From nkasabov@commerce.otago.ac.nz Sun Jan 19 19:16:05 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id TAA01339 for ; Sun, 19 Jan 1997 19:15:58 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id TAA01285 for ; Sun, 19 Jan 1997 19:15:57 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa08840; 19 Jan 97 19:10:41 EST Received: from SKINNER.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa08838; 19 Jan 97 18:45:28 EST Received: from skinner.boltz.cs.cmu.edu by skinner.boltz.cs.cmu.edu id aa19897; 19 Jan 97 18:44 EST Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa10258; 19 Jan 97 15:40:05 EST Received: from galadriel.otago.ac.nz by RI.CMU.EDU id aa03494; 19 Jan 97 15:39:35 EST Received: from jupiter.otago.ac.nz (jupiter.otago.ac.nz [139.80.180.14]) by galadriel.otago.ac.nz (8.8.4/8.8.4) with ESMTP id JAA27970 for ; Mon, 20 Jan 1997 09:39:16 +1300 (NZDT) Received: from JUPITER/SpoolDir by jupiter.otago.ac.nz (Mercury 1.20); 20 Jan 97 09:39:18 +1100 Received: from SpoolDir by JUPITER (Mercury 1.20); 20 Jan 97 09:39:13 +1100 From: Nikola Kasabov Organization: University of Otago To: Connectionists@cs.cmu.edu Date: Mon, 20 Jan 1997 09:39:11 -1200 Subject: ICONIP'97 call for papers Priority: normal X-mailer: Pegasus Mail for Windows (v2.23) Message-ID: <120BF143F97@jupiter.otago.ac.nz> CALL FOR PAPERS, PRESENTATIONS, SPECIAL SESSIONS ICONIP'97 jointly with ANZIIS'97 and ANNES'97 (in cooperation with IEEE NNC and INNS) The Fourth International Conference on Neural Information Processing-- The Annual Conference of the Asian Pacific Neural Network Assembly, jointly with The Fifth Australian and New Zealand International Conference on Intelligent Information Processing Systems, and The Third New Zealand International Conference on Artificial Neural Networks and Expert Systems, 24-28 November, 1997 Dunedin/Queenstown, New Zealand The joint conference will have three parallel streams: Stream1: Neural Information Processing Stream2: Computational Intelligence and Soft Computing Stream3: Intelligent Information Systems and their Applications TOPICS OF INTEREST Stream1: Neural Information Processing * Neurobiological systems * Cognition * Cognitive models of the brain * Dynamical modelling, chaotic processes in the brain * Brain computers, biological computers * Consciousness, awareness, attention * Adaptive biological systems * Modelling emotions * Perception, vision * Learning languages * Evolution Stream2: Computational Intelligence and Soft Computing * Artificial neural networks: models, architectures, algorithms * Fuzzy systems * Evolutionary programming and genetic algorithms * Artificial life * Distributed AI systems, agent-based systems * Soft computing--paradigms, methods, tools * Approximate reasoning * Probabilistic and statistical methods * Software tools, hardware implementation Stream3: Intelligent Information Systems and their Applications * Connectionist-based information systems * Hybrid systems * Expert systems * Adaptive systems * Machine learning, data mining and intelligent databases * Pattern recognition and image processing * Speech recognition and language processing * Intelligent information retrieval systems * Human-computer interfaces * Time-series prediction * Control * Diagnosis * Optimisation * Application of intelligent information technologies in: manufacturing, process control, quality testing, finance, economics, marketing, management, banking, agriculture, environment protection, medicine, geographic information systems, government, law, education, and sport * Intelligent information technologies on the global networks HONORARY CHAIR Shun-Ichi Amari, Tokyo University GENERAL CONFERENCE CHAIR Nik Kasabov, University of Otago nkasabov@otago.ac.nz COFERENCE CO-CHAIRS Yianni Attikiouzel, University of Western Australia Marwan Jabri, Sydney University PROGRAM CO-CHAIRS Tom Gedeon, University of New South Wales George Coghill, University of Auckland LOCAL ORGANIZING COMMITTEE CHAIR: Philip Sallis, University of Otago CONFERENCE ORGANISER Ms Kitty Ko Department of Information Science, University of Otago, PO Box 56, Dunedin, New Zealand phone: +64 3 479 8153, fax: +64 3 479 8311, email: kittyko@commerce.otago.ac.nz CALL FOR PAPERS Papers must be received by 30 May 1997. They will be reviewed by senior researchers in the field and the authors will be informed about the decision of the review process by 20 July 1997. The accepted papers must be submitted in a camera-ready format by 20 August. All accepted papers will be published by Springer-Verlag. As the conference is a multi-disciplinary meeting the papers are required to be comprehensible to a wider rather than to a very specialised audience. Papers will be presented at the conference either in an oral or in a poster session. Please submit three copies of the paper written in English on A4-format white paper with one inch margins on all four sides, in two column format, on not more than 4 pages, single-spaced, in Times or similar font of 10 points, and printed on one side of the page only. Centred at the top of the first page should be the complete title, author(s), mailing and e-mailing addresses, followed by an abstract and the text. In the covering letter the stream and the topic of the paper according to the list above should be indicated. SPECIAL ISSUES OF JOURNALS AND EDITED VOLUMES Selected papers will be published in special issues of scientific journals and in edited volumes which will include chapters covering the conference topics written by invited conference participants. TUTORIALS (24 November) Conference tutorials will be organized to introduce the basics of cognitive modelling, dynamical systems, neural networks, fuzzy systems, evolutionary programming, machine learning, soft computing, expert systems,hybrid systems, and adaptive systems. EXHIBITION Companies and university research laboratories are encouraged to exhibit their developed or distributing software and hardware systems. SPECIAL EVENTS FOR PRACTITIONERS The New Zealand Computer Society is organising special demonstrations, lectures and materials for practitioners working in the area of information technologies. VENUE (Dunedin/Queenstown) The Conference will be held at the University of Otago, Dunedin, New Zealand. The closing session will be held on Friday, 28 November on a cruise on one of the most beautiful lakes in the world, Lake Wakatipu. The cruise departs from the famous tourist centre Queenstown, about 300 km from Dunedin. Transportation will be provided and there will be a separate discount cost for the cruise. TRAVELLING The Dunedin branch of House of Travel, a travelling company, is happy to assist in any domestic and international travelling arrangements for the Conference delegates. They can be contacted through email: travel@es.co.nz, fax: +64 3 477 3806, phone: +64 3 477 3464, or toll free number: 0800 735 737 (within NZ). POSTCONFERENCE EVENTS Following the closing conference cruise, delegates may like to experience the delights of Queenstown, Central Otago, and Fiordland. Travel plans can be coordinated by the Dunedin Visitor Centre (phone: +64 3 474 3300, fax: +64 3 474 3311). IMPORTANT DATES Papers due: 30 May 1997 Notification of acceptance: 20 July 1997 Final camera-ready papers due: 20 August 1997 Registration of at least one author of a paper: 20 August 1997 Early registration: 20 August 1997 CONFERENCE CONTACTS, PAPER SUBMISSIONS, CONFERENCE INFORMATION, REGISTRATION FORMS Conference Secretariat Department of Information Science, University of Otago, PO Box 56, Dunedin, New Zealand; phone: +64 3 479 8142; fax: +64 3 479 8311; email: iconip97@otago.ac.nz Home page: http://divcom.otago.ac.nz:800/com/infosci/kel/conferen.htm RELATED CONFERENCE The World Manufacturing Congress'97 (WMC'97) will be held from November 18-21, 1997 at Massesy University, Albany Campus, Auckland, New Zealand.For further information please visit the Web Site: http://www.compusmart.ab.ca/icsc/wmc97.htm From langley@flamingo.Stanford.EDU Mon Jan 20 02:15:21 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id CAA03577 for ; Mon, 20 Jan 1997 02:12:58 -0600 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id CAA04059 for ; Mon, 20 Jan 1997 02:12:55 -0600 (CST) Received: from (parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id OAA09027; Mon, 20 Jan 1997 14:58:09 +0800 Message-Id: <199701200658.OAA09027@cs.uwa.oz.au> From: Pat Langley To: mpsych-l@brownvm.brown.edu, neuron-request@cattell.psych.upenn.edu, neuropl@plearn.edu.pl, neuropsych@mailbase.ac.uk, news-announce-conferences@uunet.uu.net, psicopatologia@vortex.ufrgs.br, psy-language@netcom.com.psyche-d@rfmh.org, psyc@pucc.princeton.edu, psycgrad@acadvm1.uottawa.ca, frieze@vms.cis.pitt.edu, quantitative-mri@mailbase.ac.uk, reinforce@cs.uwa.edu.au, sdaviss@umabnet.ab.umd.edu, sigart@vaxa.isi.edu, slling-l@yalevm.ycc.yale.edu, socio-moral@vortex.ufrgs.br, uai@maillist.cs.orst.edu, vision-list@teleos.com, lcq@spc.dcs.tsinghua.edu.cn, psychology.of.science@umich.edu, psyqnga@herts.ac.uk, brennavm@ctrvax.vanderbilt.edu Subject: submission deadlines for Cognitive Science Conference Date: Sat, 18 Jan 1997 20:53:26 -0800 The Nineteenth Annual Conference of the Cognitive Science Society, to be held at Stanford University from August 7 to 10, 1997, solicits papers on all topics related to the study of the mind. The various deadlines for this year's meeting are: - Submission of full (six-page) papers February 4, 1997 - Submission of (one-page) poster abstracts March 4, 1997 - Early registration (with lower fees) July 1, 1997 The deadline for submitting full papers is only two weeks away, so if you have not started working on your paper, now is the time. For details about submission length and format, please see the web site http://www-csli.stanford.edu/cogsci97 which also contains information about other aspects of the conference. We are hoping that each of the fields that make up Cognitive Science will be well represented at this year's meeting, so please consider submitting a paper or abstract even if you have not done so before. From kmathia@gotham.accurate-automation.com Mon Jan 20 02:59:46 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id CAA03823 for ; Mon, 20 Jan 1997 02:59:39 -0600 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id CAA04233 for ; Mon, 20 Jan 1997 02:59:36 -0600 (CST) Received: from (parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id OAA08914; Mon, 20 Jan 1997 14:56:26 +0800 Message-Id: <199701200656.OAA08914@cs.uwa.oz.au> From: Karl Mathia To: nl-kr@snyside.sunnyside.com Cc: nonlin-l@list.nih.gov, reinforce@cs.uwa.edu.au, scivw-request@hitl.washington.edu, www@sigart.acm.org Subject: CFP: Learning Control at SCI97 Date: Fri, 17 Jan 1997 14:03:52 -0500 (EST) ! PLEASE POST ! PLEASE POST ! PLEASE POST ! PLEASE POST ! *********************************************************************** First Call for Papers: WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS (SCI'97) Caracas, Venezuela July 7-11, 1997 Special Session on Learning Control ----------------------------------- *********************************************************************** OVERVIEW -------- SCI'97 is a truly multi-disciplinary conference, covering intelligent computing, information theory, cybernetics, social and biological systems, psychology, and applications. General information about the conference is listed below or can be found at the website http://www.iiis.org/ SCI'97 is an ideal platform for a special session on "Learning Control", an emerging discipline which is receiving more and more attention from both the academic and industrial controls community, due to the increasing complexity of (technical) systems. LEARNING CONTROL ---------------- "Learning Control" is a term attributed to a broad class of self-tuning processes, where the performance of the controlled system with respect to a particular task is self-improved based on the performance for previous identical tasks. The idea of self-learning control systems is aesthetically appealing and represents a fundamental step towards fully autonomous systems. This is of advantage when dealing with uncertain or changing systems. The major difference between adaptive and learning control is sometimes characterized in terms of 'local' and 'global' learning. An adaptive systems continuously adapts to changes in environment and system para- meters (local), whereas a learning systems memorizes and recognizes previously experienced situations (global). The classification of learning control will be one of many topics at this SCI'97 session. We invite you to present your recent research results, learn about current avenues in the field, and to meet interesting people. TOPICS ------ The Learning Control Session will include, but is not limited, to the following topics (further suggestions are encouraged): * Classification of learning control systems. * Mathematical learning theory in a controls context. * Biological or social self-learning control mechanisms and their extension to technical systems. * Human operator modeling. Human operators are (currently) the ultimate learning controller for complex systems. * Neurocontrol, using biological or artificial neural networks. * Fuzzy logic and learning. * Optimal Control type learning algorithms (adaptive critics, Q-learning, etc.). * Variable structure learning of controllers and its variants, e.g. reconfigurable and reparameterizable controllers. * Stability of learning control systems (important!). * Hardware implementations. * Applications and case studies which exceed the usual benchmark problems towards real-world complex systems. Questions about, or contributions to this special session can be e-mailed to Karl Mathia at karl@mathia.com or kmathia@accurate-automation.com PAPER SUBMISSION ---------------- Please mail three (3) hardcopies of your abstract or draft (1-2 pages) to: Dr. Karl Mathia Accurate Automation Corporation 7001 Shallowford Road Chattanooga, TN 37421 USA Full-size papers (max. 8 pages, single spaced) may be submitted by authors after the notification of acceptance. Please note the deadline of May 12, 1997. DEADLINES --------- March 15, 1997 Submission of 1-2 page abstracts or drafts. March 31, 1997 Acceptance notifications. May 12, 1997 Submission of camera ready papers (max. 8 pages, single spaced). *********************************************************************** Overview: WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS Caracas, Venezuela July 7-11, 1997 MAJOR THEMES .. Conceptual Infrastructure of Systemics, Cybernetics and Informatics .. Information Systems (ISAS '97) .. Control Systems .. Managerial/Corporative Systems .. Human Resources Systems .. Natural Resources Systems .. Social Systems .. Educational Systems .. Financial Systems .. SCI in Psychology, Cognition and Spirituality .. SCI in Biology and Medicine .. SCI in Art .. Globalization, Development and Emerging Economies ACADEMIC AND SCIENTIFIC SPONSORS .. World Organization of Systemics and Cybernetics (WOSC) (France) .. IFSR: International Federation for Systems Research (Austria/USA) .. International Systems Institute (USA) .. CUST, Engineer Science Institute of the Blaise Pascal University (France) .. The International Institute for Advanced Studies in Systems Research and Cybernetics (Canada) .. Society Applied Systems Research (Canada) .. Cybernetics and Human Knowing: A Journal of Second Order Cybernetics and Cybersemiotics (Denmark) .. International Institute of Informatics and Systemics (USA) .. IEEE (Venezuela Chapter) .. Simon Bolivar University (Venezuela) .. Universidad Central de Venezuela INCLUSION OF SCI'97 PROCEEDINGS IN A CD-ROM EXTENDED ENCYCLOPEDIA An electronic version of the SCI 97 proceedings will also be available on CD-ROM, with search and hypertext features. Other media, such as sound, animation and video, are also being considered. These proceedings will also be included in the CD-ROM Extended Encyclopedia of Systemics and Cybernetics (TM), whose development in presently in progress. TYPES OF SUBMISSIONS ACCEPTED .. Research, Review or Position Papers .. Panel Presentation, Workshop and/or Round Table Proposals .. New Topics Proposal (which should include a minimum of 15 papers) .. Focus Symposia (which should include a minimum of 15 papers) JOURNALS PUBLICATIONS FOR BEST PAPERS Best papers will be published by "Cybernetics and Human Knowing: A Journal of Second Order Cybernetics and Cybersemiotics". Members of the Program Committee who are refrees of the Journal will take the decision on the issue. Other Journals are being considered for other areas of SCI'97/ISAS'97. WEB SITE http://www.iiis.com PURPOSE The purpose of the Conference is to bring together, from universities and corporations, academics and professionals, researchers and consultants, scientists and engineers, theoreticians and practitioners, all over the world to discuss themes of the conference and to partici- pate with original ideas or innovations, knowledge or experience, theories or methodologies, in the areas of Systemics, Cybernetics and Informatics (SCI). Systemics, Cybernetics and Informatics (SCI) are being increasingly related to each other and to almost every scientific discipline and human activity. Their common transdisciplinarity characterizes and communicates them, generating strong relations among them and with other disciplines. They interpenetrate each other integrating a whole that is permeating human thinking and practice. This phenomenon induced the Organization Committee to structure SCI'97 as a multiconference where participants may focus on an area, or on a discipline, while maintaining open the possibility of attending conferences from other areas or disciplines. This systemic approach stimulates cross-ferti- lization among different disciplines, inspiring scholars, generating analogies and provoking innovations; which, after all, is one of the very basic principles of the systems movement and a fundamental aim in cybernetics. BACKGROUND The success achieved in ISAS'95 (Information Systems Analysis and Synthesis) held in Baden-Baden (Germany), symbolized by the award granted by the International Institute for Advanced Studios in Systems Research and Cybernetics (Canada), as the best and largest symposium at the 5th International Conference on Systems Research, Informatics and Cybernetics, encouraged its sponsors and session chairs to organize ISAS '96 at Orlando and prepare a more general Conference on Systemics, Cybernetics and Informatics (SCI '97) at Caracas (Venezuela). The widely acknowledged success of ISAS'96 (held on July 22-26 at Orlando) by means of spontaneous verbal feedback and a written comprehensive evaluation from 143 authors, of high quality papers, from 32 countries, galvanized the Program and Organizing Committees to make a definitive commitment to organize SCI'97 and ISAS '97 at Caracas, in July 7-11, 1997. Many Program and Organizing Committees members from past inter- national and world conferences are joining us for SCI '97 and ISAS'97, including most of those who organized the World Conference on Systems Sponsored by UNESCO and the United Nations' World Federation of Engineering Organizations (WFEO). We are still looking for more organizational support from experienced scholars, consultants, practitioners, professionals and researchers, as well as from inter- national or national organizations, public or private, academic or professional. ****************************************************************** From radford@cs.toronto.edu Mon Jan 20 22:51:01 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id WAA16732 for ; Mon, 20 Jan 1997 22:50:55 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id WAA16519 for ; Mon, 20 Jan 1997 22:50:54 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa10265; 20 Jan 97 22:29:56 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa10263; 20 Jan 97 22:04:14 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa00619; 20 Jan 97 22:04:10 EST Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa28779; 20 Jan 97 13:52:44 EST Received: from yonge.cs.toronto.edu by RI.CMU.EDU id aa05691; 20 Jan 97 13:52:16 EST Received: from neuron.ai.toronto.edu ([128.100.3.14]) by yonge.cs.toronto.edu with SMTP id <86475-29391>; Mon, 20 Jan 1997 13:52:13 -0500 Received: by neuron.ai.toronto.edu id <1028>; Mon, 20 Jan 1997 13:52:04 -0500 From: Radford Neal To: connectionists@cs.cmu.edu Subject: Software & Technical Report available Message-Id: <97Jan20.135204edt.1028@neuron.ai.toronto.edu> Date: Mon, 20 Jan 1997 13:52:03 -0500 Now available free for research and educational use: SOFTWARE FOR FLEXIBLE BAYESIAN MODELING This software implements a variety of Bayesian models for regression and classification based on neural networks and Gaussian processes. The software is written in C for Unix. The neural network programs are an update of those previously distributed, which are described in my book, Bayesian Learning for Neural Networks (Springer-Verlag 1996, ISBN 0-387-94724-8). The Gaussian process models and their implementation are described in the following technical report: MONTE CARLO IMPLEMENTATION OF GAUSSIAN PROCESS MODELS FOR BAYESIAN REGRESSION AND CLASSIFICATION Radford M. Neal Dept. of Statistics and Dept. of Computer Science University of Toronto Gaussian processes are a natural way of defining prior distributions over functions of one or more input variables. In a simple non- parametric regression problem, where such a function gives the mean of a Gaussian distribution for an observed response, a Gaussian process model can easily be implemented using matrix computations that are feasible for datasets of up to about a thousand cases. Hyperparameters that define the covariance function of the Gaussian process can be sampled using Markov chain methods. Regression models where the noise has a t distribution and logistic or probit models for classification applications can be implemented by sampling as well for latent values underlying the observations. Software is now available that implements these methods using covariance functions with hierarchical parameterizations. Models defined in this way can discover high-level properties of the data, such as which inputs are relevant to predicting the response. Both the software and the technical report can be obtained via my home page, at URL http://www.cs.utoronto.ca/~radford/ You can directly obtain the compressed Postscript for the technical report at URL ftp://ftp.cs.utoronto.ca/pub/radford/mc-gp.ps.Z Please let me know if you encounter any difficulties. ---------------------------------------------------------------------------- Radford M. Neal radford@cs.utoronto.ca Dept. of Statistics and Dept. of Computer Science radford@utstat.utoronto.ca University of Toronto http://www.cs.utoronto.ca/~radford ---------------------------------------------------------------------------- From pazzani@super-pan.ICS.UCI.EDU Tue Jan 21 17:42:01 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id RAA28681 for ; Tue, 21 Jan 1997 17:41:56 -0600 Received: from paris.ics.uci.edu (mmdf@paris.ics.uci.edu [128.195.1.50]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id RAA00795; Tue, 21 Jan 1997 17:41:38 -0600 (CST) Received: from super-pan.ics.uci.edu by paris.ics.uci.edu id aa18304; 21 Jan 97 8:42 PST To: ML-LIST:; Subject: Machine Learning List: Vol. 9, No. 1 Reply-to: ml@ics.uci.edu Date: Tue, 21 Jan 1997 08:09:09 -0800 From: Michael Pazzani Message-ID: <9701210842.aa18304@paris.ics.uci.edu> Machine Learning List: Vol. 9, No. 1 Monday, January 20, 1996 Contents: HAI 97 CFP submission deadlines for Cognitive Science Conference MLJ Table of Contents Knowledge Refinement Research Positions Available ML in design VACANCY: MACHINE LEARNING OF LANGUAGE ACL 97/EACL 97 Workshop ***CALL FOR PAPERS*** NNSP97: FINAL Call for papers ICONIP'97 call for papers Feature Transformation and Subset Selection Second CFP: ECML/MLNET Workshop on Empirical Learning of NLP Tasks The Machine Learning List is moderated. Contributions should be relevant to the scientific study of machine learning. Mail contributions to ml@ics.uci.edu. Mail requests to be added or deleted to ml-request@ics.uci.edu. Back issues may be obtained from http://www.ics.uci.edu/AI/ML/Machine-Learning.html ---------------------------------------------------------------------- Date: Thu, 2 Jan 1997 23:30:54 +0100 (MET) From: Michael Kaiser Subject: HAI 97 CFP ************************************************************************** CALL FOR PAPERS MLNET FAMILIARIZATION WORKSHOP AT THE ECML 97 IN PRAGUE, CZECH REPUBLIC MACHINE LEARNING AND HUMAN-AGENT INTERACTION (HAI 97) ************************************************************************** Up-to-date information on HAI 97 is available at http://wwwipr.ira.uka.de/events/hai97/ ECML-97 information can be obtained from http://is.vse.cz/ecml97/home.html ------------------------------ Date: Sat, 18 Jan 1997 20:48:06 -0800 From: Pat Langley Subject: submission deadlines for Cognitive Science Conference The Nineteenth Annual Conference of the Cognitive Science Society, to be held at Stanford University from August 7 to 10, 1997, solicits papers on all topics related to the study of the mind. The various deadlines for this year's meeting are: - Submission of full (six-page) papers February 4, 1997 - Submission of (one-page) poster abstracts March 4, 1997 - Early registration (with lower fees) July 1, 1997 The deadline for submitting full papers is only two weeks away, so if you have not started working on your paper, now is the time. For details about submission length and format, please see the web site http://www-csli.stanford.edu/cogsci97 which also contains information about other aspects of the conference. We are hoping that each of the fields that make up Cognitive Science will be well represented at this year's meeting, so please consider submitting a paper or abstract even if you have not done so before. ------------------------------ Date: Mon, 20 Jan 1997 11:26:35 -0800 From: "Jeffrey C. Schlimmer" Subject: MLJ Table of Contents Machine Learning Journal Table of Contents Vol. 26, No. 1 (January, 1997) Empirical Support for Winnow and Weighted-Majority Algorithms: Results on a Calendar Scheduling Domain, Avrim Blum, Page 5. Exact Learning of Formulas in Parallel, Nader H. Bshouty, Page 25. Learning and Updating of Uncertainty in Dirichlet Models, Enrique Castillo, Ali S. Hadi and Cristina Solares, Page 43. A 'Microscopic' Study of Minimum Entropy Search in Learning Decomposable Markov Networks, Y. Xiang, S.K.M. Wong and N. Cercone, Page 65. -- Dr. 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/ PGP key: ftp://ftp.eecs.wsu.edu/pub/pgp/schlimmer.hqx, .txt powerPen Faculty Advisor, powerPen@eecs.wsu.edu http://www.eecs.wsu.edu/~schlimme/newton/index.shtml ftp://ftp.eecs.wsu.edu/pub/newton/ ------------------------------ Date: Wed, 8 Jan 1997 14:37:50 GMT From: Susan Craw Subject: Knowledge Refinement Research Positions Available Research Fellow (Ref 686) and Research Student Posts We are looking for a Research Fellow (RA1A post) and a Research Student to work on an EPSRC funded project entitled "Developing a Toolkit for Automated Knowledge Refinement" The Research Fellowship will be a 3 year appointment starting early in 1997, date to be arranged. The Research Studentship starts on or before 1 October 1997. This project will provide refinement tools which assist with debugging a knowledge based system and will develop a general refinement framework and extensible toolkit with which knowledge engineers can construct particular refinement tools. Further details about the posts and an overview of the project are available at http://www.scms.rgu.ac.uk/research/kbs/krustworks Informal enquiries to: Dr Susan Craw School of Computer and Mathematical Sciences Tel +44(0)1224 262711 Fax +44(0)1224 262727 Email s.craw@scms.rgu.ac.uk Application Forms/Further Details Research Fellow: Research Student: (Please quote Ref No.) Miss Emma Forster Personnel Department Academic Affairs Department The Robert Gordon University The Robert Gordon University Schoolhill Schoolhill ABERDEEN AB10 1FR ABERDEEN AB10 1FR Tel +44(0)1224 262085 Tel +44(0)1224 262163 Fax +44(0)1224 262090 Fax +44(0)1224 262171 Email staffrec@rgu.ac.uk Email e.forster@rgu.ac.uk ------------------------------ Date: Fri, 27 Dec 1996 21:46:43 -0500 From: David Brown Subject: ML in design Request for Papers MACHINE LEARNING IN DESIGN Special Issue of the AI EDAM Journal After the successful conclusion of the Machine Learning in Design (MLinD) Workshop at this year's AI in Design conference, the workshop organisers -- Dave Brown, Ashok Goel and Alex Duffy -- decided to put together a special issue to be submitted to the Cambridge University Press Journal: "AI EDAM: Artificial Intelligence for Engineering Design, Analysis and Manufacturing". http://www2.hmc.edu/~dym/aiedam.html The purpose of the workshop was to explore the issues and requirements of learning in design with the intent to critically evaluate the required support from machine learning techniques. The objective was not only to identify key areas for future research but also to stimulate synergy in the Machine Learning in Design research community. (See http://cs.wpi.edu/~dcb/AID/AID96-MLinD.html ) The discussion centred around a number of "dimensions" of MLinD proposed by D. L. Grecu and D. C. Brown, namely: i). What can trigger learning? ii). What are the elements supporting learning? iii). What might be learned? iv). Availability of knowledge for learning? v). Methods of learning? vi). Local vs Global learning vii). Consequences of learning For further details see http://cs.wpi.edu/~dcb/AID/taxonomy.html >> You are invited to submit a paper discussing your work in relation >> to the above dimensions. Your response should address three main elements: a). A presentation of your MLinD work. b). An attempt to categorise it in terms of the dimensions. c). A critique of the proposed dimensions based on that attempt. Shorter papers would also be acceptable that just address part c). Every paper submitted will be reviewed by at least three reviewers. Submitting a paper indicates willingness to review. Every attempt will be made to uphold the high standards of the journal. The procedure will be overseen by the journal editor. The proposed schedule for this special issue is: Apr 1998 Issue 12(2) appears 17 October 1997 Revised papers to Guest editors 29 August 1997 Reviews to Authors 8 August 1997 Reviews due 27 June 1997 Papers due 7 March 1997 Declaration of interest from authors due Please send the paper, and all correspondence, via email to the guest editors by using the address: mlind@cad.strath.ac.uk Send the paper in both postscript form and also in plain text. The plain text will only be used if there are problems with the postscript, and, if so, you will be notified so that you can send any diagrams. Please respond via email to let us know whether you intend to submit a paper. Guest editors: Dr Alex H B Duffy University of Strathclyde, U.K. alex@cad.strath.ac.uk http://www.cad.strath.ac.uk/People/alex.html Prof Ashok Goel Georgia Institute of Technology, U.S.A. goel@cc.gatech.edu http://www.cc.gatech.edu/aimosaic/faculty/goel/ Prof David C Brown Worcester Polytechnic Institute, U.S.A. dcb@cs.wpi.edu http://www.wpi.edu/~dcb/ ------------------------------ Date: Thu, 16 Jan 1997 11:12:04 +0100 (MET) From: Walter.Daelemans@kub.nl Subject: VACANCY: MACHINE LEARNING OF LANGUAGE VACANCY: COMPUTATIONAL LINGUIST Tilburg University Arts faculty Computational Linguistics Vacancy for a PhD Researcher (from April 1 1997) on the project MACHINE LEARNING AS A METHOD IN LANGUAGE ANALYSIS A grant of the Netherlands Organisation for Scientific research (NWO) is available for this vacancy (about 27,500 Dutch guilders per year, for four years). When succeeding in concluding the research with a PhD within the alotted 4 years, a 2 year temporary postdoc position is subsequently offered. About the project: The availability of large language corpora combined with large computing power has opened up exciting new possibilities for computer-aided linguistic analysis. In the ILK (Induction of Language Knowledge) project of Tilburg University we investigate how inductive learning algorithms, developed in machine learning (a sub-discipline of artificial intelligence) and statistical pattern recognition can be of use in linguistic analysis, language technology, and cognitive modeling. We are looking for someone with a background in (Computational) Linguistics or Artificial Intelligence (Machine Learning) who is willing to research applications of Machine Learning in Linguistics and prepare a PhD on this topic. About the group: At full strength (mid 1997), the ILK research group will consist of the main researcher, an NWO postdoc, and four PhD researchers. Good computing facilities (mainly Unix workstations) are available. Several close research cooperations exist with other groups in The Netherlands and in Europe. For more information: About this vacancy: Walter Daelemans (walter@kub.nl, +31 13 4663070) About financial aspects: Marleen van de Wiel (M.M.vdWiel@kub.nl, +31 13 4663357) Application: Send your application with curriculum vitae, short description of research interests, and example of recent research (e.g. master's thesis) before February 15, 1997 to Walter Daelemans Tilburg University Computational Linguistics PO BOX 90153 5000 LE TILBURG The Netherlands ---------------------------------------------------------------------- Dr. Walter Daelemans: Associate Professor; Computational Linguistics, Tilburg University; P.O. BOX 90153; NL-5000 LE Tilburg; The Netherlands; Tel: +31 13 4663070; Fax: 4663110; E-mail: walter.daelemans@kub.nl; http://tkiwww.kub.nl:2080/tki/Faces/Wd/walter.html ---------------------------------------------------------------------- ------------------------------ Date: Fri, 10 Jan 1997 10:33:28 -0500 From: Jill C Burstein Subject: ACL 97/EACL 97 Workshop ***CALL FOR PAPERS*** -------------------------------------------------------- CALL FOR PAPERS ACL'97/EACL'97 Workshop July 11 or 12, 1997 Madrid, Spain -------------------------------------------------------- "From Research to Commercial Applications: Making NLP Technology Work in Practice" Success in the marketplace is one form of validation for NLP techniques and underlying theories. The broad vision of this workshop is to bring together researchers to discuss commercial or commercial-bound systems that use NLP for either text or speech. We are interested in learning about systems that show promise in re-using NLP techniques, and in the process of technology transfer for NLP applications. Another topic of interest in this workshop is industry-based practical considerations involving NLP technology. The workshop should invoke discussion about experiences and problems -- technical, logistic, or cultural -- among people working on operational and commercial NLP applications. The workshop will begin a dialogue among researchers to explore issues in technology transfer and the re-use of domain-specific systems. New applications could get leverage from using successful existing NLP technologies. The ability to re-use NLP technology for diverse applications should not only give the application a solid grounding, but should also save time and money. For example, text generation techniques are being used to build prototypes for essay analysis by Educational Testing Service. Other types of NLP technology re-use need to be identified for different applications. Closely related to the re-use of domain-specific technology is the issue of constructing general purpose tools that can be shared by the community, e.g., for tokenization, proper-noun detection, tagging, NP-identification, etc. Another purpose of the workshop is to explore industry-based practicalities that often guide the design of NLP technology. General practicalities that might be discussed are customization and trade-offs between accuracy and other requirements, such as speed, and ease of use. For example, determining the appropriate balance between reporting false positives and false negatives in information retrieval; what depth/breadth of coverage is "enough" in grammar checking; and how can adaptive systems, such as speaker-dependent speech recognizers, train themselves to the user without becoming obtrusive. Discussion of the issues above would help to create connections between both academic and industry-based research efforts to build a solid infrastructure for NLP technology re-use and lead to a deeper understanding of commercial NLP potential. WORKSHOP ORGANIZATION: Presentations will last for 20 minutes, followed by a 10 minute discussion period. Papers will be organized around themes. Ideally, we would like to include the following sessions: 1. Commercial/commercial-bound systems using NLP 2. Software re-use 3. Technology transfer SUBMISSIONS: Authors should submit a full length paper (not exceeding 3,200 words, exclusive of references) and must include a descriptive abstract of about 200 words. Electronic submissions are encouraged and should be submitted as described below. The title page should include title of the paper,names, addresses, e-mail address, telephone and fax number of all authors. Any correspondence will be addressed to the first author. FORMAT FOR SUBMISSION: Papers should be original work. Papers may be submitted either electronically or in hard copy. Electronic or hard-copy submissions must use the ACL submission style (aclsub.sty) retrievable from the ACL LISTSERV server via anonymous ftp: ftp ftp.cs.columbia.edu Name: anonymous Password: cd acl-l/ACL97 get aclsub.sty Electronic submissions should be mailed to jburstein@ets.org or ftp to: ftp clarity.princeton.edu Name: anonymous Password: cd incoming/workshop97 put Electronic submissions must either be a) plain ascii text, b) a single postscript file, or c) a single latex file following the ACL-97 submission style sheet (see ftp site above). * Please use the following naming conventions. The filename is the last name of the first author: smith.ps the .ps version of the paper smith.ascii the .ascii version of the paper (if postscript not available) smith.author the .ascii file of the title page (title, authors names, addresses, abstract) Hard copy submissions must be received by March 10. Send to: Jill Burstein ETS, MS 11-R Rosedale Road Princeton, NJ 08541 USA Tel: (609)734-5823 REQUIREMENTS: A paper accepted for presentation cannot be presented or have been presented at any other meeting. Please indicate in your submission if you have submitted your paper to another conference. SCHEDULE: Submissions Deadline: March 10, 1997 Notification Date: April 16, 1997 Camera ready copy due: April 28, 1997 PROGRAM CHAIRS: Jill Burstein, Educational Testing Service Claudia Leacock, Princeton University ORGANIZING AND PROGRAM COMMITTEE MEMBERS: Andrew Golding, Mitsubishi Electric Mary Dee Harris, Language Technology, Inc. Kevin Knight, USC/ISI Karen Kukich, Bellcore Lisa Rau, SRA International Yael Ravin, IBM, T.J. Watson Research Center Susanne Wolff, Educational Testing Service Wlodek Zadrozny, IBM, T.J. Watson Research Center ------------------------------ Date: Tue, 14 Jan 1997 22:22:17 -0800 (PST) From: KDD-97 Account ========================================================================= CALL FOR PAPERS ========================================================================= The Third International Conference on Knowledge Discovery and Data Mining (KDD-97) August 14-17, 1997 Newport Beach, California, U.S.A. ================================= Sponsored by the American Association for Artificial Intelligence in cooperation with the American Statistical Association Visit the KDD-97 WWW page at http://www-aig.jpl.nasa.gov/kdd97 The rapid growth of data and information has created a need and an opportunity for extracting knowledge from databases, and both researchers and application developers have been responding to that need. Knowledge discovery in databases (KDD), also referred to as data mining, is an area of common interest to researchers in machine discovery, statistics, databases, knowledge acquisition, machine learning, data visualization, high performance computing, and knowledge-based systems. KDD applications have been developed for astronomy, biology, finance, insurance, marketing, medicine, and many other fields. The Third International Conference on Knowledge Discovery and Data Mining (KDD-97) will follow up the success of KDD-95 and KDD-96 by bringing together researchers and application developers from different areas focusing on unifying themes. Suggested Topics The topics of interest include, but are not limited to: Theory and Foundational Issues in KDD * Probabilistic/statistical modeling and uncertainty management * Data and knowledge representation * Modeling of structured, unstructured and multimedia data * Fundamental advances in search, retrieval, and discovery methods Data Mining Methods and Algorithms * Probabilistic and statistical models and methods * Algorithmic complexity, efficiency and scalability issues in data mining * Using prior domain knowledge and re-use of discovered knowledge * Data mining techniques implemented on scalable platforms, including parallel, distributed and clustered systems * High dimensional datasets and data preprocessing * Unsupervised discovery and predictive modeling KDD Process and Human Interaction * Models of the KDD process * Data and knowledge visualization * Interactive data exploration and discovery * Privacy and security Applications * Data mining systems and data mining tools * Application of KDD in business, science, medicine and engineering * Application of KDD methods for mining knowledge in text, image, audio, sensor, numeric, categorical or mixed format data * Resource and knowledge discovery using the Internet This list of topics is not intended to be exhaustive but an indication of typical topics of interest. Prospective authors are encouraged to submit papers on any topics of relevance to knowledge discovery and data mining. Demonstration Sessions KDD-97 also invites working demonstrations of discovery systems. Contact information for details is provided below. Submission and Review Criteria Both research and applications papers are solicited. All submitted papers will be reviewed on the basis of technical quality, relevance to KDD, novelty, significance, and clarity. Authors are encouraged to make their work accessible to readers from other disciplines by including a carefully written introduction. Papers should clearly state their relevance to KDD. Please submit 7 hardcopies of a short paper (a maximum of 9 single-spaced pages not including cover page and bibliography, 1 inch margins, and 12pt font) to be received by March 10, 1997. A cover page must include author(s) full address, email, paper title and a 200 word abstract, and up to 5 keywords. This cover page must accompany the paper. In addition, an ascii version of the cover page must be submitted electronically by March 3 1997 (earlier if possible), preferrably using a WWW form located at http://www-aig.jpl.nasa.gov/kdd97/. If the WWW form cannot be used, please submit the ascii cover page by email to kdd97pgm@aig.jpl.nasa.gov, using the template available by ftp at http://www-aig.jpl.nasa.gov/kdd97/. Please mail the 7 hardcopies of the full papers to: AAAI (KDD-97) 445 Burgess Drive Menlo Park, CA 94025-3496 USA Phone: (+1 415) 328-3123 Fax: (+1 415) 321-4457 Email: kdd@aaai.org Web Site: http://www.aaai.org. *************** IMPORTANT DATES *************** * Submissions Due: March 10, 1997 * Acceptance Notice: April 28, 1997 * Camera-ready paper due: May 26, 1997 KDD-97 Organization General Conference Chair Ramasamy Uthurusamy (General Motors Corporation, USA) Program Co-Chairs David Heckerman (Microsoft Research, USA) Heikki Mannila (University of Helsinki, Finland) Daryl Pregibon (AT&T Labs, USA) Publicity Chair Paul Stolorz (Jet Propulsion Laboratory, USA) Tutorial Chair Padhraic Smyth (UC Irvine, USA) Demo and Poster Sessions Chair Tej Anand (NCR Corporation, USA) Awards Chair Gregory Piatetsky-Shapiro (GTE Laboratories, USA) Panel Chair Willi Kloesgen (GMD, Germany) Program Committee Tej Anand (NCR, USA) Ron Brachman (AT&T Laboratories, USA) Carla Brodley (Purdue University, USA) Dan Carr (George Mason University. USA) Peter Cheeseman (NASA AMES Research Center, USA) David Cheung (University of Hong Kong, Hong Kong) Wesley Chu (University of California at Los Angeles, USA) Gregory Cooper (University of Pittsburgh, USA) Robert Cowell (City University, UK) Bruce Croft (University of Massachusetts at Amherst, USA) Bill Eddy (Carnegie Mellon University, USA) Charles Elkan (Univeristy of California at San Diego, USA) Usama Fayyad (Microsoft Research, USA) Ronen Feldman (Bar-Ilan University, Israel) Jerry Friedman (Stanford University, USA) Dan Geiger (Technion, Israel) Clark Glymour (Carnegie-Mellon University, USA) Moises Goldszmidt (Stanford Research Institute, USA) George Grinstein (University of Lowell, USA) Jiawei Han (Simon Fraser University, Canada) David Hand (Open University, UK) David Heckerman (Microsoft Corporation, USA) Haym Hirsh (Rutgers University, USA) Jim Hodges (University of Minnesota, USA) Se June Hong (IBM T.J. Watson Research Center, USA) Tomasz Imielinski (Rutgers University, USA) Yannis Ioannidis (University of Wisconsin, USA) Larry Jackel (AT&T Laboratories, USA) David Jensen (Univsersity of Massachusetts, USA) Michael Jordan (Massachusetts Institute of Technology, USA) Dan Keim (University of Munich, Germany) Willi Kloesgen (GMD, Germany) Ronny Kohavi (Silicon Graphics, USA) David Madigan (University of Washington, USA) Heikki Mannila (University of Helsinki, Finland) Brij Masand (GTE Laboratories, USA) Gary McDonald (General Motors Research, USA) Eric Mjolsness (University of California at San Diego, USA) Sally Morton (Rand Corporation, USA) Richard Muntz (University of California at Los Angeles, USA) Raymond Ng (University of British Columbia, Canada) Steve Omohundro (NEC Research, USA) Gregory Piatetsky-Shapiro (GTE Laboratories, USA) Daryl Pregibon (Bell Laboratories, USA) Pat Riddle (Boeing Computer Services, USA) Jude Shavlik (University of Wisconsin at Madison, USA) Wei-Min Shen (University of Southern California, USA) Arno Siebes (CWI, Netherlands) Avi Silberschatz (Bell Laboratories, USA) Evangelos Simoudis (IBM Almaden Research Center, USA) Andrzej Skowron (University of Warsaw, Poland) Padhraic Smyth (University of California at Irvine, USA) Ramakrishnan Srikant (IBM Almaden Research Center, USA) John Stasko (Georgia Institute of Technology, USA) Sal Stolfo (Columbia University, USA) Paul Stolorz (Jet Propulsion Laboratory, USA) Alex Tuzhilin (NYU Stern School, USA) Ramasamy Uthurusamy (General Motors R&D Center, USA) Graham Wills (Bell Laboratories, USA) David Wolpert (IBM Almaden Research Center, USA) Wojciech Ziarko (University of Regina, Canada) Jan Zytkow (Wichita State University, USA) Contact Information For further information, send inquiries regarding * submission logistics to AAAI at kdd@aaai.org Phone: (+1 415) 328-3123 Fax: (+1 415) 321-4457 * KDD-97 sponsorship and industry participation to Ramasamy Uthurusamy samy@gmr.com Phone: 810-696-0669 Fax: 810-696-0580 * technical program and content to kdd97pgm@aig.jpl.nasa.gov * demo and poster sessions to tanand@winhitc.atlantaga.ncr.com * general and publicity issues to kdd97@aig.jpl.nasa.gov ------------------------------ Date: Wed, 15 Jan 97 11:02:13 EST From: Aalbert De Vries x2456 Subject: NNSP97: FINAL Call for papers 1997 IEEE Workshop on Neural Networks for Signal Processing 24-26 September 1997 Amelia Island Plantation, Florida ANNOUNCEMENT AND FINAL CALL FOR PAPERS Submission deadline: 27 January 1997 Thanks to the sponsorship of the IEEE Signal Processing Society and the co-sponsorship of the IEEE Neural Network Council, we are proud to announce the seventh of a series of IEEE Workshops on Neural Networks for Signal Processing. Papers are solicited for, but not limited to, the following topics: * Paradigms: artificial neural networks, Markov models, fuzzy logic, inference net, evolutionary computation, nonlinear signal processing, and wavelets * Application areas: speech processing, image processing, OCR, robotics, adaptive filtering, communications, sensors, system identification, issues related to RWC, and other general signal processing and pattern recognition * Theories: generalization, design algorithms, optimization, parameter estimation, and network architectures * Implementations: parallel and distributed implementation, hardware design, and other general implementation technologies ************************************************************************ * Special Sessions: * BLIND SIGNAL PROCESSING source separation, deconvolution, channel equalization, ... * APPLICATIONS OF NEURAL NETWORKS TO BIOMEDICAL SIGNAL PROCESSING Session Organizer: Tulay Adali Biomedical signal processing problems, with their particular features, challenges, and definition of objectives, have provided a unique platform for the application of artificial neural networks (ANNs) and the exploration of their relationship to other techniques. In this special session organized within NNSP'97, our aim is to bring researchers in the field together in a forum to present and discuss promising applications of ANNs in the biomedical domain and their relationship to more conventional ones in terms of performance, cost, and implementation. Contributions are sought dealing with both single (EEG, ECG, sensory data, etc.) and multi-dimensional (MR, PET, CT, functional MR, etc.) biomedical signals. Submissions for the special sessions should follow the general guidelines for papers submitted to NNSP'97 with an indication of the Special Session name (biomedical signal processing - BIO; blind signal processing - BSP). ************************************************************************ Instructions for submitting papers Prospective authors are invited to submit 5 copies of extended summaries of no more than 6 pages. The top of the first page of the summary should include a title, authors' names, affiliations, address, telephone and fax numbers and email address, if any. Camera-ready full papers of accepted proposals will be published in a hard-bound volume by IEEE and distributed at the workshop. Submissions should be sent to: Dr. Jose C. Principe IEEE NNSP'97 444 CSE Bldg #42 P.O. Box 116130 University of Florida Gainesville, FL 32611 Important Dates: **************************************************** * Submission of extended summary: January 27, 1997 * **************************************************** * Notification of acceptance: March 31, 1997 * Submission of photo-ready accepted paper: April 26, 1997 * Advanced registration: before July 1, 1997 Further Information Local Organizer Ms. Sharon Bosarge Telephone: 352-392-2585 Fax: 352-392-0044 e-mail: sharon@ee1.ee.ufl.edu World Wide Web http://www.cnel.ufl.edu/nnsp97/ Organization General Chairs Lee Giles (giles@research.nj.nec.com), NEC Research Nelson Morgan (morgan@icsi.berkeley.edu), UC Berkeley Proceeding Chair Elizabeth J. Wilson (bwilson@ed.ray.com), Raytheon Co. Publicity Chair Bert DeVries (bdevries@sarnoff.com), David Sarnoff Research Center Program Chair Jose Principe (principe@synapse.ee.ufl.edu), University of Florida BSP Session Chair Tulay Adali (adali@engr.umbc.edu), University of Maryland Baltimore County Program Committee Les ATLAS Charles BACHMANN Andrew BACK A. CONSTANTINIDES Federico GIROSI Lars Kai HANSEN Allen GORIN Yu-Hen HU Jenq-Neng HWANG Biing-Hwang JUANG Shigeru KATAGIRI Gary KUHN Sun-Yuan KUNG Richard LIPPMANN John MAKHOUL Elias MANOLAKOS Erkki OJA Tomaso POGGIO Tulay ADALI Volker TRESP John SORENSEN Takao WATANABE Raymond WATROUS Andreas WEIGEND Christian WELLEKENS About Amelia Island Plantation Amelia Island is in the extreme northeast Florida, across the St. Mary's river. The island is just 29 miles from Jacksonville International Airport, which is served by all major airlines. Amelia Island Plantation is a 1,250 acre resort/paradise that offers something for every traveler. The Plantation offers 33,000 square feet of workable meeting space and a staff dedicated to providing an efficient, yet relaxed atmosphere. The many amenities of the Plantation include 45 holes of championship golf, 23 Har-Tru tennis courts, modern fitness facilities, an award winning children's program, more than 7 miles of flora-filled bike and jogging trails, 21 swimming pools, diverse accommodations, exquisite dining opportunities, and of course, miles of glistening Atlantic beach front. ------------------------------ Date: Mon, 20 Jan 1997 09:31:43 -1200 From: Nikola Kasabov Subject: ICONIP'97 call for papers CALL FOR PAPERS, PRESENTATIONS, SPECIAL SESSIONS ICONIP'97 jointly with ANZIIS'97 and ANNES'97 (in cooperation with IEEE NNC and INNS) The Fourth International Conference on Neural Information Processing-- The Annual Conference of the Asian Pacific Neural Network Assembly, jointly with The Fifth Australian and New Zealand International Conference on Intelligent Information Processing Systems, and The Third New Zealand International Conference on Artificial Neural Networks and Expert Systems, 24-28 November, 1997 Dunedin/Queenstown, New Zealand The joint conference will have three parallel streams: Stream1: Neural Information Processing Stream2: Computational Intelligence and Soft Computing Stream3: Intelligent Information Systems and their Applications TOPICS OF INTEREST Stream1: Neural Information Processing * Neurobiological systems * Cognition * Cognitive models of the brain * Dynamical modelling, chaotic processes in the brain * Brain computers, biological computers * Consciousness, awareness, attention * Adaptive biological systems * Modelling emotions * Perception, vision * Learning languages * Evolution Stream2: Computational Intelligence and Soft Computing * Artificial neural networks: models, architectures, algorithms * Fuzzy systems * Evolutionary programming and genetic algorithms * Artificial life * Distributed AI systems, agent-based systems * Soft computing--paradigms, methods, tools * Approximate reasoning * Probabilistic and statistical methods * Software tools, hardware implementation Stream3: Intelligent Information Systems and their Applications * Connectionist-based information systems * Hybrid systems * Expert systems * Adaptive systems * Machine learning, data mining and intelligent databases * Pattern recognition and image processing * Speech recognition and language processing * Intelligent information retrieval systems * Human-computer interfaces * Time-series prediction * Control * Diagnosis * Optimisation * Application of intelligent information technologies in: manufacturing, process control, quality testing, finance, economics, marketing, management, banking, agriculture, environment protection, medicine, geographic information systems, government, law, education, and sport * Intelligent information technologies on the global networks HONORARY CHAIR Shun-Ichi Amari, Tokyo University GENERAL CONFERENCE CHAIR Nik Kasabov, University of Otago nkasabov@otago.ac.nz COFERENCE CO-CHAIRS Yianni Attikiouzel, University of Western Australia Marwan Jabri, Sydney University PROGRAM CO-CHAIRS Tom Gedeon, University of New South Wales George Coghill, University of Auckland LOCAL ORGANIZING COMMITTEE CHAIR: Philip Sallis, University of Otago CONFERENCE ORGANISER Ms Kitty Ko Department of Information Science, University of Otago, PO Box 56, Dunedin, New Zealand phone: +64 3 479 8153, fax: +64 3 479 8311, email: kittyko@commerce.otago.ac.nz CALL FOR PAPERS Papers must be received by 30 May 1997. They will be reviewed by senior researchers in the field and the authors will be informed about the decision of the review process by 20 July 1997. The accepted papers must be submitted in a camera-ready format by 20 August. All accepted papers will be published by Springer-Verlag. As the conference is a multi-disciplinary meeting the papers are required to be comprehensible to a wider rather than to a very specialised audience. Papers will be presented at the conference either in an oral or in a poster session. Please submit three copies of the paper written in English on A4-format white paper with one inch margins on all four sides, in two column format, on not more than 4 pages, single-spaced, in Times or similar font of 10 points, and printed on one side of the page only. Centred at the top of the first page should be the complete title, author(s), mailing and e-mailing addresses, followed by an abstract and the text. In the covering letter the stream and the topic of the paper according to the list above should be indicated. SPECIAL ISSUES OF JOURNALS AND EDITED VOLUMES Selected papers will be published in special issues of scientific journals and in edited volumes which will include chapters covering the conference topics written by invited conference participants. TUTORIALS (24 November) Conference tutorials will be organized to introduce the basics of cognitive modelling, dynamical systems, neural networks, fuzzy systems, evolutionary programming, machine learning, soft computing, expert systems,hybrid systems, and adaptive systems. EXHIBITION Companies and university research laboratories are encouraged to exhibit their developed or distributing software and hardware systems. SPECIAL EVENTS FOR PRACTITIONERS The New Zealand Computer Society is organising special demonstrations, lectures and materials for practitioners working in the area of information technologies. VENUE (Dunedin/Queenstown) The Conference will be held at the University of Otago, Dunedin, New Zealand. The closing session will be held on Friday, 28 November on a cruise on one of the most beautiful lakes in the world, Lake Wakatipu. The cruise departs from the famous tourist centre Queenstown, about 300 km from Dunedin. Transportation will be provided and there will be a separate discount cost for the cruise. TRAVELLING The Dunedin branch of House of Travel, a travelling company, is happy to assist in any domestic and international travelling arrangements for the Conference delegates. They can be contacted through email: travel@es.co.nz, fax: +64 3 477 3806, phone: +64 3 477 3464, or toll free number: 0800 735 737 (within NZ). POSTCONFERENCE EVENTS Following the closing conference cruise, delegates may like to experience the delights of Queenstown, Central Otago, and Fiordland. Travel plans can be coordinated by the Dunedin Visitor Centre (phone: +64 3 474 3300, fax: +64 3 474 3311). IMPORTANT DATES Papers due: 30 May 1997 Notification of acceptance: 20 July 1997 Final camera-ready papers due: 20 August 1997 Registration of at least one author of a paper: 20 August 1997 Early registration: 20 August 1997 CONFERENCE CONTACTS, PAPER SUBMISSIONS, CONFERENCE INFORMATION, REGISTRATION FORMS Conference Secretariat Department of Information Science, University of Otago, PO Box 56, Dunedin, New Zealand; phone: +64 3 479 8142; fax: +64 3 479 8311; email: iconip97@otago.ac.nz Home page: http://divcom.otago.ac.nz:800/com/infosci/kel/conferen.htm RELATED CONFERENCE The World Manufacturing Congress'97 (WMC'97) will be held from November 18-21, 1997 at Massesy University, Albany Campus, Auckland, New Zealand.For further information please visit the Web Site: http://www.compusmart.ab.ca/icsc/wmc97.htm ------------------------------ Date: Thu, 09 Jan 97 16:07:57 +0900 From: motoda@sanken.osaka-u.ac.jp Subject: Feature Transformation and Subset Selection Call For Papers IEEE Expert Special Issue on Feature Transformation and Subset Selection Guest Editors: Huan Liu and Hiroshi Motoda I. BACKGROUND As computer and database technologies have advanced, human beings rely more and more on computers to accumulate data, process data, and make use of data. Machine learning, knowledge discovery, and data mining are some of the Artificial Intelligence (AI) tools that help human accomplish those tasks. Researchers and practitioners realize that in order to use these tools effectively, an important part is pre-processing in which data is processed before it is presented to any learning, discovering, or visualizing algorithm. In many discovery applications (for example, marketing data analysis), a key operation is to find subsets of the population that behave enough alike to be worthy of focused analysis. Feature transformation and subset selection are applied frequently in data pre-processing. Feature transformation (FT) is a process through which a new set of features is created. The variants of FT are feature construction, feature discovery, and feature extraction. Assuming the original set consists of A1, A2,..., An features, these variants can be defined below. Feature construction is a process that augments the space of features by inferring or creating additional features. After feature construction, we may have additional m features An+1,An+2,...,An+m. For example, a new feature Ak (n < k <= n+m) could be constructed by performing a logical operation of Ai and Aj from the original set. Feature discovery is a process that discovers missing information about the relationships between features and forms a new set of features. An example of feature discovery is as follows: a two-dimensional problem (say, A1=width and A2=length) may be transformed to a one-dimensional problem (B1=area) after feature discovery. Feature extraction is a process that extracts a set of new features from the original features through some functional mapping. After feature extraction, we have B1, B2,..., Bm (m < n), Bi = Fi(A1,A2,...,An), and Fi is a mapping function. For instance, B1=c1A1+c2A2 where c1 and c2 are constants. Subset selection (SS) is different from FT in that no new features will be generated, but only a subset of original features is selected and the feature space is reduced. As to FT, feature construction expands the feature space, whereas feature discovery and feature extraction reduce the feature space. There is a wide and strong interest in FT and SS among practitioners from Statistics, Pattern Recognition, Data Mining, and Knowledge Discovery to Machine Learning since data preprocessing is an essential step in the knowledge discovery process for real-world applications. II. OBJECTIVE and SCOPE The objective of this special issue is to report on the recent studies in FS and SS. The main goal is to increase the awareness of the AI community to the research of FT and SS, currently conducted in isolation. Through this special issue, we hope to produce a contemporary overview of modern solutions, to create synergy among these seemingly different branches but with a similar goal - facilitating data processing and knowledge discovery, and to point to future research directions. Papers are expected to cover the following aspects of FT and SS; in all cases, authors are strongly encouraged to use real-world examples to show that their work is scalable and applicable to practical problems: . Theories and Methodologies of novel approaches to feature transformation and subset selection . Applications of feature transformation and subset selection to real-world problems: practice, experiments, and lessons learned . Combinations of different methods such as machine learning, statistics as well as neural networks in feature transformation . Future directions and important issues in unifying this currently diversified field III. SUBMISSION REQUIREMENTS and SCHEDULE High quality, original papers that deal with real-world problems are solicitated. All the submitted manuscripts will be subject to a rigorous review process. Manuscripts should be prepared in accordance with the IEEE Expert "submission guidelines". Manuscripts should be approximately 5,000 words long, preferably not exceeding 10 references. This special issue is scheduled to appear in late 1997. Important Dates: Submission April 30 (FIRM DEADLINE) Notification June 30 Prospective authors should submit six copies of the completed manuscript to one of the guest editors: Huan Liu Hiroshi Motoda S16 #4-17 Institute of Scientific & Industrial Dept of Info Sys & Comp Sci Research National University of Singapore Osaka University Kent Ridge, Singapore, 119260 Ibaraki, Osaka 567, Japan liuh@iscs.nus.sg motoda@sanken.osaka-u.ac.jp ------------------------------ Date: Thu, 9 Jan 1997 12:11:35 +0100 (MET) From: Antal van den Bosch Subject: Second CFP: ECML/MLNET Workshop on Empirical Learning of NLP Tasks ECML'97 MLNET Familiarization Workshop April 26, 1997, Prague, Czech Republic Empirical Learning of Natural Language Processing Tasks WORKSHOP in cooperation with ACL SIGNLL General information The `Empirical Learning of Natural Language Processing Tasks' MLNET Familiarization Workshop is held in conjunction with the 1997 European Conference on Machine Learning, in Prague, April 23-26, 1997. The programme will consist of invited keynote lectures, submitted presentations, and moderated discussions. The time allocated to each of these three components is roughly equal, to ensure ample time for discussions and informal contact. The workshop is organised in cooperation with ACL SIGNLL. Confirmed keynote events The following keynote events have been confirmed: * Keynote speaker: Luc Steels (VUB, Brussels, Belgium): "Self-organisation in the origin and acquisition of language" * Key-panel: David Page (Oxford, UK), Luc De Raedt (Leuven, Belgium), Luc Dehaspe (Leuven, Belgium): "Inductive Logic Programming for tagging and parsing" Information on keynote events and the workshop programme is continuously updated on the workshop web page at http://www.cs.unimaas.nl/ecml97/. Focus and motivation It is becoming apparent that empirical learning of Natural Language Processing (NLP) can alleviate NLP's all-time main problem, viz. the knowledge acquisition bottleneck: for each new language, domain, theoretical framework, and application, linguistic knowledge bases (lexicons, rule sets, grammars) have to be built basically from scratch. Empirical, symbolic machine learning methods such as rule induction, top down induction of decision trees, lazy learning, and inductive logic programming, seem to be excellently suited to automatically learn (induce) exactly that knowledge that is hard to gather by hand. We see at least three reasons why Machine Learning researchers should become more interested in NLP as an application area. * Availability of Large Datasets. NLP problems provide realistically sized training sets for inductive algorithms. Datasets of tens or hundreds of thousands of instances are readily available. Traditional "benchmark datasets" usually contain far less instances. * Real-World Application. "Hand-crafting" NLP knowledge bases has proven to be infeasible or unaffordable for most practical applications. ML techniques may help in realising the enormous market potential for NLP applications. * Type of Complexity. Data sets describing language problems at all levels of description exhibit a complex interaction of regularities, sub-regularities, pockets of exceptions, idiosyncratic exceptions, and noise. As such, they are a perfect model for a large class of other poorly-understood real world problems (e.g. medical diagnosis) for which it is less easy to find large amounts of data. Topics The workshop addresses the following topics: * Suitability of different empirical Machine Learning paradigms (ILP, Lazy Learning, TDIDT, supervised-learning neural networks, etc.) to solving classes of NLP tasks (phonology, morphology, syntax, semantics, discourse; analysis, generation, translation; speech technology). * Case studies of NLP tasks solved with ML techniques. * Application feedback: how did properties of the NLP target application influence the design of the algorithm (e.g. in case of sparse data, or very large datasets). * Comparisons of empirical symbolic ML methods to connectionist, stochastic, and `hand-crafting' approaches on NLP tasks. Submission requirements Contributions should take the form of a paper of max. 10 pages, including title, author(s), addresses (including e-mail if possible), and affiliation across the top of the first page. The paper should be received by the contact person of the organising committee, preferrably by e-mail, before 15 February 1997. Accepted papers will be collected and published in a Workshop Proceedings. They will also be made publicly available via FTP. Format specifications Papers may be submitted either as ASCII files or as LaTeX files. In the latter case, we kindly ask you to use as standard LaTeX as possible, using only standard macros and including preferably only .EPS (encapsulated postscript) figures. Please follow these global guidelines in preparing your submission: * the paper should be in single-column format; * line spacing should be single (1.0); * the font should be 12 point, preferrably Times Roman. Submission address Please send your paper according to the format specifications mentioned above via e-mail to Antal van den Bosch, antal@cs.unimaas.nl If a submission via email is not possible, please send a laserprinted hardcopy of your paper to Antal van den Bosch Department of Computer Science Faculty of General Sciences Universiteit Maastricht PO Box 616 NL-6200 MD Maastricht The Netherlands phone: +31.43.3882019 fax: +31.43.3252392 Important dates * Contribution submissions 15 February 1997 * Notification of acceptance 8 March 1997 * Deadline camera-ready copy 1 April 1997 * Workshop 26 April 1997 Organizing committee Walter Daelemans (Walter.Daelemans@kub.nl, Tilburg University) Ton Weijters (weijters@cs.unimaas.nl, Universiteit Maastricht) Antal van den Bosch (antal@cs.unimaas.nl, Universiteit Maastricht) Registration The workshops will be open to anyone. Participants who are not members of MLnet pay a fee to cover the marginal costs of the workshop. The fee is yet to be determined. MLnet will pay the organisational costs for its members. MLnet will arrange travel bursaries for its members to take part in the workshops. World-Wide Web Information on the workshop is also available on the world-wide-web at http://www.cs.unimaas.nl/ecml97/ ------------------------------ End of ML-LIST (Digest format) **************************************** From georg@ai.univie.ac.at Tue Jan 21 19:12:35 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id TAA29630 for ; Tue, 21 Jan 1997 19:12:29 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id TAA02090 for ; Tue, 21 Jan 1997 19:12:28 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa11387; 21 Jan 97 18:01:35 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa11378; 21 Jan 97 17:32:31 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa01647; 21 Jan 97 17:31:56 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa19673; 21 Jan 97 11:36:57 EST Received: from [192.76.244.84] by CS.CMU.EDU id aa18064; 21 Jan 97 11:31:07 EST Received: (from georg@localhost) by jedlesee.ai.univie.ac.at (8.7.5/8.7.3) id RAA21869; Tue, 21 Jan 1997 17:30:14 +0100 (MET) From: Georg Dorffner Message-Id: <199701211630.RAA21869@jedlesee.ai.univie.ac.at> Subject: CFP: NN in biomedical systems To: connectionists@cs.cmu.edu, nn-at@ci.tuwien.ac.at Date: Tue, 21 Jan 1997 17:30:13 +0100 (MET) X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Call for Abstracts for a ======================================= Special track on biomedical systems ======================================= at the International Conference on Engineering Applications of Neural Networks (EANN '97) Stockholm, Sweden 16-18 June 1997 ----------------------------------------------------------------------------- The deadline for submission of abstracts to the special track on biomedical systems at EANN '97 has been extended to =================================== January 31, 1997 (email submission) =================================== Please send your submissions to georg@ai.univie.ac.at (Georg Dorffner) --------------- Instructions: Abstracts of one page (about 400 words) should be sent to georg@ai.univie.ac.at by 31 January 1997 by e-mail in plain ASCII format. Please mention two to four keywords, and whether you prefer it to be a short paper or a full paper and whether you will prefer oral or poster presentation. The short papers will be 4 pages in length, and full papers may be upto 8 pages. Notification of acceptance will be sent around 7 February. Submissions will be reviewed and the number of full papers will be very limited. For information on earlier EANN conferences see the www pages at http://www.abo.fi/~abulsari/EANN95.html and http://www.abo.fi/~abulsari/EANN96.html --------------- About the conference: The conference is a forum for presenting the latest results on neural network applications in technical fields. The applications may be in any engineering or technical field, including but not limited to systems engineering, mechanical engineering, robotics, process engineering, metallurgy, pulp and paper technology, aeronautical engineering, computer science, machine vision, chemistry, chemical engineering, physics, electrical engineering, electronics, civil engineering, geophysical sciences, biotechnology, biomedical systems, and environmental engineering. Other special tracks are: Computer Vision (J. Heikkonen, Jukka.Heikkonen@jrc.it), Control Systems (E. Tulunay, Ersin-Tulunay@metu.edu.tr), Hybrid Systems (D. Tsaptsinos, D.Tsaptsinos@kingston.ac.uk), Mechanical Engineering (A. Scherer, Andreas_Scherer@hp.com), Process Engineering (R. Baratti, baratti@ndchem3.unica.it) Advisory board J. Hopfield (USA) A. Lansner (Sweden) G. Sjodin (Sweden) Organising committee A. Bulsari (Finland) H. Liljenstrom (Sweden) D. Tsaptsinos (UK) International program committee G. Baier (Germany) R. Baratti (Italy) S. Cho (Korea) T. Clarkson (UK) J. DeMott (USA) G. Dorffner (Austria) W. Duch (Poland) G. Forsgren (Sweden) A. Gorni (Brazil) J. Heikkonen (Italy) F. Norlund (Sweden) A. Ruano (Portugal) A. Scherer (Germany) C. Schizas (Cyprus) J. Thibault (Canada) E. Tulunay (Turkey) Electronic mail is not absolutely reliable, so if you have not heard from the conference secretariat after sending your abstract, please contact us again. You should receive an abstract number in a couple of days after the submission. International Conference on Engineering Applications of Neural Networks (EANN '97) Stockholm, Sweden 16-18 June 1997 Registration information Registration form can be picked up from the www (or can be sent to you by e-mail) and can be returned after the conference fee has been sent. A registration form sent before the payment of the conference fee is not valid and therefore will not be stored. For more information, please ask eann97@kth.se. The conference fee will be SEK 4148 (SEK 3400 excluding VAT) until 28 February, and SEK 4978 (SEK 4080 excluding VAT) after that. The conference fee includes attendance to the conference and the proceedings. If your organisation (university or company or institute) has a VAT registration from a European Union country other than Finland, then your VAT number should be mentioned on the bank transfer as well as the registration form, and VAT need not be added to the conference fee. At least one author of each accepted paper should register by 15 March to ensure that the paper will be included in the proceedings. The correct conference fee amount should be received in the account number 207 799 342, Svenska Handelsbanken International, Stockholm branch. It can be paid by bank transfer (with all expenses paid by the sender) to "EANN Conference". To avoid extra bureaucracy and correction of the amount at the registration desk, make sure that you have taken care of the bank transfer fees. It is essential to mention the name of the participant with the bank transfer. If you need to pay it in another way (bank drafts, Eurocheques, postal order; no credit cards), please contact us at eann97@kth.se. Invoicing will cost SEK 100. From atick@monaco.rockefeller.edu Tue Jan 21 19:12:38 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id TAA29628 for ; Tue, 21 Jan 1997 19:12:28 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id TAA02079 for ; Tue, 21 Jan 1997 19:12:19 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa11376; 21 Jan 97 17:49:47 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa11374; 21 Jan 97 17:30:45 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa01639; 21 Jan 97 17:30:29 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id ab23693; 21 Jan 97 14:50:09 EST Received: from monaco.rockefeller.edu by EDRC.CMU.EDU id aa02210; 21 Jan 97 14:49:43 EST Received: by monaco (940816.SGI.8.6.9/940406.SGI) id OAA26137; Tue, 21 Jan 1997 14:50:32 -0500 From: Joseph Atick Message-Id: <9701211450.ZM26135@monaco.rockefeller.edu> Date: Tue, 21 Jan 1997 14:50:31 -0500 X-Mailer: Z-Mail (3.2.2 10apr95 MediaMail) To: connectionists@cs.cmu.edu Subject: Job Openings in Computer Vision Research Cc: atick@MONACO.CMCL.CS.CMU.EDU Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii FYI %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% JOB OPENINGS IN Pattern Recognition Research Join a growing team of scientists and software engineers developing real world applications of visual pattern recognition technology (e.g. face recognition systems). The openings are at various levels and will be at Visionics' research facility in New Jersey (about 20 minutes outside New York City). The candidate is expected to have experience in pattern recognition research, numerical analysis, C/C++ programming. Strong computer programming abilities are a must. A research track record in computer vision, artificial neural network, image processing, or scene understanding is a definite plus. If you are interested in an exciting job opportunity and would like a chance for rapid career development and significant financial rewards, please fax your resume to (908) 549 5323, Re: Job Posting, for consideration. Alternatively, you can email it to jobs@faceit.com. Additional information can be found at http://www.faceit.com. Visionics is an equal opportunity employer. Minority and women candidates are encouraged to apply. %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% -- Joseph J. Atick Rockefeller University 1230 York Avenue New York, NY 10021 Tel: 212 327 7421 Fax: 212 327 7422 From giles@research.nj.nec.com Wed Jan 22 16:19:04 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id QAA19538 for ; Wed, 22 Jan 1997 16:18:58 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id QAA18856 for ; Wed, 22 Jan 1997 16:18:56 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa12750; 22 Jan 97 14:23:12 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa12748; 22 Jan 97 13:55:11 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa02857; 22 Jan 97 13:54:52 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id ae15902; 22 Jan 97 12:50:27 EST Received: from zingo.nj.nec.com by EDRC.CMU.EDU id aa08696; 22 Jan 97 10:51:50 EST Received: from alta (alta [138.15.159.81]) by zingo.nj.nec.com (8.7.4/8.7.3) with SMTP id KAA01542 for ; Wed, 22 Jan 1997 10:51:32 -0500 (EST) Received: by alta (5.52/cliff's joyful mailer #2) id AA06169(alta); Wed, 22 Jan 97 10:49:30 EST Date: Wed, 22 Jan 97 10:49:30 EST From: Lee Giles Message-Id: <9701221549.AA06169@alta> To: connectionists@cs.cmu.edu Subject: TR on Alternative Discrete-time Operators in Neural Networks Cc: giles@research.nj.nec.com The following TR is now available from the University of Maryland, NEC Research Institute and the Laboratory of Artificial Brain Systems archives. ************************************************************************************ Alternative Discrete-Time Operators and Their Application to Nonlinear Models Andrew D. Back [1], Ah Chung Tsoi [2], Bill G. Horne [3], C. Lee Giles [4,5] [1] Laboratory for Artificial Brain Systems, Frontier Research Program RIKEN, The Institute of Physical and Chemical Research, 2-1 Hirosawa, Wako--shi, Saitama 351-01, Japan [2] Faculty of Informatics, University of Wollongong, Northfields Avenue, Wollongong, Australia [3] AADM Consulting, 9 Pace Farm Rd., Califon, NJ 07830 [4} NEC Research Institute, 4 Independence Way, Princeton, NJ 08540 [5] Inst. for Advanced Computer Studies, U. of Maryland, College Park, MD. 20742 U. of Maryland Technical Report CS-TR-3738 and UMIACS-TR-97-03 ABSTRACT The shift operator, defined as q x(t) = x(t+1), is the basis for almost all discrete-time models. It has been shown however, that linear models based on the shift operator suffer problems when used to model lightly-damped-low-frequency (LDLF) systems, with poles near $(1,0)$ on the unit circle in the complex plane. This problem occurs under fast sampling conditions. As the sampling rate increases, coefficient sensitivity and round-off noise become a problem as the difference between successive sampled inputs becomes smaller and smaller. The resulting coefficients of the model approach the coefficients obtained in a binomial expansion, regardless of the underlying continuous-time system. This implies that for a given finite wordlength, severe inaccuracies may result. Wordlengths for the coefficients may also need to be made longer to accommodate models which have low frequency characteristics, corresponding to poles in the neighbourhood of (1,0). These problems also arise in neural network models which comprise of linear parts and nonlinear neural activation functions. Various alternative discrete-time operators can be introduced which offer numerical computational advantages over the conventional shift operator. The alternative discrete-time operators have been proposed independently of each other in the fields of digital filtering, adaptive control and neural networks. These include the delta, rho, gamma and bilinear operators. In this paper we first review these operators and examine some of their properties. An analysis of the TDNN and FIR MLP network structures is given which shows their susceptibility to parameter sensitivity problems. Subsequently, it is shown that models may be formulated using alternative discrete-time operators which have low sensitivity properties. Consideration is given to the problem of finding parameters for stable alternative discrete-time operators. A learning algorithm which adapts the alternative discrete-time operators parameters on-line is presented for MLP neural network models based on alternative discrete-time operators. It is shown that neural network models which use these alternative discrete-time perform better than those using the shift operator alone. Keywords: Shift operator, alternative discrete-time operator, gamma operator, rho operator, low sensitivity, time delay neural network, high speed sampling, finite wordlength, LDLF, MLP, TDNN. ___________________________________________________________________________________ http://www.neci.nj.nec.com/homepages/giles.html http://www.cs.umd.edu/TRs/TR-no-abs.html http://zoo.riken.go.jp/abs1/back/Welcome.html -- C. Lee Giles / Computer Sciences / NEC Research Institute / 4 Independence Way / Princeton, NJ 08540, USA / 609-951-2642 / Fax 2482 www.neci.nj.nec.com/homepages/giles.html == From Yassine.Faihe@info.unine.ch Wed Jan 22 23:55:09 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id XAA23326 for ; Wed, 22 Jan 1997 23:55:01 -0600 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id XAA24862 for ; Wed, 22 Jan 1997 23:54:58 -0600 (CST) Received: from (parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id MAA27370; Thu, 23 Jan 1997 12:33:35 +0800 Message-Id: <199701230433.MAA27370@cs.uwa.oz.au> From: INFAIHE To: Reinforcement List (Non Receipt Notification Requested) Subject: Value function approximation Date: Wed, 22 Jan 1997 12:11:58 +0100 Dear, I am looking for detailed specifications as well as source code for a value function approximator using neural networks. Thanks. Yassine Faihe IIIA Emile Argand 11 CH-2007 Neuchatel Switzerland Phone : +41 32 718 27 27 Fax : +41 32 718 27 01 email : faihe@info.unine.ch From michael@salk.edu Thu Jan 23 00:17:28 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id AAA23353 for ; Thu, 23 Jan 1997 00:17:17 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id AAA25156 for ; Thu, 23 Jan 1997 00:17:16 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa13353; 22 Jan 97 23:08:19 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa13349; 22 Jan 97 22:56:58 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa03157; 22 Jan 97 22:56:15 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa25356; 22 Jan 97 21:20:44 EST Received: from tesla-e0.salk.edu by CS.CMU.EDU id aa15040; 22 Jan 97 21:19:19 EST Received: from gabor.salk.edu (michael@gabor.salk.edu [198.202.70.41]) by tesla-e0.salk.edu (8.7.5/8.7.3) with ESMTP id SAA05450 for ; Wed, 22 Jan 1997 18:19:01 -0800 (PST) From: michael@salk.edu Received: (from michael@localhost) by gabor.salk.edu (8.7.5/8.7.3) id SAA03230 for connectionists@cs.cmu.edu; Wed, 22 Jan 1997 18:19:03 -0800 Message-Id: <199701230219.SAA03230@gabor.salk.edu> Subject: NIPS*96 preprints To: connectionists@cs.cmu.edu Date: Wed, 22 Jan 1997 18:19:02 -0800 (PST) X-Mailer: ELM [version 2.4 PL24] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Connectionists - This is an announcement of several NIPS*96 preprints from the Computational Neurobiology Lab at the Salk Institute in San Diego. These will appear in "Advances in Neural Information Processing Systems 9" (available May 1997), edited by Mozer, M.C., Jordan, M.I., and Petsche, T., and published by MIT Press of Cambridge, MA. We enclose the abstracts and ftp addresses of these papers. Full citations are at the bottom of each abstract. Comments and feedback are welcome. - Marni Stewart Bartlett, Tony Bell, Michael Gray, Mike Lewicki, Terry Sejnowski, Magnus Stensmo, Akaysha Tang ************************************************************** VIEWPOINT INVARIANT FACE RECOGNITION USING INDEPENDENT COMPONENT ANALYSIS AND ATTRACTOR NETWORKS Bartlett, M. Stewart & Sejnowski, T.J. EDGES ARE THE `INDEPENDENT COMPONENTS' OF NATURAL SCENES Bell A.J. & Sejnowski T.J. DYNAMIC FEATURES FOR VISUAL SPEECHREADING: A SYSTEMATIC COMPARISON Gray, M.S., Movellan, J.R., & Sejnowski, T.J. SELECTIVE INTEGRATION: A MODEL FOR DISPARITY ESTIMATION Gray, M.S., Pouget, A., Zemel, R., Nowlan, S., & Sejnowski, T.J. BLIND SEPARATION OF DELAYED AND CONVOLVED SOURCES Lee T-W., Bell A.J. & Lambert R. BAYESIAN UNSUPERVISED LEARNING OF HIGHER ORDER STRUCTURE Lewicki, M.S. & Sejnowski, T.J. LEARNING DECISION THEORETIC UTILITIES THROUGH REINFORCEMENT LEARNING Stensmo, M. & Sejnowski, T.J. CHOLINERGIC MODULATION PRESERVES SPIKE TIMING UNDER PHYSIOLOGICALLY REALISTIC FLUCTUATING INPUT Tang, A.C., Bartels, A.M., & Sejnowski, T.J. ************************************************************** VIEWPOINT INVARIANT FACE RECOGNITION USING INDEPENDENT COMPONENT ANALYSIS AND ATTRACTOR NETWORKS Bartlett, M. Stewart & Sejnowski, T.J. We have explored two approaches to recognizing faces across changes in pose. First, we developed a representation of face images based on independent component analysis (ICA) and compared it to a principal component analysis (PCA) representation for face recognition. The ICA basis vectors for this data set were more spatially local than the PCA basis vectors and the ICA representation had greater invariance to changes in pose. Second, we present a model for the development of viewpoint invariant responses to faces from visual experience in a biological system. The temporal continuity of natural visual experience was incorporated into an attractor network model by Hebbian learning following a lowpass temporal filter on unit activities. When combined with the temporal filter, a basic Hebbian update rule became a generalization of Griniasty et al. (1993), which associates temporally proximal input patterns into basins of attraction. The system acquired representations of faces that were largely independent of pose. ftp://ftp.cnl.salk.edu/pub/marni/nips96_bartlett.ps http://www.cnl.salk.edu/~marni/publications.html Bartlett, M. Stewart & Sejnowski, T. J. (in press). Viewpoint invariant face recognition using independent component analysis and attractor networks. In Mozer, M.C., Jordan, M.I., Petsche, T.(Eds.), Advances in Neural Information Processing Systems 9. MIT Press, Cambridge, MA, U.S.A. ************************************************************** EDGES ARE THE `INDEPENDENT COMPONENTS' OF NATURAL SCENES Bell A.J. & Sejnowski T.J. Field (1994) has suggested that neurons with line and edge selectivities found in primary visual cortex of cats and monkeys form a sparse, distributed representation of natural scenes, and Barlow (1989) has reasoned that such responses should emerge from an unsupervised learning algorithm that attempts to find a factorial code of independent visual features. We show here that non-linear `infomax', when applied to an ensemble of natural scenes, produces sets of visual filters that are localised and oriented. Some of these filters are Gabor-like and resemble those produced by the sparseness-maximisation network of Olshausen \& Field (1996). In addition, the outputs of these filters are as independent as possible, since the infomax network is able to perform Independent Components Analysis (ICA). We compare the resulting ICA filters and their associated basis functions, with other decorrelating filters produced by Principal Components Analysis (PCA) and zero-phase whitening filters (ZCA). The ICA filters have more sparsely distributed (kurtotic) outputs on natural scenes. They also resemble the receptive fields of simple cells in visual cortex, which suggests that these neurons form an information-theoretic co-ordinate system for images. ftp://ftp.cnl.salk.edu/pub/tony/edge.ps.Z Bell A.J. & Sejnowski T.J. (In press). Edges are the `Independent Components' of Natural Scenes. In Mozer, M.C., Jordan, M.I., Petsche, T. (Eds.), Advances in Neural Information Processing Systems 9. MIT Press, Cambridge, MA, U.S.A. ************************************************************** DYNAMIC FEATURES FOR VISUAL SPEECHREADING: A SYSTEMATIC COMPARISON Gray, M. S., Movellan, J. R., & Sejnowski, T. J. Humans use visual as well as auditory speech signals to recognize spoken words. A variety of systems have been investigated for performing this task. The main purpose of this research was to systematically compare the performance of a range of dynamic visual features on a speechreading task. We have found that normalization of images to eliminate variation due to translation, scale, and planar rotation yielded substantial improvements in generalization performance regardless of the visual representation used. In addition, the dynamic information in the difference between successive frames yielded better performance than optical-flow based approaches, and compression by local low-pass filtering worked surprisingly better than global principal components analysis (PCA). These results are examined and possible explanations are explored. ftp://ftp.cnl.salk.edu/pub/michael/nips_lips.ps ftp://ftp.cnl.salk.edu/pub/michael/nips_lips-abs.text Gray, M. S., Movellan, J. R., & Sejnowski, T. J. (In press). Dynamic features for visual speechreading: A systematic comparison. In Mozer, M.C., Jordan, M.I., Petsche, T. (Eds.), Advances in Neural Information Processing Systems 9. MIT Press, Cambridge, MA, U.S.A. ************************************************************** SELECTIVE INTEGRATION: A MODEL FOR DISPARITY ESTIMATION Gray, M. S., Pouget, A., Zemel, R., Nowlan, S., & Sejnowski, T. J. Local disparity information is often sparse and noisy, which creates two conflicting demands when estimating disparity in an image region: the need to spatially average to get an accurate estimate, and the problem of not averaging over discontinuities. We have developed a network model of disparity estimation based on disparity-selective neurons, such as those found in the early stages of processing in visual cortex. The model can accurately estimate multiple disparities in a region, which may be caused by transparency or occlusion, in real images and random-dot stereograms. The use of a selection mechanism to selectively integrate reliable local disparity estimates results in superior performance compared to standard back-propagation and cross-correlation approaches. In addition, the representations learned with this selection mechanism are consistent with recent neurophysiological results of von der Heydt, Zhou, Friedman, and Poggio (1995) for cells in cortical visual area V2. Combining multi-scale biologically-plausible image processing with the power of the mixture-of-experts learning algorithm represents a promising approach that yields both high performance and new insights into visual system function. ftp://ftp.cnl.salk.edu/pub/michael/nips_stereo.ps ftp://ftp.cnl.salk.edu/pub/michael/nips_stereo-abs.text Gray, M. S., Pouget, A., Zemel, R., Nowlan, S., & Sejnowski, T. J. (In press). Selective Integration: A Model for Disparity Estimation. In Mozer, M.C., Jordan, M.I., Petsche, T. (Eds.), Advances in Neural Information Processing Systems 9. MIT Press, Cambridge, MA, U.S.A. ************************************************************** BLIND SEPARATION OF DELAYED AND CONVOLVED SOURCES Lee T-W., Bell A.J. & Lambert R. We address the difficult problem of separating multiple speakers with multiple microphones in a real room. We combine the work of Torkkola and Amari, Cichocki and Yang, to give Natural Gradient information maximisation rules for recurrent (IIR) networks, blindly adjusting delays, separating and deconvolving mixed signals. While they work well on simulated data, these rules fail in real rooms which usually involve non-minimum phase transfer functions, not-invertible using stable IIR filters. An approach that sidesteps this problem is to perform infomax on a feedforward architecture in the frequency domain (Lambert 1996). We demonstrate real-room separation of two natural signals using this approach. ftp://ftp.cnl.salk.edu/pub/tony/twfinal.ps.Z Lee T-W., Bell A.J. & Lambert R. (In press). Blind separation of delayed and convolved sources. In Mozer, M.C., Jordan, M.I., Petsche, T. (Eds.), Advances in Neural Information Processing Systems 9. MIT Press, Cambridge, MA, U.S.A. ************************************************************** BAYESIAN UNSUPERVISED LEARNING OF HIGHER ORDER STRUCTURE Lewicki, M. S. & Sejnowski, T. J. Multilayer architectures such as those used in Bayesian belief networks and Helmholtz machines provide a powerful framework for representing and learning higher order statistical relations among inputs. Because exact probability calculations with these models are often intractable, there is much interest in finding approximate algorithms. We present an algorithm that efficiently discovers higher order structure using EM and Gibbs sampling. The model can be interpreted as a stochastic recurrent network in which ambiguity in lower-level states is resolved through feedback from higher levels. We demonstrate the performance of the algorithm on benchmark problems. ftp://ftp.cnl.salk.edu/pub/lewicki/nips96.ps.Z ftp://ftp.cnl.salk.edu/pub/lewicki/nips96-abs.text Lewicki, M.S. and Sejnowski, T.J. (In press). Bayesian unsupervised learning of higher order structure. In Mozer, M.C., Jordan, M.I., and Petsche, T. (Eds.), Advances in Neural and Information Processing Systems 9. MIT Press, Cambridge, MA, U.S.A. ************************************************************** LEARNING DECISION THEORETIC UTILITIES THROUGH REINFORCEMENT LEARNING Stensmo, M. & Sejnowski, T. J. Probability models can be used to predict outcomes and compensate for missing data, but even a perfect model cannot be used to make decisions unless the values of the outcomes, or preferences between them, are also provided. This arises in many real-world problems, such as medical diagnosis, where the cost of the test as well as the expected improvement in the outcome must be considered. Relatively little work has been done on learning the utilities of outcomes for optimal decision making. In this paper, we show how temporal-difference (TD($\lambda$)) reinforcement learning can be used to determine decision theoretic utilities within the context of a mixture model and apply this new approach to a problem in medical diagnosis. TD($\lambda$) learning reduces the number of tests that have to be done to achieve the same level of performance with the probability model alone, which result in significant cost savings and increased efficiency. http://www.cs.berkeley.edu/~magnus/papers/nips96.ps.Z Stensmo, M. and Sejnowski, T. J. (in press). Learning decision theoretic utilities through reinforcement learning. In: Mozer, M.C., Jordan, M.I. and Petsche, T., (Eds.), Advances in Neural Information Processing Systems, Vol. 9. MIT Press, Cambridge, MA, U.S.A. ************************************************************** CHOLINERGIC MODULATION PRESERVES SPIKE TIMING UNDER PHYSIOLOGICALLY REALISTIC FLUCTUATING INPUT Tang, A. C., Bartels, A. M., & Sejnowski, T. J. Neuromodulation can change not only the mean firing rate of a neuron, but also its pattern of firing. Therefore, a reliable neural coding scheme, whether a rate coding or a spike time based coding, must be robust in a dynamic neuromodulatory environment. The common observation that cholinergic modulation leads to a reduction in spike frequency adaptation implies a modification of spike timing, which would make a neural code based on precise spike timing difficult to maintain. In this paper, the effects of cholinergic modulation were studied to test the hypothesis that precise spike timing can serve as a reliable neural code. Using the whole cell patch-clamp technique in rat neocortical slice preparation and compartmental modeling techniques, we show that cholinergic modulation, surprisingly, preserved spike timing in response to a fluctuating inputs that resembles {\em in vivo} conditions. This result suggests that in vivo spike timing may be much more resistant to changes in neuromodulator concentrations than previous physiological studies have implied. ftp://ftp.cnl.salk.edu/pub/tang/ach_timing.ps.gz ftp://ftp.cnl.salk.edu/pub/tang/ach_timing_abs.txt Akaysha C. Tang, Andreas M. Bartels, and Terrence J Sejnowski. (In press). Cholinergic Modulation Preserves Spike Timing Under Physiologically Realistic Fluctuating Input. In Mozer, M.C., Jordan, M.I., Petsche, T. (Eds.), Advances in Neural Information Processing Systems 9. MIT Press, Cambridge, MA, U.S.A. ************************************************************** From back@zoo.riken.go.jp Thu Jan 23 16:06:31 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id QAA03768 for ; Thu, 23 Jan 1997 16:05:53 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id QAA06471 for ; Thu, 23 Jan 1997 16:05:52 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa14302; 23 Jan 97 11:58:09 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa14300; 23 Jan 97 11:40:43 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa03896; 23 Jan 97 11:40:06 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id ab06874; 23 Jan 97 11:01:13 EST Received: from [134.160.48.38] by CS.CMU.EDU id aa19969; 23 Jan 97 11:00:21 EST Received: by tora.riken.go.jp; id AA05123; Fri, 24 Jan 1997 01:10:57 +0900 Message-Id: <9701231610.AA05123@tora.riken.go.jp> From: Andrew Back To: connectionists@cs.cmu.edu MMDF-Warning: Parse error in original version of preceding line at DST.BOLTZ.CS.CMU.EDU Subject: URL Correction: TR on Alternative Discrete-time Operators in Neural Networks Date: Fri, 24 Jan 1997 00:59:24 +0900 X-Msmail-Priority: Normal X-Priority: 3 X-Mailer: Microsoft Internet Mail 4.70.1155 Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Please note the following URL correction for the previously announced TR: Alternative Discrete-Time Operators and Their Application to Nonlinear Models Andrew D. Back, Ah Chung Tsoi, Bill G. Horne, C. Lee Giles U. of Maryland Technical Report CS-TR-3738 and UMIACS-TR-97-03 Instead of: http://zoo.riken.go.jp/abs1/back/Welcome.html please use: http://www.bip.riken.go.jp/absl/back Our apologies for any inconvenience caused. -- Andrew Back Brain Information Processing Group The Institute of Physical and Chemical Research (RIKEN), Japan. WWW: http://www.bip.riken.go.jp/absl/back From ingber@ingber.com Thu Jan 23 22:47:29 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id WAA13660 for ; Thu, 23 Jan 1997 22:47:23 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id WAA13130 for ; Thu, 23 Jan 1997 22:47:21 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa14614; 23 Jan 97 17:38:42 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa14611; 23 Jan 97 17:25:57 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa04161; 23 Jan 97 17:25:46 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa11821; 23 Jan 97 15:01:28 EST Received: from [131.215.50.235] by CS.CMU.EDU id aa22892; 23 Jan 97 14:59:12 EST Received: (from ingber@localhost) by alumnae.caltech.edu (8.8.3/8.7.3) id LAA03723 for connectionists@cs.cmu.edu; Thu, 23 Jan 1997 11:58:41 -0800 (PST) Message-Id: <199701231958.LAA03723@alumnae.caltech.edu> From: Lester Ingber Date: Thu, 23 Jan 1997 14:58:40 -0500 Reply-To: Lester Ingber X-URL: http://www.ingber.com/ X-FTP: ftp.ingber.com X-Mailer: Mail User's Shell (7.2.6 alpha(3) 7/19/95) To: connectionists@cs.cmu.edu Subject: Papers: Canonical momenta indicators ... Below are URLs and abstracts for 4 papers utilizing canonical momenta indicators (CMI), in analyses of neocortical EEG, financial markets, combat simulation, and data mining/knowledge discovery. Below these are instructions for retrieval of files. As noted by a Physical Review E referee for the EEG paper, ... the paper ... has potential value for a wide variety of systems, especially for very complex systems. Its filename [and size] is smni97_cmi.ps.Z [170K] %A L. Ingber %T Statistical mechanics of neocortical interactions: Canonical momenta indicators of electroencephalography %J Physical Review E %P (to be published) %D 1997 %O URL http://www.ingber.com/smni97_cmi.ps.Z ABSTRACT: A series of papers has developed a statistical mechanics of neocortical interactions (SMNI), deriving aggregate behavior of experimentally observed columns of neurons from statistical electrical-chemical properties of synaptic interactions. While not useful to yield insights at the single neuron level, SMNI has demonstrated its capability in describing large-scale properties of short-term memory and electroencephalographic (EEG) systematics. The necessity of including nonlinear and stochastic structures in this development has been stressed. Sets of EEG and evoked potential data were fit, collected to investigate genetic predispositions to alcoholism and to extract brain "signatures" of short-term memory. Adaptive Simulated Annealing (ASA), a global optimization algorithm, was used to perform maximum likelihood fits of Lagrangians defined by path integrals of multivariate conditional probabilities. Canonical momenta indicators (CMI) are thereby derived for individual's EEG data. The CMI give better signal recognition than the raw data, and can be used to advantage as correlates of behavioral states. These results give strong quantitative support for an accurate intuitive picture, portraying neocortical interactions as having common algebraic or physics mechanisms that scale across quite disparate spatial scales and functional or behavioral phenomena, i.e., describing interactions among neurons, columns of neurons, and regional masses of neurons. The markets file is the final version of a preprint posted in March '96. markets96_momenta.ps.Z [45K] %A L. Ingber %T Canonical momenta indicators of financial markets and neocortical EEG %B International Conference on Neural Information Processing (ICONIP'96) %I Springer %C New York %P 777-784 %D 1996 %O Invited paper to the 1996 International Conference on Neural Information Processing (ICONIP'96), Hong Kong, 24-27 September 1996. URL http://www.ingber.com/markets96_momenta.ps.Z ABSTRACT: A paradigm of statistical mechanics of financial markets (SMFM) is fit to multivariate financial markets using Adaptive Simulated Annealing (ASA), a global optimization algorithm, to perform maximum likelihood fits of Lagrangians defined by path integrals of multivariate conditional probabilities. Canonical momenta are thereby derived and used as technical indicators in a recursive ASA optimization process to tune trading rules. These trading rules are then used on out-of-sample data, to demonstrate that they can profit from the SMFM model, to illustrate that these markets are likely not efficient. This methodology can be extended to other systems, e.g., electroencephalography. This approach to complex systems emphasizes the utility of blending an intuitive and powerful mathematical-physics formalism to generate indicators which are used by AI-type rule-based models of management. combat97_cmi.ps.Z [55K] %A M. Bowman %A L. Ingber %T Canonical momenta of nonlinear combat %B Proceedings of the 1997 Simulation Multi-Conference, 6-10 April 1997, Atlanta, GA %I Society for Computer Simulation %C San Diego, CA %P (to be published) %D 1997 %O URL http://www.ingber.com/combat97_cmi.ps.Z ABSTRACT: The context of nonlinear combat calls for more sophisticated measures of effectiveness. We present a set of tools that can be used as such supplemental indicators, based on stochastic nonlinear multivariate modeling used to benchmark Janus simulation to exercise data from the U.S. Army National Training Center (NTC). As a prototype study, a strong global optimization tool, adaptive simulated annealing (ASA), is used to explicitly fit Janus data, deriving coefficients of relative measures of effectiveness, and developing a sound intuitive graphical decision aid, canonical momentum indicators (CMI), faithful to the sophisticated algebraic model. We argue that these tools will become increasingly important to aid simulation studies of the importance of maneuver in combat in the 21st century. path97_datamining.ps.Z [90K] %A L. Ingber %T Data mining and knowledge discovery via statistical mechanics in nonlinear stochastic systems %P (submitted) %D 1997 %O URL http://www.ingber.com/path97_datamining.ps.Z ABSTRACT: A modern calculus of multivariate nonlinear multiplicative Gaussian-Markovian systems provides models of many complex systems faithful to their nature, e.g., by not prematurely applying quasi-linear approximations for the sole purpose of easing analysis. To handle these complex algebraic constructs, sophisticated numerical tools have been developed, e.g., methods of adaptive simulated annealing (ASA) global optimization and of path integration (PATHINT). In-depth application to three quite different complex systems have yielded some insights into the benefits to be obtained by application of these algorithms and tools, in statistical mechanical descriptions of neocortex (electroencephalography), financial markets (interest-rate and trading models), and combat analysis (baselining simulations to exercise data). The latest Adaptive Simulated Annealing (ASA) optimization code may be retrieved at no charge from this archive in several formats: http://www.ingber.com/ASA-shar [1350K] http://www.ingber.com/ASA-shar.Z [500K] http://www.ingber.com/ASA.tar.Z [450K] http://www.ingber.com/ASA.tar.gz [320K] http://www.ingber.com/ASA.zip [330K] The archive can be accessed via WWW path http://www.ingber.com/ http://www.alumni.caltech.edu/~ingber/ where the last address is a mirror homepage for the full archive. Code and reprints can be retrieved via anonymous ftp from ftp.ingber.com. Interactively [brackets signify machine prompts]: [your_machine%] ftp ftp.ingber.com [Name (...):] anonymous [Password:] your_e-mail_address [ftp>] binary [ftp>] ls [ftp>] get file_of_interest [ftp>] quit If you do not have ftp access, get information on the FTPmail service by: mail ftpmail@ftpmail.ramona.vix.com (was ftpmail@decwrl.dec.com), and send only the word "help" in the body of the message. Limited help assisting people with queries on my codes and papers is available only by electronic mail correspondence. Sorry, I cannot mail out hardcopies of code or papers. /* RESEARCH ingber@ingber.com * * INGBER ftp://ftp.ingber.com * * LESTER http://www.ingber.com/ * * Prof. Lester Ingber __ PO Box 857 __ McLean, VA 22101-0857 __ USA */ From regier@tidbit Fri Jan 24 15:51:45 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id PAA07643 for ; Fri, 24 Jan 1997 15:51:38 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id PAA29968 for ; Fri, 24 Jan 1997 15:51:35 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa14961; 23 Jan 97 22:36:46 EST Received: from SKINNER.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa14958; 23 Jan 97 22:21:55 EST Received: from skinner.boltz.cs.cmu.edu by skinner.boltz.cs.cmu.edu id aa15490; 23 Jan 97 22:21 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id ab16045; 23 Jan 97 18:10:34 EST Received: from [128.135.84.104] by CS.CMU.EDU id aa25054; 23 Jan 97 18:09:44 EST Received: by tidbit. (SMI-8.6/SMI-SVR4) id RAA03913; Thu, 23 Jan 1997 17:09:08 -0600 From: Terry Regier Message-Id: <199701232309.RAA03913@tidbit.> Subject: FEB 15 DEADLINE for Computational Psycholinguistics conference To: connectionists@cs.cmu.edu Date: Thu, 23 Jan 1997 23:09:07 +0000 (GMT) X-Mailer: ELM [version 2.4 PL23] Content-Type: text **** REMINDER! **** ---->> ABSTRACTS DUE FEBRUARY 15. <<---- CALL FOR ABSTRACTS Conference on Computational Psycholinguistics CPL '97 August 10-12, 1997 Berkeley, California In Conjunction with Cognitive Science 1997 Sponsored by the Cognitive Science Society International Computer Science Institute Institute for Cognitive Science, University of Colorado Psychology Department, University of Chicago Institute for Cognitive Studies, UC Berkeley ******* Invited Speakers ****** Jeff Elman Ted Gibson Mark Seidenberg Paul Smolensky ******************************* This conference is intended to bring together researchers who work on psychologically motivated computational models of human language. We solicit contributions on models of linguistic processing, acquisition, or representation at every level: phonetic, phonological, morphological, syntactic, semantic, and pragmatic. The goal of the conference is to build bridges between computationally oriented researchers who have focused on different aspects of human language processing. AREAS OF INTEREST: We solicit extended abstracts for oral or poster presentations on psychologically motivated computational models of human language processing, or empirical or theoretical results bearing on such models. Papers/posters may concern any aspect of human language processing, including but not limited to: phonetic, phonological, or morphological processing lexical access acquisition of phonology or morphology acquisition of syntax and semantics syntactic parsing semantic and pragmatic interpretation, text understanding conversation (e.g. turn taking, pauses, discourse cues) generation lexical choice prosody disambiguation Authors are urged to write for computationally literate researchers that may not be in their own subfield. We hope the conference will afford people an opportunity to present work in progress for feedback, and to get ideas and epiphanies from other computational or psychological researchers with different backgrounds. To facilitate the interchange of ideas, the schedule will set aside a significant amount of time for discussion, as well as an outing, probably to Napa for winetasting. SUBMISSION FORMAT AND DATES: The submission should consist of a title/identification page plus an abstract. The title page should contain the title, author(s), affiliation(s), and the submitting author's mailing address, telephone number, fax number and e-mail address, as well as a preference for an ORAL PRESENTATION or a POSTER PRESENTATION. Please note that oral presentations and posters will be considered to be of equal status at this conference; as a result, they will be reviewed equally, and will have equal chances of appearing in subsequent publications. In order to help place oral and poster presentations on an equal footing, both poster and oral presenters will give 2-3 oral summary "previews" of their presentations. However, authors may not get their first choice of presentation method because of scheduling conflicts. The actual abstract should be 2-3 pages long, in sufficient detail to allow substantive evaluation. It should not contain the authors' names or addresses, as reviewing will be blind. Furthermore, self-references that reveal the authors' identity (e.g. "We previously showed (Chiu, 1991)...") should be avoided. Instead use references like "Chiu previously showed (Chiu, 1991) ...". Submissions by e-mail are STRONGLY encouraged. Acceptable formats for electronic submissions include, in order of preference: 1) HTML 2) Postscript (e.g. from LaTeX) 3) ASCII (plain text) A sample HTML skeleton abstract form which may be downloaded and copied, as well as other submission details, are included on our website: http://www.ccp.uchicago.edu/cpl We expect that some or all of the submissions will be published in either a conference or a themed volume. Submissions for publication will be full-length papers, and will themselves be reviewed at a later date. Please keep checking the web page for further information on publishing plans. SCHEDULE: Deadline for receiving abstracts: Feb 15, 1997 ************** Information on acceptance sent out: April 1, 1997 Conference Aug 10-12, 1997 SUBMISSION ADDRESS: For electronic submissions (preferred) : cpl@ccp.uchicago.edu For hardcopy submissions (dispreferred) , either: CPL '97 c/o Prof. Dan Jurafsky Department of Linguistics University of Colorado, Boulder, CO 80309-0295 USA or CPL '97 c/o Prof. Terry Regier Department of Psychology University of Chicago 5848 S. University Avenue Chicago, IL 60637 USA PROGRAM COMMITTEE Sessions will be organized and contributions will be reviewed by the program committee: Dan Jurafsky, University of Colorado (Co-chair) Terry Regier, University of Chicago (Co-chair) Diane Bradley, CUNY Michael Brent, Johns Hopkins University Walter Daelemans, University of Tilburg Gary Dell, University of Illinois, Urbana-Champaign Mark Ellison, University of Edinburgh Jerry Feldman, ICSI / UC Berkeley Michael Gasser, Indiana University John Goldsmith, University of Chicago Gene Gragg, University of Chicago Mary Hare, UC San Diego Marti Hearst, Xerox PARC Jamie Henderson, University of Exeter Julia Hirschberg, AT&T Bell Labs Ron Kaplan, Xerox PARC, Stanford University Gerard Kempen, NIAS Pat Langley, Stanford University Brian MacWhinney, Carnegie-Mellon University Gary Marcus, University of Massachusetts Mitch Marcus, University of Pennsylvania Don Mitchell, University of Exeter Howard Nusbaum, University of Chicago Kim Plunkett, Oxford University Robert Port, Indiana University Philip Resnik, University of Maryland Ardi Roelofs, Max Planck Institute, Nijmegen Stephanie Seneff, MIT Lokendra Shastri, ICSI (Berkeley) Richard Shillcock, University of Edinburgh Liz Shriberg, SRI International Jeff Mark Siskind, University of Vermont Koenraad de Smedt, University of Bergen Michael Spivey-Knowlton, Cornell University Suzanne Stevenson, Rutgers University Oliviero Stock, IRST, Trento Virginia Teller, CUNY Wolfgang Wahlster, DFKI / University of Saarbruecken Nigel Ward, University of Tokyo FURTHER INFORMATION: For further information please contact Dan and Terry at cpl@ccp.uchicago.edu From atick@monaco.rockefeller.edu Fri Jan 24 20:09:32 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id UAA11898 for ; Fri, 24 Jan 1997 20:09:03 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id UAA04129 for ; Fri, 24 Jan 1997 20:09:01 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa16095; 24 Jan 97 12:37:33 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa16093; 24 Jan 97 12:17:31 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05187; 24 Jan 97 12:16:04 EST Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id ac03549; 24 Jan 97 11:55:20 EST Received: from monaco.rockefeller.edu by RI.CMU.EDU id aa02118; 24 Jan 97 11:54:34 EST Received: by monaco (940816.SGI.8.6.9/940406.SGI) id LAA28096; Fri, 24 Jan 1997 11:56:11 -0500 From: Joseph Atick Message-Id: <9701241156.ZM28094@monaco.rockefeller.edu> Date: Fri, 24 Jan 1997 11:56:11 -0500 X-Mailer: Z-Mail (3.2.2 10apr95 MediaMail) To: connectionists@cs.cmu.edu Subject: Network: CNS, Table of Contents, Vol. 8, 1,97 Cc: atick@MONACO.CMCL.CS.CMU.EDU Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Network: Computation in Neural Systems Table of Contents Volume 8, 1, 1997 As you may know, the journal has adopted incremental publishing in its online edition, which means a paper is immediately published as soon as it is accepted and processed. Every 3 months we finalize an issue for archival reasons and issue a table of contents. Online journal and information can be found at http://www.iop.org/Journals/ne (limited access to non-subcribers, access to full length articles to insitutional subscribers) Table of contents of latest issue: %%%%%%%%%%%%% Editorial: Thank you to all our referees TOPICAL REVIEW R1 On the use of computation in modelling behaviour F van der Velde PAPERS 1 Nitric oxide: what can it compute? B Krekelberg and J G Taylor 17 Analysis of ocular dominance pattern formation in a high-dimensional self-organizing-map model H-U Bauer, D Brockmann and T Geisel 35 Capacity and information efficiency of the associative net B Graham and D Willshaw 55 A neural net model of the adaptation of binocular vertical eye alignment J W McCandless and C M Schor 71 Quality and efficiency of retrieval for Willshaw-like autoassociative networks: III. Willshaw--Potts model A Kartashov, A Frolov, A Goltsev and R Folk 87 Stereo vision using a microcanonical mean field annealing neural network Jeng-Sheng Huang and Hsiao-Chung Liu 104 Abstracts of Topical reviews published during 1996 Mutual information maximization: models of cortical self-organization S. Becker The development of topography in the visual cortex: a review of models N. Swindale Auditory cortical representation of complex acoustiv spectra as inferred from the ripple analysis method S. Shamma Human colour perception and its adaptation M. Webster %%%%%%%%%% Coming up in the May issue (1) Metric-space analysis of spike trains: theory, algorithm and application Jonathon Victor, & Keith Purpura (2) A neural model of the stroboscopic alternative motion A Bartschl and J L van Hemmen and much much more... %%%%%%%%%%%%%% Network:CNS would like to welcome its new editorial board: Larry Abott, Brandeis Peter Dayan, MIT Peter Hancock, University of Stirling David Heeger, Stanford University Leo van Hemmen, University of Munich Tony Movshon, NYU Markus Meister, Harvard Dan Ruderman, Salk Insitute Jonathon Victor, Cornell Univeristy David Willshaw, University of Edinburgh As always, we are happy to hear your suggestions and receive your submissions. We hope to continue to make Network:CNS an indispensible research tool for the computational and neuroscience community. Best regards joseph atick Editor-in-chief -- Joseph J. Atick Rockefeller University 1230 York Avenue New York, NY 10021 Tel: 212 327 7421 Fax: 212 327 7422 From lane@katrix.com Sat Jan 25 04:13:36 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id EAA15576 for ; Sat, 25 Jan 1997 04:13:28 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id EAA07414 for ; Sat, 25 Jan 1997 04:13:26 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa16657; 24 Jan 97 22:46:12 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa16653; 24 Jan 97 22:32:16 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05544; 24 Jan 97 22:32:08 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id ab07513; 24 Jan 97 14:50:50 EST Received: from postoffice.usa.net by CS.CMU.EDU id aa04432; 24 Jan 97 14:49:44 EST Received: from athos.katrix.com (athos.katrix.com [205.214.69.1]) by postoffice.usa.net (8.8.0/8.7.5) with SMTP id MAA28163 for ; Fri, 24 Jan 1997 12:48:06 -0700 (MST) Received: from engarde.katrix.com by athos.katrix.com via SMTP (940816.SGI.8.6.9/930416.SGI.AUTO) for id OAA11915; Fri, 24 Jan 1997 14:39:34 -0500 Received: by engarde.katrix.com with Microsoft Mail id <01BC0A05.B08EE400@engarde.katrix.com>; Fri, 24 Jan 1997 14:48:41 -0500 Message-ID: <01BC0A05.B08EE400@engarde.katrix.com> From: Stephen Lane To: "'connectionists@cs.cmu.edu'" Subject: Job Openings in Intelligent Agent R&D Date: Fri, 24 Jan 1997 14:48:39 -0500 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit JOB OPENINGS IN INTELLIGENT AGENT RESEARCH AND DEVELOPMENT OVERVIEW Katrix Inc. has developed technology that enables intelligent agents to be embodied as fully articulated three-dimensional human and animal-like interactive characters in computer games, virtual reality simulations and distributed interactive network applications. Intelligent agents created with Katrix Technology think, learn and act, and as a result, can adapt their behavior and movement in real-time based upon interactions with human users and the 3D virtual environment. Katrix currently is developing a suite of products that support the creation and control of such intelligent agents for use as fully interactive Internet Avatars, Digital Actors and Virtual Creatures. These products include point and click behavioral animation authoring tools, libraries of off-the-shelf interactive characters and intelligent behaviors, as well as a totally new single-hand computer input device particularly well suited for virtual reality and gaming applications. STAFF POSITIONS AVAILABLE The positions available involve core technology development in the areas of intelligent control, robotics, behavioral animation, neural networks, knowledge-based systems, distributed interactive simulation and visual programming language design. Prospective candidates should have a strong math background and be self-motivated. Required programming skills include proficiency in C and C++ on PC and/or Unix platforms. A research track record in controls and dynamics, robotics or neural networks is a definite plus. Familiarity with design and implementation of graphical user interfaces, 3D computer animation, interactive simulation or 3D games also is desirable. Staff positions are available at various levels at Katrix facility located in Princeton, New Jersey (about 60 minutes from both New York City and Philadelphia). CONTACT If you are interested in an exciting career opportunity with a rapidly growing company in an industry poised for explosive growth, please send your resume immediately to: Stephen H. Lane, President FAX: (609) 921-7547 Email: lane@katrix.com Katrix Inc. 31 Airpark Road Princeton, NJ 08540 (609) 921-7544 From rao@cs.rochester.edu Sat Jan 25 07:54:10 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id HAA16748 for ; Sat, 25 Jan 1997 07:54:03 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id HAA09201 for ; Sat, 25 Jan 1997 07:54:01 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa17246; 25 Jan 97 3:25:35 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa17244; 25 Jan 97 3:16:25 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05896; 25 Jan 97 3:15:51 EST Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa16929; 25 Jan 97 0:37:27 EST Received: from cayuga.cs.rochester.edu by RI.CMU.EDU id aa06553; 25 Jan 97 0:36:59 EST Received: from porcupine.cs.rochester.edu (porcupine.cs.rochester.edu [192.5.53.126]) by cayuga.cs.rochester.edu (8.6.9/H) with ESMTP id AAA14454; Sat, 25 Jan 1997 00:36:51 -0500 Received: (from rao@localhost) by porcupine.cs.rochester.edu (8.6.9/K) id AAA04030; Sat, 25 Jan 1997 00:36:49 -0500 Date: Sat, 25 Jan 1997 00:36:49 -0500 Message-Id: <199701250536.AAA04030@porcupine.cs.rochester.edu> From: Rajesh Rao To: connectionists@cs.cmu.edu, neuron@cattell.psych.upenn.edu, comp-neuro@smaug.bbb.caltech.edu, submission@vislist.com, cvnet@skivs.ski.org Subject: Technical Report: Visual recognition and robust Kalman filters The following paper on appearance-based visual recognition and robust Kalman filtering is now available for retrieval via ftp. Comments and suggestions welcome (This message has been cross-posted - my apologies to those who received it more than once). -- Rajesh Rao Internet: rao@cs.rochester.edu Dept. of Computer Science VOX: (716) 275-2527 University of Rochester FAX: (716) 461-2018 Rochester NY 14627-0226 WWW: http://www.cs.rochester.edu/u/rao/ =========================================================================== Robust Kalman Filters for Prediction, Recognition, and Learning Rajesh P.N. Rao Department of Computer Science University of Rochester Rochester, NY 14627-0226 Technical Report 645 December, 1996 Using results from the field of robust statistics, we derive a class of Kalman filters that are robust to structured and unstructured noise in the input data stream. Each filter from this class maintains robust optimal estimates of the input process's hidden state by allowing the measurement covariance matrix to be a non-linear function of the prediction errors. This endows the filter with the ability to reject outliers in the input stream. Simultaneously, the filter also learns an internal model of input dynamics by adapting its measurement and state transition matrices using two additional Kalman filter-based adaptation rules. We present experimental results demonstrating the efficacy of such filters in mediating appearance-based segmentation and recognition of objects and image sequences in the presence of varying degrees of occlusion, clutter, and noise. Retrieval information: FTP-host: ftp.cs.rochester.edu FTP-pathname: /pub/u/rao/papers/robust.ps.Z URL: ftp://ftp.cs.rochester.edu/pub/u/rao/papers/robust.ps.Z 15 pages; 296K compressed, 1015K uncompressed ------------------------------------------------------------------------- Anonymous ftp instructions: >ftp ftp.cs.rochester.edu Connected to anon.cs.rochester.edu. 220 anon.cs.rochester.edu FTP server (Version wu-2.4(3)) ready. Name: [type 'anonymous' here] 331 Guest login ok, send your complete e-mail address as password. Password: [type your e-mail address here] ftp> cd /pub/u/rao/papers/ ftp> get robust.ps ftp> bye From wray@Ultimode.com Sat Jan 25 18:33:50 1997 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id SAA24304 for ; Sat, 25 Jan 1997 18:33:32 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id SAA14830 for ; Sat, 25 Jan 1997 18:33:30 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa18358; 25 Jan 97 16:31:31 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa18356; 25 Jan 97 16:16:57 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa06457; 25 Jan 97 16:16:35 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa27935; 25 Jan 97 13:52:05 EST Received: from ultimode.com by EDRC.CMU.EDU id aa01948; 25 Jan 97 13:51:33 EST Received: (from wray@localhost) by Ultimode.com (8.7.6/8.7.3) id KAA12584 for connectionists@cs.cmu.edu; Sat, 25 Jan 1997 10:50:52 -0800 Date: Sat, 25 Jan 1997 10:50:52 -0800 From: Wray Buntine Message-Id: <199701251850.KAA12584@Ultimode.com> To: connectionists@cs.cmu.edu Subject: PhD/Masters Research Assistantship PhD/Masters Research Assistantships Field: probabilistic algorithms, data analysis/mining and optimization for CAD Place: Electrical Engineering and Computer Science University of California, Berkeley The CAD group in the EECS Dept. at UC Berkeley is offering research support for its Masters and Doctoral program. Research areas include but are not limited to the use of data mining/analysis/engineering techniques in CAD or optimization, and probabilistic methods for optimization or specialized compilation. The Electronic Design Technology (EDT) field is concerned with computer automated or computer-assisted design of complex electronic systems. With current hardware capabilities advancing rapidly, a key bottleneck is the development of advanced algorithms for optimization and simulation of partial, abstract or completed designs. Our task is to design, code and experiment with new algorithms, methodologies, and software technologies for alleviating this bottleneck. The task can include the use of data mining/analysis to understand the nature of the optimization task, or in order to develop adaptive optimization methods. The ideal candidate should have a background in computer science, electrical engineering or related disciplines, should be an accomplished or developing programmer, and should have an interest in the theory and mathematical techniques used in optimization, data analysis, or probabilistic methods. Candidates who wish to apply are invited to respond with a copy of their CV to: Professor R. Newton URL: http://www.eecs.berkeley.edu/~newton Dr. Wray Buntine URL: http://www.eecs.berkeley.edu/~wray Dr. Andrew Mayer URL: http://www.eecs.berkeley.edu/~mayer Dept. of Electrical Engineering and Computer Sciences 520 Cory Hall University of California at Berkeley Berkeley, CA, 94720 The CAD Group URL: http://www-cad.eecs.berkeley.edu EECS, UC Berkeley URL: http://www.eecs.berkeley.edu