From Dave_Touretzky@DST.BOLTZ.CS.CMU.EDU Sun Feb 9 22:47:58 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id WAA28052 for ; Sun, 9 Feb 1997 22:47:51 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id WAA25537 for ; Sun, 9 Feb 1997 22:47:49 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa12390; 9 Feb 97 22:17:14 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa12387; 9 Feb 97 21:55:43 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05222; 9 Feb 97 21:55:29 EST Received: from DST.BOLTZ.CS.CMU.EDU by B.GP.CS.CMU.EDU id aa24512; 9 Feb 97 21:45:11 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05116; 9 Feb 97 21:44:52 EST To: Connectionists@cs.cmu.edu Reply-To: Dave_Touretzky@cs.cmu.edu Subject: CNBC summer undergraduate research program Date: Sun, 09 Feb 97 21:44:50 EST Message-ID: <5114.855542690@DST.BOLTZ.CS.CMU.EDU> From: Dave_Touretzky@DST.BOLTZ.CS.CMU.EDU The Center for the Neural Basis of Cognition, a joint project of Carnegie Mellon University and the University of Pittsburgh, is seeking applications from top-quality undergraduates interested in pursuing summer research in cognitive or computational neuroscience. The CNBC summer training program is a ten week intensive program of lectures, laboratory tours, and guided research. State of the art facilities include computerized microscopy; laboratories for human and animal electrophysiological recording; behavioral assessment laboratories for rat, primate, and human experimentation; MRI and PET scanners for brain imaging; the Pittsburgh Supercomputing Center; and a regional medical center providing access to human clinical populations. The Summer Training Program is a National Science Foundation sponsored program; we expect to support ten students in each of the next five years. Applications are encouraged from students with interests in biology, neuroscience psychology, engineering, physics, mathematics, computer science, or robotics. To be eligible, students must not yet have completed their bachelor's degree at the time they participate. The application deadline is March 15, 1997. For more information about the program, and detailed application instructions, see our web site at: http://www.cnbc.cmu.edu/Training/summer/index.html In addition to its summer program, the Center for the Neural Basis of Cognition (CNBC) offers an interdisciplinary training program for Ph.D. and postdoctoral students in collaboration with various affiliated departments at Carnegie Mellon University and the University of Pittsburgh. This training program is the descendant of the Neural Processes in Cognition program started in 1990 under the National Science Foundation. We now have thirty six graduate students and thirty five faculty affiliated with the CNBC. The program focuses on understanding higher level brain function in terms of neurophysiological, cognitive, and brain imaging data complemented with computational modeling. Individually designed programs of study encompass cellular and systems neuroscience, computational neuroscience, cognitive modeling, and brain imaging. For a brochure describing the graduate training program and application materials, contact us at the following address: Center for the Neural Basis of Cognition 115 Mellon Institute 4400 Fifth Avenue Pittsburgh, PA 15213 Telephone: (412) 268-4000 Fax: (412) 268-5060 Email: cnbc-admissions@cnbc.cmu.edu This material is also available on our web site at http://www.cnbc.cmu.edu Faculty: The CNBC training faculty includes: German Barrionuevo (Pitt Neuroscience): LTP in hippocampal slice; Marlene Behrmann (CMU Psychology): spatial representations in parietal cortex; Pat Carpenter (CMU Psychology): mental imagery, language, and problem solving; Jonathan Cohen (CMU Psychology): schizophrenia; dopamine and attention; Carol Colby (Pitt Neuroscience): spatial reps. in primate parietal cortex; Bard Ermentrout (Pitt Mathematics): oscillations in neural systems; Julie Fiez (Pitt Psychology): fMRI studies of language; John Horn (Pitt Neurobiology): synaptic learning in autonomic ganglia; Allen Humphrey (Pitt Neurobiology): motion processing in primary visual cortex; Marcel Just (CMU Psychology): visual thinking, language comprehension; Eric Klann (Pitt Neuroscience): hippocampal LTP and LTD; Alan Koretsky (CMU Biological Sciences): new fMRI techniques for brain imaging; Tai Sing Lee (CMU Comp. Sci.): primate visual cortex; computer vision; David Lewis (Pitt Neuroscience): anatomy of frontal cortex; James McClelland (CMU Psychology): connectionist models of cognition; Carl Olson (CNBC): spatial representations in primate frontal cortex; David Plaut (CMU Psychology): connectionist models of reading; Michael Pogue-Geile (Pitt Psychology): development of schizophrenia; John Pollock (CMU Biological Sci.): neurodevelopment of the fly visual system; Walter Schneider (Pitt Psychology): fMRI studies of attention and skill acquisition; Charles Scudder (Pitt Neurobiology): motor learning in cerebellum; Susan Sesack (Pitt Neuroscience): anatomy of the dopaminergic system; Dan Simons (Pitt Neurobiology): sensory physiology of the cerebral cortex; William Skaggs (Pitt Neuroscience): representations in rodent hippocampus; and David Touretzky (CMU Comp. Sci.): hippocampus, rat navigation, animal learning. Walter Schneider David Touretzky Professor of Psychology Computer Science Department University of Pittsburgh Carnegie Mellon University From meunier@orphee.polytechnique.fr Mon Feb 10 17:11:53 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id RAA14494 for ; Mon, 10 Feb 1997 17:11:44 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id RAA14897 for ; Mon, 10 Feb 1997 17:11:42 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa13942; 10 Feb 97 16:41:32 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa13940; 10 Feb 97 16:28:11 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa06175; 10 Feb 97 16:27:35 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa02905; 10 Feb 97 7:58:34 EST Received: from polytechnique.polytechnique.fr by CS.CMU.EDU id aa18680; 10 Feb 97 7:57:43 EST Received: from orphee.polytechnique.fr (orphee.polytechnique.fr [129.104.3.2]) by polytechnique.polytechnique.fr (z.y.z/x.y.z) with ESMTP id NAA03781 for ; Mon, 10 Feb 1997 13:59:29 +0100 (MET) Received: from [129.104.10.16] (binah.polytechnique.fr [129.104.10.16]) by orphee.polytechnique.fr (x.y.z/x.y.z) with SMTP id NAA28697 for ; Mon, 10 Feb 1997 13:56:56 +0100 (MET) Message-Id: Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Date: Mon, 10 Feb 1997 14:02:44 +0100 To: Connectionists@cs.cmu.edu From: Claude Meunier Research associate Center for Theoretical Physics Ecole Polytechnique, France The Center for Theoretical Physics invites applications for a possible one year position of research associate (no teaching duties), starting Fall 1997. Six month stays may also be considered. Candidates are expected to carry out their research in the framework of our existing research programs in: - computational neurosciences - condensed matter - field theory and particle physics - plasma physics Applicants should submit a resume with publications list, statement of research interests, and two letters of references to: Dr. M.-N. Bussac Centre de Physique Th=E9orique Ecole Polytechnique 91128 Palaiseau cedex France =46ax: 00 33 01 69 33 30 08 E-mail: bussac@cpth.polytechnique.fr Send requests of information on this temporary position and post doctoral positions in theoretical physics at Ecole Polytechnique to the same address. The closing date for the receipt of applications is March 15, 1997. From klaus@prosun.first.gmd.de Mon Feb 10 18:47:07 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id SAA16879 for ; Mon, 10 Feb 1997 18:46:54 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id SAA16896 for ; Mon, 10 Feb 1997 18:46:52 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa13955; 10 Feb 97 16:51:01 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa13944; 10 Feb 97 16:29:05 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa06185; 10 Feb 97 16:28:13 EST Received: by B.GP.CS.CMU.EDU id ac08030; 10 Feb 97 13:35:04 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa07882; 10 Feb 97 13:23:35 EST Received: from prosun.first.gmd.de by EDRC.CMU.EDU id aa20800; 10 Feb 97 13:22:16 EST Received: by prosun.first.gmd.de (4.1/SMI-4.1) id AA06771; Mon, 10 Feb 97 19:22:12 +0100 Message-Id: <9702101822.AA06771@prosun.first.gmd.de> To: Connectionists@cs.cmu.edu Subject: Call for Tricks ;-) Date: Mon, 10 Feb 1997 19:22:12 +0100 From: "Klaus-R. Mueller" ********************************************* * Call for Papers * * Tricks of the Trade * ********************************************* Dear Colleagues, At the Nips*96 workshops we had a workshop called "Tricks of the Trade: How to Make Algorithms Really Work". As a follow-up to this workshop, we are collecting papers for a "Book of Tricks" (this is our working title), which will be tentatively published in the LNCS State-of-the-Art Surveys series. We would like to invite you to contribute. What is a Trick?: A technique, rule-of-thumb, or heuristic that * is easy to describe and understand * can make a real difference in practice * is not (yet) part of well documented technique * has broad application and may or may not (yet) have a theoretical explanation. Content and Format: In order to keep everything focussed, we suggest the following main topics of the book: 1. architectural tricks 2. sampling and data preprocessing 3. speeding learning procedures 4. improving generalization and optimization To give consistency across papers, we would like there to be a structural similarity in the contents which is based on the outline we proposed for the talks: - intro/motivation - trick - where has it been tried and how well does it work? - why does it work? - possible theoretical explanation (if any), - heuristic explanation (if any) & discussion For More Details: Please look at the call for papers on our web site: In the US: http://www.willamette.edu/~gorr/tricks/guidelines.html In Europe: http://www.first.gmd.de/persons/Mueller.Klaus-Robert/CALL.html If you have questions, please email to: Jenny Orr (gorr@willamette.edu) Klaus-Robert M"uller (klaus@first.gmd.de) Rich Caruana (caruana@cs.cmu.edu) From steinr@moodys.com Tue Feb 11 10:18:57 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id KAA27379 for ; Tue, 11 Feb 1997 10:18:50 -0600 Received: from bandon.moodys.com (firewall-user@BANDON.MOODYS.COM [141.160.2.224]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id KAA00244 for ; Tue, 11 Feb 1997 10:18:12 -0600 (CST) Received: by bandon.moodys.com; id AA21208; Tue, 11 Feb 97 11:20:06 EST Received: from hannibal(141.160.10.156) by bandon.moodys.com via smap (V3.1.1) id xma021201; Tue, 11 Feb 97 11:19:58 -0500 Received: from smtpgate1.moodys.com by moodys.com (4.1/SMI-4.1) id AA29843; Tue, 11 Feb 97 11:16:22 EST Received: by smtpgate1.moodys.com with Microsoft Mail id <33009C2B@smtpgate1.moodys.com>; Tue, 11 Feb 97 11:19:55 EST From: "Stein, Roger" To: "'smtp:ml@cs.wisc.edu'" Subject: A new book on applying learning systems to business Date: Tue, 11 Feb 97 11:17:00 EST Message-Id: <33009C2B@smtpgate1.moodys.com> Encoding: 126 TEXT X-Mailer: Microsoft Mail V3.0 Members of the Santa Fe Institute mailing list may have already received this. Apologies... My colleague, Vasant Dhar, and I have just finished a short book on applying intelligent and adaptive systems to business problems. It may be of interest to others working in the field. There are two versions of the book available, one is suited to business people and one is suited to teaching. The book provides a practical methodology for mapping business problems onto solutions involving neural networks, GAs, nearest-neighbor algorithms, etc. We also provide extended case studies of firms that have successfully done this. The reaction to the book, in both the academic and professional community, seems to be favorable: "Intelligent Systems are becoming vital at all levels of management from the CEO to the foreman. Dhar and Stein provide one of the clearest and most accessible treatments to date of the subject." - Herbert A. Simon, Nobel Laureate "Seven Methods effectively bridges the gap between lofty technical explanation and the down-to-earth business application of a brand new world of modeling technologies." - Win Farrell, Partner, Coopers and Lybrand A brief summary of the book follows: Seven Methods for Transforming Corporate Data into Business Intelligence combines a thorough treatment of techniques for applying intelligent systems to decision support with a practical framework for analyzing business problems. Vasant Dhar (Principal, Morgan Stanley and New York University) and Roger Stein (Vice President, Moody s Investors Service and New York University) present in clear and vivid terms the essentials of modern decision support. Seven Methods takes a three stage approach to discussing these new technologies. The book is organized around: ? A framework for analyzing business decision problems and mapping solutions onto them ? An intuitive but full discussion of the technologies for data mining and automated decision systems ? A series of extensive case studies that show, using the framework, how major organizations have made use of these technologies In addition to discussing technologies, Dhar and Stein introduce a unified methodology for analyzing organizations business problems and evaluating potential solutions. This framework, based on the authors years of combined experience applying intelligent systems to real business decision problems, encourages business people to think critically about how the strengths and weaknesses of each technique relate to the particular dynamics of an organization and its problems. The authors show not only when a particular modeling method may be useful, but also when its attributes might make it undesirable for a particular problem. The text does not limit itself to one or a few techniques, but rather views various AI and database techniques as components of a toolbox that, if used correctly, can make organizations dramatically more intelligent. Seven Methods provides accessible detailed coverage of ? OLAP and data warehousing ? Genetic algorithms ? Neural networks ? Rule-based expert systems ? Fuzzy systems ? Case-based reasoning ? Machine learning The text adopts an informal, conversational style in their exposition. Despite the relaxed style, the book delves into the subtle aspects of each technique while keeping the text readable and non-technical. In order to make the material more accessible, the text makes frequent use of rich graphics. The graphical representation of complex concepts are invaluable in elucidating these topics. To drive home the discussions of modeling techniques and organizational dynamics, the book also provides extended case studies that show in detail how the framework can be applied to analyzing the problems of real organizations. Cases are taken from the experience of firms in a diversity of industries solving an assortment of problems. Firms include: ? US WEST ? Moody s Investors Service ? Compaq Computer Corp. ? LBS Capital Management ? NYNEX, Inc. ? Kaufhof AG ? A. C. Neilsen Problem domains include: ? customer service ? scheduling ? data mining ? financial market prediction ? quality control ? consumer product marketing The book is available from Prentice-Hall: (Professional version) Seven Methods for Transforming Corporate Data into Business Intelligence, Upper Saddle River, NJ, Prentice-Hall, 1997. (Academic version) Intelligent Decision Support Methods: The Science of Knowledge Work, Upper Saddle River, NJ, Prentice-Hall, 1997. Online Orders: www.amazon.com Phone: 1-(800) 643-5506. Please give the operator the following "key code": E1001-A1(3). FAX: 1-(800) 835-5327. From meunier@orphee.polytechnique.fr Tue Feb 11 17:33:24 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id RAA00946 for ; Tue, 11 Feb 1997 17:33:18 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id RAA06801 for ; Tue, 11 Feb 1997 17:33:17 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa15802; 11 Feb 97 12:43:57 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa15797; 11 Feb 97 12:24:03 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa06861; 11 Feb 97 12:23:33 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa09258; 11 Feb 97 3:57:59 EST Received: from polytechnique.polytechnique.fr by EDRC.CMU.EDU id aa25741; 11 Feb 97 3:57:25 EST Received: from orphee.polytechnique.fr (orphee.polytechnique.fr [129.104.3.2]) by polytechnique.polytechnique.fr (z.y.z/x.y.z) with ESMTP id JAA17201 for ; Tue, 11 Feb 1997 09:58:46 +0100 (MET) Received: from [129.104.10.16] (binah.polytechnique.fr [129.104.10.16]) by orphee.polytechnique.fr (x.y.z/x.y.z) with SMTP id JAA22769 for ; Tue, 11 Feb 1997 09:56:52 +0100 (MET) Message-Id: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Date: Tue, 11 Feb 1997 10:02:01 +0100 To: Connectionists@cs.cmu.edu From: Claude Meunier Subject: research associate position Research associate Center for Theoretical Physics Ecole Polytechnique, France The Center for Theoretical Physics invites applications for a possible one year position of research associate (no teaching duties), starting Fall 1997. Six month stays may also be considered. Candidates are expected to carry out their research in the framework of our existing research programs in: - computational neurosciences - condensed matter - field theory and particle physics - plasma physics Applicants should submit a resume with publications list, statement of research interests, and two letters of references to: Dr. M.-N. Bussac Centre de Physique Th=E9orique Ecole Polytechnique 91128 Palaiseau cedex France fax: 00 33 01 69 33 30 08 E-mail: bussac@cpth.polytechnique.fr Send requests of information on this temporary position and post doctoral positions in theoretical physics at Ecole Polytechnique to the same address. The closing date for the receipt of applications is March 15, 1997. From karaali@ukraine.corp.mot.com Tue Feb 11 21:28:40 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id VAA01370 for ; Tue, 11 Feb 1997 21:28:35 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id VAA10433 for ; Tue, 11 Feb 1997 21:28:34 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa16519; 11 Feb 97 21:09:58 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa16517; 11 Feb 97 20:57:39 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa07114; 11 Feb 97 20:57:22 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa03750; 11 Feb 97 12:34:34 EST Received: from ftpbox.mot.com by EDRC.CMU.EDU id aa28169; 11 Feb 97 12:34:25 EST Received: from pobox.mot.com (pobox.mot.com [129.188.137.100]) by ftpbox.mot.com (8.7.6/8.6.10/MOT-3.8) with ESMTP id LAA18436 for ; Tue, 11 Feb 1997 11:34:21 -0600 (CST) Received: from ukraine.corp.mot.com (ukraine.ccrl.mot.com [182.1.83.20]) by pobox.mot.com (8.7.6/8.6.10/MOT-3.8) with SMTP id LAA18665 for ; Tue, 11 Feb 1997 11:34:19 -0600 (CST) Received: from fiji.mot.com by ukraine.corp.mot.com (4.1/SMI-4.1) id AA27097; Tue, 11 Feb 97 11:34:16 CST Received: by fiji.mot.com (SMI-8.6/SMI-SVR4) id LAA03748; Tue, 11 Feb 1997 11:34:16 -0600 Date: Tue, 11 Feb 1997 11:34:16 -0600 From: Orhan Karaali Message-Id: <199702111734.LAA03748@fiji.mot.com> To: Connectionists@cs.cmu.edu Subject: Motorola NN Speech Synthesizer Article X-Sun-Charset: US-ASCII FTP-host: archive.cis.ohio-state.edu FTP-filename: /pub/neuroprose/karaali.synthesis_wcnn96.ps.Z Motorola Neural Network Speech Synthesizer Article A new neural network based speech synthesizer has been developed here at Motorola Chicago Corporate Research Laboratories by the Speech Synthesis and Machine Learning Group. We believe that the quality of the synthesized speech it produces surpasses the current state of the art, particularly in naturalness. An invited paper describing this neural network speech synthesizer was presented in the Speech Session of the World Congress on Neural Networks 96 in San Diego. This paper is now available in the NEUROPROSE archive as karaali.synthesis_wcnn96.ps.Z. If you have a problem getting the paper from NEUROPROSE, I can email it to you. Orhan Karaali email: karaali@mot.com --------------------------------------------------------------------- Speech Synthesis with Neural Networks Orhan Karaali, Gerald Corrigan, and Ira Gerson Motorola, Inc., 1301 E. Algonquin Road, Schaumburg, IL 60196 karaali@mot.com, corrigan@mot.com, gerson@mot.com ABSTRACT Text-to-speech conversion has traditionally been performed either by concatenating short samples of speech or by using rule-based systems to convert a phonetic representation of speech into an acoustic representation, which is then converted into speech. This paper describes a system that uses a time-delay neural network (TDNN) to perform this phonetic-to-acoustic mapping, with another neural network to control the timing of the generated speech. The neural network system requires less memory than a concatenation system, and performed well in tests comparing it to commercial systems using other technologies. ----- End Included Message ----- From beiu@lanl.gov Wed Feb 12 14:52:06 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id OAA02324 for ; Wed, 12 Feb 1997 14:51:59 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id OAA28259 for ; Wed, 12 Feb 1997 14:51:58 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa17588; 12 Feb 97 14:13:39 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa17586; 12 Feb 97 13:52:11 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa07786; 12 Feb 97 13:51:23 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id an11809; 12 Feb 97 10:37:15 EST Received: from mailhost.lanl.gov by CS.CMU.EDU id aa09965; 11 Feb 97 22:53:45 EST Received: from newreg.lanl.gov (newreg.lanl.gov [128.165.3.60]) by mailhost.lanl.gov (8.8.5/8.8.3) with ESMTP id UAA18783 for ; Tue, 11 Feb 1997 20:53:38 -0700 (MST) Received: from dapspc10 by newreg.lanl.gov (8.7.5/SMI-4.1) id UAA20073; Tue, 11 Feb 1997 20:53:39 -0700 (MST) Message-Id: <2.2.32.19970212035018.003026f0@nis-pop.lanl.gov> X-Sender: beiu@nis-pop.lanl.gov X-Mailer: Windows Eudora Pro Version 2.2 (32) Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Date: Tue, 11 Feb 1997 20:50:18 -0700 To: Connectionists@cs.cmu.edu From: Valeriu Beiu Subject: CFP: IV Brazilian Symposium on Neural Networks SBRN'97 /\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\ I V t h B R A Z I L I A N S Y M P O S I U M O N N E U R A L N E T W O R K S SBRN'97 /\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\ Goiania, GO, Brazil, December 03 - 05, 1997 Sponsored by: Brazilian Computer Society (SBC) International Neural Networks Society (INNS) Organized by the School of Electrical Engineering (EEE) Federal University of Goias (UFG) Conference Chairmen: Weber Martins (EEE-UFG) Dibio Leandro Borges (EEE-UFG) ======================================================================= Latest information will be placed at the conference WWW-page http://www.eee.ufg.br/sbrn97/ ======================================================================= P u r p o s e ----------------------------------------------------------------------- The fourth Brazilian Symposium on Neural Networks will be held at the School of Electrical Engineering, Federal University of Goias (UFG), Goiania, GO (Brazil), on 3rd, 4th, and 5th December, 1997. The Brazilian Symposia on Neural Networks are organized by the interest group in Neural Networks of the Brazilian Computer Society. In order to promote research in Neural Networks and Evolutionary Computation, and scientific interchange among Brazilian AI researchers and practitioners, and their counterparts worldwide, papers from the international community are most welcome. The papers will be reviewed by an international program committee. T o p i c s o f I n t e r e s t ----------------------------------------------------------------------- Submissions are invited on substantial, original, and previously unpublished research in all aspects of Neural Networks, including, but not limited to: * Biological Perspectives * Cognitive Modeling * Dynamic Systems * Evolutionary Computation * Fuzzy Logic * Hardware Implementation * Hybrid Systems * Learning Models * Neural Network Algorithms and Architectures * Neural Network Applications * Optimization * Pattern Recognition and Image Processing * Robotics and Control * Signal Processing * Theoretical Models P r o g r a m C o m m i t t e e ----------------------------------------------------------------------- Nigel M. Allinson (Univ. Manchester Institute of Technology - UK) Jose Nelson Amaral (Pontificia Catholic University, RS - BRAZIL) William Armstrong (University of Alberta - CANADA) Valeriu Beiu (Los Alamos National Laboratory - USA) Dibio Leandro Borges * (Federal University of Goias - BRAZIL) Antonio de Padua Braga (Federal University of Minas Gerais - BRAZIL) Andre L.P. de Carvalho (University of Sao Paulo, S. Carlos - BRAZIL) Weber Martins * (Federal University of Goias - BRAZIL) Edilberto P. Teixeira (Federal University of Uberlandia - BRAZIL) Harold Szu (University of Southwestern Louisiana - USA) Germano C. Vasconcelos (Federal University of Pernambuco - BRAZIL) * Program Chairmen T i m e t a b l e ----------------------------------------------------------------------- Submissions due May 2nd, 1997 Notification of acceptance July 5th, 1997 Final manuscript due August 5th, 1997 Conference date December 3rd-5th, 1997 P a p e r S u b m i s s i o n s ----------------------------------------------------------------------- We invite submissions of scientific papers to any topic related to Neural Networks and Evolutionary Computation. Authors should submit four (4) copies of their papers in hard copy form. Neither computer files nor fax submission are acceptable. Submissions must be printed on 8 1/2 x 11 inch (21.59 x 27.94 cm) or A4 paper using 12 point type, and they must be a maximum of twenty (20) pages long, double space, including all figures and references. The reviewing process will be blind to the identities of the authors, please note that this requires that authors exercise some care not to identify themselves in their papers. Title page and paper body ------------------------- Each copy of the paper must include a title page, separate from the body of the paper, containing the title of the paper, the names and addresses of all authors (please, complete addresses including also e-mail and FAX), a short abstract of less than 200 words, and a list of keywords giving the area/subarea of the paper. The second page, on which the paper body begins, should include the same title, abstract, keywords, but not the names and affiliations of the authors. All paper submissions should be to the following address: --------------------------------------------------------- IVth Brazilian Symposium on Neural Networks (SBRN'97) (PAPER SUBMISSION) School of Electrical Engineering (EEE) Federal University of Goias (UFG) Pca. Universitaria s/n Setor Universitario 74605-220 Goiania, GO (BRAZIL) FAX: +55 62 202 - 0325 E-mail: sbrn97@eee.ufg.br Review criteria --------------- Papers will be subject to peer review by an international program committee. Selection criteria include accuracy and originality of ideas, clarity and significance of results and the quality of the presentation. P u b l i c a t i o n ----------------------------------------------------------------------- We are planning to publish the international proceedings with a major publishing house, and details will be available soon. Papers submitted in Portuguese or Spanish will be published in a separate volume. Both proceedings will be available at the conference. Please, note that at least one author should attend the conference for presentation of the accepted paper. I n q u i r i e s ----------------------------------------------------------------------- Inquiries regarding any aspect of the conference may be sent to the internet address: sbrn97@eee.ufg.br or to the Conference Chairmen: Weber Martins and Dibio Leandro Borges both at: School of Electrical Engineering Federal University of Goias Pca. Universitaria s/n Setor Universitario 74605-220 Goiania, GO (BRAZIL) \/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\ From wermter@nats5.informatik.uni-hamburg.de Wed Feb 12 22:17:44 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id WAA13312 for ; Wed, 12 Feb 1997 22:17:35 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id WAA08509 for ; Wed, 12 Feb 1997 22:17:34 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab17588; 12 Feb 97 14:14:34 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab17586; 12 Feb 97 13:52:16 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa07791; 12 Feb 97 13:51:38 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa12229; 12 Feb 97 10:44:33 EST Received: from [134.100.10.105] by CS.CMU.EDU id aa12531; 12 Feb 97 7:46:55 EST Received: from nats6 (nats6.informatik.uni-hamburg.de [134.100.10.106]) by nats5.informatik.uni-hamburg.de (8.6.10/8.6.10) with ESMTP id NAA03203 for ; Wed, 12 Feb 1997 13:46:36 +0100 From: Stefan Wermter Received: (wermter@localhost) by nats6 (SMI-8.6/8.6.10) id NAA12800 for Connectionists@cs.cmu.edu; Wed, 12 Feb 1997 13:45:25 +0100 Date: Wed, 12 Feb 1997 13:45:25 +0100 Message-Id: <199702121245.NAA12800@nats6> To: Connectionists@cs.cmu.edu Subject: JAIR article - connectionist natural language learning Content-Type: X-sun-attachment X-Sun-Charset: US-ASCII ----- Begin Included Message ----- From: jair-ed@ptolemy.arc.nasa.gov JAIR is pleased to announce the publication of the following article, which may be of interest to readers of this mailing list: Wermter, S. and Weber, V. (1997) "SCREEN: Learning a Flat Syntactic and Semantic Spoken Language Analysis Using Artificial Neural Networks", Volume 6, pages 35-85. Available in HTML, Postscript (1.1M) and compressed Postscript (290K). For quick access via your WWW browser, use this URL: http://www.cs.washington.edu/research/jair/abstracts/wermter97a.html More detailed instructions are below. Abstract: Previous approaches of analyzing spontaneously spoken language often have been based on encoding syntactic and semantic knowledge manually and symbolically. While there has been some progress using statistical or connectionist language models, many current spoken- language systems still use a relatively brittle, hand-coded symbolic grammar or symbolic semantic component.

In contrast, we describe a so-called screening approach for learning robust processing of spontaneously spoken language. A screening approach is a flat analysis which uses shallow sequences of category representations for analyzing an utterance at various syntactic, semantic and dialog levels. Rather than using a deeply structured symbolic analysis, we use a flat connectionist analysis. This screening approach aims at supporting speech and language processing by using (1) data-driven learning and (2) robustness of connectionist networks. In order to test this approach, we have developed the SCREEN system which is based on this new robust, learned and flat analysis.

In this paper, we focus on a detailed description of SCREEN's architecture, the flat syntactic and semantic analysis, the interaction with a speech recognizer, and a detailed evaluation analysis of the robustness under the influence of noisy or incomplete input. The main result of this paper is that flat representations allow more robust processing of spontaneous spoken language than deeply structured representations. In particular, we show how the fault-tolerance and learning capability of connectionist networks can support a flat analysis for providing more robust spoken-language processing within an overall hybrid symbolic/connectionist framework. The article is available via: -- comp.ai.jair.papers (also see comp.ai.jair.announce) -- World Wide Web: The URL for our World Wide Web server is http://www.cs.washington.edu/research/jair/home.html For direct access to this article and related files try: http://www.cs.washington.edu/research/jair/abstracts/wermter97a.html -- Anonymous FTP from either of the two sites below. Carnegie-Mellon University (USA): ftp://ftp.cs.cmu.edu/project/jair/volume6/wermter97a.ps The University of Genoa (Italy): ftp://ftp.mrg.dist.unige.it/pub/jair/pub/volume6/wermter97a.ps The compressed PostScript file is named wermter97a.ps.Z (290K) -- automated email. Send mail to jair@cs.cmu.edu or jair@ftp.mrg.dist.unige.it with the subject AUTORESPOND and our automailer will respond. To get the Postscript file, use the message body GET volume6/wermter97a.ps (Note: Your mailer might find this file too large to handle.) Only one can file be requested in each message. For more information about JAIR, visit our WWW or FTP sites, or send electronic mail to jair@cs.cmu.edu with the subject AUTORESPOND and the message body HELP, or contact jair-ed@ptolemy.arc.nasa.gov. ----- End Included Message ----- ***************************************************************** Dr. Stefan Wermter University of Hamburg Dept. of Computer Science Vogt-Koelln-Str. 30 D-22527 Hamburg Germany Email: wermter@informatik.uni-hamburg.de Phone: +49-5494 2531 Fax: +49-5494 2515 http://www.informatik.uni-hamburg.de/NATS/staff/wermter.html From lawrence@research.nj.nec.com Thu Feb 13 02:30:22 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id CAA16252 for ; Thu, 13 Feb 1997 02:30:16 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id CAA12100 for ; Thu, 13 Feb 1997 02:30:15 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa17604; 12 Feb 97 14:25:32 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa17590; 12 Feb 97 13:53:06 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa07797; 12 Feb 97 13:52:15 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa19741; 12 Feb 97 13:07:49 EST Received: from purgatory.nj.nec.com by CS.CMU.EDU id aa15680; 12 Feb 97 13:05:58 EST Received: (from lawrence@localhost) by purgatory.nj.nec.com (8.7.6/8.6.9) id NAA31782; Wed, 12 Feb 1997 13:05:44 -0500 Message-ID: <19970212130543.19266@purgatory.nj.nec.com> Date: Wed, 12 Feb 1997 13:05:43 -0500 From: Steve Lawrence To: connectionists@cs.cmu.edu Subject: Student Position: Learning for Agents and Multi-Agent Systems Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.61 The NEC Research Institute in Princeton, NJ has an immediate opening for a student research position in the area of learning for agents and multi-agent systems. Candidates must have experience in research and be able to effectively communicate research results. Ideal candidates will have knowledge of one or more machine learning techniques (e.g. neural networks, decision trees, rule based systems, and nearest neighbor techniques), and be proficient in the software implementation of algorithms. NEC Research provides an outstanding research environment with many recognized experts and excellent resources including several multiprocessor machines. Interested applicants should apply by email, mail or fax including their resumes and any specific interests in learning for agents and multi-agent systems to: Dr. C. Lee Giles NEC Research Institute 4 Independence Way Princeton NJ 08540 Phone: (609) 951 2642 Fax: (609) 951 2482 Email: giles@research.nj.nec.com -- Steve Lawrence <*> http://www.neci.nj.nec.com/homepages/lawrence From jbednar@cs.utexas.edu Fri Feb 14 20:50:06 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id UAA24468 for ; Fri, 14 Feb 1997 20:50:00 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id UAA16996 for ; Fri, 14 Feb 1997 20:49:58 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa20677; 14 Feb 97 20:01:12 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa20675; 14 Feb 97 19:37:56 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa01885; 14 Feb 97 19:37:26 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa11236; 14 Feb 97 17:16:51 EST Received: from mail.cs.utexas.edu by CS.CMU.EDU id aa02670; 14 Feb 97 17:16:06 EST Received: from duckula.cs.utexas.edu (jbednar@duckula.cs.utexas.edu [128.83.143.211]) by mail.cs.utexas.edu (8.8.5/8.8.5) with ESMTP id QAA21629; Fri, 14 Feb 1997 16:15:58 -0600 (CST) Received: by duckula.cs.utexas.edu (8.8.5/Client-1.5) id QAA35148; Fri, 14 Feb 1997 16:11:31 -0600 Date: Fri, 14 Feb 1997 16:11:31 -0600 Message-Id: <199702142211.QAA35148@duckula.cs.utexas.edu> From: jbednar@cs.utexas.edu To: connectionists@cs.cmu.edu CC: risto@cs.utexas.edu, sirosh@cs.utexas.edu, yschoe@cs.utexas.edu Subject: Overview paper and theses on the RF-LISSOM project Reply-to: jbednar@cs.utexas.edu The following paper (to appear in Psychology of Learning and Motivation) gives an overview of the RF-LISSOM project on modeling the primary visual cortex, ongoing at the UTCS Neural Networks Research Group. For those seeking details, please refer to the dissertation and the theses also announced below. All these publications (and others) are available from our web page at http://www.cs.utexas.edu/users/nn (under publications, self-organization; the direct ftp addresses are included below as well). Public domain LISSOM code, for self-organization in laterally connected maps, will be announced in the near future. -- The Authors ------------------------------------------------------------------------- SELF-ORGANIZATION, PLASTICITY, AND LOW-LEVEL VISUAL PHENOMENA IN A LATERALLY CONNECTED MAP MODEL OF THE PRIMARY VISUAL CORTEX Risto Miikkulainen, James A. Bednar, Yoonsuck Choe, and Joseph Sirosh Department of Computer Sciences, The University of Texas at Austin. In R. L. Goldstone, P. G. Schyns, and D. L. Medin (eds.), Psychology of Learning and Motivation, vol. 36, 1997 in press (36 pages). ftp://ftp.cs.utexas.edu/pub/neural-nets/papers/miikkulainen.visual-cortex.ps.Z Based on a Hebbian adaptation process, the afferent and lateral connections in the RF-LISSOM model organize simultaneously and cooperatively, and form structures such as those observed in the primary visual cortex. The neurons in the model develop local receptive fields that are organized into orientation, ocular dominance, and size selectivity columns. At the same time, patterned lateral connections form between neurons that follow the receptive field organization. This structure is in a continuously-adapting dynamic equilibrium with the external and intrinsic input, and can account for reorganization of the adult cortex following retinal and cortical lesions. The same learning processes may be responsible for a number of low-level functional phenomena such as tilt aftereffects, and combined with the leaky integrator model of the spiking neuron, for segmentation and binding. The model can also be used to verify quantitatively the hypothesis that the visual cortex forms a sparse, redundancy-reduced encoding of the input, which allows it to process massive amounts of visual information efficiently. ------------------------------------------------------------------------- A SELF-ORGANIZING NEURAL NETWORK MODEL OF THE PRIMARY VISUAL CORTEX Joseph Sirosh Department of Computer Sciences, The University of Texas at Austin. PhD Dissertation and Technical Report AI95-237, August 1995 (137 pages). ftp://ftp.cs.utexas.edu/pub/neural-nets/papers/sirosh.diss.tar This work is aimed at modeling and analyzing the computational processes by which sensory information is learned and represented in the brain. First, a general self-organizing neural network architecture that forms efficient representations of visual inputs is presented. Two kinds of visual knowledge are stored in the cortical network: information about the principal feature dimensions of the visual world (such as line orientation and ocularity) is stored in the afferent connections, and correlations between these features in the lateral connections. During visual processing, the cortical network filters out these correlations, generating a redundancy-reduced sparse coding of the visual input. Through massively parallel computational simulations, this architecture is shown to give rise to structures similar to those in the primary visual cortex, such as (1) receptive fields, (2) topographic maps, (3) ocular dominance, orientation and size preference columns, and (4) patterned lateral connections between neurons. The same computational process is shown to account for many of the dynamic processes in the visual cortex, such as reorganization following retinal and cortical lesions, and perceptual shifts following dynamic receptive field changes. These results suggest that a single self-organizing process underlies development, plasticity and visual functions in the primary visual cortex. ------------------------------------------------------------------------- TILT AFTEREFFECTS IN A SELF-ORGANIZING MODEL OF THE PRIMARY VISUAL CORTEX James A. Bednar Department of Computer Sciences, The University of Texas at Austin. Masters Thesis and Technical Report AI97-259, January 1997 (104 pages). ftp://ftp.cs.utexas.edu/pub/neural-nets/papers/bednar.thesis.tar The psychological phenomenon known as the tilt aftereffect was used to demonstrate the functional properties of RF-LISSOM, a self-organizing model of laterally connected orientation maps in the primary visual cortex. The same self-organizing processes that are responsible for the development of the map and its lateral connections are shown to result in tilt aftereffects as well. The model allows analysis of data that are difficult to measure in humans, thus providing a view of the cortex that is otherwise not available. The results give computational support for the idea that tilt aftereffects arise from lateral interactions between adapting feature detectors, as has long been surmised. They also suggest that indirect tilt aftereffects could result from the conservation of synaptic resources. The model thus provides a unified computational explanation of self-organization and both direct and indirect tilt aftereffects in the primary visual cortex. ------------------------------------------------------------------------- LATERALLY INTERCONNECTED SELF-ORGANIZING FEATURE MAP IN HANDWRITTEN DIGIT RECOGNITION Yoonsuck Choe Department of Computer Sciences, The University of Texas at Austin. Masters Thesis and Technical Report AI95-236, August 1995 (65 pages). ftp://ftp.cs.utexas.edu/pub/neural-nets/papers/choe.thesis.tar.Z An application of biologically motivated laterally interconnected synergetically self-organizing maps (LISSOM) to off-line recognition of handwritten digit is presented. The lateral connections of the LISSOM map learn the correlations between units through Hebbian learning. As a result, the excitatory connections focus the activity in local patches and lateral connections decorrelate redundant activity on the map. This process forms internal representations for the input that are easier to recognize than the input bitmaps themselves or the activation patterns on a standard Self-Organizing Map (SOM). The recognition rate on a publically available subset of NIST special database 3 with LISSOM is 4.0% higher than that based on SOM, and 15.8% higher than that based on raw input bitmaps. These results form a promising starting point for building pattern recognition systems with a LISSOM map as a front end.