and invited speaker suggestions to: Professor Thomas S. Wallsten Math Psych '96 Program Committee Department of Psychology CB 3270, Davie Hall University of North Carolina Chapel Hill, NC 27599-3270, U.S.A. E-mail tom.wallsten@unc.edu Tel +1-919-962-2538, fax +1-919-962-2537 Send all other questions concerning the Mathematical Psychology Meeting to: Ms. Colleen R. Schwoerke Division of Continuing Education CB 1020, Friday Center University of North Carolina Chapel Hill, NC 27599-1020, U.S.A. E-mail smp96@cs.unc.edu Tel +1-919-962-6298, fax +1-919-962-2061 Expenses: Registration fees will be kept very low, as in past SMP conferences. Low-cost dorm accommodations will be available, as will standard hotel rooms. Travel: The University of North Carolina at Chapel Hill is approximately 20-25 minutes from the Raleigh-Durham International Airport (RDU). Information about accommodations and transportation will be sent in early spring to members of the Society for Mathematical Psychology; others should contact Colleen Schwoerke at the above address. Information about the Society for Mathematical Psychology is available via the World Wide Web at http://www.socsci.uci.edu/smp/. Sponsors: University of North Carolina at Chapel Hill -- College of Arts and Sciences, Department of Psychology, Department of Computer Science Society for Mathematical Psychology ------------------------------ From: Eric Brill Subject: Call For Papers: Conf. on Empirical NLP Date: Mon, 29 Jan 1996 09:16:32 -0500 ACL's Special Interest Group SIGDAT announces the CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING FINAL CALL FOR PAPERS * FINAL CALL FOR PAPERS * FINAL CALL FOR PAPERS FINAL CALL FOR PAPERS * FINAL CALL FOR PAPERS * FINAL CALL FOR PAPERS The Conference on Empirical Methods in Natural Language Processing will be held in conjunction with the 50th Anniversary celebration of the Eniac Computer, taking place at the University of Pennsylvania May 17-18, 1996. In the spirit of SIGDAT events, this conference will offer a general forum for novel research in corpus-based and statistical natural language processing. Areas of interest include (but are not limited to): automatic linguistic annotation of text (eg. phrase structure, word senses, parts of speech), language modelling, machine translation, spelling correction and lexicography. In addition to providing a general forum, the conference will be centered around the following theme: Algorithm or Representation? Many novel approaches to empirical natural language processing have been developed recently. How much of a method's success is due to the particular algorithm used, and how much to the richness and appropriateness of the feature set? Is it true that diverse algorithms tend to perform roughly the same given the same training data and feature set? Where are the greatest benefits to be found: in refining the representation, enhancing the algorithm or increasing the training set size? Papers providing quantitative comparisons are especially welcome. We encourage submission of papers addressing this topic, as well as papers describing strengths, weaknesses, and advances in the areas of algorithms and representations appropriate for corpus-based natural language processing. However the conference will be diverse in scope and all innovative papers on empirical methods in NLP will be welcome. PROGRAM CHAIR: Eric Brill, Johns Hopkins University and co-chair: Ken Church, AT&T Bell Laboratories SPONSORS: Department of Computer and Information Science, University of Pennsylvania. Lexis-Nexis, a Division of Reed Elsevier, Inc. SIGDAT, a special interest group of the ACL. SCHEDULE: Submission Deadline: February 20 Notification of Acceptance: March 18 Camera-ready Final Papers: April 15 Conference Dates: May 17-18 FORMAT FOR SUBMISSION: Authors should submit a full-length paper (3500-8000 words) either electronically or in hard-copy. Electronic submissions must either be plain ascii text or a single latex file. Hard copy submissions should include six (6) copies of the paper. Please be sure to include your e-mail address on your paper. Unless requested otherwise, notification of acceptance will be sent electronically to the first author. A paper accepted for presentation at this conference cannot be presented or have been presented at any other meeting with publicly available proceedings. Papers that are being submitted to other conferences must include notification of this fact with the submission. CONTACT AND ADDRESS FOR SUBMISSION: Eric Brill: EMNLP Conference Department of Computer Science 3400 N. Charles St. Room 224 NEB Johns Hopkins University Baltimore, Md. 21218-2694 brill@cs.jhu.edu http://www.cs.jhu.edu/faculty/brill/Conf_on_Emp_Meth.html SigDat Home Page: http://www.cis.upenn.edu/~yarowsky/sigdat.html PROGRAM COMMITTEE: Claire Cardie, Cornell University Eugene Charniak, Brown University Yuqing Gao, IBM Marti Hearst, Xerox PARC Gunnel Kallgren, Stockholm University Raymond J. Mooney, University of Texas, Austin Yoshinori Sagisaka, ATR Geoffrey Sampson, Sussex University David Yarowsky, Johns Hopkins University Joe Zhou, Lexis-Nexis REGISTRATION INFORMATION: Will be posted shortly. NOTE: This conference will be complementary to the Fourth Workshop on Very Large Corpora (http://www.ling.umu.se/SIGDAT/WVLC-4.html), being held at COLING-96 in Copenhagen on August 4, 1996. For information on other events being held in conjunction with the 50th anniversary of the ENIAC computer, see: http://homepage.seas.upenn.edu/~museum/ For information on visiting Philadelphia, see: http://www.libertynet.org/phila-visitor ------------------------------ From: Debra Wallace Subject: SDAIR'96 - Advance Program Date: Mon, 29 Jan 1996 12:27:54 -0800 Fifth Annual Symposium on Document Analysis and Information Retrieval April 15 - 17, 1996 Alexis Park Resort Las Vegas, Nevada Sponsored by the Information Science Research Institute and The Howard R. Hughes College of Engineering University of Nevada, Las Vegas Symposium Chair Henry S. Baird, AT&T Bell Laboratories Invited Speakers Hans-Peter Frei, Union Bank of Switzerland Michael Lesk, Bellcore Juergen Schuermann, Daimler Benz Research Center Debate Teams Henry S. Baird, AT&T Bell Laboratories Robert Haralick, University of Washington Daniel Lopresti, Panasonic Technologies, Inc. George Nagy, Rensselaer Polytechnic Institute Document Analysis Committee Andreas Dengel, Chair, German Research Center for Artificial Intelligence (DFKI) Norbert Bartneck, Daimler Benz Research Center Hiromichi Fujisawa, Hitachi Central Research Lab Jonathan Hull, Ricoh California Research Center Junichi Kanai, University of Nevada, Las Vegas Larry Spitz, Daimler Benz Research Center Suzanne Taylor, Loral Research Laboratory Karl Tombre, INRIA Lorraine Information Retrieval Committee Jan Pedersen, Chair, Xerox Palo Alto Research Center Susan Dumais, Bellcore Stephen Gallant, Belmont Donna Harman, National Institute of Standards & Technology Marti Hearst, Xerox Palo Alto Research Center David Lewis, AT&T Bell Laboratories Peter Schauble, Swiss Federal Institute of Technology Kazem Taghva, University of Nevada, Las Vegas Yiming Yang, Mayo Clinic/Foundation Symposium Manager Debbie Wallace University of Nevada, Las Vegas Information Science Research Institute 4505 Maryland Parkway, Box 454021 Las Vegas, NV 89154-4021 (702)895-3338 fax:(702)895-1183 sdair@isri.unlv.edu CONFERENCE SCHEDULE Sunday, April 14, 1996 7:00pm - 10:00pm Alexis Park Resort Reception and Registration Monday, April 15, 1996 7:00am - 11:00am Alexis Park Resort Registration 8:15am - 8:30am Alexis Park Resort Welcome Henry S. Baird, Symposium Chair AT&T Bell Laboratories William R. Wells, Dean Howard R. Hughes College of Engineering University of Nevada, Las Vegas Kazem Taghva, Associate Director Information Science Research Institute University of Nevada, Las Vegas 8:30am - 9:15am Alexis Park Resort Invited Speaker Substituting Images for Books: Library Economics, Technology, and Politics Michael Lesk Bellcore 9:15am - 10:15am Alexis Park Resort Session 1 Maximum Spanning Trees for Text Segmentation Antonio P. Dias; Harvard University In-house Mail Distribution by Automatic Address and Content Interpretation Thomas Bruckner, Peter Suda, Hans Ulrich Block, Gerd Maderlechner; Siemens AG, Corporate Research and Development 10:15am - 10:30am Alexis Park Resort Refreshment Break 10:30am - 12:00pm Alexis Park Resort Session 2 USeg: A Retargetable Word Segmentation Procedure for Information Retrieval Jay M. Ponte, W. Bruce Croft; University of Massachusetts Text Categorization: A Symbolic Approach Isabelle Moulinier, *Gailius Raskinis, Jean-Gabriel Ganascia; University of Paris, *Vtautas Magnus University Support Tools for Visual Information Management Gokhan Kutlu, Bruce A. Draper, Eliot B. Moss, Edward M. Riseman; University of Massachusetts 12:00pm - 1:15pm Lunch Alexis Park Resort 1:15pm - 2:00pm Alexis Park Resort Invited Speaker Text Recognition - From Pixels to Meaning Juergen Schuermann Daimler Benz Research Center 2:00pm - 3:30pm Alexis Park Resort Session 3 Edit Distance of Regular Languages Horst Bunke; University of Bern Language Identification: Examining the Issues Penelope Sibun, *Jeffrey C. Reynar; Northwestern University, *University of Pennsylvania Fast Decision Tree Ensembles for Optical Character Recognition Harris Drucker; AT&T Bell Laboratories 3:30pm - 3:45pm Alexis Park Resort Refreshment Break 3:45pm - 5:15pm Alexis Park Resort Session 4 Length Normalization in Degraded Text Collections Amit Singhal, Gerard Salton, Chris Buckley; Cornell University Extraction of Thematically Relevant Text from Images Francine R. Chen, Dan S. Bloomberg; Xerox Palo Alto Research Center Measuring the Effects of Data Corruption on Information Retrieval Elke Mittendorf, Peter Schauble; Swiss Federal Institute of Technology (ETH) 6:00pm - 10:00pm Happy Hour Dinner Boyd Dining Room, Frank and Estella Beam Hall, William F. Harrah College of Hotel Adminstration, UNLV Tuesday, April 16, 1996 7:30am - 11:00am Alexis Park Resort Registration 8:00am - 8:45am Alexis Park Resort Invited Speaker Information Retrieval - From Academic Research to Practical Applications Hans-Peter Frei Union Bank of Switzerland 8:45am - 10:15am Alexis Park Resort Session 5 Keyword-Based Browsing and Analysis of Large Document Sets Ido Dagan, Ronen Feldman, *Haym Hirsh; Bar-Ilan University, *Rutgers University Tailoring a Retrieval System for Naive Users Adrienne J. Kleiboemer, Manette B. Lazear, *Jan O. Pedersen; MITRE Corporation, *Xerox Palo Alto Research Center Improving Full-Text Precision on Short Queries using Simple Constraints Marti A. Hearst; Xerox Palo Alto Research Center 10:15am - 10:30am Alexis Park Resort Refreshment Break 10:30am - 12:00pm Alexis Park Resort Session 6 Degraded Character Image Restoration John D. Hobby, Henry S. Baird; AT&T Bell Laboratories Automatically-Generated High-Reliability Features for Dichotomies of Printed Characters George Nagy, Xiaoyin Wang; Rensselaer Polytechnic Institute Retrieval Strategies for Noisy Text Daniel Lopresti, Jiangying Zhou; Panasonic Technologies, Inc. 12:00pm - 1:15pm Lunch Alexis Park Resort 1:15pm - 2:00pm Alexis Park Resort Team Debate "Defect Models are Important to Advance the State-of-the-Art of Optical Character Recognition" Affirmative Team: Henry S. Baird AT&T Bell Laboratories Robert Haralick University of Washington Negative Team: Daniel Lopresti Panasonic Technologies, Inc. George Nagy Rensselaer Polytechnic Institute Moderator: Tom Nartker Information Science Research Institute 2:00pm - 3:30pm Alexis Park Resort Session 7 A General-Purpose Japanese Optical Character Recognition System Sargur N. Srihari, Geetha Srikantan, Tao Hong, Brian Grom; State University of New York at Buffalo, Center of Excellence for Document Analysis and Recognition OCR and Voting Shell Fulfilling Specific Text Analysis Requirements Thorsten Jager; German Research Center for Artificial Intelligence (DFKI) Histograms to Evaluate OCR Accuracy and OCR Coupling Philippe Lefevre; EDF-Direction des Etudes et Recherches 3:30pm - 3:45pm Alexis Park Resort Refreshment Break 3:45pm - 5:15pm Alexis Park Resort Session 8 Logotype Detection in Compressed Images using Alignment Signatures A. Lawrence Spitz; Daimler Benz Research and Technology Center Reliable Recognition of Handwritten Marks in Checkboxes B. Latanzio, A. Garzotto; Swiss Life Information Systems Research Generalized Form Registration Using Structure-Based Techniques Michael D. Garris, Patrick J. Grother; National Institute of Standards and Technology 5:15pm Alexis Park Resort Symposium Adjourn Wednesday, April 17, 1996 8:20am - 8:30am Alexis Park Resort ISRI Welcome Thomas A. Nartker, Director Information Science Research Institute Howard R. Hughes College of Engineering University of Nevada, Las Vegas 8:30am - 9:45am Alexis Park Resort The Fifth Annual Test of OCR Accuracy Steve Rice Information Science Research Institute 9:45am - 10:00am Alexis Park Resort Refreshment Break 10:00am - 12:00pm Alexis Park Resort ISRI Research Reviews ISRI Staff Invited Speakers Hans-Peter Frei is the head of UBILAB, the Information Technology Research and Innovation Laboratory of the Union Bank of Switzerland (UBS). Dr. Frei holds a diploma in mathematics and a Ph.D. in computer science from the University of Zurich. Before joining UBS, he was a professor of computer science and chairman of the Department of Computer Science at ETH, the Swiss Federal Institute of Technology in Zurich, Switzerland. Prior to that he was the head of a management support unit of a large Swiss insurance company. Dr. Frei has held several research positions with various research institutions, such as HumRRO, IBM Research, Xerox PARC, University of Melbourne, and ICSI of the UC Berkeley. His research interests focus on interactive systems and in particular on information and document processing. Michael Lesk received the Ph.D. degree in Chemical Physics in 1969. He joined the computer science research group at Bell Laboratories, where he worked until 1984. Since 1984 he has managed the computer science research group at Bellcore. Dr. Lesk is best known for work in electronic libraries, including the CORE project for chemical information, and for writing some Unix system utilities including those for table printing (tbl), lexical analyzers (lex), and inter-system mail (uucp). His other technical interests include document production and retrieval software, computer networks, computer languages, and human-computer interfaces. Dr. Lesk has been chair of the Association for Computing Machinery's special interest groups on Language Analysis and on Information Retrieval. During 1987 he was Senior Visiting Fellow of the British Library, and he is currently Visiting Professor of Computer Science at University College London. Juergen Schuermann received the Dipl.-Ing. degree in Communications Engineering in 1960 and the Dr.-Ing. degree in 1968, both from the Technical University in Berlin, Germany. In 1963 Dr. Schuermann joined the Telefunken Research Laboratories in Ulm, Germany, which later became part of Daimler-Benz Research. Since 1974 he has been teaching Pattern Recognition at the Technical University of Darmstadt where he has served as Honorary Professor since 1981. Presently he is heading the Pattern Understanding Group of the Information Technology Department at Daimler-Benz Research embracing efforts in Text, Speech and Image Understanding. Together with his research group and the respective development departments he has been closely involved in the development of document understanding systems - especially in the postal business (AEG-ElectroCom) and in speech understanding systems, vision based driver assistance systems, and imaging radar systems for traffic applications. Dr. Schuermann is the general chair of the forthcoming International Conference in Document Analysis and Recognition ICDAR'97, to be held in August 1997 in Ulm Germany. Debate Teams Henry S. Baird is a Member of Technical Staff at the Computing Science Research Center, AT&T Bell Laboratories, Murray Hill, New Jersey. His research focuses on the design and analysis of algorithms for machine vision with emphasis on the interpretation of images of printed documents. Dr. Baird is an Area Editor for the journal Computer Vision and Image Understanding. In 1989-91, he was an Associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence. He was principal organizer of the 1990 IAPR Workshop on Syntactic and Structural Pattern Recognition. His Princeton University Ph.D. thesis on algorithms for image matching won a 1984 ACM Distinguished Dissertation Award and was published by the MIT Press. In 1976, his Master's thesis gave the first complete description of the sweep-line algorithm, a fundamental technique in computational geometry. Dr. Baird is a senior member of the IEEE, a member of ACM, and active in the IAPR. Bob Haralick is the Boeing Clairmont Egtvedt Professor in Electrical Engineering at the University of Washington. His recent work is in shape analysis and extraction using the techniques of mathematical morphology, robust pose estimation, techniques for making geometric inferences from perspective projection information, propagation of random perturbations through image analysis algorithms, and in document image analysis. Dr. Haralick joined the faculty of the Electrical Engineering Department at the University of Kansas from 1975 to 1978. In 1979 he joined the EE Department at Virginia Polytechnic Institute where he was Professor and Director of the Spatial Data Analysis Laboratory. From 1984 to 1986, he served as Vice President of Research at Machine Vision International in Ann Arbor, MI. Professor Haralick is a Fellow of IEEE for his contributions in computer vision and image processing. He is a Fellow of the IAPR for his contributions in image processing, computer vision and mathematical morphology. He has served on the Editorial Board of IEEE PAMI and is a past associate editor of IEEE Systems, Man, and Cybernetics and IEEE Image Processing. He currently serves on the Editorial board of Real Time Imaging and is an associate editor for Journal of Electronic Imaging. Dr. Haralick received a B.A. in Mathematics from the University of Kansas in 1964, a B.S. degree in Electrical Engineering in 1966 and an M.S. degree in Electrical Engineering in 1967. He completed his Ph.D. at the University of Kansas in 1969. Daniel Lopresti received the A.B. degree in Mathematics from Dartmouth College in 1982, and the Ph.D. degree in Computer Science from Princeton University in 1987. From 1986 until 1991, he was on the faculty of the Computer Science Department at Brown University. In 1991 he joined the newly-formed Matsushita Information Technology Laboratory as a Senior Scientist and leader of the Carbon Project. His research interests include document analysis, information retrieval, parallel VLSI architectures, and computational aspects of molecular biology. George Nagy received the B.Eng. and M.Eng. degrees from McGill University, and the Ph.D. in Electrical Engineering from Cornell University in 1962. For the next ten years Dr. Nagy conducted research on various aspects of pattern recognition and OCR at the IBM T.J. Watson Research Center in Yorktown Heights. From 1972 to 1985 he was Professor of Computer Science at the University of Nebraska - Lincoln, and worked on remote sensing applications, geographic information systems, computational geometry, and human-computer interfaces. Since 1985 he has been Professor of Computer Engineering at Rensselaer Polytechnic Institute. Dr. Nagy has held visiting appointments at the Stanford Research Institute, Cornell, the University of Montreal, the National Scientific Research Institute of Quebec, the University of Genoa and the Italian National Research Council in Naples and Genoa, AT&T Bell Laboratories, IBM Almaden, McGill University, and the Information Science Research Institute at UNLV. In addition to document image analysis and character recognition, his interests include solid modeling, finite-precision spatial computation, and computer vision. Registration Pre-Registration: before March 15, 1996 On-site Registration: Sunday, April 14, 7:00pm to 10:00pm Monday, April 15, 7:00am to 11:00am Tuesday, April 16, 7:30am to 11:00am Location: Alexis Park Resort Cost: $425.00 before March 15, 1996 $500.00 after March 15, 1996 Dinner Monday April 15, 1996 The College of Hotel Administration at the University of Nevada, Las Vegas is one of the finest programs of its type in the nation, and has an international reputation as well. We are delighted to have the students from the College's Food and Beverage Management Department prepare and serve an outstanding dinner for symposium guests on Monday evening from 6:00pm to 10:00pm. The dinner will be held in the Boyd Dining Room in Frank and Estella Beam Hall. The cost is $20 per person. For resevations please fill out the section on the attached symposium registration form. Hotel Accommodations Alexis Park Resort, located near the center of the Las Vegas strip, is the host hotel for the 1996 Symposium. If you choose to stay at the Alexis Park Resort, please make hotel reservations no later than March 14 to ensure room availability. A reservation form is included in this advance program for your convenience. Due to convention season in Las Vegas, ROOMS WILL FILL UP QUICKLY AT ALL HOTELS. Please make hotel reservations as soon as possible. Should you choose to stay at a hotel other than the host hotel, the Las Vegas Convention and Visitors Authority can give hotel information and make all hotel room reservations throughout the city of Las Vegas. For more information please call the Las Vegas Convention and Visitors Authority 1-800-332-5333. Fifth Annual Symposium on Document Analysis and Information Retrieval INFORMATION SCIENCE RESEARCH INSTITUTE University of Nevada, Las Vegas April 15-17, 1996 Conference Registration Form Name: ________________________________________________________________________ Title: _______________________________________________________________________ Company: _____________________________________________________________________ Address: _____________________________________________________________________ City: ________________________________________________________________________ State/Country: ______________________________________ Zip: ___________________ Telephone: ___________________________Fax: ___________________________________ E-mail Address: ______________________________________________________________ Registration Fees Pre-Reg Regular Amount before 3/15/96 after 3/15/96 Conference Registration $425.00 $500.00 $____________ Includes lunch Monday, 4/15/96; and lunch Tuesday, 4/16/96) Monday Dinner (per person) $ 20.00 $____________ Conference Proceedings (Extra Proceedings) $ 50.00 $____________ (One Proceedings is included as part of the registration fee) 1995 CD-ROM $100.00 $____________ (1995 Conference Proceedings and Annual Report) 1992, 1993 and 1994 CD-ROM $100.00 $____________ (1992, 1993 and 1994 Conference Proceedings and 1993 and 1994 Annual Report) TOTAL AMOUNT DUE: $____________ Enclosed is my payment payable by (check one): Check/Money Order _____ Mastercard _____ VISA _____ Discover _____ Make checks/money orders payable to: UNLV Board of Regents. All checks must be in U.S. Dollars and drawn on a U.S. Bank. For payment by credit card please fill out the following information: Credit Card Number:_______________________________ Expiration Date:__________ Please Print Name (as it appears on card):____________________________________ I authorize ISRI/UNLV to debit my account for the TOTAL AMOUNT DUE: signature: ___________________________________ Mail completed conference registration form and payment to: Symposium Manager Information Science Research Institute Telephone (702)895-4571 University of Nevada, Las Vegas Fax (702)895-1183 4505 Maryland Parkway Email sdair@isri.unlv.edu Box 454021 Las Vegas, NV 89154-4021 Alexis Park Resort Hotel Registration Form P.O. Box 95698 Las Vegas, NV 89193-5698 Rooms reserved under the name: SDAIR '96 Mail your reservation directly to Alexis Park Resort or call Room Reservations: (800)582-2228 Fax: (702)796-4334 Reservations received after March 14, 1996 will be accepted on a space available basis only. Please reserve accommodations for: Name: ________________________________________________________________________ Home Address: ________________________________________________________________ City: _____________________ State/Country: __________________ Zip: ___________ Company Name: ________________________________________________________________ Business Address: ____________________________________________________________ City: _____________________ State/Country: __________________ Zip: ___________ Business Phone: ______________________________________________________________ SINGLE OCCUPANCY - $100.00 (+8% tax) TRIPLE OCCUPANCY - $115.00 (+8% tax) DOUBLE OCCUPANCY - $100.00 (+8% tax) QUAD OCCUPANCY - $130.00 (+8% tax) Will Arrive: _____________________________, 1996 Time: ____________________ Will Depart: _____________________________, 1996 Time: ____________________ Enclosed is my deposit payable by (check one): Check _____ Mastercard _____ JCB _____ Visa _____ American Express _____ Carte Blanche _____ Discover _____ Diners Club _____ Credit Card Number: __________________________________________________________ Expiration Date: _____________________________________________________________ Print name as it appears on card: ____________________________________________ ------------------------------ End of ML-LIST (Digest format) ****************************************