From tewon at salk.edu Sun Feb 1 20:50:29 1998 From: tewon at salk.edu (Te-Won Lee) Date: Sun, 01 Feb 1998 17:50:29 -0800 Subject: ICA paper available on-line. Message-ID: <199802020150.RAA05626@hebb.salk.edu> Paper available on-line "A Unifying Information-theoretic Framework for Independent Component Analysis" T-W. Lee, M. Girolami, A.J. Bell and T.J. Sejnowski. International Journal on Mathematical and Computer Modeling (in press) http://www.cnl.salk.edu/~tewon/Public/mcm.ps.gz (130k, 23 pages) Abstract: We show that different theories recently proposed for Independent Component Analysis (ICA) lead to the same iterative learning algorithm for blind separation of mixed independent sources. We review those theories and suggest that information theory can be used to unify several lines of research. Pearlmutter and Parra (1996) and Cardoso (1997) showed that the infomax approach of Bell and Sejnowski (1995) and the maximum likelihood estimation approach are equivalent. We show that negentropy maximization also has equivalent properties and therefore all three approaches yield the same learning rule for a fixed nonlinearity. Girolami and Fyfe (1997a) have shown that the nonlinear Principal Component Analysis (PCA) algorithm of Karhunen and Joutsensalo (1994) and Oja (1997) can also be viewed from information-theoretic principles since it minimizes the sum of squares of the fourth-order marginal cumulants and therefore approximately minimizes the mutual information (Comon, 1994). Lambert (1996) has proposed different Bussgang cost functions for multichannel blind deconvolution. We show how the Bussgang property relates to the infomax principle. Finally, we discuss convergence and stability as well as future research issues in blind source separation. ---------------------------------------------------------------------- Dr. Te-Won Lee EMAIL: tewon at salk.edu Computational Neurobiology Lab, WORK: (619) 453-4100 x1215 Salk Institute, HOME: (619) 450-9036 10010 N. Torrey Pines Rd. FAX: (619) 587-0417 La Jolla, CA 92037 WEB: http://www.cnl.salk.edu/~tewon ---------------------------------------------------------------------- From bressler at walt.ccs.fau.edu Mon Feb 2 20:11:39 1998 From: bressler at walt.ccs.fau.edu (Steven Bressler) Date: Mon, 02 Feb 1998 20:11:39 -0500 Subject: Postdoctoral Position in Computational Neuroscience Message-ID: <3.0.1.32.19980202201139.00700758@mail.ccs.fau.edu> COMPUTATIONAL NEUROSCIENCE POSTDOCTORAL POSITION AVAILABLE Center for Complex Systems Florida Atlantic University A postdoctoral position is open in the Center for Complex Systems at Florida Atlantic University to participate in a project in computational neuroscience. The aim of the project is to develop multivariate techniques for the analysis of cortical event-related potentials, and use the results from such analysis as the basis for computational modeling. The approach will emphasize the close interplay between state-of-the-art multivariate autoregressive analysis and the development of dynamical models of distributed information processing in the cerebral cortex. The research project will be conducted in close collaboration with S. Bressler, a cognitive neuroscientist and M. Ding, a computational modeler. The position is for two years, possibly renewable for another year. Required background: -- Ph.D. degree -- Experience in C programming on UNIX systems and X11 Window programming -- Basic knowledge in dynamical systems, matrix algebra, signal processing, and statistics -- Research experience Desired background: -- Working knowledge in neurobiology and neural networks -- Knowledge in autoregressive time series modeling This project is funded by research grants from the National Science Foundation and the National Institute of Mental Health. Please send curriculum vitae, expression of interest, and the names and e-mail or phone numbers of three references to Steven Bressler at bressler at walt.ccs.fau.edu. Information about the Center for Complex Systems at Florida Atlantic University is available at http://www.ccs.fau.edu/ Steven L. Bressler, Ph.D. voice: 561-297-2322 Professor, Program in fax: 561-297-3634 Complex Systems & Brain Sciences Center for Complex Systems bressler at walt.ccs.fau.edu Florida Atlantic University http://www.ccs.fau.edu/~bressler/ 777 Glades Road Boca Raton, FL 33431 U.S.A. From rreilly at ollamh.ucd.ie Mon Feb 2 18:20:04 1998 From: rreilly at ollamh.ucd.ie (Ronan G. Reilly) Date: Mon, 02 Feb 1998 23:20:04 +0000 (GMT) Subject: Postdoctoral position(s) in Dublin Message-ID: <143090E2FEE@ollamh.ucd.ie> ************************************* * LCG TMR Network * * Learning Computational Grammars * * * ************************************* ****************************************************************** * POSTDOCTORAL RESEARCH OPPORTUNITY AT UNIVERSITY COLLEGE DUBLIN * ****************************************************************** LCG (Learning Computational Grammars) is a research network shortlisted for funding by the EC Training and Mobility of Researchers programme (TMR). LCG's contract is currently being negotiated. The network is expected to run from 1st March 1998 for three years. The LCG network involves seven European partners. The research goal of the network is the application of machine learning techniques to extending a variety of computational grammars. The particular focus of UCD's research will be on the use of artificial neural network learning algorithms. See http://www.let.rug.nl/~nerbonne/tmr/lcg.html for more details. Subject to successful contract negotiation, there will be three years of postdoctoral funding available in the Department of Computer Science at University College Dublin tenable from March '98. The ideal postdoctoral candidates will have research experience in the use of ANNs in natural language processing. As the funding is provided by the EU Training and Mobility of researchers programme there are some restrictions on who may benefit from it: * Candidates must be aged 35 or younger * Candidates must be Nationals of an EU country, Norway, Switzerland or Iceland * Candidates must have studied or be studying for a Doctoral Degree * Candidates must not be Irish Nationals or worked in Ireland 18 out of the last 24 months If you are interested and eligible, e-mail your CV (RTF, ASCII, or PS versions only) and the names and addresses of two referees to the address below. Your CV should include a list of recent publications. Please also outline in 2-3 pages your interest in LCG, how it is related to work you have done, and what special expertise you bring to the problem. --------------------------------------------- Ronan G. Reilly, PhD Department of Computer Science University College Belfield Dublin 4 IRELAND http://cs-www.ucd.ie/staff/html/ronan.htm e-mail: Ronan.Reilly at ucd.ie Tel. : +353-1-706 2475 Fax : +353-1-269 7262 From witbrock at jprc.com Tue Feb 3 11:07:37 1998 From: witbrock at jprc.com (witbrock@jprc.com) Date: Tue, 3 Feb 1998 11:07:37 -0500 Subject: CALD Workshop on Mixed Media Databases Message-ID: <199802031607.LAA02778@hurricane.jprc.com> Dear Colleague, You are invited to participate in the Center for Automated Learning and Discovery workshop on Mixed Media databases. This workshop will be held in conjunction with the Conference on Automated Learning and Discovery, being held at Carnegie Mellon University in Pittsburgh from June the 11th to the 13th 1998. This workshop is intended for researchers with an interest in learning from multiple media. The workshop will emphasize both algorithms and applications of learning with mixed media databases. Papers that describe algorithms should cover either novel approaches designed to benefit from mixed-media data, or modifications of standard algorithms that utilize multiple media data sources. Application papers should clearly demonstrate the benefits of learning from two or more types of media. Different media areas to be addressed include: Vision: Image, Video, and VRML Speech and Audio Text, including OCR, Closed-Captioning, handwriting, and web-documents Olfactory perception Haptic and Touch sensing If you would like to present at this workshop, please submit a paper describing original research work and results. Four copies of the paper should be submitted in hardcopy by Feb 15, 1998. The ideal paper should cover two or more topics listed above and apply some aspect of learning to the multiple media data. The learning may involve, but is not limited to neural networks, as well as statistical and probabilistic models. All statistical, probabilistic, and learning approaches are welcome. Papers submitted to this workshop may also be submitted to other conferences or to journals. If you plan to submit a paper or attend, please contact the organizers (listed below). Detailed submission instructions can be found at: http://www.cs.cmu.edu/~conald/call.shtml Selected papers from the workshop will be considered for publication in an upcoming special issue of IEEE Expert journal. Organizers: Shumeet Baluja (baluja at jprc.com) Christos Faloutsos (christos at cs.cmu.edu) Alex Hauptmann (alex+ at cs.cmu.edu) Michael Witbrock (witbrock at jprc.com) The Conference main site is at http://www.cs.cmu.edu/~conald/ Please visit it soon. And please forward this Call to any colleagues who may be interested. --------------------------------------------------------------------- Michael Witbrock Justsystem Pittsburgh Research Center Research Scientist 4616 Henry St, Pittsburgh, PA 15213 Phone: +1 412 683 9486 Fax: +1 412 683 4175 witbrock at jprc.com http://www.justresearch.com/ From tom.ziemke at ida.his.se Tue Feb 3 08:45:24 1998 From: tom.ziemke at ida.his.se (Tom Ziemke) Date: Tue, 3 Feb 1998 14:45:24 +0100 Subject: Biologically inspired robotics - CALL FOR PARTICIPATION Message-ID: <199802031345.OAA22842@tor.ida.his.se> ----------------------------------------- Sorry if you receive this more than once ----------------------------------------- **** SELF-LEARNING ROBOTS II: BIO-ROBOTICS **** An Institution of Electrical Engineers (IEE) Seminar Savoy Place, London, UK: February 12, 1998. Co-sponsors: Royal Institute of Navigation (RIN) Biotechnology and Biological Sciences Research Council (BBSRC) British Computer Science Society (BCS) Society for the Study of Artificial Intelligence and the Simulation of Behaviour (AISB) Biologically inspired robotics or bio-robotics is an exciting trend in the integration of engineering and life sciences. Although this has a long history dating back to the turn of the century, it is only within the last few years that it has picked up momentum as many have realised that life is still the best model we have for intelligent behavior. This cross fertilisation is beginning to bear fruit in robotics within specialist areas such as evolutionary methods, artificial life, neural computing, and navigation. It is now time to bring these threads together and ask the life scientists to assess the developments and also to discuss how and what the life sciences could learn from robotics. This one-day seminar aims to bring together some of Europe's leading researchers within the areas of animal and robot behavior to discuss the foundations and future directions of biologically inspired robotics. Each Speaker will be followed by a Discussant who will follow up on some of the issues raised by in the paper and make general points about the field. 9.30-10.30 EMBODIMENT Rolf Pfeifer (Speaker) Computer Scientist and Roboticist, Switzerland. Stevan Harnad (Discussant) Psychologist, UK. 10.30-10.45 Coffee 10.45-11.45 EVOLUTIONARY LEARNING Stefano Nolfi (Speaker) Roboticist and Psychologist, Italy. Richard Dawkins (Discussant) Evolutionary Zoologist, UK. 11.45-12.45 CONDITIONED LEARNING. Marco Dorigo (Speaker) Computer Scientist and Roboticist, Belgium. Tony Savage (Discussant) Animal Psychologist, N. Ireland. 12.45-2.00 Lunch 2.00-3.00 NAVIGATION: THE INSECT MODEL Dimitrios Lambrinos (Speaker) Computer Scientist and Roboticist, Switzerland. Tom Collett (Discussant) Neurobiologist, UK. 3.00-4.00 NAVIGATION: THE MAMMALIAN MODEL Neil Burgess (Speaker) Neuroscientist, UK. Ariane Etienne (Discussant) Ethologist, Switzerland. 4.00-4.15 Tea PANEL: THE FUTURE OF BIO-ROBOTICS 4.15-5.45 Introduced and Chaired by Jean-Arcady Meyer, Computer Scientist and Ethologist, France. ORGANISERS Noel Sharkey, Computer Scientist, Psychologist, and Roboticist, University of Sheffield, UK. Tom Ziemke, Computer Scientist and Roboticist, Universities of Sheffield, UK and Skovde, Sweden. REGISTRATION It would be advisable to register as early as possible since places will be limited. Please contact Jon Maddison (IEE) at jmaddison at iee.org.uk. From Asim.Roy at asu.edu Wed Feb 4 02:16:14 1998 From: Asim.Roy at asu.edu (Asim Roy) Date: Wed, 04 Feb 1998 00:16:14 -0700 (US Mountain Standard Time) Subject: COULD THERE BE REAL-TIME, INSTANTANEOUS LEARNING IN THE BRAIN? Message-ID: I am posting this memo to various newsgroups. So my apologies if you get multiple copies. ----------------------------------------------------------- This is a summary of the responses (comments/questions) I have received so far. My sincere apologies for the long delay in posting this summary. There were a number of interesting questions and I did respond to most of the individuals directly. Since many of the questions were similar, the first part of this memo poses those common, generic questions and answers them. This is followed by the individual responses received. In the Appendix, a copy of my original memo is included for reference. I hope I have not missed any of the responses. If I did, please let me know and I will post them. There will be a panel discussion on the question "COULD THERE BE REAL-TIME, INSTANTANEOUS LEARNING IN THE BRAIN?" at the World Congress on Computational Intelligence (WCCI'98) in Anchorage, Alaska in May, 1998. I will post an announcement on this soon. The question of real-time, instantaneous learning is tied to such other classical connectionist ideas as local learning and memoryless learning. These three ideas have led the development of various brain-like learning algorithms for the last 40 to 50 years. So these open discussions are about some of the most fundamental ideas of this field. It is quite possible that we have been developing the wrong kinds of algorithms all these years. I hope more scholars from neuroscience, cognitive science and artificial neural networks will participate in these informal, open discussions and enrich this discussion. All comments/questions are welcome. Asim Roy Arizona State University ------------------------------------------------ ANSWERS TO SOME TYPICAL, GENERIC QUESTIONS (A) FIRST A CLARIFICATION OF THE NOTION OF "REAL-TIME, INSTANTANEOUS" LEARNING I think there was some confusion in my use of the term "real-time." It should have been clear from my memo that I was using the term "real-time" to refer to "Hebbian-style" instantaneous and permanent learning. Hebbian-style learning is used in such well-known algorithms as back-propagation. In Hebbian-style learning, a training example is used for some type of instantaneous adjustment to the network and then the example is discarded (so-called memoryless learning). So in Hebbian-style learning, there is no recording or retention of any particular information (a training example, that is) in the system for subsequent use. This is the style of learning generally used by all learning algorithms in the field of artificial neural networks. The key notion in Hebbian-style learning is that of "instantaneous and permanent" learning from each and every example provided. I used the term "real-time" to refer to this mode of learning. But "memory-based learning" can also be "real-time" in the sense that learning can begin as soon as some information about the problem is collected and stored. So, in that sense, learning of motor skills in the Shadmehr and Holcomb [1997] study could be considered real-time, although it was not "real-time, instantaneous" in the Hebbian-sense - the learning took about "5 to 6 hours" to complete!! Learning in "5 to 6 hours" is real-time, but not "instantaneous." If there is Hebbian-style "instantaneous" learning in the brain, learning should have been "complete" as soon as the practice session ended; it wouldn't have taken any further time after practice and not the "5 to 6 hours" it took in this case. I think most people understood my use of the term "real-time" in the way I intended, but I realize that it may have created confusion with some. "Hebbian-style learning" instead of "real-time, instantaneous" would have been a more accurate term. -------------------- (B) A CLARIFICATION OF THE DIFFERENCE BETWEEN "MEMORY" (SIMPLE RECORDING OF INFORMATION) AND "LEARNING" Several comments (by Gary Cottrell, Gale Martin, Stefan Schaal) result from confusion about the terms "memory" and "learning". In some fields (and in everyday life), the terms "memory" and "learning" are used synonymously. So some of them claim that "learning" is indeed instantaneous. However, they are actually refering to simple recording of information that was instantaneous, not to "learning" that was instantaneous. From Yves.Moreau at esat.kuleuven.ac.be Fri Feb 6 04:20:13 1998 From: Yves.Moreau at esat.kuleuven.ac.be (Yves Moreau) Date: Fri, 06 Feb 1998 10:20:13 +0100 Subject: TR: Embedding Recurrent Neural Networks into Predator-Prey Models (corrected URL) Message-ID: <34DAD5CD.C1BD086@esat.kuleuven.ac.be> Hello, A number of people have been trying to download our technical report via my home page and list of publications; they were directed to a wrong URL (the direct ftp URL itself is correct) and thought the report was not available. I have fixed this problem and you can get the technical report whichever way you like. My apologies to the other readers for the repeated posting. Best regards, Yves Moreau Yves Moreau wrote: > Dear Connectionists, > > The following technical report is available via ftp or the World Wide > Web: > > EMBEDDING RECURRENT NEURAL NETWORKS INTO PREDATOR-PREY MODELS > > Yves Moreau and Joos Vandewalle, K.U.Leuven ESAT-SISTA > > K.U.Leuven, Elektrotechniek-ESAT, Technical report ESAT-SISTA TR98-02 > ftp://ftp.esat.kuleuven.ac.be/pub/SISTA/moreau/reports/lotka_volterra_tr98-02.ps > > Comments are more than welcome! > > ABSTRACT > ======== > > We study changes of coordinates that allow the embedding of the > ordinary differential equations describing continuous-time recurrent > neural networks into differential equations describing predator-prey > models ---also called Lotka-Volterra systems. We do this by transforming > the equations for the neural network first into quasi-monomial form, > where we express the vector field of the dynamical > system as a linear combination of products of powers of the > variables. From this quasi-monomial form, we can directly > transform the system further into Lotka-Volterra equations. The > resulting Lotka-Volterra system is of higher dimension than the > original system, but the behavior of its first variables is > equivalent to the behavior of the original neural network. We expect > that this transformation will permit the application of existing > techniques for the analysis of Lotka-Volterra systems to recurrent-neural > networks. Furthermore, our result shows that Lotka-Volterra systems > are universal approximators of dynamical systems, just as > continuous-time neural networks. > > Keywords: Continuous-time neural networks, > Equivalence of dynamical systems, Lotka-Volterra systems, > Predator-prey models, Quasi-monomial forms. > > -------------------------------------------------------------- > > To get it from the World Wide Web, point your browser at: > ftp://ftp.esat.kuleuven.ac.be/pub/SISTA/moreau/reports/lotka_volterra_tr98-02.ps > > To get it via FTP: > ftp ftp.esat.kuleuven.ac.be > cd pub/SISTA/moreau/reports > get lotka_volterra_tr98-02.ps > > -------------------- > > Yves Moreau > > Department of Electrical Engineering > Katholieke Universiteit Leuven > Leuven, Belgium > > email: moreau at esat.kuleuven.ac.be > > homepage: http://www.esat.kuleuven.ac.be/~moreau > > publications: > http://www.esat.kuleuven.ac.be/~moreau/publication_list.html From postma at cs.unimaas.nl Fri Feb 6 04:50:42 1998 From: postma at cs.unimaas.nl (Eric Postma) Date: Fri, 06 Feb 1998 10:50:42 +0100 Subject: 2 Research Assistantships NNs for Image Recognition Message-ID: <1.5.4.32.19980206095042.01b29c8c@bommel.cs.unimaas.nl> 2 Research Assistantships, leading to Ph.D. The Computer Science Department of the Universiteit Maastricht in the Netherlands performs research in the field of Artificial Intelligence. The main subjects of research are Neural Networks and Multi-Agent Systems. The research group Neural Networks invites applications for two research assistantships on the research project Neural Networks for Image Recognition The candidates will develop neural-network models for the recognition of natural objects and scenes. Biological vision serves as a source of inspiration for the development of the models. The project focuses on the active selection of static and dynamic visual information through an attentive mechanism (e.g., eye movements). Applications include visual information retrieval from image databases and real-time vision in autonomous agents or robots. Both fundamental and application-oriented research will be performed. The research will be rounded off with a Ph.D. thesis. Candidates should have: - MSc in computer science, cognitive science, or related discipline, - interest in theoretical and practical research, - good programming skills (e.g., in C, C++, and/or Java), - knowledge of neural networks, preferably in relation to vision or visual recognition. Knowledge of the psychology and biology of vision will be an advantage. Applications should be sent to the administrator of the Department of Computer Science, Ms. A. Klinkers, by Email: klinkers at cs.unimaas.nl or by regular mail: Department of Computer Science, P.O. Box 616, 6200 MD Maastricht, The Netherlands. Additional information can be obtained from Eric Postma (postma at cs.unimaas.nl; +31 43 388 3493) or prof. Jaap van den Herik (herik at cs.unimaas.nl; +31 43 3883477). A salary commensurate with Ph.D. student status in the Netherlands is offered: Dfl. 2135 per month in the first year, rising to Dfl. 3812 (gross) per month in the fourth year. From weaveraj at helios.aston.ac.uk Mon Feb 9 05:25:05 1998 From: weaveraj at helios.aston.ac.uk (Andrew Weaver) Date: Mon, 09 Feb 1998 10:25:05 +0000 Subject: Studentship Available, Aston University, UK Message-ID: <29800.199802091025@sun.aston.ac.uk> Neural Computing Research Group, Aston University, Birmingham, UK We invite applications for EPSRC and Divisional PhD studentships in the following areas: * Neural Nets for Control: Advancing the Theory * Neural Networks for Affinity Ligand Synthesis * Statistical mechanics of support vector machines * Bayesian approaches to online learning * Advanced mean field methods for Bayesian learning * Analysing Brain-derived Magnetic Fields using Neural Networks * Non-linear Time Series Analysis: Characterisation by Feature Processing * Neural Network Analysis of Wake EEG * Image Understanding with Probabilistic Models Studentships are available to people of all nationalities, although the EPSRC studentships will only pay tuition fees and living expenses to UK citizens, and tuition fees only to (non-UK) EU citizens. Applicants should have, or expect to gain, a First Class or Upper Second Class Degree (or overseas equivalent) in a numerate discipline. The Research Group also has 5 EPSRC Advanced Course studentships for the MSc in Pattern Analysis and Neural Networks, further details of which are also available at the web pages below. In order to apply for these studentships you will need to complete an official Aston University application form, and should therefore send your name and address to ncrg at aston.ac.uk (subject line NCRG2 - IF YOU DO NOT USE THIS SUBJECT LINE YOU WILL NOT BE SENT THE CORRECT INFORMATION) by 9.00am on Friday 20th February 1998. Written applications should be received by Friday 27th March 1998. Details of the information required will be found in the covering letter sent with the application form. Further details of the Research Group and the topics can be found at http://www.ncrg.aston.ac.uk/ From Simon.N.CUMMING at British-Airways.com Mon Feb 9 13:08:04 1998 From: Simon.N.CUMMING at British-Airways.com (Simon.N.CUMMING@British-Airways.com) Date: 09 Feb 1998 18:08:04 Z Subject: ANNOUNCEMENT: NCAF Conference, SUNDERLAND 22-23April1998 Message-ID: <"BSC400A1 980209180759206661*/c=GB/admd=ATTMAIL/prmd=BA/o=British Airways PLC/s=CUMMING/g=SIMON/i=N/"@MHS> The purpose of the Neural Computing Applications Forum (NCAF) is to promote widespread exploitation of neural computing technology by: - providing a focus for neural network practitioners. - disseminating information on all aspects of neural computing. - encouraging close co-operation between industrialists and academics. NCAF holds four, two-day conferences per year, in the UK, with speakers from commercial and industrial organisations and universities. The focus of the talks is on practical issues in the application of neural network technology and related methods to solving real-world problems. ____________________________________________________________________ The April meeting will be hosted by The School of Computing and Information Systems on the St Peter's Campus of The University of Sunderland on Wednesday 22nd and Thursday 23rd April 1998. -------------------------------------------- the theme will be: DTI Neural Computing Guidelines. The 2 days will be packed with applications oriented papers as usual. There will also be adequate time for networking with other practitioners, during coffee, lunch and the Wednesday evening event. NCAF Conference at SUNDERLAND, UK. 22 - 23 April 1998 ====================================================== DTI Neural Computing Applications Guidelines Wednesday 22nd April 1998 ------------------------- Introduction and Welcome John MacIntyre, University of Sunderland 1hr overview: By a guest speaker to be announced Practical Assessment of Neural Network Applications Ian Nabney, Aston University Neural Networks and Error Bars David Lowe, Aston University Cracking the Code: a fully interactive workshop putting the Guidelines into practice Graham Hesketh, Rolls-Royce and Iain Strachan, AEA Technology From Project to Product, a Neural Based Cardiac Monitor Tom Harris, Brunel University Thursday 23rd April 1998 ------------------------ Robust Neural Networks with Confidence Bounds Julian Morris and Elaine Martin, University of Newcastle Neural Network Techniques for on-line Monitoring of Vigilance Mihaela Duta, Oxford University Applications of Normalised RBF nets to Robot Trajectories Learning Guido Bugmann, University of Plymouth Data Fusion in Complex Machine Monitoring Odin Taylor, University of Sunderland Neural Networks for Steam Leak Location Peter Mattison, University of Sunderland ____________________________________________________________________ Social Programme: The most widely acclaimed social event ever organised by NCAF was a visit to the Beamish Open Air Museum, so by popular demand we are visiting there again. plus Puzzle Corner: To Irradiate or Not To Irradiate - that is the question Graham 'Rottweiler' Hesketh (Rolls-Royce) ___________________________________________________________________ Attendance at the conference costs 100 pounds for non-members or 20 pounds for NCAF members. [Food, social event and accommodation not included]. NCAF MEMBERSHIP DETAILS: ------------------------ All amounts are in pounds Sterling, per annum. All members receive a quarterly newsletter and are eligible to vote at the AGM (but see note on corporate membership). Currently, membership includes a free copy of the book "A Guide to Neural Computing Applications" by Prof Lionel Tarassenko of Oxford University. (This book is on sale in bookshops for 29.99 pounds). Full (Corporate) Membership : 300 pounds (allows any number of people in the member organisation to attend meetings at member rates; voting rights are restricted to one, named, individual. Includes automatic subscription to the journal Neural Computing and Applications.) Individual Membership : 170 pounds (allows one, named, individual to attend meetings at member rates; includes journal) Associate Membership: 110 pounds: includes subscription to the journal and newsletter but does not cover admission to the meetings. Reduced (Student) Membership : 65 pounds including Journal; 30 pounds without journal. Applications for student membership should be accompanied by a copy of a current full-time student ID card, UB40, etc. ___________________________________________________________________ For registration, membership enquiries or further information please e-mail ncafsec at brunel.ac.uk or Phone Sally Francis (+44)(0)1784 477271 ___________________________________________________________________ From polzer at uran.informatik.uni-bonn.de Mon Feb 9 11:08:59 1998 From: polzer at uran.informatik.uni-bonn.de (Andreas Polzer) Date: Mon, 9 Feb 1998 17:08:59 +0100 (MET) Subject: CFP: ECCV Workshop on Learning in Computer Vision Message-ID: <199802091609.QAA08896@cornea.informatik.uni-bonn.de> We apologize if you receive multiple copies of this message. ------------------------------------------------------------ WORKSHOP ON LEARNING IN COMPUTER VISION in conjunction with ECCV '98 June 6, 1998 Freiburg, Germany Description ----------- In recent years rising computer performance has made it possible to exploit complex statistical models and to learn and estimate their parameters from an increasing amount of data. Therefore the issues of computational and statistical learning theory and Bayesian inference become more and more relevant for computer vision applications. Especially the related topics of generalization and choice of model complexity are of central importance in computer vision. Furthermore, the question of needed accuracy for optimization and parameter estimation turns out to be a closely related topic. The application of methods from statistical learning theory and neurally inspired approaches in computer vision are rather diverse and learning in computer vision is by no means a homogeneous field. But the necessity becomes more and more evident to take a more fundamental point of view and to clarify the multiple implications that the recent achievements of statistical learning theory have on computer vision problems. Statistical learning theory might have significant influence on many applications ranging from classification and statistical object recognition, grouping and segmentation to statistical field models and optimization. We are convinced that focussing on these joint aspects may yield a major contribution to the understanding and improvement of the diverse range of learning applications in computer vision. A workshop on learning in computer vision may greatly contribute to these goals. Workshop Issues --------------- The workshop will focus on the latest developments of learning in computer vision and will try to clarify to what extent statistical learning theory and Bayesian inference support computer vision applications. The workshop will present high quality oral contributions on any aspects of learning in computer vision, including but not restricted to the following topics: * Supervised Learning and its application to classification, support vector networks and model learning * Unsupervised Learning for structure detection in images * Robustness of Computer Vision algorithms and generalization * Probabilistic model estimation and selection, e.g. Bayesian inference for vision Attendance and Workshop Format ------------------------------ The workshop will consist of invited keynote talks and regular talks in one track. For submissions please send an extended abstract of 1-2 pages by March 31, 1998 to Workshop Learning in Computer Vision c/o Prof. Joachim Buhmann Institut fuer Informatik Roemerstrasse 164 D-53117 Bonn Germany In case of more submissions than available time slots a selection will be made based on a peer review of the submissions by the program committee. Venue ----- The workshop will be held in Freiburg, Germany on June 6, 1998 in conjunction with the European Conference on Computer Vision (ECCV '98). Program Committee ----------------- * Joachim M. Buhmann, Chair (University of Bonn, Germany) * Andrew Blake (University of Oxford, UK) * Jitendra Malik (UC Berkeley, USA) * Tomaso Poggio (MIT, USA) * Daphna Weinshall (Hebrew University, Israel) Local Organization: Andreas Polzer, Jan Puzicha (University of Bonn) To obtain further information please contact: WWW: http://www-dbv.cs.uni-bonn.de/learning.html e-mail: jan at cs.uni-bonn.de From elmar.steurer at dbag.ulm.DaimlerBenz.COM Wed Feb 11 10:25:02 1998 From: elmar.steurer at dbag.ulm.DaimlerBenz.COM (Elmar Steurer) Date: Wed, 11 Feb 1998 16:25:02 +0100 Subject: please include this CFP to your mailing list Message-ID: <34E1C2CE.51F6@dbag.ulm.DaimlerBenz.com> Call for Papers Workshop: Application of Machine Learning and Data Mining in Finance 10th European Conference on Machine Learning (ECML-98) Chemnitz, Germany, April 24 1998 General Information In conjunction with the 10th European Conference on Machine Learning (ECML-98) the workshop "Application of Machine Learning and Data Mining in Finance" will be held in Chemnitz, Germany, on April, 24th 1998. The main conference takes place from April, 21st to 23rd 1998. Motivation Advanced data analysis and forecasting technologies such as neural networks, symbolic machine learning and genetic algorithms are being increasingly applied to support financial asset management and credit risk management. These methods are considered by many financial management institutions as innovative technologies to support conventional quantitative techniques. Their use in computational finance will have a major impact in the modelling of the currency markets, in tactical asset allocation, bond and stock valuation and portfolio optimisation. In addition the application of these tools for scoring tasks delivers valuable support for the management of client credit risk. Targets This workshop is designed to bring together researchers in the field of Machine Learning with those practicing financial consulting. The purpose is twofold: - Practitioners should become familiar with the state of the art in machine learning research for predictive modelling and scoring systems. - The research community should receive ideas and requirements from participants from the financial world with the aim to improve the acceptance of Machine Learning applications and to identify future areas of research. Research papers representing new and significant developments in methodology as well as applications of practical use will be presented. Topics include: Application aspects: - Scoring systems: Application and Behavioural Scoring - Trading- and forecasting models - Volatility models - Value at Risk - Financially motivated objective functions Methodological aspects: - Symbolic Learning in financial engineering - Neural Networks for financial applications - Aspects and dependencies of data transformation and model selection - Backtest procedures: Advantages and bottlenecks - Pre-testing as an alternative to backtest - Data Mining process model for financial applications Submission of papers Authors wishing to present a paper should send an electronic version (uuencoded compressed PostScript) not later than 28 February 98 to: Dr. Elmar Steurer DAIMLER-BENZ AG - Research and Technology Postfach 2360 89013 Ulm Tel.: 0049 - 731 / 505 -2868 Fax: 0049 - 731 / 505 4210 Email: elmar.steurer at dbag.ulm.DaimlerBenz.COM Accepted papers will be published in the workshop notes. Selected papers will be issued in a proceedings. Contributors will be allocated 20 minutes for an oral presentation during the workshop. Further invited talks and a panel discussion are planned. Program committee: Ulrich Anders University of Otago, Dunedin, New Zealand Jeremy H. Armitage State Street Bank and Trust Company, London, UK Dirk Baestens Generale Bank, Brussels, Belgium Georg Bol University of Karlsruhe, Germany Guenter Grimm allfonds, Munich, Germany Tae H. Hann University of Karlsruhe, Germany Ashar Mahboob Fuji Capital Markets Corporation, New York, USA Andreas Weigend STERN Business School, New York University, USA Apostolos N. Refenes London Business School, UK Andrea Sczesny ZEW Mannheim, Germany Charles Taylor University of Leeds, UK Diethelm Wuertz ETH, Zurich, Switzerland Hans-Georg Zimmermann Siemens AG, Munich, Germany Important Dates: Submission deadline: 28 February 1998 Notification of acceptance: 15 March 1998 Camera ready copy: 28 March 1998 Workshop: 24 April 1998 Organization: Gholamreza Nakhaeizadeh and Elmar Steurer DAIMLER-BENZ AG - Research and Technology e-mail: nakhaeizadeh at dbag.ulm.DaimlerBenz.COM elmar.steurer at dbag.ulm.DaimlerBenz.COM Registration and further information: For further information about the main conference and registration please contact: ecml98 at lri.fr ecml98 at informatik.tu-chemnitz.de or visit the web site: http://www.tu-chemnitz.de/informatik/ecml98 From nnesmed at DI.Unipi.IT Wed Feb 11 11:35:33 1998 From: nnesmed at DI.Unipi.IT (Tonina Starita) Date: Wed, 11 Feb 1998 17:35:33 +0100 (MET) Subject: Final Call NNESMED`98 (Extended Deadline) Message-ID: <199802111635.RAA00554@neuron.di.unipi.it> * * * E X T E N D E D D E A D L I N E: February 27 * * * FINAL CALL FOR PAPERS 3rd International Conference on Neural Networks and Expert Systems in Medicine and Healthcare NNESMED '98 Pisa, Italy,2-4 September 1998 http://www.di.unipi.it/~nnesmed/home.htm NNESMED '98 is organised by the Computer Science Department of the University of Pisa Conference Chair: Professor Starita, University of Pisa Conference Co-Chairs: Professor Ifeachor, University of Plymouth Professor Simi University of Pisa Keynote Speakers Dr Lee Giles (USA) University of Princeton Professor Mario Stefanelli (Italy) University of Pavia Professor Paulo Lisboa (UK) Liverpool John Moores University Programme/Advisory Committee Dr Lee Giles (USA) Professor Marco Gori (Italy) Professor Emmanuel Ifeachor (UK) Dr Barrie Jervis (UK) Professor Marzuki Khalid (Malaysia) Professor Priklis Ktonas (USA) Professor Paulo Lisboa (UK) Professor George Papadurakis (Greece) Professor Karl Rosen (Sweden) Professor Maria Simi (Italy) Dr Alessandro Sperduti (Italy) Professor Mario Stefanelli (Italy) Professor Hiroshi Tanaka (Japan) Professor John Taylor (UK) Topics Neural Networks Expert Systems Soft Computing Hybrid Systems Signal Processing Fuzzy Logic Knowledge Bases DataMining Deductive Reasoning Telemedicine Tools and Applications Scope NNESMED '98 is organised by the Computer Science Department of the University of Pisa and it will be held in Pisa, on September 2-4 1998. It will provide a forum for the presentation of the results of ongoing works and research in the field of the Neural Networks and Expert Systems in Medicine and Healthcare. NNESMED '98 will be the third edition of this series and it will promote the exchange of ideas and experiences among researchers from the AI communities in medical field. Pisa is well connected to the rest of Europe by its international airport and good road and rail links. Paper submission The submission deadline is ** EXTENDED **: February 27, 1998. Papers must not exceed 4 pages, they must be written in English, with a cover page containing: * a 200-word abstract * keywords * postal and electronic mailing address * phone and fax number of the first author Submission will be electronic and available via the conference web site. Authors will be notified of the acceptance (oral and/or poster session) or rejection of their papers by May 1, 1998. Additional Information http://www.di.unipi.it/~nnesmed/home.htm e_mail: nnesmed at di.unipi.it Tel: +39-50-887215/ +39-50-887249 Fax: +39-50-887226 From priel at mail.biu.ac.il Thu Feb 12 10:02:30 1998 From: priel at mail.biu.ac.il (Avner Priel) Date: Thu, 12 Feb 1998 17:02:30 +0200 (WET) Subject: paper on time series generation Message-ID: The following paper on the subject of time series generation by feed-forward networks has appeared on the Journal of Physics A 31(4) 1189 (1998). The paper is available from my home-page : http://faculty.biu.ac.il/~priel/ comments are welcome. *************** NO HARD COPIES ****************** ---------------------------------------------------------------------- Noisy time series generation by feed-forward networks ----------------------------------------------------- A Priel, I Kanter and D A Kessler Department of Physics, Bar Ilan University, 52900 Ramat Gan,Israel ABSTRACT: We study the properties of a noisy time series generated by a continuous-valued feed-forward network in which the next input vector is determined from past output values. Numerical simulations of a perceptron-type network exhibit the expected broadening of the noise-free attractor, without changing the attractor dimension. We show that the broadening of the attractor due to the noise scales inversely with the size of the system ,$N$, as $1/ \sqrt{N}$. We show both analytically and numerically that the diffusion constant for the phase along the attractor scales inversely with $N$. Hence, phase coherence holds up to a time that scales linearly with the size of the system. We find that the mean first passage time, $t$, to switch between attractors depends on $N$, and the reduced distance from bifurcation $\tau$ as $t = a {N \over \tau} \exp(b \tau N^{1/2})$, where $b$ is a constant which depends on the amplitude of the external noise. This result is obtained analytically for small $\tau$ and confirmed by numerical simulations. ---------------------------------------------------- Priel Avner < priel at mail.biu.ac.il > < http://faculty.biu.ac.il/~priel > Department of Physics, Bar-Ilan University. Ramat-Gan, 52900. Israel. From omori at cc.tuat.ac.jp Thu Feb 12 23:32:28 1998 From: omori at cc.tuat.ac.jp (Takashi Omori) Date: Fri, 13 Feb 1998 13:32:28 +0900 Subject: Call for Paper : ICONIP'98-Kitakyushu Message-ID: <01BD3883.D43B76E0@BRAIN> ----------------------------------------- Sorry if you receive this more than once ----------------------------------------- For your remind of ICONIP'98-Kitakyushu. The dead line is March 31-st, 1998. Please refer http://jnns-www.okabe.rcast.u-tokyo.ac.jp/jnns/ICONIP98.html for latest information. The Fifth International Conference on Neural Information Processing (ICONIP'98) October 21-23,1998 Kitakyushu International Conference Center 3-9-30 Asano, Kokura-ku, Kitakyushu 802, Japan Organized by Japanese Neural Network Society (JNNS) Sponsored by Asian Pacific Neural Network Assembly (APNNA) The annual conference of the Asian Pacific Neural Network Assembly, ICONIP'98, will be held jointly with the ninth annual conference of Japanese Neural Network Society, from 21 to 23 October 1998 in Kitakyushu, Japan. The goal of ICONIP'98 is to provide a forum for researchers and engineers from academia and industries to meet and to exchange ideas on advanced techniques and recent developments in neural information processing. The conference further serves to stimulate local and regional interests in neural information processing and its potential applications to industries indigenous to this region. Topics of Interest Track$B-5(J: Neurobiological Basis of Brain Functions(J Track$B-6(J: Mathematical Theory of Brain Functions(J Track$B-7(J: Cognitive and Behavioral Aspects of Brain Functions(J Track$B-8(J: Theoretical and Technical Aspects of Neural Networks(J Track$B-9(J: Distributed Processing Systems(J Track$B-:(J: Applications of Neural Networks(J Track$B-;(J: Implementations of Neural Networks(J Topics cover (Key Words): Neuroscience, Neurobiology and Biophysics, Learning and Plasticity, Sensory and Motor Systems, Cognition and Perception Algorithms and Architectures, Learning and Generalization, Memory, Neurodynamics and Chaos, Probabilistic and Statistical Methods, Neural Coding Emotion, Consciousness and Attention, Visual and Auditory Computation, Speech and Languages, Neural Control and Robotics, Pattern Recognition and Signal Processing, Time Series Forecasting, Blind Separation, Knowledge Acquisition, Data Mining, Rule Extraction Emergent Computation, Distributed AI Systems, Agent-Based Systems, Soft Computing, Real World Systems, Neuro-Fuzzy Systems Neural Device and Hardware, Neural and Brain Computers, Software Tools, System Integration Conference Committee Conference Chair: Kunihiko Fukushima, Osaka University Conference Vice-chair: Minoru Tsukada, Tamagawa University Organizing Chair: Shuji Yoshizawa, Tokyo University Program Chair: Shiro Usui, Toyohashi University of Technology International Advisory Committee (tentative) Chair: Shun-ichi Amari, Institute of Physical and Chemical Research Members: S. Bang (Korea), J. Bezdek (USA), J. Dayhoff (USA), R. Eckmiller (Germany), W. Freeman (USA), N. Kasabov (New Zealand), H. Mallot (Germany), G. Matsumoto (Japan), N. Sugie (Japan), R. Suzuki (Japan), K. Toyama (Japan), Y. Wu (China), L.Xei (Hong Kong), J. Zurada (USA) Call for paper The Program Committee is looking for original papers on the above mentioned topics. Authors should pay special attention to explanation of theoretical and technical choices involved, point out possible limitations and describe the current states of their work. All received papers will be reviewed by the Program Committee. The authors will be informed about the decision of the review process by June 22, 1998. All accepted papers will be published. As the conference is a multi-disciplinary meeting the papers are required to be comprehensible to a wider rather than to a very specialized audience. Instruction to Authors Papers must be received by March 31, 1998. The papers must be submitted in a camera-ready format. Electronic or fax submission is not acceptable. Papers will be presented at the conference either in an oral or in a poster session. Please submit a completed full original pages and five copies of the paper written in English, and backing material in a large mailing envelope. Do not fold or bend your paper in any way. They must be prepared 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. Centered at the top of the first page should be the complete title, author(s), mailing and e-mailing addresses, followed by 100-150 words abstract and the text. Extra 2 pages are permitted with a cost of 5000 yen/page. Use black ink. Do not use any other color, either in the text or illustrations. The proceedings will be printed with black ink on white paper. In the covering letter the track and the topic of the paper according to the list above should be indicated. No changes will be possible after submission of your manuscript. Authors may also retrieve the ICONIP style "iconip98.tex", "iconip98.sty" and "sample.eps" files (they are compressed as form.tar.gz) for the conference via WWW at URL http://jnns-www.okabe.rcast.u-tokyo.ac.jp/jnns/ICONIP98.html. Language The use of English is required for papers and presentation. No simultaneous interpretation will be provided. Registration The deadline for Registration for speakers and Early Registration for non-speakers with remittance will be July 31, 1998. The registration fee for General Participant includes attendance to the conference, proceedings, banquette and reception. The registration fee for Student includes attendance to the conference and proceedings. Conference Venue Kitakyushu is a northern city in Kyushu Island, south west of Japan main islands. The place is one of the Japanese major industrial areas, and also has long history of two thousand years in Japanese and Chinese ancient records. There are direct flights from Asian and American major airports. You will be able to enjoy some technical tours and excursion in the area. Passport and Visa All foreign attendants entering Japan must possess a valid passport. Those requiring visas should apply to the Japanese council or diplomatic mission in their own country prior to departure. For details, participants are advised to consult their travel agents, air-line reservation office or the nearest Japanese mission. Events Exhibition, poster sessions, workshops, forum will be held at the conference. Two satellite workshops will be held just before or after the conference. Social Events Banquette, reception and excursion will be held at the conference. The details will be announced in the second circular. Workshops Two satellite workshops will be held. One is "Satellite workshop for young researcher on Information processing" that will be held after the conference. The detail is announced in the attached paper. Another workshop "Dynamical Brain" is under programming. This will take place in Brain Science Research Center, Tamagawa University Research Institute. The details will be announced in the Second Circular. Please see second circular for more information on these workshops, and possibly other new ones. Important Dates for ICONIP'98 Papers Due: March 31, 1998 Notification of Paper Acceptance: June 22, 1998 Second Circular (with Registration Form): June 22, 1998 Registration of at least one author of a paper: July 31, 1998 Early Registration: July 31, 1998 Conference: October 21-23, 1998 Workshop: October 24-26, 1998 Further Information & Paper Submissions ICONIP'98 Secretariat Mr. Masahito Matsue Japan Technical Information Service Sogo Kojimachi No.3 Bldg. 1-6 Kojimachi, Chiyoda-ku, Tokyo 102, Japan Tel:+81-3-3239-4565 Fax:+81-3-3239-4714 E-mail: jatisc at msn.com $B!y(J Could you suggest your friends and acquaintances who will be interested (J in ICONIP'98-Kitakyushu? Thank you. ---------------------------------------------------------------------------- - ICONIP'98-Kitakyushu 21-23 October, 1998 Tentative Registration (PLEASE PRINT) Name: Professor Dr. Ms. Mr. Last Name First Name Middle Name Affiliation: Address: Country: Telephone: Fax: E-mail: $B""(J I intend to submit a paper.(J The tentative title of my paper is: $B""(J I intend to attend the conference.(J $B""(J I want to receive the Second Circular.(J Please mail a copy of this completed form to: ICONIP'98 Secretariat Mr. Masahito Matue Japan Technical Information Service Sogo Kojimachi No.3 Bldg. 1-6 Kojimachi, Chiyoda-ku, Tokyo 102, Japan Tel:+81-3-3239-4565 Fax:+81-3-3239-4714 E-mail: jatisc at msn.com ************************************************** * Takashi Omori, Ph.D * * BASE: Biologocal Applications & Systems Engineering * * Tokyo University of Agriculture & Technology * Nakacho 2-24-16 , Koganei, Tokyo 184 Japan * +81-423-88-7148 FAX:+81-423-85-5395 * omori at cc.tuat.ac.jp ************************************************************** From jls at cs.man.ac.uk Fri Feb 13 11:17:37 1998 From: jls at cs.man.ac.uk (Jon Shapiro) Date: Fri, 13 Feb 1998 16:17:37 GMT Subject: Lectureship in Modelling of Living/Organic Systems and Information Systems Message-ID: <199802131617.QAA07007@rdf074.cs.man.ac.uk.> Hi, We are seeking applicants for an opening in the Computer Science Department at Manchester University for a Lecturer in Modelling of Living/Organic Systems and Information Systems. This is equivalent to a tenure-track Assistant Professor position in the U.S. Closing date is 28 February 1998. Please pass this on to any researcher you think might be interested. For more information, look at http://www.cs.man.ac.uk, or contact Professor John Gurd (jrg at cs.man.ac.uk). Thanks, Jonathan Shapiro ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Department of Computer Science University of Manchester A Research-Led Expansion in Computer Science has led to the establishment of the following posts: Chair in Formal Methods for Computing Science Chair and 2 Lectureships in Mobile Systems Architecture 3 Lectureships in Modelling and Simulation: Lectureships in Process Modelling and Information Engineering, Modelling of Living/Organic Systems and Information Systems. 50 Years after the first stored-program electronic digital computer was developed at the University of Manchester, the Department of Computer Science at Manchester remains a world leader in research and teaching in Computer Science. We are looking to appoint staff with international research reputation or potential. These new posts offer individuals with appropriate experience an opportunity to contribute to world leading research developments from a position of strength. See our Web Page http://www.cs.man.ac.uk for further details. From SaadE at TTACS.TTU.EDU Fri Feb 13 16:29:10 1998 From: SaadE at TTACS.TTU.EDU (Emad William Saad) Date: Fri, 13 Feb 1998 15:29:10 -0600 Subject: Explanation Capability of Neural Networks Message-ID: <34E4BB26.D086E4EE@ttu.edu> I have been doing litterature search on the subject of "Explanation Capability of Neural Networks/ Rule extraction of NN's", and came with the following bibliography: [1] Fu, Y., ?Data mining: Tasks, techniques and applications,? Potentials, vol. 16, no. 4, pp. 18-20, 1997. [2] Andrews, R., Diederich, J., and Tickle, A., ?A Survey and Critique of Techniques for Extracting Rules from Trained Artificial Neural Networks,? Knowledge-Based Systems, vol. 8, no. 6, pp. 373-389, 1996. [3] Benitez, J. M., Castro, J. L., and Requena, I., ?Are Artificial Neural Networks Black Boxes?,? IEEE Trans. Neural Networks, vol. 8, no. 5, pp. 1156-1164, 1997. [4] Tsukimoto, H., ?Extracting Propositions from Trained Neural Networks,? in Proc. IEEE International Conference on Neural Networks, August 1997. [5] Kindermann, J., and Linden, A., ?Detection of Minimal Microfeatures by Internal Feedback,? in Proc. fifth Austrian Artificial Intelligence Meeting, pp. 230-239, 1989. [6] Healy, M. J., and Caudell, T. P., ?Acquiring Rule Sets as a Product of Learning in a Logical Neural Architecture,? IEEE Trans. Neural Networks, vol. 8, no. 3, pp. 461-474, 1997. [7] Yeung, D. S., and Hak-shun, Fong, "Knowledge Matrix - An Explanation and Knowledge Rrefinement Facility for a Rule Induced Neural Network," in Proc. Twelfth National Conference on Artificial Intelligence, 1994, vol. 2, pp. 889-894. [8] Machado, R. J., and da Rocha, A. F., "Inference, Inquiry, Evidence Censorship, and Explanation in Connectionist Expert Systems," IEEE Trans. Fuzzy Systems, vol. 5, no. 3, pp 443-459. [9] Gilstrap, L. O., and Dominy, R. E., "A General Explanation and Interogation System for Neural Networks," in Proc. International Joint Conference on Neural Networks, Washington, DC, June 1989, vol. 2, pp. 594. [10] Taha, I., and Ghosh, J., "Evaluation and Ordering of Rules Extracted from Feedward Networks," in Proc. IEEE International Conference on Neural Networks, Houston, TX, June 1997, vol. 1, pp. 408-413. [11] Ornes, C., and Sklansky, J., "A Neural Network that Explains as Well as Predicts Financial Market Behavior," in Proc. IEEE/IAFE Computational Intelligence for Financial Engineering, March 1997, pp. 43-49. [12] Ornes, C., and Sklansky, J., "A Visual Multi-Expert Neural Classifier," in Proc. IEEE International Conference on Neural Networks, June 1997, vol. 3, pp. 1448-1453. [13] Taha, I., and Ghosh, J., "Three techniques for extracting rules from feedforward networks," in Intelligent Engineering Systems Through Artificial Neural Networks, vol. 6., ASME Press, November 1996. Please, I would be glad if anybody can guide me to more litterature/ web pages/ resources in this area. Emad Saad Applied Computational Intelligence Laboratory Dept. of Electrical Eng. Texas Tech University, Lubbock, TX 79409 From kr10000 at eng.cam.ac.uk Mon Feb 16 05:46:34 1998 From: kr10000 at eng.cam.ac.uk (K. Reinhard) Date: Mon, 16 Feb 1998 10:46:34 GMT Subject: Announcement of Technical Report availability. Message-ID: <199802161046.11893@opal.eng.cam.ac.uk> The following technical report is available by anonymous ftp from the archive of the Speech, Vision and Robotics Group at the Cambridge University Engineering Department (http://svr-www.eng.cam.ac.uk/reports/index-full.html). PARAMETRIC SUBSPACE MODELING OF SPEECH TRANSITIONS K. Reinhard and M. Niranjan Technical Report CUED/F-INFENG/TR.308 Cambridge University Engineering Department Trumpington Street, Cambridge CB2 1PZ U.K., England Abstract This report describes an attempt at capturing segmental transition information for speech recognition tasks. The slowly varying dynamics of spectral trajectories carries much discriminant information that is very crudely modelled by traditional approaches such as HMMs. In approaches such as recurrent neural networks there is the hope, but not the convincing demonstration, that such transitional information could be captured. The method presented here starts from the very different position of explicitly capturing the trajectory of short time spectral parameter vectors on a subspace in which the temporal sequence information is preserved. We approach this by introducing a temporal constraint into the well known technique of Principal Component Analysis. On this subspace, we attempt a parametric modelling of the trajectory, and compute a distance metric to perform classification of diphones. We use the principal curves method of Hastie and Stuetzle and the Generative Topographic map (GTM) technique of Bishop, Svenson and Williams to describe the temporal evolution in terms of latent variables. On the difficult problem of /bee/, /dee/, /gee/ we are able to retain discriminatory information with a small number of parameters. Experimental illustrations present results on ISOLET and TIMIT database. From robbie at hiki.bcs.rochester.edu Mon Feb 16 12:52:32 1998 From: robbie at hiki.bcs.rochester.edu (Robbie Jacobs) Date: Mon, 16 Feb 1998 12:52:32 -0500 Subject: postdoc position available Message-ID: <199802161752.MAA14907@hiki.bcs.rochester.edu> Postdoctoral Fellowship, Department of Brain and Cognitive Sciences, UNIVERSITY OF ROCHESTER -- The Department of Brain and Cognitive Sciences seeks an outstanding postdoctoral fellow with research interests in the areas of learning and/or developmental cognitive science. Supervising faculty work on the problems of learning and development using behavioral, computational, and neurobiological approaches. Candidates should have prior background/training in at least one of these approaches and an interest in working collaboratively in a highly interdisciplinary setting. Several faculty have special interest in statistical learning in the domains of language and perception, although a commitment to this interest is not a requirement of all applicants. This fellowship is open only to US citizens or permanent residents. Applicants should send a letter describing their graduate training and research interests, a curriculum vitae, and arrange to have three letters of recommendation sent to: Learning, Development, and Biology Training, Department of Brain and Cognitive Sciences, Meliora Hall, University of Rochester, Rochester, NY 14627-0268. Review of applications will begin on April 1, 1998 and continue until the position is filled, with an expected start date of August/September, 1998. Applicants can learn about the department, its faculty, and the opportunities for training by referring to our Web page (http://www.bcs.rochester.edu). Applications from women and members of underrepresented minority groups are especially welcome. The University of Rochester is an Equal Opportunity Employer. From eugene at engr.uconn.edu Mon Feb 16 08:48:18 1998 From: eugene at engr.uconn.edu (Eugene Santos) Date: Mon, 16 Feb 1998 08:48:18 -0500 Subject: [CFP] AI Meets the Real World '98 Lessons Learned! Message-ID: <199802161348.IAA11288@ultra9.uconn.edu> [Sorry if you get this message more than once! It is being posted to several distribution lists.] ------------------------------------------------------------------------------- ------------------------------------------------------------------------------- AI meets the Real World '98 Lessons Learned C a l l f o r P a r t i c i p a t i o n September 16 - 18, 1998 University of Connecticut -- Stamford Campus Stamford, CT Sponsored by: University of Connecticut Honeywell Technology Center US Air Force Research Labs -- Phillips Lab DARPA To a large and growing extent, techniques from the field of Artificial Intelligence are being applied in the implementation of fielded systems addressing practical problems in a wide range of domains, from manufacturing, to consumer services, to military and spacecraft operations, to name a very few. As a result, an informal and pragmatic practice of "AI engineering" has arisen, involving the identification, adaptation, and application of techniques including diagnostic systems, trend analysis and projection, uncertain reasoning and decision analysis, virtual environments/reality, training and tutoring systems, planning and scheduling, natural language parsing and generation, and parameter estimation and other forms of learning. The resulting systems range from large-scale, stand-alone intelligent systems, to embedded knowledge bases, to minor components of much larger applications. As one might expect from a body of work largely developed within a common intellectual and philosophical tradition, what we have here broadly termed "AI techniques" have some common features. These approaches tend to be complex and computationally intensive and to require a great deal of understanding and modelling, in some cases engineering, of the target domain and application for the approach to be successful. The aim of this meeting is to bring together researchers, practitioners, and developers of intelligent systems throughout academia, industry, and government to discuss and disseminate lessons learned from successful (or unsuccessful) attempts to design, construct, field, and maintain intelligent systems. The meeting will consist of presentations, panel discussions, and invited speakers. Our hope is to build a better knowledge base of how to successfully apply and correctly use artificial intelligence in real world systems. This meeting is not intended as a forum for those who already deeply immersed in AI. We particularly welcome people who are considering an AI-based approach to their problem to attend and participate in these discussions. We invite the submission of papers and topic ideas for panel discussions. Papers and presentations should be based on systems developed (or in progress) for real world use. Among the issues that might be of interest in such a presentation we would expect to find the following: -- What characteristics of the domain and the application lead to your choice of solution method? What alternative methods were considered and rejected? Were these choices revisited (and revised?) at some later point? -- What difficulties did you encounter? Which ones were expected? Unexpected? -- What was the final outcome? What qualifications or modifications of the original statement of the problem or system requirements were made? -- What lessons can be drawn from this experience, regarding: +++ domains where particular AI techniques are or aren't useful? +++ how to go about determining the utility of a technique in a new domain? +++ pitfalls to beware in system design, implementation, etc., that are peculiar to intelligent systems? We are also especially INTERESTED in soliciting questions/issues at all levels from both new and experienced systems builders on problems and approaches of using AI. Members of our program committee will attempt to answer and/or provide advice to these questions. These will be published in our printed proceedings. Of these, a select set of questions or general class of questions will be chosen for a special panel discussion session at the conference. Up-to-date meeting information will be provided at: http://www.eng2.uconn.edu/~eugene/AIMTRW Proceedings of invited papers will be published. ---------------- | Organizers | ---------------- Meeting Co-Chairs - ----------------- Eugene Santos, Jr. (University of Connecticut -- Storrs) Mark Boddy (Honeywell Technology Center, Minneapolis, MN) Doug Dyer (DARPA) Program Committee - ----------------- Sheila B. Banks (Air Force Institute of Technology) Piero Bonissone (GE) Jack Breese (Microsoft) Wray Buntine (Ultimode) Fabio Cozman (University of Sao Paulo) Bruce D'Ambrosio (Prevision & Oregon State University) Neal Glassman (Air Force Office of Scientific Research) James Hendler (University of Maryland) Chahira Hopper (Air Force Research Labs, Wright Lab) Lewis Johnson (University of Southern California) F. Alex Kilpatrick (Air Force Research Labs, Phillips Lab) Michael B. Leahy Jr. (DARPA) Claudia M. Meyer (NASA LERC) Alan L. Meyrowitz (Naval Research Laboratory) Doug Moran (SRI) Steve Rogers (Battelle) Solomon Eyal Shimony (Ben Gurion University of the Negev) Mike Shneier (Office of Naval Research) Valerie J. Shute (Air Force Research Labs, Armstrong Lab) Douglas Smith (Kestrel Institute) Martin R. Stytz (Air Force Institute of Technology) Abraham Waksman (Air Force Office of Scientific Research) Fred A. Watkins (Hyperlogic) Edward Wong (Polytechnic University) --------------------------- | Submission Guidelines | --------------------------- Authors should submit full papers addressing the above issues with a strong emphasis on "lessons learned." These will be evaluated for clarity of presentation and significance of contribution to the community. All accepted papers will be presented either orally or through a poster session and will be made available in a printed proceedings. Papers may be submitted either electronically or in hard copy form. Electronic submission may take the form of PostScript files, ASCII, or LaTeX files. Authors should be careful to include all macro files necessary for LaTeX files as we will not be responsible for files which cannot be formatted. Figures for LaTeX should be PostScript files. Hardcopy submissions should have 1-inch margins on all sides and should be in 12-point type. Papers should be a maximum of 20 pages long, including figures and references. Names, address, and e-mail of authors and an abstract should be included at the beginning of each paper. Hard copy submissions must arrive by May 15, 1998, and sent to Eugene Santos, Jr. [ATTN: AIMTRW-98] Computer Science and Engineering Department University of Connecticut UTEB, 191 Auditorium Rd., U-155 Storrs, CT 06269-3155 (860) 486-1458 Electronic submissions should be e-mailed by May 15, 1998, to eugene at eng2.uconn.edu Papers not meeting the deadline will not be considered. Proposals for panel discussions and invited speakers should be e-mailed by May 15, 1997, to the above address. For questions/issues, we solicit up to two (2) pages per question. Provide as much detail as possible for proper evaluation of the question by the program committee. We prefer electronic submissions to the above email address. Hard copy is welcome to the above address. These are also due May 15, 1998. ++++++++++++++++++++++++++++++++++++++ !++Meeting Attendance/Participation++! ++++++++++++++++++++++++++++++++++++++ Due to the limited space available for this meeting, we request that those planning to attend send an e-mail by May 1, 1998 to eugene at eng2.uconn.edu stating your intent and whether you will be also submitting a paper. --------------------- | Important Dates | --------------------- May 1, 1998 Deadline for participation request May 15, 1998 Deadline for paper submission May 15, 1998 Deadline for question submission May 15, 1998 Deadline for panel proposals, etc. June 15, 1998 Notification of acceptance or rejection June 29, 1998 Final camera-ready papers due September 16 - 18, 1998 Meeting dates From kirchmai at informatik.tu-muenchen.de Mon Feb 16 09:39:59 1998 From: kirchmai at informatik.tu-muenchen.de (Clemens Kirchmair) Date: Mon, 16 Feb 1998 15:39:59 +0100 (MET) Subject: Early registration deadline for FNS'98: 02/18/1998 Message-ID: ######################################################################### ATTENTION: The early registration deadline for the FNS '98 Workshop is Wednesday, February 18th, 1998. You can still save 100,- DM if you register now! Don't miss this excellent workshop! (Full program -- see below) The 5th International Workshop "Fuzzy-Neuro Systems '98 - Computational Intelligence" takes place in Munich, Germany, from March 19 to 20, 1998. Visit our WWW Homepage: http://wwwbrauer.informatik.tu-muenchen.de/~fns98/ Conference fees (registration UNTIL February 18th) industry rate: 495,- DM university rate: 345,- DM GI members: 295,- DM students (up to age of 26): 60,- DM (excluding proceedings and conference dinner.) Conference fees (registration AFTER February 18th) industry rate: 595,- DM university rate: 445,- DM GI members: 395,- DM students (up to age of 26): 160,- DM (excluding proceedings and conference dinner.) ######################################################################### ---------------------------------- | Fuzzy-Neuro Systems '98 | | - Computational Intelligence - | | | | 5th International Workshop | | March, 19 - 20, 1998 | ---------------------------------- Technische Universitaet Muenchen Gesellschaft fuer Informatik e.V. Fachausschuss 1.2 "Inferenzsysteme" Technische Universitaet Muenchen Institut fuer Informatik Fuzzy-Neuro Systems '98 is the fifth event of a well established series of workshops with international participation. Its aim is to give an overview of the state of art in research and development of fuzzy systems and artificial neural networks. Another aim is to highlight applications of these methods and to forge innovative links between theory and application by means of creative discussions. Fuzzy-Neuro Systems '98 is being organized by the Technical Committee 1.2 "Inference Systems" (Fachausschuss 1.2 "Inferenzsysteme") of the German Informatics Society GI (Gesellschaft fuer Informatik e. V.) and Institut fuer Informatik, Technische Universitaet Muenchen in cooperation with Siemens AG and with the support of Kratzer Automatisierung GmbH. The workshop takes place at the Technische Universitaet Muenchen in Munich from March, 19 to 20, 1998. PROGRAM ------- Wednesday, March 18, 1998 18:00 Informal Get-Together Registration 21:00 End of reception and registration Thursday, March 19, 1998 8:00 Registration 9:00 Formal Opening President, TU Muenchen Dekan, Institut fuer Informatik, TU Muenchen Workshop Chair 9:15 Invited Lecture 1: Sets, Fuzzy Sets and Rough Sets Zdzislaw Pawlak, Warsaw University of Technology, Poland Chairman: W. Brauer, TU Muenchen 10:00 Session 1: Fuzzy Control Chairman: R. Isermann, TU Darmstadt Indirect Adaptive Sugeno Fuzzy Control J. Abonyi, L. Nagy, S. Ferenc, University of Veszprem, Veszprem, Hungary Simultaneous Creation of Fuzzy Sets and Rules for Hierarchical Fuzzy Systems R. Holve, FORWISS, Erlangen, Germany 10:50 Coffee break - Presentation of Posters 11:10 Session 2: Neural Networks for Classification Chairman: K. Obermayer, TU Berlin Hybrid Systems for Time Series Classification C. Neukirchen, G. Rigoll, Gerhard-Mercator-Universitaet, Duisburg How Parallel Plug-in Classifiers Optimally Contribute to the Overall System W. Utschick, J.A. Nossek, TU Muenchen 12:00 Invited Lecture 2: Is Readibility Compatible with Accuracy? Hugues Bersini, Universite Libre de Bruxelles, Belgium Chairman: J. Hollatz, Siemens AG, Muenchen 12:45 Lunch 14:00 Session 3: Fuzzy Logic in Data Analysis Chairman: C. Freksa, Universitaet Hamburg Fuzzy Topographic Kernel Clustering T. Graepel, K. Obermayer, TU Berlin Dynamic Data Analysis: Similarity Between Trajectories A. Joentgen, L. Mikenina, R. Weber, H.-J. Zimmermann, RWTH Aachen Spatial Reasoning with Uncertain Data Using Stochastic Relaxation R. Moratz, C. Freksa, Universitaet Hamburg Noise Clustering For Partially Supervised Classifier Design C. Otte, P. Jensch, Universitaet Oldenburg Fuzzy c-Mixed Prototypes Clustering C. Stutz, TU Muenchen T.A. Runkler, Siemens AG, Muenchen 16:00 Coffee break - Presentation of Posters 16:30 Invited Lecture 3: Neural Network Architectures for Time Series Prediction with Applications to Financial Data Forecasting Hans-Georg Zimmermann, Siemens AG, Muenchen Chairman: R. Rojas, FU Berlin 17:15 Session 4: Fuzzy-Neuro Systems Chairman: R. Kruse, Universitaet Magdeburg A Neuro-Fuzzy Approach to Feedforward Modeling of Nonlinear Time Series T. Briegel, V. Tresp, Siemens AG, Muenchen A Learning Algorithm for Fuzzy Neural Nets T. Feuring,Westfaelische Wilhelms-Universitaet Muenster James J. Buckley, University of Alabama at Birmingham, Birmingham, USA Improving a priori Control Knowledge by Reinforcement Learning M. Spott, M. Riedmiller, Universitaet Karlsruhe 18:30 End of First Day 20:00 Conference Dinner Friday, March 20, 1998 9:00 Session 5: Applications Chairman: G. Nakhaeizadeh, Daimler Benz AG, Forschung + Technik, Ulm Batch Recipe Optimization with Neural Networks and Genetice Algorithms K. Eder, Kratzer Automatisierung GmbH, Unterschleissheim Robust Tuning of Power System Stabilizers by an Accelerated Fuzzy-Logic Based Genetic Algorithm M. Khederzadeh, Power and Water Institute of Technology, Tehran, Iran Relating Chemical Structure to Activity: An Application of the Neural Folding Architecture T. Schmitt, C. Goller, TU Muenchen Optimization of a Fuzzy System Using Evolutionary Algorithms Q. Zhuang, M. Kreutz, J. Gayko, Ruhr-Universitaet Bochum 10:40 Coffee break - Presentation of Posters 11:00 Invited Lecture 4: Advanced Fuzzy-Concepts and Applications Harro Kiendl, Universitaet Dortmund Chairman: K. Eder, Kratzer Automatisierung GmbH, Unterschleissheim 11:45 Session 6: Theory and Foundations of Fuzzy-Logic Chairman: P. Klement, Universitaet Linz, Austria Rule Weights in Fuzzy Systems D. Nauck, R. Kruse, Universitaet Magdeburg Sliding-Mode-Based analysis of Fuzzy Gain Schedulers - The MIMO Case R. Palm, Siemens AG, Muenchen D. Driankov, University of Linkoeping, Sweden Qualitative Operators For Dealing With Uncertainty H. Seridi, Universite de Reims, France F. Bannay-Dupin, Universite d'Angers, France H. Akdag, Universite P. & M. Curie, Paris, France 13:00 Lunch 14:00 Session 7: Theory and Foundations of Neural Networks Chairman: A. Grauel, Universitaet Paderborn Prestructured Recurrent Neural Networks T. Brychcy, TU Muenchen Formalizing Neural Networks I. Fischer, University of Erlangen M. Koch, Technical University of Berlin M.R. Berthold, University of California, Berkeley, USA Correlation and Regression Based Neuron Pruning Strategies M. Rychetsky, S. Ortmann, C. Labeck, M. Glesner, TU Darmstadt 15:15 Invited Lecture 5: Soft Computing: the Synergistic Interaction of Fuzzy, Neural, and Evolutionary Computation Piero P. Bonissone, General Electric Corporate R&D Artificial Intelligence Laboratory, Schenectady, USA Chairman: S. Gottwald, Universitaet Leipzig 16:00 Closing Remarks and Invitation to FNS'99 Posters ------- Comparing Fuzzy Graphs M.R. Berthold, University of California, Berkeley, USA K.-P. Huber, Universitaet Karlsruhe A Numerical Approach to Approximate Reasoning via a Symbolic Interface. Application to Image Classification A. Borgi, H. Akdag, Universite P. & M. Curie, Paris, France J.-M. Bazin, Universite de Reims, France Entropy-Controlled Probabilistic Search M. David, J. Gottlieb, I. Kupka, TU Clausthal Ensembles of Evolutionary Created Artificial Neural Networks C.M. Friedrich, Universitaet Witten/Herdecke Design and Implementation of a Flexible Simulation Tool for Hybrid Problem Solving H. Geiger, IBV and TU Muenchen J. Pfalzgraf, K. Frank, T. Neuboeck, J. Weichenberger, Universitaet Salzburg, Austria A. Buecherl, TU Muenchen A Fuzzy Invariant Indexing Technique for Object Recognition under Partial Occlusion T. Graf, A. Knoll, A. Wolfram, Universitaet Bielefeld Fuzzy Causal Networks R. Hofmann, V. Tresp, Siemens AG, Muenchen Dynamic Data Analysis: Problem Description And Solution Approaches A. Joentgen, L. Mikenina, R. Weber, H.-J. Zimmermann, RWTH Aachen Filtering and Compressing Information by Neural Information Processor R. Kamimura, Tokai University, Japan A Fuzzy Local Map with Asymmetric Smoothing Using Voronoi Diagrams B. Lang, Siemens AG, Muenchen Fuzzy Interface with Prior Concepts and Non-convex Regularization J.C. Lemm, Universitaet Muenster Modeling and Simulating a Time-Dependent Physical System Using Fuzzy Techniques and a Recurrent Neural Network A. Nuernberger, A. Radetzky, R. Kruse, Universitaet Magdeburg The Kohonen Network Incorporating Explicit Statistics and Its Application to the Traveling Salesman Problem B.J. Oommen, Carleton University, Ottawa, Canada Automated Feature Selection Strategies: An experimental comparison improving Engine Knock Detection S. Ortmann, M. Rychetsky, M. Glesner, TU Darmstadt A Fuzzy-Neuro System for Reconstruction of Multi-Sensor information S. Petit-Renaud, T. Deneux, Universite de Technologie de Compiegne, Compiegne, France RACE: Relational Alternating Cluster Estimation and the Wedding Table Problem T.A. Runkler, Siemens AG, Muenchen J.C. Bezdek, University of West Florida, Pensacola, USA Neural Networks Handle Technological Information for Milling if Training Data is Carefully Preprocessed G. Schulz, D. Fichtner, A. Nestler, J. Hoffmann, TU Dresden Medically Motivated Testbed for Reinforcement Learning in Neural Architectures D. Surmeli, G. Koehler, H.-M. Gross, TU Ilmenau Adaptive Input-Space Clustering for Continuous Learning Tasks M. Tagscherer, P. Protzel, FORWISS, Erlangen A Criminalistic And Forensic Application Of Neural Networks A. Tenhagen, T. Feuring, W.-M. Lippe, G. Henke, H. Lahl, WWU-Muenster A Classical and a Fuzzy System Based Algorithm for the Simulation of the Waste Humidity in a Landfill M. Theisen, M. Glesner, TU Darmstadt FuNN, A Fuzzy Neural Logic Model R. Yasdi, GMD - Forschungszentrum Informationstechnik, Sankt Augustin An Efficient Model for Learning Systems of High-Dimensional Input within Local Scenarios J. Zhang, V. Schwert, Universitaet Bielefeld Optimization of a Fuzzy Controller for a Driver Assistant System Q. Zhuang, J. Gayko, M. Kreutz, Ruhr-Universitaet-Bochum Program Committee ----------------- Prof. Dr. W. Banzhaf, Universitaet Dortmund Dr. M. Berthold, Universitaet Karlsruhe Prof. Dr. Dr. h.c. W. Brauer, TU Muenchen (Chairman) Prof. Dr. G. Brewka, Universitaet Leipzig Dr. K. Eder, Kratzer Automatisierung GmbH, Unterschleissheim Prof. Dr. C. Freksa, Universitaet Hamburg Prof. Dr. M. Glesner, TU Darmstadt Prof. Dr. S. Gottwald, Universitaet Leipzig Prof. Dr. A. Grauel, Universitaet Paderborn/Soest Prof. Dr. H.-M. Gross, TU Ilmenau Dr. A. Guenter, Universitaet Bremen Dr. J. Hollatz, Siemens AG, Muenchen Prof. Dr. R. Isermann, TU Darmstadt Prof. Dr. P. Klement, Universitaet Linz, Austria Prof. Dr. R. Kruse, Universitaet Magdeburg (Vice Chairman) Prof. Dr. B. Mertsching, Universitaet Hamburg Prof. Dr. G. Nakhaeizadeh, Daimler Benz AG, Forschung + Technik, Ulm Prof. Dr. K. Obermayer, TU Berlin Prof. Dr. G. Palm, Universitaet Ulm Dr. R. Palm, Siemens AG, Muenchen Dr. L. Peters, GMD - Forschungszentrum Informationstechnik GmbH, Sankt Augustin Prof. Dr. F. Pichler, Universitaet Linz, Austria Dr. P. Protzel, FORWISS, Erlangen Prof. Dr. B. Reusch, Universitaet Dortmund Prof. Dr. Rigoll, Universitaet Duisburg Prof. Dr. R. Rojas, Freie Universitaet Berlin Prof. Dr. B. Schuermann, Siemens AG, Muenchen (Vice Chairman) Prof. Dr. W. von Seelen, Universitaet Bochum Prof. Dr. H. Thiele, Universitaet Dortmund Prof. Dr. W. Wahlster, Universitaet Saarbruecken Prof. Dr. H.-J. Zimmermann, RWTH Aachen Organization Committee ---------------------- Prof. Dr. Dr. h.c. W. Brauer (Chairman) Dieter Bartmann Till Brychcy Clemens Kirchmair Technische Universitaet Muenchen Tel.: 0 89/2 89-2 84 19 Fax: 0 89/2 89-2 84 83 Dr. Juergen Hollatz, Siemens AG, Muenchen (Vice Chairman) Christine Harms, - ccHa -, Sankt Augustin Conference Site --------------- TU Muenchen Barerstrasse 23 Entrance: Arcisstrasse Lecture hall S0320 D-80333 Muenchen Workshop Secretariat -------------------- Christine Harms c/o GMD / FNS'98 Schloss Birlinghoven D-53754 Sankt Augustin Tel.: ++49 2241 14-24 73 Fax: ++49 2241 14-24 72 email: christine.harms at gmd.de Registration ------------ Please make your (binding) reservation by sending the enclosed registration form to the conference secretariat. Confirmation will be given after receipt of the registration form. Conference Fees: (see registration form) industry rate: 495,- DM university rate: 345,- DM GI members: 295,- DM authors: 295,- DM students (up to age of 26): 60,- DM (*) *) excluding proceedings and conference dinner. A surcharge of DM 100,- is payable for registration after February, 18, 1998. Services of Gesellschaft fuer Informatik e. V. (GI) are VAT-free according to German law p. 4 Nr. 22a UStG. Payment (see registration form) ------- [ ] I have transferred the whole amount of DM________ to Gesellschaft fuer Informatik (GI), Sparkasse Bonn Account No.: 39 479 Bankcode: 380 500 00 Ref: SK-Fuzzy-98 [ ] I enclose a Eurocheque amounting to made payable to Gesellschaft fuer Informatik [ ] Please debit my [ ] Diners [ ] Visa [ ] Euro/Mastercard Cardnumber: Expiration date: Cardholder: Social events ------------- Informal get-together: March, 18, 1998, 18.00 - 21.00 Conference dinner: Thursday, March, 19,1998. Accommodation ------------- A limited number of rooms has been reserved at the FORUM/Penta Hotel at the special rate of single room DM 175,- double room DM 200,- FORUM Hotel Hochstrasse 3 D-81669 Muenchen Cancellation ------------ If cancellation is received up to February, 17, 1998, a 75% refund will be given. For cancellations received afterwards, no refunds can be guaranteed. WWW-Homepage ------------ URL: http://wwwbrauer.informatik.tu-muenchen.de/~fns98/ ----- snip, snip ----- Registration form for Fuzzy-Neuro Systems '98 --------------------------------------------- Please register me as follows Conference Fees: ---------------- [ ] industry rate: 495,- DM [ ] university rate: 345,- DM [ ] GI member No. 295,- DM [ ] authors: 295,- DM [ ] students (up to age of 26): 60,- DM (*) *) excluding proceedings and conference dinner Accommodation: -------------- I would like to make a binding reservation at the FORUM/Penta Hotel [ ] single room DM 175,- [ ] double room DM 200,- (together with ____________________________) Arrival date ______________________________ Departure date ___________________________ Payment directly at the hotel. Hotel booking has to be made until February, 17, 1998. After that we cannot guarantee any bookings. Conference diner: ----------------- [ ] I intend to participate in the conference dinner ...... extra ticket for conference dinner DM 50,-. Payment: -------- [ ] I have transferred the whole amount of DM________ to Gesellschaft fuer Informatik (GI), Sparkasse Bonn Account No.: 39 479 Bankcode: 380 500 00 Reference: SK-Fuzzy-98 [ ] I enclose a Eurocheque amounting to DM_________ made payable to Gesellschaft fuer Informatik [ ] Please debit my [ ] Diners [ ] Visa [ ] Euro/Mastercard Cardnumber:______________Expiration date:_________ Cardholder:_______________________________________ If cancellation is received up to February, 17, 1998, a 75% refund will be given. For cancellations received afterwards, no refunds can be guaranteed. Date:___________ Signature:__________________ Sender: ------- Last Name (Mr. / Mrs. / MS. Title): ________________________________________ First Name: ________________________________________ Affiliation: ________________________________________ Street/POB: ________________________________________ Zip/Postal Code/City: ________________________________________ Country: ________________________________________ Phone/Fax: ________________________________________ E-mail: ________________________________________ If you would like to take part in the workshop, please send the completed registration form to Christine Harms c/o GMD / FNS'98 Schloss Birlinghoven D-53754 Sankt Augustin Tel.: ++49 2241 14-24 73 Fax: ++49 2241 14-24 72 email: christine.harms at gmd.de From pfbaldi at netid.com Tue Feb 17 16:04:07 1998 From: pfbaldi at netid.com (pfbaldi@netid.com) Date: Tue, 17 Feb 1998 21:04:07 +0000 Subject: Book on Bioinformatics Message-ID: <199802180507.VAA21966@polaris.pacificnet.net> The following book is now available from MIT Press: Bioinformatics: the Machine Learning Approach Pierre Baldi and Soren Brunak February 1998 ISBN 0-262-02442-X 360 pp., 62 illus., 10 color $40.00 (cloth) MIT Press (800) 625-8569 (617) 253-5249 (617) 258-6894 (FAX) Additional information can be found at: http://mitpress.mit.edu/book-home.tcl?isbn=026202442X -------------------------------------------------------------------------- Table of Contents Series Foreword Preface 1 Introduction 1.1 Biological Data in Digital Symbol Sequences 1.2 Genomes--Diversity, Size, and Structure 1.3 Proteins and Proteomes 1.4 On the Information Content of Biological Sequences 1.5 Prediction of Molecular Function and Structure 2 Machine Learning Foundations: The Probabilistic Framework 2.1 Introduction: Bayesian Modeling 2.2 The Cox-Jaynes Axioms 2.3 Bayesian Inference and Induction 2.4 Model Structures: Graphical Models and Other Tricks 2.5 Summary 3 Probabilistic Modeling and Inference: Examples 3.1 The Simplest Sequence Models 3.2 Statistical Mechanics 4 Machine Learning Algorithms 4.1 Introduction 4.2 Dynamic Programming 4.3 Gradient Descent 4.4 EM/GEM Algorithms 4.5 Markov Chain Monte Carlo Methods 4.6 Simulated Annealing 4.7 Evolutionary and Genetic Algorithms 4.8 Learning Algorithms: Miscellaneous Aspects 5 Neural Networks: The Theory 5.1 Introduction 5.2 Universal Approximation Properties 5.3 Priors and Likelihoods 5.4 Learning Algorithms: Backpropagation 6 Neural Networks: Applications 6.1 Sequence Encoding and Output Interpretation 6.2 Prediction of Protein Secondary Structure 6.3 Prediction of Signal Peptides and Their Cleavage Sites 6.4 Applications for DNA and RNA Nucleotide Sequences 7 Hidden Markov Models: The Theory 7.1 Introduction 7.2 Prior Information and Initialization 7.3 Likelihood and Basic Algorithms 7.4 Learning Algorithms 7.5 Applications of HMMs: General Aspects 8 Hidden Markov Models: Applications 8.1 Protein Applications 8.2 DNA and RNA Applications 8.3 Conclusion: Advantages and Limitations of HMMs 9 Hybrid Systems: Hidden Markov Models and Neural Networks 9.1 Introduction to Hybrid Models 9.2 The Single-Model Case 9.3 The Multiple-Model Case 9.4 Simulation Results 9.5 Summary 10 Probabilistic Models of Evolution: Phylogenetic Trees 10.1 Introduction to Probabilistic Models of Evolution 10.2 Substitution Probabilities and Evolutionary Rates 10.3 Rates of Evolution 10.4 Data Likelihood 10.5 Optimal Trees and Learning 10.6 Parsimony 10.7 Extensions 11 Stochastic Grammars and Linguistics 11.1 Introduction to Formal Grammars 11.2 Formal Grammars and the Chomsky Hierarchy 11.3 Applications of Grammars to Biological Sequences 11.4 Prior Information and Initialization 11.5 Likelihood 11.6 Learning Algorithms 11.7 Applications of SCFGs 11.8 Experiments 11.9 Future Directions 12 Internet Resources and Public Databases 12.1 A Rapidly Changing Set of Resources 12.2 Databases over Databases and Tools 12.3 Databases over Databases 12.4 Databases 12.5 Sequence Similarity Searches 12.6 Alignment 12.7 Selected Prediction Servers 12.8 Molecular Biology Software Links 12.9 Ph.D. Courses over the Internet 12.10 HMM/NN Simulator A Statistics A.1 Decision Theory and Loss Functions A.2 Quadratic Loss Functions A.3 The Bias/Variance Trade-off A.4 Combining Estimators A.5 Error Bars A.6 Sufficient Statistics A.7 Exponential Family A.8 Gaussian Process Models A.9 Variational Methods B Information Theory, Entropy, and Relative Entropy B.1 Entropy B.2 Relative Entropy B.3 Mutual Information B.4 Jensen's Inequality B.5 Maximum Entropy B.6 Minimum Relative Entropy C Probabilistic Graphical Models C.1 Notation and Preliminaries C.2 The Undirected Case: Markov Random Fields C.3 The Directed Case: Bayesian Networks D HMM Technicalities, Scaling, Periodic Architectures, State Functions, and Dirichlet Mixtures D.1 Scaling D.2 Periodic Architectures D.3 State Functions: Bendability D.4 Dirichlet Mixtures E List of Main Symbols and Abbreviations References Index -------------------------------------------------------------------------------- From dblank at comp.uark.edu Tue Feb 17 23:47:51 1998 From: dblank at comp.uark.edu (Douglas Blank) Date: Tue, 17 Feb 1998 22:47:51 -0600 Subject: PhD Thesis: "Learning to See Analogies: A Connectionist Exploration" Message-ID: <3.0.32.19980217224749.00710f30@comp.uark.edu> The following Ph.D. thesis is now available via - anonymous ftp (ftp://dangermouse.uark.edu/pub/thesis) - web site (http://www.uark.edu/~dblank/thesis.html) - hardcopy (send address to dblank at comp.uark.edu) It is about 200 pages long and the chapters can be retrieved individually as PostScript or PDF files. (Specific retrieval instructions below). Title: Learning to See Analogies: A Connectionist Exploration Douglas S. Blank Joint Ph.D. in Cognitive Science and Computer Science Indiana University, Bloomington ABSTRACT This dissertation explores the integration of learning and analogy-making through the development of a computer program, called Analogator, that learns to make analogies by example. By "seeing" many different analogy problems, along with possible solutions, Analogator gradually develops an ability to make new analogies. That is, it learns to make analogies by analogy. This approach stands in contrast to most existing research on analogy-making, in which typically the a priori existence of analogical mechanisms within a model is assumed. The present research extends standard connectionist methodologies by developing a specialized associative training procedure for a recurrent network architecture. The network is trained to divide input scenes (or situations) into appropriate figure and ground components. Seeing one scene in terms of a particular figure and ground provides the context for seeing another in an analogous fashion. After training, the model is able to make new analogies between novel situations. Analogator has much in common with lower-level perceptual models of categorization and recognition; it thus serves as a unifying framework encompassing both high-level analogical learning and low-level perception. This approach is compared and contrasted with other computational models of analogy-making. The model's training and generalization performance is examined, and limitations are discussed. =========================================================== Title, Abstract, Acknowledgments, Contents 0_intro.pdf 54k 0_intro.ps.gz 71k Chapter 1 INTRODUCTION 1_ch.pdf 172k 1_ch.ps.gz 187k Chapter 2 ANALOGY-MAKING, LEARNING, AND GENERALIZATION 2_ch.pdf 32k 2_ch.ps.gz 40k Chapter 3 CONNECTIONIST FOUNDATIONS 3_ch.pdf 221k 3_ch.ps.gz 189k Chapter 4 THE ANALOGATOR MODEL 4_ch.pdf 578k 4_ch.ps.gz 390k Chapter 5 EXPERIMENTAL RESULTS 5_ch.pdf 702k 5_ch.ps.gz 566k Chapter 6 COMPARISONS WITH OTHER MODELS OF ANALOGY-MAKING 6_ch.pdf 305k 6_ch.ps.gz 276k Chapter 7 CONCLUSION 7_ch.pdf 16k 7_ch.ps.gz 24k APPENDICES, REFERENCES 8_end.pdf 57k 8_end.ps.gz 91k Everything all.pdf 2M all.ps.gz 1M =========================================================== FTP instructions: (e.g., to retrieve Chapter 1) unix> ftp dangermouse.uark.edu Name: anonymous Password: youremail at domain ftp> cd pub/thesis ftp> get 1_ch.ps.gz ftp> bye unix> gunzip 1_ch.ps.gz unix> lpr 1_ch.ps ===================================================================== dblank at comp.uark.edu Douglas Blank, University of Arkansas Assistant Professor Computer Science ==================== http://www.uark.edu/~dblank ==================== From erik at bbf.uia.ac.be Wed Feb 18 11:37:34 1998 From: erik at bbf.uia.ac.be (Erik De Schutter) Date: Wed, 18 Feb 1998 16:37:34 GMT Subject: 1998 Crete Course in Computational Neuroscience Message-ID: <199802181637.QAA14539@kuifje.bbf.uia.ac.be> CRETE COURSE IN COMPUTATIONAL NEUROSCIENCE SEPTEMBER 13 - OCTOBER 9, 1998 FORTH INSTITUTE, CRETE, GREECE DIRECTORS: Erik De Schutter (University of Antwerp, Belgium) Adonis Moschovakis (University of Crete, Greece) Idan Segev (Hebrew University, Jerusalem, Israel) The Crete Course in Computational Neuroscience introduces students to the practical application of computational methods in neuroscience, in particular how to create biologically realistic models of neurons and networks. The course consists of two complimentary parts. A distinguished international faculty gives morning lectures on topics in experimental and computational neuroscience. The rest of the day is spent learning how to use simulation software and how to implement a model of the system the student wishes to study. The first week of the course introduces students to the most important techniques in modeling single cells, networks and neural systems. Students learn how to use the GENESIS, NEURON, XPP and other software packages on their individual unix workstations. During the following three weeks the lectures will be more general, but each week topics ranging from modeling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the the brain will be covered. The course ends with a presentation of the students' modeling projects. The Crete Course in Computational Neuroscience is designed for advanced graduate students and postdoctoral fellows in a variety of disciplines, including neuroscience, physics, electrical engineering, computer science and psychology. Students are expected to have a basic background in neurobiology as well as some computer experience. A total of 28 students will be accepted with an age limit of 35 years. We will accept students of any nationality, but the majority will be from the European Union and affiliated countries (Iceland, Israel, Liechtenstein and Norway). We specifically encourage applications from researchers who work in less-favoured regions of the EU, from women and from researchers from industry. Every student will be charged a tuition fee of 700 ECU (approx. US$770). In the case of students with a nationality from the EU, affiliated countries or Japan, this tuition fee covers lodging, local travel and all course-related expenses. All applicants with other nationalities will be charged an ADDITIONAL fee of 1000 ECU (approx. US$1100) to cover lodging, local travel and course-related expenses. For nationals from EU and affiliated countries economy travel from an EU country to Crete will be refunded after the course. A limited number of students from less-favoured regions world-wide will get their fees and travel refunded. More information and application forms can be obtained: - WWW access: http://bbf-www.uia.ac.be/Crete_index.html Please apply electronically using a web browser if possible. - email: crete_course at bbf.uia.ac.be - by mail: Prof. E. De Schutter Born-Bunge Foundation University of Antwerp - UIA, Universiteitsplein 1 B2610 Antwerp Belgium FAX: +32-3-8202669 APPLICATION DEADLINE: May 1, 1998. Applicants will be notified of the results of the selection procedures by May 31. FACULTY: M. Abeles (Hebrew University Jerusalem, Israel), A. Aertsen (Albert Ludwigs University Freiburg, Germany), A. Borst (Max Planck Institute Tuebingen, Germany), R. Calabrese (Emory University, USA), R. Douglas (Institute of Neuroinformatics, Zurich), G. Dupond (Free University Brussels, Belgium), O. Ekeberg (Royal Institute of Technology, Sweden), A. Feltz (University of Strasbourg, France), T. Flash (Weizmann Institute of Science, Israel), D. Hansel (Ecole Polytechnique Paris, France), J.J.B. Jack (Oxford University, England), R. Kotter (Heinrich Heine University Dusseldorf, Germany), G. LeMasson (University of Bordeaux, France), K. Martin (Institute of Neuroinformatics, Zurich), M. Nicolelis (Duke University, USA), G. Rizzolatti (University of Parma, Italy), J.M. Rinzel (NIH, USA), H. Sompolinsky (Hebrew University Jerusalem, Israel), M. Spira (Hebrew University Jerusalem, Israel), S. Tanaka (RIKEN, Japan), C. Wilson (University of Tennessee, USA), Y. Yarom (Hebrew University Jerusalem, Israel) and others to be named. The Crete Course in Computational Neuroscience is supported by the European Commission (4th Framework Training and Mobility of Researchers program) and by The Brain Science Foundation (Tokyo). Local administrative organization: the Institute of Applied and Computational Mathematics of FORTH (Crete, GR). From cmbishop at microsoft.com Wed Feb 18 11:14:08 1998 From: cmbishop at microsoft.com (Christopher Bishop) Date: Wed, 18 Feb 1998 08:14:08 -0800 Subject: Paper and software available on-line Message-ID: <3FF8121C9B6DD111812100805F31FC0D810C85@red-msg-59.dns.microsoft.com> Paper and Software Available Online: A HIERARCHICAL LATENT VARIABLE MODEL FOR DATA VISUALIZATION NCRG/96/028 Christopher M. Bishop* and Michael E. Tipping# * Microsoft Research St. George House, 1 Guildhall Street Cambridge CB2 3NH, U.K. # Neural Computing Research Group Aston University, Birmingham B4 7ET, U.K. http://neural-server.aston.ac.uk/Papers/postscript/NCRG_96_028.ps.Z Abstract: Visualization has proven to be a powerful and widely-applicable tool for the analysis and interpretation of multi-variate data. Most visualization algorithms aim to find a projection from the data space down to a two-dimensional visualization space. However, for complex data sets living in a high-dimensional space it is unlikely that a single two-dimensional projection can reveal all of the interesting structure. We therefore introduce a hierarchical visualization algorithm which allows the complete data set to be visualized at the top level, with clusters and sub-clusters of data points visualized at deeper levels. The algorithm is based on a hierarchical mixture of latent variable models, whose parameters are estimated using the expectation-maximization algorithm. We demonstrate the principle of the approach on a toy data set, and we then apply the algorithm to the visualization of a synthetic data set in 12 dimensions obtained from a simulation of multi-phase flows in oil pipelines, and to data in 36 dimensions derived from satellite images. A Matlab(R) software implementation of the algorithm is publicly available from the world-wide web. Paper: http://neural-server.aston.ac.uk/Papers/postscript/NCRG_96_028.ps.Z Software: http://www.ncrg.aston.ac.uk/PhiVis Complete searchable database of publications: http://neural-server.aston.ac.uk/ ---------------------------------------------------------------------------- ---- Professor Christopher M. Bishop Microsoft Research, Cambridge St. George House, 1 Guildhall Street Cambridge CB2 3NH Tel: +44/0 1223 744 751 Fax: +44/0 1223 744 777 Email: cmbishop at microsoft.com Web: http://www.ncrg.aston.ac.uk/People/bishopc/Welcome.html ---------------------------------------------------------------------------- ---- From SteinR at moodys.com Wed Feb 18 11:20:49 1998 From: SteinR at moodys.com (Stein, Roger) Date: Wed, 18 Feb 1998 11:20:49 -0500 Subject: Adaptive and intelligent systems in business: Book available Message-ID: Members of the Santa Fe Institute mailing list may have already received this. Apologies... SEVEN METHODS FOR TRANSFORMING CORPORATE DATA INTO BUSINESS INTELLIGENCE by Vasant Dhar and Roger Stein Upper Saddle River, NJ, Prentice-Hall, 1997. My colleague, Vasant Dhar, and I have written a short book on applying intelligent and adaptive systems to business problems. It may be of interest to some subscribers. There are two versions of the book available, one is suited to business people and one is suited to teaching. The book provides a practical methodology for mapping business problems onto solutions involving neural networks, genetic algorithms, nearest-neighbor algorithms, etc. We also provide extended case studies of organizations that have successfully done this. The reaction to the book, in both the academic and professional community, seems to be favorable: "Intelligent Systems are becoming vital at all levels of management from the CEO to the foreman. Dhar and Stein provide one of the clearest and most accessible treatments to date of the subject." - Herbert A. Simon, Nobel Laureate "Seven Methods effectively bridges the gap between lofty technical explanation and the down-to-earth business application of a brand new world of modeling technologies." - Win Farrell, Partner, Coopers and Lybrand A brief summary of the book follows: Seven Methods for Transforming Corporate Data into Business Intelligence combines a thorough treatment of techniques for applying intelligent systems to decision support with a practical framework for analyzing business problems. Vasant Dhar (former Principal, Morgan Stanley and New York University) and Roger Stein (Vice President, Moody's Investors Service and New York University) present in clear and vivid terms the essentials of modern decision support. Seven Methods takes a three stage approach to discussing these new technologies. The book is organized around: * A framework for analyzing business decision problems and mapping solutions onto them * An intuitive but full discussion of the technologies for data mining and automated decision systems * A series of extensive case studies that show, using the framework, how major organizations have made use of these technologies In addition to discussing technologies, Dhar and Stein introduce a unified methodology for analyzing organizations' business problems and evaluating potential solutions. This framework, based on the authors' years of combined experience applying intelligent systems to real business decision problems, encourages business people to think critically about how the strengths and weaknesses of each technique relate to the particular dynamics of an organization and its problems. The authors show not only when a particular modeling method may be useful, but also when its attributes might make it undesirable for a particular problem. The text does not limit itself to one or a few techniques, but rather views various AI and database techniques as components of a toolbox that, if used correctly, can make organizations dramatically more intelligent. Seven Methods provides accessible detailed coverage of * OLAP and data warehousing * Genetic algorithms * Neural networks * Rule-based expert systems * Fuzzy systems * Case-based reasoning * Machine learning The text adopts an informal, conversational style in their exposition. Despite the relaxed style, the book delves into the subtle aspects of each technique while keeping the text readable and non-technical. In order to make the material more accessible, the text makes frequent use of rich graphics. The graphical representation of complex concepts are invaluable in elucidating these topics. To drive home the discussions of modeling techniques and organizational dynamics, the book also provides extended case studies that show in detail how the framework can be applied to analyzing the problems of real organizations. Cases are taken from the experience of firms in a diversity of industries solving an assortment of problems. Firms include: * US WEST * Moody's Investors Service * Compaq Computer Corp. * LBS Capital Management * NYNEX, Inc. * Kaufhof AG * A. C. Neilsen Problem domains include: * customer service * scheduling * data mining * financial market prediction * quality control * consumer product marketing The book is available from Prentice-Hall: (Professional version) Seven Methods for Transforming Corporate Data into Business Intelligence, Upper Saddle River, NJ, Prentice-Hall, 1997. (Academic version) Intelligent Decision Support Methods: The Science of Knowledge Work, Upper Saddle River, NJ, Prentice-Hall, 1997. Online Orders: www.amazon.com Phone: 1-(800) 643-5506. Please give the operator the following "key code": E1001-A1(3). FAX: 1-(800) 835-5327. From annesp at vaxsa.csied.unisa.it Wed Feb 18 10:46:29 1998 From: annesp at vaxsa.csied.unisa.it (annesp@vaxsa.csied.unisa.it) Date: Wed, 18 Feb 1998 16:46:29 +0100 Subject: summer school Message-ID: <98021816462905@vaxsa.csied.unisa.it> From: SMTP%"iiass at tin.it" 18-FEB-1998 16:34:18.19 To: annesp at vaxsa.csied.unisa.it CC: Subj: call ***************************************************************** Please post **************************************************************** International Summer School ``Neural Nets E. R. Caianiello" 3rd Course "A Course on Speech Processing, Recognition, and Artificial Neural Networks" web page: http://wsfalco.ing.uniroma1.it/Speeschool.html The school is jointly organized by: INTERNATIONAL INSTITUTE FOR ADVANCED SCIENTIFIC STUDIES (IIASS) Vietri sul Mare (SA) Italy, ETTORE MAJORANA FOUNDATION AND CENTER FOR SCIENTIFIC CULTURE (EMFCSC) Erice (TR), Italy Supported by: EUROPEAN SPEECH COMMUNICATION ASSOCIATION (ESCA) Sponsored by: SALERNO UNIVERSITY, Dipartimento di Scienze Fisiche E.R. Caianiello (Italy) DIRECTORS OF THE COURSE DIRECTORS OF THE SCHOOL AND ORGANIZING COMMITTEE: Gerard Chollet (France). Maria Marinaro (Italy) M. Gabriella Di Benedetto (Italy) Michael Jordan (USA) Anna Esposito (Italy) Maria Marinaro (Italy) PLACE: International Institute for Advanced Scientific Studies (IIASS) Via Pellegrino 19, 84019 Vietri sul Mare, Salerno (Italy) DATES: 5th-14th October 1998 POETIC TOUCH Vietri (from "Veteri", its ancient Roman name) sul Mare ("on sea") is located within walking distance from Salerno and marks the beginning of the Amalfi coast. Short rides take to Positano, Sorrento, Pompei, Herculaneum, Paestum, Vesuvius, or by boat, the islands of Capri, Ischia, and Procida. Velia (the ancient "Elea" of Zeno and Parmenide) is a hundred kilometers farther down along the coast. Student Fee: 1500 dollars Student fee include accommodations (arranged by the school), meals, one day of excursion, and a copy of the proceedings of the school. Transportation is not included. A few scholarships are available for students who are otherwise unable to participate at the school, and who cannot apply for the grants offered by ESCA. The scholarship will partially cover lodging and living expenses. Day time: 3 hour in the morning, three hour in the afternoon. Day free: One day with an excursion of the places around. AIMS: The aim of this school is to present the experiments, the theories and the perspectives of acoustic phonetics, as well as to discuss recent results in the speech literature. The school aims to provide a background for further study in many of the fields related to speech science and linguistics, including automatic speech recognition. The school will bring together leading researchers and selected students in the field of speech science and technology to discuss and disseminate the latest techniques. The school is devoted to an international audience and in particular to all students and scientists who are working on some aspects of speech and want to learn other aspects of this discipline. MAJOR TOPICS The school will cover a number of broad themes relevant to speech, among them: 1) Speech production and acoustic phonetics 2) Articulatory, acoustic, and prosodic features 3) Acoustic cues in speech perception 4) Models of speech perception 5) Speech processing (Preprocessing algorithms for Speech) 6) Neural Networks for automatic speech recognition 7) Multi-modal speech recognition and recognition in adverse environments. 8) Speech to speech translation (Vermobil and CSTAR projects) 9) Applications (Foreign Language training aids, aids for handicapped, ....). 10) Stochastic Models and Dialogue systems FORMAT The meeting will follow the usual format of tutorials and panel discussions together with poster sessions for contributed papers. The following tutorials are planned: ABEER ALWAN UCLA University (CA) USA "Models of Speech Production and Their Application in Coding and Recognition" ANDREA CALABRESE University of Connecticut (USA) "Prosodic and Phonological Aspects of Language" GERARD CHOLLET CNRS - ENST France ALISP, Speaker Verification, Interactive Voice Servers" RENATO DE MORI Universite d' Avignon, France "Statistical Methods for Automatic Speech Recognition" M. GABRIELLA DI BENEDETTO Universita' degli Studi di Roma "La Sapienza", Rome, Italy ``Acoustic Analysis and Perception of Classes of Sounds (vowels and consonants)" BJORN GRANSTROM Royal Institute of Technology (KTH) Sweden "Multi-modal Speech Synthesis with Application" JEAN P. HATON Universite Henri-Poincare, CRIN-INRIA, France "Neural Networks for Automatic Speech Recognition" HYNEK HERMANSKY Oregon Graduate Institute, USA "Goals and Techniques of Speech Analysis" JOHN OHALA University of California at Berkeley (CA) USA "Articulatory Constraints on Distinctive Features" JEAN SYLVAIN LIENARD LIMSI-CNRS, France "Speech Perception, Voice Perception" "Beyond Pattern Recognition" PROCEEDINGS The proceedings will be published in the form of a book containing tutorial chapters written by the lecturers and possibly shorter papers from other participants. One free copy of the book will be distributed to each participant. LANGUAGE The official language of the school will be English. POSTER SUBMISSION There will be a poster session for contributed presentations from participants. Proposals consisting of a one page abstract for review by the organizers should be submitted with applications. DURATION Participants are expected to arrive in time for the evening meal on Sunday 4th October and depart on Tuesday 15th October. Sessions will take place from Monday 5th-Wednesday 14th. COST The cost per participant of 1.500 $ dollars covers accommodation (in twin rooms), meals for the duration of the course, and one day of excursion. -- A supplement of 40 dollars per night should be paid for single room. Payment details will be notified with acceptance of applications. GRANTS -- A few ESCA grants are available for participants (which cover tuition and, maybe, part of the lodging). See http://ophale.icp.inpg.fr/esca/grants.html for further information. Individual applications for grants should be sent to Wolfgang Hess by e-mail: wgh at sunwgh.ikp.uni-bonn.de ELIGIBILITY The school is open to all suitably qualified scientists from around the world. APPLICATION PROCEDURE: Important Date: Application deadline: May 15 1998 Notification of acceptance: May 30 1998 Registration fee payment deadline: July 10 1998 People with few years of experience in the field should include a recommendation letter of their supervisor or group leader Places are limited to a maximum of 60 participants in addition to the lecturers. These will be allocated on a first come, first served basis. ************************************************************************** APPLICATION FORM Title:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Family Name:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Other Names:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Name to appear on badge:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Mailing Address (include institution or company name if appropriate): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Phone:^^^^^^^^^^^^^^^^^^^^^^Fax:^^^^^^^^^^^^^^^^^^^ E-mail:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Date of Arrival : Date of Departure: Will you be applying for a ESCA grant ? yes/no* *(please delete the alternatives which do not apply) Will you be applying for a scholarship ? yes/no* *(please delete the alternatives which do not apply) *(please include in your application a justification for scholarship request) ***************************************************************** Please send the application form together the recommendation letter by electronic mail to: iiass at tin.it, subject: summer school; or by fax: +39 89 761 189 (att.ne Prof. M. Marinaro) or by ordinary mail to the address below: IIASS Via Pellegrino 19, I84019 Vietri sul Mare (Sa) Italy For further information please contact: Anna Esposito International Institute for advanced Scientific Studies (IIASS) Via Pellegrino, 19, 84019 Vietri sul Mare (SA) Italy Fax: + 39 89 761189 e-mail: annesp at vaxsa.csied.unisa.it ================== RFC 822 Headers ================== From iiass at tin.it Wed Feb 18 09:56:12 1998 From: iiass at tin.it (IIASS) Date: Wed, 18 Feb 1998 15:56:12 +0100 Subject: call Message-ID: <34EAF68C.2DF0@tin.it> From lek at cict.fr Thu Feb 19 10:02:23 1998 From: lek at cict.fr (Sovan LEK) Date: Thu, 19 Feb 1998 16:02:23 +0100 Subject: Neural Networks Workshop Message-ID: <1.5.4.32.19980219150223.00aec2b4@mail.cict.fr> INTERNATIONAL WORKSHOP ON APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS TO ECOLOGICAL MODELLING (2nd circular) 14-17 December 1998, Toulouse (FRANCE) Local Organizing Committee: Dr. Sovan Lek, CESAC, UMR 5576 du CNRS, UPS, B?t IVR3, 118 route de Narbonne, F-31062 Toulouse cedex 4, France Phone: 33-5 61 55 86 87 Fax: 33-5 61 55 60 96 E-mail: lek at cict.fr Dr. Jean-Fran?ois Gu?gan, ORSTOM, D?partement Biologie, Ecologie & Evolution, Laboratoire d'Hydrobiologie marine et Continentale, Universit? de Montpellier II (USTL), C.C. 093, place E. Bataillon, 34095 Montpellier cedex 05, France. Phone: 33 4 67 14 37 51 Fax : 33 4 67 14 46 46 E-mail : guegan at crit.univ-montp2.fr BACKGROUND You are cordially invited to attend the first "International Workshop on the Application of Artificial Neural Networks to Ecological Modelling" to be held at the Centre d'Ecologie des Syst?mes Aquatiques Continentaux in Toulouse (France). Toulouse is France's fourth largest city (650,350 people with suburbs), and is the European Space capital. It is situated on the Garonne river in very lush surroundings. The Toulouse of today is a lively university town (with more than 100,000 students) and has a rich medieval history. OBJECTIVES: Predictive modelling is a major concern in theoretical ecology, evolution and environmental sciences. Relationships between variables in natural systems are frequently non-linear, and thus conventional modelling tools could appear to be inappropriate to capture the complexity of such systems. This International Workshop will bring together theoretical and applied biological research, practitioners, and developers, as well as domain scientists from multiple ecological disciplines, for the presentation and exchange of current research and on concepts, tools and techniques for scientific and non linear statistical application in ecology, evolution and environmental sciences. The objectives are: ? To promote collaboration among scientists of different interested countries and research fields encouraging both teaching and research collaboration. ? To consider recent advances in Artificial Neural Networks to modelling data (identification, control, prediction, classification problems,...). INVITED SPEAKERS: Dr. S.E. Jorgensen (DK): Ecological Modelling: State of the Art. Pr. R. Tomassone (Fr): Dynamic systems and experimental planning: from data to modelling Dr. P. Bourret (Fr): Non -supervised classification: from observations to assumption. Dr. A. Teriokhin (Russia): On Neural Networks capable to realize evolutionarily optimal animal strategies of growth and reproduction in a seasonal environment. Pr. P. Auger (Fr): Non-linear Modelling in Ecology: from Individuals to Populations. Dr. F. Recknagel (Australia): Elucidation and Prediction of Aquatic Ecosystems by Artificial Neural Networks THEMES (you need to report your choice in the reply form, section Publication, which sub-theme?): o Pattern Recognition o Pattern Classification o Clustering and Classification o Diagnosis and Monitoring o Prediction and Control o Signal Processing o Temporal and Spatial Sequences PUBLICATION Final Instructions for Submission of Abstracts: o Abstract deadline: Abstracts must be submitted in English style, and received by the organisers before 1 April 1998. All abstracts will be refereed before final acceptance. o Please give complete name of your institution, followed by town and country. o The text of your abstract must be informative and contain: 1) a statement of the study's specific aims; 2) a statement of the method used; 3) a summary of results obtained; 4) a statement of conclusion. Avoid non-informative sentences. o Format: Abstracts must not exceed one page (format A4) and be sent directly by electronic mail to Drs. Lek or Gu?gan. If your abstract is too long it will be shortened by the organisers. The publication of the oral contributions is being considered. Please indicate if you are interested in submitting your paper for consideration in a special volume. Original papers will be published on merit in a special volume of the Springer Verlag Environmental Science Series. Other papers will form a special issue of Ecological Modelling. Both Editing Houses have been contacted and have accepted to co-edit these two special volumes. All contributions will be reviewed by at least two referees before acceptance for publication. SUBMISSION GUIDELINES OF PAPER(S) All contributions must be submitted by September 30th of 1998 to the Organizing Committee. Research papers should be up to 8,000 words long. All papers for publication should be sent by electronic mail (Ms-Word) or by post (4 hard-copies are needed) to Dr. Sovan Lek. All papers will be acknowledged of receipt. A notification of acceptance, modification or refusal will be sent by November 15th of 1998 to delegates having submitted a contribution with details given on which publication (hard volume of Springer Verlag or special issue of Ecological Modelling) the paper will be proposed. GENERAL INFORMATION: Languages: French and English will be the two official languages during the Conference, but abstracts, posters, and published papers will be exclusively written in English style. Venue: The Conference venue will be the Conference Centre of Toulouse University. This venue is ideal for a medium conference (about 150 people), with excellent, modern facilities which will allow for productive exchanges of ideas. Dates: Monday 14 December 1998 to Thursday 17 December 1998. Travel: Destination is Toulouse. Delegates must make their own travel arrangements to at least this destination. From dsilver at mgmt.dal.ca Fri Feb 20 18:17:40 1998 From: dsilver at mgmt.dal.ca (Daniel L. Silver) Date: Fri, 20 Feb 1998 23:17:40 +0000 Subject: Tech. Report - Task Rehearsal Method of Sequential Learning Message-ID: <199802210318.XAA24285@Snoopy.UCIS.Dal.Ca> Dear colleagues, the following TR is now available: "The Task Rehearsal Method of Sequential Learning" Department of Computer Science Univeristy of Western Ontario Technical Report # 517 Daniel L. Silver and Robert E. Mercer Abstract An hypothesis of functional transfer of task knowledge is presented that requires the development of a measure of task relatedness and a method of sequential learning. The "task rehearsal method" (TRM) is introduced to address the issues of sequential learning, namely retention and transfer of knowledge. TRM is a knowledge based inductive learning system that uses functional domain knowledge as a source of inductive bias. The representations of successfully learned tasks are stored within domain knowledge. "Virtual examples" generated by domain knowledge are rehearsed in parallel with the each new task using either the standard multiple task learning (MTL) or the $\eta$MTL neural network methods. The results of experiments conducted on a synthetic domain of seven tasks demonstrate the method's ability to retain and transfer task knowledge. TRM is shown to be effective in developing hypothesis for tasks that suffer from impoverished training sets. Difficulties encountered during sequential learning over the diverse domain reinforce the need for a more robust measure of task relatedness. ---------------------------------------------------------------------- Comments are welcome! Download sites: http://www.csd.uwo.ca/~dsilver/trmpaper.ps or http://www.csd.uwo.ca/~dsilver/trmpaper.ps.Z ////////////////////////////////////////////////////////////////////// Daniel L. Silver CogNova Technologies Phone: (902) 582-7558 1226 J.Jordan Road Fax: (902) 582-3140 Canning,Nova Scotia Dal.U: (902) 494-1813 Canada B0P 1H0 Email: dsilver at mgmt.dal.ca Homepage: http://www.meadoworks.ns.ca/cognova /////////////////////////////////////////////////////////////// From marwan at ee.usyd.edu.au Mon Feb 23 04:28:33 1998 From: marwan at ee.usyd.edu.au (Marwan Jabri) Date: Mon, 23 Feb 1998 20:28:33 +1100 (EST) Subject: Post-doctoral fellowship Message-ID: Post-Doctoral Fellow Department of Electrical Engineering The University of Sydney Applications are invited for Post-doctoral fellow position funded by an Australian Research Council project grant. The three-year project aims at investigating computational models of the superior colliculus, the implementation of the models in microelectronics and their integration in sensorimotor control systems. The fellow will join a group several academics and doctoral students working on biological models for sensorimotor control. The research is a collaboration between M. Jabri (Elec. Eng., Sydney University) S. Carlile (Physiology, Sydney University) and T. Sejnowski (Salk Institute). The fellow will be based in Sydney, but will be expected to travel and spend several weeks every year at the Salk Institute. Applicants would have completed (or about to complete) their PhD in electrical, computer or related engineering or science discipline and have demonstrated research capacity in the area of neuromorphic engineering, computational neurobiology or microelectronics. Appointment will be made initially for a period of one year, and renewable for another two years subject to progress. Expected starting date in May, 1998. Closing date: March 20, 1998 Salary range: A$34k-46k To apply, send letter of application, CV and names, fax and email of three referees to M. Jabri Tel (+61-2) 9351 2240, Fax (+61-2) 9351 7209, Email: marwan at sedal.su.oz.au From Nicolino.Pizzi at nrc.ca Mon Feb 23 10:12:54 1998 From: Nicolino.Pizzi at nrc.ca (Pizzi, Nicolino) Date: Mon, 23 Feb 1998 10:12:54 -0500 Subject: Postdoctoral Research Opportunity - University of Manitoba Message-ID: POSTDOCTORAL RESEARCH OPPORTUNITY - COMPUTER ENGINEERING HYBRID KNOWLEDGE-BASED CLASSIFICATION OF VOLUMETRIC PATTERNS Pending final approval, a postdoctoral position is available within the Electrical and Computer Engineering Department to participate in an NSERC-funded strategic research project investigating hybrid knowledge-based classification of volumetric patterns. The position is for a one-year term with a possible one year renewal. The research project will be conducted in close collaboration with Prof. W. Pedrycz and Dr. N. Pizzi. Volumetric (three-dimensional) data are found in many application areas such as radar scans of meteorological formations. These data normally contain a number of three-dimensional regions of interest (ROI's) that belong to several classes. The classification of an ROI is determined by some well-established reference test. In the case of meteorological radar scans, the ROI's may be cloud formations that cause severe weather, the classes may be hail, heavy rain, wind, or tornadic events, and the reference test might be eye-witness accounts of the storm events. The intent of this project is to develop a comprehensive pattern recognition methodology aimed at such data and propose a suite of classification algorithms that can take a ROI and produce a classification outcome that matches the class to which it was assigned by the corresponding reference test. A number of factors can confound the classification process. It may become difficult to glean any discriminating features from volumetric data if it contains noise due to limitations of sensors, instrumentation, or the data acquisition process. Moreover, the ROI's may be extremely complex in nature. Several preprocessing methods are proposed in order to transform the original ROI in order to eliminate or diminish the effects of noise and/or reduce the dimensionality of the input space as well as focus the classification effort on the most significant features. The problem of identifying discriminating features is further aggravated by the fact that the accepted reference test itself may be imprecise or even unreliable. Finally, the volumetric data may be incomplete and sophisticated interpolation methods will be required to deal with missing values. Required background: - Recent Ph.D. graduate - Experience in C++ programming on UNIX systems - Knowledge of pattern recognition techniques Desired background: - Working knowledge of fuzzy systems, artificial neural networks, and data mining Please send a curriculum vitae, expression of interest (including earliest start date), and the names and e-mail addresses (or telephone numbers) of two references to N. Pizzi at pizzi at ibd.nrc.ca. Your curriculum vitae should include a list of recent publications. Please outline your interest in this project, how it is related to work that you have done, and what special expertise you would bring to the project. Nicolino Pizzi, Ph.D. Associate Research Officer Institute for Biodiagnostics National Research Council 435 Ellice Avenue Winnipeg MB R3B 1Y6 CANADA From Shaogang.Gong at dcs.qmw.ac.uk Mon Feb 23 11:35:53 1998 From: Shaogang.Gong at dcs.qmw.ac.uk (Shaogang Gong) Date: Mon, 23 Feb 1998 16:35:53 +0000 (GMT) Subject: Post-Doc Research in Face and Gesture Recognition Message-ID: <199802231635.QAA01578@seans-pc.dcs.qmw.ac.uk> Post-doctoral Research in Visual Learning for Face Gesture Recognition and Intention Prediction for Visually Mediated Interaction Department of Computer Science Queen Mary and Westfield College, University of London, UK Applications are invited for a post-doctoral research assistant in the Dept of Computer Science at Queen Mary and Westfield College to work on a new EPSRC research project. The successful candidate will be undertaking novel research in statistical learning methods, real-time view-based face and gesture representation and recognition, data fusion for active camera control and intention prediction. Our lab is equipped with extensive real-time image capturing and tracking systems including Pentium and Pentium II real-time active camera systems, SGI O2 systems, Datacube MaxVideo 250 and MD1/2GX, AMT DAP 500 parallel processors, with numerous SPARC workstations. The candidate should have experience in computer vision and neural network research. In particular, any experience in view-based representation and statistical learning theories would be an advantage (more details can be found on the Web at http://www.dcs.qmw.ac.uk/research/vision/ ). You should also be competent in programming C under X and NT windows and using Unix systems. You will be expected to start as soon as possible on a 2 year contract. Salary in range of 17,293-22,237 pounds per annum inclusive, depending on age and experience. The project is to be closely collaborated with a concurrent project at Sussex COGS involving Prof Hilary Buxton and Dr Jonathan Howell. The project will also involve the BT and BBC R&Ds. The Department of Computer Science at QMW has extensive experience in object detection, tracking and recognition for dynamic scene understanding in image sequences. Recent and current funded projects relevant to this research include ESPRIT II VIEWS for visual interpretation and evaluation of wide area scenes, RACE II Mona Lisa for virtual studios, ESPRIT III FIVE working group for immersive virtual environment, EPSRC IMV Initiative on real-time detection, tracking and recognition of moving people, EC HCM Network PAMONOP on parallel modelling of neural operators for pattern recognition, a BT Short Term Research Fellowship Scheme on real-time view-based estimation of head pose, and the EPSRC/BBC CASE program for studies on the visual segmentation and tracking of moving actors in studio environment. For further details and an application form please phone +(44) (0)171-975-5171 (24 hour answer-phone) quoting Ref. number 97135 or send an email request to sgg at dcs.qmw.ac.uk. Completed applications and CV should be returned by 20/03/98 to: The Recruitment Coordinator, Personnel Office, Queen Mary and Westfield College, Mile End Road, London, E1 4NS. QMW: WORKING TOWARDS EQUAL OPPORTUNITIES From hollidie at pcmail.aston.ac.uk Mon Feb 23 15:59:33 1998 From: hollidie at pcmail.aston.ac.uk (Ian Holliday) Date: Mon, 23 Feb 1998 15:59:33 GMT+1 Subject: postdoc + PhD Studentship: neural nets and MEG Message-ID: Postdoctoral Research Fellowship and Graduate Studentship Neural Computing Research Group Aston University Birmingham B4 7ET, U.K. The Neural Computing Research Group at Aston is looking for a highly motivated individual for a 3 year postdoctoral research position in the area of `Signal and Pattern Processing of Magnetoencephalographic Data`. The project will study single and multichannel data obtained from an Aston magnetoencephalography (MEG) facility for signal enhancement and processing. The MEG research group is engaged in basic studies of normal and abnormal vision, epilepsy, and gamma- band activity; and in clinically related studies on the localisation of eloquent cortex in pre-surgical investigations. Advanced pattern processing techniques are needed, including artificial neural network methods for enhancement, clustering, visualisation, segmentation and classification. Potential candidates should have strong mathematical and computational skills and an interest in the application of these skills to basic and clinically related neurosciences research. Knowledge of linear and nonlinear signal processing or expertise in biosignal analysis would be useful. The successful candidate will also have an opportunity to contribute to experimental work in MEG. A supported studentship is also available in the same area. Further information on this and other positions can be obtained from http://www.ncrg.aston.ac.uk/. Salaries for the Fellowship will be at or above point 6 on the RA 1A scale, currently 16927 UK pounds. These salary scales are subject to annual increments. The studentship is supported at the standard UK rate for PhD students. If you wish to be considered for this position, please send a full CV and publications list, together with the names of 3 referees, to: Prof David Lowe or Dr. Ian Holliday Neural Computing Research Group Psychology Institute Aston University Birmingham B4 7ET, U.K. Tel: 0121 333 4631 tel: 0121 359 3611 ext 4930 Fax: 0121 333 4586 fax: 0121 359 3257 e-mail: d.lowe at aston.ac.uk email: hollidie at aston.ac.uk Email submission of postscript files is welcome. Closing date: 10 April 1998. From ericr at mech.gla.ac.uk Tue Feb 24 07:20:03 1998 From: ericr at mech.gla.ac.uk (Eric Ronco) Date: Tue, 24 Feb 1998 12:20:03 GMT Subject: Constructing a Controller network Message-ID: <199802241220.MAA05138@googie.mech.gla.ac.uk> Dear all, Just to let you know of the http availability of a new technical report entitled "Two Controller Networks Automatically Constructed Through System Linearisations and Learning" (it is a compressed file. Please, gunzip the file to view or print it). It is available (among others) at: http://www.mech.gla.ac.uk/~ericr/research.html or at http://www.mech.gla.ac.uk/~yunli/reports.htm This report has been written by Eric Ronco and Peter J. Gawthrop. Its title is Two Controller Networks Automatically Constructed Through System Linearisations and Learning. The keywords are: controller network, off-equilibrium linearisation, learning Abstract: This study aims at comparing two linear controller networks as well as two methods to automaticly construct their architecture. The general idea of a controller network is to use a number of linear local controllers valid for different operating regions of a non-linear system. The two controller networks studied here are the ""Clustered Controller Network'' (CCN) and the ""Model-Controller Network'' (MCN). They differ by the method used for the selection of the controllers at each instant. In the CCN, the controllers are selected according to a spatial clustering of the operating space whereas in the MCN the selection of the controllers depends of the performance of the model associated to each local controller. The two different methods to construct the architecture of these controller networks are the ""multiple off-equilibrium system linearisations'' and the ""learning control through incremental network construction''. It is shown that these network construction methods make the two controller networks general and systematic non-linear controller design approaches. However, the selection method applied by the MCN is preferable for control purposes since it is directly related to the controller capability unlike the method implemented by the CCN. In other hand, the flexibility of the controller selection applied by the MCN makes accurate local control learning difficult to achieve. A mixture of this two methods of controller selection should remove these problems. Regards, Eric Ronco ----------------------------------------------------------------------------- | Eric Ronco | | Dt of Mechanical Engineering E.mail : ericr at mech.gla.ac.uk | | James Watt Building WWW : http://www.mech.gla.ac.uk/~ericr | | Glasgow University Tel : (44) (0)141 330 4370 | | Glasgow G12 8QQ Fax : (44) (0)141 330 4343 | | Scotland, UK | ----------------------------------------------------------------------------- From thimm at idiap.ch Tue Feb 24 12:37:14 1998 From: thimm at idiap.ch (Georg Thimm) Date: Tue, 24 Feb 1998 18:37:14 +0100 Subject: Events on Neural Networks, Vision and Speech Message-ID: <199802241737.SAA13879@rotondo.idiap.ch> ----------------------------------------- WWW page for Announcements of Conferences, Workshops and Other Events on Neural Networks, Vision and Speech ----------------------------------------- This WWW page allows you to look up and enter announcements for conferences, workshops, and other events concerned with neural networks, vision, speech, and related fields. ------------------------------------------------------------------------- Search and lookup can be restricted to events with forthcoming deadlines! ------------------------------------------------------------------------- The event lists, which is updated almost daily, contains currently more than 200 forthcoming events, and can be accessed via the URL: http://www.idiap.ch/~thimm The entries are ordered chronologically and presented in a format for fast and easy lookup of: - the date and place of the event, - the title of the event, - a contact address (surface mail, email, ftp, and WWW address, as well as telephone or fax number), and - deadlines for submissions, registration, etc. - topics of the event Conference organizers are kindly asked to enter their conference into the database. The list is in parts published in the journal Neurocomputing by Elsevier Science B.V. Information on passed conferences are also available. Kind Regards, Georg Thimm P.S. Please distribute this announcement to related mailing lists. Comments and suggestions are welcome! From Friedrich.Leisch at ci.tuwien.ac.at Wed Feb 25 10:00:42 1998 From: Friedrich.Leisch at ci.tuwien.ac.at (Friedrich Leisch) Date: Wed, 25 Feb 1998 16:00:42 +0100 Subject: CI BibTeX Collection -- Update Message-ID: <199802251500.QAA04534@galadriel.ci.tuwien.ac.at> The following volumes have been added to the collection of BibTeX files maintained by the Vienna Center for Computational Intelligence: Machine Learning 28-30 Neural Networks 10/4-9, Neural Computation 9/6-10/2, Neural Processing Letters 5/3-7/2 Most files have been converted automatically from various source formats, please report any bugs you find. The complete collection can be downloaded from http://www.ci.tuwien.ac.at/docs/ci/bibtex_collection.html ftp://ftp.ci.tuwien.ac.at/pub/texmf/bibtex/ Best, Fritz Leisch ------------------------------------------------------------------ Friedrich Leisch Institut f?r Statistik Tel: (+43 1) 58801 4541 Technische Universit?t Wien Fax: (+43 1) 504 14 98 Wiedner Hauptstra?e 8-10/1071 Friedrich.Leisch at ci.tuwien.ac.at A-1040 Wien, Austria http://www.ci.tuwien.ac.at/~leisch PGP public key http://www.ci.tuwien.ac.at/~leisch/pgp.key ------------------------------------------------------------------ From kia at particle.kth.se Fri Feb 27 10:22:03 1998 From: kia at particle.kth.se (Karina Waldemark) Date: Fri, 27 Feb 1998 16:22:03 +0100 Subject: Neural Network Workshop June-98 Message-ID: <34F6DA1B.D4C49ADB@particle.kth.se> ------------------------------------------------------------------------ VI-DYNN'98 Workshop on Virtual Intelligence - Dynamic Neural Networks Stockholm June 22-26, 1998 Royal Institute of Technology, KTH, Stockholm, Sweden ------------------------------------------------------------------------ VI-DYNN'98 Web: http://www.particle.kth.se/vi-dynn Abstracts due to: March 20, 1998 ****** papers up to 20 pages can be accepted ******* Deliver camera-ready manuscripts at registration Papers will be published by SPIE Papers will be considered for further publication in IEEE Transactions on Industrial Applications Contact: Thomas Lindblad (KTH) - Conf. Chairman email: lindblad at particle.kth.se Phone: [+46] - (0)8 - 16 11 09 ClarkS. Lindsey (KTH) - Conf. Secretary email: lindsey at particle.kth.se Phone: [+46] - (0)8 - 16 10 74 Switchboard: [+46] - (0)8 - 16 10 00 Fax: [+46] - (0)8 - 15 86 74 -------------------------------------------------------------------- Tentative Programme for VI-DYNN'98 Workshop -------------------------------------------------------------------- Monday PCNN tutorial Morning Session chair: Thomas Lindblad 1. Introduction 2. PCNN Theory 3. PCNN Image Processing 4. The PCNN Kernel 5. Target Recognition 6. Dealing with Noise Afternoon Session chair: Jason Kinser 7. Feedback 8. Object Isolation 9. Foveation 10. Image Fusion 11. Hardware Realization 12. Miscellaneous Applications and Summary Tuesday Session: Neurodynamics Session chair: Hans Liljenstrom Keynote Talk: Hans Liljenstrom, Control and amplification of cortical neurodynamics I. Opher (Tel Aviv), Data Clustering via Temporal Segmentation of Spiking Neurons Session: Electronic Nose Session chair: Hans Liljenstrom J. Waldemark (KTH) Neural Networks and PCA for determing ROI in sensory data preprocessing M. L. Padgett (Auburn U.) PCNN factoring and automated outlier detection T. A. Roppel (Auburn U.) Sensory plane analog/VLSI for interfacting sensor arrays to neural networks Session: Models of neural systems Session chair: Hans Liljenstrom Session: PCNN Applications Session chair: J. Kinser Keynote Talk: J. Kinser, Kurt Moore (Los Alamos) , 1-D Peak Fitting using PCNN J. Karvonen (Finnish Inst. Of Marine Research), PCNN for sea-ice classification from RADARSAT SAR-images V.Becanovic (KTH), PCNN for License Plate Identification O.J.Goeboden (Ostfold ), Using PCNN for SONAR Images Panel Discussion: Wednesday Session: Signals from the Brain Session chair: John Taylor Keynote Talk: JG Taylor (Kings College), Analysing Non-invasive Brain Images E. Oja, ICA Analysis of MEG and EEG Signals A. Villa, Single Cell Measurements from Behaving Animals B. Krause (Juelich), PET and Structural Brain Modelling B. Gulyas (Karolinska Inst.), B. Horwitz (NIH), Structural Modelling of PET Data A. Ioannides (Julich), MEG & the Brain Panel Discussion: Session: Defense Applications Session chair: K. Waldemark Keynote Talk: Natalie Clark, Micro-Optical Silicon Eye Authors: Natalie Clark, John Comtois, Adrian Micalicek, and Paul Furth Air Force Research Laboratory, Kirtland AFB NM 87117 I. Renhorn, (Defence Research Establishment), General Specifications for ATR J.L. Johnson J. Kinser, Pulse Couple Spiral Image Fusion Th. Lindblad, Smart sensors inspired by processes in the primate visual cortex Panel Discussion: Thursday Session: Hardware Session chair: Natalie Clark Keynote Talk: J. L. Johnson, Test Results for a 32x32 PCNN Array, J. L. Johnson, R. F Sims, and T. Branch. J. Johnson (MICOM), PCNN Chip Development J. Waldemark (KTH), PCNN in FPGA unknown (John Hopkins), PCNN Hardware IBM ZISC, Zero instruction set computer, Application for noise reduction Trento TOTEM, The Reactive Tabu Search Session: PCNN & other Algorithms Session chair: J. Waldemark G. Szekely, Adaptive PCNN J. Kinser M.Kaipainen, Sea Ice Classification using PCNN J. Johnson, PCNN Theory: State of the art Panel Discussion: Friday Tutorial Session: Virtual Intelligence Session chair: Mary Lou Padgett Theme: Virtual Intelligence Track AM Opening Remarks Keynote Talk: M. L. Padgett, Overview of Virtual Intelligence Motivational material, update on funding, hot topics, why important, how interacts with PCNN, etc. Tutorial: Overview of Neural Networks Fuzzy Systems Evolutionary Computation Rough Sets Virtual Reality Electronic Nose Description of topics, and pointers to websites and printed material for more detailed info e.g. Handbook on Applications of Computational Intelligence Eds. Padgett, Karayiannis, Zadeh CRC Press 1999 and Handbook on NeuroControl Eds. Jorgensen, Werbos and Padgett CRC Press 1999 Session: NNW Applications Session chair: Mary Lou Padgett K. Waldemark (KTH), Sleep Apnea R. Curbelo (Univ. of Uraguay), Fingerprint Identification using Neural Networks D. A. Salo (Ostfold), Neural Networks for Fingerprint identification T. Sanne (Ostfold), Neural Network for Identification Based on the Iris J. Hansen (Ostfold), Facial Recognition using Neural Networks A. Sokolov (Protvino), Hadron Energy Reconstruction by Combined Calorimeter using Neural Network L. Hildingsson,(SKI) Fuel Assembly Assessment from Digital Image Analysis Lunch and Virtual Intelligence Standards Working Group Meeting From weaveraj at helios.aston.ac.uk Mon Feb 9 05:25:05 1998 From: weaveraj at helios.aston.ac.uk (Andrew Weaver) Date: Mon, 09 Feb 1998 10:25:05 +0000 Subject: Studentship Available, Aston University, UK Message-ID: <29800.199802091025@sun.aston.ac.uk> Neural Computing Research Group, Aston University, Birmingham, UK We invite applications for EPSRC and Divisional PhD studentships in the following areas: * Neural Nets for Control: Advancing the Theory * Neural Networks for Affinity Ligand Synthesis * Statistical mechanics of support vector machines * Bayesian approaches to online learning * Advanced mean field methods for Bayesian learning * Analysing Brain-derived Magnetic Fields using Neural Networks * Non-linear Time Series Analysis: Characterisation by Feature Processing * Neural Network Analysis of Wake EEG * Image Understanding with Probabilistic Models Studentships are available to people of all nationalities, although the EPSRC studentships will only pay tuition fees and living expenses to UK citizens, and tuition fees only to (non-UK) EU citizens. Applicants should have, or expect to gain, a First Class or Upper Second Class Degree (or overseas equivalent) in a numerate discipline. The Research Group also has 5 EPSRC Advanced Course studentships for the MSc in Pattern Analysis and Neural Networks, further details of which are also available at the web pages below. In order to apply for these studentships you will need to complete an official Aston University application form, and should therefore send your name and address to ncrg at aston.ac.uk (subject line NCRG2 - IF YOU DO NOT USE THIS SUBJECT LINE YOU WILL NOT BE SENT THE CORRECT INFORMATION) by 9.00am on Friday 20th February 1998. Written applications should be received by Friday 27th March 1998. Details of the information required will be found in the covering letter sent with the application form. Further details of the Research Group and the topics can be found at http://www.ncrg.aston.ac.uk/ From Simon.N.CUMMING at British-Airways.com Mon Feb 9 13:08:04 1998 From: Simon.N.CUMMING at British-Airways.com (Simon.N.CUMMING@British-Airways.com) Date: 09 Feb 1998 18:08:04 Z Subject: ANNOUNCEMENT: NCAF Conference, SUNDERLAND 22-23April1998 Message-ID: <"BSC400A1 980209180759206661*/c=GB/admd=ATTMAIL/prmd=BA/o=British Airways PLC/s=CUMMING/g=SIMON/i=N/"@MHS> The purpose of the Neural Computing Applications Forum (NCAF) is to promote widespread exploitation of neural computing technology by: - providing a focus for neural network practitioners. - disseminating information on all aspects of neural computing. - encouraging close co-operation between industrialists and academics. NCAF holds four, two-day conferences per year, in the UK, with speakers from commercial and industrial organisations and universities. The focus of the talks is on practical issues in the application of neural network technology and related methods to solving real-world problems. ____________________________________________________________________ The April meeting will be hosted by The School of Computing and Information Systems on the St Peter's Campus of The University of Sunderland on Wednesday 22nd and Thursday 23rd April 1998. -------------------------------------------- the theme will be: DTI Neural Computing Guidelines. The 2 days will be packed with applications oriented papers as usual. There will also be adequate time for networking with other practitioners, during coffee, lunch and the Wednesday evening event. NCAF Conference at SUNDERLAND, UK. 22 - 23 April 1998 ====================================================== DTI Neural Computing Applications Guidelines Wednesday 22nd April 1998 ------------------------- Introduction and Welcome John MacIntyre, University of Sunderland 1hr overview: By a guest speaker to be announced Practical Assessment of Neural Network Applications Ian Nabney, Aston University Neural Networks and Error Bars David Lowe, Aston University Cracking the Code: a fully interactive workshop putting the Guidelines into practice Graham Hesketh, Rolls-Royce and Iain Strachan, AEA Technology From Project to Product, a Neural Based Cardiac Monitor Tom Harris, Brunel University Thursday 23rd April 1998 ------------------------ Robust Neural Networks with Confidence Bounds Julian Morris and Elaine Martin, University of Newcastle Neural Network Techniques for on-line Monitoring of Vigilance Mihaela Duta, Oxford University Applications of Normalised RBF nets to Robot Trajectories Learning Guido Bugmann, University of Plymouth Data Fusion in Complex Machine Monitoring Odin Taylor, University of Sunderland Neural Networks for Steam Leak Location Peter Mattison, University of Sunderland ____________________________________________________________________ Social Programme: The most widely acclaimed social event ever organised by NCAF was a visit to the Beamish Open Air Museum, so by popular demand we are visiting there again. plus Puzzle Corner: To Irradiate or Not To Irradiate - that is the question Graham 'Rottweiler' Hesketh (Rolls-Royce) ___________________________________________________________________ Attendance at the conference costs 100 pounds for non-members or 20 pounds for NCAF members. [Food, social event and accommodation not included]. NCAF MEMBERSHIP DETAILS: ------------------------ All amounts are in pounds Sterling, per annum. All members receive a quarterly newsletter and are eligible to vote at the AGM (but see note on corporate membership). Currently, membership includes a free copy of the book "A Guide to Neural Computing Applications" by Prof Lionel Tarassenko of Oxford University. (This book is on sale in bookshops for 29.99 pounds). Full (Corporate) Membership : 300 pounds (allows any number of people in the member organisation to attend meetings at member rates; voting rights are restricted to one, named, individual. Includes automatic subscription to the journal Neural Computing and Applications.) Individual Membership : 170 pounds (allows one, named, individual to attend meetings at member rates; includes journal) Associate Membership: 110 pounds: includes subscription to the journal and newsletter but does not cover admission to the meetings. Reduced (Student) Membership : 65 pounds including Journal; 30 pounds without journal. Applications for student membership should be accompanied by a copy of a current full-time student ID card, UB40, etc. ___________________________________________________________________ For registration, membership enquiries or further information please e-mail ncafsec at brunel.ac.uk or Phone Sally Francis (+44)(0)1784 477271 ___________________________________________________________________ From polzer at uran.informatik.uni-bonn.de Mon Feb 9 11:08:59 1998 From: polzer at uran.informatik.uni-bonn.de (Andreas Polzer) Date: Mon, 9 Feb 1998 17:08:59 +0100 (MET) Subject: CFP: ECCV Workshop on Learning in Computer Vision Message-ID: <199802091609.QAA08896@cornea.informatik.uni-bonn.de> We apologize if you receive multiple copies of this message. ------------------------------------------------------------ WORKSHOP ON LEARNING IN COMPUTER VISION in conjunction with ECCV '98 June 6, 1998 Freiburg, Germany Description ----------- In recent years rising computer performance has made it possible to exploit complex statistical models and to learn and estimate their parameters from an increasing amount of data. Therefore the issues of computational and statistical learning theory and Bayesian inference become more and more relevant for computer vision applications. Especially the related topics of generalization and choice of model complexity are of central importance in computer vision. Furthermore, the question of needed accuracy for optimization and parameter estimation turns out to be a closely related topic. The application of methods from statistical learning theory and neurally inspired approaches in computer vision are rather diverse and learning in computer vision is by no means a homogeneous field. But the necessity becomes more and more evident to take a more fundamental point of view and to clarify the multiple implications that the recent achievements of statistical learning theory have on computer vision problems. Statistical learning theory might have significant influence on many applications ranging from classification and statistical object recognition, grouping and segmentation to statistical field models and optimization. We are convinced that focussing on these joint aspects may yield a major contribution to the understanding and improvement of the diverse range of learning applications in computer vision. A workshop on learning in computer vision may greatly contribute to these goals. Workshop Issues --------------- The workshop will focus on the latest developments of learning in computer vision and will try to clarify to what extent statistical learning theory and Bayesian inference support computer vision applications. The workshop will present high quality oral contributions on any aspects of learning in computer vision, including but not restricted to the following topics: * Supervised Learning and its application to classification, support vector networks and model learning * Unsupervised Learning for structure detection in images * Robustness of Computer Vision algorithms and generalization * Probabilistic model estimation and selection, e.g. Bayesian inference for vision Attendance and Workshop Format ------------------------------ The workshop will consist of invited keynote talks and regular talks in one track. For submissions please send an extended abstract of 1-2 pages by March 31, 1998 to Workshop Learning in Computer Vision c/o Prof. Joachim Buhmann Institut fuer Informatik Roemerstrasse 164 D-53117 Bonn Germany In case of more submissions than available time slots a selection will be made based on a peer review of the submissions by the program committee. Venue ----- The workshop will be held in Freiburg, Germany on June 6, 1998 in conjunction with the European Conference on Computer Vision (ECCV '98). Program Committee ----------------- * Joachim M. Buhmann, Chair (University of Bonn, Germany) * Andrew Blake (University of Oxford, UK) * Jitendra Malik (UC Berkeley, USA) * Tomaso Poggio (MIT, USA) * Daphna Weinshall (Hebrew University, Israel) Local Organization: Andreas Polzer, Jan Puzicha (University of Bonn) To obtain further information please contact: WWW: http://www-dbv.cs.uni-bonn.de/learning.html e-mail: jan at cs.uni-bonn.de From elmar.steurer at dbag.ulm.DaimlerBenz.COM Wed Feb 11 10:25:02 1998 From: elmar.steurer at dbag.ulm.DaimlerBenz.COM (Elmar Steurer) Date: Wed, 11 Feb 1998 16:25:02 +0100 Subject: please include this CFP to your mailing list Message-ID: <34E1C2CE.51F6@dbag.ulm.DaimlerBenz.com> Call for Papers Workshop: Application of Machine Learning and Data Mining in Finance 10th European Conference on Machine Learning (ECML-98) Chemnitz, Germany, April 24 1998 General Information In conjunction with the 10th European Conference on Machine Learning (ECML-98) the workshop "Application of Machine Learning and Data Mining in Finance" will be held in Chemnitz, Germany, on April, 24th 1998. The main conference takes place from April, 21st to 23rd 1998. Motivation Advanced data analysis and forecasting technologies such as neural networks, symbolic machine learning and genetic algorithms are being increasingly applied to support financial asset management and credit risk management. These methods are considered by many financial management institutions as innovative technologies to support conventional quantitative techniques. Their use in computational finance will have a major impact in the modelling of the currency markets, in tactical asset allocation, bond and stock valuation and portfolio optimisation. In addition the application of these tools for scoring tasks delivers valuable support for the management of client credit risk. Targets This workshop is designed to bring together researchers in the field of Machine Learning with those practicing financial consulting. The purpose is twofold: - Practitioners should become familiar with the state of the art in machine learning research for predictive modelling and scoring systems. - The research community should receive ideas and requirements from participants from the financial world with the aim to improve the acceptance of Machine Learning applications and to identify future areas of research. Research papers representing new and significant developments in methodology as well as applications of practical use will be presented. Topics include: Application aspects: - Scoring systems: Application and Behavioural Scoring - Trading- and forecasting models - Volatility models - Value at Risk - Financially motivated objective functions Methodological aspects: - Symbolic Learning in financial engineering - Neural Networks for financial applications - Aspects and dependencies of data transformation and model selection - Backtest procedures: Advantages and bottlenecks - Pre-testing as an alternative to backtest - Data Mining process model for financial applications Submission of papers Authors wishing to present a paper should send an electronic version (uuencoded compressed PostScript) not later than 28 February 98 to: Dr. Elmar Steurer DAIMLER-BENZ AG - Research and Technology Postfach 2360 89013 Ulm Tel.: 0049 - 731 / 505 -2868 Fax: 0049 - 731 / 505 4210 Email: elmar.steurer at dbag.ulm.DaimlerBenz.COM Accepted papers will be published in the workshop notes. Selected papers will be issued in a proceedings. Contributors will be allocated 20 minutes for an oral presentation during the workshop. Further invited talks and a panel discussion are planned. Program committee: Ulrich Anders University of Otago, Dunedin, New Zealand Jeremy H. Armitage State Street Bank and Trust Company, London, UK Dirk Baestens Generale Bank, Brussels, Belgium Georg Bol University of Karlsruhe, Germany Guenter Grimm allfonds, Munich, Germany Tae H. Hann University of Karlsruhe, Germany Ashar Mahboob Fuji Capital Markets Corporation, New York, USA Andreas Weigend STERN Business School, New York University, USA Apostolos N. Refenes London Business School, UK Andrea Sczesny ZEW Mannheim, Germany Charles Taylor University of Leeds, UK Diethelm Wuertz ETH, Zurich, Switzerland Hans-Georg Zimmermann Siemens AG, Munich, Germany Important Dates: Submission deadline: 28 February 1998 Notification of acceptance: 15 March 1998 Camera ready copy: 28 March 1998 Workshop: 24 April 1998 Organization: Gholamreza Nakhaeizadeh and Elmar Steurer DAIMLER-BENZ AG - Research and Technology e-mail: nakhaeizadeh at dbag.ulm.DaimlerBenz.COM elmar.steurer at dbag.ulm.DaimlerBenz.COM Registration and further information: For further information about the main conference and registration please contact: ecml98 at lri.fr ecml98 at informatik.tu-chemnitz.de or visit the web site: http://www.tu-chemnitz.de/informatik/ecml98 From nnesmed at DI.Unipi.IT Wed Feb 11 11:35:33 1998 From: nnesmed at DI.Unipi.IT (Tonina Starita) Date: Wed, 11 Feb 1998 17:35:33 +0100 (MET) Subject: Final Call NNESMED`98 (Extended Deadline) Message-ID: <199802111635.RAA00554@neuron.di.unipi.it> * * * E X T E N D E D D E A D L I N E: February 27 * * * FINAL CALL FOR PAPERS 3rd International Conference on Neural Networks and Expert Systems in Medicine and Healthcare NNESMED '98 Pisa, Italy,2-4 September 1998 http://www.di.unipi.it/~nnesmed/home.htm NNESMED '98 is organised by the Computer Science Department of the University of Pisa Conference Chair: Professor Starita, University of Pisa Conference Co-Chairs: Professor Ifeachor, University of Plymouth Professor Simi University of Pisa Keynote Speakers Dr Lee Giles (USA) University of Princeton Professor Mario Stefanelli (Italy) University of Pavia Professor Paulo Lisboa (UK) Liverpool John Moores University Programme/Advisory Committee Dr Lee Giles (USA) Professor Marco Gori (Italy) Professor Emmanuel Ifeachor (UK) Dr Barrie Jervis (UK) Professor Marzuki Khalid (Malaysia) Professor Priklis Ktonas (USA) Professor Paulo Lisboa (UK) Professor George Papadurakis (Greece) Professor Karl Rosen (Sweden) Professor Maria Simi (Italy) Dr Alessandro Sperduti (Italy) Professor Mario Stefanelli (Italy) Professor Hiroshi Tanaka (Japan) Professor John Taylor (UK) Topics Neural Networks Expert Systems Soft Computing Hybrid Systems Signal Processing Fuzzy Logic Knowledge Bases DataMining Deductive Reasoning Telemedicine Tools and Applications Scope NNESMED '98 is organised by the Computer Science Department of the University of Pisa and it will be held in Pisa, on September 2-4 1998. It will provide a forum for the presentation of the results of ongoing works and research in the field of the Neural Networks and Expert Systems in Medicine and Healthcare. NNESMED '98 will be the third edition of this series and it will promote the exchange of ideas and experiences among researchers from the AI communities in medical field. Pisa is well connected to the rest of Europe by its international airport and good road and rail links. Paper submission The submission deadline is ** EXTENDED **: February 27, 1998. Papers must not exceed 4 pages, they must be written in English, with a cover page containing: * a 200-word abstract * keywords * postal and electronic mailing address * phone and fax number of the first author Submission will be electronic and available via the conference web site. Authors will be notified of the acceptance (oral and/or poster session) or rejection of their papers by May 1, 1998. Additional Information http://www.di.unipi.it/~nnesmed/home.htm e_mail: nnesmed at di.unipi.it Tel: +39-50-887215/ +39-50-887249 Fax: +39-50-887226 From priel at mail.biu.ac.il Thu Feb 12 10:02:30 1998 From: priel at mail.biu.ac.il (Avner Priel) Date: Thu, 12 Feb 1998 17:02:30 +0200 (WET) Subject: paper on time series generation Message-ID: The following paper on the subject of time series generation by feed-forward networks has appeared on the Journal of Physics A 31(4) 1189 (1998). The paper is available from my home-page : http://faculty.biu.ac.il/~priel/ comments are welcome. *************** NO HARD COPIES ****************** ---------------------------------------------------------------------- Noisy time series generation by feed-forward networks ----------------------------------------------------- A Priel, I Kanter and D A Kessler Department of Physics, Bar Ilan University, 52900 Ramat Gan,Israel ABSTRACT: We study the properties of a noisy time series generated by a continuous-valued feed-forward network in which the next input vector is determined from past output values. Numerical simulations of a perceptron-type network exhibit the expected broadening of the noise-free attractor, without changing the attractor dimension. We show that the broadening of the attractor due to the noise scales inversely with the size of the system ,$N$, as $1/ \sqrt{N}$. We show both analytically and numerically that the diffusion constant for the phase along the attractor scales inversely with $N$. Hence, phase coherence holds up to a time that scales linearly with the size of the system. We find that the mean first passage time, $t$, to switch between attractors depends on $N$, and the reduced distance from bifurcation $\tau$ as $t = a {N \over \tau} \exp(b \tau N^{1/2})$, where $b$ is a constant which depends on the amplitude of the external noise. This result is obtained analytically for small $\tau$ and confirmed by numerical simulations. ---------------------------------------------------- Priel Avner < priel at mail.biu.ac.il > < http://faculty.biu.ac.il/~priel > Department of Physics, Bar-Ilan University. Ramat-Gan, 52900. Israel. From omori at cc.tuat.ac.jp Thu Feb 12 23:32:28 1998 From: omori at cc.tuat.ac.jp (Takashi Omori) Date: Fri, 13 Feb 1998 13:32:28 +0900 Subject: Call for Paper : ICONIP'98-Kitakyushu Message-ID: <01BD3883.D43B76E0@BRAIN> ----------------------------------------- Sorry if you receive this more than once ----------------------------------------- For your remind of ICONIP'98-Kitakyushu. The dead line is March 31-st, 1998. Please refer http://jnns-www.okabe.rcast.u-tokyo.ac.jp/jnns/ICONIP98.html for latest information. The Fifth International Conference on Neural Information Processing (ICONIP'98) October 21-23,1998 Kitakyushu International Conference Center 3-9-30 Asano, Kokura-ku, Kitakyushu 802, Japan Organized by Japanese Neural Network Society (JNNS) Sponsored by Asian Pacific Neural Network Assembly (APNNA) The annual conference of the Asian Pacific Neural Network Assembly, ICONIP'98, will be held jointly with the ninth annual conference of Japanese Neural Network Society, from 21 to 23 October 1998 in Kitakyushu, Japan. The goal of ICONIP'98 is to provide a forum for researchers and engineers from academia and industries to meet and to exchange ideas on advanced techniques and recent developments in neural information processing. The conference further serves to stimulate local and regional interests in neural information processing and its potential applications to industries indigenous to this region. Topics of Interest Track$B-5(J: Neurobiological Basis of Brain Functions(J Track$B-6(J: Mathematical Theory of Brain Functions(J Track$B-7(J: Cognitive and Behavioral Aspects of Brain Functions(J Track$B-8(J: Theoretical and Technical Aspects of Neural Networks(J Track$B-9(J: Distributed Processing Systems(J Track$B-:(J: Applications of Neural Networks(J Track$B-;(J: Implementations of Neural Networks(J Topics cover (Key Words): Neuroscience, Neurobiology and Biophysics, Learning and Plasticity, Sensory and Motor Systems, Cognition and Perception Algorithms and Architectures, Learning and Generalization, Memory, Neurodynamics and Chaos, Probabilistic and Statistical Methods, Neural Coding Emotion, Consciousness and Attention, Visual and Auditory Computation, Speech and Languages, Neural Control and Robotics, Pattern Recognition and Signal Processing, Time Series Forecasting, Blind Separation, Knowledge Acquisition, Data Mining, Rule Extraction Emergent Computation, Distributed AI Systems, Agent-Based Systems, Soft Computing, Real World Systems, Neuro-Fuzzy Systems Neural Device and Hardware, Neural and Brain Computers, Software Tools, System Integration Conference Committee Conference Chair: Kunihiko Fukushima, Osaka University Conference Vice-chair: Minoru Tsukada, Tamagawa University Organizing Chair: Shuji Yoshizawa, Tokyo University Program Chair: Shiro Usui, Toyohashi University of Technology International Advisory Committee (tentative) Chair: Shun-ichi Amari, Institute of Physical and Chemical Research Members: S. Bang (Korea), J. Bezdek (USA), J. Dayhoff (USA), R. Eckmiller (Germany), W. Freeman (USA), N. Kasabov (New Zealand), H. Mallot (Germany), G. Matsumoto (Japan), N. Sugie (Japan), R. Suzuki (Japan), K. Toyama (Japan), Y. Wu (China), L.Xei (Hong Kong), J. Zurada (USA) Call for paper The Program Committee is looking for original papers on the above mentioned topics. Authors should pay special attention to explanation of theoretical and technical choices involved, point out possible limitations and describe the current states of their work. All received papers will be reviewed by the Program Committee. The authors will be informed about the decision of the review process by June 22, 1998. All accepted papers will be published. As the conference is a multi-disciplinary meeting the papers are required to be comprehensible to a wider rather than to a very specialized audience. Instruction to Authors Papers must be received by March 31, 1998. The papers must be submitted in a camera-ready format. Electronic or fax submission is not acceptable. Papers will be presented at the conference either in an oral or in a poster session. Please submit a completed full original pages and five copies of the paper written in English, and backing material in a large mailing envelope. Do not fold or bend your paper in any way. They must be prepared 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. Centered at the top of the first page should be the complete title, author(s), mailing and e-mailing addresses, followed by 100-150 words abstract and the text. Extra 2 pages are permitted with a cost of 5000 yen/page. Use black ink. Do not use any other color, either in the text or illustrations. The proceedings will be printed with black ink on white paper. In the covering letter the track and the topic of the paper according to the list above should be indicated. No changes will be possible after submission of your manuscript. Authors may also retrieve the ICONIP style "iconip98.tex", "iconip98.sty" and "sample.eps" files (they are compressed as form.tar.gz) for the conference via WWW at URL http://jnns-www.okabe.rcast.u-tokyo.ac.jp/jnns/ICONIP98.html. Language The use of English is required for papers and presentation. No simultaneous interpretation will be provided. Registration The deadline for Registration for speakers and Early Registration for non-speakers with remittance will be July 31, 1998. The registration fee for General Participant includes attendance to the conference, proceedings, banquette and reception. The registration fee for Student includes attendance to the conference and proceedings. Conference Venue Kitakyushu is a northern city in Kyushu Island, south west of Japan main islands. The place is one of the Japanese major industrial areas, and also has long history of two thousand years in Japanese and Chinese ancient records. There are direct flights from Asian and American major airports. You will be able to enjoy some technical tours and excursion in the area. Passport and Visa All foreign attendants entering Japan must possess a valid passport. Those requiring visas should apply to the Japanese council or diplomatic mission in their own country prior to departure. For details, participants are advised to consult their travel agents, air-line reservation office or the nearest Japanese mission. Events Exhibition, poster sessions, workshops, forum will be held at the conference. Two satellite workshops will be held just before or after the conference. Social Events Banquette, reception and excursion will be held at the conference. The details will be announced in the second circular. Workshops Two satellite workshops will be held. One is "Satellite workshop for young researcher on Information processing" that will be held after the conference. The detail is announced in the attached paper. Another workshop "Dynamical Brain" is under programming. This will take place in Brain Science Research Center, Tamagawa University Research Institute. The details will be announced in the Second Circular. Please see second circular for more information on these workshops, and possibly other new ones. Important Dates for ICONIP'98 Papers Due: March 31, 1998 Notification of Paper Acceptance: June 22, 1998 Second Circular (with Registration Form): June 22, 1998 Registration of at least one author of a paper: July 31, 1998 Early Registration: July 31, 1998 Conference: October 21-23, 1998 Workshop: October 24-26, 1998 Further Information & Paper Submissions ICONIP'98 Secretariat Mr. Masahito Matsue Japan Technical Information Service Sogo Kojimachi No.3 Bldg. 1-6 Kojimachi, Chiyoda-ku, Tokyo 102, Japan Tel:+81-3-3239-4565 Fax:+81-3-3239-4714 E-mail: jatisc at msn.com $B!y(J Could you suggest your friends and acquaintances who will be interested (J in ICONIP'98-Kitakyushu? Thank you. ---------------------------------------------------------------------------- - ICONIP'98-Kitakyushu 21-23 October, 1998 Tentative Registration (PLEASE PRINT) Name: Professor Dr. Ms. Mr. Last Name First Name Middle Name Affiliation: Address: Country: Telephone: Fax: E-mail: $B""(J I intend to submit a paper.(J The tentative title of my paper is: $B""(J I intend to attend the conference.(J $B""(J I want to receive the Second Circular.(J Please mail a copy of this completed form to: ICONIP'98 Secretariat Mr. Masahito Matue Japan Technical Information Service Sogo Kojimachi No.3 Bldg. 1-6 Kojimachi, Chiyoda-ku, Tokyo 102, Japan Tel:+81-3-3239-4565 Fax:+81-3-3239-4714 E-mail: jatisc at msn.com ************************************************** * Takashi Omori, Ph.D * * BASE: Biologocal Applications & Systems Engineering * * Tokyo University of Agriculture & Technology * Nakacho 2-24-16 , Koganei, Tokyo 184 Japan * +81-423-88-7148 FAX:+81-423-85-5395 * omori at cc.tuat.ac.jp ************************************************************** From jls at cs.man.ac.uk Fri Feb 13 11:17:37 1998 From: jls at cs.man.ac.uk (Jon Shapiro) Date: Fri, 13 Feb 1998 16:17:37 GMT Subject: Lectureship in Modelling of Living/Organic Systems and Information Systems Message-ID: <199802131617.QAA07007@rdf074.cs.man.ac.uk.> Hi, We are seeking applicants for an opening in the Computer Science Department at Manchester University for a Lecturer in Modelling of Living/Organic Systems and Information Systems. This is equivalent to a tenure-track Assistant Professor position in the U.S. Closing date is 28 February 1998. Please pass this on to any researcher you think might be interested. For more information, look at http://www.cs.man.ac.uk, or contact Professor John Gurd (jrg at cs.man.ac.uk). Thanks, Jonathan Shapiro ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Department of Computer Science University of Manchester A Research-Led Expansion in Computer Science has led to the establishment of the following posts: Chair in Formal Methods for Computing Science Chair and 2 Lectureships in Mobile Systems Architecture 3 Lectureships in Modelling and Simulation: Lectureships in Process Modelling and Information Engineering, Modelling of Living/Organic Systems and Information Systems. 50 Years after the first stored-program electronic digital computer was developed at the University of Manchester, the Department of Computer Science at Manchester remains a world leader in research and teaching in Computer Science. We are looking to appoint staff with international research reputation or potential. These new posts offer individuals with appropriate experience an opportunity to contribute to world leading research developments from a position of strength. See our Web Page http://www.cs.man.ac.uk for further details. From SaadE at TTACS.TTU.EDU Fri Feb 13 16:29:10 1998 From: SaadE at TTACS.TTU.EDU (Emad William Saad) Date: Fri, 13 Feb 1998 15:29:10 -0600 Subject: Explanation Capability of Neural Networks Message-ID: <34E4BB26.D086E4EE@ttu.edu> I have been doing litterature search on the subject of "Explanation Capability of Neural Networks/ Rule extraction of NN's", and came with the following bibliography: [1] Fu, Y., ?Data mining: Tasks, techniques and applications,? Potentials, vol. 16, no. 4, pp. 18-20, 1997. [2] Andrews, R., Diederich, J., and Tickle, A., ?A Survey and Critique of Techniques for Extracting Rules from Trained Artificial Neural Networks,? Knowledge-Based Systems, vol. 8, no. 6, pp. 373-389, 1996. [3] Benitez, J. M., Castro, J. L., and Requena, I., ?Are Artificial Neural Networks Black Boxes?,? IEEE Trans. Neural Networks, vol. 8, no. 5, pp. 1156-1164, 1997. [4] Tsukimoto, H., ?Extracting Propositions from Trained Neural Networks,? in Proc. IEEE International Conference on Neural Networks, August 1997. [5] Kindermann, J., and Linden, A., ?Detection of Minimal Microfeatures by Internal Feedback,? in Proc. fifth Austrian Artificial Intelligence Meeting, pp. 230-239, 1989. [6] Healy, M. J., and Caudell, T. P., ?Acquiring Rule Sets as a Product of Learning in a Logical Neural Architecture,? IEEE Trans. Neural Networks, vol. 8, no. 3, pp. 461-474, 1997. [7] Yeung, D. S., and Hak-shun, Fong, "Knowledge Matrix - An Explanation and Knowledge Rrefinement Facility for a Rule Induced Neural Network," in Proc. Twelfth National Conference on Artificial Intelligence, 1994, vol. 2, pp. 889-894. [8] Machado, R. J., and da Rocha, A. F., "Inference, Inquiry, Evidence Censorship, and Explanation in Connectionist Expert Systems," IEEE Trans. Fuzzy Systems, vol. 5, no. 3, pp 443-459. [9] Gilstrap, L. O., and Dominy, R. E., "A General Explanation and Interogation System for Neural Networks," in Proc. International Joint Conference on Neural Networks, Washington, DC, June 1989, vol. 2, pp. 594. [10] Taha, I., and Ghosh, J., "Evaluation and Ordering of Rules Extracted from Feedward Networks," in Proc. IEEE International Conference on Neural Networks, Houston, TX, June 1997, vol. 1, pp. 408-413. [11] Ornes, C., and Sklansky, J., "A Neural Network that Explains as Well as Predicts Financial Market Behavior," in Proc. IEEE/IAFE Computational Intelligence for Financial Engineering, March 1997, pp. 43-49. [12] Ornes, C., and Sklansky, J., "A Visual Multi-Expert Neural Classifier," in Proc. IEEE International Conference on Neural Networks, June 1997, vol. 3, pp. 1448-1453. [13] Taha, I., and Ghosh, J., "Three techniques for extracting rules from feedforward networks," in Intelligent Engineering Systems Through Artificial Neural Networks, vol. 6., ASME Press, November 1996. Please, I would be glad if anybody can guide me to more litterature/ web pages/ resources in this area. Emad Saad Applied Computational Intelligence Laboratory Dept. of Electrical Eng. Texas Tech University, Lubbock, TX 79409 From kr10000 at eng.cam.ac.uk Mon Feb 16 05:46:34 1998 From: kr10000 at eng.cam.ac.uk (K. Reinhard) Date: Mon, 16 Feb 1998 10:46:34 GMT Subject: Announcement of Technical Report availability. Message-ID: <199802161046.11893@opal.eng.cam.ac.uk> The following technical report is available by anonymous ftp from the archive of the Speech, Vision and Robotics Group at the Cambridge University Engineering Department (http://svr-www.eng.cam.ac.uk/reports/index-full.html). PARAMETRIC SUBSPACE MODELING OF SPEECH TRANSITIONS K. Reinhard and M. Niranjan Technical Report CUED/F-INFENG/TR.308 Cambridge University Engineering Department Trumpington Street, Cambridge CB2 1PZ U.K., England Abstract This report describes an attempt at capturing segmental transition information for speech recognition tasks. The slowly varying dynamics of spectral trajectories carries much discriminant information that is very crudely modelled by traditional approaches such as HMMs. In approaches such as recurrent neural networks there is the hope, but not the convincing demonstration, that such transitional information could be captured. The method presented here starts from the very different position of explicitly capturing the trajectory of short time spectral parameter vectors on a subspace in which the temporal sequence information is preserved. We approach this by introducing a temporal constraint into the well known technique of Principal Component Analysis. On this subspace, we attempt a parametric modelling of the trajectory, and compute a distance metric to perform classification of diphones. We use the principal curves method of Hastie and Stuetzle and the Generative Topographic map (GTM) technique of Bishop, Svenson and Williams to describe the temporal evolution in terms of latent variables. On the difficult problem of /bee/, /dee/, /gee/ we are able to retain discriminatory information with a small number of parameters. Experimental illustrations present results on ISOLET and TIMIT database. From robbie at hiki.bcs.rochester.edu Mon Feb 16 12:52:32 1998 From: robbie at hiki.bcs.rochester.edu (Robbie Jacobs) Date: Mon, 16 Feb 1998 12:52:32 -0500 Subject: postdoc position available Message-ID: <199802161752.MAA14907@hiki.bcs.rochester.edu> Postdoctoral Fellowship, Department of Brain and Cognitive Sciences, UNIVERSITY OF ROCHESTER -- The Department of Brain and Cognitive Sciences seeks an outstanding postdoctoral fellow with research interests in the areas of learning and/or developmental cognitive science. Supervising faculty work on the problems of learning and development using behavioral, computational, and neurobiological approaches. Candidates should have prior background/training in at least one of these approaches and an interest in working collaboratively in a highly interdisciplinary setting. Several faculty have special interest in statistical learning in the domains of language and perception, although a commitment to this interest is not a requirement of all applicants. This fellowship is open only to US citizens or permanent residents. Applicants should send a letter describing their graduate training and research interests, a curriculum vitae, and arrange to have three letters of recommendation sent to: Learning, Development, and Biology Training, Department of Brain and Cognitive Sciences, Meliora Hall, University of Rochester, Rochester, NY 14627-0268. Review of applications will begin on April 1, 1998 and continue until the position is filled, with an expected start date of August/September, 1998. Applicants can learn about the department, its faculty, and the opportunities for training by referring to our Web page (http://www.bcs.rochester.edu). Applications from women and members of underrepresented minority groups are especially welcome. The University of Rochester is an Equal Opportunity Employer. From eugene at engr.uconn.edu Mon Feb 16 08:48:18 1998 From: eugene at engr.uconn.edu (Eugene Santos) Date: Mon, 16 Feb 1998 08:48:18 -0500 Subject: [CFP] AI Meets the Real World '98 Lessons Learned! Message-ID: <199802161348.IAA11288@ultra9.uconn.edu> [Sorry if you get this message more than once! It is being posted to several distribution lists.] ------------------------------------------------------------------------------- ------------------------------------------------------------------------------- AI meets the Real World '98 Lessons Learned C a l l f o r P a r t i c i p a t i o n September 16 - 18, 1998 University of Connecticut -- Stamford Campus Stamford, CT Sponsored by: University of Connecticut Honeywell Technology Center US Air Force Research Labs -- Phillips Lab DARPA To a large and growing extent, techniques from the field of Artificial Intelligence are being applied in the implementation of fielded systems addressing practical problems in a wide range of domains, from manufacturing, to consumer services, to military and spacecraft operations, to name a very few. As a result, an informal and pragmatic practice of "AI engineering" has arisen, involving the identification, adaptation, and application of techniques including diagnostic systems, trend analysis and projection, uncertain reasoning and decision analysis, virtual environments/reality, training and tutoring systems, planning and scheduling, natural language parsing and generation, and parameter estimation and other forms of learning. The resulting systems range from large-scale, stand-alone intelligent systems, to embedded knowledge bases, to minor components of much larger applications. As one might expect from a body of work largely developed within a common intellectual and philosophical tradition, what we have here broadly termed "AI techniques" have some common features. These approaches tend to be complex and computationally intensive and to require a great deal of understanding and modelling, in some cases engineering, of the target domain and application for the approach to be successful. The aim of this meeting is to bring together researchers, practitioners, and developers of intelligent systems throughout academia, industry, and government to discuss and disseminate lessons learned from successful (or unsuccessful) attempts to design, construct, field, and maintain intelligent systems. The meeting will consist of presentations, panel discussions, and invited speakers. Our hope is to build a better knowledge base of how to successfully apply and correctly use artificial intelligence in real world systems. This meeting is not intended as a forum for those who already deeply immersed in AI. We particularly welcome people who are considering an AI-based approach to their problem to attend and participate in these discussions. We invite the submission of papers and topic ideas for panel discussions. Papers and presentations should be based on systems developed (or in progress) for real world use. Among the issues that might be of interest in such a presentation we would expect to find the following: -- What characteristics of the domain and the application lead to your choice of solution method? What alternative methods were considered and rejected? Were these choices revisited (and revised?) at some later point? -- What difficulties did you encounter? Which ones were expected? Unexpected? -- What was the final outcome? What qualifications or modifications of the original statement of the problem or system requirements were made? -- What lessons can be drawn from this experience, regarding: +++ domains where particular AI techniques are or aren't useful? +++ how to go about determining the utility of a technique in a new domain? +++ pitfalls to beware in system design, implementation, etc., that are peculiar to intelligent systems? We are also especially INTERESTED in soliciting questions/issues at all levels from both new and experienced systems builders on problems and approaches of using AI. Members of our program committee will attempt to answer and/or provide advice to these questions. These will be published in our printed proceedings. Of these, a select set of questions or general class of questions will be chosen for a special panel discussion session at the conference. Up-to-date meeting information will be provided at: http://www.eng2.uconn.edu/~eugene/AIMTRW Proceedings of invited papers will be published. ---------------- | Organizers | ---------------- Meeting Co-Chairs - ----------------- Eugene Santos, Jr. (University of Connecticut -- Storrs) Mark Boddy (Honeywell Technology Center, Minneapolis, MN) Doug Dyer (DARPA) Program Committee - ----------------- Sheila B. Banks (Air Force Institute of Technology) Piero Bonissone (GE) Jack Breese (Microsoft) Wray Buntine (Ultimode) Fabio Cozman (University of Sao Paulo) Bruce D'Ambrosio (Prevision & Oregon State University) Neal Glassman (Air Force Office of Scientific Research) James Hendler (University of Maryland) Chahira Hopper (Air Force Research Labs, Wright Lab) Lewis Johnson (University of Southern California) F. Alex Kilpatrick (Air Force Research Labs, Phillips Lab) Michael B. Leahy Jr. (DARPA) Claudia M. Meyer (NASA LERC) Alan L. Meyrowitz (Naval Research Laboratory) Doug Moran (SRI) Steve Rogers (Battelle) Solomon Eyal Shimony (Ben Gurion University of the Negev) Mike Shneier (Office of Naval Research) Valerie J. Shute (Air Force Research Labs, Armstrong Lab) Douglas Smith (Kestrel Institute) Martin R. Stytz (Air Force Institute of Technology) Abraham Waksman (Air Force Office of Scientific Research) Fred A. Watkins (Hyperlogic) Edward Wong (Polytechnic University) --------------------------- | Submission Guidelines | --------------------------- Authors should submit full papers addressing the above issues with a strong emphasis on "lessons learned." These will be evaluated for clarity of presentation and significance of contribution to the community. All accepted papers will be presented either orally or through a poster session and will be made available in a printed proceedings. Papers may be submitted either electronically or in hard copy form. Electronic submission may take the form of PostScript files, ASCII, or LaTeX files. Authors should be careful to include all macro files necessary for LaTeX files as we will not be responsible for files which cannot be formatted. Figures for LaTeX should be PostScript files. Hardcopy submissions should have 1-inch margins on all sides and should be in 12-point type. Papers should be a maximum of 20 pages long, including figures and references. Names, address, and e-mail of authors and an abstract should be included at the beginning of each paper. Hard copy submissions must arrive by May 15, 1998, and sent to Eugene Santos, Jr. [ATTN: AIMTRW-98] Computer Science and Engineering Department University of Connecticut UTEB, 191 Auditorium Rd., U-155 Storrs, CT 06269-3155 (860) 486-1458 Electronic submissions should be e-mailed by May 15, 1998, to eugene at eng2.uconn.edu Papers not meeting the deadline will not be considered. Proposals for panel discussions and invited speakers should be e-mailed by May 15, 1997, to the above address. For questions/issues, we solicit up to two (2) pages per question. Provide as much detail as possible for proper evaluation of the question by the program committee. We prefer electronic submissions to the above email address. Hard copy is welcome to the above address. These are also due May 15, 1998. ++++++++++++++++++++++++++++++++++++++ !++Meeting Attendance/Participation++! ++++++++++++++++++++++++++++++++++++++ Due to the limited space available for this meeting, we request that those planning to attend send an e-mail by May 1, 1998 to eugene at eng2.uconn.edu stating your intent and whether you will be also submitting a paper. --------------------- | Important Dates | --------------------- May 1, 1998 Deadline for participation request May 15, 1998 Deadline for paper submission May 15, 1998 Deadline for question submission May 15, 1998 Deadline for panel proposals, etc. June 15, 1998 Notification of acceptance or rejection June 29, 1998 Final camera-ready papers due September 16 - 18, 1998 Meeting dates From kirchmai at informatik.tu-muenchen.de Mon Feb 16 09:39:59 1998 From: kirchmai at informatik.tu-muenchen.de (Clemens Kirchmair) Date: Mon, 16 Feb 1998 15:39:59 +0100 (MET) Subject: Early registration deadline for FNS'98: 02/18/1998 Message-ID: ######################################################################### ATTENTION: The early registration deadline for the FNS '98 Workshop is Wednesday, February 18th, 1998. You can still save 100,- DM if you register now! Don't miss this excellent workshop! (Full program -- see below) The 5th International Workshop "Fuzzy-Neuro Systems '98 - Computational Intelligence" takes place in Munich, Germany, from March 19 to 20, 1998. Visit our WWW Homepage: http://wwwbrauer.informatik.tu-muenchen.de/~fns98/ Conference fees (registration UNTIL February 18th) industry rate: 495,- DM university rate: 345,- DM GI members: 295,- DM students (up to age of 26): 60,- DM (excluding proceedings and conference dinner.) Conference fees (registration AFTER February 18th) industry rate: 595,- DM university rate: 445,- DM GI members: 395,- DM students (up to age of 26): 160,- DM (excluding proceedings and conference dinner.) ######################################################################### ---------------------------------- | Fuzzy-Neuro Systems '98 | | - Computational Intelligence - | | | | 5th International Workshop | | March, 19 - 20, 1998 | ---------------------------------- Technische Universitaet Muenchen Gesellschaft fuer Informatik e.V. Fachausschuss 1.2 "Inferenzsysteme" Technische Universitaet Muenchen Institut fuer Informatik Fuzzy-Neuro Systems '98 is the fifth event of a well established series of workshops with international participation. Its aim is to give an overview of the state of art in research and development of fuzzy systems and artificial neural networks. Another aim is to highlight applications of these methods and to forge innovative links between theory and application by means of creative discussions. Fuzzy-Neuro Systems '98 is being organized by the Technical Committee 1.2 "Inference Systems" (Fachausschuss 1.2 "Inferenzsysteme") of the German Informatics Society GI (Gesellschaft fuer Informatik e. V.) and Institut fuer Informatik, Technische Universitaet Muenchen in cooperation with Siemens AG and with the support of Kratzer Automatisierung GmbH. The workshop takes place at the Technische Universitaet Muenchen in Munich from March, 19 to 20, 1998. PROGRAM ------- Wednesday, March 18, 1998 18:00 Informal Get-Together Registration 21:00 End of reception and registration Thursday, March 19, 1998 8:00 Registration 9:00 Formal Opening President, TU Muenchen Dekan, Institut fuer Informatik, TU Muenchen Workshop Chair 9:15 Invited Lecture 1: Sets, Fuzzy Sets and Rough Sets Zdzislaw Pawlak, Warsaw University of Technology, Poland Chairman: W. Brauer, TU Muenchen 10:00 Session 1: Fuzzy Control Chairman: R. Isermann, TU Darmstadt Indirect Adaptive Sugeno Fuzzy Control J. Abonyi, L. Nagy, S. Ferenc, University of Veszprem, Veszprem, Hungary Simultaneous Creation of Fuzzy Sets and Rules for Hierarchical Fuzzy Systems R. Holve, FORWISS, Erlangen, Germany 10:50 Coffee break - Presentation of Posters 11:10 Session 2: Neural Networks for Classification Chairman: K. Obermayer, TU Berlin Hybrid Systems for Time Series Classification C. Neukirchen, G. Rigoll, Gerhard-Mercator-Universitaet, Duisburg How Parallel Plug-in Classifiers Optimally Contribute to the Overall System W. Utschick, J.A. Nossek, TU Muenchen 12:00 Invited Lecture 2: Is Readibility Compatible with Accuracy? Hugues Bersini, Universite Libre de Bruxelles, Belgium Chairman: J. Hollatz, Siemens AG, Muenchen 12:45 Lunch 14:00 Session 3: Fuzzy Logic in Data Analysis Chairman: C. Freksa, Universitaet Hamburg Fuzzy Topographic Kernel Clustering T. Graepel, K. Obermayer, TU Berlin Dynamic Data Analysis: Similarity Between Trajectories A. Joentgen, L. Mikenina, R. Weber, H.-J. Zimmermann, RWTH Aachen Spatial Reasoning with Uncertain Data Using Stochastic Relaxation R. Moratz, C. Freksa, Universitaet Hamburg Noise Clustering For Partially Supervised Classifier Design C. Otte, P. Jensch, Universitaet Oldenburg Fuzzy c-Mixed Prototypes Clustering C. Stutz, TU Muenchen T.A. Runkler, Siemens AG, Muenchen 16:00 Coffee break - Presentation of Posters 16:30 Invited Lecture 3: Neural Network Architectures for Time Series Prediction with Applications to Financial Data Forecasting Hans-Georg Zimmermann, Siemens AG, Muenchen Chairman: R. Rojas, FU Berlin 17:15 Session 4: Fuzzy-Neuro Systems Chairman: R. Kruse, Universitaet Magdeburg A Neuro-Fuzzy Approach to Feedforward Modeling of Nonlinear Time Series T. Briegel, V. Tresp, Siemens AG, Muenchen A Learning Algorithm for Fuzzy Neural Nets T. Feuring,Westfaelische Wilhelms-Universitaet Muenster James J. Buckley, University of Alabama at Birmingham, Birmingham, USA Improving a priori Control Knowledge by Reinforcement Learning M. Spott, M. Riedmiller, Universitaet Karlsruhe 18:30 End of First Day 20:00 Conference Dinner Friday, March 20, 1998 9:00 Session 5: Applications Chairman: G. Nakhaeizadeh, Daimler Benz AG, Forschung + Technik, Ulm Batch Recipe Optimization with Neural Networks and Genetice Algorithms K. Eder, Kratzer Automatisierung GmbH, Unterschleissheim Robust Tuning of Power System Stabilizers by an Accelerated Fuzzy-Logic Based Genetic Algorithm M. Khederzadeh, Power and Water Institute of Technology, Tehran, Iran Relating Chemical Structure to Activity: An Application of the Neural Folding Architecture T. Schmitt, C. Goller, TU Muenchen Optimization of a Fuzzy System Using Evolutionary Algorithms Q. Zhuang, M. Kreutz, J. Gayko, Ruhr-Universitaet Bochum 10:40 Coffee break - Presentation of Posters 11:00 Invited Lecture 4: Advanced Fuzzy-Concepts and Applications Harro Kiendl, Universitaet Dortmund Chairman: K. Eder, Kratzer Automatisierung GmbH, Unterschleissheim 11:45 Session 6: Theory and Foundations of Fuzzy-Logic Chairman: P. Klement, Universitaet Linz, Austria Rule Weights in Fuzzy Systems D. Nauck, R. Kruse, Universitaet Magdeburg Sliding-Mode-Based analysis of Fuzzy Gain Schedulers - The MIMO Case R. Palm, Siemens AG, Muenchen D. Driankov, University of Linkoeping, Sweden Qualitative Operators For Dealing With Uncertainty H. Seridi, Universite de Reims, France F. Bannay-Dupin, Universite d'Angers, France H. Akdag, Universite P. & M. Curie, Paris, France 13:00 Lunch 14:00 Session 7: Theory and Foundations of Neural Networks Chairman: A. Grauel, Universitaet Paderborn Prestructured Recurrent Neural Networks T. Brychcy, TU Muenchen Formalizing Neural Networks I. Fischer, University of Erlangen M. Koch, Technical University of Berlin M.R. Berthold, University of California, Berkeley, USA Correlation and Regression Based Neuron Pruning Strategies M. Rychetsky, S. Ortmann, C. Labeck, M. Glesner, TU Darmstadt 15:15 Invited Lecture 5: Soft Computing: the Synergistic Interaction of Fuzzy, Neural, and Evolutionary Computation Piero P. Bonissone, General Electric Corporate R&D Artificial Intelligence Laboratory, Schenectady, USA Chairman: S. Gottwald, Universitaet Leipzig 16:00 Closing Remarks and Invitation to FNS'99 Posters ------- Comparing Fuzzy Graphs M.R. Berthold, University of California, Berkeley, USA K.-P. Huber, Universitaet Karlsruhe A Numerical Approach to Approximate Reasoning via a Symbolic Interface. Application to Image Classification A. Borgi, H. Akdag, Universite P. & M. Curie, Paris, France J.-M. Bazin, Universite de Reims, France Entropy-Controlled Probabilistic Search M. David, J. Gottlieb, I. Kupka, TU Clausthal Ensembles of Evolutionary Created Artificial Neural Networks C.M. Friedrich, Universitaet Witten/Herdecke Design and Implementation of a Flexible Simulation Tool for Hybrid Problem Solving H. Geiger, IBV and TU Muenchen J. Pfalzgraf, K. Frank, T. Neuboeck, J. Weichenberger, Universitaet Salzburg, Austria A. Buecherl, TU Muenchen A Fuzzy Invariant Indexing Technique for Object Recognition under Partial Occlusion T. Graf, A. Knoll, A. Wolfram, Universitaet Bielefeld Fuzzy Causal Networks R. Hofmann, V. Tresp, Siemens AG, Muenchen Dynamic Data Analysis: Problem Description And Solution Approaches A. Joentgen, L. Mikenina, R. Weber, H.-J. Zimmermann, RWTH Aachen Filtering and Compressing Information by Neural Information Processor R. Kamimura, Tokai University, Japan A Fuzzy Local Map with Asymmetric Smoothing Using Voronoi Diagrams B. Lang, Siemens AG, Muenchen Fuzzy Interface with Prior Concepts and Non-convex Regularization J.C. Lemm, Universitaet Muenster Modeling and Simulating a Time-Dependent Physical System Using Fuzzy Techniques and a Recurrent Neural Network A. Nuernberger, A. Radetzky, R. Kruse, Universitaet Magdeburg The Kohonen Network Incorporating Explicit Statistics and Its Application to the Traveling Salesman Problem B.J. Oommen, Carleton University, Ottawa, Canada Automated Feature Selection Strategies: An experimental comparison improving Engine Knock Detection S. Ortmann, M. Rychetsky, M. Glesner, TU Darmstadt A Fuzzy-Neuro System for Reconstruction of Multi-Sensor information S. Petit-Renaud, T. Deneux, Universite de Technologie de Compiegne, Compiegne, France RACE: Relational Alternating Cluster Estimation and the Wedding Table Problem T.A. Runkler, Siemens AG, Muenchen J.C. Bezdek, University of West Florida, Pensacola, USA Neural Networks Handle Technological Information for Milling if Training Data is Carefully Preprocessed G. Schulz, D. Fichtner, A. Nestler, J. Hoffmann, TU Dresden Medically Motivated Testbed for Reinforcement Learning in Neural Architectures D. Surmeli, G. Koehler, H.-M. Gross, TU Ilmenau Adaptive Input-Space Clustering for Continuous Learning Tasks M. Tagscherer, P. Protzel, FORWISS, Erlangen A Criminalistic And Forensic Application Of Neural Networks A. Tenhagen, T. Feuring, W.-M. Lippe, G. Henke, H. Lahl, WWU-Muenster A Classical and a Fuzzy System Based Algorithm for the Simulation of the Waste Humidity in a Landfill M. Theisen, M. Glesner, TU Darmstadt FuNN, A Fuzzy Neural Logic Model R. Yasdi, GMD - Forschungszentrum Informationstechnik, Sankt Augustin An Efficient Model for Learning Systems of High-Dimensional Input within Local Scenarios J. Zhang, V. Schwert, Universitaet Bielefeld Optimization of a Fuzzy Controller for a Driver Assistant System Q. Zhuang, J. Gayko, M. Kreutz, Ruhr-Universitaet-Bochum Program Committee ----------------- Prof. Dr. W. Banzhaf, Universitaet Dortmund Dr. M. Berthold, Universitaet Karlsruhe Prof. Dr. Dr. h.c. W. Brauer, TU Muenchen (Chairman) Prof. Dr. G. Brewka, Universitaet Leipzig Dr. K. Eder, Kratzer Automatisierung GmbH, Unterschleissheim Prof. Dr. C. Freksa, Universitaet Hamburg Prof. Dr. M. Glesner, TU Darmstadt Prof. Dr. S. Gottwald, Universitaet Leipzig Prof. Dr. A. Grauel, Universitaet Paderborn/Soest Prof. Dr. H.-M. Gross, TU Ilmenau Dr. A. Guenter, Universitaet Bremen Dr. J. Hollatz, Siemens AG, Muenchen Prof. Dr. R. Isermann, TU Darmstadt Prof. Dr. P. Klement, Universitaet Linz, Austria Prof. Dr. R. Kruse, Universitaet Magdeburg (Vice Chairman) Prof. Dr. B. Mertsching, Universitaet Hamburg Prof. Dr. G. Nakhaeizadeh, Daimler Benz AG, Forschung + Technik, Ulm Prof. Dr. K. Obermayer, TU Berlin Prof. Dr. G. Palm, Universitaet Ulm Dr. R. Palm, Siemens AG, Muenchen Dr. L. Peters, GMD - Forschungszentrum Informationstechnik GmbH, Sankt Augustin Prof. Dr. F. Pichler, Universitaet Linz, Austria Dr. P. Protzel, FORWISS, Erlangen Prof. Dr. B. Reusch, Universitaet Dortmund Prof. Dr. Rigoll, Universitaet Duisburg Prof. Dr. R. Rojas, Freie Universitaet Berlin Prof. Dr. B. Schuermann, Siemens AG, Muenchen (Vice Chairman) Prof. Dr. W. von Seelen, Universitaet Bochum Prof. Dr. H. Thiele, Universitaet Dortmund Prof. Dr. W. Wahlster, Universitaet Saarbruecken Prof. Dr. H.-J. Zimmermann, RWTH Aachen Organization Committee ---------------------- Prof. Dr. Dr. h.c. W. Brauer (Chairman) Dieter Bartmann Till Brychcy Clemens Kirchmair Technische Universitaet Muenchen Tel.: 0 89/2 89-2 84 19 Fax: 0 89/2 89-2 84 83 Dr. Juergen Hollatz, Siemens AG, Muenchen (Vice Chairman) Christine Harms, - ccHa -, Sankt Augustin Conference Site --------------- TU Muenchen Barerstrasse 23 Entrance: Arcisstrasse Lecture hall S0320 D-80333 Muenchen Workshop Secretariat -------------------- Christine Harms c/o GMD / FNS'98 Schloss Birlinghoven D-53754 Sankt Augustin Tel.: ++49 2241 14-24 73 Fax: ++49 2241 14-24 72 email: christine.harms at gmd.de Registration ------------ Please make your (binding) reservation by sending the enclosed registration form to the conference secretariat. Confirmation will be given after receipt of the registration form. Conference Fees: (see registration form) industry rate: 495,- DM university rate: 345,- DM GI members: 295,- DM authors: 295,- DM students (up to age of 26): 60,- DM (*) *) excluding proceedings and conference dinner. A surcharge of DM 100,- is payable for registration after February, 18, 1998. Services of Gesellschaft fuer Informatik e. V. (GI) are VAT-free according to German law p. 4 Nr. 22a UStG. Payment (see registration form) ------- [ ] I have transferred the whole amount of DM________ to Gesellschaft fuer Informatik (GI), Sparkasse Bonn Account No.: 39 479 Bankcode: 380 500 00 Ref: SK-Fuzzy-98 [ ] I enclose a Eurocheque amounting to made payable to Gesellschaft fuer Informatik [ ] Please debit my [ ] Diners [ ] Visa [ ] Euro/Mastercard Cardnumber: Expiration date: Cardholder: Social events ------------- Informal get-together: March, 18, 1998, 18.00 - 21.00 Conference dinner: Thursday, March, 19,1998. Accommodation ------------- A limited number of rooms has been reserved at the FORUM/Penta Hotel at the special rate of single room DM 175,- double room DM 200,- FORUM Hotel Hochstrasse 3 D-81669 Muenchen Cancellation ------------ If cancellation is received up to February, 17, 1998, a 75% refund will be given. For cancellations received afterwards, no refunds can be guaranteed. WWW-Homepage ------------ URL: http://wwwbrauer.informatik.tu-muenchen.de/~fns98/ ----- snip, snip ----- Registration form for Fuzzy-Neuro Systems '98 --------------------------------------------- Please register me as follows Conference Fees: ---------------- [ ] industry rate: 495,- DM [ ] university rate: 345,- DM [ ] GI member No. 295,- DM [ ] authors: 295,- DM [ ] students (up to age of 26): 60,- DM (*) *) excluding proceedings and conference dinner Accommodation: -------------- I would like to make a binding reservation at the FORUM/Penta Hotel [ ] single room DM 175,- [ ] double room DM 200,- (together with ____________________________) Arrival date ______________________________ Departure date ___________________________ Payment directly at the hotel. Hotel booking has to be made until February, 17, 1998. After that we cannot guarantee any bookings. Conference diner: ----------------- [ ] I intend to participate in the conference dinner ...... extra ticket for conference dinner DM 50,-. Payment: -------- [ ] I have transferred the whole amount of DM________ to Gesellschaft fuer Informatik (GI), Sparkasse Bonn Account No.: 39 479 Bankcode: 380 500 00 Reference: SK-Fuzzy-98 [ ] I enclose a Eurocheque amounting to DM_________ made payable to Gesellschaft fuer Informatik [ ] Please debit my [ ] Diners [ ] Visa [ ] Euro/Mastercard Cardnumber:______________Expiration date:_________ Cardholder:_______________________________________ If cancellation is received up to February, 17, 1998, a 75% refund will be given. For cancellations received afterwards, no refunds can be guaranteed. Date:___________ Signature:__________________ Sender: ------- Last Name (Mr. / Mrs. / MS. Title): ________________________________________ First Name: ________________________________________ Affiliation: ________________________________________ Street/POB: ________________________________________ Zip/Postal Code/City: ________________________________________ Country: ________________________________________ Phone/Fax: ________________________________________ E-mail: ________________________________________ If you would like to take part in the workshop, please send the completed registration form to Christine Harms c/o GMD / FNS'98 Schloss Birlinghoven D-53754 Sankt Augustin Tel.: ++49 2241 14-24 73 Fax: ++49 2241 14-24 72 email: christine.harms at gmd.de From pfbaldi at netid.com Tue Feb 17 16:04:07 1998 From: pfbaldi at netid.com (pfbaldi@netid.com) Date: Tue, 17 Feb 1998 21:04:07 +0000 Subject: Book on Bioinformatics Message-ID: <199802180507.VAA21966@polaris.pacificnet.net> The following book is now available from MIT Press: Bioinformatics: the Machine Learning Approach Pierre Baldi and Soren Brunak February 1998 ISBN 0-262-02442-X 360 pp., 62 illus., 10 color $40.00 (cloth) MIT Press (800) 625-8569 (617) 253-5249 (617) 258-6894 (FAX) Additional information can be found at: http://mitpress.mit.edu/book-home.tcl?isbn=026202442X -------------------------------------------------------------------------- Table of Contents Series Foreword Preface 1 Introduction 1.1 Biological Data in Digital Symbol Sequences 1.2 Genomes--Diversity, Size, and Structure 1.3 Proteins and Proteomes 1.4 On the Information Content of Biological Sequences 1.5 Prediction of Molecular Function and Structure 2 Machine Learning Foundations: The Probabilistic Framework 2.1 Introduction: Bayesian Modeling 2.2 The Cox-Jaynes Axioms 2.3 Bayesian Inference and Induction 2.4 Model Structures: Graphical Models and Other Tricks 2.5 Summary 3 Probabilistic Modeling and Inference: Examples 3.1 The Simplest Sequence Models 3.2 Statistical Mechanics 4 Machine Learning Algorithms 4.1 Introduction 4.2 Dynamic Programming 4.3 Gradient Descent 4.4 EM/GEM Algorithms 4.5 Markov Chain Monte Carlo Methods 4.6 Simulated Annealing 4.7 Evolutionary and Genetic Algorithms 4.8 Learning Algorithms: Miscellaneous Aspects 5 Neural Networks: The Theory 5.1 Introduction 5.2 Universal Approximation Properties 5.3 Priors and Likelihoods 5.4 Learning Algorithms: Backpropagation 6 Neural Networks: Applications 6.1 Sequence Encoding and Output Interpretation 6.2 Prediction of Protein Secondary Structure 6.3 Prediction of Signal Peptides and Their Cleavage Sites 6.4 Applications for DNA and RNA Nucleotide Sequences 7 Hidden Markov Models: The Theory 7.1 Introduction 7.2 Prior Information and Initialization 7.3 Likelihood and Basic Algorithms 7.4 Learning Algorithms 7.5 Applications of HMMs: General Aspects 8 Hidden Markov Models: Applications 8.1 Protein Applications 8.2 DNA and RNA Applications 8.3 Conclusion: Advantages and Limitations of HMMs 9 Hybrid Systems: Hidden Markov Models and Neural Networks 9.1 Introduction to Hybrid Models 9.2 The Single-Model Case 9.3 The Multiple-Model Case 9.4 Simulation Results 9.5 Summary 10 Probabilistic Models of Evolution: Phylogenetic Trees 10.1 Introduction to Probabilistic Models of Evolution 10.2 Substitution Probabilities and Evolutionary Rates 10.3 Rates of Evolution 10.4 Data Likelihood 10.5 Optimal Trees and Learning 10.6 Parsimony 10.7 Extensions 11 Stochastic Grammars and Linguistics 11.1 Introduction to Formal Grammars 11.2 Formal Grammars and the Chomsky Hierarchy 11.3 Applications of Grammars to Biological Sequences 11.4 Prior Information and Initialization 11.5 Likelihood 11.6 Learning Algorithms 11.7 Applications of SCFGs 11.8 Experiments 11.9 Future Directions 12 Internet Resources and Public Databases 12.1 A Rapidly Changing Set of Resources 12.2 Databases over Databases and Tools 12.3 Databases over Databases 12.4 Databases 12.5 Sequence Similarity Searches 12.6 Alignment 12.7 Selected Prediction Servers 12.8 Molecular Biology Software Links 12.9 Ph.D. Courses over the Internet 12.10 HMM/NN Simulator A Statistics A.1 Decision Theory and Loss Functions A.2 Quadratic Loss Functions A.3 The Bias/Variance Trade-off A.4 Combining Estimators A.5 Error Bars A.6 Sufficient Statistics A.7 Exponential Family A.8 Gaussian Process Models A.9 Variational Methods B Information Theory, Entropy, and Relative Entropy B.1 Entropy B.2 Relative Entropy B.3 Mutual Information B.4 Jensen's Inequality B.5 Maximum Entropy B.6 Minimum Relative Entropy C Probabilistic Graphical Models C.1 Notation and Preliminaries C.2 The Undirected Case: Markov Random Fields C.3 The Directed Case: Bayesian Networks D HMM Technicalities, Scaling, Periodic Architectures, State Functions, and Dirichlet Mixtures D.1 Scaling D.2 Periodic Architectures D.3 State Functions: Bendability D.4 Dirichlet Mixtures E List of Main Symbols and Abbreviations References Index -------------------------------------------------------------------------------- From dblank at comp.uark.edu Tue Feb 17 23:47:51 1998 From: dblank at comp.uark.edu (Douglas Blank) Date: Tue, 17 Feb 1998 22:47:51 -0600 Subject: PhD Thesis: "Learning to See Analogies: A Connectionist Exploration" Message-ID: <3.0.32.19980217224749.00710f30@comp.uark.edu> The following Ph.D. thesis is now available via - anonymous ftp (ftp://dangermouse.uark.edu/pub/thesis) - web site (http://www.uark.edu/~dblank/thesis.html) - hardcopy (send address to dblank at comp.uark.edu) It is about 200 pages long and the chapters can be retrieved individually as PostScript or PDF files. (Specific retrieval instructions below). Title: Learning to See Analogies: A Connectionist Exploration Douglas S. Blank Joint Ph.D. in Cognitive Science and Computer Science Indiana University, Bloomington ABSTRACT This dissertation explores the integration of learning and analogy-making through the development of a computer program, called Analogator, that learns to make analogies by example. By "seeing" many different analogy problems, along with possible solutions, Analogator gradually develops an ability to make new analogies. That is, it learns to make analogies by analogy. This approach stands in contrast to most existing research on analogy-making, in which typically the a priori existence of analogical mechanisms within a model is assumed. The present research extends standard connectionist methodologies by developing a specialized associative training procedure for a recurrent network architecture. The network is trained to divide input scenes (or situations) into appropriate figure and ground components. Seeing one scene in terms of a particular figure and ground provides the context for seeing another in an analogous fashion. After training, the model is able to make new analogies between novel situations. Analogator has much in common with lower-level perceptual models of categorization and recognition; it thus serves as a unifying framework encompassing both high-level analogical learning and low-level perception. This approach is compared and contrasted with other computational models of analogy-making. The model's training and generalization performance is examined, and limitations are discussed. =========================================================== Title, Abstract, Acknowledgments, Contents 0_intro.pdf 54k 0_intro.ps.gz 71k Chapter 1 INTRODUCTION 1_ch.pdf 172k 1_ch.ps.gz 187k Chapter 2 ANALOGY-MAKING, LEARNING, AND GENERALIZATION 2_ch.pdf 32k 2_ch.ps.gz 40k Chapter 3 CONNECTIONIST FOUNDATIONS 3_ch.pdf 221k 3_ch.ps.gz 189k Chapter 4 THE ANALOGATOR MODEL 4_ch.pdf 578k 4_ch.ps.gz 390k Chapter 5 EXPERIMENTAL RESULTS 5_ch.pdf 702k 5_ch.ps.gz 566k Chapter 6 COMPARISONS WITH OTHER MODELS OF ANALOGY-MAKING 6_ch.pdf 305k 6_ch.ps.gz 276k Chapter 7 CONCLUSION 7_ch.pdf 16k 7_ch.ps.gz 24k APPENDICES, REFERENCES 8_end.pdf 57k 8_end.ps.gz 91k Everything all.pdf 2M all.ps.gz 1M =========================================================== FTP instructions: (e.g., to retrieve Chapter 1) unix> ftp dangermouse.uark.edu Name: anonymous Password: youremail at domain ftp> cd pub/thesis ftp> get 1_ch.ps.gz ftp> bye unix> gunzip 1_ch.ps.gz unix> lpr 1_ch.ps ===================================================================== dblank at comp.uark.edu Douglas Blank, University of Arkansas Assistant Professor Computer Science ==================== http://www.uark.edu/~dblank ==================== From erik at bbf.uia.ac.be Wed Feb 18 11:37:34 1998 From: erik at bbf.uia.ac.be (Erik De Schutter) Date: Wed, 18 Feb 1998 16:37:34 GMT Subject: 1998 Crete Course in Computational Neuroscience Message-ID: <199802181637.QAA14539@kuifje.bbf.uia.ac.be> CRETE COURSE IN COMPUTATIONAL NEUROSCIENCE SEPTEMBER 13 - OCTOBER 9, 1998 FORTH INSTITUTE, CRETE, GREECE DIRECTORS: Erik De Schutter (University of Antwerp, Belgium) Adonis Moschovakis (University of Crete, Greece) Idan Segev (Hebrew University, Jerusalem, Israel) The Crete Course in Computational Neuroscience introduces students to the practical application of computational methods in neuroscience, in particular how to create biologically realistic models of neurons and networks. The course consists of two complimentary parts. A distinguished international faculty gives morning lectures on topics in experimental and computational neuroscience. The rest of the day is spent learning how to use simulation software and how to implement a model of the system the student wishes to study. The first week of the course introduces students to the most important techniques in modeling single cells, networks and neural systems. Students learn how to use the GENESIS, NEURON, XPP and other software packages on their individual unix workstations. During the following three weeks the lectures will be more general, but each week topics ranging from modeling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the the brain will be covered. The course ends with a presentation of the students' modeling projects. The Crete Course in Computational Neuroscience is designed for advanced graduate students and postdoctoral fellows in a variety of disciplines, including neuroscience, physics, electrical engineering, computer science and psychology. Students are expected to have a basic background in neurobiology as well as some computer experience. A total of 28 students will be accepted with an age limit of 35 years. We will accept students of any nationality, but the majority will be from the European Union and affiliated countries (Iceland, Israel, Liechtenstein and Norway). We specifically encourage applications from researchers who work in less-favoured regions of the EU, from women and from researchers from industry. Every student will be charged a tuition fee of 700 ECU (approx. US$770). In the case of students with a nationality from the EU, affiliated countries or Japan, this tuition fee covers lodging, local travel and all course-related expenses. All applicants with other nationalities will be charged an ADDITIONAL fee of 1000 ECU (approx. US$1100) to cover lodging, local travel and course-related expenses. For nationals from EU and affiliated countries economy travel from an EU country to Crete will be refunded after the course. A limited number of students from less-favoured regions world-wide will get their fees and travel refunded. More information and application forms can be obtained: - WWW access: http://bbf-www.uia.ac.be/Crete_index.html Please apply electronically using a web browser if possible. - email: crete_course at bbf.uia.ac.be - by mail: Prof. E. De Schutter Born-Bunge Foundation University of Antwerp - UIA, Universiteitsplein 1 B2610 Antwerp Belgium FAX: +32-3-8202669 APPLICATION DEADLINE: May 1, 1998. Applicants will be notified of the results of the selection procedures by May 31. FACULTY: M. Abeles (Hebrew University Jerusalem, Israel), A. Aertsen (Albert Ludwigs University Freiburg, Germany), A. Borst (Max Planck Institute Tuebingen, Germany), R. Calabrese (Emory University, USA), R. Douglas (Institute of Neuroinformatics, Zurich), G. Dupond (Free University Brussels, Belgium), O. Ekeberg (Royal Institute of Technology, Sweden), A. Feltz (University of Strasbourg, France), T. Flash (Weizmann Institute of Science, Israel), D. Hansel (Ecole Polytechnique Paris, France), J.J.B. Jack (Oxford University, England), R. Kotter (Heinrich Heine University Dusseldorf, Germany), G. LeMasson (University of Bordeaux, France), K. Martin (Institute of Neuroinformatics, Zurich), M. Nicolelis (Duke University, USA), G. Rizzolatti (University of Parma, Italy), J.M. Rinzel (NIH, USA), H. Sompolinsky (Hebrew University Jerusalem, Israel), M. Spira (Hebrew University Jerusalem, Israel), S. Tanaka (RIKEN, Japan), C. Wilson (University of Tennessee, USA), Y. Yarom (Hebrew University Jerusalem, Israel) and others to be named. The Crete Course in Computational Neuroscience is supported by the European Commission (4th Framework Training and Mobility of Researchers program) and by The Brain Science Foundation (Tokyo). Local administrative organization: the Institute of Applied and Computational Mathematics of FORTH (Crete, GR). From cmbishop at microsoft.com Wed Feb 18 11:14:08 1998 From: cmbishop at microsoft.com (Christopher Bishop) Date: Wed, 18 Feb 1998 08:14:08 -0800 Subject: Paper and software available on-line Message-ID: <3FF8121C9B6DD111812100805F31FC0D810C85@red-msg-59.dns.microsoft.com> Paper and Software Available Online: A HIERARCHICAL LATENT VARIABLE MODEL FOR DATA VISUALIZATION NCRG/96/028 Christopher M. Bishop* and Michael E. Tipping# * Microsoft Research St. George House, 1 Guildhall Street Cambridge CB2 3NH, U.K. # Neural Computing Research Group Aston University, Birmingham B4 7ET, U.K. http://neural-server.aston.ac.uk/Papers/postscript/NCRG_96_028.ps.Z Abstract: Visualization has proven to be a powerful and widely-applicable tool for the analysis and interpretation of multi-variate data. Most visualization algorithms aim to find a projection from the data space down to a two-dimensional visualization space. However, for complex data sets living in a high-dimensional space it is unlikely that a single two-dimensional projection can reveal all of the interesting structure. We therefore introduce a hierarchical visualization algorithm which allows the complete data set to be visualized at the top level, with clusters and sub-clusters of data points visualized at deeper levels. The algorithm is based on a hierarchical mixture of latent variable models, whose parameters are estimated using the expectation-maximization algorithm. We demonstrate the principle of the approach on a toy data set, and we then apply the algorithm to the visualization of a synthetic data set in 12 dimensions obtained from a simulation of multi-phase flows in oil pipelines, and to data in 36 dimensions derived from satellite images. A Matlab(R) software implementation of the algorithm is publicly available from the world-wide web. Paper: http://neural-server.aston.ac.uk/Papers/postscript/NCRG_96_028.ps.Z Software: http://www.ncrg.aston.ac.uk/PhiVis Complete searchable database of publications: http://neural-server.aston.ac.uk/ ---------------------------------------------------------------------------- ---- Professor Christopher M. Bishop Microsoft Research, Cambridge St. George House, 1 Guildhall Street Cambridge CB2 3NH Tel: +44/0 1223 744 751 Fax: +44/0 1223 744 777 Email: cmbishop at microsoft.com Web: http://www.ncrg.aston.ac.uk/People/bishopc/Welcome.html ---------------------------------------------------------------------------- ---- From SteinR at moodys.com Wed Feb 18 11:20:49 1998 From: SteinR at moodys.com (Stein, Roger) Date: Wed, 18 Feb 1998 11:20:49 -0500 Subject: Adaptive and intelligent systems in business: Book available Message-ID: Members of the Santa Fe Institute mailing list may have already received this. Apologies... SEVEN METHODS FOR TRANSFORMING CORPORATE DATA INTO BUSINESS INTELLIGENCE by Vasant Dhar and Roger Stein Upper Saddle River, NJ, Prentice-Hall, 1997. My colleague, Vasant Dhar, and I have written a short book on applying intelligent and adaptive systems to business problems. It may be of interest to some subscribers. There are two versions of the book available, one is suited to business people and one is suited to teaching. The book provides a practical methodology for mapping business problems onto solutions involving neural networks, genetic algorithms, nearest-neighbor algorithms, etc. We also provide extended case studies of organizations that have successfully done this. The reaction to the book, in both the academic and professional community, seems to be favorable: "Intelligent Systems are becoming vital at all levels of management from the CEO to the foreman. Dhar and Stein provide one of the clearest and most accessible treatments to date of the subject." - Herbert A. Simon, Nobel Laureate "Seven Methods effectively bridges the gap between lofty technical explanation and the down-to-earth business application of a brand new world of modeling technologies." - Win Farrell, Partner, Coopers and Lybrand A brief summary of the book follows: Seven Methods for Transforming Corporate Data into Business Intelligence combines a thorough treatment of techniques for applying intelligent systems to decision support with a practical framework for analyzing business problems. Vasant Dhar (former Principal, Morgan Stanley and New York University) and Roger Stein (Vice President, Moody's Investors Service and New York University) present in clear and vivid terms the essentials of modern decision support. Seven Methods takes a three stage approach to discussing these new technologies. The book is organized around: * A framework for analyzing business decision problems and mapping solutions onto them * An intuitive but full discussion of the technologies for data mining and automated decision systems * A series of extensive case studies that show, using the framework, how major organizations have made use of these technologies In addition to discussing technologies, Dhar and Stein introduce a unified methodology for analyzing organizations' business problems and evaluating potential solutions. This framework, based on the authors' years of combined experience applying intelligent systems to real business decision problems, encourages business people to think critically about how the strengths and weaknesses of each technique relate to the particular dynamics of an organization and its problems. The authors show not only when a particular modeling method may be useful, but also when its attributes might make it undesirable for a particular problem. The text does not limit itself to one or a few techniques, but rather views various AI and database techniques as components of a toolbox that, if used correctly, can make organizations dramatically more intelligent. Seven Methods provides accessible detailed coverage of * OLAP and data warehousing * Genetic algorithms * Neural networks * Rule-based expert systems * Fuzzy systems * Case-based reasoning * Machine learning The text adopts an informal, conversational style in their exposition. Despite the relaxed style, the book delves into the subtle aspects of each technique while keeping the text readable and non-technical. In order to make the material more accessible, the text makes frequent use of rich graphics. The graphical representation of complex concepts are invaluable in elucidating these topics. To drive home the discussions of modeling techniques and organizational dynamics, the book also provides extended case studies that show in detail how the framework can be applied to analyzing the problems of real organizations. Cases are taken from the experience of firms in a diversity of industries solving an assortment of problems. Firms include: * US WEST * Moody's Investors Service * Compaq Computer Corp. * LBS Capital Management * NYNEX, Inc. * Kaufhof AG * A. C. Neilsen Problem domains include: * customer service * scheduling * data mining * financial market prediction * quality control * consumer product marketing The book is available from Prentice-Hall: (Professional version) Seven Methods for Transforming Corporate Data into Business Intelligence, Upper Saddle River, NJ, Prentice-Hall, 1997. (Academic version) Intelligent Decision Support Methods: The Science of Knowledge Work, Upper Saddle River, NJ, Prentice-Hall, 1997. Online Orders: www.amazon.com Phone: 1-(800) 643-5506. Please give the operator the following "key code": E1001-A1(3). FAX: 1-(800) 835-5327. From annesp at vaxsa.csied.unisa.it Wed Feb 18 10:46:29 1998 From: annesp at vaxsa.csied.unisa.it (annesp@vaxsa.csied.unisa.it) Date: Wed, 18 Feb 1998 16:46:29 +0100 Subject: summer school Message-ID: <98021816462905@vaxsa.csied.unisa.it> From: SMTP%"iiass at tin.it" 18-FEB-1998 16:34:18.19 To: annesp at vaxsa.csied.unisa.it CC: Subj: call ***************************************************************** Please post **************************************************************** International Summer School ``Neural Nets E. R. Caianiello" 3rd Course "A Course on Speech Processing, Recognition, and Artificial Neural Networks" web page: http://wsfalco.ing.uniroma1.it/Speeschool.html The school is jointly organized by: INTERNATIONAL INSTITUTE FOR ADVANCED SCIENTIFIC STUDIES (IIASS) Vietri sul Mare (SA) Italy, ETTORE MAJORANA FOUNDATION AND CENTER FOR SCIENTIFIC CULTURE (EMFCSC) Erice (TR), Italy Supported by: EUROPEAN SPEECH COMMUNICATION ASSOCIATION (ESCA) Sponsored by: SALERNO UNIVERSITY, Dipartimento di Scienze Fisiche E.R. Caianiello (Italy) DIRECTORS OF THE COURSE DIRECTORS OF THE SCHOOL AND ORGANIZING COMMITTEE: Gerard Chollet (France). Maria Marinaro (Italy) M. Gabriella Di Benedetto (Italy) Michael Jordan (USA) Anna Esposito (Italy) Maria Marinaro (Italy) PLACE: International Institute for Advanced Scientific Studies (IIASS) Via Pellegrino 19, 84019 Vietri sul Mare, Salerno (Italy) DATES: 5th-14th October 1998 POETIC TOUCH Vietri (from "Veteri", its ancient Roman name) sul Mare ("on sea") is located within walking distance from Salerno and marks the beginning of the Amalfi coast. Short rides take to Positano, Sorrento, Pompei, Herculaneum, Paestum, Vesuvius, or by boat, the islands of Capri, Ischia, and Procida. Velia (the ancient "Elea" of Zeno and Parmenide) is a hundred kilometers farther down along the coast. Student Fee: 1500 dollars Student fee include accommodations (arranged by the school), meals, one day of excursion, and a copy of the proceedings of the school. Transportation is not included. A few scholarships are available for students who are otherwise unable to participate at the school, and who cannot apply for the grants offered by ESCA. The scholarship will partially cover lodging and living expenses. Day time: 3 hour in the morning, three hour in the afternoon. Day free: One day with an excursion of the places around. AIMS: The aim of this school is to present the experiments, the theories and the perspectives of acoustic phonetics, as well as to discuss recent results in the speech literature. The school aims to provide a background for further study in many of the fields related to speech science and linguistics, including automatic speech recognition. The school will bring together leading researchers and selected students in the field of speech science and technology to discuss and disseminate the latest techniques. The school is devoted to an international audience and in particular to all students and scientists who are working on some aspects of speech and want to learn other aspects of this discipline. MAJOR TOPICS The school will cover a number of broad themes relevant to speech, among them: 1) Speech production and acoustic phonetics 2) Articulatory, acoustic, and prosodic features 3) Acoustic cues in speech perception 4) Models of speech perception 5) Speech processing (Preprocessing algorithms for Speech) 6) Neural Networks for automatic speech recognition 7) Multi-modal speech recognition and recognition in adverse environments. 8) Speech to speech translation (Vermobil and CSTAR projects) 9) Applications (Foreign Language training aids, aids for handicapped, ....). 10) Stochastic Models and Dialogue systems FORMAT The meeting will follow the usual format of tutorials and panel discussions together with poster sessions for contributed papers. The following tutorials are planned: ABEER ALWAN UCLA University (CA) USA "Models of Speech Production and Their Application in Coding and Recognition" ANDREA CALABRESE University of Connecticut (USA) "Prosodic and Phonological Aspects of Language" GERARD CHOLLET CNRS - ENST France ALISP, Speaker Verification, Interactive Voice Servers" RENATO DE MORI Universite d' Avignon, France "Statistical Methods for Automatic Speech Recognition" M. GABRIELLA DI BENEDETTO Universita' degli Studi di Roma "La Sapienza", Rome, Italy ``Acoustic Analysis and Perception of Classes of Sounds (vowels and consonants)" BJORN GRANSTROM Royal Institute of Technology (KTH) Sweden "Multi-modal Speech Synthesis with Application" JEAN P. HATON Universite Henri-Poincare, CRIN-INRIA, France "Neural Networks for Automatic Speech Recognition" HYNEK HERMANSKY Oregon Graduate Institute, USA "Goals and Techniques of Speech Analysis" JOHN OHALA University of California at Berkeley (CA) USA "Articulatory Constraints on Distinctive Features" JEAN SYLVAIN LIENARD LIMSI-CNRS, France "Speech Perception, Voice Perception" "Beyond Pattern Recognition" PROCEEDINGS The proceedings will be published in the form of a book containing tutorial chapters written by the lecturers and possibly shorter papers from other participants. One free copy of the book will be distributed to each participant. LANGUAGE The official language of the school will be English. POSTER SUBMISSION There will be a poster session for contributed presentations from participants. Proposals consisting of a one page abstract for review by the organizers should be submitted with applications. DURATION Participants are expected to arrive in time for the evening meal on Sunday 4th October and depart on Tuesday 15th October. Sessions will take place from Monday 5th-Wednesday 14th. COST The cost per participant of 1.500 $ dollars covers accommodation (in twin rooms), meals for the duration of the course, and one day of excursion. -- A supplement of 40 dollars per night should be paid for single room. Payment details will be notified with acceptance of applications. GRANTS -- A few ESCA grants are available for participants (which cover tuition and, maybe, part of the lodging). See http://ophale.icp.inpg.fr/esca/grants.html for further information. Individual applications for grants should be sent to Wolfgang Hess by e-mail: wgh at sunwgh.ikp.uni-bonn.de ELIGIBILITY The school is open to all suitably qualified scientists from around the world. APPLICATION PROCEDURE: Important Date: Application deadline: May 15 1998 Notification of acceptance: May 30 1998 Registration fee payment deadline: July 10 1998 People with few years of experience in the field should include a recommendation letter of their supervisor or group leader Places are limited to a maximum of 60 participants in addition to the lecturers. These will be allocated on a first come, first served basis. ************************************************************************** APPLICATION FORM Title:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Family Name:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Other Names:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Name to appear on badge:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Mailing Address (include institution or company name if appropriate): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Phone:^^^^^^^^^^^^^^^^^^^^^^Fax:^^^^^^^^^^^^^^^^^^^ E-mail:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Date of Arrival : Date of Departure: Will you be applying for a ESCA grant ? yes/no* *(please delete the alternatives which do not apply) Will you be applying for a scholarship ? yes/no* *(please delete the alternatives which do not apply) *(please include in your application a justification for scholarship request) ***************************************************************** Please send the application form together the recommendation letter by electronic mail to: iiass at tin.it, subject: summer school; or by fax: +39 89 761 189 (att.ne Prof. M. Marinaro) or by ordinary mail to the address below: IIASS Via Pellegrino 19, I84019 Vietri sul Mare (Sa) Italy For further information please contact: Anna Esposito International Institute for advanced Scientific Studies (IIASS) Via Pellegrino, 19, 84019 Vietri sul Mare (SA) Italy Fax: + 39 89 761189 e-mail: annesp at vaxsa.csied.unisa.it ================== RFC 822 Headers ================== From iiass at tin.it Wed Feb 18 09:56:12 1998 From: iiass at tin.it (IIASS) Date: Wed, 18 Feb 1998 15:56:12 +0100 Subject: call Message-ID: <34EAF68C.2DF0@tin.it> From lek at cict.fr Thu Feb 19 10:02:23 1998 From: lek at cict.fr (Sovan LEK) Date: Thu, 19 Feb 1998 16:02:23 +0100 Subject: Neural Networks Workshop Message-ID: <1.5.4.32.19980219150223.00aec2b4@mail.cict.fr> INTERNATIONAL WORKSHOP ON APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS TO ECOLOGICAL MODELLING (2nd circular) 14-17 December 1998, Toulouse (FRANCE) Local Organizing Committee: Dr. Sovan Lek, CESAC, UMR 5576 du CNRS, UPS, B?t IVR3, 118 route de Narbonne, F-31062 Toulouse cedex 4, France Phone: 33-5 61 55 86 87 Fax: 33-5 61 55 60 96 E-mail: lek at cict.fr Dr. Jean-Fran?ois Gu?gan, ORSTOM, D?partement Biologie, Ecologie & Evolution, Laboratoire d'Hydrobiologie marine et Continentale, Universit? de Montpellier II (USTL), C.C. 093, place E. Bataillon, 34095 Montpellier cedex 05, France. Phone: 33 4 67 14 37 51 Fax : 33 4 67 14 46 46 E-mail : guegan at crit.univ-montp2.fr BACKGROUND You are cordially invited to attend the first "International Workshop on the Application of Artificial Neural Networks to Ecological Modelling" to be held at the Centre d'Ecologie des Syst?mes Aquatiques Continentaux in Toulouse (France). Toulouse is France's fourth largest city (650,350 people with suburbs), and is the European Space capital. It is situated on the Garonne river in very lush surroundings. The Toulouse of today is a lively university town (with more than 100,000 students) and has a rich medieval history. OBJECTIVES: Predictive modelling is a major concern in theoretical ecology, evolution and environmental sciences. Relationships between variables in natural systems are frequently non-linear, and thus conventional modelling tools could appear to be inappropriate to capture the complexity of such systems. This International Workshop will bring together theoretical and applied biological research, practitioners, and developers, as well as domain scientists from multiple ecological disciplines, for the presentation and exchange of current research and on concepts, tools and techniques for scientific and non linear statistical application in ecology, evolution and environmental sciences. The objectives are: ? To promote collaboration among scientists of different interested countries and research fields encouraging both teaching and research collaboration. ? To consider recent advances in Artificial Neural Networks to modelling data (identification, control, prediction, classification problems,...). INVITED SPEAKERS: Dr. S.E. Jorgensen (DK): Ecological Modelling: State of the Art. Pr. R. Tomassone (Fr): Dynamic systems and experimental planning: from data to modelling Dr. P. Bourret (Fr): Non -supervised classification: from observations to assumption. Dr. A. Teriokhin (Russia): On Neural Networks capable to realize evolutionarily optimal animal strategies of growth and reproduction in a seasonal environment. Pr. P. Auger (Fr): Non-linear Modelling in Ecology: from Individuals to Populations. Dr. F. Recknagel (Australia): Elucidation and Prediction of Aquatic Ecosystems by Artificial Neural Networks THEMES (you need to report your choice in the reply form, section Publication, which sub-theme?): o Pattern Recognition o Pattern Classification o Clustering and Classification o Diagnosis and Monitoring o Prediction and Control o Signal Processing o Temporal and Spatial Sequences PUBLICATION Final Instructions for Submission of Abstracts: o Abstract deadline: Abstracts must be submitted in English style, and received by the organisers before 1 April 1998. All abstracts will be refereed before final acceptance. o Please give complete name of your institution, followed by town and country. o The text of your abstract must be informative and contain: 1) a statement of the study's specific aims; 2) a statement of the method used; 3) a summary of results obtained; 4) a statement of conclusion. Avoid non-informative sentences. o Format: Abstracts must not exceed one page (format A4) and be sent directly by electronic mail to Drs. Lek or Gu?gan. If your abstract is too long it will be shortened by the organisers. The publication of the oral contributions is being considered. Please indicate if you are interested in submitting your paper for consideration in a special volume. Original papers will be published on merit in a special volume of the Springer Verlag Environmental Science Series. Other papers will form a special issue of Ecological Modelling. Both Editing Houses have been contacted and have accepted to co-edit these two special volumes. All contributions will be reviewed by at least two referees before acceptance for publication. SUBMISSION GUIDELINES OF PAPER(S) All contributions must be submitted by September 30th of 1998 to the Organizing Committee. Research papers should be up to 8,000 words long. All papers for publication should be sent by electronic mail (Ms-Word) or by post (4 hard-copies are needed) to Dr. Sovan Lek. All papers will be acknowledged of receipt. A notification of acceptance, modification or refusal will be sent by November 15th of 1998 to delegates having submitted a contribution with details given on which publication (hard volume of Springer Verlag or special issue of Ecological Modelling) the paper will be proposed. GENERAL INFORMATION: Languages: French and English will be the two official languages during the Conference, but abstracts, posters, and published papers will be exclusively written in English style. Venue: The Conference venue will be the Conference Centre of Toulouse University. This venue is ideal for a medium conference (about 150 people), with excellent, modern facilities which will allow for productive exchanges of ideas. Dates: Monday 14 December 1998 to Thursday 17 December 1998. Travel: Destination is Toulouse. Delegates must make their own travel arrangements to at least this destination. From dsilver at mgmt.dal.ca Fri Feb 20 18:17:40 1998 From: dsilver at mgmt.dal.ca (Daniel L. Silver) Date: Fri, 20 Feb 1998 23:17:40 +0000 Subject: Tech. Report - Task Rehearsal Method of Sequential Learning Message-ID: <199802210318.XAA24285@Snoopy.UCIS.Dal.Ca> Dear colleagues, the following TR is now available: "The Task Rehearsal Method of Sequential Learning" Department of Computer Science Univeristy of Western Ontario Technical Report # 517 Daniel L. Silver and Robert E. Mercer Abstract An hypothesis of functional transfer of task knowledge is presented that requires the development of a measure of task relatedness and a method of sequential learning. The "task rehearsal method" (TRM) is introduced to address the issues of sequential learning, namely retention and transfer of knowledge. TRM is a knowledge based inductive learning system that uses functional domain knowledge as a source of inductive bias. The representations of successfully learned tasks are stored within domain knowledge. "Virtual examples" generated by domain knowledge are rehearsed in parallel with the each new task using either the standard multiple task learning (MTL) or the $\eta$MTL neural network methods. The results of experiments conducted on a synthetic domain of seven tasks demonstrate the method's ability to retain and transfer task knowledge. TRM is shown to be effective in developing hypothesis for tasks that suffer from impoverished training sets. Difficulties encountered during sequential learning over the diverse domain reinforce the need for a more robust measure of task relatedness. ---------------------------------------------------------------------- Comments are welcome! Download sites: http://www.csd.uwo.ca/~dsilver/trmpaper.ps or http://www.csd.uwo.ca/~dsilver/trmpaper.ps.Z ////////////////////////////////////////////////////////////////////// Daniel L. Silver CogNova Technologies Phone: (902) 582-7558 1226 J.Jordan Road Fax: (902) 582-3140 Canning,Nova Scotia Dal.U: (902) 494-1813 Canada B0P 1H0 Email: dsilver at mgmt.dal.ca Homepage: http://www.meadoworks.ns.ca/cognova /////////////////////////////////////////////////////////////// From marwan at ee.usyd.edu.au Mon Feb 23 04:28:33 1998 From: marwan at ee.usyd.edu.au (Marwan Jabri) Date: Mon, 23 Feb 1998 20:28:33 +1100 (EST) Subject: Post-doctoral fellowship Message-ID: Post-Doctoral Fellow Department of Electrical Engineering The University of Sydney Applications are invited for Post-doctoral fellow position funded by an Australian Research Council project grant. The three-year project aims at investigating computational models of the superior colliculus, the implementation of the models in microelectronics and their integration in sensorimotor control systems. The fellow will join a group several academics and doctoral students working on biological models for sensorimotor control. The research is a collaboration between M. Jabri (Elec. Eng., Sydney University) S. Carlile (Physiology, Sydney University) and T. Sejnowski (Salk Institute). The fellow will be based in Sydney, but will be expected to travel and spend several weeks every year at the Salk Institute. Applicants would have completed (or about to complete) their PhD in electrical, computer or related engineering or science discipline and have demonstrated research capacity in the area of neuromorphic engineering, computational neurobiology or microelectronics. Appointment will be made initially for a period of one year, and renewable for another two years subject to progress. Expected starting date in May, 1998. Closing date: March 20, 1998 Salary range: A$34k-46k To apply, send letter of application, CV and names, fax and email of three referees to M. Jabri Tel (+61-2) 9351 2240, Fax (+61-2) 9351 7209, Email: marwan at sedal.su.oz.au From Nicolino.Pizzi at nrc.ca Mon Feb 23 10:12:54 1998 From: Nicolino.Pizzi at nrc.ca (Pizzi, Nicolino) Date: Mon, 23 Feb 1998 10:12:54 -0500 Subject: Postdoctoral Research Opportunity - University of Manitoba Message-ID: POSTDOCTORAL RESEARCH OPPORTUNITY - COMPUTER ENGINEERING HYBRID KNOWLEDGE-BASED CLASSIFICATION OF VOLUMETRIC PATTERNS Pending final approval, a postdoctoral position is available within the Electrical and Computer Engineering Department to participate in an NSERC-funded strategic research project investigating hybrid knowledge-based classification of volumetric patterns. The position is for a one-year term with a possible one year renewal. The research project will be conducted in close collaboration with Prof. W. Pedrycz and Dr. N. Pizzi. Volumetric (three-dimensional) data are found in many application areas such as radar scans of meteorological formations. These data normally contain a number of three-dimensional regions of interest (ROI's) that belong to several classes. The classification of an ROI is determined by some well-established reference test. In the case of meteorological radar scans, the ROI's may be cloud formations that cause severe weather, the classes may be hail, heavy rain, wind, or tornadic events, and the reference test might be eye-witness accounts of the storm events. The intent of this project is to develop a comprehensive pattern recognition methodology aimed at such data and propose a suite of classification algorithms that can take a ROI and produce a classification outcome that matches the class to which it was assigned by the corresponding reference test. A number of factors can confound the classification process. It may become difficult to glean any discriminating features from volumetric data if it contains noise due to limitations of sensors, instrumentation, or the data acquisition process. Moreover, the ROI's may be extremely complex in nature. Several preprocessing methods are proposed in order to transform the original ROI in order to eliminate or diminish the effects of noise and/or reduce the dimensionality of the input space as well as focus the classification effort on the most significant features. The problem of identifying discriminating features is further aggravated by the fact that the accepted reference test itself may be imprecise or even unreliable. Finally, the volumetric data may be incomplete and sophisticated interpolation methods will be required to deal with missing values. Required background: - Recent Ph.D. graduate - Experience in C++ programming on UNIX systems - Knowledge of pattern recognition techniques Desired background: - Working knowledge of fuzzy systems, artificial neural networks, and data mining Please send a curriculum vitae, expression of interest (including earliest start date), and the names and e-mail addresses (or telephone numbers) of two references to N. Pizzi at pizzi at ibd.nrc.ca. Your curriculum vitae should include a list of recent publications. Please outline your interest in this project, how it is related to work that you have done, and what special expertise you would bring to the project. Nicolino Pizzi, Ph.D. Associate Research Officer Institute for Biodiagnostics National Research Council 435 Ellice Avenue Winnipeg MB R3B 1Y6 CANADA From Shaogang.Gong at dcs.qmw.ac.uk Mon Feb 23 11:35:53 1998 From: Shaogang.Gong at dcs.qmw.ac.uk (Shaogang Gong) Date: Mon, 23 Feb 1998 16:35:53 +0000 (GMT) Subject: Post-Doc Research in Face and Gesture Recognition Message-ID: <199802231635.QAA01578@seans-pc.dcs.qmw.ac.uk> Post-doctoral Research in Visual Learning for Face Gesture Recognition and Intention Prediction for Visually Mediated Interaction Department of Computer Science Queen Mary and Westfield College, University of London, UK Applications are invited for a post-doctoral research assistant in the Dept of Computer Science at Queen Mary and Westfield College to work on a new EPSRC research project. The successful candidate will be undertaking novel research in statistical learning methods, real-time view-based face and gesture representation and recognition, data fusion for active camera control and intention prediction. Our lab is equipped with extensive real-time image capturing and tracking systems including Pentium and Pentium II real-time active camera systems, SGI O2 systems, Datacube MaxVideo 250 and MD1/2GX, AMT DAP 500 parallel processors, with numerous SPARC workstations. The candidate should have experience in computer vision and neural network research. In particular, any experience in view-based representation and statistical learning theories would be an advantage (more details can be found on the Web at http://www.dcs.qmw.ac.uk/research/vision/ ). You should also be competent in programming C under X and NT windows and using Unix systems. You will be expected to start as soon as possible on a 2 year contract. Salary in range of 17,293-22,237 pounds per annum inclusive, depending on age and experience. The project is to be closely collaborated with a concurrent project at Sussex COGS involving Prof Hilary Buxton and Dr Jonathan Howell. The project will also involve the BT and BBC R&Ds. The Department of Computer Science at QMW has extensive experience in object detection, tracking and recognition for dynamic scene understanding in image sequences. Recent and current funded projects relevant to this research include ESPRIT II VIEWS for visual interpretation and evaluation of wide area scenes, RACE II Mona Lisa for virtual studios, ESPRIT III FIVE working group for immersive virtual environment, EPSRC IMV Initiative on real-time detection, tracking and recognition of moving people, EC HCM Network PAMONOP on parallel modelling of neural operators for pattern recognition, a BT Short Term Research Fellowship Scheme on real-time view-based estimation of head pose, and the EPSRC/BBC CASE program for studies on the visual segmentation and tracking of moving actors in studio environment. For further details and an application form please phone +(44) (0)171-975-5171 (24 hour answer-phone) quoting Ref. number 97135 or send an email request to sgg at dcs.qmw.ac.uk. Completed applications and CV should be returned by 20/03/98 to: The Recruitment Coordinator, Personnel Office, Queen Mary and Westfield College, Mile End Road, London, E1 4NS. QMW: WORKING TOWARDS EQUAL OPPORTUNITIES From hollidie at pcmail.aston.ac.uk Mon Feb 23 15:59:33 1998 From: hollidie at pcmail.aston.ac.uk (Ian Holliday) Date: Mon, 23 Feb 1998 15:59:33 GMT+1 Subject: postdoc + PhD Studentship: neural nets and MEG Message-ID: Postdoctoral Research Fellowship and Graduate Studentship Neural Computing Research Group Aston University Birmingham B4 7ET, U.K. The Neural Computing Research Group at Aston is looking for a highly motivated individual for a 3 year postdoctoral research position in the area of `Signal and Pattern Processing of Magnetoencephalographic Data`. The project will study single and multichannel data obtained from an Aston magnetoencephalography (MEG) facility for signal enhancement and processing. The MEG research group is engaged in basic studies of normal and abnormal vision, epilepsy, and gamma- band activity; and in clinically related studies on the localisation of eloquent cortex in pre-surgical investigations. Advanced pattern processing techniques are needed, including artificial neural network methods for enhancement, clustering, visualisation, segmentation and classification. Potential candidates should have strong mathematical and computational skills and an interest in the application of these skills to basic and clinically related neurosciences research. Knowledge of linear and nonlinear signal processing or expertise in biosignal analysis would be useful. The successful candidate will also have an opportunity to contribute to experimental work in MEG. A supported studentship is also available in the same area. Further information on this and other positions can be obtained from http://www.ncrg.aston.ac.uk/. Salaries for the Fellowship will be at or above point 6 on the RA 1A scale, currently 16927 UK pounds. These salary scales are subject to annual increments. The studentship is supported at the standard UK rate for PhD students. If you wish to be considered for this position, please send a full CV and publications list, together with the names of 3 referees, to: Prof David Lowe or Dr. Ian Holliday Neural Computing Research Group Psychology Institute Aston University Birmingham B4 7ET, U.K. Tel: 0121 333 4631 tel: 0121 359 3611 ext 4930 Fax: 0121 333 4586 fax: 0121 359 3257 e-mail: d.lowe at aston.ac.uk email: hollidie at aston.ac.uk Email submission of postscript files is welcome. Closing date: 10 April 1998. From ericr at mech.gla.ac.uk Tue Feb 24 07:20:03 1998 From: ericr at mech.gla.ac.uk (Eric Ronco) Date: Tue, 24 Feb 1998 12:20:03 GMT Subject: Constructing a Controller network Message-ID: <199802241220.MAA05138@googie.mech.gla.ac.uk> Dear all, Just to let you know of the http availability of a new technical report entitled "Two Controller Networks Automatically Constructed Through System Linearisations and Learning" (it is a compressed file. Please, gunzip the file to view or print it). It is available (among others) at: http://www.mech.gla.ac.uk/~ericr/research.html or at http://www.mech.gla.ac.uk/~yunli/reports.htm This report has been written by Eric Ronco and Peter J. Gawthrop. Its title is Two Controller Networks Automatically Constructed Through System Linearisations and Learning. The keywords are: controller network, off-equilibrium linearisation, learning Abstract: This study aims at comparing two linear controller networks as well as two methods to automaticly construct their architecture. The general idea of a controller network is to use a number of linear local controllers valid for different operating regions of a non-linear system. The two controller networks studied here are the ""Clustered Controller Network'' (CCN) and the ""Model-Controller Network'' (MCN). They differ by the method used for the selection of the controllers at each instant. In the CCN, the controllers are selected according to a spatial clustering of the operating space whereas in the MCN the selection of the controllers depends of the performance of the model associated to each local controller. The two different methods to construct the architecture of these controller networks are the ""multiple off-equilibrium system linearisations'' and the ""learning control through incremental network construction''. It is shown that these network construction methods make the two controller networks general and systematic non-linear controller design approaches. However, the selection method applied by the MCN is preferable for control purposes since it is directly related to the controller capability unlike the method implemented by the CCN. In other hand, the flexibility of the controller selection applied by the MCN makes accurate local control learning difficult to achieve. A mixture of this two methods of controller selection should remove these problems. Regards, Eric Ronco ----------------------------------------------------------------------------- | Eric Ronco | | Dt of Mechanical Engineering E.mail : ericr at mech.gla.ac.uk | | James Watt Building WWW : http://www.mech.gla.ac.uk/~ericr | | Glasgow University Tel : (44) (0)141 330 4370 | | Glasgow G12 8QQ Fax : (44) (0)141 330 4343 | | Scotland, UK | ----------------------------------------------------------------------------- From thimm at idiap.ch Tue Feb 24 12:37:14 1998 From: thimm at idiap.ch (Georg Thimm) Date: Tue, 24 Feb 1998 18:37:14 +0100 Subject: Events on Neural Networks, Vision and Speech Message-ID: <199802241737.SAA13879@rotondo.idiap.ch> ----------------------------------------- WWW page for Announcements of Conferences, Workshops and Other Events on Neural Networks, Vision and Speech ----------------------------------------- This WWW page allows you to look up and enter announcements for conferences, workshops, and other events concerned with neural networks, vision, speech, and related fields. ------------------------------------------------------------------------- Search and lookup can be restricted to events with forthcoming deadlines! ------------------------------------------------------------------------- The event lists, which is updated almost daily, contains currently more than 200 forthcoming events, and can be accessed via the URL: http://www.idiap.ch/~thimm The entries are ordered chronologically and presented in a format for fast and easy lookup of: - the date and place of the event, - the title of the event, - a contact address (surface mail, email, ftp, and WWW address, as well as telephone or fax number), and - deadlines for submissions, registration, etc. - topics of the event Conference organizers are kindly asked to enter their conference into the database. The list is in parts published in the journal Neurocomputing by Elsevier Science B.V. Information on passed conferences are also available. Kind Regards, Georg Thimm P.S. Please distribute this announcement to related mailing lists. Comments and suggestions are welcome! From Friedrich.Leisch at ci.tuwien.ac.at Wed Feb 25 10:00:42 1998 From: Friedrich.Leisch at ci.tuwien.ac.at (Friedrich Leisch) Date: Wed, 25 Feb 1998 16:00:42 +0100 Subject: CI BibTeX Collection -- Update Message-ID: <199802251500.QAA04534@galadriel.ci.tuwien.ac.at> The following volumes have been added to the collection of BibTeX files maintained by the Vienna Center for Computational Intelligence: Machine Learning 28-30 Neural Networks 10/4-9, Neural Computation 9/6-10/2, Neural Processing Letters 5/3-7/2 Most files have been converted automatically from various source formats, please report any bugs you find. The complete collection can be downloaded from http://www.ci.tuwien.ac.at/docs/ci/bibtex_collection.html ftp://ftp.ci.tuwien.ac.at/pub/texmf/bibtex/ Best, Fritz Leisch ------------------------------------------------------------------ Friedrich Leisch Institut f?r Statistik Tel: (+43 1) 58801 4541 Technische Universit?t Wien Fax: (+43 1) 504 14 98 Wiedner Hauptstra?e 8-10/1071 Friedrich.Leisch at ci.tuwien.ac.at A-1040 Wien, Austria http://www.ci.tuwien.ac.at/~leisch PGP public key http://www.ci.tuwien.ac.at/~leisch/pgp.key ------------------------------------------------------------------ From kia at particle.kth.se Fri Feb 27 10:22:03 1998 From: kia at particle.kth.se (Karina Waldemark) Date: Fri, 27 Feb 1998 16:22:03 +0100 Subject: Neural Network Workshop June-98 Message-ID: <34F6DA1B.D4C49ADB@particle.kth.se> ------------------------------------------------------------------------ VI-DYNN'98 Workshop on Virtual Intelligence - Dynamic Neural Networks Stockholm June 22-26, 1998 Royal Institute of Technology, KTH, Stockholm, Sweden ------------------------------------------------------------------------ VI-DYNN'98 Web: http://www.particle.kth.se/vi-dynn Abstracts due to: March 20, 1998 ****** papers up to 20 pages can be accepted ******* Deliver camera-ready manuscripts at registration Papers will be published by SPIE Papers will be considered for further publication in IEEE Transactions on Industrial Applications Contact: Thomas Lindblad (KTH) - Conf. Chairman email: lindblad at particle.kth.se Phone: [+46] - (0)8 - 16 11 09 ClarkS. Lindsey (KTH) - Conf. Secretary email: lindsey at particle.kth.se Phone: [+46] - (0)8 - 16 10 74 Switchboard: [+46] - (0)8 - 16 10 00 Fax: [+46] - (0)8 - 15 86 74 -------------------------------------------------------------------- Tentative Programme for VI-DYNN'98 Workshop -------------------------------------------------------------------- Monday PCNN tutorial Morning Session chair: Thomas Lindblad 1. Introduction 2. PCNN Theory 3. PCNN Image Processing 4. The PCNN Kernel 5. Target Recognition 6. Dealing with Noise Afternoon Session chair: Jason Kinser 7. Feedback 8. Object Isolation 9. Foveation 10. Image Fusion 11. Hardware Realization 12. Miscellaneous Applications and Summary Tuesday Session: Neurodynamics Session chair: Hans Liljenstrom Keynote Talk: Hans Liljenstrom, Control and amplification of cortical neurodynamics I. Opher (Tel Aviv), Data Clustering via Temporal Segmentation of Spiking Neurons Session: Electronic Nose Session chair: Hans Liljenstrom J. Waldemark (KTH) Neural Networks and PCA for determing ROI in sensory data preprocessing M. L. Padgett (Auburn U.) PCNN factoring and automated outlier detection T. A. Roppel (Auburn U.) Sensory plane analog/VLSI for interfacting sensor arrays to neural networks Session: Models of neural systems Session chair: Hans Liljenstrom Session: PCNN Applications Session chair: J. Kinser Keynote Talk: J. Kinser, Kurt Moore (Los Alamos) , 1-D Peak Fitting using PCNN J. Karvonen (Finnish Inst. Of Marine Research), PCNN for sea-ice classification from RADARSAT SAR-images V.Becanovic (KTH), PCNN for License Plate Identification O.J.Goeboden (Ostfold ), Using PCNN for SONAR Images Panel Discussion: Wednesday Session: Signals from the Brain Session chair: John Taylor Keynote Talk: JG Taylor (Kings College), Analysing Non-invasive Brain Images E. Oja, ICA Analysis of MEG and EEG Signals A. Villa, Single Cell Measurements from Behaving Animals B. Krause (Juelich), PET and Structural Brain Modelling B. Gulyas (Karolinska Inst.), B. Horwitz (NIH), Structural Modelling of PET Data A. Ioannides (Julich), MEG & the Brain Panel Discussion: Session: Defense Applications Session chair: K. Waldemark Keynote Talk: Natalie Clark, Micro-Optical Silicon Eye Authors: Natalie Clark, John Comtois, Adrian Micalicek, and Paul Furth Air Force Research Laboratory, Kirtland AFB NM 87117 I. Renhorn, (Defence Research Establishment), General Specifications for ATR J.L. Johnson J. Kinser, Pulse Couple Spiral Image Fusion Th. Lindblad, Smart sensors inspired by processes in the primate visual cortex Panel Discussion: Thursday Session: Hardware Session chair: Natalie Clark Keynote Talk: J. L. Johnson, Test Results for a 32x32 PCNN Array, J. L. Johnson, R. F Sims, and T. Branch. J. Johnson (MICOM), PCNN Chip Development J. Waldemark (KTH), PCNN in FPGA unknown (John Hopkins), PCNN Hardware IBM ZISC, Zero instruction set computer, Application for noise reduction Trento TOTEM, The Reactive Tabu Search Session: PCNN & other Algorithms Session chair: J. Waldemark G. Szekely, Adaptive PCNN J. Kinser M.Kaipainen, Sea Ice Classification using PCNN J. Johnson, PCNN Theory: State of the art Panel Discussion: Friday Tutorial Session: Virtual Intelligence Session chair: Mary Lou Padgett Theme: Virtual Intelligence Track AM Opening Remarks Keynote Talk: M. L. Padgett, Overview of Virtual Intelligence Motivational material, update on funding, hot topics, why important, how interacts with PCNN, etc. Tutorial: Overview of Neural Networks Fuzzy Systems Evolutionary Computation Rough Sets Virtual Reality Electronic Nose Description of topics, and pointers to websites and printed material for more detailed info e.g. Handbook on Applications of Computational Intelligence Eds. Padgett, Karayiannis, Zadeh CRC Press 1999 and Handbook on NeuroControl Eds. Jorgensen, Werbos and Padgett CRC Press 1999 Session: NNW Applications Session chair: Mary Lou Padgett K. Waldemark (KTH), Sleep Apnea R. Curbelo (Univ. of Uraguay), Fingerprint Identification using Neural Networks D. A. Salo (Ostfold), Neural Networks for Fingerprint identification T. Sanne (Ostfold), Neural Network for Identification Based on the Iris J. Hansen (Ostfold), Facial Recognition using Neural Networks A. Sokolov (Protvino), Hadron Energy Reconstruction by Combined Calorimeter using Neural Network L. Hildingsson,(SKI) Fuel Assembly Assessment from Digital Image Analysis Lunch and Virtual Intelligence Standards Working Group Meeting From ngoddard at psc.edu Fri Feb 27 15:14:50 1998 From: ngoddard at psc.edu (Nigel Goddard) Date: Fri, 27 Feb 98 15:14:50 -0500 Subject: Faculty Positions in Informatics at University of Edinburgh Message-ID: <16628.888610490@pscuxc.psc.edu> LECTURESHIPS IN INFORMATICS University of Edinburgh We invite applications for six lectureships Informatics is the study of the structure, behaviour, and interactions of both natural and artificial computational systems. As part of a major expansion of our work in this area, we invite applications for up to six lectureships in Informatics. Successful candidates will add to our existing strengths in research and teaching, encourage the integration of their own research with that of others, and contribute to the development of Informatics at Edinburgh. We seek candidates, working in any area of Informatics, who will contribute to Edinburgh's excellence in teaching and research. Areas of particular interest for these appointments include: cognition, computation and human learning; computational and cognitive aspects of neuroscience and neural networks; computational and cognitive models of human communication; computational complexity; computational vision; design and analysis of integrated hardware and software computer systems; distributed systems; network and mobile computing; evolutionary systems; formal semantics of natural language; knowledge representation and practical reasoning; mobile robotics. Permanent appointments may be available for suitably qualified candidates, otherwise appointments will be for five years in the first instance. Further particulars including details of the application procedure are available on-line: http://www.dcs.ed.ac.uk/ipu/particulars/ or from the Personnel Department: Recruitment Personnel Office, The University of Edinburgh, 1 Roxburgh Street, Edinburgh EH8 9TB email personnel at ed.ac.uk Tel: +44 (0) 131-650-2511 (24 hour answering service). Fax +44 (0) 131-650-6509 Application forms should be obtained from the personnel department, which may be contacted by phone, fax, or post, or by completing this form: http://www.ed.ac.uk/~persnnel/enqentry.cgi Please quote Reference 896095WW Closing date: 9th March 1998 Further information about Informatics at Edinburgh may be obtained from our WWW page: http://www.dcs.ed.ac.uk/ipu/ or from the Head of Informatics: Professor Michael Fourman Department of Computer Science, JCMB, King's Buildings, Mayfield Road, Edinburgh EH9 3JZ Telephone +44 (0) 131 650 5197 e-mail Informatics at ed.ac.uk From tewon at salk.edu Sun Feb 1 20:50:29 1998 From: tewon at salk.edu (Te-Won Lee) Date: Sun, 01 Feb 1998 17:50:29 -0800 Subject: ICA paper available on-line. Message-ID: <199802020150.RAA05626@hebb.salk.edu> Paper available on-line "A Unifying Information-theoretic Framework for Independent Component Analysis" T-W. Lee, M. Girolami, A.J. Bell and T.J. Sejnowski. International Journal on Mathematical and Computer Modeling (in press) http://www.cnl.salk.edu/~tewon/Public/mcm.ps.gz (130k, 23 pages) Abstract: We show that different theories recently proposed for Independent Component Analysis (ICA) lead to the same iterative learning algorithm for blind separation of mixed independent sources. We review those theories and suggest that information theory can be used to unify several lines of research. Pearlmutter and Parra (1996) and Cardoso (1997) showed that the infomax approach of Bell and Sejnowski (1995) and the maximum likelihood estimation approach are equivalent. We show that negentropy maximization also has equivalent properties and therefore all three approaches yield the same learning rule for a fixed nonlinearity. Girolami and Fyfe (1997a) have shown that the nonlinear Principal Component Analysis (PCA) algorithm of Karhunen and Joutsensalo (1994) and Oja (1997) can also be viewed from information-theoretic principles since it minimizes the sum of squares of the fourth-order marginal cumulants and therefore approximately minimizes the mutual information (Comon, 1994). Lambert (1996) has proposed different Bussgang cost functions for multichannel blind deconvolution. We show how the Bussgang property relates to the infomax principle. Finally, we discuss convergence and stability as well as future research issues in blind source separation. ---------------------------------------------------------------------- Dr. Te-Won Lee EMAIL: tewon at salk.edu Computational Neurobiology Lab, WORK: (619) 453-4100 x1215 Salk Institute, HOME: (619) 450-9036 10010 N. Torrey Pines Rd. FAX: (619) 587-0417 La Jolla, CA 92037 WEB: http://www.cnl.salk.edu/~tewon ---------------------------------------------------------------------- From bressler at walt.ccs.fau.edu Mon Feb 2 20:11:39 1998 From: bressler at walt.ccs.fau.edu (Steven Bressler) Date: Mon, 02 Feb 1998 20:11:39 -0500 Subject: Postdoctoral Position in Computational Neuroscience Message-ID: <3.0.1.32.19980202201139.00700758@mail.ccs.fau.edu> COMPUTATIONAL NEUROSCIENCE POSTDOCTORAL POSITION AVAILABLE Center for Complex Systems Florida Atlantic University A postdoctoral position is open in the Center for Complex Systems at Florida Atlantic University to participate in a project in computational neuroscience. The aim of the project is to develop multivariate techniques for the analysis of cortical event-related potentials, and use the results from such analysis as the basis for computational modeling. The approach will emphasize the close interplay between state-of-the-art multivariate autoregressive analysis and the development of dynamical models of distributed information processing in the cerebral cortex. The research project will be conducted in close collaboration with S. Bressler, a cognitive neuroscientist and M. Ding, a computational modeler. The position is for two years, possibly renewable for another year. Required background: -- Ph.D. degree -- Experience in C programming on UNIX systems and X11 Window programming -- Basic knowledge in dynamical systems, matrix algebra, signal processing, and statistics -- Research experience Desired background: -- Working knowledge in neurobiology and neural networks -- Knowledge in autoregressive time series modeling This project is funded by research grants from the National Science Foundation and the National Institute of Mental Health. Please send curriculum vitae, expression of interest, and the names and e-mail or phone numbers of three references to Steven Bressler at bressler at walt.ccs.fau.edu. Information about the Center for Complex Systems at Florida Atlantic University is available at http://www.ccs.fau.edu/ Steven L. Bressler, Ph.D. voice: 561-297-2322 Professor, Program in fax: 561-297-3634 Complex Systems & Brain Sciences Center for Complex Systems bressler at walt.ccs.fau.edu Florida Atlantic University http://www.ccs.fau.edu/~bressler/ 777 Glades Road Boca Raton, FL 33431 U.S.A. From rreilly at ollamh.ucd.ie Mon Feb 2 18:20:04 1998 From: rreilly at ollamh.ucd.ie (Ronan G. Reilly) Date: Mon, 02 Feb 1998 23:20:04 +0000 (GMT) Subject: Postdoctoral position(s) in Dublin Message-ID: <143090E2FEE@ollamh.ucd.ie> ************************************* * LCG TMR Network * * Learning Computational Grammars * * * ************************************* ****************************************************************** * POSTDOCTORAL RESEARCH OPPORTUNITY AT UNIVERSITY COLLEGE DUBLIN * ****************************************************************** LCG (Learning Computational Grammars) is a research network shortlisted for funding by the EC Training and Mobility of Researchers programme (TMR). LCG's contract is currently being negotiated. The network is expected to run from 1st March 1998 for three years. The LCG network involves seven European partners. The research goal of the network is the application of machine learning techniques to extending a variety of computational grammars. The particular focus of UCD's research will be on the use of artificial neural network learning algorithms. See http://www.let.rug.nl/~nerbonne/tmr/lcg.html for more details. Subject to successful contract negotiation, there will be three years of postdoctoral funding available in the Department of Computer Science at University College Dublin tenable from March '98. The ideal postdoctoral candidates will have research experience in the use of ANNs in natural language processing. As the funding is provided by the EU Training and Mobility of researchers programme there are some restrictions on who may benefit from it: * Candidates must be aged 35 or younger * Candidates must be Nationals of an EU country, Norway, Switzerland or Iceland * Candidates must have studied or be studying for a Doctoral Degree * Candidates must not be Irish Nationals or worked in Ireland 18 out of the last 24 months If you are interested and eligible, e-mail your CV (RTF, ASCII, or PS versions only) and the names and addresses of two referees to the address below. Your CV should include a list of recent publications. Please also outline in 2-3 pages your interest in LCG, how it is related to work you have done, and what special expertise you bring to the problem. --------------------------------------------- Ronan G. Reilly, PhD Department of Computer Science University College Belfield Dublin 4 IRELAND http://cs-www.ucd.ie/staff/html/ronan.htm e-mail: Ronan.Reilly at ucd.ie Tel. : +353-1-706 2475 Fax : +353-1-269 7262 From witbrock at jprc.com Tue Feb 3 11:07:37 1998 From: witbrock at jprc.com (witbrock@jprc.com) Date: Tue, 3 Feb 1998 11:07:37 -0500 Subject: CALD Workshop on Mixed Media Databases Message-ID: <199802031607.LAA02778@hurricane.jprc.com> Dear Colleague, You are invited to participate in the Center for Automated Learning and Discovery workshop on Mixed Media databases. This workshop will be held in conjunction with the Conference on Automated Learning and Discovery, being held at Carnegie Mellon University in Pittsburgh from June the 11th to the 13th 1998. This workshop is intended for researchers with an interest in learning from multiple media. The workshop will emphasize both algorithms and applications of learning with mixed media databases. Papers that describe algorithms should cover either novel approaches designed to benefit from mixed-media data, or modifications of standard algorithms that utilize multiple media data sources. Application papers should clearly demonstrate the benefits of learning from two or more types of media. Different media areas to be addressed include: Vision: Image, Video, and VRML Speech and Audio Text, including OCR, Closed-Captioning, handwriting, and web-documents Olfactory perception Haptic and Touch sensing If you would like to present at this workshop, please submit a paper describing original research work and results. Four copies of the paper should be submitted in hardcopy by Feb 15, 1998. The ideal paper should cover two or more topics listed above and apply some aspect of learning to the multiple media data. The learning may involve, but is not limited to neural networks, as well as statistical and probabilistic models. All statistical, probabilistic, and learning approaches are welcome. Papers submitted to this workshop may also be submitted to other conferences or to journals. If you plan to submit a paper or attend, please contact the organizers (listed below). Detailed submission instructions can be found at: http://www.cs.cmu.edu/~conald/call.shtml Selected papers from the workshop will be considered for publication in an upcoming special issue of IEEE Expert journal. Organizers: Shumeet Baluja (baluja at jprc.com) Christos Faloutsos (christos at cs.cmu.edu) Alex Hauptmann (alex+ at cs.cmu.edu) Michael Witbrock (witbrock at jprc.com) The Conference main site is at http://www.cs.cmu.edu/~conald/ Please visit it soon. And please forward this Call to any colleagues who may be interested. --------------------------------------------------------------------- Michael Witbrock Justsystem Pittsburgh Research Center Research Scientist 4616 Henry St, Pittsburgh, PA 15213 Phone: +1 412 683 9486 Fax: +1 412 683 4175 witbrock at jprc.com http://www.justresearch.com/ From tom.ziemke at ida.his.se Tue Feb 3 08:45:24 1998 From: tom.ziemke at ida.his.se (Tom Ziemke) Date: Tue, 3 Feb 1998 14:45:24 +0100 Subject: Biologically inspired robotics - CALL FOR PARTICIPATION Message-ID: <199802031345.OAA22842@tor.ida.his.se> ----------------------------------------- Sorry if you receive this more than once ----------------------------------------- **** SELF-LEARNING ROBOTS II: BIO-ROBOTICS **** An Institution of Electrical Engineers (IEE) Seminar Savoy Place, London, UK: February 12, 1998. Co-sponsors: Royal Institute of Navigation (RIN) Biotechnology and Biological Sciences Research Council (BBSRC) British Computer Science Society (BCS) Society for the Study of Artificial Intelligence and the Simulation of Behaviour (AISB) Biologically inspired robotics or bio-robotics is an exciting trend in the integration of engineering and life sciences. Although this has a long history dating back to the turn of the century, it is only within the last few years that it has picked up momentum as many have realised that life is still the best model we have for intelligent behavior. This cross fertilisation is beginning to bear fruit in robotics within specialist areas such as evolutionary methods, artificial life, neural computing, and navigation. It is now time to bring these threads together and ask the life scientists to assess the developments and also to discuss how and what the life sciences could learn from robotics. This one-day seminar aims to bring together some of Europe's leading researchers within the areas of animal and robot behavior to discuss the foundations and future directions of biologically inspired robotics. Each Speaker will be followed by a Discussant who will follow up on some of the issues raised by in the paper and make general points about the field. 9.30-10.30 EMBODIMENT Rolf Pfeifer (Speaker) Computer Scientist and Roboticist, Switzerland. Stevan Harnad (Discussant) Psychologist, UK. 10.30-10.45 Coffee 10.45-11.45 EVOLUTIONARY LEARNING Stefano Nolfi (Speaker) Roboticist and Psychologist, Italy. Richard Dawkins (Discussant) Evolutionary Zoologist, UK. 11.45-12.45 CONDITIONED LEARNING. Marco Dorigo (Speaker) Computer Scientist and Roboticist, Belgium. Tony Savage (Discussant) Animal Psychologist, N. Ireland. 12.45-2.00 Lunch 2.00-3.00 NAVIGATION: THE INSECT MODEL Dimitrios Lambrinos (Speaker) Computer Scientist and Roboticist, Switzerland. Tom Collett (Discussant) Neurobiologist, UK. 3.00-4.00 NAVIGATION: THE MAMMALIAN MODEL Neil Burgess (Speaker) Neuroscientist, UK. Ariane Etienne (Discussant) Ethologist, Switzerland. 4.00-4.15 Tea PANEL: THE FUTURE OF BIO-ROBOTICS 4.15-5.45 Introduced and Chaired by Jean-Arcady Meyer, Computer Scientist and Ethologist, France. ORGANISERS Noel Sharkey, Computer Scientist, Psychologist, and Roboticist, University of Sheffield, UK. Tom Ziemke, Computer Scientist and Roboticist, Universities of Sheffield, UK and Skovde, Sweden. REGISTRATION It would be advisable to register as early as possible since places will be limited. Please contact Jon Maddison (IEE) at jmaddison at iee.org.uk. From Asim.Roy at asu.edu Wed Feb 4 02:16:14 1998 From: Asim.Roy at asu.edu (Asim Roy) Date: Wed, 04 Feb 1998 00:16:14 -0700 (US Mountain Standard Time) Subject: COULD THERE BE REAL-TIME, INSTANTANEOUS LEARNING IN THE BRAIN? Message-ID: I am posting this memo to various newsgroups. So my apologies if you get multiple copies. ----------------------------------------------------------- This is a summary of the responses (comments/questions) I have received so far. My sincere apologies for the long delay in posting this summary. There were a number of interesting questions and I did respond to most of the individuals directly. Since many of the questions were similar, the first part of this memo poses those common, generic questions and answers them. This is followed by the individual responses received. In the Appendix, a copy of my original memo is included for reference. I hope I have not missed any of the responses. If I did, please let me know and I will post them. There will be a panel discussion on the question "COULD THERE BE REAL-TIME, INSTANTANEOUS LEARNING IN THE BRAIN?" at the World Congress on Computational Intelligence (WCCI'98) in Anchorage, Alaska in May, 1998. I will post an announcement on this soon. The question of real-time, instantaneous learning is tied to such other classical connectionist ideas as local learning and memoryless learning. These three ideas have led the development of various brain-like learning algorithms for the last 40 to 50 years. So these open discussions are about some of the most fundamental ideas of this field. It is quite possible that we have been developing the wrong kinds of algorithms all these years. I hope more scholars from neuroscience, cognitive science and artificial neural networks will participate in these informal, open discussions and enrich this discussion. All comments/questions are welcome. Asim Roy Arizona State University ------------------------------------------------ ANSWERS TO SOME TYPICAL, GENERIC QUESTIONS (A) FIRST A CLARIFICATION OF THE NOTION OF "REAL-TIME, INSTANTANEOUS" LEARNING I think there was some confusion in my use of the term "real-time." It should have been clear from my memo that I was using the term "real-time" to refer to "Hebbian-style" instantaneous and permanent learning. Hebbian-style learning is used in such well-known algorithms as back-propagation. In Hebbian-style learning, a training example is used for some type of instantaneous adjustment to the network and then the example is discarded (so-called memoryless learning). So in Hebbian-style learning, there is no recording or retention of any particular information (a training example, that is) in the system for subsequent use. This is the style of learning generally used by all learning algorithms in the field of artificial neural networks. The key notion in Hebbian-style learning is that of "instantaneous and permanent" learning from each and every example provided. I used the term "real-time" to refer to this mode of learning. But "memory-based learning" can also be "real-time" in the sense that learning can begin as soon as some information about the problem is collected and stored. So, in that sense, learning of motor skills in the Shadmehr and Holcomb [1997] study could be considered real-time, although it was not "real-time, instantaneous" in the Hebbian-sense - the learning took about "5 to 6 hours" to complete!! Learning in "5 to 6 hours" is real-time, but not "instantaneous." If there is Hebbian-style "instantaneous" learning in the brain, learning should have been "complete" as soon as the practice session ended; it wouldn't have taken any further time after practice and not the "5 to 6 hours" it took in this case. I think most people understood my use of the term "real-time" in the way I intended, but I realize that it may have created confusion with some. "Hebbian-style learning" instead of "real-time, instantaneous" would have been a more accurate term. -------------------- (B) A CLARIFICATION OF THE DIFFERENCE BETWEEN "MEMORY" (SIMPLE RECORDING OF INFORMATION) AND "LEARNING" Several comments (by Gary Cottrell, Gale Martin, Stefan Schaal) result from confusion about the terms "memory" and "learning". In some fields (and in everyday life), the terms "memory" and "learning" are used synonymously. So some of them claim that "learning" is indeed instantaneous. However, they are actually refering to simple recording of information that was instantaneous, not to "learning" that was instantaneous. From Yves.Moreau at esat.kuleuven.ac.be Fri Feb 6 04:20:13 1998 From: Yves.Moreau at esat.kuleuven.ac.be (Yves Moreau) Date: Fri, 06 Feb 1998 10:20:13 +0100 Subject: TR: Embedding Recurrent Neural Networks into Predator-Prey Models (corrected URL) Message-ID: <34DAD5CD.C1BD086@esat.kuleuven.ac.be> Hello, A number of people have been trying to download our technical report via my home page and list of publications; they were directed to a wrong URL (the direct ftp URL itself is correct) and thought the report was not available. I have fixed this problem and you can get the technical report whichever way you like. My apologies to the other readers for the repeated posting. Best regards, Yves Moreau Yves Moreau wrote: > Dear Connectionists, > > The following technical report is available via ftp or the World Wide > Web: > > EMBEDDING RECURRENT NEURAL NETWORKS INTO PREDATOR-PREY MODELS > > Yves Moreau and Joos Vandewalle, K.U.Leuven ESAT-SISTA > > K.U.Leuven, Elektrotechniek-ESAT, Technical report ESAT-SISTA TR98-02 > ftp://ftp.esat.kuleuven.ac.be/pub/SISTA/moreau/reports/lotka_volterra_tr98-02.ps > > Comments are more than welcome! > > ABSTRACT > ======== > > We study changes of coordinates that allow the embedding of the > ordinary differential equations describing continuous-time recurrent > neural networks into differential equations describing predator-prey > models ---also called Lotka-Volterra systems. We do this by transforming > the equations for the neural network first into quasi-monomial form, > where we express the vector field of the dynamical > system as a linear combination of products of powers of the > variables. From this quasi-monomial form, we can directly > transform the system further into Lotka-Volterra equations. The > resulting Lotka-Volterra system is of higher dimension than the > original system, but the behavior of its first variables is > equivalent to the behavior of the original neural network. We expect > that this transformation will permit the application of existing > techniques for the analysis of Lotka-Volterra systems to recurrent-neural > networks. Furthermore, our result shows that Lotka-Volterra systems > are universal approximators of dynamical systems, just as > continuous-time neural networks. > > Keywords: Continuous-time neural networks, > Equivalence of dynamical systems, Lotka-Volterra systems, > Predator-prey models, Quasi-monomial forms. > > -------------------------------------------------------------- > > To get it from the World Wide Web, point your browser at: > ftp://ftp.esat.kuleuven.ac.be/pub/SISTA/moreau/reports/lotka_volterra_tr98-02.ps > > To get it via FTP: > ftp ftp.esat.kuleuven.ac.be > cd pub/SISTA/moreau/reports > get lotka_volterra_tr98-02.ps > > -------------------- > > Yves Moreau > > Department of Electrical Engineering > Katholieke Universiteit Leuven > Leuven, Belgium > > email: moreau at esat.kuleuven.ac.be > > homepage: http://www.esat.kuleuven.ac.be/~moreau > > publications: > http://www.esat.kuleuven.ac.be/~moreau/publication_list.html From postma at cs.unimaas.nl Fri Feb 6 04:50:42 1998 From: postma at cs.unimaas.nl (Eric Postma) Date: Fri, 06 Feb 1998 10:50:42 +0100 Subject: 2 Research Assistantships NNs for Image Recognition Message-ID: <1.5.4.32.19980206095042.01b29c8c@bommel.cs.unimaas.nl> 2 Research Assistantships, leading to Ph.D. The Computer Science Department of the Universiteit Maastricht in the Netherlands performs research in the field of Artificial Intelligence. The main subjects of research are Neural Networks and Multi-Agent Systems. The research group Neural Networks invites applications for two research assistantships on the research project Neural Networks for Image Recognition The candidates will develop neural-network models for the recognition of natural objects and scenes. Biological vision serves as a source of inspiration for the development of the models. The project focuses on the active selection of static and dynamic visual information through an attentive mechanism (e.g., eye movements). Applications include visual information retrieval from image databases and real-time vision in autonomous agents or robots. Both fundamental and application-oriented research will be performed. The research will be rounded off with a Ph.D. thesis. Candidates should have: - MSc in computer science, cognitive science, or related discipline, - interest in theoretical and practical research, - good programming skills (e.g., in C, C++, and/or Java), - knowledge of neural networks, preferably in relation to vision or visual recognition. Knowledge of the psychology and biology of vision will be an advantage. Applications should be sent to the administrator of the Department of Computer Science, Ms. A. Klinkers, by Email: klinkers at cs.unimaas.nl or by regular mail: Department of Computer Science, P.O. Box 616, 6200 MD Maastricht, The Netherlands. Additional information can be obtained from Eric Postma (postma at cs.unimaas.nl; +31 43 388 3493) or prof. Jaap van den Herik (herik at cs.unimaas.nl; +31 43 3883477). A salary commensurate with Ph.D. student status in the Netherlands is offered: Dfl. 2135 per month in the first year, rising to Dfl. 3812 (gross) per month in the fourth year. From weaveraj at helios.aston.ac.uk Mon Feb 9 05:25:05 1998 From: weaveraj at helios.aston.ac.uk (Andrew Weaver) Date: Mon, 09 Feb 1998 10:25:05 +0000 Subject: Studentship Available, Aston University, UK Message-ID: <29800.199802091025@sun.aston.ac.uk> Neural Computing Research Group, Aston University, Birmingham, UK We invite applications for EPSRC and Divisional PhD studentships in the following areas: * Neural Nets for Control: Advancing the Theory * Neural Networks for Affinity Ligand Synthesis * Statistical mechanics of support vector machines * Bayesian approaches to online learning * Advanced mean field methods for Bayesian learning * Analysing Brain-derived Magnetic Fields using Neural Networks * Non-linear Time Series Analysis: Characterisation by Feature Processing * Neural Network Analysis of Wake EEG * Image Understanding with Probabilistic Models Studentships are available to people of all nationalities, although the EPSRC studentships will only pay tuition fees and living expenses to UK citizens, and tuition fees only to (non-UK) EU citizens. Applicants should have, or expect to gain, a First Class or Upper Second Class Degree (or overseas equivalent) in a numerate discipline. The Research Group also has 5 EPSRC Advanced Course studentships for the MSc in Pattern Analysis and Neural Networks, further details of which are also available at the web pages below. In order to apply for these studentships you will need to complete an official Aston University application form, and should therefore send your name and address to ncrg at aston.ac.uk (subject line NCRG2 - IF YOU DO NOT USE THIS SUBJECT LINE YOU WILL NOT BE SENT THE CORRECT INFORMATION) by 9.00am on Friday 20th February 1998. Written applications should be received by Friday 27th March 1998. Details of the information required will be found in the covering letter sent with the application form. Further details of the Research Group and the topics can be found at http://www.ncrg.aston.ac.uk/ From Simon.N.CUMMING at British-Airways.com Mon Feb 9 13:08:04 1998 From: Simon.N.CUMMING at British-Airways.com (Simon.N.CUMMING@British-Airways.com) Date: 09 Feb 1998 18:08:04 Z Subject: ANNOUNCEMENT: NCAF Conference, SUNDERLAND 22-23April1998 Message-ID: <"BSC400A1 980209180759206661*/c=GB/admd=ATTMAIL/prmd=BA/o=British Airways PLC/s=CUMMING/g=SIMON/i=N/"@MHS> The purpose of the Neural Computing Applications Forum (NCAF) is to promote widespread exploitation of neural computing technology by: - providing a focus for neural network practitioners. - disseminating information on all aspects of neural computing. - encouraging close co-operation between industrialists and academics. NCAF holds four, two-day conferences per year, in the UK, with speakers from commercial and industrial organisations and universities. The focus of the talks is on practical issues in the application of neural network technology and related methods to solving real-world problems. ____________________________________________________________________ The April meeting will be hosted by The School of Computing and Information Systems on the St Peter's Campus of The University of Sunderland on Wednesday 22nd and Thursday 23rd April 1998. -------------------------------------------- the theme will be: DTI Neural Computing Guidelines. The 2 days will be packed with applications oriented papers as usual. There will also be adequate time for networking with other practitioners, during coffee, lunch and the Wednesday evening event. NCAF Conference at SUNDERLAND, UK. 22 - 23 April 1998 ====================================================== DTI Neural Computing Applications Guidelines Wednesday 22nd April 1998 ------------------------- Introduction and Welcome John MacIntyre, University of Sunderland 1hr overview: By a guest speaker to be announced Practical Assessment of Neural Network Applications Ian Nabney, Aston University Neural Networks and Error Bars David Lowe, Aston University Cracking the Code: a fully interactive workshop putting the Guidelines into practice Graham Hesketh, Rolls-Royce and Iain Strachan, AEA Technology From Project to Product, a Neural Based Cardiac Monitor Tom Harris, Brunel University Thursday 23rd April 1998 ------------------------ Robust Neural Networks with Confidence Bounds Julian Morris and Elaine Martin, University of Newcastle Neural Network Techniques for on-line Monitoring of Vigilance Mihaela Duta, Oxford University Applications of Normalised RBF nets to Robot Trajectories Learning Guido Bugmann, University of Plymouth Data Fusion in Complex Machine Monitoring Odin Taylor, University of Sunderland Neural Networks for Steam Leak Location Peter Mattison, University of Sunderland ____________________________________________________________________ Social Programme: The most widely acclaimed social event ever organised by NCAF was a visit to the Beamish Open Air Museum, so by popular demand we are visiting there again. plus Puzzle Corner: To Irradiate or Not To Irradiate - that is the question Graham 'Rottweiler' Hesketh (Rolls-Royce) ___________________________________________________________________ Attendance at the conference costs 100 pounds for non-members or 20 pounds for NCAF members. [Food, social event and accommodation not included]. NCAF MEMBERSHIP DETAILS: ------------------------ All amounts are in pounds Sterling, per annum. All members receive a quarterly newsletter and are eligible to vote at the AGM (but see note on corporate membership). Currently, membership includes a free copy of the book "A Guide to Neural Computing Applications" by Prof Lionel Tarassenko of Oxford University. (This book is on sale in bookshops for 29.99 pounds). Full (Corporate) Membership : 300 pounds (allows any number of people in the member organisation to attend meetings at member rates; voting rights are restricted to one, named, individual. Includes automatic subscription to the journal Neural Computing and Applications.) Individual Membership : 170 pounds (allows one, named, individual to attend meetings at member rates; includes journal) Associate Membership: 110 pounds: includes subscription to the journal and newsletter but does not cover admission to the meetings. Reduced (Student) Membership : 65 pounds including Journal; 30 pounds without journal. Applications for student membership should be accompanied by a copy of a current full-time student ID card, UB40, etc. ___________________________________________________________________ For registration, membership enquiries or further information please e-mail ncafsec at brunel.ac.uk or Phone Sally Francis (+44)(0)1784 477271 ___________________________________________________________________ From polzer at uran.informatik.uni-bonn.de Mon Feb 9 11:08:59 1998 From: polzer at uran.informatik.uni-bonn.de (Andreas Polzer) Date: Mon, 9 Feb 1998 17:08:59 +0100 (MET) Subject: CFP: ECCV Workshop on Learning in Computer Vision Message-ID: <199802091609.QAA08896@cornea.informatik.uni-bonn.de> We apologize if you receive multiple copies of this message. ------------------------------------------------------------ WORKSHOP ON LEARNING IN COMPUTER VISION in conjunction with ECCV '98 June 6, 1998 Freiburg, Germany Description ----------- In recent years rising computer performance has made it possible to exploit complex statistical models and to learn and estimate their parameters from an increasing amount of data. Therefore the issues of computational and statistical learning theory and Bayesian inference become more and more relevant for computer vision applications. Especially the related topics of generalization and choice of model complexity are of central importance in computer vision. Furthermore, the question of needed accuracy for optimization and parameter estimation turns out to be a closely related topic. The application of methods from statistical learning theory and neurally inspired approaches in computer vision are rather diverse and learning in computer vision is by no means a homogeneous field. But the necessity becomes more and more evident to take a more fundamental point of view and to clarify the multiple implications that the recent achievements of statistical learning theory have on computer vision problems. Statistical learning theory might have significant influence on many applications ranging from classification and statistical object recognition, grouping and segmentation to statistical field models and optimization. We are convinced that focussing on these joint aspects may yield a major contribution to the understanding and improvement of the diverse range of learning applications in computer vision. A workshop on learning in computer vision may greatly contribute to these goals. Workshop Issues --------------- The workshop will focus on the latest developments of learning in computer vision and will try to clarify to what extent statistical learning theory and Bayesian inference support computer vision applications. The workshop will present high quality oral contributions on any aspects of learning in computer vision, including but not restricted to the following topics: * Supervised Learning and its application to classification, support vector networks and model learning * Unsupervised Learning for structure detection in images * Robustness of Computer Vision algorithms and generalization * Probabilistic model estimation and selection, e.g. Bayesian inference for vision Attendance and Workshop Format ------------------------------ The workshop will consist of invited keynote talks and regular talks in one track. For submissions please send an extended abstract of 1-2 pages by March 31, 1998 to Workshop Learning in Computer Vision c/o Prof. Joachim Buhmann Institut fuer Informatik Roemerstrasse 164 D-53117 Bonn Germany In case of more submissions than available time slots a selection will be made based on a peer review of the submissions by the program committee. Venue ----- The workshop will be held in Freiburg, Germany on June 6, 1998 in conjunction with the European Conference on Computer Vision (ECCV '98). Program Committee ----------------- * Joachim M. Buhmann, Chair (University of Bonn, Germany) * Andrew Blake (University of Oxford, UK) * Jitendra Malik (UC Berkeley, USA) * Tomaso Poggio (MIT, USA) * Daphna Weinshall (Hebrew University, Israel) Local Organization: Andreas Polzer, Jan Puzicha (University of Bonn) To obtain further information please contact: WWW: http://www-dbv.cs.uni-bonn.de/learning.html e-mail: jan at cs.uni-bonn.de From elmar.steurer at dbag.ulm.DaimlerBenz.COM Wed Feb 11 10:25:02 1998 From: elmar.steurer at dbag.ulm.DaimlerBenz.COM (Elmar Steurer) Date: Wed, 11 Feb 1998 16:25:02 +0100 Subject: please include this CFP to your mailing list Message-ID: <34E1C2CE.51F6@dbag.ulm.DaimlerBenz.com> Call for Papers Workshop: Application of Machine Learning and Data Mining in Finance 10th European Conference on Machine Learning (ECML-98) Chemnitz, Germany, April 24 1998 General Information In conjunction with the 10th European Conference on Machine Learning (ECML-98) the workshop "Application of Machine Learning and Data Mining in Finance" will be held in Chemnitz, Germany, on April, 24th 1998. The main conference takes place from April, 21st to 23rd 1998. Motivation Advanced data analysis and forecasting technologies such as neural networks, symbolic machine learning and genetic algorithms are being increasingly applied to support financial asset management and credit risk management. These methods are considered by many financial management institutions as innovative technologies to support conventional quantitative techniques. Their use in computational finance will have a major impact in the modelling of the currency markets, in tactical asset allocation, bond and stock valuation and portfolio optimisation. In addition the application of these tools for scoring tasks delivers valuable support for the management of client credit risk. Targets This workshop is designed to bring together researchers in the field of Machine Learning with those practicing financial consulting. The purpose is twofold: - Practitioners should become familiar with the state of the art in machine learning research for predictive modelling and scoring systems. - The research community should receive ideas and requirements from participants from the financial world with the aim to improve the acceptance of Machine Learning applications and to identify future areas of research. Research papers representing new and significant developments in methodology as well as applications of practical use will be presented. Topics include: Application aspects: - Scoring systems: Application and Behavioural Scoring - Trading- and forecasting models - Volatility models - Value at Risk - Financially motivated objective functions Methodological aspects: - Symbolic Learning in financial engineering - Neural Networks for financial applications - Aspects and dependencies of data transformation and model selection - Backtest procedures: Advantages and bottlenecks - Pre-testing as an alternative to backtest - Data Mining process model for financial applications Submission of papers Authors wishing to present a paper should send an electronic version (uuencoded compressed PostScript) not later than 28 February 98 to: Dr. Elmar Steurer DAIMLER-BENZ AG - Research and Technology Postfach 2360 89013 Ulm Tel.: 0049 - 731 / 505 -2868 Fax: 0049 - 731 / 505 4210 Email: elmar.steurer at dbag.ulm.DaimlerBenz.COM Accepted papers will be published in the workshop notes. Selected papers will be issued in a proceedings. Contributors will be allocated 20 minutes for an oral presentation during the workshop. Further invited talks and a panel discussion are planned. Program committee: Ulrich Anders University of Otago, Dunedin, New Zealand Jeremy H. Armitage State Street Bank and Trust Company, London, UK Dirk Baestens Generale Bank, Brussels, Belgium Georg Bol University of Karlsruhe, Germany Guenter Grimm allfonds, Munich, Germany Tae H. Hann University of Karlsruhe, Germany Ashar Mahboob Fuji Capital Markets Corporation, New York, USA Andreas Weigend STERN Business School, New York University, USA Apostolos N. Refenes London Business School, UK Andrea Sczesny ZEW Mannheim, Germany Charles Taylor University of Leeds, UK Diethelm Wuertz ETH, Zurich, Switzerland Hans-Georg Zimmermann Siemens AG, Munich, Germany Important Dates: Submission deadline: 28 February 1998 Notification of acceptance: 15 March 1998 Camera ready copy: 28 March 1998 Workshop: 24 April 1998 Organization: Gholamreza Nakhaeizadeh and Elmar Steurer DAIMLER-BENZ AG - Research and Technology e-mail: nakhaeizadeh at dbag.ulm.DaimlerBenz.COM elmar.steurer at dbag.ulm.DaimlerBenz.COM Registration and further information: For further information about the main conference and registration please contact: ecml98 at lri.fr ecml98 at informatik.tu-chemnitz.de or visit the web site: http://www.tu-chemnitz.de/informatik/ecml98 From nnesmed at DI.Unipi.IT Wed Feb 11 11:35:33 1998 From: nnesmed at DI.Unipi.IT (Tonina Starita) Date: Wed, 11 Feb 1998 17:35:33 +0100 (MET) Subject: Final Call NNESMED`98 (Extended Deadline) Message-ID: <199802111635.RAA00554@neuron.di.unipi.it> * * * E X T E N D E D D E A D L I N E: February 27 * * * FINAL CALL FOR PAPERS 3rd International Conference on Neural Networks and Expert Systems in Medicine and Healthcare NNESMED '98 Pisa, Italy,2-4 September 1998 http://www.di.unipi.it/~nnesmed/home.htm NNESMED '98 is organised by the Computer Science Department of the University of Pisa Conference Chair: Professor Starita, University of Pisa Conference Co-Chairs: Professor Ifeachor, University of Plymouth Professor Simi University of Pisa Keynote Speakers Dr Lee Giles (USA) University of Princeton Professor Mario Stefanelli (Italy) University of Pavia Professor Paulo Lisboa (UK) Liverpool John Moores University Programme/Advisory Committee Dr Lee Giles (USA) Professor Marco Gori (Italy) Professor Emmanuel Ifeachor (UK) Dr Barrie Jervis (UK) Professor Marzuki Khalid (Malaysia) Professor Priklis Ktonas (USA) Professor Paulo Lisboa (UK) Professor George Papadurakis (Greece) Professor Karl Rosen (Sweden) Professor Maria Simi (Italy) Dr Alessandro Sperduti (Italy) Professor Mario Stefanelli (Italy) Professor Hiroshi Tanaka (Japan) Professor John Taylor (UK) Topics Neural Networks Expert Systems Soft Computing Hybrid Systems Signal Processing Fuzzy Logic Knowledge Bases DataMining Deductive Reasoning Telemedicine Tools and Applications Scope NNESMED '98 is organised by the Computer Science Department of the University of Pisa and it will be held in Pisa, on September 2-4 1998. It will provide a forum for the presentation of the results of ongoing works and research in the field of the Neural Networks and Expert Systems in Medicine and Healthcare. NNESMED '98 will be the third edition of this series and it will promote the exchange of ideas and experiences among researchers from the AI communities in medical field. Pisa is well connected to the rest of Europe by its international airport and good road and rail links. Paper submission The submission deadline is ** EXTENDED **: February 27, 1998. Papers must not exceed 4 pages, they must be written in English, with a cover page containing: * a 200-word abstract * keywords * postal and electronic mailing address * phone and fax number of the first author Submission will be electronic and available via the conference web site. Authors will be notified of the acceptance (oral and/or poster session) or rejection of their papers by May 1, 1998. Additional Information http://www.di.unipi.it/~nnesmed/home.htm e_mail: nnesmed at di.unipi.it Tel: +39-50-887215/ +39-50-887249 Fax: +39-50-887226 From priel at mail.biu.ac.il Thu Feb 12 10:02:30 1998 From: priel at mail.biu.ac.il (Avner Priel) Date: Thu, 12 Feb 1998 17:02:30 +0200 (WET) Subject: paper on time series generation Message-ID: The following paper on the subject of time series generation by feed-forward networks has appeared on the Journal of Physics A 31(4) 1189 (1998). The paper is available from my home-page : http://faculty.biu.ac.il/~priel/ comments are welcome. *************** NO HARD COPIES ****************** ---------------------------------------------------------------------- Noisy time series generation by feed-forward networks ----------------------------------------------------- A Priel, I Kanter and D A Kessler Department of Physics, Bar Ilan University, 52900 Ramat Gan,Israel ABSTRACT: We study the properties of a noisy time series generated by a continuous-valued feed-forward network in which the next input vector is determined from past output values. Numerical simulations of a perceptron-type network exhibit the expected broadening of the noise-free attractor, without changing the attractor dimension. We show that the broadening of the attractor due to the noise scales inversely with the size of the system ,$N$, as $1/ \sqrt{N}$. We show both analytically and numerically that the diffusion constant for the phase along the attractor scales inversely with $N$. Hence, phase coherence holds up to a time that scales linearly with the size of the system. We find that the mean first passage time, $t$, to switch between attractors depends on $N$, and the reduced distance from bifurcation $\tau$ as $t = a {N \over \tau} \exp(b \tau N^{1/2})$, where $b$ is a constant which depends on the amplitude of the external noise. This result is obtained analytically for small $\tau$ and confirmed by numerical simulations. ---------------------------------------------------- Priel Avner < priel at mail.biu.ac.il > < http://faculty.biu.ac.il/~priel > Department of Physics, Bar-Ilan University. Ramat-Gan, 52900. Israel. From omori at cc.tuat.ac.jp Thu Feb 12 23:32:28 1998 From: omori at cc.tuat.ac.jp (Takashi Omori) Date: Fri, 13 Feb 1998 13:32:28 +0900 Subject: Call for Paper : ICONIP'98-Kitakyushu Message-ID: <01BD3883.D43B76E0@BRAIN> ----------------------------------------- Sorry if you receive this more than once ----------------------------------------- For your remind of ICONIP'98-Kitakyushu. The dead line is March 31-st, 1998. Please refer http://jnns-www.okabe.rcast.u-tokyo.ac.jp/jnns/ICONIP98.html for latest information. The Fifth International Conference on Neural Information Processing (ICONIP'98) October 21-23,1998 Kitakyushu International Conference Center 3-9-30 Asano, Kokura-ku, Kitakyushu 802, Japan Organized by Japanese Neural Network Society (JNNS) Sponsored by Asian Pacific Neural Network Assembly (APNNA) The annual conference of the Asian Pacific Neural Network Assembly, ICONIP'98, will be held jointly with the ninth annual conference of Japanese Neural Network Society, from 21 to 23 October 1998 in Kitakyushu, Japan. The goal of ICONIP'98 is to provide a forum for researchers and engineers from academia and industries to meet and to exchange ideas on advanced techniques and recent developments in neural information processing. The conference further serves to stimulate local and regional interests in neural information processing and its potential applications to industries indigenous to this region. Topics of Interest Track$B-5(J: Neurobiological Basis of Brain Functions(J Track$B-6(J: Mathematical Theory of Brain Functions(J Track$B-7(J: Cognitive and Behavioral Aspects of Brain Functions(J Track$B-8(J: Theoretical and Technical Aspects of Neural Networks(J Track$B-9(J: Distributed Processing Systems(J Track$B-:(J: Applications of Neural Networks(J Track$B-;(J: Implementations of Neural Networks(J Topics cover (Key Words): Neuroscience, Neurobiology and Biophysics, Learning and Plasticity, Sensory and Motor Systems, Cognition and Perception Algorithms and Architectures, Learning and Generalization, Memory, Neurodynamics and Chaos, Probabilistic and Statistical Methods, Neural Coding Emotion, Consciousness and Attention, Visual and Auditory Computation, Speech and Languages, Neural Control and Robotics, Pattern Recognition and Signal Processing, Time Series Forecasting, Blind Separation, Knowledge Acquisition, Data Mining, Rule Extraction Emergent Computation, Distributed AI Systems, Agent-Based Systems, Soft Computing, Real World Systems, Neuro-Fuzzy Systems Neural Device and Hardware, Neural and Brain Computers, Software Tools, System Integration Conference Committee Conference Chair: Kunihiko Fukushima, Osaka University Conference Vice-chair: Minoru Tsukada, Tamagawa University Organizing Chair: Shuji Yoshizawa, Tokyo University Program Chair: Shiro Usui, Toyohashi University of Technology International Advisory Committee (tentative) Chair: Shun-ichi Amari, Institute of Physical and Chemical Research Members: S. Bang (Korea), J. Bezdek (USA), J. Dayhoff (USA), R. Eckmiller (Germany), W. Freeman (USA), N. Kasabov (New Zealand), H. Mallot (Germany), G. Matsumoto (Japan), N. Sugie (Japan), R. Suzuki (Japan), K. Toyama (Japan), Y. Wu (China), L.Xei (Hong Kong), J. Zurada (USA) Call for paper The Program Committee is looking for original papers on the above mentioned topics. Authors should pay special attention to explanation of theoretical and technical choices involved, point out possible limitations and describe the current states of their work. All received papers will be reviewed by the Program Committee. The authors will be informed about the decision of the review process by June 22, 1998. All accepted papers will be published. As the conference is a multi-disciplinary meeting the papers are required to be comprehensible to a wider rather than to a very specialized audience. Instruction to Authors Papers must be received by March 31, 1998. The papers must be submitted in a camera-ready format. Electronic or fax submission is not acceptable. Papers will be presented at the conference either in an oral or in a poster session. Please submit a completed full original pages and five copies of the paper written in English, and backing material in a large mailing envelope. Do not fold or bend your paper in any way. They must be prepared 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. Centered at the top of the first page should be the complete title, author(s), mailing and e-mailing addresses, followed by 100-150 words abstract and the text. Extra 2 pages are permitted with a cost of 5000 yen/page. Use black ink. Do not use any other color, either in the text or illustrations. The proceedings will be printed with black ink on white paper. In the covering letter the track and the topic of the paper according to the list above should be indicated. No changes will be possible after submission of your manuscript. Authors may also retrieve the ICONIP style "iconip98.tex", "iconip98.sty" and "sample.eps" files (they are compressed as form.tar.gz) for the conference via WWW at URL http://jnns-www.okabe.rcast.u-tokyo.ac.jp/jnns/ICONIP98.html. Language The use of English is required for papers and presentation. No simultaneous interpretation will be provided. Registration The deadline for Registration for speakers and Early Registration for non-speakers with remittance will be July 31, 1998. The registration fee for General Participant includes attendance to the conference, proceedings, banquette and reception. The registration fee for Student includes attendance to the conference and proceedings. Conference Venue Kitakyushu is a northern city in Kyushu Island, south west of Japan main islands. The place is one of the Japanese major industrial areas, and also has long history of two thousand years in Japanese and Chinese ancient records. There are direct flights from Asian and American major airports. You will be able to enjoy some technical tours and excursion in the area. Passport and Visa All foreign attendants entering Japan must possess a valid passport. Those requiring visas should apply to the Japanese council or diplomatic mission in their own country prior to departure. For details, participants are advised to consult their travel agents, air-line reservation office or the nearest Japanese mission. Events Exhibition, poster sessions, workshops, forum will be held at the conference. Two satellite workshops will be held just before or after the conference. Social Events Banquette, reception and excursion will be held at the conference. The details will be announced in the second circular. Workshops Two satellite workshops will be held. One is "Satellite workshop for young researcher on Information processing" that will be held after the conference. The detail is announced in the attached paper. Another workshop "Dynamical Brain" is under programming. This will take place in Brain Science Research Center, Tamagawa University Research Institute. The details will be announced in the Second Circular. Please see second circular for more information on these workshops, and possibly other new ones. Important Dates for ICONIP'98 Papers Due: March 31, 1998 Notification of Paper Acceptance: June 22, 1998 Second Circular (with Registration Form): June 22, 1998 Registration of at least one author of a paper: July 31, 1998 Early Registration: July 31, 1998 Conference: October 21-23, 1998 Workshop: October 24-26, 1998 Further Information & Paper Submissions ICONIP'98 Secretariat Mr. Masahito Matsue Japan Technical Information Service Sogo Kojimachi No.3 Bldg. 1-6 Kojimachi, Chiyoda-ku, Tokyo 102, Japan Tel:+81-3-3239-4565 Fax:+81-3-3239-4714 E-mail: jatisc at msn.com $B!y(J Could you suggest your friends and acquaintances who will be interested (J in ICONIP'98-Kitakyushu? Thank you. ---------------------------------------------------------------------------- - ICONIP'98-Kitakyushu 21-23 October, 1998 Tentative Registration (PLEASE PRINT) Name: Professor Dr. Ms. Mr. Last Name First Name Middle Name Affiliation: Address: Country: Telephone: Fax: E-mail: $B""(J I intend to submit a paper.(J The tentative title of my paper is: $B""(J I intend to attend the conference.(J $B""(J I want to receive the Second Circular.(J Please mail a copy of this completed form to: ICONIP'98 Secretariat Mr. Masahito Matue Japan Technical Information Service Sogo Kojimachi No.3 Bldg. 1-6 Kojimachi, Chiyoda-ku, Tokyo 102, Japan Tel:+81-3-3239-4565 Fax:+81-3-3239-4714 E-mail: jatisc at msn.com ************************************************** * Takashi Omori, Ph.D * * BASE: Biologocal Applications & Systems Engineering * * Tokyo University of Agriculture & Technology * Nakacho 2-24-16 , Koganei, Tokyo 184 Japan * +81-423-88-7148 FAX:+81-423-85-5395 * omori at cc.tuat.ac.jp ************************************************************** From jls at cs.man.ac.uk Fri Feb 13 11:17:37 1998 From: jls at cs.man.ac.uk (Jon Shapiro) Date: Fri, 13 Feb 1998 16:17:37 GMT Subject: Lectureship in Modelling of Living/Organic Systems and Information Systems Message-ID: <199802131617.QAA07007@rdf074.cs.man.ac.uk.> Hi, We are seeking applicants for an opening in the Computer Science Department at Manchester University for a Lecturer in Modelling of Living/Organic Systems and Information Systems. This is equivalent to a tenure-track Assistant Professor position in the U.S. Closing date is 28 February 1998. Please pass this on to any researcher you think might be interested. For more information, look at http://www.cs.man.ac.uk, or contact Professor John Gurd (jrg at cs.man.ac.uk). Thanks, Jonathan Shapiro ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Department of Computer Science University of Manchester A Research-Led Expansion in Computer Science has led to the establishment of the following posts: Chair in Formal Methods for Computing Science Chair and 2 Lectureships in Mobile Systems Architecture 3 Lectureships in Modelling and Simulation: Lectureships in Process Modelling and Information Engineering, Modelling of Living/Organic Systems and Information Systems. 50 Years after the first stored-program electronic digital computer was developed at the University of Manchester, the Department of Computer Science at Manchester remains a world leader in research and teaching in Computer Science. We are looking to appoint staff with international research reputation or potential. These new posts offer individuals with appropriate experience an opportunity to contribute to world leading research developments from a position of strength. See our Web Page http://www.cs.man.ac.uk for further details. From SaadE at TTACS.TTU.EDU Fri Feb 13 16:29:10 1998 From: SaadE at TTACS.TTU.EDU (Emad William Saad) Date: Fri, 13 Feb 1998 15:29:10 -0600 Subject: Explanation Capability of Neural Networks Message-ID: <34E4BB26.D086E4EE@ttu.edu> I have been doing litterature search on the subject of "Explanation Capability of Neural Networks/ Rule extraction of NN's", and came with the following bibliography: [1] Fu, Y., ?Data mining: Tasks, techniques and applications,? Potentials, vol. 16, no. 4, pp. 18-20, 1997. [2] Andrews, R., Diederich, J., and Tickle, A., ?A Survey and Critique of Techniques for Extracting Rules from Trained Artificial Neural Networks,? Knowledge-Based Systems, vol. 8, no. 6, pp. 373-389, 1996. [3] Benitez, J. M., Castro, J. L., and Requena, I., ?Are Artificial Neural Networks Black Boxes?,? IEEE Trans. Neural Networks, vol. 8, no. 5, pp. 1156-1164, 1997. [4] Tsukimoto, H., ?Extracting Propositions from Trained Neural Networks,? in Proc. IEEE International Conference on Neural Networks, August 1997. [5] Kindermann, J., and Linden, A., ?Detection of Minimal Microfeatures by Internal Feedback,? in Proc. fifth Austrian Artificial Intelligence Meeting, pp. 230-239, 1989. [6] Healy, M. J., and Caudell, T. P., ?Acquiring Rule Sets as a Product of Learning in a Logical Neural Architecture,? IEEE Trans. Neural Networks, vol. 8, no. 3, pp. 461-474, 1997. [7] Yeung, D. S., and Hak-shun, Fong, "Knowledge Matrix - An Explanation and Knowledge Rrefinement Facility for a Rule Induced Neural Network," in Proc. Twelfth National Conference on Artificial Intelligence, 1994, vol. 2, pp. 889-894. [8] Machado, R. J., and da Rocha, A. F., "Inference, Inquiry, Evidence Censorship, and Explanation in Connectionist Expert Systems," IEEE Trans. Fuzzy Systems, vol. 5, no. 3, pp 443-459. [9] Gilstrap, L. O., and Dominy, R. E., "A General Explanation and Interogation System for Neural Networks," in Proc. International Joint Conference on Neural Networks, Washington, DC, June 1989, vol. 2, pp. 594. [10] Taha, I., and Ghosh, J., "Evaluation and Ordering of Rules Extracted from Feedward Networks," in Proc. IEEE International Conference on Neural Networks, Houston, TX, June 1997, vol. 1, pp. 408-413. [11] Ornes, C., and Sklansky, J., "A Neural Network that Explains as Well as Predicts Financial Market Behavior," in Proc. IEEE/IAFE Computational Intelligence for Financial Engineering, March 1997, pp. 43-49. [12] Ornes, C., and Sklansky, J., "A Visual Multi-Expert Neural Classifier," in Proc. IEEE International Conference on Neural Networks, June 1997, vol. 3, pp. 1448-1453. [13] Taha, I., and Ghosh, J., "Three techniques for extracting rules from feedforward networks," in Intelligent Engineering Systems Through Artificial Neural Networks, vol. 6., ASME Press, November 1996. Please, I would be glad if anybody can guide me to more litterature/ web pages/ resources in this area. Emad Saad Applied Computational Intelligence Laboratory Dept. of Electrical Eng. Texas Tech University, Lubbock, TX 79409 From kr10000 at eng.cam.ac.uk Mon Feb 16 05:46:34 1998 From: kr10000 at eng.cam.ac.uk (K. Reinhard) Date: Mon, 16 Feb 1998 10:46:34 GMT Subject: Announcement of Technical Report availability. Message-ID: <199802161046.11893@opal.eng.cam.ac.uk> The following technical report is available by anonymous ftp from the archive of the Speech, Vision and Robotics Group at the Cambridge University Engineering Department (http://svr-www.eng.cam.ac.uk/reports/index-full.html). PARAMETRIC SUBSPACE MODELING OF SPEECH TRANSITIONS K. Reinhard and M. Niranjan Technical Report CUED/F-INFENG/TR.308 Cambridge University Engineering Department Trumpington Street, Cambridge CB2 1PZ U.K., England Abstract This report describes an attempt at capturing segmental transition information for speech recognition tasks. The slowly varying dynamics of spectral trajectories carries much discriminant information that is very crudely modelled by traditional approaches such as HMMs. In approaches such as recurrent neural networks there is the hope, but not the convincing demonstration, that such transitional information could be captured. The method presented here starts from the very different position of explicitly capturing the trajectory of short time spectral parameter vectors on a subspace in which the temporal sequence information is preserved. We approach this by introducing a temporal constraint into the well known technique of Principal Component Analysis. On this subspace, we attempt a parametric modelling of the trajectory, and compute a distance metric to perform classification of diphones. We use the principal curves method of Hastie and Stuetzle and the Generative Topographic map (GTM) technique of Bishop, Svenson and Williams to describe the temporal evolution in terms of latent variables. On the difficult problem of /bee/, /dee/, /gee/ we are able to retain discriminatory information with a small number of parameters. Experimental illustrations present results on ISOLET and TIMIT database. From robbie at hiki.bcs.rochester.edu Mon Feb 16 12:52:32 1998 From: robbie at hiki.bcs.rochester.edu (Robbie Jacobs) Date: Mon, 16 Feb 1998 12:52:32 -0500 Subject: postdoc position available Message-ID: <199802161752.MAA14907@hiki.bcs.rochester.edu> Postdoctoral Fellowship, Department of Brain and Cognitive Sciences, UNIVERSITY OF ROCHESTER -- The Department of Brain and Cognitive Sciences seeks an outstanding postdoctoral fellow with research interests in the areas of learning and/or developmental cognitive science. Supervising faculty work on the problems of learning and development using behavioral, computational, and neurobiological approaches. Candidates should have prior background/training in at least one of these approaches and an interest in working collaboratively in a highly interdisciplinary setting. Several faculty have special interest in statistical learning in the domains of language and perception, although a commitment to this interest is not a requirement of all applicants. This fellowship is open only to US citizens or permanent residents. Applicants should send a letter describing their graduate training and research interests, a curriculum vitae, and arrange to have three letters of recommendation sent to: Learning, Development, and Biology Training, Department of Brain and Cognitive Sciences, Meliora Hall, University of Rochester, Rochester, NY 14627-0268. Review of applications will begin on April 1, 1998 and continue until the position is filled, with an expected start date of August/September, 1998. Applicants can learn about the department, its faculty, and the opportunities for training by referring to our Web page (http://www.bcs.rochester.edu). Applications from women and members of underrepresented minority groups are especially welcome. The University of Rochester is an Equal Opportunity Employer. From eugene at engr.uconn.edu Mon Feb 16 08:48:18 1998 From: eugene at engr.uconn.edu (Eugene Santos) Date: Mon, 16 Feb 1998 08:48:18 -0500 Subject: [CFP] AI Meets the Real World '98 Lessons Learned! Message-ID: <199802161348.IAA11288@ultra9.uconn.edu> [Sorry if you get this message more than once! It is being posted to several distribution lists.] ------------------------------------------------------------------------------- ------------------------------------------------------------------------------- AI meets the Real World '98 Lessons Learned C a l l f o r P a r t i c i p a t i o n September 16 - 18, 1998 University of Connecticut -- Stamford Campus Stamford, CT Sponsored by: University of Connecticut Honeywell Technology Center US Air Force Research Labs -- Phillips Lab DARPA To a large and growing extent, techniques from the field of Artificial Intelligence are being applied in the implementation of fielded systems addressing practical problems in a wide range of domains, from manufacturing, to consumer services, to military and spacecraft operations, to name a very few. As a result, an informal and pragmatic practice of "AI engineering" has arisen, involving the identification, adaptation, and application of techniques including diagnostic systems, trend analysis and projection, uncertain reasoning and decision analysis, virtual environments/reality, training and tutoring systems, planning and scheduling, natural language parsing and generation, and parameter estimation and other forms of learning. The resulting systems range from large-scale, stand-alone intelligent systems, to embedded knowledge bases, to minor components of much larger applications. As one might expect from a body of work largely developed within a common intellectual and philosophical tradition, what we have here broadly termed "AI techniques" have some common features. These approaches tend to be complex and computationally intensive and to require a great deal of understanding and modelling, in some cases engineering, of the target domain and application for the approach to be successful. The aim of this meeting is to bring together researchers, practitioners, and developers of intelligent systems throughout academia, industry, and government to discuss and disseminate lessons learned from successful (or unsuccessful) attempts to design, construct, field, and maintain intelligent systems. The meeting will consist of presentations, panel discussions, and invited speakers. Our hope is to build a better knowledge base of how to successfully apply and correctly use artificial intelligence in real world systems. This meeting is not intended as a forum for those who already deeply immersed in AI. We particularly welcome people who are considering an AI-based approach to their problem to attend and participate in these discussions. We invite the submission of papers and topic ideas for panel discussions. Papers and presentations should be based on systems developed (or in progress) for real world use. Among the issues that might be of interest in such a presentation we would expect to find the following: -- What characteristics of the domain and the application lead to your choice of solution method? What alternative methods were considered and rejected? Were these choices revisited (and revised?) at some later point? -- What difficulties did you encounter? Which ones were expected? Unexpected? -- What was the final outcome? What qualifications or modifications of the original statement of the problem or system requirements were made? -- What lessons can be drawn from this experience, regarding: +++ domains where particular AI techniques are or aren't useful? +++ how to go about determining the utility of a technique in a new domain? +++ pitfalls to beware in system design, implementation, etc., that are peculiar to intelligent systems? We are also especially INTERESTED in soliciting questions/issues at all levels from both new and experienced systems builders on problems and approaches of using AI. Members of our program committee will attempt to answer and/or provide advice to these questions. These will be published in our printed proceedings. Of these, a select set of questions or general class of questions will be chosen for a special panel discussion session at the conference. Up-to-date meeting information will be provided at: http://www.eng2.uconn.edu/~eugene/AIMTRW Proceedings of invited papers will be published. ---------------- | Organizers | ---------------- Meeting Co-Chairs - ----------------- Eugene Santos, Jr. (University of Connecticut -- Storrs) Mark Boddy (Honeywell Technology Center, Minneapolis, MN) Doug Dyer (DARPA) Program Committee - ----------------- Sheila B. Banks (Air Force Institute of Technology) Piero Bonissone (GE) Jack Breese (Microsoft) Wray Buntine (Ultimode) Fabio Cozman (University of Sao Paulo) Bruce D'Ambrosio (Prevision & Oregon State University) Neal Glassman (Air Force Office of Scientific Research) James Hendler (University of Maryland) Chahira Hopper (Air Force Research Labs, Wright Lab) Lewis Johnson (University of Southern California) F. Alex Kilpatrick (Air Force Research Labs, Phillips Lab) Michael B. Leahy Jr. (DARPA) Claudia M. Meyer (NASA LERC) Alan L. Meyrowitz (Naval Research Laboratory) Doug Moran (SRI) Steve Rogers (Battelle) Solomon Eyal Shimony (Ben Gurion University of the Negev) Mike Shneier (Office of Naval Research) Valerie J. Shute (Air Force Research Labs, Armstrong Lab) Douglas Smith (Kestrel Institute) Martin R. Stytz (Air Force Institute of Technology) Abraham Waksman (Air Force Office of Scientific Research) Fred A. Watkins (Hyperlogic) Edward Wong (Polytechnic University) --------------------------- | Submission Guidelines | --------------------------- Authors should submit full papers addressing the above issues with a strong emphasis on "lessons learned." These will be evaluated for clarity of presentation and significance of contribution to the community. All accepted papers will be presented either orally or through a poster session and will be made available in a printed proceedings. Papers may be submitted either electronically or in hard copy form. Electronic submission may take the form of PostScript files, ASCII, or LaTeX files. Authors should be careful to include all macro files necessary for LaTeX files as we will not be responsible for files which cannot be formatted. Figures for LaTeX should be PostScript files. Hardcopy submissions should have 1-inch margins on all sides and should be in 12-point type. Papers should be a maximum of 20 pages long, including figures and references. Names, address, and e-mail of authors and an abstract should be included at the beginning of each paper. Hard copy submissions must arrive by May 15, 1998, and sent to Eugene Santos, Jr. [ATTN: AIMTRW-98] Computer Science and Engineering Department University of Connecticut UTEB, 191 Auditorium Rd., U-155 Storrs, CT 06269-3155 (860) 486-1458 Electronic submissions should be e-mailed by May 15, 1998, to eugene at eng2.uconn.edu Papers not meeting the deadline will not be considered. Proposals for panel discussions and invited speakers should be e-mailed by May 15, 1997, to the above address. For questions/issues, we solicit up to two (2) pages per question. Provide as much detail as possible for proper evaluation of the question by the program committee. We prefer electronic submissions to the above email address. Hard copy is welcome to the above address. These are also due May 15, 1998. ++++++++++++++++++++++++++++++++++++++ !++Meeting Attendance/Participation++! ++++++++++++++++++++++++++++++++++++++ Due to the limited space available for this meeting, we request that those planning to attend send an e-mail by May 1, 1998 to eugene at eng2.uconn.edu stating your intent and whether you will be also submitting a paper. --------------------- | Important Dates | --------------------- May 1, 1998 Deadline for participation request May 15, 1998 Deadline for paper submission May 15, 1998 Deadline for question submission May 15, 1998 Deadline for panel proposals, etc. June 15, 1998 Notification of acceptance or rejection June 29, 1998 Final camera-ready papers due September 16 - 18, 1998 Meeting dates From kirchmai at informatik.tu-muenchen.de Mon Feb 16 09:39:59 1998 From: kirchmai at informatik.tu-muenchen.de (Clemens Kirchmair) Date: Mon, 16 Feb 1998 15:39:59 +0100 (MET) Subject: Early registration deadline for FNS'98: 02/18/1998 Message-ID: ######################################################################### ATTENTION: The early registration deadline for the FNS '98 Workshop is Wednesday, February 18th, 1998. You can still save 100,- DM if you register now! Don't miss this excellent workshop! (Full program -- see below) The 5th International Workshop "Fuzzy-Neuro Systems '98 - Computational Intelligence" takes place in Munich, Germany, from March 19 to 20, 1998. Visit our WWW Homepage: http://wwwbrauer.informatik.tu-muenchen.de/~fns98/ Conference fees (registration UNTIL February 18th) industry rate: 495,- DM university rate: 345,- DM GI members: 295,- DM students (up to age of 26): 60,- DM (excluding proceedings and conference dinner.) Conference fees (registration AFTER February 18th) industry rate: 595,- DM university rate: 445,- DM GI members: 395,- DM students (up to age of 26): 160,- DM (excluding proceedings and conference dinner.) ######################################################################### ---------------------------------- | Fuzzy-Neuro Systems '98 | | - Computational Intelligence - | | | | 5th International Workshop | | March, 19 - 20, 1998 | ---------------------------------- Technische Universitaet Muenchen Gesellschaft fuer Informatik e.V. Fachausschuss 1.2 "Inferenzsysteme" Technische Universitaet Muenchen Institut fuer Informatik Fuzzy-Neuro Systems '98 is the fifth event of a well established series of workshops with international participation. Its aim is to give an overview of the state of art in research and development of fuzzy systems and artificial neural networks. Another aim is to highlight applications of these methods and to forge innovative links between theory and application by means of creative discussions. Fuzzy-Neuro Systems '98 is being organized by the Technical Committee 1.2 "Inference Systems" (Fachausschuss 1.2 "Inferenzsysteme") of the German Informatics Society GI (Gesellschaft fuer Informatik e. V.) and Institut fuer Informatik, Technische Universitaet Muenchen in cooperation with Siemens AG and with the support of Kratzer Automatisierung GmbH. The workshop takes place at the Technische Universitaet Muenchen in Munich from March, 19 to 20, 1998. PROGRAM ------- Wednesday, March 18, 1998 18:00 Informal Get-Together Registration 21:00 End of reception and registration Thursday, March 19, 1998 8:00 Registration 9:00 Formal Opening President, TU Muenchen Dekan, Institut fuer Informatik, TU Muenchen Workshop Chair 9:15 Invited Lecture 1: Sets, Fuzzy Sets and Rough Sets Zdzislaw Pawlak, Warsaw University of Technology, Poland Chairman: W. Brauer, TU Muenchen 10:00 Session 1: Fuzzy Control Chairman: R. Isermann, TU Darmstadt Indirect Adaptive Sugeno Fuzzy Control J. Abonyi, L. Nagy, S. Ferenc, University of Veszprem, Veszprem, Hungary Simultaneous Creation of Fuzzy Sets and Rules for Hierarchical Fuzzy Systems R. Holve, FORWISS, Erlangen, Germany 10:50 Coffee break - Presentation of Posters 11:10 Session 2: Neural Networks for Classification Chairman: K. Obermayer, TU Berlin Hybrid Systems for Time Series Classification C. Neukirchen, G. Rigoll, Gerhard-Mercator-Universitaet, Duisburg How Parallel Plug-in Classifiers Optimally Contribute to the Overall System W. Utschick, J.A. Nossek, TU Muenchen 12:00 Invited Lecture 2: Is Readibility Compatible with Accuracy? Hugues Bersini, Universite Libre de Bruxelles, Belgium Chairman: J. Hollatz, Siemens AG, Muenchen 12:45 Lunch 14:00 Session 3: Fuzzy Logic in Data Analysis Chairman: C. Freksa, Universitaet Hamburg Fuzzy Topographic Kernel Clustering T. Graepel, K. Obermayer, TU Berlin Dynamic Data Analysis: Similarity Between Trajectories A. Joentgen, L. Mikenina, R. Weber, H.-J. Zimmermann, RWTH Aachen Spatial Reasoning with Uncertain Data Using Stochastic Relaxation R. Moratz, C. Freksa, Universitaet Hamburg Noise Clustering For Partially Supervised Classifier Design C. Otte, P. Jensch, Universitaet Oldenburg Fuzzy c-Mixed Prototypes Clustering C. Stutz, TU Muenchen T.A. Runkler, Siemens AG, Muenchen 16:00 Coffee break - Presentation of Posters 16:30 Invited Lecture 3: Neural Network Architectures for Time Series Prediction with Applications to Financial Data Forecasting Hans-Georg Zimmermann, Siemens AG, Muenchen Chairman: R. Rojas, FU Berlin 17:15 Session 4: Fuzzy-Neuro Systems Chairman: R. Kruse, Universitaet Magdeburg A Neuro-Fuzzy Approach to Feedforward Modeling of Nonlinear Time Series T. Briegel, V. Tresp, Siemens AG, Muenchen A Learning Algorithm for Fuzzy Neural Nets T. Feuring,Westfaelische Wilhelms-Universitaet Muenster James J. Buckley, University of Alabama at Birmingham, Birmingham, USA Improving a priori Control Knowledge by Reinforcement Learning M. Spott, M. Riedmiller, Universitaet Karlsruhe 18:30 End of First Day 20:00 Conference Dinner Friday, March 20, 1998 9:00 Session 5: Applications Chairman: G. Nakhaeizadeh, Daimler Benz AG, Forschung + Technik, Ulm Batch Recipe Optimization with Neural Networks and Genetice Algorithms K. Eder, Kratzer Automatisierung GmbH, Unterschleissheim Robust Tuning of Power System Stabilizers by an Accelerated Fuzzy-Logic Based Genetic Algorithm M. Khederzadeh, Power and Water Institute of Technology, Tehran, Iran Relating Chemical Structure to Activity: An Application of the Neural Folding Architecture T. Schmitt, C. Goller, TU Muenchen Optimization of a Fuzzy System Using Evolutionary Algorithms Q. Zhuang, M. Kreutz, J. Gayko, Ruhr-Universitaet Bochum 10:40 Coffee break - Presentation of Posters 11:00 Invited Lecture 4: Advanced Fuzzy-Concepts and Applications Harro Kiendl, Universitaet Dortmund Chairman: K. Eder, Kratzer Automatisierung GmbH, Unterschleissheim 11:45 Session 6: Theory and Foundations of Fuzzy-Logic Chairman: P. Klement, Universitaet Linz, Austria Rule Weights in Fuzzy Systems D. Nauck, R. Kruse, Universitaet Magdeburg Sliding-Mode-Based analysis of Fuzzy Gain Schedulers - The MIMO Case R. Palm, Siemens AG, Muenchen D. Driankov, University of Linkoeping, Sweden Qualitative Operators For Dealing With Uncertainty H. Seridi, Universite de Reims, France F. Bannay-Dupin, Universite d'Angers, France H. Akdag, Universite P. & M. Curie, Paris, France 13:00 Lunch 14:00 Session 7: Theory and Foundations of Neural Networks Chairman: A. Grauel, Universitaet Paderborn Prestructured Recurrent Neural Networks T. Brychcy, TU Muenchen Formalizing Neural Networks I. Fischer, University of Erlangen M. Koch, Technical University of Berlin M.R. Berthold, University of California, Berkeley, USA Correlation and Regression Based Neuron Pruning Strategies M. Rychetsky, S. Ortmann, C. Labeck, M. Glesner, TU Darmstadt 15:15 Invited Lecture 5: Soft Computing: the Synergistic Interaction of Fuzzy, Neural, and Evolutionary Computation Piero P. Bonissone, General Electric Corporate R&D Artificial Intelligence Laboratory, Schenectady, USA Chairman: S. Gottwald, Universitaet Leipzig 16:00 Closing Remarks and Invitation to FNS'99 Posters ------- Comparing Fuzzy Graphs M.R. Berthold, University of California, Berkeley, USA K.-P. Huber, Universitaet Karlsruhe A Numerical Approach to Approximate Reasoning via a Symbolic Interface. Application to Image Classification A. Borgi, H. Akdag, Universite P. & M. Curie, Paris, France J.-M. Bazin, Universite de Reims, France Entropy-Controlled Probabilistic Search M. David, J. Gottlieb, I. Kupka, TU Clausthal Ensembles of Evolutionary Created Artificial Neural Networks C.M. Friedrich, Universitaet Witten/Herdecke Design and Implementation of a Flexible Simulation Tool for Hybrid Problem Solving H. Geiger, IBV and TU Muenchen J. Pfalzgraf, K. Frank, T. Neuboeck, J. Weichenberger, Universitaet Salzburg, Austria A. Buecherl, TU Muenchen A Fuzzy Invariant Indexing Technique for Object Recognition under Partial Occlusion T. Graf, A. Knoll, A. Wolfram, Universitaet Bielefeld Fuzzy Causal Networks R. Hofmann, V. Tresp, Siemens AG, Muenchen Dynamic Data Analysis: Problem Description And Solution Approaches A. Joentgen, L. Mikenina, R. Weber, H.-J. Zimmermann, RWTH Aachen Filtering and Compressing Information by Neural Information Processor R. Kamimura, Tokai University, Japan A Fuzzy Local Map with Asymmetric Smoothing Using Voronoi Diagrams B. Lang, Siemens AG, Muenchen Fuzzy Interface with Prior Concepts and Non-convex Regularization J.C. Lemm, Universitaet Muenster Modeling and Simulating a Time-Dependent Physical System Using Fuzzy Techniques and a Recurrent Neural Network A. Nuernberger, A. Radetzky, R. Kruse, Universitaet Magdeburg The Kohonen Network Incorporating Explicit Statistics and Its Application to the Traveling Salesman Problem B.J. Oommen, Carleton University, Ottawa, Canada Automated Feature Selection Strategies: An experimental comparison improving Engine Knock Detection S. Ortmann, M. Rychetsky, M. Glesner, TU Darmstadt A Fuzzy-Neuro System for Reconstruction of Multi-Sensor information S. Petit-Renaud, T. Deneux, Universite de Technologie de Compiegne, Compiegne, France RACE: Relational Alternating Cluster Estimation and the Wedding Table Problem T.A. Runkler, Siemens AG, Muenchen J.C. Bezdek, University of West Florida, Pensacola, USA Neural Networks Handle Technological Information for Milling if Training Data is Carefully Preprocessed G. Schulz, D. Fichtner, A. Nestler, J. Hoffmann, TU Dresden Medically Motivated Testbed for Reinforcement Learning in Neural Architectures D. Surmeli, G. Koehler, H.-M. Gross, TU Ilmenau Adaptive Input-Space Clustering for Continuous Learning Tasks M. Tagscherer, P. Protzel, FORWISS, Erlangen A Criminalistic And Forensic Application Of Neural Networks A. Tenhagen, T. Feuring, W.-M. Lippe, G. Henke, H. Lahl, WWU-Muenster A Classical and a Fuzzy System Based Algorithm for the Simulation of the Waste Humidity in a Landfill M. Theisen, M. Glesner, TU Darmstadt FuNN, A Fuzzy Neural Logic Model R. Yasdi, GMD - Forschungszentrum Informationstechnik, Sankt Augustin An Efficient Model for Learning Systems of High-Dimensional Input within Local Scenarios J. Zhang, V. Schwert, Universitaet Bielefeld Optimization of a Fuzzy Controller for a Driver Assistant System Q. Zhuang, J. Gayko, M. Kreutz, Ruhr-Universitaet-Bochum Program Committee ----------------- Prof. Dr. W. Banzhaf, Universitaet Dortmund Dr. M. Berthold, Universitaet Karlsruhe Prof. Dr. Dr. h.c. W. Brauer, TU Muenchen (Chairman) Prof. Dr. G. Brewka, Universitaet Leipzig Dr. K. Eder, Kratzer Automatisierung GmbH, Unterschleissheim Prof. Dr. C. Freksa, Universitaet Hamburg Prof. Dr. M. Glesner, TU Darmstadt Prof. Dr. S. Gottwald, Universitaet Leipzig Prof. Dr. A. Grauel, Universitaet Paderborn/Soest Prof. Dr. H.-M. Gross, TU Ilmenau Dr. A. Guenter, Universitaet Bremen Dr. J. Hollatz, Siemens AG, Muenchen Prof. Dr. R. Isermann, TU Darmstadt Prof. Dr. P. Klement, Universitaet Linz, Austria Prof. Dr. R. Kruse, Universitaet Magdeburg (Vice Chairman) Prof. Dr. B. Mertsching, Universitaet Hamburg Prof. Dr. G. Nakhaeizadeh, Daimler Benz AG, Forschung + Technik, Ulm Prof. Dr. K. Obermayer, TU Berlin Prof. Dr. G. Palm, Universitaet Ulm Dr. R. Palm, Siemens AG, Muenchen Dr. L. Peters, GMD - Forschungszentrum Informationstechnik GmbH, Sankt Augustin Prof. Dr. F. Pichler, Universitaet Linz, Austria Dr. P. Protzel, FORWISS, Erlangen Prof. Dr. B. Reusch, Universitaet Dortmund Prof. Dr. Rigoll, Universitaet Duisburg Prof. Dr. R. Rojas, Freie Universitaet Berlin Prof. Dr. B. Schuermann, Siemens AG, Muenchen (Vice Chairman) Prof. Dr. W. von Seelen, Universitaet Bochum Prof. Dr. H. Thiele, Universitaet Dortmund Prof. Dr. W. Wahlster, Universitaet Saarbruecken Prof. Dr. H.-J. Zimmermann, RWTH Aachen Organization Committee ---------------------- Prof. Dr. Dr. h.c. W. Brauer (Chairman) Dieter Bartmann Till Brychcy Clemens Kirchmair Technische Universitaet Muenchen Tel.: 0 89/2 89-2 84 19 Fax: 0 89/2 89-2 84 83 Dr. Juergen Hollatz, Siemens AG, Muenchen (Vice Chairman) Christine Harms, - ccHa -, Sankt Augustin Conference Site --------------- TU Muenchen Barerstrasse 23 Entrance: Arcisstrasse Lecture hall S0320 D-80333 Muenchen Workshop Secretariat -------------------- Christine Harms c/o GMD / FNS'98 Schloss Birlinghoven D-53754 Sankt Augustin Tel.: ++49 2241 14-24 73 Fax: ++49 2241 14-24 72 email: christine.harms at gmd.de Registration ------------ Please make your (binding) reservation by sending the enclosed registration form to the conference secretariat. Confirmation will be given after receipt of the registration form. Conference Fees: (see registration form) industry rate: 495,- DM university rate: 345,- DM GI members: 295,- DM authors: 295,- DM students (up to age of 26): 60,- DM (*) *) excluding proceedings and conference dinner. A surcharge of DM 100,- is payable for registration after February, 18, 1998. Services of Gesellschaft fuer Informatik e. V. (GI) are VAT-free according to German law p. 4 Nr. 22a UStG. Payment (see registration form) ------- [ ] I have transferred the whole amount of DM________ to Gesellschaft fuer Informatik (GI), Sparkasse Bonn Account No.: 39 479 Bankcode: 380 500 00 Ref: SK-Fuzzy-98 [ ] I enclose a Eurocheque amounting to made payable to Gesellschaft fuer Informatik [ ] Please debit my [ ] Diners [ ] Visa [ ] Euro/Mastercard Cardnumber: Expiration date: Cardholder: Social events ------------- Informal get-together: March, 18, 1998, 18.00 - 21.00 Conference dinner: Thursday, March, 19,1998. Accommodation ------------- A limited number of rooms has been reserved at the FORUM/Penta Hotel at the special rate of single room DM 175,- double room DM 200,- FORUM Hotel Hochstrasse 3 D-81669 Muenchen Cancellation ------------ If cancellation is received up to February, 17, 1998, a 75% refund will be given. For cancellations received afterwards, no refunds can be guaranteed. WWW-Homepage ------------ URL: http://wwwbrauer.informatik.tu-muenchen.de/~fns98/ ----- snip, snip ----- Registration form for Fuzzy-Neuro Systems '98 --------------------------------------------- Please register me as follows Conference Fees: ---------------- [ ] industry rate: 495,- DM [ ] university rate: 345,- DM [ ] GI member No. 295,- DM [ ] authors: 295,- DM [ ] students (up to age of 26): 60,- DM (*) *) excluding proceedings and conference dinner Accommodation: -------------- I would like to make a binding reservation at the FORUM/Penta Hotel [ ] single room DM 175,- [ ] double room DM 200,- (together with ____________________________) Arrival date ______________________________ Departure date ___________________________ Payment directly at the hotel. Hotel booking has to be made until February, 17, 1998. After that we cannot guarantee any bookings. Conference diner: ----------------- [ ] I intend to participate in the conference dinner ...... extra ticket for conference dinner DM 50,-. Payment: -------- [ ] I have transferred the whole amount of DM________ to Gesellschaft fuer Informatik (GI), Sparkasse Bonn Account No.: 39 479 Bankcode: 380 500 00 Reference: SK-Fuzzy-98 [ ] I enclose a Eurocheque amounting to DM_________ made payable to Gesellschaft fuer Informatik [ ] Please debit my [ ] Diners [ ] Visa [ ] Euro/Mastercard Cardnumber:______________Expiration date:_________ Cardholder:_______________________________________ If cancellation is received up to February, 17, 1998, a 75% refund will be given. For cancellations received afterwards, no refunds can be guaranteed. Date:___________ Signature:__________________ Sender: ------- Last Name (Mr. / Mrs. / MS. Title): ________________________________________ First Name: ________________________________________ Affiliation: ________________________________________ Street/POB: ________________________________________ Zip/Postal Code/City: ________________________________________ Country: ________________________________________ Phone/Fax: ________________________________________ E-mail: ________________________________________ If you would like to take part in the workshop, please send the completed registration form to Christine Harms c/o GMD / FNS'98 Schloss Birlinghoven D-53754 Sankt Augustin Tel.: ++49 2241 14-24 73 Fax: ++49 2241 14-24 72 email: christine.harms at gmd.de From pfbaldi at netid.com Tue Feb 17 16:04:07 1998 From: pfbaldi at netid.com (pfbaldi@netid.com) Date: Tue, 17 Feb 1998 21:04:07 +0000 Subject: Book on Bioinformatics Message-ID: <199802180507.VAA21966@polaris.pacificnet.net> The following book is now available from MIT Press: Bioinformatics: the Machine Learning Approach Pierre Baldi and Soren Brunak February 1998 ISBN 0-262-02442-X 360 pp., 62 illus., 10 color $40.00 (cloth) MIT Press (800) 625-8569 (617) 253-5249 (617) 258-6894 (FAX) Additional information can be found at: http://mitpress.mit.edu/book-home.tcl?isbn=026202442X -------------------------------------------------------------------------- Table of Contents Series Foreword Preface 1 Introduction 1.1 Biological Data in Digital Symbol Sequences 1.2 Genomes--Diversity, Size, and Structure 1.3 Proteins and Proteomes 1.4 On the Information Content of Biological Sequences 1.5 Prediction of Molecular Function and Structure 2 Machine Learning Foundations: The Probabilistic Framework 2.1 Introduction: Bayesian Modeling 2.2 The Cox-Jaynes Axioms 2.3 Bayesian Inference and Induction 2.4 Model Structures: Graphical Models and Other Tricks 2.5 Summary 3 Probabilistic Modeling and Inference: Examples 3.1 The Simplest Sequence Models 3.2 Statistical Mechanics 4 Machine Learning Algorithms 4.1 Introduction 4.2 Dynamic Programming 4.3 Gradient Descent 4.4 EM/GEM Algorithms 4.5 Markov Chain Monte Carlo Methods 4.6 Simulated Annealing 4.7 Evolutionary and Genetic Algorithms 4.8 Learning Algorithms: Miscellaneous Aspects 5 Neural Networks: The Theory 5.1 Introduction 5.2 Universal Approximation Properties 5.3 Priors and Likelihoods 5.4 Learning Algorithms: Backpropagation 6 Neural Networks: Applications 6.1 Sequence Encoding and Output Interpretation 6.2 Prediction of Protein Secondary Structure 6.3 Prediction of Signal Peptides and Their Cleavage Sites 6.4 Applications for DNA and RNA Nucleotide Sequences 7 Hidden Markov Models: The Theory 7.1 Introduction 7.2 Prior Information and Initialization 7.3 Likelihood and Basic Algorithms 7.4 Learning Algorithms 7.5 Applications of HMMs: General Aspects 8 Hidden Markov Models: Applications 8.1 Protein Applications 8.2 DNA and RNA Applications 8.3 Conclusion: Advantages and Limitations of HMMs 9 Hybrid Systems: Hidden Markov Models and Neural Networks 9.1 Introduction to Hybrid Models 9.2 The Single-Model Case 9.3 The Multiple-Model Case 9.4 Simulation Results 9.5 Summary 10 Probabilistic Models of Evolution: Phylogenetic Trees 10.1 Introduction to Probabilistic Models of Evolution 10.2 Substitution Probabilities and Evolutionary Rates 10.3 Rates of Evolution 10.4 Data Likelihood 10.5 Optimal Trees and Learning 10.6 Parsimony 10.7 Extensions 11 Stochastic Grammars and Linguistics 11.1 Introduction to Formal Grammars 11.2 Formal Grammars and the Chomsky Hierarchy 11.3 Applications of Grammars to Biological Sequences 11.4 Prior Information and Initialization 11.5 Likelihood 11.6 Learning Algorithms 11.7 Applications of SCFGs 11.8 Experiments 11.9 Future Directions 12 Internet Resources and Public Databases 12.1 A Rapidly Changing Set of Resources 12.2 Databases over Databases and Tools 12.3 Databases over Databases 12.4 Databases 12.5 Sequence Similarity Searches 12.6 Alignment 12.7 Selected Prediction Servers 12.8 Molecular Biology Software Links 12.9 Ph.D. Courses over the Internet 12.10 HMM/NN Simulator A Statistics A.1 Decision Theory and Loss Functions A.2 Quadratic Loss Functions A.3 The Bias/Variance Trade-off A.4 Combining Estimators A.5 Error Bars A.6 Sufficient Statistics A.7 Exponential Family A.8 Gaussian Process Models A.9 Variational Methods B Information Theory, Entropy, and Relative Entropy B.1 Entropy B.2 Relative Entropy B.3 Mutual Information B.4 Jensen's Inequality B.5 Maximum Entropy B.6 Minimum Relative Entropy C Probabilistic Graphical Models C.1 Notation and Preliminaries C.2 The Undirected Case: Markov Random Fields C.3 The Directed Case: Bayesian Networks D HMM Technicalities, Scaling, Periodic Architectures, State Functions, and Dirichlet Mixtures D.1 Scaling D.2 Periodic Architectures D.3 State Functions: Bendability D.4 Dirichlet Mixtures E List of Main Symbols and Abbreviations References Index -------------------------------------------------------------------------------- From dblank at comp.uark.edu Tue Feb 17 23:47:51 1998 From: dblank at comp.uark.edu (Douglas Blank) Date: Tue, 17 Feb 1998 22:47:51 -0600 Subject: PhD Thesis: "Learning to See Analogies: A Connectionist Exploration" Message-ID: <3.0.32.19980217224749.00710f30@comp.uark.edu> The following Ph.D. thesis is now available via - anonymous ftp (ftp://dangermouse.uark.edu/pub/thesis) - web site (http://www.uark.edu/~dblank/thesis.html) - hardcopy (send address to dblank at comp.uark.edu) It is about 200 pages long and the chapters can be retrieved individually as PostScript or PDF files. (Specific retrieval instructions below). Title: Learning to See Analogies: A Connectionist Exploration Douglas S. Blank Joint Ph.D. in Cognitive Science and Computer Science Indiana University, Bloomington ABSTRACT This dissertation explores the integration of learning and analogy-making through the development of a computer program, called Analogator, that learns to make analogies by example. By "seeing" many different analogy problems, along with possible solutions, Analogator gradually develops an ability to make new analogies. That is, it learns to make analogies by analogy. This approach stands in contrast to most existing research on analogy-making, in which typically the a priori existence of analogical mechanisms within a model is assumed. The present research extends standard connectionist methodologies by developing a specialized associative training procedure for a recurrent network architecture. The network is trained to divide input scenes (or situations) into appropriate figure and ground components. Seeing one scene in terms of a particular figure and ground provides the context for seeing another in an analogous fashion. After training, the model is able to make new analogies between novel situations. Analogator has much in common with lower-level perceptual models of categorization and recognition; it thus serves as a unifying framework encompassing both high-level analogical learning and low-level perception. This approach is compared and contrasted with other computational models of analogy-making. The model's training and generalization performance is examined, and limitations are discussed. =========================================================== Title, Abstract, Acknowledgments, Contents 0_intro.pdf 54k 0_intro.ps.gz 71k Chapter 1 INTRODUCTION 1_ch.pdf 172k 1_ch.ps.gz 187k Chapter 2 ANALOGY-MAKING, LEARNING, AND GENERALIZATION 2_ch.pdf 32k 2_ch.ps.gz 40k Chapter 3 CONNECTIONIST FOUNDATIONS 3_ch.pdf 221k 3_ch.ps.gz 189k Chapter 4 THE ANALOGATOR MODEL 4_ch.pdf 578k 4_ch.ps.gz 390k Chapter 5 EXPERIMENTAL RESULTS 5_ch.pdf 702k 5_ch.ps.gz 566k Chapter 6 COMPARISONS WITH OTHER MODELS OF ANALOGY-MAKING 6_ch.pdf 305k 6_ch.ps.gz 276k Chapter 7 CONCLUSION 7_ch.pdf 16k 7_ch.ps.gz 24k APPENDICES, REFERENCES 8_end.pdf 57k 8_end.ps.gz 91k Everything all.pdf 2M all.ps.gz 1M =========================================================== FTP instructions: (e.g., to retrieve Chapter 1) unix> ftp dangermouse.uark.edu Name: anonymous Password: youremail at domain ftp> cd pub/thesis ftp> get 1_ch.ps.gz ftp> bye unix> gunzip 1_ch.ps.gz unix> lpr 1_ch.ps ===================================================================== dblank at comp.uark.edu Douglas Blank, University of Arkansas Assistant Professor Computer Science ==================== http://www.uark.edu/~dblank ==================== From erik at bbf.uia.ac.be Wed Feb 18 11:37:34 1998 From: erik at bbf.uia.ac.be (Erik De Schutter) Date: Wed, 18 Feb 1998 16:37:34 GMT Subject: 1998 Crete Course in Computational Neuroscience Message-ID: <199802181637.QAA14539@kuifje.bbf.uia.ac.be> CRETE COURSE IN COMPUTATIONAL NEUROSCIENCE SEPTEMBER 13 - OCTOBER 9, 1998 FORTH INSTITUTE, CRETE, GREECE DIRECTORS: Erik De Schutter (University of Antwerp, Belgium) Adonis Moschovakis (University of Crete, Greece) Idan Segev (Hebrew University, Jerusalem, Israel) The Crete Course in Computational Neuroscience introduces students to the practical application of computational methods in neuroscience, in particular how to create biologically realistic models of neurons and networks. The course consists of two complimentary parts. A distinguished international faculty gives morning lectures on topics in experimental and computational neuroscience. The rest of the day is spent learning how to use simulation software and how to implement a model of the system the student wishes to study. The first week of the course introduces students to the most important techniques in modeling single cells, networks and neural systems. Students learn how to use the GENESIS, NEURON, XPP and other software packages on their individual unix workstations. During the following three weeks the lectures will be more general, but each week topics ranging from modeling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the the brain will be covered. The course ends with a presentation of the students' modeling projects. The Crete Course in Computational Neuroscience is designed for advanced graduate students and postdoctoral fellows in a variety of disciplines, including neuroscience, physics, electrical engineering, computer science and psychology. Students are expected to have a basic background in neurobiology as well as some computer experience. A total of 28 students will be accepted with an age limit of 35 years. We will accept students of any nationality, but the majority will be from the European Union and affiliated countries (Iceland, Israel, Liechtenstein and Norway). We specifically encourage applications from researchers who work in less-favoured regions of the EU, from women and from researchers from industry. Every student will be charged a tuition fee of 700 ECU (approx. US$770). In the case of students with a nationality from the EU, affiliated countries or Japan, this tuition fee covers lodging, local travel and all course-related expenses. All applicants with other nationalities will be charged an ADDITIONAL fee of 1000 ECU (approx. US$1100) to cover lodging, local travel and course-related expenses. For nationals from EU and affiliated countries economy travel from an EU country to Crete will be refunded after the course. A limited number of students from less-favoured regions world-wide will get their fees and travel refunded. More information and application forms can be obtained: - WWW access: http://bbf-www.uia.ac.be/Crete_index.html Please apply electronically using a web browser if possible. - email: crete_course at bbf.uia.ac.be - by mail: Prof. E. De Schutter Born-Bunge Foundation University of Antwerp - UIA, Universiteitsplein 1 B2610 Antwerp Belgium FAX: +32-3-8202669 APPLICATION DEADLINE: May 1, 1998. Applicants will be notified of the results of the selection procedures by May 31. FACULTY: M. Abeles (Hebrew University Jerusalem, Israel), A. Aertsen (Albert Ludwigs University Freiburg, Germany), A. Borst (Max Planck Institute Tuebingen, Germany), R. Calabrese (Emory University, USA), R. Douglas (Institute of Neuroinformatics, Zurich), G. Dupond (Free University Brussels, Belgium), O. Ekeberg (Royal Institute of Technology, Sweden), A. Feltz (University of Strasbourg, France), T. Flash (Weizmann Institute of Science, Israel), D. Hansel (Ecole Polytechnique Paris, France), J.J.B. Jack (Oxford University, England), R. Kotter (Heinrich Heine University Dusseldorf, Germany), G. LeMasson (University of Bordeaux, France), K. Martin (Institute of Neuroinformatics, Zurich), M. Nicolelis (Duke University, USA), G. Rizzolatti (University of Parma, Italy), J.M. Rinzel (NIH, USA), H. Sompolinsky (Hebrew University Jerusalem, Israel), M. Spira (Hebrew University Jerusalem, Israel), S. Tanaka (RIKEN, Japan), C. Wilson (University of Tennessee, USA), Y. Yarom (Hebrew University Jerusalem, Israel) and others to be named. The Crete Course in Computational Neuroscience is supported by the European Commission (4th Framework Training and Mobility of Researchers program) and by The Brain Science Foundation (Tokyo). Local administrative organization: the Institute of Applied and Computational Mathematics of FORTH (Crete, GR). From cmbishop at microsoft.com Wed Feb 18 11:14:08 1998 From: cmbishop at microsoft.com (Christopher Bishop) Date: Wed, 18 Feb 1998 08:14:08 -0800 Subject: Paper and software available on-line Message-ID: <3FF8121C9B6DD111812100805F31FC0D810C85@red-msg-59.dns.microsoft.com> Paper and Software Available Online: A HIERARCHICAL LATENT VARIABLE MODEL FOR DATA VISUALIZATION NCRG/96/028 Christopher M. Bishop* and Michael E. Tipping# * Microsoft Research St. George House, 1 Guildhall Street Cambridge CB2 3NH, U.K. # Neural Computing Research Group Aston University, Birmingham B4 7ET, U.K. http://neural-server.aston.ac.uk/Papers/postscript/NCRG_96_028.ps.Z Abstract: Visualization has proven to be a powerful and widely-applicable tool for the analysis and interpretation of multi-variate data. Most visualization algorithms aim to find a projection from the data space down to a two-dimensional visualization space. However, for complex data sets living in a high-dimensional space it is unlikely that a single two-dimensional projection can reveal all of the interesting structure. We therefore introduce a hierarchical visualization algorithm which allows the complete data set to be visualized at the top level, with clusters and sub-clusters of data points visualized at deeper levels. The algorithm is based on a hierarchical mixture of latent variable models, whose parameters are estimated using the expectation-maximization algorithm. We demonstrate the principle of the approach on a toy data set, and we then apply the algorithm to the visualization of a synthetic data set in 12 dimensions obtained from a simulation of multi-phase flows in oil pipelines, and to data in 36 dimensions derived from satellite images. A Matlab(R) software implementation of the algorithm is publicly available from the world-wide web. Paper: http://neural-server.aston.ac.uk/Papers/postscript/NCRG_96_028.ps.Z Software: http://www.ncrg.aston.ac.uk/PhiVis Complete searchable database of publications: http://neural-server.aston.ac.uk/ ---------------------------------------------------------------------------- ---- Professor Christopher M. Bishop Microsoft Research, Cambridge St. George House, 1 Guildhall Street Cambridge CB2 3NH Tel: +44/0 1223 744 751 Fax: +44/0 1223 744 777 Email: cmbishop at microsoft.com Web: http://www.ncrg.aston.ac.uk/People/bishopc/Welcome.html ---------------------------------------------------------------------------- ---- From SteinR at moodys.com Wed Feb 18 11:20:49 1998 From: SteinR at moodys.com (Stein, Roger) Date: Wed, 18 Feb 1998 11:20:49 -0500 Subject: Adaptive and intelligent systems in business: Book available Message-ID: Members of the Santa Fe Institute mailing list may have already received this. Apologies... SEVEN METHODS FOR TRANSFORMING CORPORATE DATA INTO BUSINESS INTELLIGENCE by Vasant Dhar and Roger Stein Upper Saddle River, NJ, Prentice-Hall, 1997. My colleague, Vasant Dhar, and I have written a short book on applying intelligent and adaptive systems to business problems. It may be of interest to some subscribers. There are two versions of the book available, one is suited to business people and one is suited to teaching. The book provides a practical methodology for mapping business problems onto solutions involving neural networks, genetic algorithms, nearest-neighbor algorithms, etc. We also provide extended case studies of organizations that have successfully done this. The reaction to the book, in both the academic and professional community, seems to be favorable: "Intelligent Systems are becoming vital at all levels of management from the CEO to the foreman. Dhar and Stein provide one of the clearest and most accessible treatments to date of the subject." - Herbert A. Simon, Nobel Laureate "Seven Methods effectively bridges the gap between lofty technical explanation and the down-to-earth business application of a brand new world of modeling technologies." - Win Farrell, Partner, Coopers and Lybrand A brief summary of the book follows: Seven Methods for Transforming Corporate Data into Business Intelligence combines a thorough treatment of techniques for applying intelligent systems to decision support with a practical framework for analyzing business problems. Vasant Dhar (former Principal, Morgan Stanley and New York University) and Roger Stein (Vice President, Moody's Investors Service and New York University) present in clear and vivid terms the essentials of modern decision support. Seven Methods takes a three stage approach to discussing these new technologies. The book is organized around: * A framework for analyzing business decision problems and mapping solutions onto them * An intuitive but full discussion of the technologies for data mining and automated decision systems * A series of extensive case studies that show, using the framework, how major organizations have made use of these technologies In addition to discussing technologies, Dhar and Stein introduce a unified methodology for analyzing organizations' business problems and evaluating potential solutions. This framework, based on the authors' years of combined experience applying intelligent systems to real business decision problems, encourages business people to think critically about how the strengths and weaknesses of each technique relate to the particular dynamics of an organization and its problems. The authors show not only when a particular modeling method may be useful, but also when its attributes might make it undesirable for a particular problem. The text does not limit itself to one or a few techniques, but rather views various AI and database techniques as components of a toolbox that, if used correctly, can make organizations dramatically more intelligent. Seven Methods provides accessible detailed coverage of * OLAP and data warehousing * Genetic algorithms * Neural networks * Rule-based expert systems * Fuzzy systems * Case-based reasoning * Machine learning The text adopts an informal, conversational style in their exposition. Despite the relaxed style, the book delves into the subtle aspects of each technique while keeping the text readable and non-technical. In order to make the material more accessible, the text makes frequent use of rich graphics. The graphical representation of complex concepts are invaluable in elucidating these topics. To drive home the discussions of modeling techniques and organizational dynamics, the book also provides extended case studies that show in detail how the framework can be applied to analyzing the problems of real organizations. Cases are taken from the experience of firms in a diversity of industries solving an assortment of problems. Firms include: * US WEST * Moody's Investors Service * Compaq Computer Corp. * LBS Capital Management * NYNEX, Inc. * Kaufhof AG * A. C. Neilsen Problem domains include: * customer service * scheduling * data mining * financial market prediction * quality control * consumer product marketing The book is available from Prentice-Hall: (Professional version) Seven Methods for Transforming Corporate Data into Business Intelligence, Upper Saddle River, NJ, Prentice-Hall, 1997. (Academic version) Intelligent Decision Support Methods: The Science of Knowledge Work, Upper Saddle River, NJ, Prentice-Hall, 1997. Online Orders: www.amazon.com Phone: 1-(800) 643-5506. Please give the operator the following "key code": E1001-A1(3). FAX: 1-(800) 835-5327. From annesp at vaxsa.csied.unisa.it Wed Feb 18 10:46:29 1998 From: annesp at vaxsa.csied.unisa.it (annesp@vaxsa.csied.unisa.it) Date: Wed, 18 Feb 1998 16:46:29 +0100 Subject: summer school Message-ID: <98021816462905@vaxsa.csied.unisa.it> From: SMTP%"iiass at tin.it" 18-FEB-1998 16:34:18.19 To: annesp at vaxsa.csied.unisa.it CC: Subj: call ***************************************************************** Please post **************************************************************** International Summer School ``Neural Nets E. R. Caianiello" 3rd Course "A Course on Speech Processing, Recognition, and Artificial Neural Networks" web page: http://wsfalco.ing.uniroma1.it/Speeschool.html The school is jointly organized by: INTERNATIONAL INSTITUTE FOR ADVANCED SCIENTIFIC STUDIES (IIASS) Vietri sul Mare (SA) Italy, ETTORE MAJORANA FOUNDATION AND CENTER FOR SCIENTIFIC CULTURE (EMFCSC) Erice (TR), Italy Supported by: EUROPEAN SPEECH COMMUNICATION ASSOCIATION (ESCA) Sponsored by: SALERNO UNIVERSITY, Dipartimento di Scienze Fisiche E.R. Caianiello (Italy) DIRECTORS OF THE COURSE DIRECTORS OF THE SCHOOL AND ORGANIZING COMMITTEE: Gerard Chollet (France). Maria Marinaro (Italy) M. Gabriella Di Benedetto (Italy) Michael Jordan (USA) Anna Esposito (Italy) Maria Marinaro (Italy) PLACE: International Institute for Advanced Scientific Studies (IIASS) Via Pellegrino 19, 84019 Vietri sul Mare, Salerno (Italy) DATES: 5th-14th October 1998 POETIC TOUCH Vietri (from "Veteri", its ancient Roman name) sul Mare ("on sea") is located within walking distance from Salerno and marks the beginning of the Amalfi coast. Short rides take to Positano, Sorrento, Pompei, Herculaneum, Paestum, Vesuvius, or by boat, the islands of Capri, Ischia, and Procida. Velia (the ancient "Elea" of Zeno and Parmenide) is a hundred kilometers farther down along the coast. Student Fee: 1500 dollars Student fee include accommodations (arranged by the school), meals, one day of excursion, and a copy of the proceedings of the school. Transportation is not included. A few scholarships are available for students who are otherwise unable to participate at the school, and who cannot apply for the grants offered by ESCA. The scholarship will partially cover lodging and living expenses. Day time: 3 hour in the morning, three hour in the afternoon. Day free: One day with an excursion of the places around. AIMS: The aim of this school is to present the experiments, the theories and the perspectives of acoustic phonetics, as well as to discuss recent results in the speech literature. The school aims to provide a background for further study in many of the fields related to speech science and linguistics, including automatic speech recognition. The school will bring together leading researchers and selected students in the field of speech science and technology to discuss and disseminate the latest techniques. The school is devoted to an international audience and in particular to all students and scientists who are working on some aspects of speech and want to learn other aspects of this discipline. MAJOR TOPICS The school will cover a number of broad themes relevant to speech, among them: 1) Speech production and acoustic phonetics 2) Articulatory, acoustic, and prosodic features 3) Acoustic cues in speech perception 4) Models of speech perception 5) Speech processing (Preprocessing algorithms for Speech) 6) Neural Networks for automatic speech recognition 7) Multi-modal speech recognition and recognition in adverse environments. 8) Speech to speech translation (Vermobil and CSTAR projects) 9) Applications (Foreign Language training aids, aids for handicapped, ....). 10) Stochastic Models and Dialogue systems FORMAT The meeting will follow the usual format of tutorials and panel discussions together with poster sessions for contributed papers. The following tutorials are planned: ABEER ALWAN UCLA University (CA) USA "Models of Speech Production and Their Application in Coding and Recognition" ANDREA CALABRESE University of Connecticut (USA) "Prosodic and Phonological Aspects of Language" GERARD CHOLLET CNRS - ENST France ALISP, Speaker Verification, Interactive Voice Servers" RENATO DE MORI Universite d' Avignon, France "Statistical Methods for Automatic Speech Recognition" M. GABRIELLA DI BENEDETTO Universita' degli Studi di Roma "La Sapienza", Rome, Italy ``Acoustic Analysis and Perception of Classes of Sounds (vowels and consonants)" BJORN GRANSTROM Royal Institute of Technology (KTH) Sweden "Multi-modal Speech Synthesis with Application" JEAN P. HATON Universite Henri-Poincare, CRIN-INRIA, France "Neural Networks for Automatic Speech Recognition" HYNEK HERMANSKY Oregon Graduate Institute, USA "Goals and Techniques of Speech Analysis" JOHN OHALA University of California at Berkeley (CA) USA "Articulatory Constraints on Distinctive Features" JEAN SYLVAIN LIENARD LIMSI-CNRS, France "Speech Perception, Voice Perception" "Beyond Pattern Recognition" PROCEEDINGS The proceedings will be published in the form of a book containing tutorial chapters written by the lecturers and possibly shorter papers from other participants. One free copy of the book will be distributed to each participant. LANGUAGE The official language of the school will be English. POSTER SUBMISSION There will be a poster session for contributed presentations from participants. Proposals consisting of a one page abstract for review by the organizers should be submitted with applications. DURATION Participants are expected to arrive in time for the evening meal on Sunday 4th October and depart on Tuesday 15th October. Sessions will take place from Monday 5th-Wednesday 14th. COST The cost per participant of 1.500 $ dollars covers accommodation (in twin rooms), meals for the duration of the course, and one day of excursion. -- A supplement of 40 dollars per night should be paid for single room. Payment details will be notified with acceptance of applications. GRANTS -- A few ESCA grants are available for participants (which cover tuition and, maybe, part of the lodging). See http://ophale.icp.inpg.fr/esca/grants.html for further information. Individual applications for grants should be sent to Wolfgang Hess by e-mail: wgh at sunwgh.ikp.uni-bonn.de ELIGIBILITY The school is open to all suitably qualified scientists from around the world. APPLICATION PROCEDURE: Important Date: Application deadline: May 15 1998 Notification of acceptance: May 30 1998 Registration fee payment deadline: July 10 1998 People with few years of experience in the field should include a recommendation letter of their supervisor or group leader Places are limited to a maximum of 60 participants in addition to the lecturers. These will be allocated on a first come, first served basis. ************************************************************************** APPLICATION FORM Title:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Family Name:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Other Names:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Name to appear on badge:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Mailing Address (include institution or company name if appropriate): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Phone:^^^^^^^^^^^^^^^^^^^^^^Fax:^^^^^^^^^^^^^^^^^^^ E-mail:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Date of Arrival : Date of Departure: Will you be applying for a ESCA grant ? yes/no* *(please delete the alternatives which do not apply) Will you be applying for a scholarship ? yes/no* *(please delete the alternatives which do not apply) *(please include in your application a justification for scholarship request) ***************************************************************** Please send the application form together the recommendation letter by electronic mail to: iiass at tin.it, subject: summer school; or by fax: +39 89 761 189 (att.ne Prof. M. Marinaro) or by ordinary mail to the address below: IIASS Via Pellegrino 19, I84019 Vietri sul Mare (Sa) Italy For further information please contact: Anna Esposito International Institute for advanced Scientific Studies (IIASS) Via Pellegrino, 19, 84019 Vietri sul Mare (SA) Italy Fax: + 39 89 761189 e-mail: annesp at vaxsa.csied.unisa.it ================== RFC 822 Headers ================== From iiass at tin.it Wed Feb 18 09:56:12 1998 From: iiass at tin.it (IIASS) Date: Wed, 18 Feb 1998 15:56:12 +0100 Subject: call Message-ID: <34EAF68C.2DF0@tin.it> From lek at cict.fr Thu Feb 19 10:02:23 1998 From: lek at cict.fr (Sovan LEK) Date: Thu, 19 Feb 1998 16:02:23 +0100 Subject: Neural Networks Workshop Message-ID: <1.5.4.32.19980219150223.00aec2b4@mail.cict.fr> INTERNATIONAL WORKSHOP ON APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS TO ECOLOGICAL MODELLING (2nd circular) 14-17 December 1998, Toulouse (FRANCE) Local Organizing Committee: Dr. Sovan Lek, CESAC, UMR 5576 du CNRS, UPS, B?t IVR3, 118 route de Narbonne, F-31062 Toulouse cedex 4, France Phone: 33-5 61 55 86 87 Fax: 33-5 61 55 60 96 E-mail: lek at cict.fr Dr. Jean-Fran?ois Gu?gan, ORSTOM, D?partement Biologie, Ecologie & Evolution, Laboratoire d'Hydrobiologie marine et Continentale, Universit? de Montpellier II (USTL), C.C. 093, place E. Bataillon, 34095 Montpellier cedex 05, France. Phone: 33 4 67 14 37 51 Fax : 33 4 67 14 46 46 E-mail : guegan at crit.univ-montp2.fr BACKGROUND You are cordially invited to attend the first "International Workshop on the Application of Artificial Neural Networks to Ecological Modelling" to be held at the Centre d'Ecologie des Syst?mes Aquatiques Continentaux in Toulouse (France). Toulouse is France's fourth largest city (650,350 people with suburbs), and is the European Space capital. It is situated on the Garonne river in very lush surroundings. The Toulouse of today is a lively university town (with more than 100,000 students) and has a rich medieval history. OBJECTIVES: Predictive modelling is a major concern in theoretical ecology, evolution and environmental sciences. Relationships between variables in natural systems are frequently non-linear, and thus conventional modelling tools could appear to be inappropriate to capture the complexity of such systems. This International Workshop will bring together theoretical and applied biological research, practitioners, and developers, as well as domain scientists from multiple ecological disciplines, for the presentation and exchange of current research and on concepts, tools and techniques for scientific and non linear statistical application in ecology, evolution and environmental sciences. The objectives are: ? To promote collaboration among scientists of different interested countries and research fields encouraging both teaching and research collaboration. ? To consider recent advances in Artificial Neural Networks to modelling data (identification, control, prediction, classification problems,...). INVITED SPEAKERS: Dr. S.E. Jorgensen (DK): Ecological Modelling: State of the Art. Pr. R. Tomassone (Fr): Dynamic systems and experimental planning: from data to modelling Dr. P. Bourret (Fr): Non -supervised classification: from observations to assumption. Dr. A. Teriokhin (Russia): On Neural Networks capable to realize evolutionarily optimal animal strategies of growth and reproduction in a seasonal environment. Pr. P. Auger (Fr): Non-linear Modelling in Ecology: from Individuals to Populations. Dr. F. Recknagel (Australia): Elucidation and Prediction of Aquatic Ecosystems by Artificial Neural Networks THEMES (you need to report your choice in the reply form, section Publication, which sub-theme?): o Pattern Recognition o Pattern Classification o Clustering and Classification o Diagnosis and Monitoring o Prediction and Control o Signal Processing o Temporal and Spatial Sequences PUBLICATION Final Instructions for Submission of Abstracts: o Abstract deadline: Abstracts must be submitted in English style, and received by the organisers before 1 April 1998. All abstracts will be refereed before final acceptance. o Please give complete name of your institution, followed by town and country. o The text of your abstract must be informative and contain: 1) a statement of the study's specific aims; 2) a statement of the method used; 3) a summary of results obtained; 4) a statement of conclusion. Avoid non-informative sentences. o Format: Abstracts must not exceed one page (format A4) and be sent directly by electronic mail to Drs. Lek or Gu?gan. If your abstract is too long it will be shortened by the organisers. The publication of the oral contributions is being considered. Please indicate if you are interested in submitting your paper for consideration in a special volume. Original papers will be published on merit in a special volume of the Springer Verlag Environmental Science Series. Other papers will form a special issue of Ecological Modelling. Both Editing Houses have been contacted and have accepted to co-edit these two special volumes. All contributions will be reviewed by at least two referees before acceptance for publication. SUBMISSION GUIDELINES OF PAPER(S) All contributions must be submitted by September 30th of 1998 to the Organizing Committee. Research papers should be up to 8,000 words long. All papers for publication should be sent by electronic mail (Ms-Word) or by post (4 hard-copies are needed) to Dr. Sovan Lek. All papers will be acknowledged of receipt. A notification of acceptance, modification or refusal will be sent by November 15th of 1998 to delegates having submitted a contribution with details given on which publication (hard volume of Springer Verlag or special issue of Ecological Modelling) the paper will be proposed. GENERAL INFORMATION: Languages: French and English will be the two official languages during the Conference, but abstracts, posters, and published papers will be exclusively written in English style. Venue: The Conference venue will be the Conference Centre of Toulouse University. This venue is ideal for a medium conference (about 150 people), with excellent, modern facilities which will allow for productive exchanges of ideas. Dates: Monday 14 December 1998 to Thursday 17 December 1998. Travel: Destination is Toulouse. Delegates must make their own travel arrangements to at least this destination. From dsilver at mgmt.dal.ca Fri Feb 20 18:17:40 1998 From: dsilver at mgmt.dal.ca (Daniel L. Silver) Date: Fri, 20 Feb 1998 23:17:40 +0000 Subject: Tech. Report - Task Rehearsal Method of Sequential Learning Message-ID: <199802210318.XAA24285@Snoopy.UCIS.Dal.Ca> Dear colleagues, the following TR is now available: "The Task Rehearsal Method of Sequential Learning" Department of Computer Science Univeristy of Western Ontario Technical Report # 517 Daniel L. Silver and Robert E. Mercer Abstract An hypothesis of functional transfer of task knowledge is presented that requires the development of a measure of task relatedness and a method of sequential learning. The "task rehearsal method" (TRM) is introduced to address the issues of sequential learning, namely retention and transfer of knowledge. TRM is a knowledge based inductive learning system that uses functional domain knowledge as a source of inductive bias. The representations of successfully learned tasks are stored within domain knowledge. "Virtual examples" generated by domain knowledge are rehearsed in parallel with the each new task using either the standard multiple task learning (MTL) or the $\eta$MTL neural network methods. The results of experiments conducted on a synthetic domain of seven tasks demonstrate the method's ability to retain and transfer task knowledge. TRM is shown to be effective in developing hypothesis for tasks that suffer from impoverished training sets. Difficulties encountered during sequential learning over the diverse domain reinforce the need for a more robust measure of task relatedness. ---------------------------------------------------------------------- Comments are welcome! Download sites: http://www.csd.uwo.ca/~dsilver/trmpaper.ps or http://www.csd.uwo.ca/~dsilver/trmpaper.ps.Z ////////////////////////////////////////////////////////////////////// Daniel L. Silver CogNova Technologies Phone: (902) 582-7558 1226 J.Jordan Road Fax: (902) 582-3140 Canning,Nova Scotia Dal.U: (902) 494-1813 Canada B0P 1H0 Email: dsilver at mgmt.dal.ca Homepage: http://www.meadoworks.ns.ca/cognova /////////////////////////////////////////////////////////////// From marwan at ee.usyd.edu.au Mon Feb 23 04:28:33 1998 From: marwan at ee.usyd.edu.au (Marwan Jabri) Date: Mon, 23 Feb 1998 20:28:33 +1100 (EST) Subject: Post-doctoral fellowship Message-ID: Post-Doctoral Fellow Department of Electrical Engineering The University of Sydney Applications are invited for Post-doctoral fellow position funded by an Australian Research Council project grant. The three-year project aims at investigating computational models of the superior colliculus, the implementation of the models in microelectronics and their integration in sensorimotor control systems. The fellow will join a group several academics and doctoral students working on biological models for sensorimotor control. The research is a collaboration between M. Jabri (Elec. Eng., Sydney University) S. Carlile (Physiology, Sydney University) and T. Sejnowski (Salk Institute). The fellow will be based in Sydney, but will be expected to travel and spend several weeks every year at the Salk Institute. Applicants would have completed (or about to complete) their PhD in electrical, computer or related engineering or science discipline and have demonstrated research capacity in the area of neuromorphic engineering, computational neurobiology or microelectronics. Appointment will be made initially for a period of one year, and renewable for another two years subject to progress. Expected starting date in May, 1998. Closing date: March 20, 1998 Salary range: A$34k-46k To apply, send letter of application, CV and names, fax and email of three referees to M. Jabri Tel (+61-2) 9351 2240, Fax (+61-2) 9351 7209, Email: marwan at sedal.su.oz.au From Nicolino.Pizzi at nrc.ca Mon Feb 23 10:12:54 1998 From: Nicolino.Pizzi at nrc.ca (Pizzi, Nicolino) Date: Mon, 23 Feb 1998 10:12:54 -0500 Subject: Postdoctoral Research Opportunity - University of Manitoba Message-ID: POSTDOCTORAL RESEARCH OPPORTUNITY - COMPUTER ENGINEERING HYBRID KNOWLEDGE-BASED CLASSIFICATION OF VOLUMETRIC PATTERNS Pending final approval, a postdoctoral position is available within the Electrical and Computer Engineering Department to participate in an NSERC-funded strategic research project investigating hybrid knowledge-based classification of volumetric patterns. The position is for a one-year term with a possible one year renewal. The research project will be conducted in close collaboration with Prof. W. Pedrycz and Dr. N. Pizzi. Volumetric (three-dimensional) data are found in many application areas such as radar scans of meteorological formations. These data normally contain a number of three-dimensional regions of interest (ROI's) that belong to several classes. The classification of an ROI is determined by some well-established reference test. In the case of meteorological radar scans, the ROI's may be cloud formations that cause severe weather, the classes may be hail, heavy rain, wind, or tornadic events, and the reference test might be eye-witness accounts of the storm events. The intent of this project is to develop a comprehensive pattern recognition methodology aimed at such data and propose a suite of classification algorithms that can take a ROI and produce a classification outcome that matches the class to which it was assigned by the corresponding reference test. A number of factors can confound the classification process. It may become difficult to glean any discriminating features from volumetric data if it contains noise due to limitations of sensors, instrumentation, or the data acquisition process. Moreover, the ROI's may be extremely complex in nature. Several preprocessing methods are proposed in order to transform the original ROI in order to eliminate or diminish the effects of noise and/or reduce the dimensionality of the input space as well as focus the classification effort on the most significant features. The problem of identifying discriminating features is further aggravated by the fact that the accepted reference test itself may be imprecise or even unreliable. Finally, the volumetric data may be incomplete and sophisticated interpolation methods will be required to deal with missing values. Required background: - Recent Ph.D. graduate - Experience in C++ programming on UNIX systems - Knowledge of pattern recognition techniques Desired background: - Working knowledge of fuzzy systems, artificial neural networks, and data mining Please send a curriculum vitae, expression of interest (including earliest start date), and the names and e-mail addresses (or telephone numbers) of two references to N. Pizzi at pizzi at ibd.nrc.ca. Your curriculum vitae should include a list of recent publications. Please outline your interest in this project, how it is related to work that you have done, and what special expertise you would bring to the project. Nicolino Pizzi, Ph.D. Associate Research Officer Institute for Biodiagnostics National Research Council 435 Ellice Avenue Winnipeg MB R3B 1Y6 CANADA From Shaogang.Gong at dcs.qmw.ac.uk Mon Feb 23 11:35:53 1998 From: Shaogang.Gong at dcs.qmw.ac.uk (Shaogang Gong) Date: Mon, 23 Feb 1998 16:35:53 +0000 (GMT) Subject: Post-Doc Research in Face and Gesture Recognition Message-ID: <199802231635.QAA01578@seans-pc.dcs.qmw.ac.uk> Post-doctoral Research in Visual Learning for Face Gesture Recognition and Intention Prediction for Visually Mediated Interaction Department of Computer Science Queen Mary and Westfield College, University of London, UK Applications are invited for a post-doctoral research assistant in the Dept of Computer Science at Queen Mary and Westfield College to work on a new EPSRC research project. The successful candidate will be undertaking novel research in statistical learning methods, real-time view-based face and gesture representation and recognition, data fusion for active camera control and intention prediction. Our lab is equipped with extensive real-time image capturing and tracking systems including Pentium and Pentium II real-time active camera systems, SGI O2 systems, Datacube MaxVideo 250 and MD1/2GX, AMT DAP 500 parallel processors, with numerous SPARC workstations. The candidate should have experience in computer vision and neural network research. In particular, any experience in view-based representation and statistical learning theories would be an advantage (more details can be found on the Web at http://www.dcs.qmw.ac.uk/research/vision/ ). You should also be competent in programming C under X and NT windows and using Unix systems. You will be expected to start as soon as possible on a 2 year contract. Salary in range of 17,293-22,237 pounds per annum inclusive, depending on age and experience. The project is to be closely collaborated with a concurrent project at Sussex COGS involving Prof Hilary Buxton and Dr Jonathan Howell. The project will also involve the BT and BBC R&Ds. The Department of Computer Science at QMW has extensive experience in object detection, tracking and recognition for dynamic scene understanding in image sequences. Recent and current funded projects relevant to this research include ESPRIT II VIEWS for visual interpretation and evaluation of wide area scenes, RACE II Mona Lisa for virtual studios, ESPRIT III FIVE working group for immersive virtual environment, EPSRC IMV Initiative on real-time detection, tracking and recognition of moving people, EC HCM Network PAMONOP on parallel modelling of neural operators for pattern recognition, a BT Short Term Research Fellowship Scheme on real-time view-based estimation of head pose, and the EPSRC/BBC CASE program for studies on the visual segmentation and tracking of moving actors in studio environment. For further details and an application form please phone +(44) (0)171-975-5171 (24 hour answer-phone) quoting Ref. number 97135 or send an email request to sgg at dcs.qmw.ac.uk. Completed applications and CV should be returned by 20/03/98 to: The Recruitment Coordinator, Personnel Office, Queen Mary and Westfield College, Mile End Road, London, E1 4NS. QMW: WORKING TOWARDS EQUAL OPPORTUNITIES From hollidie at pcmail.aston.ac.uk Mon Feb 23 15:59:33 1998 From: hollidie at pcmail.aston.ac.uk (Ian Holliday) Date: Mon, 23 Feb 1998 15:59:33 GMT+1 Subject: postdoc + PhD Studentship: neural nets and MEG Message-ID: Postdoctoral Research Fellowship and Graduate Studentship Neural Computing Research Group Aston University Birmingham B4 7ET, U.K. The Neural Computing Research Group at Aston is looking for a highly motivated individual for a 3 year postdoctoral research position in the area of `Signal and Pattern Processing of Magnetoencephalographic Data`. The project will study single and multichannel data obtained from an Aston magnetoencephalography (MEG) facility for signal enhancement and processing. The MEG research group is engaged in basic studies of normal and abnormal vision, epilepsy, and gamma- band activity; and in clinically related studies on the localisation of eloquent cortex in pre-surgical investigations. Advanced pattern processing techniques are needed, including artificial neural network methods for enhancement, clustering, visualisation, segmentation and classification. Potential candidates should have strong mathematical and computational skills and an interest in the application of these skills to basic and clinically related neurosciences research. Knowledge of linear and nonlinear signal processing or expertise in biosignal analysis would be useful. The successful candidate will also have an opportunity to contribute to experimental work in MEG. A supported studentship is also available in the same area. Further information on this and other positions can be obtained from http://www.ncrg.aston.ac.uk/. Salaries for the Fellowship will be at or above point 6 on the RA 1A scale, currently 16927 UK pounds. These salary scales are subject to annual increments. The studentship is supported at the standard UK rate for PhD students. If you wish to be considered for this position, please send a full CV and publications list, together with the names of 3 referees, to: Prof David Lowe or Dr. Ian Holliday Neural Computing Research Group Psychology Institute Aston University Birmingham B4 7ET, U.K. Tel: 0121 333 4631 tel: 0121 359 3611 ext 4930 Fax: 0121 333 4586 fax: 0121 359 3257 e-mail: d.lowe at aston.ac.uk email: hollidie at aston.ac.uk Email submission of postscript files is welcome. Closing date: 10 April 1998. From ericr at mech.gla.ac.uk Tue Feb 24 07:20:03 1998 From: ericr at mech.gla.ac.uk (Eric Ronco) Date: Tue, 24 Feb 1998 12:20:03 GMT Subject: Constructing a Controller network Message-ID: <199802241220.MAA05138@googie.mech.gla.ac.uk> Dear all, Just to let you know of the http availability of a new technical report entitled "Two Controller Networks Automatically Constructed Through System Linearisations and Learning" (it is a compressed file. Please, gunzip the file to view or print it). It is available (among others) at: http://www.mech.gla.ac.uk/~ericr/research.html or at http://www.mech.gla.ac.uk/~yunli/reports.htm This report has been written by Eric Ronco and Peter J. Gawthrop. Its title is Two Controller Networks Automatically Constructed Through System Linearisations and Learning. The keywords are: controller network, off-equilibrium linearisation, learning Abstract: This study aims at comparing two linear controller networks as well as two methods to automaticly construct their architecture. The general idea of a controller network is to use a number of linear local controllers valid for different operating regions of a non-linear system. The two controller networks studied here are the ""Clustered Controller Network'' (CCN) and the ""Model-Controller Network'' (MCN). They differ by the method used for the selection of the controllers at each instant. In the CCN, the controllers are selected according to a spatial clustering of the operating space whereas in the MCN the selection of the controllers depends of the performance of the model associated to each local controller. The two different methods to construct the architecture of these controller networks are the ""multiple off-equilibrium system linearisations'' and the ""learning control through incremental network construction''. It is shown that these network construction methods make the two controller networks general and systematic non-linear controller design approaches. However, the selection method applied by the MCN is preferable for control purposes since it is directly related to the controller capability unlike the method implemented by the CCN. In other hand, the flexibility of the controller selection applied by the MCN makes accurate local control learning difficult to achieve. A mixture of this two methods of controller selection should remove these problems. Regards, Eric Ronco ----------------------------------------------------------------------------- | Eric Ronco | | Dt of Mechanical Engineering E.mail : ericr at mech.gla.ac.uk | | James Watt Building WWW : http://www.mech.gla.ac.uk/~ericr | | Glasgow University Tel : (44) (0)141 330 4370 | | Glasgow G12 8QQ Fax : (44) (0)141 330 4343 | | Scotland, UK | ----------------------------------------------------------------------------- From thimm at idiap.ch Tue Feb 24 12:37:14 1998 From: thimm at idiap.ch (Georg Thimm) Date: Tue, 24 Feb 1998 18:37:14 +0100 Subject: Events on Neural Networks, Vision and Speech Message-ID: <199802241737.SAA13879@rotondo.idiap.ch> ----------------------------------------- WWW page for Announcements of Conferences, Workshops and Other Events on Neural Networks, Vision and Speech ----------------------------------------- This WWW page allows you to look up and enter announcements for conferences, workshops, and other events concerned with neural networks, vision, speech, and related fields. ------------------------------------------------------------------------- Search and lookup can be restricted to events with forthcoming deadlines! ------------------------------------------------------------------------- The event lists, which is updated almost daily, contains currently more than 200 forthcoming events, and can be accessed via the URL: http://www.idiap.ch/~thimm The entries are ordered chronologically and presented in a format for fast and easy lookup of: - the date and place of the event, - the title of the event, - a contact address (surface mail, email, ftp, and WWW address, as well as telephone or fax number), and - deadlines for submissions, registration, etc. - topics of the event Conference organizers are kindly asked to enter their conference into the database. The list is in parts published in the journal Neurocomputing by Elsevier Science B.V. Information on passed conferences are also available. Kind Regards, Georg Thimm P.S. Please distribute this announcement to related mailing lists. Comments and suggestions are welcome! From Friedrich.Leisch at ci.tuwien.ac.at Wed Feb 25 10:00:42 1998 From: Friedrich.Leisch at ci.tuwien.ac.at (Friedrich Leisch) Date: Wed, 25 Feb 1998 16:00:42 +0100 Subject: CI BibTeX Collection -- Update Message-ID: <199802251500.QAA04534@galadriel.ci.tuwien.ac.at> The following volumes have been added to the collection of BibTeX files maintained by the Vienna Center for Computational Intelligence: Machine Learning 28-30 Neural Networks 10/4-9, Neural Computation 9/6-10/2, Neural Processing Letters 5/3-7/2 Most files have been converted automatically from various source formats, please report any bugs you find. The complete collection can be downloaded from http://www.ci.tuwien.ac.at/docs/ci/bibtex_collection.html ftp://ftp.ci.tuwien.ac.at/pub/texmf/bibtex/ Best, Fritz Leisch ------------------------------------------------------------------ Friedrich Leisch Institut f?r Statistik Tel: (+43 1) 58801 4541 Technische Universit?t Wien Fax: (+43 1) 504 14 98 Wiedner Hauptstra?e 8-10/1071 Friedrich.Leisch at ci.tuwien.ac.at A-1040 Wien, Austria http://www.ci.tuwien.ac.at/~leisch PGP public key http://www.ci.tuwien.ac.at/~leisch/pgp.key ------------------------------------------------------------------ From kia at particle.kth.se Fri Feb 27 10:22:03 1998 From: kia at particle.kth.se (Karina Waldemark) Date: Fri, 27 Feb 1998 16:22:03 +0100 Subject: Neural Network Workshop June-98 Message-ID: <34F6DA1B.D4C49ADB@particle.kth.se> ------------------------------------------------------------------------ VI-DYNN'98 Workshop on Virtual Intelligence - Dynamic Neural Networks Stockholm June 22-26, 1998 Royal Institute of Technology, KTH, Stockholm, Sweden ------------------------------------------------------------------------ VI-DYNN'98 Web: http://www.particle.kth.se/vi-dynn Abstracts due to: March 20, 1998 ****** papers up to 20 pages can be accepted ******* Deliver camera-ready manuscripts at registration Papers will be published by SPIE Papers will be considered for further publication in IEEE Transactions on Industrial Applications Contact: Thomas Lindblad (KTH) - Conf. Chairman email: lindblad at particle.kth.se Phone: [+46] - (0)8 - 16 11 09 ClarkS. Lindsey (KTH) - Conf. Secretary email: lindsey at particle.kth.se Phone: [+46] - (0)8 - 16 10 74 Switchboard: [+46] - (0)8 - 16 10 00 Fax: [+46] - (0)8 - 15 86 74 -------------------------------------------------------------------- Tentative Programme for VI-DYNN'98 Workshop -------------------------------------------------------------------- Monday PCNN tutorial Morning Session chair: Thomas Lindblad 1. Introduction 2. PCNN Theory 3. PCNN Image Processing 4. The PCNN Kernel 5. Target Recognition 6. Dealing with Noise Afternoon Session chair: Jason Kinser 7. Feedback 8. Object Isolation 9. Foveation 10. Image Fusion 11. Hardware Realization 12. Miscellaneous Applications and Summary Tuesday Session: Neurodynamics Session chair: Hans Liljenstrom Keynote Talk: Hans Liljenstrom, Control and amplification of cortical neurodynamics I. Opher (Tel Aviv), Data Clustering via Temporal Segmentation of Spiking Neurons Session: Electronic Nose Session chair: Hans Liljenstrom J. Waldemark (KTH) Neural Networks and PCA for determing ROI in sensory data preprocessing M. L. Padgett (Auburn U.) PCNN factoring and automated outlier detection T. A. Roppel (Auburn U.) Sensory plane analog/VLSI for interfacting sensor arrays to neural networks Session: Models of neural systems Session chair: Hans Liljenstrom Session: PCNN Applications Session chair: J. Kinser Keynote Talk: J. Kinser, Kurt Moore (Los Alamos) , 1-D Peak Fitting using PCNN J. Karvonen (Finnish Inst. Of Marine Research), PCNN for sea-ice classification from RADARSAT SAR-images V.Becanovic (KTH), PCNN for License Plate Identification O.J.Goeboden (Ostfold ), Using PCNN for SONAR Images Panel Discussion: Wednesday Session: Signals from the Brain Session chair: John Taylor Keynote Talk: JG Taylor (Kings College), Analysing Non-invasive Brain Images E. Oja, ICA Analysis of MEG and EEG Signals A. Villa, Single Cell Measurements from Behaving Animals B. Krause (Juelich), PET and Structural Brain Modelling B. Gulyas (Karolinska Inst.), B. Horwitz (NIH), Structural Modelling of PET Data A. Ioannides (Julich), MEG & the Brain Panel Discussion: Session: Defense Applications Session chair: K. Waldemark Keynote Talk: Natalie Clark, Micro-Optical Silicon Eye Authors: Natalie Clark, John Comtois, Adrian Micalicek, and Paul Furth Air Force Research Laboratory, Kirtland AFB NM 87117 I. Renhorn, (Defence Research Establishment), General Specifications for ATR J.L. Johnson J. Kinser, Pulse Couple Spiral Image Fusion Th. Lindblad, Smart sensors inspired by processes in the primate visual cortex Panel Discussion: Thursday Session: Hardware Session chair: Natalie Clark Keynote Talk: J. L. Johnson, Test Results for a 32x32 PCNN Array, J. L. Johnson, R. F Sims, and T. Branch. J. Johnson (MICOM), PCNN Chip Development J. Waldemark (KTH), PCNN in FPGA unknown (John Hopkins), PCNN Hardware IBM ZISC, Zero instruction set computer, Application for noise reduction Trento TOTEM, The Reactive Tabu Search Session: PCNN & other Algorithms Session chair: J. Waldemark G. Szekely, Adaptive PCNN J. Kinser M.Kaipainen, Sea Ice Classification using PCNN J. Johnson, PCNN Theory: State of the art Panel Discussion: Friday Tutorial Session: Virtual Intelligence Session chair: Mary Lou Padgett Theme: Virtual Intelligence Track AM Opening Remarks Keynote Talk: M. L. Padgett, Overview of Virtual Intelligence Motivational material, update on funding, hot topics, why important, how interacts with PCNN, etc. Tutorial: Overview of Neural Networks Fuzzy Systems Evolutionary Computation Rough Sets Virtual Reality Electronic Nose Description of topics, and pointers to websites and printed material for more detailed info e.g. Handbook on Applications of Computational Intelligence Eds. Padgett, Karayiannis, Zadeh CRC Press 1999 and Handbook on NeuroControl Eds. Jorgensen, Werbos and Padgett CRC Press 1999 Session: NNW Applications Session chair: Mary Lou Padgett K. Waldemark (KTH), Sleep Apnea R. Curbelo (Univ. of Uraguay), Fingerprint Identification using Neural Networks D. A. Salo (Ostfold), Neural Networks for Fingerprint identification T. Sanne (Ostfold), Neural Network for Identification Based on the Iris J. Hansen (Ostfold), Facial Recognition using Neural Networks A. Sokolov (Protvino), Hadron Energy Reconstruction by Combined Calorimeter using Neural Network L. Hildingsson,(SKI) Fuel Assembly Assessment from Digital Image Analysis Lunch and Virtual Intelligence Standards Working Group Meeting From weaveraj at helios.aston.ac.uk Mon Feb 9 05:25:05 1998 From: weaveraj at helios.aston.ac.uk (Andrew Weaver) Date: Mon, 09 Feb 1998 10:25:05 +0000 Subject: Studentship Available, Aston University, UK Message-ID: <29800.199802091025@sun.aston.ac.uk> Neural Computing Research Group, Aston University, Birmingham, UK We invite applications for EPSRC and Divisional PhD studentships in the following areas: * Neural Nets for Control: Advancing the Theory * Neural Networks for Affinity Ligand Synthesis * Statistical mechanics of support vector machines * Bayesian approaches to online learning * Advanced mean field methods for Bayesian learning * Analysing Brain-derived Magnetic Fields using Neural Networks * Non-linear Time Series Analysis: Characterisation by Feature Processing * Neural Network Analysis of Wake EEG * Image Understanding with Probabilistic Models Studentships are available to people of all nationalities, although the EPSRC studentships will only pay tuition fees and living expenses to UK citizens, and tuition fees only to (non-UK) EU citizens. Applicants should have, or expect to gain, a First Class or Upper Second Class Degree (or overseas equivalent) in a numerate discipline. The Research Group also has 5 EPSRC Advanced Course studentships for the MSc in Pattern Analysis and Neural Networks, further details of which are also available at the web pages below. In order to apply for these studentships you will need to complete an official Aston University application form, and should therefore send your name and address to ncrg at aston.ac.uk (subject line NCRG2 - IF YOU DO NOT USE THIS SUBJECT LINE YOU WILL NOT BE SENT THE CORRECT INFORMATION) by 9.00am on Friday 20th February 1998. Written applications should be received by Friday 27th March 1998. Details of the information required will be found in the covering letter sent with the application form. Further details of the Research Group and the topics can be found at http://www.ncrg.aston.ac.uk/ From Simon.N.CUMMING at British-Airways.com Mon Feb 9 13:08:04 1998 From: Simon.N.CUMMING at British-Airways.com (Simon.N.CUMMING@British-Airways.com) Date: 09 Feb 1998 18:08:04 Z Subject: ANNOUNCEMENT: NCAF Conference, SUNDERLAND 22-23April1998 Message-ID: <"BSC400A1 980209180759206661*/c=GB/admd=ATTMAIL/prmd=BA/o=British Airways PLC/s=CUMMING/g=SIMON/i=N/"@MHS> The purpose of the Neural Computing Applications Forum (NCAF) is to promote widespread exploitation of neural computing technology by: - providing a focus for neural network practitioners. - disseminating information on all aspects of neural computing. - encouraging close co-operation between industrialists and academics. NCAF holds four, two-day conferences per year, in the UK, with speakers from commercial and industrial organisations and universities. The focus of the talks is on practical issues in the application of neural network technology and related methods to solving real-world problems. ____________________________________________________________________ The April meeting will be hosted by The School of Computing and Information Systems on the St Peter's Campus of The University of Sunderland on Wednesday 22nd and Thursday 23rd April 1998. -------------------------------------------- the theme will be: DTI Neural Computing Guidelines. The 2 days will be packed with applications oriented papers as usual. There will also be adequate time for networking with other practitioners, during coffee, lunch and the Wednesday evening event. NCAF Conference at SUNDERLAND, UK. 22 - 23 April 1998 ====================================================== DTI Neural Computing Applications Guidelines Wednesday 22nd April 1998 ------------------------- Introduction and Welcome John MacIntyre, University of Sunderland 1hr overview: By a guest speaker to be announced Practical Assessment of Neural Network Applications Ian Nabney, Aston University Neural Networks and Error Bars David Lowe, Aston University Cracking the Code: a fully interactive workshop putting the Guidelines into practice Graham Hesketh, Rolls-Royce and Iain Strachan, AEA Technology From Project to Product, a Neural Based Cardiac Monitor Tom Harris, Brunel University Thursday 23rd April 1998 ------------------------ Robust Neural Networks with Confidence Bounds Julian Morris and Elaine Martin, University of Newcastle Neural Network Techniques for on-line Monitoring of Vigilance Mihaela Duta, Oxford University Applications of Normalised RBF nets to Robot Trajectories Learning Guido Bugmann, University of Plymouth Data Fusion in Complex Machine Monitoring Odin Taylor, University of Sunderland Neural Networks for Steam Leak Location Peter Mattison, University of Sunderland ____________________________________________________________________ Social Programme: The most widely acclaimed social event ever organised by NCAF was a visit to the Beamish Open Air Museum, so by popular demand we are visiting there again. plus Puzzle Corner: To Irradiate or Not To Irradiate - that is the question Graham 'Rottweiler' Hesketh (Rolls-Royce) ___________________________________________________________________ Attendance at the conference costs 100 pounds for non-members or 20 pounds for NCAF members. [Food, social event and accommodation not included]. NCAF MEMBERSHIP DETAILS: ------------------------ All amounts are in pounds Sterling, per annum. All members receive a quarterly newsletter and are eligible to vote at the AGM (but see note on corporate membership). Currently, membership includes a free copy of the book "A Guide to Neural Computing Applications" by Prof Lionel Tarassenko of Oxford University. (This book is on sale in bookshops for 29.99 pounds). Full (Corporate) Membership : 300 pounds (allows any number of people in the member organisation to attend meetings at member rates; voting rights are restricted to one, named, individual. Includes automatic subscription to the journal Neural Computing and Applications.) Individual Membership : 170 pounds (allows one, named, individual to attend meetings at member rates; includes journal) Associate Membership: 110 pounds: includes subscription to the journal and newsletter but does not cover admission to the meetings. Reduced (Student) Membership : 65 pounds including Journal; 30 pounds without journal. Applications for student membership should be accompanied by a copy of a current full-time student ID card, UB40, etc. ___________________________________________________________________ For registration, membership enquiries or further information please e-mail ncafsec at brunel.ac.uk or Phone Sally Francis (+44)(0)1784 477271 ___________________________________________________________________ From polzer at uran.informatik.uni-bonn.de Mon Feb 9 11:08:59 1998 From: polzer at uran.informatik.uni-bonn.de (Andreas Polzer) Date: Mon, 9 Feb 1998 17:08:59 +0100 (MET) Subject: CFP: ECCV Workshop on Learning in Computer Vision Message-ID: <199802091609.QAA08896@cornea.informatik.uni-bonn.de> We apologize if you receive multiple copies of this message. ------------------------------------------------------------ WORKSHOP ON LEARNING IN COMPUTER VISION in conjunction with ECCV '98 June 6, 1998 Freiburg, Germany Description ----------- In recent years rising computer performance has made it possible to exploit complex statistical models and to learn and estimate their parameters from an increasing amount of data. Therefore the issues of computational and statistical learning theory and Bayesian inference become more and more relevant for computer vision applications. Especially the related topics of generalization and choice of model complexity are of central importance in computer vision. Furthermore, the question of needed accuracy for optimization and parameter estimation turns out to be a closely related topic. The application of methods from statistical learning theory and neurally inspired approaches in computer vision are rather diverse and learning in computer vision is by no means a homogeneous field. But the necessity becomes more and more evident to take a more fundamental point of view and to clarify the multiple implications that the recent achievements of statistical learning theory have on computer vision problems. Statistical learning theory might have significant influence on many applications ranging from classification and statistical object recognition, grouping and segmentation to statistical field models and optimization. We are convinced that focussing on these joint aspects may yield a major contribution to the understanding and improvement of the diverse range of learning applications in computer vision. A workshop on learning in computer vision may greatly contribute to these goals. Workshop Issues --------------- The workshop will focus on the latest developments of learning in computer vision and will try to clarify to what extent statistical learning theory and Bayesian inference support computer vision applications. The workshop will present high quality oral contributions on any aspects of learning in computer vision, including but not restricted to the following topics: * Supervised Learning and its application to classification, support vector networks and model learning * Unsupervised Learning for structure detection in images * Robustness of Computer Vision algorithms and generalization * Probabilistic model estimation and selection, e.g. Bayesian inference for vision Attendance and Workshop Format ------------------------------ The workshop will consist of invited keynote talks and regular talks in one track. For submissions please send an extended abstract of 1-2 pages by March 31, 1998 to Workshop Learning in Computer Vision c/o Prof. Joachim Buhmann Institut fuer Informatik Roemerstrasse 164 D-53117 Bonn Germany In case of more submissions than available time slots a selection will be made based on a peer review of the submissions by the program committee. Venue ----- The workshop will be held in Freiburg, Germany on June 6, 1998 in conjunction with the European Conference on Computer Vision (ECCV '98). Program Committee ----------------- * Joachim M. Buhmann, Chair (University of Bonn, Germany) * Andrew Blake (University of Oxford, UK) * Jitendra Malik (UC Berkeley, USA) * Tomaso Poggio (MIT, USA) * Daphna Weinshall (Hebrew University, Israel) Local Organization: Andreas Polzer, Jan Puzicha (University of Bonn) To obtain further information please contact: WWW: http://www-dbv.cs.uni-bonn.de/learning.html e-mail: jan at cs.uni-bonn.de From elmar.steurer at dbag.ulm.DaimlerBenz.COM Wed Feb 11 10:25:02 1998 From: elmar.steurer at dbag.ulm.DaimlerBenz.COM (Elmar Steurer) Date: Wed, 11 Feb 1998 16:25:02 +0100 Subject: please include this CFP to your mailing list Message-ID: <34E1C2CE.51F6@dbag.ulm.DaimlerBenz.com> Call for Papers Workshop: Application of Machine Learning and Data Mining in Finance 10th European Conference on Machine Learning (ECML-98) Chemnitz, Germany, April 24 1998 General Information In conjunction with the 10th European Conference on Machine Learning (ECML-98) the workshop "Application of Machine Learning and Data Mining in Finance" will be held in Chemnitz, Germany, on April, 24th 1998. The main conference takes place from April, 21st to 23rd 1998. Motivation Advanced data analysis and forecasting technologies such as neural networks, symbolic machine learning and genetic algorithms are being increasingly applied to support financial asset management and credit risk management. These methods are considered by many financial management institutions as innovative technologies to support conventional quantitative techniques. Their use in computational finance will have a major impact in the modelling of the currency markets, in tactical asset allocation, bond and stock valuation and portfolio optimisation. In addition the application of these tools for scoring tasks delivers valuable support for the management of client credit risk. Targets This workshop is designed to bring together researchers in the field of Machine Learning with those practicing financial consulting. The purpose is twofold: - Practitioners should become familiar with the state of the art in machine learning research for predictive modelling and scoring systems. - The research community should receive ideas and requirements from participants from the financial world with the aim to improve the acceptance of Machine Learning applications and to identify future areas of research. Research papers representing new and significant developments in methodology as well as applications of practical use will be presented. Topics include: Application aspects: - Scoring systems: Application and Behavioural Scoring - Trading- and forecasting models - Volatility models - Value at Risk - Financially motivated objective functions Methodological aspects: - Symbolic Learning in financial engineering - Neural Networks for financial applications - Aspects and dependencies of data transformation and model selection - Backtest procedures: Advantages and bottlenecks - Pre-testing as an alternative to backtest - Data Mining process model for financial applications Submission of papers Authors wishing to present a paper should send an electronic version (uuencoded compressed PostScript) not later than 28 February 98 to: Dr. Elmar Steurer DAIMLER-BENZ AG - Research and Technology Postfach 2360 89013 Ulm Tel.: 0049 - 731 / 505 -2868 Fax: 0049 - 731 / 505 4210 Email: elmar.steurer at dbag.ulm.DaimlerBenz.COM Accepted papers will be published in the workshop notes. Selected papers will be issued in a proceedings. Contributors will be allocated 20 minutes for an oral presentation during the workshop. Further invited talks and a panel discussion are planned. Program committee: Ulrich Anders University of Otago, Dunedin, New Zealand Jeremy H. Armitage State Street Bank and Trust Company, London, UK Dirk Baestens Generale Bank, Brussels, Belgium Georg Bol University of Karlsruhe, Germany Guenter Grimm allfonds, Munich, Germany Tae H. Hann University of Karlsruhe, Germany Ashar Mahboob Fuji Capital Markets Corporation, New York, USA Andreas Weigend STERN Business School, New York University, USA Apostolos N. Refenes London Business School, UK Andrea Sczesny ZEW Mannheim, Germany Charles Taylor University of Leeds, UK Diethelm Wuertz ETH, Zurich, Switzerland Hans-Georg Zimmermann Siemens AG, Munich, Germany Important Dates: Submission deadline: 28 February 1998 Notification of acceptance: 15 March 1998 Camera ready copy: 28 March 1998 Workshop: 24 April 1998 Organization: Gholamreza Nakhaeizadeh and Elmar Steurer DAIMLER-BENZ AG - Research and Technology e-mail: nakhaeizadeh at dbag.ulm.DaimlerBenz.COM elmar.steurer at dbag.ulm.DaimlerBenz.COM Registration and further information: For further information about the main conference and registration please contact: ecml98 at lri.fr ecml98 at informatik.tu-chemnitz.de or visit the web site: http://www.tu-chemnitz.de/informatik/ecml98 From nnesmed at DI.Unipi.IT Wed Feb 11 11:35:33 1998 From: nnesmed at DI.Unipi.IT (Tonina Starita) Date: Wed, 11 Feb 1998 17:35:33 +0100 (MET) Subject: Final Call NNESMED`98 (Extended Deadline) Message-ID: <199802111635.RAA00554@neuron.di.unipi.it> * * * E X T E N D E D D E A D L I N E: February 27 * * * FINAL CALL FOR PAPERS 3rd International Conference on Neural Networks and Expert Systems in Medicine and Healthcare NNESMED '98 Pisa, Italy,2-4 September 1998 http://www.di.unipi.it/~nnesmed/home.htm NNESMED '98 is organised by the Computer Science Department of the University of Pisa Conference Chair: Professor Starita, University of Pisa Conference Co-Chairs: Professor Ifeachor, University of Plymouth Professor Simi University of Pisa Keynote Speakers Dr Lee Giles (USA) University of Princeton Professor Mario Stefanelli (Italy) University of Pavia Professor Paulo Lisboa (UK) Liverpool John Moores University Programme/Advisory Committee Dr Lee Giles (USA) Professor Marco Gori (Italy) Professor Emmanuel Ifeachor (UK) Dr Barrie Jervis (UK) Professor Marzuki Khalid (Malaysia) Professor Priklis Ktonas (USA) Professor Paulo Lisboa (UK) Professor George Papadurakis (Greece) Professor Karl Rosen (Sweden) Professor Maria Simi (Italy) Dr Alessandro Sperduti (Italy) Professor Mario Stefanelli (Italy) Professor Hiroshi Tanaka (Japan) Professor John Taylor (UK) Topics Neural Networks Expert Systems Soft Computing Hybrid Systems Signal Processing Fuzzy Logic Knowledge Bases DataMining Deductive Reasoning Telemedicine Tools and Applications Scope NNESMED '98 is organised by the Computer Science Department of the University of Pisa and it will be held in Pisa, on September 2-4 1998. It will provide a forum for the presentation of the results of ongoing works and research in the field of the Neural Networks and Expert Systems in Medicine and Healthcare. NNESMED '98 will be the third edition of this series and it will promote the exchange of ideas and experiences among researchers from the AI communities in medical field. Pisa is well connected to the rest of Europe by its international airport and good road and rail links. Paper submission The submission deadline is ** EXTENDED **: February 27, 1998. Papers must not exceed 4 pages, they must be written in English, with a cover page containing: * a 200-word abstract * keywords * postal and electronic mailing address * phone and fax number of the first author Submission will be electronic and available via the conference web site. Authors will be notified of the acceptance (oral and/or poster session) or rejection of their papers by May 1, 1998. Additional Information http://www.di.unipi.it/~nnesmed/home.htm e_mail: nnesmed at di.unipi.it Tel: +39-50-887215/ +39-50-887249 Fax: +39-50-887226 From priel at mail.biu.ac.il Thu Feb 12 10:02:30 1998 From: priel at mail.biu.ac.il (Avner Priel) Date: Thu, 12 Feb 1998 17:02:30 +0200 (WET) Subject: paper on time series generation Message-ID: The following paper on the subject of time series generation by feed-forward networks has appeared on the Journal of Physics A 31(4) 1189 (1998). The paper is available from my home-page : http://faculty.biu.ac.il/~priel/ comments are welcome. *************** NO HARD COPIES ****************** ---------------------------------------------------------------------- Noisy time series generation by feed-forward networks ----------------------------------------------------- A Priel, I Kanter and D A Kessler Department of Physics, Bar Ilan University, 52900 Ramat Gan,Israel ABSTRACT: We study the properties of a noisy time series generated by a continuous-valued feed-forward network in which the next input vector is determined from past output values. Numerical simulations of a perceptron-type network exhibit the expected broadening of the noise-free attractor, without changing the attractor dimension. We show that the broadening of the attractor due to the noise scales inversely with the size of the system ,$N$, as $1/ \sqrt{N}$. We show both analytically and numerically that the diffusion constant for the phase along the attractor scales inversely with $N$. Hence, phase coherence holds up to a time that scales linearly with the size of the system. We find that the mean first passage time, $t$, to switch between attractors depends on $N$, and the reduced distance from bifurcation $\tau$ as $t = a {N \over \tau} \exp(b \tau N^{1/2})$, where $b$ is a constant which depends on the amplitude of the external noise. This result is obtained analytically for small $\tau$ and confirmed by numerical simulations. ---------------------------------------------------- Priel Avner < priel at mail.biu.ac.il > < http://faculty.biu.ac.il/~priel > Department of Physics, Bar-Ilan University. Ramat-Gan, 52900. Israel. From omori at cc.tuat.ac.jp Thu Feb 12 23:32:28 1998 From: omori at cc.tuat.ac.jp (Takashi Omori) Date: Fri, 13 Feb 1998 13:32:28 +0900 Subject: Call for Paper : ICONIP'98-Kitakyushu Message-ID: <01BD3883.D43B76E0@BRAIN> ----------------------------------------- Sorry if you receive this more than once ----------------------------------------- For your remind of ICONIP'98-Kitakyushu. The dead line is March 31-st, 1998. Please refer http://jnns-www.okabe.rcast.u-tokyo.ac.jp/jnns/ICONIP98.html for latest information. The Fifth International Conference on Neural Information Processing (ICONIP'98) October 21-23,1998 Kitakyushu International Conference Center 3-9-30 Asano, Kokura-ku, Kitakyushu 802, Japan Organized by Japanese Neural Network Society (JNNS) Sponsored by Asian Pacific Neural Network Assembly (APNNA) The annual conference of the Asian Pacific Neural Network Assembly, ICONIP'98, will be held jointly with the ninth annual conference of Japanese Neural Network Society, from 21 to 23 October 1998 in Kitakyushu, Japan. The goal of ICONIP'98 is to provide a forum for researchers and engineers from academia and industries to meet and to exchange ideas on advanced techniques and recent developments in neural information processing. The conference further serves to stimulate local and regional interests in neural information processing and its potential applications to industries indigenous to this region. Topics of Interest Track$B-5(J: Neurobiological Basis of Brain Functions(J Track$B-6(J: Mathematical Theory of Brain Functions(J Track$B-7(J: Cognitive and Behavioral Aspects of Brain Functions(J Track$B-8(J: Theoretical and Technical Aspects of Neural Networks(J Track$B-9(J: Distributed Processing Systems(J Track$B-:(J: Applications of Neural Networks(J Track$B-;(J: Implementations of Neural Networks(J Topics cover (Key Words): Neuroscience, Neurobiology and Biophysics, Learning and Plasticity, Sensory and Motor Systems, Cognition and Perception Algorithms and Architectures, Learning and Generalization, Memory, Neurodynamics and Chaos, Probabilistic and Statistical Methods, Neural Coding Emotion, Consciousness and Attention, Visual and Auditory Computation, Speech and Languages, Neural Control and Robotics, Pattern Recognition and Signal Processing, Time Series Forecasting, Blind Separation, Knowledge Acquisition, Data Mining, Rule Extraction Emergent Computation, Distributed AI Systems, Agent-Based Systems, Soft Computing, Real World Systems, Neuro-Fuzzy Systems Neural Device and Hardware, Neural and Brain Computers, Software Tools, System Integration Conference Committee Conference Chair: Kunihiko Fukushima, Osaka University Conference Vice-chair: Minoru Tsukada, Tamagawa University Organizing Chair: Shuji Yoshizawa, Tokyo University Program Chair: Shiro Usui, Toyohashi University of Technology International Advisory Committee (tentative) Chair: Shun-ichi Amari, Institute of Physical and Chemical Research Members: S. Bang (Korea), J. Bezdek (USA), J. Dayhoff (USA), R. Eckmiller (Germany), W. Freeman (USA), N. Kasabov (New Zealand), H. Mallot (Germany), G. Matsumoto (Japan), N. Sugie (Japan), R. Suzuki (Japan), K. Toyama (Japan), Y. Wu (China), L.Xei (Hong Kong), J. Zurada (USA) Call for paper The Program Committee is looking for original papers on the above mentioned topics. Authors should pay special attention to explanation of theoretical and technical choices involved, point out possible limitations and describe the current states of their work. All received papers will be reviewed by the Program Committee. The authors will be informed about the decision of the review process by June 22, 1998. All accepted papers will be published. As the conference is a multi-disciplinary meeting the papers are required to be comprehensible to a wider rather than to a very specialized audience. Instruction to Authors Papers must be received by March 31, 1998. The papers must be submitted in a camera-ready format. Electronic or fax submission is not acceptable. Papers will be presented at the conference either in an oral or in a poster session. Please submit a completed full original pages and five copies of the paper written in English, and backing material in a large mailing envelope. Do not fold or bend your paper in any way. They must be prepared 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. Centered at the top of the first page should be the complete title, author(s), mailing and e-mailing addresses, followed by 100-150 words abstract and the text. Extra 2 pages are permitted with a cost of 5000 yen/page. Use black ink. Do not use any other color, either in the text or illustrations. The proceedings will be printed with black ink on white paper. In the covering letter the track and the topic of the paper according to the list above should be indicated. No changes will be possible after submission of your manuscript. Authors may also retrieve the ICONIP style "iconip98.tex", "iconip98.sty" and "sample.eps" files (they are compressed as form.tar.gz) for the conference via WWW at URL http://jnns-www.okabe.rcast.u-tokyo.ac.jp/jnns/ICONIP98.html. Language The use of English is required for papers and presentation. No simultaneous interpretation will be provided. Registration The deadline for Registration for speakers and Early Registration for non-speakers with remittance will be July 31, 1998. The registration fee for General Participant includes attendance to the conference, proceedings, banquette and reception. The registration fee for Student includes attendance to the conference and proceedings. Conference Venue Kitakyushu is a northern city in Kyushu Island, south west of Japan main islands. The place is one of the Japanese major industrial areas, and also has long history of two thousand years in Japanese and Chinese ancient records. There are direct flights from Asian and American major airports. You will be able to enjoy some technical tours and excursion in the area. Passport and Visa All foreign attendants entering Japan must possess a valid passport. Those requiring visas should apply to the Japanese council or diplomatic mission in their own country prior to departure. For details, participants are advised to consult their travel agents, air-line reservation office or the nearest Japanese mission. Events Exhibition, poster sessions, workshops, forum will be held at the conference. Two satellite workshops will be held just before or after the conference. Social Events Banquette, reception and excursion will be held at the conference. The details will be announced in the second circular. Workshops Two satellite workshops will be held. One is "Satellite workshop for young researcher on Information processing" that will be held after the conference. The detail is announced in the attached paper. Another workshop "Dynamical Brain" is under programming. This will take place in Brain Science Research Center, Tamagawa University Research Institute. The details will be announced in the Second Circular. Please see second circular for more information on these workshops, and possibly other new ones. Important Dates for ICONIP'98 Papers Due: March 31, 1998 Notification of Paper Acceptance: June 22, 1998 Second Circular (with Registration Form): June 22, 1998 Registration of at least one author of a paper: July 31, 1998 Early Registration: July 31, 1998 Conference: October 21-23, 1998 Workshop: October 24-26, 1998 Further Information & Paper Submissions ICONIP'98 Secretariat Mr. Masahito Matsue Japan Technical Information Service Sogo Kojimachi No.3 Bldg. 1-6 Kojimachi, Chiyoda-ku, Tokyo 102, Japan Tel:+81-3-3239-4565 Fax:+81-3-3239-4714 E-mail: jatisc at msn.com $B!y(J Could you suggest your friends and acquaintances who will be interested (J in ICONIP'98-Kitakyushu? Thank you. ---------------------------------------------------------------------------- - ICONIP'98-Kitakyushu 21-23 October, 1998 Tentative Registration (PLEASE PRINT) Name: Professor Dr. Ms. Mr. Last Name First Name Middle Name Affiliation: Address: Country: Telephone: Fax: E-mail: $B""(J I intend to submit a paper.(J The tentative title of my paper is: $B""(J I intend to attend the conference.(J $B""(J I want to receive the Second Circular.(J Please mail a copy of this completed form to: ICONIP'98 Secretariat Mr. Masahito Matue Japan Technical Information Service Sogo Kojimachi No.3 Bldg. 1-6 Kojimachi, Chiyoda-ku, Tokyo 102, Japan Tel:+81-3-3239-4565 Fax:+81-3-3239-4714 E-mail: jatisc at msn.com ************************************************** * Takashi Omori, Ph.D * * BASE: Biologocal Applications & Systems Engineering * * Tokyo University of Agriculture & Technology * Nakacho 2-24-16 , Koganei, Tokyo 184 Japan * +81-423-88-7148 FAX:+81-423-85-5395 * omori at cc.tuat.ac.jp ************************************************************** From jls at cs.man.ac.uk Fri Feb 13 11:17:37 1998 From: jls at cs.man.ac.uk (Jon Shapiro) Date: Fri, 13 Feb 1998 16:17:37 GMT Subject: Lectureship in Modelling of Living/Organic Systems and Information Systems Message-ID: <199802131617.QAA07007@rdf074.cs.man.ac.uk.> Hi, We are seeking applicants for an opening in the Computer Science Department at Manchester University for a Lecturer in Modelling of Living/Organic Systems and Information Systems. This is equivalent to a tenure-track Assistant Professor position in the U.S. Closing date is 28 February 1998. Please pass this on to any researcher you think might be interested. For more information, look at http://www.cs.man.ac.uk, or contact Professor John Gurd (jrg at cs.man.ac.uk). Thanks, Jonathan Shapiro ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Department of Computer Science University of Manchester A Research-Led Expansion in Computer Science has led to the establishment of the following posts: Chair in Formal Methods for Computing Science Chair and 2 Lectureships in Mobile Systems Architecture 3 Lectureships in Modelling and Simulation: Lectureships in Process Modelling and Information Engineering, Modelling of Living/Organic Systems and Information Systems. 50 Years after the first stored-program electronic digital computer was developed at the University of Manchester, the Department of Computer Science at Manchester remains a world leader in research and teaching in Computer Science. We are looking to appoint staff with international research reputation or potential. These new posts offer individuals with appropriate experience an opportunity to contribute to world leading research developments from a position of strength. See our Web Page http://www.cs.man.ac.uk for further details. From SaadE at TTACS.TTU.EDU Fri Feb 13 16:29:10 1998 From: SaadE at TTACS.TTU.EDU (Emad William Saad) Date: Fri, 13 Feb 1998 15:29:10 -0600 Subject: Explanation Capability of Neural Networks Message-ID: <34E4BB26.D086E4EE@ttu.edu> I have been doing litterature search on the subject of "Explanation Capability of Neural Networks/ Rule extraction of NN's", and came with the following bibliography: [1] Fu, Y., ?Data mining: Tasks, techniques and applications,? Potentials, vol. 16, no. 4, pp. 18-20, 1997. [2] Andrews, R., Diederich, J., and Tickle, A., ?A Survey and Critique of Techniques for Extracting Rules from Trained Artificial Neural Networks,? Knowledge-Based Systems, vol. 8, no. 6, pp. 373-389, 1996. [3] Benitez, J. M., Castro, J. L., and Requena, I., ?Are Artificial Neural Networks Black Boxes?,? IEEE Trans. Neural Networks, vol. 8, no. 5, pp. 1156-1164, 1997. [4] Tsukimoto, H., ?Extracting Propositions from Trained Neural Networks,? in Proc. IEEE International Conference on Neural Networks, August 1997. [5] Kindermann, J., and Linden, A., ?Detection of Minimal Microfeatures by Internal Feedback,? in Proc. fifth Austrian Artificial Intelligence Meeting, pp. 230-239, 1989. [6] Healy, M. J., and Caudell, T. P., ?Acquiring Rule Sets as a Product of Learning in a Logical Neural Architecture,? IEEE Trans. Neural Networks, vol. 8, no. 3, pp. 461-474, 1997. [7] Yeung, D. S., and Hak-shun, Fong, "Knowledge Matrix - An Explanation and Knowledge Rrefinement Facility for a Rule Induced Neural Network," in Proc. Twelfth National Conference on Artificial Intelligence, 1994, vol. 2, pp. 889-894. [8] Machado, R. J., and da Rocha, A. F., "Inference, Inquiry, Evidence Censorship, and Explanation in Connectionist Expert Systems," IEEE Trans. Fuzzy Systems, vol. 5, no. 3, pp 443-459. [9] Gilstrap, L. O., and Dominy, R. E., "A General Explanation and Interogation System for Neural Networks," in Proc. International Joint Conference on Neural Networks, Washington, DC, June 1989, vol. 2, pp. 594. [10] Taha, I., and Ghosh, J., "Evaluation and Ordering of Rules Extracted from Feedward Networks," in Proc. IEEE International Conference on Neural Networks, Houston, TX, June 1997, vol. 1, pp. 408-413. [11] Ornes, C., and Sklansky, J., "A Neural Network that Explains as Well as Predicts Financial Market Behavior," in Proc. IEEE/IAFE Computational Intelligence for Financial Engineering, March 1997, pp. 43-49. [12] Ornes, C., and Sklansky, J., "A Visual Multi-Expert Neural Classifier," in Proc. IEEE International Conference on Neural Networks, June 1997, vol. 3, pp. 1448-1453. [13] Taha, I., and Ghosh, J., "Three techniques for extracting rules from feedforward networks," in Intelligent Engineering Systems Through Artificial Neural Networks, vol. 6., ASME Press, November 1996. Please, I would be glad if anybody can guide me to more litterature/ web pages/ resources in this area. Emad Saad Applied Computational Intelligence Laboratory Dept. of Electrical Eng. Texas Tech University, Lubbock, TX 79409 From kr10000 at eng.cam.ac.uk Mon Feb 16 05:46:34 1998 From: kr10000 at eng.cam.ac.uk (K. Reinhard) Date: Mon, 16 Feb 1998 10:46:34 GMT Subject: Announcement of Technical Report availability. Message-ID: <199802161046.11893@opal.eng.cam.ac.uk> The following technical report is available by anonymous ftp from the archive of the Speech, Vision and Robotics Group at the Cambridge University Engineering Department (http://svr-www.eng.cam.ac.uk/reports/index-full.html). PARAMETRIC SUBSPACE MODELING OF SPEECH TRANSITIONS K. Reinhard and M. Niranjan Technical Report CUED/F-INFENG/TR.308 Cambridge University Engineering Department Trumpington Street, Cambridge CB2 1PZ U.K., England Abstract This report describes an attempt at capturing segmental transition information for speech recognition tasks. The slowly varying dynamics of spectral trajectories carries much discriminant information that is very crudely modelled by traditional approaches such as HMMs. In approaches such as recurrent neural networks there is the hope, but not the convincing demonstration, that such transitional information could be captured. The method presented here starts from the very different position of explicitly capturing the trajectory of short time spectral parameter vectors on a subspace in which the temporal sequence information is preserved. We approach this by introducing a temporal constraint into the well known technique of Principal Component Analysis. On this subspace, we attempt a parametric modelling of the trajectory, and compute a distance metric to perform classification of diphones. We use the principal curves method of Hastie and Stuetzle and the Generative Topographic map (GTM) technique of Bishop, Svenson and Williams to describe the temporal evolution in terms of latent variables. On the difficult problem of /bee/, /dee/, /gee/ we are able to retain discriminatory information with a small number of parameters. Experimental illustrations present results on ISOLET and TIMIT database. From robbie at hiki.bcs.rochester.edu Mon Feb 16 12:52:32 1998 From: robbie at hiki.bcs.rochester.edu (Robbie Jacobs) Date: Mon, 16 Feb 1998 12:52:32 -0500 Subject: postdoc position available Message-ID: <199802161752.MAA14907@hiki.bcs.rochester.edu> Postdoctoral Fellowship, Department of Brain and Cognitive Sciences, UNIVERSITY OF ROCHESTER -- The Department of Brain and Cognitive Sciences seeks an outstanding postdoctoral fellow with research interests in the areas of learning and/or developmental cognitive science. Supervising faculty work on the problems of learning and development using behavioral, computational, and neurobiological approaches. Candidates should have prior background/training in at least one of these approaches and an interest in working collaboratively in a highly interdisciplinary setting. Several faculty have special interest in statistical learning in the domains of language and perception, although a commitment to this interest is not a requirement of all applicants. This fellowship is open only to US citizens or permanent residents. Applicants should send a letter describing their graduate training and research interests, a curriculum vitae, and arrange to have three letters of recommendation sent to: Learning, Development, and Biology Training, Department of Brain and Cognitive Sciences, Meliora Hall, University of Rochester, Rochester, NY 14627-0268. Review of applications will begin on April 1, 1998 and continue until the position is filled, with an expected start date of August/September, 1998. Applicants can learn about the department, its faculty, and the opportunities for training by referring to our Web page (http://www.bcs.rochester.edu). Applications from women and members of underrepresented minority groups are especially welcome. The University of Rochester is an Equal Opportunity Employer. From eugene at engr.uconn.edu Mon Feb 16 08:48:18 1998 From: eugene at engr.uconn.edu (Eugene Santos) Date: Mon, 16 Feb 1998 08:48:18 -0500 Subject: [CFP] AI Meets the Real World '98 Lessons Learned! Message-ID: <199802161348.IAA11288@ultra9.uconn.edu> [Sorry if you get this message more than once! It is being posted to several distribution lists.] ------------------------------------------------------------------------------- ------------------------------------------------------------------------------- AI meets the Real World '98 Lessons Learned C a l l f o r P a r t i c i p a t i o n September 16 - 18, 1998 University of Connecticut -- Stamford Campus Stamford, CT Sponsored by: University of Connecticut Honeywell Technology Center US Air Force Research Labs -- Phillips Lab DARPA To a large and growing extent, techniques from the field of Artificial Intelligence are being applied in the implementation of fielded systems addressing practical problems in a wide range of domains, from manufacturing, to consumer services, to military and spacecraft operations, to name a very few. As a result, an informal and pragmatic practice of "AI engineering" has arisen, involving the identification, adaptation, and application of techniques including diagnostic systems, trend analysis and projection, uncertain reasoning and decision analysis, virtual environments/reality, training and tutoring systems, planning and scheduling, natural language parsing and generation, and parameter estimation and other forms of learning. The resulting systems range from large-scale, stand-alone intelligent systems, to embedded knowledge bases, to minor components of much larger applications. As one might expect from a body of work largely developed within a common intellectual and philosophical tradition, what we have here broadly termed "AI techniques" have some common features. These approaches tend to be complex and computationally intensive and to require a great deal of understanding and modelling, in some cases engineering, of the target domain and application for the approach to be successful. The aim of this meeting is to bring together researchers, practitioners, and developers of intelligent systems throughout academia, industry, and government to discuss and disseminate lessons learned from successful (or unsuccessful) attempts to design, construct, field, and maintain intelligent systems. The meeting will consist of presentations, panel discussions, and invited speakers. Our hope is to build a better knowledge base of how to successfully apply and correctly use artificial intelligence in real world systems. This meeting is not intended as a forum for those who already deeply immersed in AI. We particularly welcome people who are considering an AI-based approach to their problem to attend and participate in these discussions. We invite the submission of papers and topic ideas for panel discussions. Papers and presentations should be based on systems developed (or in progress) for real world use. Among the issues that might be of interest in such a presentation we would expect to find the following: -- What characteristics of the domain and the application lead to your choice of solution method? What alternative methods were considered and rejected? Were these choices revisited (and revised?) at some later point? -- What difficulties did you encounter? Which ones were expected? Unexpected? -- What was the final outcome? What qualifications or modifications of the original statement of the problem or system requirements were made? -- What lessons can be drawn from this experience, regarding: +++ domains where particular AI techniques are or aren't useful? +++ how to go about determining the utility of a technique in a new domain? +++ pitfalls to beware in system design, implementation, etc., that are peculiar to intelligent systems? We are also especially INTERESTED in soliciting questions/issues at all levels from both new and experienced systems builders on problems and approaches of using AI. Members of our program committee will attempt to answer and/or provide advice to these questions. These will be published in our printed proceedings. Of these, a select set of questions or general class of questions will be chosen for a special panel discussion session at the conference. Up-to-date meeting information will be provided at: http://www.eng2.uconn.edu/~eugene/AIMTRW Proceedings of invited papers will be published. ---------------- | Organizers | ---------------- Meeting Co-Chairs - ----------------- Eugene Santos, Jr. (University of Connecticut -- Storrs) Mark Boddy (Honeywell Technology Center, Minneapolis, MN) Doug Dyer (DARPA) Program Committee - ----------------- Sheila B. Banks (Air Force Institute of Technology) Piero Bonissone (GE) Jack Breese (Microsoft) Wray Buntine (Ultimode) Fabio Cozman (University of Sao Paulo) Bruce D'Ambrosio (Prevision & Oregon State University) Neal Glassman (Air Force Office of Scientific Research) James Hendler (University of Maryland) Chahira Hopper (Air Force Research Labs, Wright Lab) Lewis Johnson (University of Southern California) F. Alex Kilpatrick (Air Force Research Labs, Phillips Lab) Michael B. Leahy Jr. (DARPA) Claudia M. Meyer (NASA LERC) Alan L. Meyrowitz (Naval Research Laboratory) Doug Moran (SRI) Steve Rogers (Battelle) Solomon Eyal Shimony (Ben Gurion University of the Negev) Mike Shneier (Office of Naval Research) Valerie J. Shute (Air Force Research Labs, Armstrong Lab) Douglas Smith (Kestrel Institute) Martin R. Stytz (Air Force Institute of Technology) Abraham Waksman (Air Force Office of Scientific Research) Fred A. Watkins (Hyperlogic) Edward Wong (Polytechnic University) --------------------------- | Submission Guidelines | --------------------------- Authors should submit full papers addressing the above issues with a strong emphasis on "lessons learned." These will be evaluated for clarity of presentation and significance of contribution to the community. All accepted papers will be presented either orally or through a poster session and will be made available in a printed proceedings. Papers may be submitted either electronically or in hard copy form. Electronic submission may take the form of PostScript files, ASCII, or LaTeX files. Authors should be careful to include all macro files necessary for LaTeX files as we will not be responsible for files which cannot be formatted. Figures for LaTeX should be PostScript files. Hardcopy submissions should have 1-inch margins on all sides and should be in 12-point type. Papers should be a maximum of 20 pages long, including figures and references. Names, address, and e-mail of authors and an abstract should be included at the beginning of each paper. Hard copy submissions must arrive by May 15, 1998, and sent to Eugene Santos, Jr. [ATTN: AIMTRW-98] Computer Science and Engineering Department University of Connecticut UTEB, 191 Auditorium Rd., U-155 Storrs, CT 06269-3155 (860) 486-1458 Electronic submissions should be e-mailed by May 15, 1998, to eugene at eng2.uconn.edu Papers not meeting the deadline will not be considered. Proposals for panel discussions and invited speakers should be e-mailed by May 15, 1997, to the above address. For questions/issues, we solicit up to two (2) pages per question. Provide as much detail as possible for proper evaluation of the question by the program committee. We prefer electronic submissions to the above email address. Hard copy is welcome to the above address. These are also due May 15, 1998. ++++++++++++++++++++++++++++++++++++++ !++Meeting Attendance/Participation++! ++++++++++++++++++++++++++++++++++++++ Due to the limited space available for this meeting, we request that those planning to attend send an e-mail by May 1, 1998 to eugene at eng2.uconn.edu stating your intent and whether you will be also submitting a paper. --------------------- | Important Dates | --------------------- May 1, 1998 Deadline for participation request May 15, 1998 Deadline for paper submission May 15, 1998 Deadline for question submission May 15, 1998 Deadline for panel proposals, etc. June 15, 1998 Notification of acceptance or rejection June 29, 1998 Final camera-ready papers due September 16 - 18, 1998 Meeting dates From kirchmai at informatik.tu-muenchen.de Mon Feb 16 09:39:59 1998 From: kirchmai at informatik.tu-muenchen.de (Clemens Kirchmair) Date: Mon, 16 Feb 1998 15:39:59 +0100 (MET) Subject: Early registration deadline for FNS'98: 02/18/1998 Message-ID: ######################################################################### ATTENTION: The early registration deadline for the FNS '98 Workshop is Wednesday, February 18th, 1998. You can still save 100,- DM if you register now! Don't miss this excellent workshop! (Full program -- see below) The 5th International Workshop "Fuzzy-Neuro Systems '98 - Computational Intelligence" takes place in Munich, Germany, from March 19 to 20, 1998. Visit our WWW Homepage: http://wwwbrauer.informatik.tu-muenchen.de/~fns98/ Conference fees (registration UNTIL February 18th) industry rate: 495,- DM university rate: 345,- DM GI members: 295,- DM students (up to age of 26): 60,- DM (excluding proceedings and conference dinner.) Conference fees (registration AFTER February 18th) industry rate: 595,- DM university rate: 445,- DM GI members: 395,- DM students (up to age of 26): 160,- DM (excluding proceedings and conference dinner.) ######################################################################### ---------------------------------- | Fuzzy-Neuro Systems '98 | | - Computational Intelligence - | | | | 5th International Workshop | | March, 19 - 20, 1998 | ---------------------------------- Technische Universitaet Muenchen Gesellschaft fuer Informatik e.V. Fachausschuss 1.2 "Inferenzsysteme" Technische Universitaet Muenchen Institut fuer Informatik Fuzzy-Neuro Systems '98 is the fifth event of a well established series of workshops with international participation. Its aim is to give an overview of the state of art in research and development of fuzzy systems and artificial neural networks. Another aim is to highlight applications of these methods and to forge innovative links between theory and application by means of creative discussions. Fuzzy-Neuro Systems '98 is being organized by the Technical Committee 1.2 "Inference Systems" (Fachausschuss 1.2 "Inferenzsysteme") of the German Informatics Society GI (Gesellschaft fuer Informatik e. V.) and Institut fuer Informatik, Technische Universitaet Muenchen in cooperation with Siemens AG and with the support of Kratzer Automatisierung GmbH. The workshop takes place at the Technische Universitaet Muenchen in Munich from March, 19 to 20, 1998. PROGRAM ------- Wednesday, March 18, 1998 18:00 Informal Get-Together Registration 21:00 End of reception and registration Thursday, March 19, 1998 8:00 Registration 9:00 Formal Opening President, TU Muenchen Dekan, Institut fuer Informatik, TU Muenchen Workshop Chair 9:15 Invited Lecture 1: Sets, Fuzzy Sets and Rough Sets Zdzislaw Pawlak, Warsaw University of Technology, Poland Chairman: W. Brauer, TU Muenchen 10:00 Session 1: Fuzzy Control Chairman: R. Isermann, TU Darmstadt Indirect Adaptive Sugeno Fuzzy Control J. Abonyi, L. Nagy, S. Ferenc, University of Veszprem, Veszprem, Hungary Simultaneous Creation of Fuzzy Sets and Rules for Hierarchical Fuzzy Systems R. Holve, FORWISS, Erlangen, Germany 10:50 Coffee break - Presentation of Posters 11:10 Session 2: Neural Networks for Classification Chairman: K. Obermayer, TU Berlin Hybrid Systems for Time Series Classification C. Neukirchen, G. Rigoll, Gerhard-Mercator-Universitaet, Duisburg How Parallel Plug-in Classifiers Optimally Contribute to the Overall System W. Utschick, J.A. Nossek, TU Muenchen 12:00 Invited Lecture 2: Is Readibility Compatible with Accuracy? Hugues Bersini, Universite Libre de Bruxelles, Belgium Chairman: J. Hollatz, Siemens AG, Muenchen 12:45 Lunch 14:00 Session 3: Fuzzy Logic in Data Analysis Chairman: C. Freksa, Universitaet Hamburg Fuzzy Topographic Kernel Clustering T. Graepel, K. Obermayer, TU Berlin Dynamic Data Analysis: Similarity Between Trajectories A. Joentgen, L. Mikenina, R. Weber, H.-J. Zimmermann, RWTH Aachen Spatial Reasoning with Uncertain Data Using Stochastic Relaxation R. Moratz, C. Freksa, Universitaet Hamburg Noise Clustering For Partially Supervised Classifier Design C. Otte, P. Jensch, Universitaet Oldenburg Fuzzy c-Mixed Prototypes Clustering C. Stutz, TU Muenchen T.A. Runkler, Siemens AG, Muenchen 16:00 Coffee break - Presentation of Posters 16:30 Invited Lecture 3: Neural Network Architectures for Time Series Prediction with Applications to Financial Data Forecasting Hans-Georg Zimmermann, Siemens AG, Muenchen Chairman: R. Rojas, FU Berlin 17:15 Session 4: Fuzzy-Neuro Systems Chairman: R. Kruse, Universitaet Magdeburg A Neuro-Fuzzy Approach to Feedforward Modeling of Nonlinear Time Series T. Briegel, V. Tresp, Siemens AG, Muenchen A Learning Algorithm for Fuzzy Neural Nets T. Feuring,Westfaelische Wilhelms-Universitaet Muenster James J. Buckley, University of Alabama at Birmingham, Birmingham, USA Improving a priori Control Knowledge by Reinforcement Learning M. Spott, M. Riedmiller, Universitaet Karlsruhe 18:30 End of First Day 20:00 Conference Dinner Friday, March 20, 1998 9:00 Session 5: Applications Chairman: G. Nakhaeizadeh, Daimler Benz AG, Forschung + Technik, Ulm Batch Recipe Optimization with Neural Networks and Genetice Algorithms K. Eder, Kratzer Automatisierung GmbH, Unterschleissheim Robust Tuning of Power System Stabilizers by an Accelerated Fuzzy-Logic Based Genetic Algorithm M. Khederzadeh, Power and Water Institute of Technology, Tehran, Iran Relating Chemical Structure to Activity: An Application of the Neural Folding Architecture T. Schmitt, C. Goller, TU Muenchen Optimization of a Fuzzy System Using Evolutionary Algorithms Q. Zhuang, M. Kreutz, J. Gayko, Ruhr-Universitaet Bochum 10:40 Coffee break - Presentation of Posters 11:00 Invited Lecture 4: Advanced Fuzzy-Concepts and Applications Harro Kiendl, Universitaet Dortmund Chairman: K. Eder, Kratzer Automatisierung GmbH, Unterschleissheim 11:45 Session 6: Theory and Foundations of Fuzzy-Logic Chairman: P. Klement, Universitaet Linz, Austria Rule Weights in Fuzzy Systems D. Nauck, R. Kruse, Universitaet Magdeburg Sliding-Mode-Based analysis of Fuzzy Gain Schedulers - The MIMO Case R. Palm, Siemens AG, Muenchen D. Driankov, University of Linkoeping, Sweden Qualitative Operators For Dealing With Uncertainty H. Seridi, Universite de Reims, France F. Bannay-Dupin, Universite d'Angers, France H. Akdag, Universite P. & M. Curie, Paris, France 13:00 Lunch 14:00 Session 7: Theory and Foundations of Neural Networks Chairman: A. Grauel, Universitaet Paderborn Prestructured Recurrent Neural Networks T. Brychcy, TU Muenchen Formalizing Neural Networks I. Fischer, University of Erlangen M. Koch, Technical University of Berlin M.R. Berthold, University of California, Berkeley, USA Correlation and Regression Based Neuron Pruning Strategies M. Rychetsky, S. Ortmann, C. Labeck, M. Glesner, TU Darmstadt 15:15 Invited Lecture 5: Soft Computing: the Synergistic Interaction of Fuzzy, Neural, and Evolutionary Computation Piero P. Bonissone, General Electric Corporate R&D Artificial Intelligence Laboratory, Schenectady, USA Chairman: S. Gottwald, Universitaet Leipzig 16:00 Closing Remarks and Invitation to FNS'99 Posters ------- Comparing Fuzzy Graphs M.R. Berthold, University of California, Berkeley, USA K.-P. Huber, Universitaet Karlsruhe A Numerical Approach to Approximate Reasoning via a Symbolic Interface. Application to Image Classification A. Borgi, H. Akdag, Universite P. & M. Curie, Paris, France J.-M. Bazin, Universite de Reims, France Entropy-Controlled Probabilistic Search M. David, J. Gottlieb, I. Kupka, TU Clausthal Ensembles of Evolutionary Created Artificial Neural Networks C.M. Friedrich, Universitaet Witten/Herdecke Design and Implementation of a Flexible Simulation Tool for Hybrid Problem Solving H. Geiger, IBV and TU Muenchen J. Pfalzgraf, K. Frank, T. Neuboeck, J. Weichenberger, Universitaet Salzburg, Austria A. Buecherl, TU Muenchen A Fuzzy Invariant Indexing Technique for Object Recognition under Partial Occlusion T. Graf, A. Knoll, A. Wolfram, Universitaet Bielefeld Fuzzy Causal Networks R. Hofmann, V. Tresp, Siemens AG, Muenchen Dynamic Data Analysis: Problem Description And Solution Approaches A. Joentgen, L. Mikenina, R. Weber, H.-J. Zimmermann, RWTH Aachen Filtering and Compressing Information by Neural Information Processor R. Kamimura, Tokai University, Japan A Fuzzy Local Map with Asymmetric Smoothing Using Voronoi Diagrams B. Lang, Siemens AG, Muenchen Fuzzy Interface with Prior Concepts and Non-convex Regularization J.C. Lemm, Universitaet Muenster Modeling and Simulating a Time-Dependent Physical System Using Fuzzy Techniques and a Recurrent Neural Network A. Nuernberger, A. Radetzky, R. Kruse, Universitaet Magdeburg The Kohonen Network Incorporating Explicit Statistics and Its Application to the Traveling Salesman Problem B.J. Oommen, Carleton University, Ottawa, Canada Automated Feature Selection Strategies: An experimental comparison improving Engine Knock Detection S. Ortmann, M. Rychetsky, M. Glesner, TU Darmstadt A Fuzzy-Neuro System for Reconstruction of Multi-Sensor information S. Petit-Renaud, T. Deneux, Universite de Technologie de Compiegne, Compiegne, France RACE: Relational Alternating Cluster Estimation and the Wedding Table Problem T.A. Runkler, Siemens AG, Muenchen J.C. Bezdek, University of West Florida, Pensacola, USA Neural Networks Handle Technological Information for Milling if Training Data is Carefully Preprocessed G. Schulz, D. Fichtner, A. Nestler, J. Hoffmann, TU Dresden Medically Motivated Testbed for Reinforcement Learning in Neural Architectures D. Surmeli, G. Koehler, H.-M. Gross, TU Ilmenau Adaptive Input-Space Clustering for Continuous Learning Tasks M. Tagscherer, P. Protzel, FORWISS, Erlangen A Criminalistic And Forensic Application Of Neural Networks A. Tenhagen, T. Feuring, W.-M. Lippe, G. Henke, H. Lahl, WWU-Muenster A Classical and a Fuzzy System Based Algorithm for the Simulation of the Waste Humidity in a Landfill M. Theisen, M. Glesner, TU Darmstadt FuNN, A Fuzzy Neural Logic Model R. Yasdi, GMD - Forschungszentrum Informationstechnik, Sankt Augustin An Efficient Model for Learning Systems of High-Dimensional Input within Local Scenarios J. Zhang, V. Schwert, Universitaet Bielefeld Optimization of a Fuzzy Controller for a Driver Assistant System Q. Zhuang, J. Gayko, M. Kreutz, Ruhr-Universitaet-Bochum Program Committee ----------------- Prof. Dr. W. Banzhaf, Universitaet Dortmund Dr. M. Berthold, Universitaet Karlsruhe Prof. Dr. Dr. h.c. W. Brauer, TU Muenchen (Chairman) Prof. Dr. G. Brewka, Universitaet Leipzig Dr. K. Eder, Kratzer Automatisierung GmbH, Unterschleissheim Prof. Dr. C. Freksa, Universitaet Hamburg Prof. Dr. M. Glesner, TU Darmstadt Prof. Dr. S. Gottwald, Universitaet Leipzig Prof. Dr. A. Grauel, Universitaet Paderborn/Soest Prof. Dr. H.-M. Gross, TU Ilmenau Dr. A. Guenter, Universitaet Bremen Dr. J. Hollatz, Siemens AG, Muenchen Prof. Dr. R. Isermann, TU Darmstadt Prof. Dr. P. Klement, Universitaet Linz, Austria Prof. Dr. R. Kruse, Universitaet Magdeburg (Vice Chairman) Prof. Dr. B. Mertsching, Universitaet Hamburg Prof. Dr. G. Nakhaeizadeh, Daimler Benz AG, Forschung + Technik, Ulm Prof. Dr. K. Obermayer, TU Berlin Prof. Dr. G. Palm, Universitaet Ulm Dr. R. Palm, Siemens AG, Muenchen Dr. L. Peters, GMD - Forschungszentrum Informationstechnik GmbH, Sankt Augustin Prof. Dr. F. Pichler, Universitaet Linz, Austria Dr. P. Protzel, FORWISS, Erlangen Prof. Dr. B. Reusch, Universitaet Dortmund Prof. Dr. Rigoll, Universitaet Duisburg Prof. Dr. R. Rojas, Freie Universitaet Berlin Prof. Dr. B. Schuermann, Siemens AG, Muenchen (Vice Chairman) Prof. Dr. W. von Seelen, Universitaet Bochum Prof. Dr. H. Thiele, Universitaet Dortmund Prof. Dr. W. Wahlster, Universitaet Saarbruecken Prof. Dr. H.-J. Zimmermann, RWTH Aachen Organization Committee ---------------------- Prof. Dr. Dr. h.c. W. Brauer (Chairman) Dieter Bartmann Till Brychcy Clemens Kirchmair Technische Universitaet Muenchen Tel.: 0 89/2 89-2 84 19 Fax: 0 89/2 89-2 84 83 Dr. Juergen Hollatz, Siemens AG, Muenchen (Vice Chairman) Christine Harms, - ccHa -, Sankt Augustin Conference Site --------------- TU Muenchen Barerstrasse 23 Entrance: Arcisstrasse Lecture hall S0320 D-80333 Muenchen Workshop Secretariat -------------------- Christine Harms c/o GMD / FNS'98 Schloss Birlinghoven D-53754 Sankt Augustin Tel.: ++49 2241 14-24 73 Fax: ++49 2241 14-24 72 email: christine.harms at gmd.de Registration ------------ Please make your (binding) reservation by sending the enclosed registration form to the conference secretariat. Confirmation will be given after receipt of the registration form. Conference Fees: (see registration form) industry rate: 495,- DM university rate: 345,- DM GI members: 295,- DM authors: 295,- DM students (up to age of 26): 60,- DM (*) *) excluding proceedings and conference dinner. A surcharge of DM 100,- is payable for registration after February, 18, 1998. Services of Gesellschaft fuer Informatik e. V. (GI) are VAT-free according to German law p. 4 Nr. 22a UStG. Payment (see registration form) ------- [ ] I have transferred the whole amount of DM________ to Gesellschaft fuer Informatik (GI), Sparkasse Bonn Account No.: 39 479 Bankcode: 380 500 00 Ref: SK-Fuzzy-98 [ ] I enclose a Eurocheque amounting to made payable to Gesellschaft fuer Informatik [ ] Please debit my [ ] Diners [ ] Visa [ ] Euro/Mastercard Cardnumber: Expiration date: Cardholder: Social events ------------- Informal get-together: March, 18, 1998, 18.00 - 21.00 Conference dinner: Thursday, March, 19,1998. Accommodation ------------- A limited number of rooms has been reserved at the FORUM/Penta Hotel at the special rate of single room DM 175,- double room DM 200,- FORUM Hotel Hochstrasse 3 D-81669 Muenchen Cancellation ------------ If cancellation is received up to February, 17, 1998, a 75% refund will be given. For cancellations received afterwards, no refunds can be guaranteed. WWW-Homepage ------------ URL: http://wwwbrauer.informatik.tu-muenchen.de/~fns98/ ----- snip, snip ----- Registration form for Fuzzy-Neuro Systems '98 --------------------------------------------- Please register me as follows Conference Fees: ---------------- [ ] industry rate: 495,- DM [ ] university rate: 345,- DM [ ] GI member No. 295,- DM [ ] authors: 295,- DM [ ] students (up to age of 26): 60,- DM (*) *) excluding proceedings and conference dinner Accommodation: -------------- I would like to make a binding reservation at the FORUM/Penta Hotel [ ] single room DM 175,- [ ] double room DM 200,- (together with ____________________________) Arrival date ______________________________ Departure date ___________________________ Payment directly at the hotel. Hotel booking has to be made until February, 17, 1998. After that we cannot guarantee any bookings. Conference diner: ----------------- [ ] I intend to participate in the conference dinner ...... extra ticket for conference dinner DM 50,-. Payment: -------- [ ] I have transferred the whole amount of DM________ to Gesellschaft fuer Informatik (GI), Sparkasse Bonn Account No.: 39 479 Bankcode: 380 500 00 Reference: SK-Fuzzy-98 [ ] I enclose a Eurocheque amounting to DM_________ made payable to Gesellschaft fuer Informatik [ ] Please debit my [ ] Diners [ ] Visa [ ] Euro/Mastercard Cardnumber:______________Expiration date:_________ Cardholder:_______________________________________ If cancellation is received up to February, 17, 1998, a 75% refund will be given. For cancellations received afterwards, no refunds can be guaranteed. Date:___________ Signature:__________________ Sender: ------- Last Name (Mr. / Mrs. / MS. Title): ________________________________________ First Name: ________________________________________ Affiliation: ________________________________________ Street/POB: ________________________________________ Zip/Postal Code/City: ________________________________________ Country: ________________________________________ Phone/Fax: ________________________________________ E-mail: ________________________________________ If you would like to take part in the workshop, please send the completed registration form to Christine Harms c/o GMD / FNS'98 Schloss Birlinghoven D-53754 Sankt Augustin Tel.: ++49 2241 14-24 73 Fax: ++49 2241 14-24 72 email: christine.harms at gmd.de From pfbaldi at netid.com Tue Feb 17 16:04:07 1998 From: pfbaldi at netid.com (pfbaldi@netid.com) Date: Tue, 17 Feb 1998 21:04:07 +0000 Subject: Book on Bioinformatics Message-ID: <199802180507.VAA21966@polaris.pacificnet.net> The following book is now available from MIT Press: Bioinformatics: the Machine Learning Approach Pierre Baldi and Soren Brunak February 1998 ISBN 0-262-02442-X 360 pp., 62 illus., 10 color $40.00 (cloth) MIT Press (800) 625-8569 (617) 253-5249 (617) 258-6894 (FAX) Additional information can be found at: http://mitpress.mit.edu/book-home.tcl?isbn=026202442X -------------------------------------------------------------------------- Table of Contents Series Foreword Preface 1 Introduction 1.1 Biological Data in Digital Symbol Sequences 1.2 Genomes--Diversity, Size, and Structure 1.3 Proteins and Proteomes 1.4 On the Information Content of Biological Sequences 1.5 Prediction of Molecular Function and Structure 2 Machine Learning Foundations: The Probabilistic Framework 2.1 Introduction: Bayesian Modeling 2.2 The Cox-Jaynes Axioms 2.3 Bayesian Inference and Induction 2.4 Model Structures: Graphical Models and Other Tricks 2.5 Summary 3 Probabilistic Modeling and Inference: Examples 3.1 The Simplest Sequence Models 3.2 Statistical Mechanics 4 Machine Learning Algorithms 4.1 Introduction 4.2 Dynamic Programming 4.3 Gradient Descent 4.4 EM/GEM Algorithms 4.5 Markov Chain Monte Carlo Methods 4.6 Simulated Annealing 4.7 Evolutionary and Genetic Algorithms 4.8 Learning Algorithms: Miscellaneous Aspects 5 Neural Networks: The Theory 5.1 Introduction 5.2 Universal Approximation Properties 5.3 Priors and Likelihoods 5.4 Learning Algorithms: Backpropagation 6 Neural Networks: Applications 6.1 Sequence Encoding and Output Interpretation 6.2 Prediction of Protein Secondary Structure 6.3 Prediction of Signal Peptides and Their Cleavage Sites 6.4 Applications for DNA and RNA Nucleotide Sequences 7 Hidden Markov Models: The Theory 7.1 Introduction 7.2 Prior Information and Initialization 7.3 Likelihood and Basic Algorithms 7.4 Learning Algorithms 7.5 Applications of HMMs: General Aspects 8 Hidden Markov Models: Applications 8.1 Protein Applications 8.2 DNA and RNA Applications 8.3 Conclusion: Advantages and Limitations of HMMs 9 Hybrid Systems: Hidden Markov Models and Neural Networks 9.1 Introduction to Hybrid Models 9.2 The Single-Model Case 9.3 The Multiple-Model Case 9.4 Simulation Results 9.5 Summary 10 Probabilistic Models of Evolution: Phylogenetic Trees 10.1 Introduction to Probabilistic Models of Evolution 10.2 Substitution Probabilities and Evolutionary Rates 10.3 Rates of Evolution 10.4 Data Likelihood 10.5 Optimal Trees and Learning 10.6 Parsimony 10.7 Extensions 11 Stochastic Grammars and Linguistics 11.1 Introduction to Formal Grammars 11.2 Formal Grammars and the Chomsky Hierarchy 11.3 Applications of Grammars to Biological Sequences 11.4 Prior Information and Initialization 11.5 Likelihood 11.6 Learning Algorithms 11.7 Applications of SCFGs 11.8 Experiments 11.9 Future Directions 12 Internet Resources and Public Databases 12.1 A Rapidly Changing Set of Resources 12.2 Databases over Databases and Tools 12.3 Databases over Databases 12.4 Databases 12.5 Sequence Similarity Searches 12.6 Alignment 12.7 Selected Prediction Servers 12.8 Molecular Biology Software Links 12.9 Ph.D. Courses over the Internet 12.10 HMM/NN Simulator A Statistics A.1 Decision Theory and Loss Functions A.2 Quadratic Loss Functions A.3 The Bias/Variance Trade-off A.4 Combining Estimators A.5 Error Bars A.6 Sufficient Statistics A.7 Exponential Family A.8 Gaussian Process Models A.9 Variational Methods B Information Theory, Entropy, and Relative Entropy B.1 Entropy B.2 Relative Entropy B.3 Mutual Information B.4 Jensen's Inequality B.5 Maximum Entropy B.6 Minimum Relative Entropy C Probabilistic Graphical Models C.1 Notation and Preliminaries C.2 The Undirected Case: Markov Random Fields C.3 The Directed Case: Bayesian Networks D HMM Technicalities, Scaling, Periodic Architectures, State Functions, and Dirichlet Mixtures D.1 Scaling D.2 Periodic Architectures D.3 State Functions: Bendability D.4 Dirichlet Mixtures E List of Main Symbols and Abbreviations References Index -------------------------------------------------------------------------------- From dblank at comp.uark.edu Tue Feb 17 23:47:51 1998 From: dblank at comp.uark.edu (Douglas Blank) Date: Tue, 17 Feb 1998 22:47:51 -0600 Subject: PhD Thesis: "Learning to See Analogies: A Connectionist Exploration" Message-ID: <3.0.32.19980217224749.00710f30@comp.uark.edu> The following Ph.D. thesis is now available via - anonymous ftp (ftp://dangermouse.uark.edu/pub/thesis) - web site (http://www.uark.edu/~dblank/thesis.html) - hardcopy (send address to dblank at comp.uark.edu) It is about 200 pages long and the chapters can be retrieved individually as PostScript or PDF files. (Specific retrieval instructions below). Title: Learning to See Analogies: A Connectionist Exploration Douglas S. Blank Joint Ph.D. in Cognitive Science and Computer Science Indiana University, Bloomington ABSTRACT This dissertation explores the integration of learning and analogy-making through the development of a computer program, called Analogator, that learns to make analogies by example. By "seeing" many different analogy problems, along with possible solutions, Analogator gradually develops an ability to make new analogies. That is, it learns to make analogies by analogy. This approach stands in contrast to most existing research on analogy-making, in which typically the a priori existence of analogical mechanisms within a model is assumed. The present research extends standard connectionist methodologies by developing a specialized associative training procedure for a recurrent network architecture. The network is trained to divide input scenes (or situations) into appropriate figure and ground components. Seeing one scene in terms of a particular figure and ground provides the context for seeing another in an analogous fashion. After training, the model is able to make new analogies between novel situations. Analogator has much in common with lower-level perceptual models of categorization and recognition; it thus serves as a unifying framework encompassing both high-level analogical learning and low-level perception. This approach is compared and contrasted with other computational models of analogy-making. The model's training and generalization performance is examined, and limitations are discussed. =========================================================== Title, Abstract, Acknowledgments, Contents 0_intro.pdf 54k 0_intro.ps.gz 71k Chapter 1 INTRODUCTION 1_ch.pdf 172k 1_ch.ps.gz 187k Chapter 2 ANALOGY-MAKING, LEARNING, AND GENERALIZATION 2_ch.pdf 32k 2_ch.ps.gz 40k Chapter 3 CONNECTIONIST FOUNDATIONS 3_ch.pdf 221k 3_ch.ps.gz 189k Chapter 4 THE ANALOGATOR MODEL 4_ch.pdf 578k 4_ch.ps.gz 390k Chapter 5 EXPERIMENTAL RESULTS 5_ch.pdf 702k 5_ch.ps.gz 566k Chapter 6 COMPARISONS WITH OTHER MODELS OF ANALOGY-MAKING 6_ch.pdf 305k 6_ch.ps.gz 276k Chapter 7 CONCLUSION 7_ch.pdf 16k 7_ch.ps.gz 24k APPENDICES, REFERENCES 8_end.pdf 57k 8_end.ps.gz 91k Everything all.pdf 2M all.ps.gz 1M =========================================================== FTP instructions: (e.g., to retrieve Chapter 1) unix> ftp dangermouse.uark.edu Name: anonymous Password: youremail at domain ftp> cd pub/thesis ftp> get 1_ch.ps.gz ftp> bye unix> gunzip 1_ch.ps.gz unix> lpr 1_ch.ps ===================================================================== dblank at comp.uark.edu Douglas Blank, University of Arkansas Assistant Professor Computer Science ==================== http://www.uark.edu/~dblank ==================== From erik at bbf.uia.ac.be Wed Feb 18 11:37:34 1998 From: erik at bbf.uia.ac.be (Erik De Schutter) Date: Wed, 18 Feb 1998 16:37:34 GMT Subject: 1998 Crete Course in Computational Neuroscience Message-ID: <199802181637.QAA14539@kuifje.bbf.uia.ac.be> CRETE COURSE IN COMPUTATIONAL NEUROSCIENCE SEPTEMBER 13 - OCTOBER 9, 1998 FORTH INSTITUTE, CRETE, GREECE DIRECTORS: Erik De Schutter (University of Antwerp, Belgium) Adonis Moschovakis (University of Crete, Greece) Idan Segev (Hebrew University, Jerusalem, Israel) The Crete Course in Computational Neuroscience introduces students to the practical application of computational methods in neuroscience, in particular how to create biologically realistic models of neurons and networks. The course consists of two complimentary parts. A distinguished international faculty gives morning lectures on topics in experimental and computational neuroscience. The rest of the day is spent learning how to use simulation software and how to implement a model of the system the student wishes to study. The first week of the course introduces students to the most important techniques in modeling single cells, networks and neural systems. Students learn how to use the GENESIS, NEURON, XPP and other software packages on their individual unix workstations. During the following three weeks the lectures will be more general, but each week topics ranging from modeling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the the brain will be covered. The course ends with a presentation of the students' modeling projects. The Crete Course in Computational Neuroscience is designed for advanced graduate students and postdoctoral fellows in a variety of disciplines, including neuroscience, physics, electrical engineering, computer science and psychology. Students are expected to have a basic background in neurobiology as well as some computer experience. A total of 28 students will be accepted with an age limit of 35 years. We will accept students of any nationality, but the majority will be from the European Union and affiliated countries (Iceland, Israel, Liechtenstein and Norway). We specifically encourage applications from researchers who work in less-favoured regions of the EU, from women and from researchers from industry. Every student will be charged a tuition fee of 700 ECU (approx. US$770). In the case of students with a nationality from the EU, affiliated countries or Japan, this tuition fee covers lodging, local travel and all course-related expenses. All applicants with other nationalities will be charged an ADDITIONAL fee of 1000 ECU (approx. US$1100) to cover lodging, local travel and course-related expenses. For nationals from EU and affiliated countries economy travel from an EU country to Crete will be refunded after the course. A limited number of students from less-favoured regions world-wide will get their fees and travel refunded. More information and application forms can be obtained: - WWW access: http://bbf-www.uia.ac.be/Crete_index.html Please apply electronically using a web browser if possible. - email: crete_course at bbf.uia.ac.be - by mail: Prof. E. De Schutter Born-Bunge Foundation University of Antwerp - UIA, Universiteitsplein 1 B2610 Antwerp Belgium FAX: +32-3-8202669 APPLICATION DEADLINE: May 1, 1998. Applicants will be notified of the results of the selection procedures by May 31. FACULTY: M. Abeles (Hebrew University Jerusalem, Israel), A. Aertsen (Albert Ludwigs University Freiburg, Germany), A. Borst (Max Planck Institute Tuebingen, Germany), R. Calabrese (Emory University, USA), R. Douglas (Institute of Neuroinformatics, Zurich), G. Dupond (Free University Brussels, Belgium), O. Ekeberg (Royal Institute of Technology, Sweden), A. Feltz (University of Strasbourg, France), T. Flash (Weizmann Institute of Science, Israel), D. Hansel (Ecole Polytechnique Paris, France), J.J.B. Jack (Oxford University, England), R. Kotter (Heinrich Heine University Dusseldorf, Germany), G. LeMasson (University of Bordeaux, France), K. Martin (Institute of Neuroinformatics, Zurich), M. Nicolelis (Duke University, USA), G. Rizzolatti (University of Parma, Italy), J.M. Rinzel (NIH, USA), H. Sompolinsky (Hebrew University Jerusalem, Israel), M. Spira (Hebrew University Jerusalem, Israel), S. Tanaka (RIKEN, Japan), C. Wilson (University of Tennessee, USA), Y. Yarom (Hebrew University Jerusalem, Israel) and others to be named. The Crete Course in Computational Neuroscience is supported by the European Commission (4th Framework Training and Mobility of Researchers program) and by The Brain Science Foundation (Tokyo). Local administrative organization: the Institute of Applied and Computational Mathematics of FORTH (Crete, GR). From cmbishop at microsoft.com Wed Feb 18 11:14:08 1998 From: cmbishop at microsoft.com (Christopher Bishop) Date: Wed, 18 Feb 1998 08:14:08 -0800 Subject: Paper and software available on-line Message-ID: <3FF8121C9B6DD111812100805F31FC0D810C85@red-msg-59.dns.microsoft.com> Paper and Software Available Online: A HIERARCHICAL LATENT VARIABLE MODEL FOR DATA VISUALIZATION NCRG/96/028 Christopher M. Bishop* and Michael E. Tipping# * Microsoft Research St. George House, 1 Guildhall Street Cambridge CB2 3NH, U.K. # Neural Computing Research Group Aston University, Birmingham B4 7ET, U.K. http://neural-server.aston.ac.uk/Papers/postscript/NCRG_96_028.ps.Z Abstract: Visualization has proven to be a powerful and widely-applicable tool for the analysis and interpretation of multi-variate data. Most visualization algorithms aim to find a projection from the data space down to a two-dimensional visualization space. However, for complex data sets living in a high-dimensional space it is unlikely that a single two-dimensional projection can reveal all of the interesting structure. We therefore introduce a hierarchical visualization algorithm which allows the complete data set to be visualized at the top level, with clusters and sub-clusters of data points visualized at deeper levels. The algorithm is based on a hierarchical mixture of latent variable models, whose parameters are estimated using the expectation-maximization algorithm. We demonstrate the principle of the approach on a toy data set, and we then apply the algorithm to the visualization of a synthetic data set in 12 dimensions obtained from a simulation of multi-phase flows in oil pipelines, and to data in 36 dimensions derived from satellite images. A Matlab(R) software implementation of the algorithm is publicly available from the world-wide web. Paper: http://neural-server.aston.ac.uk/Papers/postscript/NCRG_96_028.ps.Z Software: http://www.ncrg.aston.ac.uk/PhiVis Complete searchable database of publications: http://neural-server.aston.ac.uk/ ---------------------------------------------------------------------------- ---- Professor Christopher M. Bishop Microsoft Research, Cambridge St. George House, 1 Guildhall Street Cambridge CB2 3NH Tel: +44/0 1223 744 751 Fax: +44/0 1223 744 777 Email: cmbishop at microsoft.com Web: http://www.ncrg.aston.ac.uk/People/bishopc/Welcome.html ---------------------------------------------------------------------------- ---- From SteinR at moodys.com Wed Feb 18 11:20:49 1998 From: SteinR at moodys.com (Stein, Roger) Date: Wed, 18 Feb 1998 11:20:49 -0500 Subject: Adaptive and intelligent systems in business: Book available Message-ID: Members of the Santa Fe Institute mailing list may have already received this. Apologies... SEVEN METHODS FOR TRANSFORMING CORPORATE DATA INTO BUSINESS INTELLIGENCE by Vasant Dhar and Roger Stein Upper Saddle River, NJ, Prentice-Hall, 1997. My colleague, Vasant Dhar, and I have written a short book on applying intelligent and adaptive systems to business problems. It may be of interest to some subscribers. There are two versions of the book available, one is suited to business people and one is suited to teaching. The book provides a practical methodology for mapping business problems onto solutions involving neural networks, genetic algorithms, nearest-neighbor algorithms, etc. We also provide extended case studies of organizations that have successfully done this. The reaction to the book, in both the academic and professional community, seems to be favorable: "Intelligent Systems are becoming vital at all levels of management from the CEO to the foreman. Dhar and Stein provide one of the clearest and most accessible treatments to date of the subject." - Herbert A. Simon, Nobel Laureate "Seven Methods effectively bridges the gap between lofty technical explanation and the down-to-earth business application of a brand new world of modeling technologies." - Win Farrell, Partner, Coopers and Lybrand A brief summary of the book follows: Seven Methods for Transforming Corporate Data into Business Intelligence combines a thorough treatment of techniques for applying intelligent systems to decision support with a practical framework for analyzing business problems. Vasant Dhar (former Principal, Morgan Stanley and New York University) and Roger Stein (Vice President, Moody's Investors Service and New York University) present in clear and vivid terms the essentials of modern decision support. Seven Methods takes a three stage approach to discussing these new technologies. The book is organized around: * A framework for analyzing business decision problems and mapping solutions onto them * An intuitive but full discussion of the technologies for data mining and automated decision systems * A series of extensive case studies that show, using the framework, how major organizations have made use of these technologies In addition to discussing technologies, Dhar and Stein introduce a unified methodology for analyzing organizations' business problems and evaluating potential solutions. This framework, based on the authors' years of combined experience applying intelligent systems to real business decision problems, encourages business people to think critically about how the strengths and weaknesses of each technique relate to the particular dynamics of an organization and its problems. The authors show not only when a particular modeling method may be useful, but also when its attributes might make it undesirable for a particular problem. The text does not limit itself to one or a few techniques, but rather views various AI and database techniques as components of a toolbox that, if used correctly, can make organizations dramatically more intelligent. Seven Methods provides accessible detailed coverage of * OLAP and data warehousing * Genetic algorithms * Neural networks * Rule-based expert systems * Fuzzy systems * Case-based reasoning * Machine learning The text adopts an informal, conversational style in their exposition. Despite the relaxed style, the book delves into the subtle aspects of each technique while keeping the text readable and non-technical. In order to make the material more accessible, the text makes frequent use of rich graphics. The graphical representation of complex concepts are invaluable in elucidating these topics. To drive home the discussions of modeling techniques and organizational dynamics, the book also provides extended case studies that show in detail how the framework can be applied to analyzing the problems of real organizations. Cases are taken from the experience of firms in a diversity of industries solving an assortment of problems. Firms include: * US WEST * Moody's Investors Service * Compaq Computer Corp. * LBS Capital Management * NYNEX, Inc. * Kaufhof AG * A. C. Neilsen Problem domains include: * customer service * scheduling * data mining * financial market prediction * quality control * consumer product marketing The book is available from Prentice-Hall: (Professional version) Seven Methods for Transforming Corporate Data into Business Intelligence, Upper Saddle River, NJ, Prentice-Hall, 1997. (Academic version) Intelligent Decision Support Methods: The Science of Knowledge Work, Upper Saddle River, NJ, Prentice-Hall, 1997. Online Orders: www.amazon.com Phone: 1-(800) 643-5506. Please give the operator the following "key code": E1001-A1(3). FAX: 1-(800) 835-5327. From annesp at vaxsa.csied.unisa.it Wed Feb 18 10:46:29 1998 From: annesp at vaxsa.csied.unisa.it (annesp@vaxsa.csied.unisa.it) Date: Wed, 18 Feb 1998 16:46:29 +0100 Subject: summer school Message-ID: <98021816462905@vaxsa.csied.unisa.it> From: SMTP%"iiass at tin.it" 18-FEB-1998 16:34:18.19 To: annesp at vaxsa.csied.unisa.it CC: Subj: call ***************************************************************** Please post **************************************************************** International Summer School ``Neural Nets E. R. Caianiello" 3rd Course "A Course on Speech Processing, Recognition, and Artificial Neural Networks" web page: http://wsfalco.ing.uniroma1.it/Speeschool.html The school is jointly organized by: INTERNATIONAL INSTITUTE FOR ADVANCED SCIENTIFIC STUDIES (IIASS) Vietri sul Mare (SA) Italy, ETTORE MAJORANA FOUNDATION AND CENTER FOR SCIENTIFIC CULTURE (EMFCSC) Erice (TR), Italy Supported by: EUROPEAN SPEECH COMMUNICATION ASSOCIATION (ESCA) Sponsored by: SALERNO UNIVERSITY, Dipartimento di Scienze Fisiche E.R. Caianiello (Italy) DIRECTORS OF THE COURSE DIRECTORS OF THE SCHOOL AND ORGANIZING COMMITTEE: Gerard Chollet (France). Maria Marinaro (Italy) M. Gabriella Di Benedetto (Italy) Michael Jordan (USA) Anna Esposito (Italy) Maria Marinaro (Italy) PLACE: International Institute for Advanced Scientific Studies (IIASS) Via Pellegrino 19, 84019 Vietri sul Mare, Salerno (Italy) DATES: 5th-14th October 1998 POETIC TOUCH Vietri (from "Veteri", its ancient Roman name) sul Mare ("on sea") is located within walking distance from Salerno and marks the beginning of the Amalfi coast. Short rides take to Positano, Sorrento, Pompei, Herculaneum, Paestum, Vesuvius, or by boat, the islands of Capri, Ischia, and Procida. Velia (the ancient "Elea" of Zeno and Parmenide) is a hundred kilometers farther down along the coast. Student Fee: 1500 dollars Student fee include accommodations (arranged by the school), meals, one day of excursion, and a copy of the proceedings of the school. Transportation is not included. A few scholarships are available for students who are otherwise unable to participate at the school, and who cannot apply for the grants offered by ESCA. The scholarship will partially cover lodging and living expenses. Day time: 3 hour in the morning, three hour in the afternoon. Day free: One day with an excursion of the places around. AIMS: The aim of this school is to present the experiments, the theories and the perspectives of acoustic phonetics, as well as to discuss recent results in the speech literature. The school aims to provide a background for further study in many of the fields related to speech science and linguistics, including automatic speech recognition. The school will bring together leading researchers and selected students in the field of speech science and technology to discuss and disseminate the latest techniques. The school is devoted to an international audience and in particular to all students and scientists who are working on some aspects of speech and want to learn other aspects of this discipline. MAJOR TOPICS The school will cover a number of broad themes relevant to speech, among them: 1) Speech production and acoustic phonetics 2) Articulatory, acoustic, and prosodic features 3) Acoustic cues in speech perception 4) Models of speech perception 5) Speech processing (Preprocessing algorithms for Speech) 6) Neural Networks for automatic speech recognition 7) Multi-modal speech recognition and recognition in adverse environments. 8) Speech to speech translation (Vermobil and CSTAR projects) 9) Applications (Foreign Language training aids, aids for handicapped, ....). 10) Stochastic Models and Dialogue systems FORMAT The meeting will follow the usual format of tutorials and panel discussions together with poster sessions for contributed papers. The following tutorials are planned: ABEER ALWAN UCLA University (CA) USA "Models of Speech Production and Their Application in Coding and Recognition" ANDREA CALABRESE University of Connecticut (USA) "Prosodic and Phonological Aspects of Language" GERARD CHOLLET CNRS - ENST France ALISP, Speaker Verification, Interactive Voice Servers" RENATO DE MORI Universite d' Avignon, France "Statistical Methods for Automatic Speech Recognition" M. GABRIELLA DI BENEDETTO Universita' degli Studi di Roma "La Sapienza", Rome, Italy ``Acoustic Analysis and Perception of Classes of Sounds (vowels and consonants)" BJORN GRANSTROM Royal Institute of Technology (KTH) Sweden "Multi-modal Speech Synthesis with Application" JEAN P. HATON Universite Henri-Poincare, CRIN-INRIA, France "Neural Networks for Automatic Speech Recognition" HYNEK HERMANSKY Oregon Graduate Institute, USA "Goals and Techniques of Speech Analysis" JOHN OHALA University of California at Berkeley (CA) USA "Articulatory Constraints on Distinctive Features" JEAN SYLVAIN LIENARD LIMSI-CNRS, France "Speech Perception, Voice Perception" "Beyond Pattern Recognition" PROCEEDINGS The proceedings will be published in the form of a book containing tutorial chapters written by the lecturers and possibly shorter papers from other participants. One free copy of the book will be distributed to each participant. LANGUAGE The official language of the school will be English. POSTER SUBMISSION There will be a poster session for contributed presentations from participants. Proposals consisting of a one page abstract for review by the organizers should be submitted with applications. DURATION Participants are expected to arrive in time for the evening meal on Sunday 4th October and depart on Tuesday 15th October. Sessions will take place from Monday 5th-Wednesday 14th. COST The cost per participant of 1.500 $ dollars covers accommodation (in twin rooms), meals for the duration of the course, and one day of excursion. -- A supplement of 40 dollars per night should be paid for single room. Payment details will be notified with acceptance of applications. GRANTS -- A few ESCA grants are available for participants (which cover tuition and, maybe, part of the lodging). See http://ophale.icp.inpg.fr/esca/grants.html for further information. Individual applications for grants should be sent to Wolfgang Hess by e-mail: wgh at sunwgh.ikp.uni-bonn.de ELIGIBILITY The school is open to all suitably qualified scientists from around the world. APPLICATION PROCEDURE: Important Date: Application deadline: May 15 1998 Notification of acceptance: May 30 1998 Registration fee payment deadline: July 10 1998 People with few years of experience in the field should include a recommendation letter of their supervisor or group leader Places are limited to a maximum of 60 participants in addition to the lecturers. These will be allocated on a first come, first served basis. ************************************************************************** APPLICATION FORM Title:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Family Name:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Other Names:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Name to appear on badge:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Mailing Address (include institution or company name if appropriate): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Phone:^^^^^^^^^^^^^^^^^^^^^^Fax:^^^^^^^^^^^^^^^^^^^ E-mail:^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Date of Arrival : Date of Departure: Will you be applying for a ESCA grant ? yes/no* *(please delete the alternatives which do not apply) Will you be applying for a scholarship ? yes/no* *(please delete the alternatives which do not apply) *(please include in your application a justification for scholarship request) ***************************************************************** Please send the application form together the recommendation letter by electronic mail to: iiass at tin.it, subject: summer school; or by fax: +39 89 761 189 (att.ne Prof. M. Marinaro) or by ordinary mail to the address below: IIASS Via Pellegrino 19, I84019 Vietri sul Mare (Sa) Italy For further information please contact: Anna Esposito International Institute for advanced Scientific Studies (IIASS) Via Pellegrino, 19, 84019 Vietri sul Mare (SA) Italy Fax: + 39 89 761189 e-mail: annesp at vaxsa.csied.unisa.it ================== RFC 822 Headers ================== From iiass at tin.it Wed Feb 18 09:56:12 1998 From: iiass at tin.it (IIASS) Date: Wed, 18 Feb 1998 15:56:12 +0100 Subject: call Message-ID: <34EAF68C.2DF0@tin.it> From lek at cict.fr Thu Feb 19 10:02:23 1998 From: lek at cict.fr (Sovan LEK) Date: Thu, 19 Feb 1998 16:02:23 +0100 Subject: Neural Networks Workshop Message-ID: <1.5.4.32.19980219150223.00aec2b4@mail.cict.fr> INTERNATIONAL WORKSHOP ON APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS TO ECOLOGICAL MODELLING (2nd circular) 14-17 December 1998, Toulouse (FRANCE) Local Organizing Committee: Dr. Sovan Lek, CESAC, UMR 5576 du CNRS, UPS, B?t IVR3, 118 route de Narbonne, F-31062 Toulouse cedex 4, France Phone: 33-5 61 55 86 87 Fax: 33-5 61 55 60 96 E-mail: lek at cict.fr Dr. Jean-Fran?ois Gu?gan, ORSTOM, D?partement Biologie, Ecologie & Evolution, Laboratoire d'Hydrobiologie marine et Continentale, Universit? de Montpellier II (USTL), C.C. 093, place E. Bataillon, 34095 Montpellier cedex 05, France. Phone: 33 4 67 14 37 51 Fax : 33 4 67 14 46 46 E-mail : guegan at crit.univ-montp2.fr BACKGROUND You are cordially invited to attend the first "International Workshop on the Application of Artificial Neural Networks to Ecological Modelling" to be held at the Centre d'Ecologie des Syst?mes Aquatiques Continentaux in Toulouse (France). Toulouse is France's fourth largest city (650,350 people with suburbs), and is the European Space capital. It is situated on the Garonne river in very lush surroundings. The Toulouse of today is a lively university town (with more than 100,000 students) and has a rich medieval history. OBJECTIVES: Predictive modelling is a major concern in theoretical ecology, evolution and environmental sciences. Relationships between variables in natural systems are frequently non-linear, and thus conventional modelling tools could appear to be inappropriate to capture the complexity of such systems. This International Workshop will bring together theoretical and applied biological research, practitioners, and developers, as well as domain scientists from multiple ecological disciplines, for the presentation and exchange of current research and on concepts, tools and techniques for scientific and non linear statistical application in ecology, evolution and environmental sciences. The objectives are: ? To promote collaboration among scientists of different interested countries and research fields encouraging both teaching and research collaboration. ? To consider recent advances in Artificial Neural Networks to modelling data (identification, control, prediction, classification problems,...). INVITED SPEAKERS: Dr. S.E. Jorgensen (DK): Ecological Modelling: State of the Art. Pr. R. Tomassone (Fr): Dynamic systems and experimental planning: from data to modelling Dr. P. Bourret (Fr): Non -supervised classification: from observations to assumption. Dr. A. Teriokhin (Russia): On Neural Networks capable to realize evolutionarily optimal animal strategies of growth and reproduction in a seasonal environment. Pr. P. Auger (Fr): Non-linear Modelling in Ecology: from Individuals to Populations. Dr. F. Recknagel (Australia): Elucidation and Prediction of Aquatic Ecosystems by Artificial Neural Networks THEMES (you need to report your choice in the reply form, section Publication, which sub-theme?): o Pattern Recognition o Pattern Classification o Clustering and Classification o Diagnosis and Monitoring o Prediction and Control o Signal Processing o Temporal and Spatial Sequences PUBLICATION Final Instructions for Submission of Abstracts: o Abstract deadline: Abstracts must be submitted in English style, and received by the organisers before 1 April 1998. All abstracts will be refereed before final acceptance. o Please give complete name of your institution, followed by town and country. o The text of your abstract must be informative and contain: 1) a statement of the study's specific aims; 2) a statement of the method used; 3) a summary of results obtained; 4) a statement of conclusion. Avoid non-informative sentences. o Format: Abstracts must not exceed one page (format A4) and be sent directly by electronic mail to Drs. Lek or Gu?gan. If your abstract is too long it will be shortened by the organisers. The publication of the oral contributions is being considered. Please indicate if you are interested in submitting your paper for consideration in a special volume. Original papers will be published on merit in a special volume of the Springer Verlag Environmental Science Series. Other papers will form a special issue of Ecological Modelling. Both Editing Houses have been contacted and have accepted to co-edit these two special volumes. All contributions will be reviewed by at least two referees before acceptance for publication. SUBMISSION GUIDELINES OF PAPER(S) All contributions must be submitted by September 30th of 1998 to the Organizing Committee. Research papers should be up to 8,000 words long. All papers for publication should be sent by electronic mail (Ms-Word) or by post (4 hard-copies are needed) to Dr. Sovan Lek. All papers will be acknowledged of receipt. A notification of acceptance, modification or refusal will be sent by November 15th of 1998 to delegates having submitted a contribution with details given on which publication (hard volume of Springer Verlag or special issue of Ecological Modelling) the paper will be proposed. GENERAL INFORMATION: Languages: French and English will be the two official languages during the Conference, but abstracts, posters, and published papers will be exclusively written in English style. Venue: The Conference venue will be the Conference Centre of Toulouse University. This venue is ideal for a medium conference (about 150 people), with excellent, modern facilities which will allow for productive exchanges of ideas. Dates: Monday 14 December 1998 to Thursday 17 December 1998. Travel: Destination is Toulouse. Delegates must make their own travel arrangements to at least this destination. From dsilver at mgmt.dal.ca Fri Feb 20 18:17:40 1998 From: dsilver at mgmt.dal.ca (Daniel L. Silver) Date: Fri, 20 Feb 1998 23:17:40 +0000 Subject: Tech. Report - Task Rehearsal Method of Sequential Learning Message-ID: <199802210318.XAA24285@Snoopy.UCIS.Dal.Ca> Dear colleagues, the following TR is now available: "The Task Rehearsal Method of Sequential Learning" Department of Computer Science Univeristy of Western Ontario Technical Report # 517 Daniel L. Silver and Robert E. Mercer Abstract An hypothesis of functional transfer of task knowledge is presented that requires the development of a measure of task relatedness and a method of sequential learning. The "task rehearsal method" (TRM) is introduced to address the issues of sequential learning, namely retention and transfer of knowledge. TRM is a knowledge based inductive learning system that uses functional domain knowledge as a source of inductive bias. The representations of successfully learned tasks are stored within domain knowledge. "Virtual examples" generated by domain knowledge are rehearsed in parallel with the each new task using either the standard multiple task learning (MTL) or the $\eta$MTL neural network methods. The results of experiments conducted on a synthetic domain of seven tasks demonstrate the method's ability to retain and transfer task knowledge. TRM is shown to be effective in developing hypothesis for tasks that suffer from impoverished training sets. Difficulties encountered during sequential learning over the diverse domain reinforce the need for a more robust measure of task relatedness. ---------------------------------------------------------------------- Comments are welcome! Download sites: http://www.csd.uwo.ca/~dsilver/trmpaper.ps or http://www.csd.uwo.ca/~dsilver/trmpaper.ps.Z ////////////////////////////////////////////////////////////////////// Daniel L. Silver CogNova Technologies Phone: (902) 582-7558 1226 J.Jordan Road Fax: (902) 582-3140 Canning,Nova Scotia Dal.U: (902) 494-1813 Canada B0P 1H0 Email: dsilver at mgmt.dal.ca Homepage: http://www.meadoworks.ns.ca/cognova /////////////////////////////////////////////////////////////// From marwan at ee.usyd.edu.au Mon Feb 23 04:28:33 1998 From: marwan at ee.usyd.edu.au (Marwan Jabri) Date: Mon, 23 Feb 1998 20:28:33 +1100 (EST) Subject: Post-doctoral fellowship Message-ID: Post-Doctoral Fellow Department of Electrical Engineering The University of Sydney Applications are invited for Post-doctoral fellow position funded by an Australian Research Council project grant. The three-year project aims at investigating computational models of the superior colliculus, the implementation of the models in microelectronics and their integration in sensorimotor control systems. The fellow will join a group several academics and doctoral students working on biological models for sensorimotor control. The research is a collaboration between M. Jabri (Elec. Eng., Sydney University) S. Carlile (Physiology, Sydney University) and T. Sejnowski (Salk Institute). The fellow will be based in Sydney, but will be expected to travel and spend several weeks every year at the Salk Institute. Applicants would have completed (or about to complete) their PhD in electrical, computer or related engineering or science discipline and have demonstrated research capacity in the area of neuromorphic engineering, computational neurobiology or microelectronics. Appointment will be made initially for a period of one year, and renewable for another two years subject to progress. Expected starting date in May, 1998. Closing date: March 20, 1998 Salary range: A$34k-46k To apply, send letter of application, CV and names, fax and email of three referees to M. Jabri Tel (+61-2) 9351 2240, Fax (+61-2) 9351 7209, Email: marwan at sedal.su.oz.au From Nicolino.Pizzi at nrc.ca Mon Feb 23 10:12:54 1998 From: Nicolino.Pizzi at nrc.ca (Pizzi, Nicolino) Date: Mon, 23 Feb 1998 10:12:54 -0500 Subject: Postdoctoral Research Opportunity - University of Manitoba Message-ID: POSTDOCTORAL RESEARCH OPPORTUNITY - COMPUTER ENGINEERING HYBRID KNOWLEDGE-BASED CLASSIFICATION OF VOLUMETRIC PATTERNS Pending final approval, a postdoctoral position is available within the Electrical and Computer Engineering Department to participate in an NSERC-funded strategic research project investigating hybrid knowledge-based classification of volumetric patterns. The position is for a one-year term with a possible one year renewal. The research project will be conducted in close collaboration with Prof. W. Pedrycz and Dr. N. Pizzi. Volumetric (three-dimensional) data are found in many application areas such as radar scans of meteorological formations. These data normally contain a number of three-dimensional regions of interest (ROI's) that belong to several classes. The classification of an ROI is determined by some well-established reference test. In the case of meteorological radar scans, the ROI's may be cloud formations that cause severe weather, the classes may be hail, heavy rain, wind, or tornadic events, and the reference test might be eye-witness accounts of the storm events. The intent of this project is to develop a comprehensive pattern recognition methodology aimed at such data and propose a suite of classification algorithms that can take a ROI and produce a classification outcome that matches the class to which it was assigned by the corresponding reference test. A number of factors can confound the classification process. It may become difficult to glean any discriminating features from volumetric data if it contains noise due to limitations of sensors, instrumentation, or the data acquisition process. Moreover, the ROI's may be extremely complex in nature. Several preprocessing methods are proposed in order to transform the original ROI in order to eliminate or diminish the effects of noise and/or reduce the dimensionality of the input space as well as focus the classification effort on the most significant features. The problem of identifying discriminating features is further aggravated by the fact that the accepted reference test itself may be imprecise or even unreliable. Finally, the volumetric data may be incomplete and sophisticated interpolation methods will be required to deal with missing values. Required background: - Recent Ph.D. graduate - Experience in C++ programming on UNIX systems - Knowledge of pattern recognition techniques Desired background: - Working knowledge of fuzzy systems, artificial neural networks, and data mining Please send a curriculum vitae, expression of interest (including earliest start date), and the names and e-mail addresses (or telephone numbers) of two references to N. Pizzi at pizzi at ibd.nrc.ca. Your curriculum vitae should include a list of recent publications. Please outline your interest in this project, how it is related to work that you have done, and what special expertise you would bring to the project. Nicolino Pizzi, Ph.D. Associate Research Officer Institute for Biodiagnostics National Research Council 435 Ellice Avenue Winnipeg MB R3B 1Y6 CANADA From Shaogang.Gong at dcs.qmw.ac.uk Mon Feb 23 11:35:53 1998 From: Shaogang.Gong at dcs.qmw.ac.uk (Shaogang Gong) Date: Mon, 23 Feb 1998 16:35:53 +0000 (GMT) Subject: Post-Doc Research in Face and Gesture Recognition Message-ID: <199802231635.QAA01578@seans-pc.dcs.qmw.ac.uk> Post-doctoral Research in Visual Learning for Face Gesture Recognition and Intention Prediction for Visually Mediated Interaction Department of Computer Science Queen Mary and Westfield College, University of London, UK Applications are invited for a post-doctoral research assistant in the Dept of Computer Science at Queen Mary and Westfield College to work on a new EPSRC research project. The successful candidate will be undertaking novel research in statistical learning methods, real-time view-based face and gesture representation and recognition, data fusion for active camera control and intention prediction. Our lab is equipped with extensive real-time image capturing and tracking systems including Pentium and Pentium II real-time active camera systems, SGI O2 systems, Datacube MaxVideo 250 and MD1/2GX, AMT DAP 500 parallel processors, with numerous SPARC workstations. The candidate should have experience in computer vision and neural network research. In particular, any experience in view-based representation and statistical learning theories would be an advantage (more details can be found on the Web at http://www.dcs.qmw.ac.uk/research/vision/ ). You should also be competent in programming C under X and NT windows and using Unix systems. You will be expected to start as soon as possible on a 2 year contract. Salary in range of 17,293-22,237 pounds per annum inclusive, depending on age and experience. The project is to be closely collaborated with a concurrent project at Sussex COGS involving Prof Hilary Buxton and Dr Jonathan Howell. The project will also involve the BT and BBC R&Ds. The Department of Computer Science at QMW has extensive experience in object detection, tracking and recognition for dynamic scene understanding in image sequences. Recent and current funded projects relevant to this research include ESPRIT II VIEWS for visual interpretation and evaluation of wide area scenes, RACE II Mona Lisa for virtual studios, ESPRIT III FIVE working group for immersive virtual environment, EPSRC IMV Initiative on real-time detection, tracking and recognition of moving people, EC HCM Network PAMONOP on parallel modelling of neural operators for pattern recognition, a BT Short Term Research Fellowship Scheme on real-time view-based estimation of head pose, and the EPSRC/BBC CASE program for studies on the visual segmentation and tracking of moving actors in studio environment. For further details and an application form please phone +(44) (0)171-975-5171 (24 hour answer-phone) quoting Ref. number 97135 or send an email request to sgg at dcs.qmw.ac.uk. Completed applications and CV should be returned by 20/03/98 to: The Recruitment Coordinator, Personnel Office, Queen Mary and Westfield College, Mile End Road, London, E1 4NS. QMW: WORKING TOWARDS EQUAL OPPORTUNITIES From hollidie at pcmail.aston.ac.uk Mon Feb 23 15:59:33 1998 From: hollidie at pcmail.aston.ac.uk (Ian Holliday) Date: Mon, 23 Feb 1998 15:59:33 GMT+1 Subject: postdoc + PhD Studentship: neural nets and MEG Message-ID: Postdoctoral Research Fellowship and Graduate Studentship Neural Computing Research Group Aston University Birmingham B4 7ET, U.K. The Neural Computing Research Group at Aston is looking for a highly motivated individual for a 3 year postdoctoral research position in the area of `Signal and Pattern Processing of Magnetoencephalographic Data`. The project will study single and multichannel data obtained from an Aston magnetoencephalography (MEG) facility for signal enhancement and processing. The MEG research group is engaged in basic studies of normal and abnormal vision, epilepsy, and gamma- band activity; and in clinically related studies on the localisation of eloquent cortex in pre-surgical investigations. Advanced pattern processing techniques are needed, including artificial neural network methods for enhancement, clustering, visualisation, segmentation and classification. Potential candidates should have strong mathematical and computational skills and an interest in the application of these skills to basic and clinically related neurosciences research. Knowledge of linear and nonlinear signal processing or expertise in biosignal analysis would be useful. The successful candidate will also have an opportunity to contribute to experimental work in MEG. A supported studentship is also available in the same area. Further information on this and other positions can be obtained from http://www.ncrg.aston.ac.uk/. Salaries for the Fellowship will be at or above point 6 on the RA 1A scale, currently 16927 UK pounds. These salary scales are subject to annual increments. The studentship is supported at the standard UK rate for PhD students. If you wish to be considered for this position, please send a full CV and publications list, together with the names of 3 referees, to: Prof David Lowe or Dr. Ian Holliday Neural Computing Research Group Psychology Institute Aston University Birmingham B4 7ET, U.K. Tel: 0121 333 4631 tel: 0121 359 3611 ext 4930 Fax: 0121 333 4586 fax: 0121 359 3257 e-mail: d.lowe at aston.ac.uk email: hollidie at aston.ac.uk Email submission of postscript files is welcome. Closing date: 10 April 1998. From ericr at mech.gla.ac.uk Tue Feb 24 07:20:03 1998 From: ericr at mech.gla.ac.uk (Eric Ronco) Date: Tue, 24 Feb 1998 12:20:03 GMT Subject: Constructing a Controller network Message-ID: <199802241220.MAA05138@googie.mech.gla.ac.uk> Dear all, Just to let you know of the http availability of a new technical report entitled "Two Controller Networks Automatically Constructed Through System Linearisations and Learning" (it is a compressed file. Please, gunzip the file to view or print it). It is available (among others) at: http://www.mech.gla.ac.uk/~ericr/research.html or at http://www.mech.gla.ac.uk/~yunli/reports.htm This report has been written by Eric Ronco and Peter J. Gawthrop. Its title is Two Controller Networks Automatically Constructed Through System Linearisations and Learning. The keywords are: controller network, off-equilibrium linearisation, learning Abstract: This study aims at comparing two linear controller networks as well as two methods to automaticly construct their architecture. The general idea of a controller network is to use a number of linear local controllers valid for different operating regions of a non-linear system. The two controller networks studied here are the ""Clustered Controller Network'' (CCN) and the ""Model-Controller Network'' (MCN). They differ by the method used for the selection of the controllers at each instant. In the CCN, the controllers are selected according to a spatial clustering of the operating space whereas in the MCN the selection of the controllers depends of the performance of the model associated to each local controller. The two different methods to construct the architecture of these controller networks are the ""multiple off-equilibrium system linearisations'' and the ""learning control through incremental network construction''. It is shown that these network construction methods make the two controller networks general and systematic non-linear controller design approaches. However, the selection method applied by the MCN is preferable for control purposes since it is directly related to the controller capability unlike the method implemented by the CCN. In other hand, the flexibility of the controller selection applied by the MCN makes accurate local control learning difficult to achieve. A mixture of this two methods of controller selection should remove these problems. Regards, Eric Ronco ----------------------------------------------------------------------------- | Eric Ronco | | Dt of Mechanical Engineering E.mail : ericr at mech.gla.ac.uk | | James Watt Building WWW : http://www.mech.gla.ac.uk/~ericr | | Glasgow University Tel : (44) (0)141 330 4370 | | Glasgow G12 8QQ Fax : (44) (0)141 330 4343 | | Scotland, UK | ----------------------------------------------------------------------------- From thimm at idiap.ch Tue Feb 24 12:37:14 1998 From: thimm at idiap.ch (Georg Thimm) Date: Tue, 24 Feb 1998 18:37:14 +0100 Subject: Events on Neural Networks, Vision and Speech Message-ID: <199802241737.SAA13879@rotondo.idiap.ch> ----------------------------------------- WWW page for Announcements of Conferences, Workshops and Other Events on Neural Networks, Vision and Speech ----------------------------------------- This WWW page allows you to look up and enter announcements for conferences, workshops, and other events concerned with neural networks, vision, speech, and related fields. ------------------------------------------------------------------------- Search and lookup can be restricted to events with forthcoming deadlines! ------------------------------------------------------------------------- The event lists, which is updated almost daily, contains currently more than 200 forthcoming events, and can be accessed via the URL: http://www.idiap.ch/~thimm The entries are ordered chronologically and presented in a format for fast and easy lookup of: - the date and place of the event, - the title of the event, - a contact address (surface mail, email, ftp, and WWW address, as well as telephone or fax number), and - deadlines for submissions, registration, etc. - topics of the event Conference organizers are kindly asked to enter their conference into the database. The list is in parts published in the journal Neurocomputing by Elsevier Science B.V. Information on passed conferences are also available. Kind Regards, Georg Thimm P.S. Please distribute this announcement to related mailing lists. Comments and suggestions are welcome! From Friedrich.Leisch at ci.tuwien.ac.at Wed Feb 25 10:00:42 1998 From: Friedrich.Leisch at ci.tuwien.ac.at (Friedrich Leisch) Date: Wed, 25 Feb 1998 16:00:42 +0100 Subject: CI BibTeX Collection -- Update Message-ID: <199802251500.QAA04534@galadriel.ci.tuwien.ac.at> The following volumes have been added to the collection of BibTeX files maintained by the Vienna Center for Computational Intelligence: Machine Learning 28-30 Neural Networks 10/4-9, Neural Computation 9/6-10/2, Neural Processing Letters 5/3-7/2 Most files have been converted automatically from various source formats, please report any bugs you find. The complete collection can be downloaded from http://www.ci.tuwien.ac.at/docs/ci/bibtex_collection.html ftp://ftp.ci.tuwien.ac.at/pub/texmf/bibtex/ Best, Fritz Leisch ------------------------------------------------------------------ Friedrich Leisch Institut f?r Statistik Tel: (+43 1) 58801 4541 Technische Universit?t Wien Fax: (+43 1) 504 14 98 Wiedner Hauptstra?e 8-10/1071 Friedrich.Leisch at ci.tuwien.ac.at A-1040 Wien, Austria http://www.ci.tuwien.ac.at/~leisch PGP public key http://www.ci.tuwien.ac.at/~leisch/pgp.key ------------------------------------------------------------------ From kia at particle.kth.se Fri Feb 27 10:22:03 1998 From: kia at particle.kth.se (Karina Waldemark) Date: Fri, 27 Feb 1998 16:22:03 +0100 Subject: Neural Network Workshop June-98 Message-ID: <34F6DA1B.D4C49ADB@particle.kth.se> ------------------------------------------------------------------------ VI-DYNN'98 Workshop on Virtual Intelligence - Dynamic Neural Networks Stockholm June 22-26, 1998 Royal Institute of Technology, KTH, Stockholm, Sweden ------------------------------------------------------------------------ VI-DYNN'98 Web: http://www.particle.kth.se/vi-dynn Abstracts due to: March 20, 1998 ****** papers up to 20 pages can be accepted ******* Deliver camera-ready manuscripts at registration Papers will be published by SPIE Papers will be considered for further publication in IEEE Transactions on Industrial Applications Contact: Thomas Lindblad (KTH) - Conf. Chairman email: lindblad at particle.kth.se Phone: [+46] - (0)8 - 16 11 09 ClarkS. Lindsey (KTH) - Conf. Secretary email: lindsey at particle.kth.se Phone: [+46] - (0)8 - 16 10 74 Switchboard: [+46] - (0)8 - 16 10 00 Fax: [+46] - (0)8 - 15 86 74 -------------------------------------------------------------------- Tentative Programme for VI-DYNN'98 Workshop -------------------------------------------------------------------- Monday PCNN tutorial Morning Session chair: Thomas Lindblad 1. Introduction 2. PCNN Theory 3. PCNN Image Processing 4. The PCNN Kernel 5. Target Recognition 6. Dealing with Noise Afternoon Session chair: Jason Kinser 7. Feedback 8. Object Isolation 9. Foveation 10. Image Fusion 11. Hardware Realization 12. Miscellaneous Applications and Summary Tuesday Session: Neurodynamics Session chair: Hans Liljenstrom Keynote Talk: Hans Liljenstrom, Control and amplification of cortical neurodynamics I. Opher (Tel Aviv), Data Clustering via Temporal Segmentation of Spiking Neurons Session: Electronic Nose Session chair: Hans Liljenstrom J. Waldemark (KTH) Neural Networks and PCA for determing ROI in sensory data preprocessing M. L. Padgett (Auburn U.) PCNN factoring and automated outlier detection T. A. Roppel (Auburn U.) Sensory plane analog/VLSI for interfacting sensor arrays to neural networks Session: Models of neural systems Session chair: Hans Liljenstrom Session: PCNN Applications Session chair: J. Kinser Keynote Talk: J. Kinser, Kurt Moore (Los Alamos) , 1-D Peak Fitting using PCNN J. Karvonen (Finnish Inst. Of Marine Research), PCNN for sea-ice classification from RADARSAT SAR-images V.Becanovic (KTH), PCNN for License Plate Identification O.J.Goeboden (Ostfold ), Using PCNN for SONAR Images Panel Discussion: Wednesday Session: Signals from the Brain Session chair: John Taylor Keynote Talk: JG Taylor (Kings College), Analysing Non-invasive Brain Images E. Oja, ICA Analysis of MEG and EEG Signals A. Villa, Single Cell Measurements from Behaving Animals B. Krause (Juelich), PET and Structural Brain Modelling B. Gulyas (Karolinska Inst.), B. Horwitz (NIH), Structural Modelling of PET Data A. Ioannides (Julich), MEG & the Brain Panel Discussion: Session: Defense Applications Session chair: K. Waldemark Keynote Talk: Natalie Clark, Micro-Optical Silicon Eye Authors: Natalie Clark, John Comtois, Adrian Micalicek, and Paul Furth Air Force Research Laboratory, Kirtland AFB NM 87117 I. Renhorn, (Defence Research Establishment), General Specifications for ATR J.L. Johnson J. Kinser, Pulse Couple Spiral Image Fusion Th. Lindblad, Smart sensors inspired by processes in the primate visual cortex Panel Discussion: Thursday Session: Hardware Session chair: Natalie Clark Keynote Talk: J. L. Johnson, Test Results for a 32x32 PCNN Array, J. L. Johnson, R. F Sims, and T. Branch. J. Johnson (MICOM), PCNN Chip Development J. Waldemark (KTH), PCNN in FPGA unknown (John Hopkins), PCNN Hardware IBM ZISC, Zero instruction set computer, Application for noise reduction Trento TOTEM, The Reactive Tabu Search Session: PCNN & other Algorithms Session chair: J. Waldemark G. Szekely, Adaptive PCNN J. Kinser M.Kaipainen, Sea Ice Classification using PCNN J. Johnson, PCNN Theory: State of the art Panel Discussion: Friday Tutorial Session: Virtual Intelligence Session chair: Mary Lou Padgett Theme: Virtual Intelligence Track AM Opening Remarks Keynote Talk: M. L. Padgett, Overview of Virtual Intelligence Motivational material, update on funding, hot topics, why important, how interacts with PCNN, etc. Tutorial: Overview of Neural Networks Fuzzy Systems Evolutionary Computation Rough Sets Virtual Reality Electronic Nose Description of topics, and pointers to websites and printed material for more detailed info e.g. Handbook on Applications of Computational Intelligence Eds. Padgett, Karayiannis, Zadeh CRC Press 1999 and Handbook on NeuroControl Eds. Jorgensen, Werbos and Padgett CRC Press 1999 Session: NNW Applications Session chair: Mary Lou Padgett K. Waldemark (KTH), Sleep Apnea R. Curbelo (Univ. of Uraguay), Fingerprint Identification using Neural Networks D. A. Salo (Ostfold), Neural Networks for Fingerprint identification T. Sanne (Ostfold), Neural Network for Identification Based on the Iris J. Hansen (Ostfold), Facial Recognition using Neural Networks A. Sokolov (Protvino), Hadron Energy Reconstruction by Combined Calorimeter using Neural Network L. Hildingsson,(SKI) Fuel Assembly Assessment from Digital Image Analysis Lunch and Virtual Intelligence Standards Working Group Meeting From ngoddard at psc.edu Fri Feb 27 15:14:50 1998 From: ngoddard at psc.edu (Nigel Goddard) Date: Fri, 27 Feb 98 15:14:50 -0500 Subject: Faculty Positions in Informatics at University of Edinburgh Message-ID: <16628.888610490@pscuxc.psc.edu> LECTURESHIPS IN INFORMATICS University of Edinburgh We invite applications for six lectureships Informatics is the study of the structure, behaviour, and interactions of both natural and artificial computational systems. As part of a major expansion of our work in this area, we invite applications for up to six lectureships in Informatics. Successful candidates will add to our existing strengths in research and teaching, encourage the integration of their own research with that of others, and contribute to the development of Informatics at Edinburgh. We seek candidates, working in any area of Informatics, who will contribute to Edinburgh's excellence in teaching and research. Areas of particular interest for these appointments include: cognition, computation and human learning; computational and cognitive aspects of neuroscience and neural networks; computational and cognitive models of human communication; computational complexity; computational vision; design and analysis of integrated hardware and software computer systems; distributed systems; network and mobile computing; evolutionary systems; formal semantics of natural language; knowledge representation and practical reasoning; mobile robotics. Permanent appointments may be available for suitably qualified candidates, otherwise appointments will be for five years in the first instance. Further particulars including details of the application procedure are available on-line: http://www.dcs.ed.ac.uk/ipu/particulars/ or from the Personnel Department: Recruitment Personnel Office, The University of Edinburgh, 1 Roxburgh Street, Edinburgh EH8 9TB email personnel at ed.ac.uk Tel: +44 (0) 131-650-2511 (24 hour answering service). Fax +44 (0) 131-650-6509 Application forms should be obtained from the personnel department, which may be contacted by phone, fax, or post, or by completing this form: http://www.ed.ac.uk/~persnnel/enqentry.cgi Please quote Reference 896095WW Closing date: 9th March 1998 Further information about Informatics at Edinburgh may be obtained from our WWW page: http://www.dcs.ed.ac.uk/ipu/ or from the Head of Informatics: Professor Michael Fourman Department of Computer Science, JCMB, King's Buildings, Mayfield Road, Edinburgh EH9 3JZ Telephone +44 (0) 131 650 5197 e-mail Informatics at ed.ac.uk