From workshop@Physik.Uni-Wuerzburg.DE Mon Jun 19 20:30:16 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Mon, 19 Jun 95 20:30:14 -0500; AA20147 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Mon, 19 Jun 95 20:30:12 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa28916; 19 Jun 95 20:07:55 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa28912; 19 Jun 95 19:46:35 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa08104; 19 Jun 95 19:45:56 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa11555; 19 Jun 95 11:09:56 EDT Received: from wptx01.physik.uni-wuerzburg.de by RI.CMU.EDU id aa20561; 19 Jun 95 11:08:17 EDT Received: (from workshop@localhost) by wptx01.physik.uni-wuerzburg.de (8.6.10/8.6.10) id RAA19777 for Connectionists@cs.cmu.edu; Mon, 19 Jun 1995 17:06:04 +0200 From: Wolfgang Kinzel Message-Id: <199506191506.RAA19777@wptx01.physik.uni-wuerzburg.de> Subject: workshop and autumn school on neural nets in Wuerzburg To: Connectionists Date: Mon, 19 Jun 95 17:06:03 MESZ Mailer: Elm [revision: 70.85] First Announcement and Call for Abstracts Interdisciplinary Autumn School and Workshop on Neural Networks: Application, Biology, and Theory October 12-14 (school) and 16-18 (workshop), 1995 W"urzburg, Germany INVITED SPEAKERS INCLUDE: M. Abeles, Jerusalem A. Aertsen, Rehovot J.K. Anlauf, Siemens AG J.P. Aubin, Paris M. Biehl, W"urzburg C. v.d. Broeck, Diepenbeek M. Cottrell, Paris B. Fritzke, Bochum Th. Fritsch, W"urzburg J. G"oppert, T"ubingen L.K.Hansen, Lyngby M. Hemberger, Daimler Benz AG L. van Hemmen, M"unchen J.A. Hertz, Copenhagen J. Hopfield, Pasadena I. Kanter, Ramat-Gan C. Koch, Pasadena P. Kraus, Bochum B. Lautrup, Copenhagen W. Maass, Graz Th. Martinetz, Siemens AG M. Opper, Santa Cruz H. Scheich, Magdeburg H.G. Schuster, Kiel S. Seung, AT&T Bell-Lab. W. Singer, Frankfurt S.A. Solla, Copenhagen H. Sompolinsky, Jerusalem F. Varela, Paris A. Weigend, Boulder AUTUMN SCHOOL, Oct. 12-14: Introductory lectures on theory and applications of neural nets for graduate students and interested postgraduates in biology, medicine, mathematics, physics, computer science, and other related disciplines. Topics include neuronal modelling, statistical physics, hardware and application of neural nets in telecommunication, financial forecasting, and biological data analysis. WORKSHOP, Oct. 16-18: Biology, theory, and applications of neural networks with particular emphasis on the interdisciplinary aspects of the field. There will be only invited lectures with ample time for discussion. In addition, poster sessions will be scheduled. REGISTRATION: Requested before AUGUST 31, per FAX or (E-)MAIL to Workshop on Neural Networks Inst. f"ur Theor. Physik, Julius-Maxmimilians-Universit"at Am Hubland, D-97074 W"urzburg, Germany Fax: +49 931 888 5141 e-mail: workshop@physik.uni-wuerzburg.de The registration fee is DM 150,- for the Autumn school and DM 150,- for the Workshop, due upon arrival (cash only). Students pay DM 80,- for each event (student ID required). ABSTRACTS: Participants who wish to present a poster should submit title and abstract together with their registration before August 31. ACCOMMODATION: Registered participants will receive a request form of the Tourist Office W"urzburg together with general informations. Early registration is advised. In case of registration after July 31 please contact directly the Fremdenverkehrsamt, Am Congress Centrum, D-97070 W"urzburg, Fax +49 931 37372. ORGANIZING COMMITTEE: M. Biehl, Th. Fritsch, W. Kinzel, Univ. W"urzburg. SCIENTIFIC ADVISORY COUNCIL: D. Flockerzi, K.-D. Kniffki, W. Knobloch, M. Meesmann, T. Nowak, F. Schneider, P. Tran-Gia, Universit"at W"urzburg. SPONSORS: Peter Beate Heller-Stiftung im Stifterverband f. die Deutsche Wissenschaft, Research Center of Daimler Benz AG, Stiftung der St"adtischen Sparkasse W"urzburg. --------------------------------cut here---------------------------------- Registration Form Please return to: Workshop on Neural Networks Institut f"ur Theoretische Physik Julius-Maximilians-Universit"at Am Hubland D-97074 W"urzburg, Germany Fax: +49 931 888 5141 E-mail : workshop@physik.uni-wuerzburg.de I will attend the Autumn School Oct. 12-14 [ ] * (Reg. fee DM $150,- [ ] / 80,- [ ] due upon arrival) * Workshop Oct. 16-18 [ ] * (Reg. fee DM $150,- [ ] / 80,- [ ] due upon arrival) * * Please mark, reduced fee applies only for participants with valid student-ID. I wish to present a poster [ ] (If yes, please send a title page with a 10-line abstract!) Name: Affiliation: Address: Phone: Fax: E-mail: (please provide full postal address in any case!) Signature: --------------------------------------------------------------------------- From piuri@elet.polimi.it Tue Jun 20 01:40:03 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Tue, 20 Jun 95 01:40:01 -0500; AA22038 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Tue, 20 Jun 95 01:39:59 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab28916; 19 Jun 95 20:09:25 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab28912; 19 Jun 95 19:46:36 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa08109; 19 Jun 95 19:46:26 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa17439; 19 Jun 95 18:23:15 EDT Received: from ipmel2.elet.polimi.it by EDRC.CMU.EDU id aa23738; 19 Jun 95 18:22:20 EDT Received: by ipmel2.elet.polimi.it (5.65/DEC-Ultrix/4.3A) id AA01819; Tue, 20 Jun 1995 00:18:57 +0100 Date: Tue, 20 Jun 1995 00:18:57 +0100 From: Vincenzo Piuri Message-Id: <9506192318.AA01819@ipmel2.elet.polimi.it> To: connectionists@cs.cmu.edu Subject: call for papers ================================================================ CESA'96 IMACS/IEEE-SMC Multiconference Computational Engineering in Systems Applications Lille, France - July 9-12, 1996 ================================================================ Call for Papers for the Special Sessions on Neural Technologies ================================================================ The aim of this meeting is to make the state of the art of the various aspects of computational engineering involved in system theory and applications. It will be organized in four distinct simultaneous symposia: "Modelling, Analysis, and Simulation", "Discrete Events and Manufacturing Systems", "Control, Optimization and Supervision", and "Robotics and Cybernetics". A Special Session on "Neural Techniques for Identification and Prediction" will be held in the Symposium on "Modelling, Analysis, and Simulation". Papers are solicited on all aspects of the neural technologies concerning system identification and prediction. In particular, the Special Session will be focused on theoretical, design and practical aspects. A Special Session on "Neural Control Systems: Techniques, Implementations, and Applications" will be held in the Symposium on "Control, Optimization and Supervision". Papers are solicited on all aspects of the neural technologies concerning system control: theory, design methodologies, realizations, case studies, and applications are welcome. Authors interested in the above Special Sessions are kindly invited to send a letter of interest by August 31, 1995, to the Special Session Organizer (email is preferred). This letter should contain the name and the address (including email) of the possible contact author, the name of the special session, a tentative title of the paper. It does not limit possible further submissions. Authors are then requested to submit to the Special Session Organizer (email and fax submission are accepted): - a one-page abstract by Semptember 30, 1995, for review assignment, - the preliminary version of the paper or an extended abstract by November 15, 1995. Acceptance/rejection will be mailed by January 15, 1996. The final camera-ready version of the paper is due by May 1, 1996. Prof. Vincenzo Piuri Organizer of the Special Sessions on Neural Technologies Department of Electronics and Information Politecnico di Milano, Italy fax +39-2-2399-3411 email piuri@elet.polimi.it ================================================================ From moreno@eel.upc.es Tue Jun 20 21:58:35 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Tue, 20 Jun 95 21:58:33 -0500; AA00761 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Tue, 20 Jun 95 21:58:29 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa00831; 20 Jun 95 21:50:06 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa00814; 20 Jun 95 21:23:05 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa09091; 20 Jun 95 21:22:47 EDT Date: Tue, 20 Jun 1995 9:55:09 UTC+0100 From: "Juan M. Moreno" To: Connectionists@cs.cmu.edu Message-Id: <582*/S=moreno/OU=eel/O=upc/PRMD=iris/ADMD=mensatex/C=es/@MHS> Subject: Ph.D. Thesis: VLSI Architectures for Evolutive Neural Models Mime-Version: 1.0 (Generated by Ean X.400 to MIME gateway) FTP-host: ftp.upc.es (147.83.98.7) FTP-file: /upc/eel/moreno_vlsi_94.tar (2 MB compressed, 5.6 MB uncompressed, 184 pages) The following Ph.D. Thesis is now available by anonymous ftp. FTP instructions can be found at the end of this message. -------------------------------------------------------------------- VLSI ARCHITECTURES FOR EVOLUTIVE NEURAL MODELS J.M. Moreno Arostegui Technical University of Catalunya Department of Electronics Engineering RESUME In the last years there has been an increasing interest in the research field related to the artificial neural network models. The reason for this interest has been the development of advanced tools and techniques for microelectronics design, which have permitted to translate into efficient physical realizations the theoretical connectionist models. However, there are several problems associated to the classical artificial neural network models, related basically to their convergence properties, and to the necessity to define heuristically the proper network structure for a particular problem In order to alleviate these problems, evolutive neural models offer the possibility to construct automatically during the training process the proper network structure able to handle efficiently a certain task. Furthermore, these neural models allows for establishing incremental learning schemes, so that new knowledge can be easily incorporated in the network, without the necessity to perform from scratch a new comple te training process. The present work tries to offer efficient solutions, under the form of VLSI microelectronics architectures, for the eventual realization of systems based on the evolutive neural paradigms. An exhaustive analysis on the different types of evolutive neural models has been first performed. The goal of this analysis is to select those evolutive neural models whose data flow is suitable for an eventual hardware implementation. As a result, the incremental evolutive neural models have been selected as the most appropriate ones in the case a hardware realization is envisaged. Afterwards, the improvement of the convergence properties of evolutive neural models has been considered. This improvement is required so as to allow for more efficient physical implementations able to face real world tasks. As a result, three different methods have been proposed so as to enhance the network construction process provided by evolutive neural models. The next step towards the implementation of evolutive neural models has consisted of the selection of the most suitable hardware architectures in order to realize the data flow imposed by the corresponding training an recall phases associated to these neural models. As a previous step, an algorithm vectorization process has been performed, so as to detect the basic operations required by the training and recall schemes. Then, by analyzing the efficiency offered by different hardware architectures in carrying out these basic operations, we have selected two architectures as the most suitable for an eventual hardware implementation. Bearing in mind the results provided by the previous architecture analysis, a digital architecture has been proposed. This architecture is able to organize properly its resources, so as to match the requirements imposed by the corresponding training and recall phases, being thus capable of emulating the two architectures selected by the analysis indicated previously. The architecture is organized as an array of processing units, which can be configured in order to provide an specific array organization. A specific RISC (Reduced Instruction Set Computer) has been developed in order to realize these processing units. This processor has a generic enough instruction set, which permits the efficient emulation (both in terms of speed and compactness) of a wide range of evolutive neural models. Finally, an analog systolic architecture has been proposed, which allows also for the physical implementation of the evolutive neural models indicated previously. This architecture has been developed using a systolic modular principle, so that it permits to emulate different neural models just by changing the functionality of the building blocks which constitute its processing units. The main advantage offered by this architecture is the possibility to develop compact systems capable to provide high processing rates, being thus suitable for those tasks where an integrated signal processing scheme is required. ---------------------------------------------------------------------------- FTP instructions: unix> ftp ftp.upc.es (147.83.98.7) Name: anonymous Password: (your e-mail address) ftp> cd /upc/eel ftp> bin ftp> get moreno_vlsi_94.tar ftp> bye unix> tar xvf moreno_vlsi_94.tar As a result, you get 12 different compressed postscript files (5.6 MB). Just uncompress these files and print them on your local printer. Sorry, but there are no hard copies available. Regards, ---------------------------------------------------------------------------- || Juan Manuel Moreno Arostegui || || || || || || Dept. Enginyeria Electronica || Tel. : +34 3 401 74 88 || || Universitat Politecnica de Catalunya || || || Modul C-4, Campus Nord || Fax : +34 3 401 67 56 || || c/ Gran Capita s/n || || || 08034-Barcelona || E-mail : moreno@eel.upc.es || || SPAIN || || ---------------------------------------------------------------------------- From pazzani@super-pan.ICS.UCI.EDU Tue Jun 20 22:31:27 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Tue, 20 Jun 95 22:31:24 -0500; AA00892 Received: from paris.ics.uci.edu by lucy.cs.wisc.edu; Tue, 20 Jun 95 22:30:58 -0500 Received: from super-pan.ics.uci.edu by paris.ics.uci.edu id aa03628; 20 Jun 95 15:11 PDT To: ML-LIST:; Subject: Machine Learning List: Vol. 7, No. 11 Reply-To: ml@ics.uci.edu Date: Tue, 20 Jun 1995 13:51:17 -0700 From: Michael Pazzani Message-Id: <9506201511.aa03628@paris.ics.uci.edu> Machine Learning List: Vol. 7, No. 11 Monday, June 19, 1995 Contents: New Releases of C4.5 and FOIL workshop proceedings Papers on cognitive modeling and machine learning Symposium on Document Analysis and Information Retrieval IMLC-95 Workshop: Applying ML in Practice KLML Workshop 1995 ACL-95 WVLC3 - Supervised Training vs Self-organizing Methods ML in Engineering - 2nd Call for Participation Symposium on Knowledge Discovery in Databases at EMCSR'96 Short Course Announcement 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: Ross Quinlan Date: Fri, 16 Jun 1995 11:08:49 +1000 Subject: New Releases of C4.5 and FOIL C4.5 Release 7 The latest release of C4.5 is now available. If you have Release 5 (i.e. the disk from Morgan Kaufmann), you can obtain the altered files by anonymous ftp from ftp.cs.su.oz.au, directory pub/ml, file patch.tar.Z. The file Modifications summarizes the changes since Release 5. Needless to say, it is advisable to retain the old files until you are satisfied with Release 7! FOIL Version 6.3 This version fixes several bugs and incorporates some improvements. It is available by anonymous ftp from ftp.cs.su.oz.au, directory pub, file foil6.sh. Please report any problems to quinlan@cs.su.oz.au. ------------------------------ From: gordon@aic.nrl.navy.mil Date: Mon, 19 Jun 95 15:09:12 EDT Subject: workshop proceedings The ML95 workshop on "Agents that Learn from Other Agents" has the proceedings online on the World Wide Web now. The URL is: http://www.cs.wisc.edu/~shavlik/ml95w1/procs.html The workshop schedule is also available from this URL. If you don't have the Web option, the papers can be obtained by ftp at ftp.cs.wisc.edu under the directory machine-learning/shavlik-group/ml95w1/ (If you don't have gunzip, the ftp server will uncompress locally - see instructions on the ftp site) Please send me email if you'd like to attend this workshop. Diana Gordon gordon@aic.nrl.navy.mil Workshop Chair ------------------------------ From: Charles X Ling Date: Thu, 15 Jun 95 10:54:52 EDT Subject: Papers on cognitive modeling and machine learning I have an ftp site that contains most of my publications (9 published journal papers, several submitted papers and published conference papers). These papers can be ftp'd at ftp.csd.uwo.ca under pub/ling/papers/ . The file README contains a complete list. Information on a few recently papers is attached. Comments are very welcome. Charles Ling (ling@csd.uwo.ca) Department of Computer Science The University of Western Ontario, London, Ontario N6A 5B7, Canada ****************************************** FILES: tr-bs1.ps.Z, tr-bs2.ps.Z, tr-bs3.ps.Z (submitted version) W.C. Schmidt and C.X. Ling. A Decision-tree Model of Balance Scale Development. Machine Learning Journal (Accepted). 36 page manuscript. Abstract: A symbolic model for child cognitive developmental process of the balance scale learning task. FILE: tr-read-aloud.ps.Z C. X. Ling and H. Wang. A Decision-Tree Model for Reading Aloud with Automatic Alignment and Grapheme Generation. Submitted. Abstract: A complete symbolic model of spelling-to-sound acquisition with representation development as part of the learning task. FILE: isps-newterm.ps.Z C.X. Ling. Introducing new predicates to model scientific revolution. {\it International Studies in the Philosophy of Science}, 9(1): 19--36. 1995. Abstract: Necessary new terms are introduced for modeling scientific revolution. FILE: jar-refinement.ps.Z C.X. Ling and M. Valtorta. Refining Rule Bases with Uncertainty via Reduction. {\it International Journal of Approximate Reasoning}. To appear. Abstract: Theoretical and practical implication of knowledge base refinement. FILE: ab-control.ps.Z C.X. Ling and R. Buchal. Learning to control dynamic systems: A progressive quantization approach. {\it Adaptive Behavior}, 3(1): 29--49, 1994. Abstract: Learning to balance the cart-pole and to acquire appropriate discrete representation at the same time. FILE: tr-overfitting.ps.Z C.X. Ling. Overfitting and Generalization in Learning Discrete Patterns. {\it Neurocomputing: An International Journal}, to appear. Abstract: Why and how overfitting happens in artificial neural networks. Interesting results on the generalization of networks of various sizes. FILE: tr-opt-w-IBL.ps.Z C.X. Ling and H. Wang. Towards optimal weight setting for nearest neighbour algorithms. Journal of Artificial Intelligence Review (conditionally accepted, Special Issue on Lazy Learning). 1995. 17 page manuscript. Abstract: Deciding (theoretically) optimal weights for 1-NN algorithms for best predictive accuracy. ------------------------------ From: Andrew D Bagdanov Date: Fri, 16 Jun 1995 11:46:44 -0700 Subject: Symposium on Document Analysis and Information Retrieval Call for Papers SDAIR '96 Fifth Annual Symposium on Document Analysis and Information Retrieval April 15-17, 1996 Alexis Park Resort, Las Vegas, Nevada SPONSOR Information Science Research Institute University of Nevada, Las Vegas SYMPOSIUM CHAIR Henry S. Baird AT&T Bell Laboratories henry.baird@att.com PROGRAM CHAIRS Document Analysis: Andreas Dengel German Research Center for Artificial Intelligence (DFKI) dengel@dfki.uni-kl.de Information Retrieval: Jan Pedersen Xerox Palo Alto Research Center pedersen@parc.xerox.com SYMPOSIUM SECRETARY Mary C. Guirsch University of Nevada, Las Vegas Information Science Research Institute 4505 Maryland Parkway Box 454021 Las Vegas, NV 89154-4021 (702)895-4571 (702)895-1183 (fax) sdair@isri.unlv.edu SCOPE The purpose of this symposium is to present results of state-of-the-art research and to encourage the exchange of ideas in the general field of automatic extraction of information from images of printed documents. Papers are solicited on all aspects of document image analysis and information retrieval, both theoretical and applied, with particular emphasis on: Document Analysis: High-Accuracy Transcription Postprocessing of OCR Results Keyword Search in Textual Images Multilingual OCR, Language ID, etc. Geometric and Logical Layout Analysis Recognition of Forms, Tables and Equations Models of Document Image Degradation Methods for Performance Evaluation Information Retrieval: Full-Text Retrieval Retrieval from OCR'ed Text Image and Multimedia Retrieval Text Categorization Retrieval from Structured Documents Language-Specific Influences on Retrieval Evaluation of IR Systems Text Representation Papers on subjects in the intersection of these two areas will be given priority. SUBMISSIONS Please send five copies of complete papers, with the corresponding author's name, postal address, telephone and fax numbers and e-mail address, to the appropriate Chair: Andreas Dengel, Chair (Document Analysis) c/o Information Science Research Institute University of Nevada, Las Vegas 4505 Maryland Parkway Box 454021 Las Vegas, NV 89154-4021 Jan O. Pedersen, Chair (Info. Retrieval) c/o Information Science Research Institute University of Nevada, Las Vegas 4505 Maryland Parkway Box 454021 Las Vegas, NV 89154-4021 Manuscripts should be no longer than 20 double-spaced pages or 5,000 words and should not already have been accepted for publication by another conference or journal, nor should they be submitted elsewhere during the SDAIR'96 review period. Both camera-ready paper and machine-readable source copies of accepted papers will be required. The proceedings will be available at the conference. CONFERENCE TIMETABLE Papers Due September 30, 1995 Notification To Authors December 1, 1995 Camera Ready and Machine Readable Copy January 15, 1996 DOCUMENT ANALYSIS COMMITTEE: Andreas DENGEL, Chair, German Research Center for Artificial Intelligence 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, Consultant, Palo Alto, CA Suzanne TAYLOR, Loral Corporation Karl TOMBRE, INRIA Lorraine INFORMATION RETRIEVAL COMMITTEE: Jan PEDERSEN, Chair, Xerox Palo Alto Research Center Susan DUMAIS, Bellcore Stephen GALLANT, Belmont, Inc. 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 (ETH) Kazem TAGHVA, University of Nevada, Las Vegas Yiming YANG, Mayo Clinic/Foundation ------------------------------ From: aha@aic.nrl.navy.mil Date: Wed, 14 Jun 1995 13:10:55 -0400 (EDT) Subject: IMLC-95 Workshop: Applying ML in Practice Our workshop will focus on characterizing the expertise used by ML experts during the application of learning algorithms to practical tasks. Our workshop schedule includes two invited talks (by Ivan Bratko & Pat Langley), eight paper presentations, and lengthy discussion sessions. We will focus these sessions on the completed questionnaires, the process models described in the papers, and reactions to the presentations. We welcome your participation! Please tell us (aha@aic.nrl.navy.mil) if you plan to attend. All details on this workshop are web-available. Organizers: David W. Aha, Jason Catlett, Haym Hirsh, Patricia Riddle Tentative Schedule for the 1995 IMLC Workshop: Applying Machine Learning in Practice http://www.aic.nrl.navy.mil/~aha/imlc95-workshop/home.html Granlibakken Resort, Tahoe City, California 9 July 1995 9:00am: Opening Statement 9:10am: Pat Langley (Invited Talk) Fielded Applications of Machine Learning 10:00am: Carla E. Brodley & Padhraic Smyth Making Machine Learning Algorithms Work in Practice 10:25am: Discussion 10:50am: Break 11:05am: Andrea Danyluk (Title to be Announced) 11:20am: Mark Schwabacher, Haym Hirsh & Thomas Ellman Inductive Learning for Engineering Design Optimization 11:35am: Discussion 12:00pm: Lunch 1:00pm: Ivan Bratko (Invited Talk) Machine learning: Between Accuracy and Interpretability 1:50pm: Stephen R. Garner, Sally Jo Cunningham, Geoffrey Holmes, Craig Nevill-Manning, & Ian H. Witten Applying a Machine Learning Workbench: Experience with Agricultural Databases 2:10pm: Gholam Nakhaeizadeh What Daimler-Benz has Learned as an Industrial Partner from the Machine Learning Project Statlog 2:25pm: Discussion 3:00pm: Break 3:15pm: Lorenza Saitta, Attilio Giordana, & Filippo Neri What is the "Real-World"? 3:50pm: Alan Schultz, John Grefenstette & Ken De Jong Adaptive Testing of Intelligent Controllers for Autonomous Vehicles using Genetic Algorithms 4:05pm: Lars Asker & Henrik Bostrom Building the DeNOx System: Experience from a Real-World Application of Machine Learning 4:20pm: Discussion ------------------------------ From: Dieter Fensel Date: Wed, 31 May 1995 16:41:37 +0200 Subject: KLML Workshop 1995 The proceedings and some further infos about the Knowledge Level Modelling and Machine Learning Workshop April 28-29, 1995, Iraklion, Greece hold in conjunction with the European Conference on Machine Learning ECML-95 are available via http://www.swi.psy.uva.nl/usr/dieter/klml/klml.html ------------------------------ From: yarowsky@unagi.cis.upenn.edu Date: Thu, 1 Jun 1995 18:14:37 -0400 Subject: ACL-95 WVLC3 - Supervised Training vs Self-organizing Methods THE THIRD WORKSHOP ON VERY LARGE CORPORA Friday, 30 June 1995 8:45 AM - 5:25 PM MIT, Cambridge, Massachusetts, USA at ACL-95 (June 26-29) (Sponsored by ACL's SIGDAT and SIGNLL) The workshop will present original research in corpus-based and statistical natural language processing. Topics will include sense disambiguation, grammar induction, part-of-speech tagging, information retrieval, language modeling, and machine translation. This year's theme is: Supervised Training vs. Self-organizing Methods Historically, annotated corpora have made a significant contribution to tasks such as part-of-speech tagging and sense disambiguation. But annotated corpora are expensive and generally unavailable for languages other than English. Self-organizing methods offer the hope that annotated corpora might not be necessary. Can we achieve comparable performance using little or no tagged training data? What are the tradeoffs? Organizers: Ken Church and David Yarowsky Industrial Sponsor: LEXIS-NEXIS, Division of Reed and Elsevier, Plc. REGISTRATION: Registration fees are $40 for payment received by 15 June 1995 and $45 at the door. Registration includes a copy of the proceedings, catered lunch and refreshments during the day. Acceptable forms of payment are US$ cheques payable to "ACL" or credit card (VISA/Mastercard) payment. E-mail registrations are encouraged. Please submit the following form along with payment: Name: Institution (for name tag): Postal address: Email address: Payment (specify cheque or credit card): Credit card info - Name on card: - Card number: - Expiration date: Dietary requirements (vegetarian, etc.): Please send to: David Yarowsky Dept. of Computer and Information Science University of Pennsylvania 200 S. 33rd St. Philadelphia, PA 19104-6389 USA email: yarowsky@unagi.cis.upenn.edu ============================================================================ PRELIMINARY PROGRAM 8:15 - 8:45 Registration. Coffee, danish, etc. available 8:45 - 8:50 Welcome 8:50 - 9:35 INVITED TALK (Mark Liberman) 9:35 - 9:50 Break 9:50 - 10:15 Eric Brill Unsupervised Learning of Disambiguation Rules for Part of Speech Tagging 10:15 - 10:40 Carl de Marcken Lexical Heads, Phrase Structure and the Induction of Grammar 10:40 - 11:05 Michael Collins and James Brooks Prepositional Phrase Attachment through a Backed-off Model 11:05 - 11:15 Break 11:15 - 11:40 Andrew Golding A Bayesian Hybrid Method for Context-sensitive Spelling Correction 11:40 - 12:05 Philip Resnik Disambiguating Noun Groupings with Respect to Wordnet Senses 12:05 - 1:05 CATERED LUNCH 1:05 - 1:30 Dekai Wu Trainable Coarse Bilingual Grammars for Parallel Text Bracketing 1:30 - 1:55 Lance Ramshaw and Mitch Marcus Text Chunking using Transformation-Based Learning 1:55 - 2:05 Break 2:05 - 3:00 INVITED TALK (Henry Kucera and Nelson Francis) 3:00 - 3:10 Break 3:10 - 3:35 Fernando Pereira, Yoram Singer and Naftali Tishby Beyond Word N-Grams 3:35 - 4:00 Jing-Shin Chang, Yi-Chung Lin and Keh-Yih Su Automatic Construction of a Chinese Electronic Dictionary 4:00 - 4:10 Break 4:10 - 4:35 Kenneth Church and William Gale Inverse Document Frequency (IDF): A Measure of Deviations from Poisson 4:35 - 5:00 Joe Zhou and Pete Dapkus Automatic Suggestion of Significant Terms for a Predefined Topic 5:00 - 5:25 Ellen Riloff and Jay Shoen Automatically Acquiring Conceptual Patterns without an Annotated Corpus More Information: http://www.cis.upenn.edu/~yarowsky/wvlc3.html ACL-95 Homepage: http://www.ai.mit.edu/people/cgdemarc/acl/acl-info.html ------------------------------ From: Benoit Julien Date: Tue, 6 Jun 95 14:25:08 EDT Subject: ML in Engineering - 2nd Call for Participation *** IJCAI-95 Workshop on Machine Learning in Engineering *** Montreal, Canada Monday August 21, 1995 The workshop notes of the IJCAI-95 workshop are now available via anonymous ftp at "crim.ca", directory "gsbc/ijcai95-wk" or via the WEB at http://www.crim.ca:80/Domaines_Services/GSBC/index-english.html You can register for the IJCAI-95 conference (IJCAI-95 390$, IAAI-95 390$ before June 21, 450$ after June 21) and the workshop ($50.00) by sending e-mail to IJCAI/AAAI at ijcai@aaai.org or via the WEB at http:://ijcai.org/ ------------------------------ From: Yves Kodratoff Date: Wed, 14 Jun 1995 14:10:32 +0200 Subject: Symposium on Knowledge Discovery in Databases at EMCSR'96 Symposium on Knowledge Discovery in Databases at EMCSR'96 April 9 -12, 1996 Information relative to the European Meeting on Cyb. and Sys. Res. in http://www.ai.univie.ac.at Knowledge discovery in databases (KDD) is a new research area at the intersection of machine learning, statistics, and databases. Hence, submitted papers must not describe only an improvement in one of the three concerned fields, but some interaction between at least two of them. KDD and Data Mining have already received attention from Industry, and we will welcome papers describing KDD applications on large sets of data of industrial interest. We would like to promote other issues as well, such as the formalization of the KDD approach (theories for KDD), and the epistemological, philosophical, and ethical issues. Just before the symposium, will take place a tutorial on KDD, delivered by Usama Fayyad and Evangelos Simoudis, two pioneers of this area. The tutorial costs $ 275 and its duration is about 4 hours of teaching. After the tutorial, a free demonstration of some publicly available KDD software will take place. *** Please reserve for the tutorial through the Conference Secretariat *** Selection committee: +++++++++++++++++++++ Pieter Adriaans, Christoph Breitner, Wray Buntine, Werner Emde, Usama Fayyad, Ronen Feldman, Jean-Gabriel Ganascia, Olivier Gascuel, Attilio Giordana, Willi Kloesgen, Yves Kodratoff, Heikki Mannila, Thierry van de Merckt, Ryszard Michalski, Katharina Morik, Vassilis Moustakis, Reza Nakhaeizadeh, Gregory Piatetsky-Shapiro, Luc De Raedt, Michele Sebag, Colin Shearer, Arno Siebes, Derek Sleeman, Charles Taylor, Ruediger Wirth, Stefan Wrobel. Submission Guidelines +++++++++++++++++++++ Acceptance of contributions will be determined on the basis of Draft Final Papers. These papers must not exceed 10 single-spaced A4 pages (maximum 43 lines, max. line length 160 mm, 12 point), in English. They have to contain the final text to be submitted, including graphs and pictures. However, these need not be of reproducible quality. The Draft Final Paper must carry the title, author(s) name(s), and affiliation (incl. e-mail address, if possible) in this order. ***Please specify the symposium in which you would like to present your paper.*** Each scientist shall submit only one paper. Please send four hard copies of the Draft Final Paper to the Conference Secretariat ****(do NOT send them to symposia chairpersons!) **** Electronic or fax submissions cannot be accepted. Deadline for Submission: October 12, 1995. ++++++++++++++++++++++++++++++++++++++++++ Notification of Acceptance/Rejection ++++++++++++++++++++++++++++++++++++ Authors will be notified about acceptance or rejection no later than December 11, 1995. Successful authors will be provided by the conference secretariat at the same time with the instructions for the preparation of the final paper, which will also be available via ftp and World-Wide Web. Final Papers ++++++++++++ The final paper will be limited to a maximum of 6 pages (10-point, double column).Camera-ready copies of the final paper will be due at the conference secretariat by Jan. 29, 1996. Presentation ++++++++++++ It is understood that each accepted paper is presented personally at the Meeting by one of its authors. Conference Fee ++++++++++++++ AS 2800 if received before January 31, 1996 AS 3300 if received later AS 3800 if paid at the conference desk. Secretariat +++++++++++ I. Ghobrial-Willmann and G. Helscher Austrian Society for Cybernetic Studies A-1010 Vienna 1, Schottengasse 3 (Austria) Phone: +43-1-53532810 Fax: +43-1-5320652 E-mail: sec@ai.univie.ac.at ------------------------------ Date: Wed, 14 Jun 95 14:27:28 CDT From: John Elder Subject: Short Course Announcement Making Sense of Data: Computer-Aided Pattern Discovery A Rice University Short Course, July 20-21, 1995 Is useful information hidden in your collection of data? How can you identify patterns and trends to classify a new case and give it contextual meaning? This two-day intensive short course will survey new methods of computer-aided data analysis that can enable researchers and analysts in many different professions to classify data and make useful estimates and forecasts. These techniques, drawn from the fields of statistics, machine learning, data mining, and inductive modeling, have been applied successfully to many real-world problems, ranging from medical diagnosis and adaptive flight control, to machine fault identification and selection of stocks and bonds. Course Content The course will focus on the leading methods used in industry, government labs, and academia. Instructors will describe the key inner workings of various algorithms, compare their merits, and demonstrate their effectiveness on practical applications. They will first review classical statistical techniques, both linear and nonparametric, then outline the ways in which these basic tools are modified and combined into more modern methods. The instructors will pay particular attention to four powerful approaches: kernels, neural networks, polynomial networks, and decision trees, and will use sample scientific, medical, and financial applications to demonstrate general techniques (such as scientific visualization) and "tricks of the trade" employed by experienced analysts. Data Workshop At a "Data Workshop" and demonstration on the first evening of the course, participants may try some of these methods using their own data. (Please indicate on the registration form if you plan to bring data for the workshop.) Who Should Attend Those from industry, government, and academia who work with data and wish to understand recent developments in pattern discovery, data mining, and inductive modeling. At the conclusion of this course, they should be able to discern the strengths of competing methods and select the appropriate tools for their applications. Participants should have prior working experience with computers and knowledge of, or interest in, applied statistical techniques. Course Outline Pattern Discovery: An Overview Inducing Models from Data: Benefits and Dangers Related Fields: Statistics, Machine Learning, Data Mining, and Artificial Intelligence Data Issues Case Diagnostics Feature Creation and Selection Classical Statistical Techniques Linear: Regression and Discriminant Analysis Nonparametric: Scatterplot Smoothers, Nearest Neighbors, Kernels Other Key Tools: Optimization, Clustering Modern Methods ASH* (Average Shifted Histograms) Neural Networks* Polynomial Networks* (ASPN, AIM) Decision Trees* (CART) Brief Survey of Other Methods Projection Pursuit MARS (Multivariate Adaptive Regression Splines) UPM* (Universal Process Modeling) Radial Basis Functions Examples of Applications Diagnosing Breast Cancer Estimating Air Quality Classifying Bat Species Investing in the Bond Market Instructors The instructors and guest lecturer each have more than a decade of experience in applying adaptive, data-driven techniques to practical problems, and have developed some of the leading methods covered in this course. Dr. John F. Elder is Research Scientist in the Department of Computational and Applied Mathematics and the Center for Research on Parallel Computation at Rice University. He is the author of three book chapters and numerous articles on adaptive methods of pattern discovery, and is technical chair of the Adaptive and Learning Systems Group of the IEEE Systems, Man, and Cybernetics Society. He has been a research scientist for an engineering consulting business and director of research for an investment management firm, and has a Ph.D. in Systems Engineering from the University of Virginia. Paul Hess has been President of Hess Consulting in Herndon, Va. since 1991. He was a research scientist for an engineering consulting firm and co-founder of AbTech Corporation, a leading maker of artificial intelligence software. Guest lecturer Dr. David W. Scott is Professor of Statistics and former Chair of the Statistics Department at Rice University. He is the author of the 1992 book Multivariate Density Estimation, as well as numerous articles. Dr. Scott is editor of the journal Computational Statistics and is on the editorial board of John Wiley & Sons. Additional Information When and Where: Thursday-Friday, July 20-21, 1995, 9:00 a.m.-12:00 noon and 1:15-4:00 p.m., on the Rice University campus, 6100 Main Street, Houston, Texas. The Data Workshop will be held Thursday evening, 6:00-8:00 p.m. Fee: $395. Early discount fee: $345 for those registering by June 15. Fee for graduate students: $245. Fee includes lecture notes, lunches at the Rice Faculty Club, and the Data Workshop. CEUs: 1.4 Refund Policy: Course fee will be refunded in full if enrollment is canceled in writing by June 30. If you drop the course June 30 through July 10, a refund will be issued only if a replacement for you can be found, and a $95 processing fee will be deducted from your refund. Refunds will not be issued after July 10. Accommodations: A block of rooms at a special rate of $65 has been reserved at the Houston Plaza Hilton, located in the Texas Medical Center, within walking distance of Rice University. Reservations must be made by July 5, 1995. Contact the hotel directly at (713) 524-6633. A list of other nearby hotels will be mailed upon request. For more information For information on registration, contact Rice University School of Continuing Studies, (713) 520-6022 or 527-4803 E-mail: scs@rice.edu For more information on course content, contact Dr. John Elder, (713) 285-5182 E-mail: elder@rice.edu ------------------------------ End of ML-LIST (Digest format) **************************************** From lawrence@research.nj.nec.com Wed Jun 21 03:07:54 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 21 Jun 95 03:07:52 -0500; AA02062 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 21 Jun 95 03:07:50 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa00812; 20 Jun 95 21:41:49 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa00809; 20 Jun 95 21:22:16 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa09085; 20 Jun 95 21:21:37 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id ac00943; 20 Jun 95 15:33:05 EDT Received: from zingo.nj.nec.com by CS.CMU.EDU id aa22489; 20 Jun 95 15:32:12 EDT Received: by zingo (940816.SGI.8.6.9/YDL1.4-910307.16) id PAA13653(zingo); Tue, 20 Jun 1995 15:30:00 -0400 Received: by heavenly (940816.SGI.8.6.9/cliff's joyful mailer #2) id PAA06572(heavenly); Tue, 20 Jun 1995 15:29:54 -0400 From: Steve Lawrence Message-Id: <199506201929.PAA06572@heavenly> Subject: TR Available: Neural Network and Machine Learning for Natural Language Processing To: connectionists@cs.cmu.edu Date: Tue, 20 Jun 1995 15:29:53 -0400 (EDT) X-Mailer: ELM [version 2.4 PL24] Content-Type: text Content-Length: 2934 The following technical report is available from the archive of the Computer Science Department, University of Maryland. http://www.cs.umd.edu:80/TR/UMCP-CSD:CS-TR-3479 ftp://ftp.cs.umd.edu:/pub/papers/papers/3479/3479.ps.Z or from our home pages http://www.neci.nj.nec.com:80/homepages/giles.html htpp://www.elec.uq.edu.au/~lawrence We welcome your comments. On the Applicability of Neural Network and Machine Learning Methodologies to Natural Language Processing Steve Lawrence, C. Lee Giles, Sandiway Fong NEC Research Institute 4 Independence Way Princeton, N.J. 08540 USA Technical Report UMIACS-TR-95-64 and CS-TR-3479 University of Maryland, College Park, MD 20742 Steve Lawrence is also with Electrical and Computer Engineering, University of Queensland, St. Lucia Qld 4072, Australia C. Lee Giles is also with the Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20742. lawrence@elec.uq.edu.au, {giles,sandiway}@research.nj.nec.com ABSTRACT We examine the inductive inference of a complex grammar - specifically, we consider the task of training a model to classify natural language sentences as grammatical or ungrammatical, thereby exhibiting the same kind of discriminatory power provided by the Principles and Parameters linguistic framework, or Government- and-Binding theory. We investigate the following models: feed-forward neural networks, Fransconi-Gori-Soda and Back-Tsoi locally recurrent networks, Elman, Narendra \& Parthasarathy, and Williams \& Zipser recurrent networks, Euclidean and edit-distance nearest-neighbors, simulated annealing, and decision trees. The feed-forward neural networks and non-neural network machine learning models are included primarily for comparison. We address the question: How can a neural network, with its distributed nature and gradient descent based iterative calculations, possess linguistic capability which is traditionally handled with symbolic computation and recursive processes? Initial simulations with all models were only partially successful by using a large temporal window as input. Models trained in this fashion did not learn the grammar to a significant degree. Attempts at training recurrent networks with small temporal input windows failed until we implemented several techniques aimed at improving the convergence of the gradient descent training algorithms. We discuss the theory and present an empirical study of a variety of models and learning algorithms which highlights behaviour not present when attempting to learn a simpler grammar. KEYWORDS: Neural networks, decision trees, simulated annealing, nearest neighbor, natural language processing, error surface, gradient descent, grammatical inference, recurrent neural networks, learning, government-and-binding theory, principles-and-parameters framework From juergen@idsia.ch Wed Jun 21 20:18:08 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 21 Jun 95 20:18:05 -0500; AA11704 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 21 Jun 95 20:18:03 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa02163; 21 Jun 95 19:13:49 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa02161; 21 Jun 95 19:02:55 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa10178; 21 Jun 95 19:02:26 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa09118; 21 Jun 95 4:11:43 EDT Received: from chsun.eunet.ch by RI.CMU.EDU id aa28071; 21 Jun 95 4:11:27 EDT Received: from fava.idsia.ch by chsun.eunet.ch (8.6.10/1.34) id KAA01323; Wed, 21 Jun 1995 10:13:11 +0200 Received: from kraut.idsia.ch by fava.idsia.ch (4.1/SMI-4.1) id AA23052; Wed, 21 Jun 95 10:09:40 +0200 Date: Wed, 21 Jun 95 10:09:40 +0200 From: Juergen Schmidhuber Message-Id: <9506210809.AA23052@fava.idsia.ch> To: connectionists@cs.cmu.edu Subject: one more http://www.idsia.ch/reports.html FTP-host: fava.idsia.ch (192.132.252.1) FTP-filename: /pub/papers/idsia59-95.ps.gz (12 pages, 69k) ENVIRONMENT-INDEPENDENT REINFORCEMENT ACCELERATION Technical Note IDSIA-59-95 Write-up of invited talk at Hongkong Univ. ST (May 29, 1995) Juergen Schmidhuber, IDSIA A reinforcement learning system with limited computational resources interacts with an unrestricted, unknown environment. Its goal is to maximize cumulative reward, to be obtained throughout its limited, unknown lifetime. System policy is an arbitrary modifiable algorithm mapping environmental inputs and internal states to outputs and new internal states. The problem is: in realistic, unknown environments, each policy modification process (PMP) occurring during system life may have unpredictable influence on environmental states, rewards and PMPs at any later time. Existing reinforcement learning algorithms cannot properly deal with this. Neither can naive exhaustive search among all policy candidates -- not even in case of very small search spaces. In fact, a reasonable way of measuring performance improvements in such general (but typical) situations is missing. I define such a measure based on the novel ``reinforcement acceleration criterion'' (RAC). RAC is satisfied if the beginning of each completed PMP that computed a currently valid policy modification has been followed by faster average reinforcement intake than system start-up and the beginnings of all previous such PMPs (the computation time for PMPs is taken into account). Then I present a method called ``environment-independent reinforcement acceleration'' (EIRA) which is guaranteed to achieve RAC. EIRA does neither care whether the system's policy allows for changing itself, nor whether there are multiple, interacting learning systems. Consequences are: (1) a sound theoretical framework for ``meta- learning'' (because the success of a PMP recursively depends on the success of all later PMPs, for which it is setting the stage). (2) A sound theoretical framework for multi-agent learning. The principles have been implemented (1) in a single system using an assembler-like programming language to modify its own policy, and (2) a system consisting of multiple agents, where each agent is in fact just a connection in a fully recurrent reinforcement learning neural net. A by-product of this research is a general reinforcement learning algorithm for such nets. Preliminary experiments illustrate the theory. Juergen Schmidhuber IDSIA, Corso Elvezia 36 6900-Lugano, Switzerland juergen@idsia.ch http://www.idsia.ch From harnad@ecs.soton.ac.uk Wed Jun 21 20:18:13 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 21 Jun 95 20:18:07 -0500; AA11709 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 21 Jun 95 20:18:05 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab02163; 21 Jun 95 19:14:53 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab02161; 21 Jun 95 19:02:58 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa10183; 21 Jun 95 19:02:41 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa19454; 21 Jun 95 16:38:55 EDT Received: from beech.soton.ac.uk by EDRC.CMU.EDU id aa03029; 21 Jun 95 16:32:05 EDT Received: from bright.ecs.soton.ac.uk (bright.ecs.soton.ac.uk [152.78.64.201]) by beech.soton.ac.uk (8.6.12/hub-8.5a) with SMTP id VAA23218; Wed, 21 Jun 1995 21:23:47 +0100 Received: from louis.ecs.soton.ac.uk by bright.ecs.soton.ac.uk; Wed, 21 Jun 95 21:23:05 BST From: Stevan Harnad Received: from cogsci by louis.ecs.soton.ac.uk; Wed, 21 Jun 95 21:22:47 BST Date: Wed, 21 Jun 95 21:23:04 +0100 Message-Id: <5416.9506212023@cogsci> To: cogneuro@ptolemy-ethernet.arc.nasa.gov, connectionists@cs.cmu.edu, neuro1-l@uicvm.bitnet Subject: EEG and Memory: PSYC Call for Commentary PSYCOLOQUY Commentary is invited on: Wolfgang Klimesch on EEG & Memory Qualified professional biobehavioral, neural or cognitive scientists are hereby invited to submit Open Peer Commentary on the target article whose abstract appears below. It has been published in PSYCOLOQUY, a refereed electronic journal sponsored by the American Psychological Association. Instructions for retrieval and for preparing commentaries follow the abstract. The address for submitting commentaries and articles and for requesting information is psyc@pucc.princteton.edu The URLs for retrieving articles are: http://www.princeton.edu/~harnad/psyc.html gopher://gopher.princeton.edu:70/11/.libraries/.pujournals ftp://ftp.princeton.edu/pub/harnad/Psycoloquy/1995.volume.6 TARGET ARTICLE AUTHOR'S RATIONALE FOR SOLICITING COMMENTARY: Memory processes can be described as brain oscillations and memory network models (such as the connectivity model (Klimesch, 1994)) can easily be applied to the neuronal level if abstract activation values are interpreted in terms of frequency values reflecting oscillatory processes. I would be very interested in eliciting commentaries on (1) this basic rationale, (2) the statement that in the cortex oscillations are mandatory for information transmission, (3) the proposed role of EEG alpha and (4) EEG theta for memory processes. ----------------------------------------------------------------------- psycoloquy.95.6.06.memory-brain.1.klimesch ISSN 1055-0143 (55 paragraphs, 75 references, 1279 lines) PSYCOLOQUY is sponsored by the American Psychological Association (APA) Copyright 1995 Wolfgang Klimesch MEMORY PROCESSES DESCRIBED AS BRAIN OSCILLATIONS IN THE EEG-ALPHA AND THETA BANDS Wolfgang Klimesch University of Salzburg Department of Physiological Psychology Institute of Psychology, Hellbrunnerstr. 34 A-5020 Salzburg, AUSTRIA Klimesch@edvz.sbg.ac.at ABSTRACT: This target article tries to integrate results in memory research from diverse disciplines such as psychophysiology, cognitive psychology, anatomy and neurophysiology. The integrating link is seen in more recent anatomical findings that provide strong arguments for the assumption that oscillations provide the basic form of communication between cortical cell assemblies. The basic argument is that episodic memory processes, which are part of a complex working memory system, are reflected by oscillations in the theta band, whereas long-term memory processes are reflected by alpha oscillations. It is assumed that alpha and theta oscillations serve to encode, access, and retrieve cortical codes that are stored in the form of widely distributed but intensely interconnected cell assemblies. KEYWORDS: Alpha, EEG, Hippocampus, Memory, Oscillation, Thalamus, Theta. ------------------------------------------------------------- These files are also on the World Wide Web and the easiest way to retrieve them is with Netscape, Mosaic, gopher, archie, veronica, etc. Here are some of the URLs you can use to get to the BBS Archive: http://www.princeton.edu/~harnad/psyc.html http://cogsci.ecs.soton.ac.uk/~harnad/psyc.html gopher://gopher.princeton.edu:70/11/.libraries/.pujournals ftp://ftp.princeton.edu/pub/harnad/Psycoloquy/1995.volume.6/ ftp://cogsci.ecs.soton.ac.uk/pub/harnad/Psycoloquy/1995.volume.6/ To retrieve a file by ftp from an Internet site, type either: ftp ftp.princeton.edu or ftp 128.112.128.1 When you are asked for your login, type: anonymous Enter password as queried (your password is your actual userid: yourlogin@yourhost.whatever.whatever - be sure to include the "@") cd /pub/harnad/Psycoloquy/1995.volume.6 To show the available files, type: ls Next, retrieve the file you want with (for example): mget *.1.klimesch When you have the file(s) you want, type: quit ---------- Where the above procedure is not available there are two fileservers: ftpmail@decwrl.dec.com and bitftp@pucc.bitnet that will do the transfer for you. To one or the other of them, send the following one line message: help for instructions (which will be similar to the above, but will be in the form of a series of lines in an email message that ftpmail or bitftp will then execute for you). ------------------------------------------------------------- INSTRUCTIONS FOR PSYCOLOQUY COMMENTATORS Accepted PSYCOLOQUY target articles have been judged by 5-8 referees to be appropriate for Open Peer Commentary, the special service provided by PSYCOLOQUY to investigators in psychology, neuroscience, behavioral biology, cognitive sciences and philosophy who wish to solicit multiple responses from an international group of fellow specialists within and across these disciplines to a particularly significant and controversial piece of work. If you feel that you can contribute substantive criticism, interpretation, elaboration or pertinent complementary or supplementary material on a PSYCOLOQUY target article, you are invited to submit a formal electronic commentary. Please note that although commentaries are solicited and most will appear, acceptance cannot, of course, be guaranteed. 1. Before preparing your commentary, please read carefully the Instructions for Authors and Commentators and examine recent numbers of PSYCOLOQUY. 2. Commentaries should be limited to 200 lines (1800 words, references included). PSYCOLOQUY reserves the right to edit commentaries for relevance and style. In the interest of speed, commentators will only be sent the edited draft for review when there have been major editorial changes. Where judged necessary by the Editor, commentaries will be formally refereed. 3. Please provide a title for your commentary. As many commentators will address the same general topic, your title should be a distinctive one that reflects the gist of your specific contribution and is suitable for the kind of keyword indexing used in modern bibliographic retrieval systems. Each commentary should have a brief (~50-60 word) abstract 4. All paragraphs should be numbered consecutively. Line length should not exceed 72 characters. The commentary should begin with the title, your name and full institutional address (including zip code) and email address. References must be prepared in accordance with the examples given in the Instructions. Please read the sections of the Instruction for Authors concerning style, preparation and editing. PSYCOLOQUY is a refereed electronic journal (ISSN 1055-0143) sponsored on an experimental basis by the American Psychological Association and currently estimated to reach a readership of 40,000. PSYCOLOQUY publishes brief reports of new ideas and findings on which the author wishes to solicit rapid peer feedback, international and interdisciplinary ("Scholarly Skywriting"), in all areas of psychology and its related fields (biobehavioral science, cognitive science, neuroscience, social science, etc.). All contributions are refereed. Target article length should normally not exceed 500 lines [c. 4500 words]. Commentaries and responses should not exceed 200 lines [c. 1800 words]. All target articles, commentaries and responses must have (1) a short abstract (up to 100 words for target articles, shorter for commentaries and responses), (2) an indexable title, (3) the authors' full name(s) and institutional address(es). In addition, for target articles only: (4) 6-8 indexable keywords, (5) a separate statement of the authors' rationale for soliciting commentary (e.g., why would commentary be useful and of interest to the field? what kind of commentary do you expect to elicit?) and (6) a list of potential commentators (with their email addresses). All paragraphs should be numbered in articles, commentaries and responses (see format of already published articles in the PSYCOLOQUY archive; line length should be < 80 characters, no hyphenation). It is strongly recommended that all figures be designed so as to be screen-readable ascii. If this is not possible, the provisional solution is the less desirable hybrid one of submitting them as postscript files (or in some other universally available format) to be printed out locally by readers to supplement the screen-readable text of the article. PSYCOLOQUY also publishes multiple reviews of books in any of the above fields; these should normally be the same length as commentaries, but longer reviews will be considered as well. Book authors should submit a 500-line self-contained Precis of their book, in the format of a target article; if accepted, this will be published in PSYCOLOQUY together with a formal Call for Reviews (of the book, not the Precis). The author's publisher must agree in advance to furnish review copies to the reviewers selected. Authors of accepted manuscripts assign to PSYCOLOQUY the right to publish and distribute their text electronically and to archive and make it permanently retrievable electronically, but they retain the copyright, and after it has appeared in PSYCOLOQUY authors may republish their text in any way they wish -- electronic or print -- as long as they clearly acknowledge PSYCOLOQUY as its original locus of publication. However, except in very special cases, agreed upon in advance, contributions that have already been published or are being considered for publication elsewhere are not eligible to be considered for publication in PSYCOLOQUY, Please submit all material to psyc@pucc.bitnet or psyc@pucc.princeton.edu Anonymous ftp archive is DIRECTORY pub/harnad/Psycoloquy HOST princeton.edu From schlimme@eecs.wsu.edu Thu Jun 22 07:41:33 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 22 Jun 95 07:41:27 -0500; AA15504 Received: from bilby.cs.uwa.oz.au by lucy.cs.wisc.edu; Thu, 22 Jun 95 07:41:23 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id RAA11331; Thu, 22 Jun 1995 17:25:32 +0800 Message-Id: <199506220925.RAA11331@cs.uwa.oz.au> From: schlimme@eecs.wsu.edu (Jeffrey C. Schlimmer) To: reinforce@cs.uwa.edu.au (Reinforcement List) Subject: 1996 Machine Learning Conference: Early Call Date: Wed, 21 Jun 1995 14:28:51 -0700 ***************************************************************** ICML'96 13th International Conference on Machine Learning Bari (Italy), July 3-6th, 1996 ***************************************************************** First Call for Papers and Workshop Proposals ***************************************************************** General Information =================== The 13th International Conference on Machine Learning (ICML'96) will be held in Bari, Italy, during July 3-6th, 1996, with informal workshops on July 3rd. The purpose of the conference is twofold: firstly, to emphasize the potential of machine learning approaches for solving problems in a wide range of application domains, secondly, to highlight relationships between machine learning and other fields, such as statistics, pattern recognition, artificial intelligence, control theory, instructional and cognitive sciences, computational complexity theory and software engineering. Program ======= The scientific program will include invited talks, presentations of refereed papers and a session of general discussion. Submissions are invited in all areas of Machine Learning, including, but not limited to: Abduction Analogy Applications of machine learning Artificial neural networks Case-Based learning Cognitive models of learning Computational learning theory Explanation-based learning Formal models of learning Inductive learning Inductive logic programming Genetic algorithms Knowledge discovery in databases Learning and problem solving Multistrategy learning Reinforcement learning Representation change Scientific discovery Theory revision Paper Format ============ Submissions must be clearly legible, with good quality print. Papers are limited to twelve (12) pages, excluding title page and bibliography, but including all tables and figures. Papers must be printed on 8-1/2 x 11 inch paper or A4 format, using 12 point type (10 characters per inch), with no more than 40 lines per page. A separate title page must include the title of the paper, the email and postal addresses of all authors, and a clear summary of the main contributions of the paper. The title page of accepted papers will be made available via World-Wide Web before the conference take place. Double-sided printing in encouraged. Requirement for Submissions =========================== Please send five (5) copies of each submitted paper to the Conference Chair. Submissions must be received by January 21st, 1996. Electronic or Fax submissions are not acceptable. Notification of acceptance or rejection will be mailed to the first (or designated) author by March 8th 1996. Camera-ready accepted papers are due on April 6th, 1996. Review Criteria =============== Each submitted paper will be reviewed by at least two members of the Program or Advisory Committee, and will be judged on significance, originality and clarity. Papers addressing application issues are welcome. Simultaneous submission to other conferences must be explicitly declared. In the case of multiple acceptance, presentation at ICML'96 and inclusion in the proceedings is only granted upon withdrawal from the other conference(s). Workshop Proposals ================== Workshop proposals are invited in all areas of Machine Learning. Please send a two (2) page description of the proposed workshop, its objectives, organizer(s), and expected number of attendees. The proposal must be received by the Workshop Chair by December 15th, 1995. Descriptions of accepted workshops will be made available via World-Wide Web. Notification of acceptance or rejection will be mailed to the organizer by January 31st, 1996. Calls for Papers for accepted workshops will be responsibility of the organizer(s). Program Chair ============= Lorenza Saitta, University of Torino saitta@di.unito.it Dipartimento di Informatica Phone: (+39) 11 - 7429.214 Corso Svizzera 185, 10149 Torino (Italy) Fax: (+39) 11 - 751.603 Local Chair =========== Floriana Esposito, University of Bari esposito@vm.csata.it Dipartimento di Informatica Phone: (+39) 80 - 5443.264 Via Orabona 4, 70125 Bari (Italy) Fax: (+39) 80 - 5443.196 Workshop Chair ============== Stefan Wrobel (wrobel@gmdzi.gmd.de) GMD, FIT.KI Schlo Birlinghoven 53754 Sankt Augustin (Germany) Publicity Chair =============== Jeff Schlimmer (schlimme@eecs.wsu.edu) School of Electrical Engineering and Computer Science Washington State University Pullman, WA 99164-2752 (USA) Advisory Committee ================== Jaime Carbonell (USA) William Cohen (USA) Kenneth De Jong (USA) Tom Dietterich (USA) Tom Mitchell (USA) Stuart Russell (USA) Derek Sleeman (UK) Paul Utgoff (USA) Organizing Committee ==================== Donato Malerba and Giovanni Semeraro (Italy) {malerbad, semeraro}@vm.csata.it Marco Botta and Filippo Neri (Italy) {botta, neri}@di.unito.it General Inquiries ================= Please address general inquiries to any of the members of the Organizing Committee or to the address: icml96@di.unito.it ICML'96 has its own page on the World-Wide Web in the URL at: http://www.di.unito.it/pub/WWW/ICML96/home.html This announcement is also available in PostScript in the URL at: ftp://ftp.di.unito.it/pub/ICML96/callforpapers.ps In order to receive further information, please send a note to the Publicity Chair. ----------------------------------------------------------------------------- Important dates =============== Workshop submission deadline: December 15, 1995 Paper submission deadline: January 21, 1996 Notification of workshop acceptance: January 31, 1996 Notification of paper acceptance: March 8, 1996 Camera-ready copy: April 6, 1996 ----------------------------------------------------------------------------- Jeffrey C. Schlimmer, Asst. Prof., School of EE & CS, Washington State University, Pullman, WA 99164-2752, (509) 335-2399, (509) 335-3818 FAX http://www.eecs.wsu.edu/~schlimme/ -----BEGIN PGP PUBLIC KEY BLOCK----- Version: 2.6.2 mQBvAy+obPwAAAEDALrQe0O/IrbBRuhPsWs9uvpCwBrNJBug+bqq25JFztmuHEEa jpmkHHe9Z5fnybs7o97E/ylN2riwoqm3TcK3F7idvIBsdaMZhpwHHlDnHHP0chx8 PY6hHbJk2X/kkZvF6QARAQABtCxKZWZmcmV5IEMuIFNjaGxpbW1lciA8c2NobGlt bWVAZWVjcy53c3UuZWR1Pg== =exEt -----END PGP PUBLIC KEY BLOCK----- From juergen@idsia.ch Thu Jun 22 07:48:51 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 22 Jun 95 07:48:47 -0500; AA15592 Received: from bilby.cs.uwa.oz.au by lucy.cs.wisc.edu; Thu, 22 Jun 95 07:48:43 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id RAA11356; Thu, 22 Jun 1995 17:27:59 +0800 Message-Id: <199506220927.RAA11356@cs.uwa.oz.au> From: juergen@idsia.ch (Juergen Schmidhuber) To: reinforce@cs.uwa.oz.au Subject: 4 new IDSIA publications [connectionists] Date: Wed, 21 Jun 95 10:13:44 +0200 4 new IDSIA publications available. Click at http://www.idsia.ch or use ftp: FTP-host: fava.idsia.ch (192.132.252.1) FTP-filenames: /pub/papers/ml95.kolmogorov.ps.gz 9 pages /pub/papers/ml95.antq.ps.gz 9 pages /pub/papers/iwann95.invertible.ps.gz 8 pages /pub/papers/idsia59-95.ps.gz 12 pages (use gunzip to uncompress) ___________________________________________________________________ DISCOVERING SOLUTIONS WITH LOW KOLMOGOROV COMPLEXITY AND HIGH GENERALIZATION CAPABILITY Juergen Schmidhuber, IDSIA To appear in Machine Learning: Proc. 12th int. conf., 1995. This paper reviews basic concepts of Kolmogorov complexity theory relevant to machine learning. It shows how a derivate of Levin's universal search algorithm can be used to discover neural nets with low Levin complexity, low Kolmogorov complexity, and high generalization capability. At least with certain toy problems where it is computationally feasible, the method can lead to generalization results unmatchable by previous neural net algorithms. The final section addresses problems with incremental learning situations. ANT-Q Luca Gambardella, IDSIA Marco Dorigo, IDSIA To appear in Machine Learning: Proc. 12th int. conf., 1995. We introduce Ant-Q, a family of algorithms which share many similarities with Q-learning (Watkins, 1989). Ant-Q is a generalization of the ``ant system'' (AS --- Dorigo, 1992; Dorigo, Maniezzo and Colorni, 1996), a distributed algorithm for combinatorial optimization based on the ant colony metaphor. In applications to symmetric traveling salesman problems (TSPs), we demonstrate (1) that some Ant-Q instances outperform AS, and (2) that Ant-Q compares favorably with other heuristic approaches based on neural nets or local search. Finally, we apply Ant-Q to some difficult asymmetric TSP's and obtain excellent results: Ant-Q finds solutions of a quality which usually can be found only by highly specialized algorithms. LEARNING THE VISUOMOTOR COORDINATION OF A MOBILE ROBOT BY USING THE INVERTIBLE KOHONEN MAP Cristina Versino, IDSIA Luca Gambardella, IDSIA In Proc. International Workshop on Artificial Neural Networks 1995. This paper is based on the insight that the Extended Kohonen Map (EKM) is naturally invertible: given an input pattern, the network output is generated by competition among the neuron fan-in weight vectors (conventional ``forward mode''). Viceversa, given an output value, a corresponding input pattern can be obtained by competition among the neuron fan-out weight vectors (unconventional ``backward mode''). This invertibility property makes EKM worth considering for sensorimotor modeling. We present an experiment concerning visuomotor coordination of a simple mobile robot. ``Learning by doing'' creates a sensorimotor model: pairs are collected by observing the robot's behavior. These pairs are used for estimating the model's parameters. Training the network on the robot's direct kinematics (forward mode), one simultaneously obtains a solution to the inverse kinematics problem (backward mode). The experiment has been performed both in a simulation and by using a real robot. ENVIRONMENT-INDEPENDENT REINFORCEMENT ACCELERATION Technical Note IDSIA-59-95 Write-up of invited talk at Hongkong Univ. ST (May 29, 1995) Juergen Schmidhuber, IDSIA A reinforcement learning system with limited computational resources interacts with an unrestricted, unknown environment. Its goal is to maximize cumulative reward, to be obtained throughout its limited, unknown lifetime. System policy is an arbitrary modifiable algorithm mapping environmental inputs and internal states to outputs and new internal states. The problem is: in realistic, unknown environments, each policy modification process (PMP) occurring during system life may have unpredictable influence on environmental states, rewards and PMPs at any later time. Existing reinforcement learning algorithms cannot properly deal with this. Neither can naive exhaustive search among all policy candidates --- not even in case of very small search spaces. In fact, a reasonable way of measuring performance improvements in such general (but typical) situations is missing. I define such a measure based on the novel ``reinforcement acceleration criterion'' (RAC). RAC is satisfied if the beginning of each completed PMP that computed a currently valid policy modification has been followed by faster average reinforcement intake than system start-up and the beginnings of all previous such PMPs (the computation time for PMPs is taken into account). Then I present a method called ``environment-independent reinforcement acceleration'' (EIRA) which is guaranteed to achieve RAC. EIRA does neither care whether the system's policy allows for changing itself, nor whether there are multiple, interacting learning systems. Consequences are: (1) a sound theoretical framework for ``meta- learning'' (because the success of a PMP recursively depends on the success of all later PMPs, for which it is setting the stage). (2) A sound theoretical framework for multi-agent learning. The principles have been implemented (1) in a single system using an assembler-like programming language to modify its own policy, and (2) a system consisting of multiple agents, where each agent is in fact just a connection in a fully recurrent reinforcement learning neural net. A by-product of this research is a general reinforcement learning algorithm for such nets. Preliminary experiments illustrate the theory. ___________________________________________________________________ Related and other papers in http://www.idsia.ch Comments welcome. Juergen Schmidhuber Research Director IDSIA, Corso Elvezia 36 6900-Lugano, Switzerland juergen@idsia.ch From icsc@freenet.edmonton.ab.ca Thu Jun 22 16:43:58 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 22 Jun 95 16:43:55 -0500; AA21825 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Thu, 22 Jun 95 16:43:53 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa03267; 22 Jun 95 15:29:40 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa03260; 22 Jun 95 15:02:49 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa11158; 22 Jun 95 15:01:59 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa03762; 22 Jun 95 12:15:00 EDT Received: from freenet.edmonton.ab.ca by EDRC.CMU.EDU id aa06886; 22 Jun 95 12:14:04 EDT Received: by freenet.edmonton.ab.ca (AIX 3.2/UCB 5.64/FEAC1.002) id AA58135; Thu, 22 Jun 1995 10:08:54 -0600 Date: Thu, 22 Jun 1995 10:08:53 -0600 (MDT) From: icsc@freenet.edmonton.ab.ca To: connectionists@cs.cmu.edu Subject: Announcement / Call for papers SOCO'96 Message-Id: Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII ICSC - International Computer Science Conventions Call for Papers International Symposium on SOFT COMPUTING - SOCO'96 (Fuzzy Logic, Artificial Neural Networks and Genetic Algorithms) To be held at the University of Reading, Whiteknights, Reading, England March 26 - 28, 1996 I. SPONSORS University of Reading, U.K. International Computer Science Conventions (ICSC), Canada/Switzerland II. ORGANISATION OF THE CONFERENCE SOCO'96 is organised as a parallel conference to IIA'96 (International Symposium on Intelligent Industrial Automation). Both conferences are joint operations of the Department of Cybernetics, University of Reading, England and International Computer Science Conventions (ICSC), Canada/Switzerland. III. PURPOSE OF THE CONFERENCE The purpose of this conference is to assist communication of research in the fields of Fuzzy Logic, Neural Networks, Genetic Algorithms and their technological applications. The 'marriage' of fuzzy logic and neural net technologies offers many advantages in terms of fault-tolerance and speed of implementation. Intelligent automation is achieved by implementing humanlike intelligence and soft computing, a newly introduced concept, which encompasses three intelligence-based methods: fuzzy logic, neural network and genetic algorithms. IV. TOPICS Papers are encouraged in all areas related to Soft Computing, such as the following examples: * Artificial Neural Networks * Fuzzy Logic * Fuzzy Control * Genetic Algorithms * AI and Expert Systems * Probabilistic Reasoning * Machine Learning * Distributed Intelligence * Learning Algorithms and Intelligent Control * Self-Organizing Systems V. INTERNATIONAL SCIENTIFIC COMMITTEE - ISC H. Adeli, USA / E. Alpaydin, Turkey / P.G. Anderson, USA (Chairman) / M. Dorigo, Belgium / H. Hellendoorn, Germany / M. Jamshidi, USA/France / B. Kosko, USA / F. Masulli, Italy / P.G. Morasso, Italy / C.C. Nguyen, USA / G.D. Smith, U.K. / N. Steele, U.K. (Vice Chairman) / S. Tzafestas, Greece / K. Warwick, U.K. VI. PUBLICATION OF PAPERS All accepted papers will appear in the conference proceedings, published by ICSC Academic Press. In addition, some selected papers may also be considered for journal publication. VII. SUBMISSIONS OF MANUSCRIPTS Prospective authors are requested to send two copies of their abstracts of 500 words for review by the International Scientific Committee. All abstracts must be written in English, starting with a succinct statement of the problem, the results achieved, their significance and a comparison with previous work. If authors believe that more details are necessary to substantiate the main claims of the paper, they may include a clearly marked appendix that will be read at the discretion of the International Scientific Committee. The abstract should also include: * Indication, if submitted for SOCO'96 or IIA'96 (see separate call for papers) * Title of proposed paper * Authors names, affiliations, addresses * Name of author to contact for correspondence * Email address and fax number of contact author * Name of topic which best describes the paper (max. 5 keywords) Contributions are welcome from those working in industry and having experience in the topics of this conference as well as from academics. The Conference language is English. Abstracts may be submitted either by electronic mail (ASCII text), fax or mail (2 copies) to either one of the following addresses: ICSC Canada P.O. Box 279 Millet, Alberta T0C 1Z0 Canada Email: icsc@freenet.edmonton.ab.ca Fax: +1-403-387-4329 or ISCS Switzerland P.O. Box 657 CH-8055 Zurich Switzerland or University of Reading Dept. of Cybernetics Whiteknights P.O. Box 225 Reading RG6 6AY U.K. VIII.WORKSHOP Contributions for a workshop on Soft Computing Methods for Pattern Recognition are welcome and abstracts (marked "workshop") may be submitted to ICSC Canada until July 31, 1995. IX. DEADLINES AND REGISTRATION It is the intention of the organizers to have the conference proceedings available for the delegates. Consequently the deadlines below are to be strictly respected: * Submission of Abstracts: July 31, 1995 * Notification of Acceptance: September 30, 1995 * Delivery of Full Papers: November 30, 1995 * Early registration: November 30, 1995 * Late registration Full registration (approx. English Pounds 325.00 for early registration) includes attendance to all sessions, lunches, dinners and coffee-breaks, pre-conference reception, conference banquet/social programme and conference proceedings. Combined registration for SOCO'96 and IIA'96 will be available at reduced rates. Full-time students, who have a valid student ID-card, may register with a rebate by eliminating proceedings, banquet/social programme and meals. Extra banquet/social programme tickets will be sold for accompanying persons and students. The proceedings can be purchased separately. X. ACCOMMODATION Accommodation (not included in the registration fee) is available at very reasonable rates at the University Campus. Full details will be made available with the letter of acceptance. XI. FURTHER INFORMATION For further information please contact: ICSC Canada, P.O. Box 279, Millet, Alberta, T0C 1Z0, Canada Email: icsc@freenet.edmonton.ab.ca Fax: +1-403-387-4329 / Phone: +1-403-387-3546 or University of Reading, Department of Cybernetics, Whiteknights, P.O. Box 225, Reading RG6 6AY, U.K. Fax: +44-1734-318 220 / Phone: +44-1734-318 214) ICSC CANADA email: icsc@freenet.edmonton.ab.ca MILLET, AB, T0C 1Z0 From rinkus@PARK.BU.EDU Fri Jun 23 13:48:53 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 23 Jun 95 13:48:50 -0500; AA22423 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 23 Jun 95 13:48:48 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa04669; 23 Jun 95 12:24:41 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa04639; 23 Jun 95 12:02:05 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12141; 23 Jun 95 12:01:15 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa20586; 23 Jun 95 11:01:18 EDT Received: from PARK.BU.EDU by RI.CMU.EDU id aa08214; 23 Jun 95 11:00:27 EDT Received: from space.bu.edu by cns.bu.edu (8.6.10/BU_Server-1.1) id KAA19876; Fri, 23 Jun 1995 10:56:02 -0400 Received: by space.bu.edu (8.6.10/BU_Client-1.1) id KAA03369; Fri, 23 Jun 1995 10:56:00 -0400 Date: Fri, 23 Jun 1995 10:56:00 -0400 From: rinkus@PARK.BU.EDU Mmdf-Warning: Parse error in original version of preceding line at DST.BOLTZ.CS.CMU.EDU Message-Id: <199506231456.KAA03369@space.bu.edu> To: Connectionists@cs.cmu.edu Subject: paper avail.: "TEMECOR: An Associative, Episodic, Temporal Sequence Memory" FTP-host: cns-ftp.bu.edu FTP-file: pub/rinkus/nips95_rinkus.ps.Z The following paper, which has been submitted to NIPS-95, and which is an extended and revised version of a paper that has been accepted for invited address at WCNN-95, is available via anonymous FTP at the above location. The paper is 8 pages long. ============================================================================ TEMECOR: An Associative, Episodic, Temporal Sequence Memory Gerard J. Rinkus Cognitive and Neural Systems Department Boston University Boston, MA 02215 rinkus@cns.bu.edu ABSTRACT A distributed associative neural model of {\em episodic memory}\/ for spatio-temporal patterns is presented. The model exhibits {\em faster-than-linear}\/ capacity scaling, under single-trial learning, for both uncorrelated and correlated patterns. The correlated pattern sets used in simulations reported herein are formally, sets of {\em complex state sequences}\/ (CSSs)---i.e. sequences in which states can recur multiple times. Efficient representation of large sets of CSSs is central to speech and language processing. The English lexicon, for example, is formally representable as a set of many thousands of CSSs over an alphabet of about 50 phonemes. The model chooses internal representations (IRs) for each state in a highly random fashion. This implies maximal {\em dispersion}---i.e. maximal average Hamming distance---over the set of IRs chosen during learning. Maximal dispersion yields maximal episodic availability of the traces of the individual exemplars. ============================================================================ FTP instructions: unix> ftp cns-ftp.bu.edu Name: anonymous Password: your full email address ftp> cd pub/rinkus ftp> get nips95_rinkus.ps.Z ftp> bye unix> uncompress nips95_rinkus.ps.Z From milanese@cui.unige.ch Fri Jun 23 13:48:55 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 23 Jun 95 13:48:52 -0500; AA22429 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 23 Jun 95 13:48:50 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab04669; 23 Jun 95 12:25:56 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab04639; 23 Jun 95 12:02:07 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12147; 23 Jun 95 12:01:43 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa19292; 23 Jun 95 9:30:57 EDT Received: from chx400.switch.ch by CS.CMU.EDU id aa16766; 23 Jun 95 9:30:19 EDT X400-Received: by mta chx400.switch.ch in /PRMD=Switch/ADMD=Arcom/C=Ch/; Relayed; Fri, 23 Jun 1995 15:29:13 +0200 X400-Received: by /PRMD=SWITCH/ADMD=ARCOM/C=CH/; Relayed; Fri, 23 Jun 1995 15:29:03 +0200 X400-Received: by /PRMD=switch/ADMD=arcom/C=ch/; Relayed; Fri, 23 Jun 1995 15:28:58 +0200 Date: Fri, 23 Jun 1995 15:28:58 +0200 X400-Originator: milanese@cui.unige.ch X400-Recipients: non-disclosure:; X400-Mts-Identifier: [/PRMD=switch/ADMD=arcom/C=ch/;950623152858] X400-Content-Type: P2-1984 (2) Content-Identifier: 2340 Alternate-Recipient: Allowed From: Ruggero Milanese Message-Id: <2340*/S=milanese/OU=cui/O=unige/PRMD=switch/ADMD=arcom/C=ch/@MHS> To: Connectionists@cs.cmu.edu Subject: Combining multiple estimates Hello, I am interested in computing the trajectory and the velocity parameters of objects moving in the camera field of view, combining classical computer vision and neural network algorithms. I have several measures/estimates of the motion parameters, extracted through different methods. I am interested in combining these estimates in order to obtain a "combined-estimate" which is closer to the "real values". So far, I have found the following papers that seem relevant to this problem: - "Combining estimators using non-constant weighting functions", by V. Tresp and M. Taniguchi, Advances in Neural Information Processing Systems 7, MIT Press, 1995. - "Multitarget-Multisensor Tracking: Advanced Applications", editor Bar-Shalom, Artech House, 1990. - "Optimal linear combination of neural networks", PhD. Thesis Sh. Hashem, 1993. Could anyone please give me any other pointers or suggest alternative approaches that possibly use non-constant weighting functions? Please send replies to: Sylvia Gil Dept. of Computer Science E-mail: gil@cui.unige.ch University of Geneva Phone: +41 (22) 705-7628 24, rue du General Dufour Fax: +41 (22) 705-7780 1211 Geneva 4 http://cuiwww.unige.ch Switzerland Thank you a lot. -Ruggero Milanese University of Geneva, Switzerland milanese@cui.unige.ch From uzimmer@informatik.uni-kl.de Fri Jun 23 13:48:56 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 23 Jun 95 13:48:48 -0500; AA22421 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 23 Jun 95 13:48:46 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab04636; 23 Jun 95 12:17:26 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab04634; 23 Jun 95 12:00:19 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12128; 23 Jun 95 11:59:50 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa19179; 23 Jun 95 9:18:03 EDT Received: from stepsun.uni-kl.de by CS.CMU.EDU id aa16658; 23 Jun 95 9:16:15 EDT Received: from uklirb.informatik.uni-kl.de by stepsun.uni-kl.de id aa13151; 23 Jun 95 15:11 MET DST Received: from ag-vp-file-server.informatik.uni-kl.de by uklirb.uklirb.informatik.uni-kl.de id aa26573; 23 Jun 95 15:07 MET DST Subject: PhD thesis "Adaptive Approaches to Basic Mobile Robot Tasks" available To: connectionists@cs.cmu.edu, neuron@CATTELL.psych.upenn.edu, crr@ireq-robot.hydro.qc.ca From: "Uwe R. Zimmer, AG vP" Date: Fri, 23 Jun 95 15:07:28 +0100 Reply-To: uzimmer@informatik.uni-kl.de Message-Id: <950623.150728.2257@ag-vp-file-server.informatik.uni-kl.de> PhD thesis available via WWW / FTP: keywords: mobile robots, exploration, world modelling, navigation, object recognition, artificial neural networks, fuzzy logic ------------------------------------------------------------------ Adaptive Approaches to Basic Mobile Robot Tasks ------------------------------------------------------------------ Uwe R. Zimmer PhD thesis - January 1995 The present thesis addresses the research field of adaptive behaviour concerning mobile robots. The world as "seen" by the robot is previously unknown and has to be explored by manoeuvring according to certain optimization criteria. This assumption enhances the fitness of a mobile robot for a range of applications beyond rigid installations, demanding normally significant effort, and offering limited ability to adapt to changes in the environment. A central concept emphasized in this thesis is the achieving of competence and fitness through continuous interaction with the robot's world. Lifelong learning is considered, even after achieving a temporally sufficient degree of adaptation and running in parallel to the actual robot's application. The levels of competence are generated bottom up, i.e. upper levels are based on the current robot's experience modelled in lower levels. The terms (the skills are formulated with) employed on higher levels are generated through real world interactions on lower levels. The robotics problems discussed are limited to some basic tasks, which are found to be relevant for most mobile robot applications. These are exploration of unknown environments, stable self-localization with respect to the current world and its internal representation, as well as navigation, target extraction, and target recognition. In order to cope with problems resulting from a lack of proper a-priori knowledge and defined and reliably detectable symbols in unknown and dynamic environments, connectionist methods are employed to a great extend. Realtime constraints are considered at all levels of competence, with the natural exception of global planning. The research field of target extraction and identification with respect to mobile robot constraints leads especially to the discussion of visual search (steering), extraction of geometric primitives even at system start-up time, and to the generation of symbols out of subsymbolic processing. These symbols can be reliably recognized and should be suitable for a following symbolic planning level, outside the focus of the present thesis. The presented approach ensures a large degree of adaptability on all levels, not discussed before to this wide extent, or even investigated for the first time regarding some components (e.g. visual search with highly focused devices). The exploration, self-localization, and navigation tasks are attacked by an integral approach allowing the parallel processing of these tasks in a dynamic environment. The stability and reliability of the discussed techniques are proven on the base of realtime and real world experiments with a mobile platform. The high error tolerance and low demands concerning the used sensor devices, as well as the small computation power required, are (currently) unique features of the presented method. Files: - Part I : Introduction - 24 pages, 0.9 MB - Part II : ALICE - 30 pages, 2.0 MB - Part III : SPIN - 60 pages, 1.6 MB - Part IV : Conclusion & Appendix - 38 pages, 0.9 MB for the WWW-links to the files of this thesis: ------------------------------------------------------------------ http://ag-vp-www.informatik.uni-kl.de/Projekte/ALICE/abs.PhD.html ------------------------------------------------------------------ for the homepage of the author (including more reports): ------------------------------------------------------------------ http://ag-vp-www.informatik.uni-kl.de/Leute/Uwe/ ------------------------------------------------------------------ or for the ftp-server hosting the files: ------------------------------------------------------------------ ftp://ag-vp-ftp.informatik.uni-kl.de/Public/Neural_Networks/ Reports/Zimmer.PhD/ ... ------------------------------------------------------------------ ----------------------------------------------------- ----- Uwe R. Zimmer --- University of Kaiserslautern - Computer Science Department | 67663 Kaiserslautern - Germany | ------------------------------.--------------------------------. Phone:+49 631 205 2624 | Fax:+49 631 205 2803 | ------------------------------.--------------------------------. http://ag-vp-www.informatik.uni-kl.de/Leute/Uwe/ | From smagt@fwi.uva.nl Sat Jun 24 01:36:47 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sat, 24 Jun 95 01:36:45 -0500; AA28320 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sat, 24 Jun 95 01:36:43 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa04636; 23 Jun 95 12:16:33 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa04634; 23 Jun 95 12:00:15 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12123; 23 Jun 95 11:59:40 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa15947; 23 Jun 95 5:35:53 EDT Received: from mail.fwi.uva.nl by RI.CMU.EDU id aa07418; 23 Jun 95 5:34:27 EDT Received: from brad.fwi.uva.nl by mail.fwi.uva.nl with SMTP (5.65c/5.1) id AA05609; Fri, 23 Jun 1995 11:34:16 +0200 Received: by brad.fwi.uva.nl id AA03412; Fri, 23 Jun 1995 11:34:13 +0200 Message-Id: <199506230934.AA03412@brad.fwi.uva.nl> Return-Path: From: Patrick van der Smagt X-Organisation: Faculty of Mathematics & Computer Science University of Amsterdam Kruislaan 403 NL-1098 SJ Amsterdam The Netherlands X-Phone: +31 20 525 7463 X-Telex: 10262 hef nl X-Fax: +31 20 525 7490 Subject: Preprint available (robotics & vision NN) To: connectionists@cs.cmu.edu Date: Fri, 23 Jun 1995 11:34:12 +0200 (MET DST) X-Mailer: ELM [version 2.4 PL23] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Content-Length: 1387 The following preprint is now available: A VISUALLY GUIDED ROBOT AND A NEURAL NETWORK JOIN TO GRASP SLANTED OBJECTS P. van der Smagt, A. Dev, and F.C.A. Groen (1995) Proceedings of the 1995 Dutch Conference on Neural Networks (in print) --------------------------------------------------------------------------- FTP-HOST: ftp.fwi.uva.nl (146.50.3.49) FTP-FILE: pub/computer-systems/aut-sys/reports/SmaDevGro95.ps.gz 84 Kb, 8 pages --------------------------------------------------------------------------- ftp://ftp.fwi.uva.nl/pub/computer-systems/aut-sys/reports/SmaDevGro95.ps.gz http://www.fwi.uva.nl/fwi/research/vg4/neuro/publications/publications.html --------------------------------------------------------------------------- Abstract: In this paper we introduce a method for model-free monocular visual guidance of a robot arm. The robot arm, with a single camera in its end-effector, should be positioned above a target, with a changing pan and tilt, which is placed against a textured background. It is shown that a trajectory can be planned in visual space by using components of the optic flow, and this trajectory can be translated to joint torques by a self-learning neural network. No model of the robot, camera, or environment is used. The method reaches a high grasping accuracy after only a few trials. From hu@eceserv0.ece.wisc.edu Sat Jun 24 01:36:53 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sat, 24 Jun 95 01:36:50 -0500; AA28326 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sat, 24 Jun 95 01:36:47 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa04796; 23 Jun 95 14:42:44 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa04794; 23 Jun 95 14:33:14 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12255; 23 Jun 95 14:32:57 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa22029; 23 Jun 95 12:42:38 EDT Received: from eceserv0.ece.wisc.edu by CS.CMU.EDU id aa18517; 23 Jun 95 12:41:27 EDT Received: by eceserv0.ece.wisc.edu (WE5:5.65c/ES5) id AA26351; Fri, 23 Jun 1995 11:41:18 -0500 Date: Fri, 23 Jun 1995 11:41:18 -0500 From: Yu Hu Message-Id: <199506231641.AA26351@eceserv0.ece.wisc.edu> To: Connectionists@cs.cmu.edu Subject: LAST CALL FOR PAPERS: 1995 Int' Symp. on ANN (Taiwan, ROC) ****************************************************************************** SECOND AND LAST CALL FOR PAPERS 1995 International Symposium on Artificial Neural Networks December 18-20, 1995, Hsinchu, Taiwan, Republic of China ****************************************************************************** Sponsored by National Chiao-Tung University in cooperation with Ministry of Education, Taiwan R.O.C., National Science Council, Taiwan R.O.C. and IEEE Signal Processing Society ************************* Distinguished Speakers: ************************* Prof. Leon Chua, UC Berkeley, USA. Prof. John Moody, Oregon Graduate Institute, USA. Porf. Tse Jun Tarn, Washington Univ., USA. ************************* Call for Papers ************************* The third of a series of International Symposium on Artificial Neural Networks will be held at the National Chiao-Tung University, Hsinchu, Taiwan in December of 1995. Papers are solicited for, but not limited to, the following topics: Associative Memory Robotics Electrical Neurocomputers Sensation & Perception Image/Speech Processing Sensory/Motor Control Systems Machine Vision Supervised Learning Neurocognition Unsupervised Learning Neurodynamics Fuzzy Neural Systems Optical Neurocomputers Mathematical Methods Optimization Other Applications Prospective authors are invited to submit 4 copies of extended summaries of no more than 4 pages. All the manuscripts should be written in English with single-spaced, single column, on 8.5" by 11" white papers. The top of the first page of the summary should include a title, authors' names, affiliations, address, telephone/fax numbers, and email address if applicable. The indicated corresponding author will receive an acknowledgement of his/her submissions. Camera-ready full papers of accepted manuscripts will be published in a hard-bound proceedings and distributed at the symposium. For more information, please consult at the MOSAIC URL site http://www.ee.washington.edu/isann95.html, or use anonymous ftp from pierce.ee.washington.edu/pub/isann95/read.me (128.95.31.129). ************************* SCHEDULE ************************* Submission of extended summary: July 15 Notification of acceptance: September 30 Submission of photo-ready paper: October 31 Advanced registration, before: November 10 ************************* For submission from USA and Europe: ************************* Professor Yu-Hen Hu Dept. of Electrical and Computer Engineering Univ. of Wisconsin - Madison, Madison, WI 53706-1691 Phone: (608) 262-6724, Fax: (608) 262-1267 Email: hu@engr.wisc.edu ************************* For submission from Asia and Other Areas: ************************* Professor Sin-Horng Chen Dept. of Communication Engineering National Chiao-Tung Univ., Hsinchu, Taiwan Phone: (886) 35-712121 ext. 54522, Fax: (886) 35-710116 Email: isann95@cc.nctu.edu.tw ORGANIZATIOIN General Co-Chairs Hsin-Chia Fu Jenq-Neng Hwang National Chiao-Tung University University of Washington Hsinchu, Taiwan Seattle, Washington, USA hcfu@csie.nctu.edu.tw hwang@ee.washington.ed Program Co-Chairs Sin-Horng Chen Yu-Hen Hu National Chiao-Tung University University of Wisconsin Hsinchu, Taiwan Madison, Wisconsin, USA schen@cc.nctu.edu.tw hu@engr.wisc.edu Advisory Board Co-Chair Sun-Yuan Kung C. Y. Wu Princeton University National Science Council Princeton, New Jersey, US Taipei, Taiwan, ROC From baluja@GS93.SP.CS.CMU.EDU Sat Jun 24 01:36:56 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sat, 24 Jun 95 01:36:53 -0500; AA28332 Message-Id: <9506240636.AA22325@lucy.cs.wisc.edu> Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sat, 24 Jun 95 01:36:51 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa04901; 23 Jun 95 16:59:42 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa04899; 23 Jun 95 16:47:22 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12384; 23 Jun 95 16:46:59 EDT Received: from GS93.SP.CS.CMU.EDU by B.GP.CS.CMU.EDU id aa26424; 23 Jun 95 16:19:28 EDT From: Shumeet Baluja Date: Fri, 23 Jun 95 16:18:51 EDT To: connectionists@cs.cmu.edu Cc: baluja@cs.cmu.edu, caruana@cs.cmu.edu Subject: paper: Removing the Genetics from the Standard Genetic Algorithm Title: Removing the Genetics from the Standard Genetic Algorithm By: Shumeet Baluja and Rich Caruana Abstract: We present an abstraction of the genetic algorithm (GA), termed population-based incremental learning (PBIL), that explicitly maintains the statistics contained in a GA's population, but which abstracts away the crossover operator and redefines the role of the population. This results in PBIL being simpler, both computationally and theoretically, than the GA. Empirical results reported elsewhere show that PBIL is faster and more effective than the GA on a large set of commonly used benchmark problems. Here we present results on a problem custom designed to benefit both from the GA's crossover operator and from its use of a population. The results show that PBIL performs as well as, or better than, GAs carefully tuned to do well on this problem. This suggests that even on problems custom designed for GAs, much of the power of the GA may derive from the statistics maintained implicitly in its population, and not from the population itself nor from the crossover operator. This paper may be of interest to the connectionist community as the PBIL algorithm is largely based upon supervised competitive learning algorithms. This paper will appear in the Proceedings of the International Confernece on Machine Learning, 1995. instructions ---------------------------------------------- via anonymous ftp at: reports.adm.cs.cmu.edu once you are logged in, issue the following commands: binary cd 1995 get CMU-CS-95-141.ps From baluja@GS93.SP.CS.CMU.EDU Sat Jun 24 01:36:57 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sat, 24 Jun 95 01:36:54 -0500; AA28334 Message-Id: <9506240636.AA22328@lucy.cs.wisc.edu> Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sat, 24 Jun 95 01:36:52 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa04949; 23 Jun 95 17:14:48 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa04947; 23 Jun 95 17:07:19 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12460; 23 Jun 95 17:07:15 EDT Received: from GS93.SP.CS.CMU.EDU by B.GP.CS.CMU.EDU id aa27156; 23 Jun 95 17:06:21 EDT From: Shumeet Baluja Date: Fri, 23 Jun 95 17:05:45 EDT To: connectionists@cs.cmu.edu Cc: baluja@cs.cmu.edu Subject: paper: ANN Based Task-Specific Focus of Attention Title: Using the Representation in a Neural Network's Hidden Layer for Task-Specific Focus of Attention By: Shumeet Baluja and Dean Pomerleau Abstract: In many real-world tasks, the ability to focus attention on the important features of the input is crucial for good performance. In this paper a mechanism for achieving task-specific focus of attention is presented. A saliency map, which is based upon a computed expectation of the contents of the inputs at the next time step, indicates which regions of the input retina are important for performing the task. The saliency map can be used to accentuate the features which are important, and de-emphasize those which are not. The performance of this method is demonstrated on a real-world robotics task: autonomous road following. The applicability of this method is also demonstrated in a non-visual domain. Architectural and algorithmic details are provided, as well as empirical results. This paper will appear in IJCAI 95. instructions ---------------------------------------------- via anonymous ftp at: reports.adm.cs.cmu.edu once you are logged in, issue the following commands: binary cd 1995 get CMU-CS-95-143.ps