From mike at soc.plym.ac.uk Tue Jan 2 06:47:15 2001 From: mike at soc.plym.ac.uk (Mike Denham) Date: Tue, 02 Jan 2001 11:47:15 +0000 Subject: Position in Auditory Psychophysics/Computational Neuroscience Message-ID: <200101021147.LAA15045@hebe.soc.plym.ac.uk> University of Plymouth, UK School of Computing, Centre for Neural and Adaptive Systems Plymouth Institute of Neuroscience Readership / Professorship in Auditory Psychophysics/Computational Neuroscience Applications are invited for a permanent academic position in the School of Computing. The successful candidate will have a strong current research activity in the area of auditory psychophysics, with an interest in theoretical and computational modelling of the auditory system. He/she will join the Centre for Neural and Adaptive Systems, a well-established research group with an international reputation, and the newly formed Plymouth Institute of Neuroscience. For appointment as a Reader or Professor, it will be necessary to meet the criteria set out by the University's Professorial Appointments Committee, with respect to academic standing and achievements. Further information about the post can be obtained via e-mail or telephone, from Professor Mike Denham (mike at soc.plym.ac.uk; tel: +44 (0)1752 232547). Michael J Denham Invensys Professor of Neural and Adaptive Systems Centre for Neural and Adaptive Systems School of Computing University of Plymouth Plymouth PL4 8AA England tel: +44 1752 232541 fax: +44 1752 232540 e-mail: mike @soc.plym.ac.uk; mdenham at plym.ac.uk http://www.tech.plym.ac.uk/soc/research/neural/index.html From mike at soc.plym.ac.uk Tue Jan 2 06:43:40 2001 From: mike at soc.plym.ac.uk (Mike Denham) Date: Tue, 02 Jan 2001 11:43:40 +0000 Subject: Position in Neural Computation / Computational Neuroscience Message-ID: <200101021143.LAA15035@hebe.soc.plym.ac.uk> University of Plymouth, UK School of Computing Centre for Neural and Adaptive Systems Readership / Professorship in Neural Computation / Computational Neuroscience Applications are invited for a permanent academic position in the School of Computing of the University of Plymouth. The successful candidate will have a strong current research activity in the area of neural and adaptive computation and/ or computational neuroscience, and an interest in contributing to the further development of the academic work of the School in this area. He/she will join the Centre for Neural and Adaptive Systems, a well-established research group with an international reputation. For appointment as a Reader or Professor, it will be necessary to meet the criteria set out by the University's Professorial Appointments Committee, with respect to academic standing and achievements. Further information about the post can be obtained via e-mail or telephone, from Professor Mike Denham (mike at soc.plym.ac.uk; tel: +44 (0)1752 232547). Michael J Denham Invensys Professor of Neural and Adaptive Systems Centre for Neural and Adaptive Systems School of Computing University of Plymouth Plymouth PL4 8AA England tel: +44 1752 232541 fax: +44 1752 232540 e-mail: mike @soc.plym.ac.uk; mdenham at plym.ac.uk http://www.tech.plym.ac.uk/soc/research/neural/index.html From P.McKevitt at ulst.ac.uk Wed Jan 3 14:40:51 2001 From: P.McKevitt at ulst.ac.uk (Prof Paul Mc Kevitt) Date: Wed, 3 Jan 2001 19:40:51 +0000 (GMT) Subject: University of Ulster (Magee): 2 Research Studentships Message-ID: Research Studentships Intelligent Systems/Intelligent Digital MultiMedia Interfaces Faculty of Informatics Intelligent Digital MultiMedia Interfaces The University of Ulster invites applicants for the above full-time Research Studentship to be situated at the Magee College campus and held within the MultiMedia Systems and Artificial Intelligence research groups of the Faculty of Informatics. The focus of the research will be to investigate the integration of the computational processing of digital multimedia (e.g. spoken dialogue, natural language and visual advanced interfaces) incorporating the modelling of emotions and automated storytelling with application to e.g. intelligent web-browsing and medical informatics. The studentship consists of an annual maintenance allowance of 10,000 pounds and payment of fees for up to three years. The successful candidate will be registered on a programme of study leading, subject to satisfactory progress, to the award of the degree of Doctor of Philosophy. Applicants should hold a minimum of an upper second Bachelor's and/or Master's degree in intelligent digital multimedia, computer science, cognitive science or a related subject and have good experience in, and be prepared for, computer programming, scientific experimentation and the use of existing software tools. Further information is available from: Professor Paul Mc Kevitt, http://www.infc.ulst.ac.uk/staff/p.mckevitt E-mail: p.mckevitt at ulst.ac.uk Phone: (+44) 028 71375433 Faculty of Engineering Intelligent Systems Applications are invited for a full-time research studentship, to investigate the application of intelligent systems technology in bionics. The research project is specifically concerned with the application of intelligent techniques and evolvable hardware to the design of self-adaptive medical prosthetics. The project will be supervised by Professor Martin McGinnity and Dr. Liam Maguire, and will involve collaboration with medical practitioners. The student will be based in the Intelligent Systems Engineering Laboratory, in the Faculty of Engineering on the Magee campus of the University. The laboratory is currently the base for 16 researchers engaged in a range of projects in the general area of intelligent systems. Further information is available at http://isel.scim.ulst.ac.uk. The studentship consists of an annual maintenance allowance of 10,000 pounds and payment of fees for up to three years. The successful candidate will be registered on a programme of study leading, subject to satisfactory progress, to the award of the degree of Doctor of Philosophy. Interested applicants may arrange to visit the laboratory by telephoning for an appointment (tel + 44 028-71375616). Applicants should hold a minimum of an upper second class honours degree in electronics, computing or closely related discipline. Preference may be given to candidates with first class degrees or a postgraduate qualification. Application materials for either award are available from: Angela Rippey, Research Office, University of Ulster, Cromore Road, Coleraine. E-mail: a.rippey at ulst.ac.uk Fax: (+44) 028 70324905 Phone: (+44) 028 70324592 The closing date for receipt of completed applications is Tuesday 6 February 2001. also found at: http://jobs.ac.uk/jobfiles/HH159.html LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL Professor Paul Mc Kevitt Chair in Digital MultiMedia School of Computing & Electronics Faculty of Informatics University of Ulster, Magee College BT48 7JL, Derry (Londonderry) NORTHERN IRELAND E-mail: p.mckevitt at ulst.ac.uk WWW: http://www.infc.ulst.ac.uk/staff/p.mckevitt FaX: (+44) 28 71375470 Phone: (+44) 28 71375433 (Office MG-221) (+44) 28 71375382 (School Office) LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL From cindy at cns.bu.edu Thu Jan 4 09:37:52 2001 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Thu, 4 Jan 2001 09:37:52 -0500 Subject: Neural Networks 14(1) Message-ID: <200101041437.JAA23594@retina.bu.edu> NEURAL NETWORKS 14(1) Contents - Volume 14, Number 1 - 2001 ------------------------------------------------------------------ CONTRIBUTED ARTICLES: ***** Neuroscience and Neuropsychology ***** A pattern correlation model of vestibulo-ocular reflex habituation T.J. Anastasio ***** Mathematical and Computational Analysis ***** Optimal control by least squares support vector machines J.A.K. Suykens, J. Vandewalle, and B. DeMoor Signal estimation and denoising using VC-theory V. Cherkassky and X. Shao Incremental projection learning for optimal generalization M. Sugiyama and H. Ogawa Properties of incremental projection learning M. Sugiyama and H. Ogawa Error correcting memorization learning for noisy training examples A. Nakashima, A. Hirabayashi, and H. Ogawa A real-coded genetic algorithm for training recurrent neural networks A. Blanco, M. Delgado, and M.C. Pegalajar A synthesis procedure for associative memories based on space-varying cellular neural networks J. Park, H.-Y. Kim, Y. Park, and S.-W. Lee The bifurcating neuron network 1 G. Lee and N.H. Farhat ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 or 660 SEK or Y 15,000 [including Neural Networks 2,000 entrance fee] or $55 (student) 460 SEK (student) Y 13,000 (student) [including 2,000 entrance fee] ----------------------------------------------------------------------------- membership without $30 200 SEK not available to Neural Networks non-students (subscribe through another society) Y 5,000 (student) [including 2,000 entrance fee] ----------------------------------------------------------------------------- Institutional rates $1132 2230 NLG Y 149,524 ----------------------------------------------------------------------------- Name: _____________________________________ Title: _____________________________________ Address: _____________________________________ _____________________________________ _____________________________________ Phone: _____________________________________ Fax: _____________________________________ Email: _____________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number ____________________________ expiration date ________________________ INNS Membership 19 Mantua Road Mount Royal NJ 08061 USA 856 423 0162 (phone) 856 423 3420 (fax) innshq at talley.com http://www.inns.org ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership c/o Professor Tsukada Faculty of Engineering Tamagawa University 6-1-1, Tamagawa Gakuen, Machida-city Tokyo 113-8656 Japan 81 42 739 8431 (phone) 81 42 739 8858 (fax) jnns at jnns.inf.eng.tamagawa.ac.jp http://jnns.inf.eng.tamagawa.ac.jp/home-j.html ----------------------------------------------------------------- From Thomas.Trappenberg at psy.ox.ac.uk Thu Jan 4 11:17:27 2001 From: Thomas.Trappenberg at psy.ox.ac.uk (Thomas Trappenberg) Date: Thu, 4 Jan 2001 16:17:27 -0000 Subject: Postdoctoral Position and Studentship in Computational Neuroscience in Oxford Message-ID: <000601c07669$d4f45580$200f4381@cogneuro.ox.ac.uk> Dear Colleagues, I want to bring to your attention an opening of a research position in computational neuroscience in Oxford. Further details are attached below. In addition, there is a full Studentship for UK citizens (or a partial Studentship for other nationalities) in our D.Phil program available. However, a rapid response to this Studentship (within two days) is required. Please write directly to Prof. Edmund Rolls (edmund.rolls at psy.ox.ac.uk). Regards, Thomas Trappenberg UNIVERSITY OF OXFORD DEPARTMENT OF EXPERIMENTAL PSYCHOLOGY Centre for Computational Neuroscience Postdoctoral post in Neural Computation Academic-Related Research Staff Grade 1A: Salary 16,775 - 25,213 A post is available as part of a long-term research programme for research combining neurophysiological and computational approaches to brain function. The post is to work with Prof E T Rolls and colleagues to develop and apply information theoretic and statistical methods to analyse data acquired from simultaneously recorded neurons, and to assist in the development of software to help acquire such data. The postholder will contribute to research aimed at understanding how information is represented in the primate visual system (see Appendix 2 of Rolls and Treves, 1998). Applicants should have a degree in a relevant scientific discipline (e.g. maths, physics, statistics or a neuroscience-related discipline), be able to program in C, and willing to work on Unix and PC systems. The appointee will be working collaboratively as part of a team. The appointment will be on the RS1A (postdoctoral) scale or RS1B scale (according to experience) for three years in the first instance. Before submitting an application, candidates should obtain further particulars from the Administrator, Department of Experimental Psychology, South Parks Road, Oxford OX1 3UD (email applications at psy.ox.ac.uk) or telephone 01865 271399 quoting Ref: CQ/etr/036 (neurophysiology post) or 037 (computational post). Further information on the research group may be found on the web-site http://www.cns.ox.ac.uk/ and on the Department at http://www.psych.ox.ac.uk/. Initial scientific enquiries about the post may be directed to Professor Edmund T. Rolls (email: edmund.rolls at psy.ox.ac.uk), who will be pleased to send papers to prospective applicants. From ckiw at dai.ed.ac.uk Thu Jan 4 11:27:42 2001 From: ckiw at dai.ed.ac.uk (Chris Williams) Date: Thu, 4 Jan 2001 16:27:42 +0000 (GMT) Subject: 2 Research fellow positions at the University of Edinburgh, UK Message-ID: The University of Edinburgh seeks to hire two research fellows in the area of astronomical databases/datamining. The position within the Division of Informatics will be based in the Institute for Adaptive and Neural Computation, where research in machine learning/probabilistic modelling is led by Dr. Chris Williams, Dr. David Barber (joining Spring 2001) and Prof. Chris Bishop. See http://www.roe.ac.uk/wfau/vacancy.html for further particulars on the jobs. Informal questions and requests for information can be sent to c.k.i.williams at ed.ac.uk Apologies if you receive this message multiple times. Dr Chris Williams c.k.i.williams at ed.ac.uk Institute for Adaptive and Neural Computation Division of Informatics, University of Edinburgh 5 Forrest Hill, Edinburgh EH1 2QL, Scotland, UK fax: +44 131 650 6899 tel: (direct) +44 131 651 1212 (department switchboard) +44 131 650 3090 http://anc.ed.ac.uk/ ------------------------------------------------------------------------- Two Postdoctoral Research Fellowships in Astronomical Databases and Datamining The University of Edinburgh seeks two postdoctoral researchers to join an interdisciplinary team working on astronomical databases and datamining. This new initiative brings together wide field astronomers from the Institute for Astronomy, computer scientists/applied mathematicians from the Division of Informatics and high performance computing specialists from the Edinburgh Parallel Computing Centre, to address issues ranging from the design and implementation of large astronomical databases to the use of machine learning and computational geometry techniques to characterise their contents. Candidates with a background in either astronomy or informatics are encouraged to apply. The posts are tenable for 2 years from 1 March 2001 (or soon thereafter), although this research is likely to be supported in the longer term through the Astro-Grid project expected to be funded by the UK Government's e-science initiative. The salary for each post will be on the AR1A (16,775-25,213 pounds pa) or AR2 (23,256 - 30,967 pounds pa) salary scale depending on age, qualifications and experience. Further particulars, including details of the application procedure, should be obtained from the Personnel Department, 9-16 Chambers Street, Edinburgh EH8 9TB or Tel: 0131 650 2511 (24 hour answering service) or www.personnel.ed.ac.uk/recruit.htm (advert will be posted in week beginning 8 January). The further particulars are also available at http://www.roe.ac.uk/wfau/vacancy.html. Closing date for receipt of applications is 31 January 2001. We cannot guarantee to consider late applications. Please quote ref 307014 (Institute for Astrnomy) or ref 307016 (Division of Informatics). Informal enquiries can be made to Dr Bob Mann (rgm at roe.ac.uk) in the Institute for Astronomy or Dr Chris Williams (c.k.i.williams at ed.ac.uk) in the Division of Informatics. From nello at dcs.rhbnc.ac.uk Thu Jan 4 18:36:14 2001 From: nello at dcs.rhbnc.ac.uk (Nello Cristianini) Date: Thu, 4 Jan 2001 23:36:14 +0000 (GMT) Subject: JMLR: Special Issue on Kernel Methods Message-ID: CALL FOR PAPERS Journal of Machine Learning Research Special Issue on "New Perspectives on Kernel Based Learning Methods" http://www.cs.rhbnc.ac.uk/colt/JMLRspecissue.html Guest Editors: Nello Cristianini, John Shawe-Taylor, Bob Williamson Important dates: Submission deadline: March 15th, 2001 Decision : May 15th, 2001 Final Versions : June 15th, 2001 Submission procedure: see webpage: http://www.cs.rhbnc.ac.uk/colt/JMLRspecissue.html Background: Recent theoretical advances and experimental results have drawn considerable attention to the use of kernel functions in learning systems. Support Vector Machines, Gaussian Processes, kernel PCA, kernel Gram-Schmidt, Bayes Point Machines, Relevance and Leverage Vector Machines, are just some of the algorithms that make crucial use of kernels for problems of classification, regression, density estimation, novelty detection and clustering. At the same time as these algorithms have been under development, novel techniques specifically designed for kernel-based systems have resulted in methods for assessing generalisation, implementing model selection, and analysing performance. The choice of model may be simply determined by parameters of the kernel, as for example the width of a Gaussian kernel. More recently, however, methods for designing and combining kernels have created a toolkit of options for choosing a kernel in a particular application. These methods have extended the applicability of the techniques beyond the natural Euclidean spaces to more general discrete structures. The field is witnessing growth on a number of fronts, with the publication of books, editing of special issues, organization of special sessions and web-sites. Moreover, a convergence of ideas and concepts from different disciplines is occurring. This special issue will accept papers in any of the following main research directions: 1) design of novel kernel-based algorithms 2) design of novel types of kernel functions 3) development of new learning theory concepts 4) application of the techniques to new problem areas More information at: http://www.cs.rhbnc.ac.uk/colt/JMLRspecissue.html Or: nello at dcs.rhbnc.ac.uk From grb at neuralt.com Fri Jan 5 15:19:18 2001 From: grb at neuralt.com (George Bolt) Date: Fri, 5 Jan 2001 20:19:18 -0000 Subject: Job Vacancy in UK's leading neural software products company - Ne ural Technologies Message-ID: <6156D7F3719BD3119D2A005004E99DAD65C388@ntl-exc1.neuralt.com> Neural Technologies Limited is the leading UK company working in the application and exploitation of neural computing and other advanced technologies across a wide range of industrial and commercial environments. Our continued growth has led to the requirement of an applied Neural Scientist to join our highly motivated team to help in the development and deployment of practical advanced computing solutions on a high profile projects. Do you want to apply your neural computing skills to solve real-world problems? Neural Technologies can offer you this opportunity - just some of the areas we work in are: * Telecommunications - fraud, churn, etc. * Finance - credit scoring, risk management, instrument trading, etc. * Marketing - modelling and analysis * * You will be expected to demonstrate not only high standards of professionalism but technical innovation second to none. Self-confidence, adaptability, proactivity and communication skills are as important as the technical skills. * * Required skills are: * Well versed in neural network and other advanced algorithm development and their practical application, should have at least 2 years applied knowledge of at least 2 of the following: * Feed-forward networks for classification and regression (e.g. MLP, RBF) * Feature mapping and clustering (e.g. VQ/LVQ, Kohonen/SOM, GTM) * Non-neural classification or regression methods (e.g. genetic algorithms, rule induction/decision trees, support vector machines, case based reasoning) * Basic statistical modelling techniques (e.g. linear/logistic regression, discriminant analysis, kernel techniques) * Proven problem solving abilities * Good mathematical background * * Experience of the following would also be an advantage: * Advanced statistical concepts (e.g. information theory, Bayesian statistics) * Data preparation (e.g. pre-processing techniques, imputation, data mining) * Application domains (credit scoring, fraud analysis, telecommunications, banking and finance) * Coding in MATLAB or C/C++ within the PC environment All candidates should be working at a practical research level or have extensive industrial experience. A keen view to the commercial realities of working within a small, but fast growing, company is required. Neural Technologies Limited operate a non-smoking policy. Please send your application & CV to Kathryn Cooper (kc at neuralt.com) together with any other enquiries. George Bolt Director of Product Innovation Neural Technologies Cafe Neural: http://www.neuralt.com Tel: +44 (0) 1730 260 256 Fax: +44 (0) 1730 260 466 NOTE Any views expressed in this message are those of the Individual sender, except where the sender specifically states them to be the views of Neural Technologies Limited This email contains information that is confidential and is for the exclusive use of the addressee. If you are not the addressee, please note that any distribution, dissemination, copying or use of this communication or the information in it is prohibited. From baolshausen at ucdavis.edu Sun Jan 7 16:40:47 2001 From: baolshausen at ucdavis.edu (Bruno Olshausen) Date: Sun, 07 Jan 2001 13:40:47 -0800 Subject: graduate/postdoctoral fellowships, UC Davis Message-ID: <3A58E25F.FD2B4B29@ucdavis.edu> GRADUATE AND POSTDOCTORAL TRAINING IN NEUROSCIENCE UNIVERSITY OF CALIFORNIA, DAVIS The Graduate Program in Neuroscience at the University of California, Davis offers interdisciplinary training in areas spanning from molecular to cognitive neuroscience. Many research opportunities exist for students and postdocs interested in computational modeling approaches to problems in neuroscience. The Center for Neuroscience and the Institute for Theoretical Dynamics provide students and faculty with numerous research facilities and an excellent environment for combining theoretical and experimental approaches. The Center for Neuroscience also offers postdoctoral training via an NIH sponsored training grant. Relevant faculty include: David Amaral - structure and function of hippocampus, amygdala Marie Burns - photoreceptors, molecular mechanisms of transduction Ken Britten - visual cortex, neural basis of motion perception Leo Chalupa - retinal neurophysiology, development Barbara Chapman - development and plasticity of sensory systems Will DeBello - auditory system development Fred Gorin - molecular neurobiology, neuroinformatics Andrew Ishida - retinal ganglion cells, synaptic integration Ted Jones - thalamo-cortical interactions, neuroinformatics Leah Krubitzer - cortical organization, comparative anatomy Kim McAllister - synaptic physiology, development Brian Mulloney - central pattern generator circuits for locomotion Bruno Olshausen - computational models of vision, efficient coding Gregg Recanzone - plasticity in auditory cortex Karen Sigvart - neural control of locomotion, Parkinson's disease Mitch Sutter - cortical mechanisms of auditory perception Marty Usrey - retina/LGN/V1 physiology, neural circuits and spike timing Jack Werner - color vision and aging Martin Wilson - synaptic transmission in the retina Ewa Wojciulik - visual attention, functional imaging Andy Yonelinas - memory, functional imaging *** Application deadline for fall admissions is January 15, 2001. *** The application deadline may be nominally met by submitting an online application and fee, along with a form letter, via the web site: http://neuroscience.ucdavis.edu/grad Further information and appplication materials may be obtained from: Nikki Larramendy tel: (530) 757-8845 Center for Neuroscience fax: (530) 757-8827 University of California, Davis e-mail: nslarramendy at ucdavis.edu 1544 Newton Ct. Davis, California 95616-8599 or Karen Sigvardt, Program Chair kasigvardt at ucdavis.edu (530) 757-8820 Those interested in postdoctoral fellowships should contact the potential sponsor (faculty member) directly. Email addresses/web pages of faculty may be obtained from the Center for Neuroscience web page: http://neuroscience.ucdavis.edu/ Davis is located approximately 15 miles west of Sacramento, the state capital. It is a unique community with miles of bicycle paths and beautiful parks, and in close proximity to the Napa and Sonoma wine country, the San Francisco bay area, Lake Tahoe and the High Sierra. From marley at ele.puc-rio.br Mon Jan 8 10:55:11 2001 From: marley at ele.puc-rio.br (Marley Vellasco) Date: Mon, 08 Jan 2001 12:55:11 -0300 Subject: Neuro-Fuzzy Special Session in IWANN2001 Conference Message-ID: <3A59E2DF.456B9912@ele.puc-rio.br> I apologize, in advance, if you receive more than one copy of this message. ________________________________________________________ Call for Papers to the special session, called "NEURO-FUZZY SYSTEMS",of the IWANN2001 - 6th. International Work-Conference on Artificial and Natural Neural Networks "Biological and Artificial Computation: Methodologies, Neural Modeling and Bioengineering Applications" which will be held in Palacio de Exposiciones y Congresos, Granada, Spain from June 13-15, 2001 This special session aims to present new developments in Neuro-Fuzzy modelling, as well as new applications. Important Dates: Final Date for Submission - February 28, 2001 Acceptance notification and start of inscription - March 31, 2001 End of reduction fee for early inscription - April 30, 2001 One hard copy of each paper should be sent to: Marley Vellasco Depto. Eng. El=E9trica - PUC-RIO Rua Marques de Sao Vicente, 225 - Gavea Rio de Janeiro - RJ - BRAZIL - 22453-900 and two extra copies should be sent to the General Chairman: Jose Mira Mira Depto. Inteligencia Artificial - UNED Senda Del Rey, 9 E-28040 Madrid - Spain I would appreciate if you could divulge this special session as widely as possible. All details for the submission of papers can be found at: http://iwann.dia.uned.es/ Looking forward to seeing you in Granada. Marley Vellasco From smithmt at MIT.EDU Mon Jan 8 10:42:09 2001 From: smithmt at MIT.EDU (Marilyn T. Smith) Date: Mon, 8 Jan 2001 10:42:09 -0500 Subject: Faculty Position Search Message-ID: FACULTY POSITION AT MIT MCGOVERN INSTITUTE FOR BRAIN RESEARCH AND DEPARTMENT OF BRAIN AND COGNITIVE SCIENCES McGovern Institute is seeking outstanding scientists with a strong record of research accomplishments for positions at any level. Positions are joint appointments with the MIT Department of Brain and Cognitive Sciences and Assistant Professor positions are tenure-track. Successful applicants will be expected to develop a significant and independent research program and have a commitment to excellence in undergraduate and graduate education. The applicant's research program should address issues pertinent to the higher functions of the brain. We are particularly interested in candidates pursuing research in the area of experimental and computational investigations of integrated neural systems in animals with complex behavior. Investigators using imaging techniques to explore dynamic neuronal functions are specifically encouraged to apply. Applicants should submit a curriculum vitae, including a summary of current and proposed research programs, and should arrange for three letters of recommendation to be sent to: MIBR Search Committee Attn: Marilyn Smith Massachusetts Institute of Technology, Room E17-529 77 Massachusetts Avenue Cambridge, MA 02139 Consideration of completed applications will begin on March 1, 2001. MIT is an Affirmative Action/Equal Opportunity employer. Qualified women and minority candidates are especially encouraged to apply. --============_-1233153965==_ma============ Content-Type: text/enriched; charset="us-ascii" FACULTY POSITION AT MIT MCGOVERN INSTITUTE FOR BRAIN RESEARCH AND DEPARTMENT OF BRAIN AND COGNITIVE SCIENCES McGovern Institute is seeking outstanding scientists with a strong record of research accomplishments for positions at any level. Positions are joint appointments with the MIT Department of Brain and Cognitive Sciences and Assistant Professor positions are tenure-track. Successful applicants will be expected to develop a significant and independent research program and have a commitment to excellence in undergraduate and graduate education. The applicant's research program should address issues pertinent to the higher functions of the brain. We are particularly interested in candidates pursuing research in the area of experimental and computational investigations of integrated neural systems in animals with complex behavior. Investigators using imaging techniques to explore dynamic neuronal functions are specifically encouraged to apply. Applicants should submit a curriculum vitae, including a summary of current and proposed research programs, and should arrange for three letters of recommendation to be sent to: MIBR Search Committee Attn: Marilyn Smith Massachusetts Institute of Technology, Room E17-529 77 Massachusetts Avenue Cambridge, MA 02139 Consideration of completed applications will begin on March 1, 2001. MIT is an Affirmative Action/Equal Opportunity employer. Qualified women and minority candidates are especially encouraged to apply. From smyth at sifnos.ICS.UCI.EDU Mon Jan 8 19:21:25 2001 From: smyth at sifnos.ICS.UCI.EDU (Padhraic Smyth) Date: Mon, 08 Jan 2001 16:21:25 -0800 Subject: Call for Papers and Announcement for INTERFACE '01 Message-ID: <200101081621.aa12556@gremlin-relay.ics.uci.edu> INTERFACE '01 ANNOUNCEMENT AND CALL FOR PAPERS JUNE 13-16, 2001, ORANGE COUNTY, CA http://www.ics.uci.edu/interface PAPER DEADLINE: MARCH 15th 2001 The 33rd Annual Symposium on the Interface of Computer Science and Statistics will be held June 13-16, 2001 in Orange County, CA. The Interface is the premier annual conference at the increasingly active intersection of computer science and statistics, attracting 300 or more attendees. This year's themes are data mining and bioinformatics with invited speakers on massive data sets, graphical models, support vector machines, Bayesian methods in bioinformatics, analyzing Web data, statistical models for text, model-based clustering, computational finance, data visualization, and many more. A special day on bioinformatics will be scheduled on June 16th with invited sessions on biological sequence analysis, gene expression data, brain imaging, and medical data management and analysis. You are cordially invited to submit a contributed paper for presentation at the Symposium. We welcome papers on all topics of potential relevance to the interface of computer science and statistics. This year, we are particularly interested in increasing submissions from computer scientists active in machine learning and related areas. Submissions should consist of a 200-word abstract with a 4-page short paper, and are due by MARCH 15th. Electronic submission of abstracts and papers will be required, with the details appearing shortly on the conference Web site at www.ics.uci.edu/interface. The complete text of papers presented at the Symposium will appear in the Interface '01 Proceedings to be published as a CD-ROM by IFNA (The Interface Foundation for North America). Arnold Goodman Padhraic Smyth [Interface '01 Program Chairs] [University of California, Irvine] From berthold at cs.berkeley.edu Mon Jan 8 19:23:01 2001 From: berthold at cs.berkeley.edu (Michael Berthold) Date: Mon, 8 Jan 2001 16:23:01 -0800 (PST) Subject: Spring School on Intelligent Data Analysis in Palermo, Sicily Message-ID: >>>> Funding for Young Researchers available! <<<< >>>> Deadline for Funding Applications: 15. Jan 2001 <<<< Call for Participation SPRING SCHOOL ON INTELLIGENT DATA ANALYSIS March 26-30, 2001 Palermo, Sicily Over the last decade or so, the size of machine-readable data sets has increased dramatically and the problem of "data explosion" has become apparent. In parallel with this recent developments in computing have provided the basic infrastructure for fast access to online data. In particular many advanced computational methods for extracting information from large quantities of heterogeneous data and for data representation are now beginning to mature. These developments have created a new range of problems and challenges for the analysts, as well as new opportunities for intelligent systems in data analysis. All this has led to the emergence of the field of Intelligent Data Analysis (IDA), a combination of diverse disciplines including Artificial Intelligence and Statistics in particular. The School on Intelligent Data Analysis (IDA) will focus on the core techniques of this exciting new area: - Statistics, - Bayesian Networks, - Neural networks, - Time Series Analysis, - Rule Induction, - Fuzzy Logic, - Evolutionary Computation. All courses are organized as to provide a wide description of the theoretical and practical aspects of each discipline. For this purpose also speakers from industry are invited to show practical and already implemented applications of Intelligent Data Analysis techniques. The target audience of the IDA Summer School are advanced undergraduate students, PhD students, postdoctoral students and academic and industrial researchers and developers. The Summer School will take place at the University of Palermo (Italy) from March, 26th until March, 30th, 2001. More information - including the preliminary program and the list of speakers - is available on IDA spring school's web page: http://www.cere.pa.cnr.it/IDAschool/ FINANCIAL SUPPORT: The Spring School is supported by the European Commission under HPCF-2000-00401 subject to contract. Some financial support will be available for young researchers (<35) to attend the school. This support will cover the registration fee and all or part of the travel and subsistence expenses. Limited funding is also available for young researchers from non-european countries, provided they are nationals of an EU memberstate. If you are interested in attending the school or would like to apply for financial support please fill out the form available on our web site. The deadline for applications is January, 15th, 2001. If you have questions or comments please send e-mail to ida at cere.pa.cnr.it. From zemel at cs.toronto.edu Tue Jan 9 15:44:05 2001 From: zemel at cs.toronto.edu (Richard Zemel) Date: Tue, 9 Jan 2001 15:44:05 -0500 Subject: postdoc position: U. of Toronto Message-ID: ************************************************************************ POSTDOCTORAL RESEARCH ASSOCIATE DEPARTMENT OF COMPUTER SCIENCE UNIVERSITY OF TORONTO A postdoctoral position is available in the Machine and Neurobiological Learning laboratory in the Department of Computer Science at the University of Toronto. For more details on research in this lab, see http://www.cs.toronto.edu/~zemel/research.html. The University of Toronto is a prominent research institute in all areas of computer science, and a world leader in artificial intelligence. We are seeking someone whose research focus lies primarily in at least one of these areas: machine learning, neural computation, or probabilistic reasoning. A strong background and education in a quantitative discipline, such as physics, mathematics, statistics, engineering, or computer science, is required. Knowledge of neuroscience or psychophysics is a plus. This position is available immediately and for a duration of 1-2 years depending on accomplishment. A competitive salary package will be offered. Please send a CV, a brief statement of research experience and interests, and the names and contact information of two references to: zemel at cs.toronto.edu. Applications can also be mailed (or faxed) to: Dr. Richard Zemel Tel: (416) 978-7497 Departmet of Computer Science Fax: (416) 978-1455 University of Toronto Email: zemel at cs.toronto.edu Toronto, ON M5S 1A4 CANADA URL: www.cs.toronto.edu/~zemel ************************************************************************ From takane at takane2.psych.mcgill.ca Tue Jan 9 13:17:52 2001 From: takane at takane2.psych.mcgill.ca (Yoshio Takane) Date: Tue, 9 Jan 2001 13:17:52 -0500 (EST) Subject: No subject Message-ID: <200101091817.NAA02950@takane2.psych.mcgill.ca> Dear Colleagues, I am organizing a symposium on "Knowledge integration in neural network models" at the International Meeting of the Psychometric Society (IMPS-2001) to be held in Osaka, Japan on July 15-19, 2001. Information about the meeting can be found at http://www.ir.rikkyo.ac.jp/imps2001/ I would like to invite anyone interested in presenting a paper on the topic to submit the title and the abstract (of no more than 300 words) of the paper to me as soon as possible. You will be notified of acceptance within one week or so of submission. Some prospective speakers so far are: Shultz, T. R., & Rivest, F. Knowledge based cascade-correlation network. --- This paper presents a method of incorporating prior knowledge learned previously into a cascade-correlation network learning new but related material. Asoh, H. An approximation of nonlinear canonical correlation analysis using neural network. --- This paper presents an approximation method for nonlinear canonical correlation analysis put forward by Becker & Hinton (1992). Takane, Y., & Oshima-Takane, Y. Nonlinear generalized canonical correlation analysis by neural network models. --- This paper presents nonlinear K-set canonical correlation analysis as a method for integrating information from K concurrent sources. Yoshio Takane Professor McGill University From cesabian at aspic.usr.dsi.unimi.it Tue Jan 9 03:33:04 2001 From: cesabian at aspic.usr.dsi.unimi.it (Nicolo` Cesa-Bianchi) Date: Tue, 9 Jan 2001 09:33:04 +0100 Subject: School on Principles of Nonparametric Learning Message-ID: <20010109093304.D10851@dsi.unimi.it> Principles of Nonparametric Learning Udine (Italy), July 9-13, 2001 Advanced School coordinated by L. Gyrfi Budapest University of Technology and Economics Hungary Modern nonparametric methods have become the most important tools in various fields of applications of pattern recognition, density and regression function estimation, data compression, on-line learning and prediction. The common feature in these problems is that some unknown underlying system generates data and the best action is to be learnt from these data. The purpose of the course is to teach the basic principles of nonparametric inference with emphasis on the cited areas. Leading international experts of these areas will introduce the participants into the theory and advanced methods of inference. A prototype problem to be discussed in depth is the problem of pattern recognition in which an observation is to be classified into one of a finite number of classes. The optimal classification must be approximated based on training data. Classical nonparametric methods such as nearest neighbor and kernel methods, as well as modern methodologies including neural networks, support vector machines, and binary tree classifiers will be studied in the course. Evolutionary optimization methodologies, e.g. genetic programming, will also be considered as they allow nonparametric learning to handle complex data and explore structured model spaces. The methodologies covered by this course have found applications in various fields such as identification of biological and mechanical systems, data mining, forecasting, universal data compression, optimal portfolio strategies for stock markets, and measurement-based call admission control for high-speed communication networks. The course is addressed to postgraduates in engineering, mathematics, and computer science, and researchers in universities and research institutions. Please visit the school home page (www.cism.it/c2001/c03/) for information on program, admission, and accomodation. From bengio at idiap.ch Wed Jan 10 03:42:40 2001 From: bengio at idiap.ch (Samy Bengio) Date: Wed, 10 Jan 2001 09:42:40 +0100 (MET) Subject: open postdoc position at IDIAP, Switzerland Message-ID: Open Postdoctoral position in Machine Learning The Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP, http://www.idiap.ch) seeks qualified applicants for a Postdoctoral position in its Machine Learning group. The research project would involve several extensions of mixture and ensemble models specifically tailored for large databases, including: - Mixture of Support Vector Machines, - Mixture of binary classifiers for multiclass problems, - Feature selection for mixture models, - Others. The ideal candidate should have strong background in statistical learning theory in general, including SVMs, neural networks, and mixture models; the candidate should also be familiar with C/C++ programming under a Unix environment. Although IDIAP is located in the French part of Switzerland, English is the main working language at IDIAP. Free English and French courses are also provided. IDIAP is located in the town of Martigny (http://www.martigny.ch) in Valais, a scenic region in the south of Switzerland, surrounded by the highest mountains of Europe, and offering exciting recreational activities, including hiking, climbing and skiing, as well as varied cultural activities. It is within close proximity to Montreux (Jazz Festival) and Lausanne (EPFL, http://www.epfl.ch). Candidates should send their detailed CV (preferably by email) to Dr. Samy Bengio Research Director. Machine Learning Group Leader. IDIAP, CP 592, rue du Simplon 4, 1920 Martigny, Switzerland. tel: +41 27 721 77 39, fax: +41 27 721 77 12. mailto:bengio at idiap.ch, http://www.idiap.ch/~bengio ----- Samy Bengio Research Director. Machine Learning Group Leader. IDIAP, CP 592, rue du Simplon 4, 1920 Martigny, Switzerland. tel: +41 27 721 77 39, fax: +41 27 721 77 12. mailto:bengio at idiap.ch, http://www.idiap.ch/~bengio From wolfskil at MIT.EDU Thu Jan 11 10:46:05 2001 From: wolfskil at MIT.EDU (Jud Wolfskill) Date: Thu, 11 Jan 2001 10:46:05 -0500 Subject: book announcement--Smola Message-ID: I thought readers of the Connectionists List might be interested in this book. For table of contents and more information please visit http://mitpress.mit.edu/promotions/books/SMOAHF00. Best, Jud Advances in Large-Margin Classifiers edited by Alexander J. Smola, Peter J. Bartlett, Bernhard Schlkopf, and Dale Schuurmans The concept of large margins is a unifying principle for the analysis of many different approaches to the classification of data from examples, including boosting, mathematical programming, neural networks, and support vector machines. The fact that it is the margin, or confidence level, of a classification --that is, a scale parameter--rather than a raw training error that matters has become a key tool for dealing with classifiers. This book shows how this idea applies to both the theoretical analysis and the design of algorithms. The book provides an overview of recent developments in large margin classifiers, examines connections with other methods (e.g., Bayesian inference), and identifies strengths and weaknesses of the method, as well as directions for future research. Among the contributors are Manfred Opper, Vladimir Vapnik, and Grace Wahba. Alexander J. Smola is a Postdoctoral Fellow at GMD-FIRST, Berlin. Peter L. Bartlett is Senior Fellow, Computer Sciences Laboratory, Australian National University. Bernhard Schlkopf is a Researcher at Microsoft Research Ltd., Cambridge, UK. Dale Schuurmans is Assistant Professor of Computer Science at the University of Waterloo, Ontario, Canada. 8 x 10, 412 pp., cloth ISBN 0-262-19448-1 Neural Information Processing series -------------------------------------------------------------------------------- Jud Wolfskill 617.253.2079 phone Associate Publicist 617.253.1709 fax MIT Press wolfskil at mit.edu 5 Cambridge Center http://mitpress.mit.edu Fourth Floor Cambridge, MA 02142 From giacomo at ini.phys.ethz.ch Fri Jan 12 14:18:43 2001 From: giacomo at ini.phys.ethz.ch (Giacomo Indiveri) Date: Fri, 12 Jan 2001 20:18:43 +0100 Subject: Telluride 2001 Workshop on Neuromoprhic Engineering References: <200101110350.f0B3oxt07285@purkinje.salk.edu> Message-ID: <3A5F5893.A486292B@ini.phys.ethz.ch> Please accept our apology for cross-postings. Workshop application announcement: http://www.ini.unizh.ch/telluride2000/tell2001_announcement.html ---------------------------------------------------------------------- NEUROMORPHIC ENGINEERING WORKSHOP Sunday, JULY 1 - Saturday, JULY 21, 2001 TELLURIDE, COLORADO ------------------------------------------------------------------------ Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Timmer HORIUCHI (Johns Hopkins University) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Christof KOCH (California Institute of Technology) Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) ------------------------------------------------------------------------ We invite applications for a three week summer workshop that will be held in Telluride, Colorado from Sunday, July 1 to Sunday, July 21, 2001. The application deadline is Friday, February 23, and application instructions are described at the bottom of this document. The 2000 summer workshop on "Neuromorphic Engineering", sponsored by the National Science Foundation, the Gatsby Foundation, Whitaker Foundation, the Office of Naval Research, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology, was an exciting event and a great success. A detailed report on the workshop is available at http://www.ini.unizh.ch/telluride2000. We strongly encourage interested parties to browse through the previous workshop web pages: http://www.ini.unizh.ch/telluride2000/ GOALS: Carver Mead introduced the term "Neuromorphic Engineering" for a new field based on the design and fabrication of artificial neural systems, such as vision systems, head-eye systems, and roving robots, whose architecture and design principles are based on those of biological nervous systems. The goal of this workshop is to bring together young investigators and more established researchers from academia with their counterparts in industry and national laboratories, working on both neurobiological as well as engineering aspects of sensory systems and sensory-motor integration. The focus of the workshop will be on active participation, with demonstration systems and hands-on-experience for all participants. Neuromorphic engineering has a wide range of applications from nonlinear adaptive control of complex systems to the design of smart sensors. Many of the fundamental principles in this field, such as the use of learning methods and the design of parallel hardware (with an emphasis on analog and asynchronous digital VLSI), are inspired by biological systems. However, existing applications are modest and the challenge of scaling up from small artificial neural networks and designing completely autonomous systems at the levels achieved by biological systems lies ahead. The assumption underlying this three week workshop is that the next generation of neuromorphic systems would benefit from closer attention to the principles found through experimental and theoretical studies of real biological nervous systems as whole systems. FORMAT: The three week summer workshop will include background lectures on systems neuroscience (in particular learning, oculo-motor and other motor systems and attention), practical tutorials on analog VLSI design, small mobile robots (Koalas and Kheperas), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed (soon to be defined). They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, the majority of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. The analog VLSI practical tutorials will cover all aspects of analog VLSI design, simulation, layout, and testing during the three weeks of the workshop. The first week covers basics of transistors, simple circuit design and simulation. This material is intended for participants who have no experience with analog VLSI. The second week will focus on design frames for silicon retinas, from the silicon compilation and layout of on-chip video scanners, to building the peripheral boards necessary for interfacing analog VLSI retinas to video output monitors. Retina chips will be provided. The third week will feature sessions on floating gates, including lectures on the physics of tunneling and injection, and on inter-chip communication systems. We will also feature a tutorial on the use of small, mobile robots, focusing on Koala's, as an ideal platform for vision, auditory and sensory-motor circuits. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * olfaction * motor control * central pattern generator * robotics, multichip communication * analog VLSI * learning The active perception project group will emphasize vision and human sensory-motor coordination. Issues to be covered will include spatial localization and constancy, attention, motor planning, eye movements, and the use of visual motion information for motor control. Demonstrations will include a robot head active vision system consisting of a three degree-of-freedom binocular camera system that is fully programmable. The central pattern generator group will focus on small walking and undulating robots. It will look at characteristics and sources of parts for building robots, play with working examples of legged and segmented robots, and discuss CPG's and theories of nonlinear oscillators for locomotion. It will also explore the use of simple analog VLSI sensors for autonomous robots. The robotics group will use rovers and working digital vision boards as well as other possible sensors to investigate issues of sensorimotor integration, navigation and learning. The audition group aims to develop biologically plausible algorithms and aVLSI implementations of specific auditory tasks such as source localization and tracking, and sound pattern recognition. Projects will be integrated with visual and motor tasks in the context of a robot platform. The multichip communication project group will use existing interchip communication interfaces to program small networks of artificial neurons to exhibit particular behaviors such as amplification, oscillation, and associative memory. Issues in multichip communication will be discussed. LOCATION AND ARRANGEMENTS: The workshop will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350 miles). America West and United Airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of workstations running UNIX and PCs running LINUX and Microsoft Windows. No cars are required. Bring hiking boots, warm clothes and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around March 9, 2001. Participants are expected to pay a $275.00 workshop fee at that time in order to reserve a place in the workshop. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. Travel reimbursement of up to $500 for US domestic travel and up to $800 for overseas travel will be possible if financial help is needed (Please specify on the application). HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e. postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage qualified women and minority candidates to apply. Application should include: * First name, Last name, valid email address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Description of special equipment needed for demonstrations that could be brought to the workshop. * Two letters of recommendation Complete applications should be sent to: Terrence Sejnowski The Salk Institute 10010 North Torrey Pines Road San Diego, CA 92037 email: telluride at salk.edu FAX: (858) 587 0417 DEADLINE: February 23, 2001 Applicants will be notified by email around March 9, 2001 From terry at salk.edu Sat Jan 13 02:43:09 2001 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 12 Jan 2001 23:43:09 -0800 (PST) Subject: NEURAL COMPUTATION 132 In-Reply-To: <3A59E2DF.456B9912@ele.puc-rio.br> Message-ID: <200101130743.f0D7h9v12640@purkinje.salk.edu> Neural Computation - Contents - Volume 13, Number 2 - February 1, 2001 Review Spatio-Temporal Connectionist Networks: A Taxonomy and Review Stefan C. Kremer Notes Formulations of Support Vector Machines: A Note from an Optimization Point of View Chih-Jen Lin Minimal Feedforward Parity Networks Using Threshold Gates Hon-Kwok Fung and Leong Kwan Li Letters Does Corticothalamic Feedback Control Cortical Velocity Tuning? Ulrich Hillenbrand and J. Leo van Hemmen A Competitive Layer Model for Feature Binding and Sensory Segmentation Heiko Wersing, Jochen J. Steil, and Helge Ritter Visual Learning Using A Priori Constraints Within ORASSYLL Norbert Kruger Binding and Normalization of Binary Sparse Distributed Representations Context-Dependent Thinning by Dmitri A. Rachkovskij and Enrst M. Kussul Resolution-Based Complexity Control for Gaussian Mixture Models Peter Meinicke and Helge Ritter ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2001 - VOLUME 13 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $88 $94.16 $136 Institution $460 $492.20 $508 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From amari at brain.riken.go.jp Mon Jan 15 00:02:38 2001 From: amari at brain.riken.go.jp (Shun-ichi Amari) Date: Mon, 15 Jan 2001 14:02:38 +0900 Subject: new book on Information Geometry Message-ID: Dear Connectionists It is my pleasure to announce the publication of a book on Information Geometry. I have been often asked if there is a good book on information geometry to know its general perspectives. Here it is. S.Amari and H.Nagaoka, Methods of Information Geometry, AMS Translations of Mathematical Monographs, vol 191 (translated by Daishi Harada) American Mathematical Society (AMS) and Oxford University Press, 206 + x pages, 2000. (See http://www.ams.org/) ******************** Shun-ichi Amari Vice Director, RIKEN Brain Science Institute Laboratory for Mathematical Neuroscience Research Group on Brain-Style Information Systems tel: +81-(0)48-467-9669; fax: +81-(0)48-467-9687 amari at brain.riken.go.jp http://www.bsis.brain.riken.go.jp/ From nic at idsia.ch Sun Jan 14 13:32:32 2001 From: nic at idsia.ch (Nici Schraudolph) Date: Sun, 14 Jan 2001 19:32:32 +0100 (CET) Subject: new institute at ETH Zurich - Ph.D. and postdoc positions Message-ID: Dear colleagues, we are building up a machine learning research group at the new Institute of Computational Sciences (ICOS) at ETH Zurich, and thus have several openings for Ph.D. students and postdoctoral researchers. ICOS (www.icos.ethz.ch) is a new multidisciplinary institute within ETH's Department of Computer Science. Our goal is to bring the latest advances in computer science to bear on challenging problems in all areas of science and technology, with a special focus on the emerging interfaces of fields such as life sciences, nanotechnology, and computation. We have initiated several collaborative projects in the above areas, within ETH as well as nationally and internationally, and are seeking creative individuals who wish to expand on this basis in a stimulating research environment. One initial focus of the machine learning group at ICOS will be the development of advanced algorithms for stochastic gradient descent. In addition to candidates that want to pursue this line of research, however, we strongly welcome applications from researchers with com- plementary orientations (e.g., kernel methods or Bayesian inference). What we are looking for is a) the ability to work with, and improve upon, the latest learning algorithms in your specialty; b) an interest in applying your work to large scale, challenging real-world problems; and c) the wish to explore the opportunities inherent in the highly interdisciplinary environment of the ETH Zurich. The ETH (Swiss Federal Institute of Technology) Zurich is considered one of the world's foremost technical universities, and offers a first-class academic environment. Zurich is the commercial center of Switzerland, fast becoming one of the hubs of information technology in the heart of Europe. It combines a high standard of living with a beautiful lakeside setting, with ample leisure opportunities (the Alps, for one) within easy reach. ETH offers highly competitive salaries with initial appointments for up to two years for post-doctoral positions and up to four years for Ph.D. positions. Renewal of these positions is possible for successful programs. To apply, please provide the following information: - a cover letter describing your research interest, - your c.v. including a list of publications, - one or two sample publications, and - e-mails and telephone numbers of three colleagues familiar with you and your work. Applications should be sent to the address: Daniela Wiesli Institute of Computational Science Weinbergstrasse 43 ETH Zentrum Zurich, CH-8092 Switzerland We welcome applications by email (in Word, PDF, or Postscript format) to wiesli at inf.ethz.ch, with the phrase "ML application" in the subject. Best regards, -- Dr. Nicol N. Schraudolph mobile: +41-76-585-3877 IDSIA, Galleria 2 home: -91-970-3877 CH-6928 Manno, Switzerland work: -91-610-8669 http://www.idsia.ch/~nic/ fax: -8661 From kenm at julian.uwo.ca Mon Jan 15 11:54:57 2001 From: kenm at julian.uwo.ca (Ken McRae) Date: Mon, 15 Jan 2001 11:54:57 -0500 Subject: Postdoc Opportunity Message-ID: Postdoctoral Fellowship in Psycholinguistics & Computational Modeling We have funding for a two-year Postdoctoral Fellowship in my lab at the University of Western Ontario in London, Ontario, Canada. The stipend is for $32,500 per year plus $2,500 per year for travel. There are no citizenship restrictions. Our research focuses on the interrelated issues of noun meaning, verb meaning, and sentence processing. Central to this work is connectionist modeling of the computation of noun and verb meaning, as well as competition-integration modeling of on-line sentence reading times. Our research integrates theories and methodologies from a number of areas, including: word recognition, concepts and categorization, sentence processing, connectionist modeling, neuroscience, and patients with acquired disorders. Thus, a PDF has the opportunity to participate in projects in a number of areas of Cognitive Science. Our department has seven Cognition faculty, all of whom conduct research related to language processing. Thus, our faculty and graduate students provide a rich research environment. I am also involved in a number of collaborations with researchers from other universities. My lab is well-equipped for both human experimentation and computational modeling. UWO also has a 4T magnet that is used for research only. London is a pleasant city of approximately 350,000, and is located 2 hours from both Toronto and Detroit. Note that a reasonable apartment in London costs approximately $500 per month. For further information on our lab and Cognition at UWO, see: http://www.sscl.uwo.ca/psychology/cognitive/faculty.html If you are interested in this position, please contact Ken McRae. *********************************************************** Ken McRae Associate Professor Department of Psychology Social Science Centre University of Western Ontario London, Ontario CANADA N6A 5C2 email: mcrae at uwo.ca http://www.sscl.uwo.ca/psychology/cognitive/mcrae/mcrae.html phone: (519) 661-2111 ext. 84688 fax: (519) 661-3961 *********************************************************** From juergen at idsia.ch Mon Jan 15 04:07:28 2001 From: juergen at idsia.ch (juergen@idsia.ch) Date: Mon, 15 Jan 2001 10:07:28 +0100 Subject: IDSIA JOBS: 2 POSTDOCS, 1 PHD STUDENT Message-ID: <200101150907.KAA16944@ruebe.idsia.ch> We are seeking two outstanding postdocs and one PhD student in the fields of artificial neural networks, unsupervised learning, reinforcement learning, and/or related areas. The initial appointment would be for 2 years, starting 2001, with possibility of prolongation. Please see http://www.idsia.ch/jobs.html IDSIA is the smallest among the world's top ten AI labs identified by Business Week, and number 4 in the category "Computer Science - Biologically Inspired." Our research focuses on recurrent and other neural networks, reinforcement learning, complexity and generalization issues, unsupervised learning and information theory, forecasting, artificial ants, combinatorial optimization, evolutionary computation. IDSIA's algorithms hold the world records for several important operations research benchmarks. We are located near the beautiful city of Lugano in Ticino, the scenic southernmost province of Switzerland, origin of special relativity and the WWW. Milano, Italy's center of fashion and finance, is 1 hour away, Venice 3 hours. Our collaborators at CSCS (the Swiss supercomputing center) are right beneath us; we are also affiliated with the University of Lugano and SUPSI. Switzerland boasts the highest citation impact factor, the most Nobel prizes per capita, the highest income per capita, and some of the best chocolate. Applicants should submit : (i) Detailed curriculum vitae, (ii) List of three references and their email addresses, (iii) Concise statement of their research interests (two pages max). Please send all documents to: Juergen Schmidhuber, IDSIA, Galleria 2, 6928 Manno (Lugano), Switzerland. Applications in plain ASCII format can also be submitted by email (only small files please) to juergen at idsia.ch. Do NOT send doc or pdf or large postscript files. Instead send WWW pointers to postscript files. Please connect your first and last name by a dot "." in the subject header, and add a meaningful extension. For instance, if your name is John Smith, then your messages could have headers such as: From krose at science.uva.nl Wed Jan 17 12:20:55 2001 From: krose at science.uva.nl (Ben Krose) Date: Wed, 17 Jan 2001 18:20:55 +0100 Subject: Ph.D. position available Message-ID: <3A65D477.8F62C6CE@science.uva.nl> I would like to announce the following job opening on the connectionists list: The Intelligent Autonomous Systems group of the Research Institute Computer Science of the University of Amsterdam, Netherlands (http://www.science.uva.nl/research/ias/) invites applications for a ------------------------------------------------------------------------- Ph.D. position "Probabilistic models for distributed surveillance systems" ------------------------------------------------------------------------- The project focusses on 'Networked Intelligent Devices' systems: autonomous functioning camera's in a network environment. Here we have to deal with several fundamental problems: the identification problem (`is the object which is observed by one camera the same as the object observed by some other camera some time ago?') and the representation problem (`how can probabilistic information be integrated in a distributed system?'). Recently Bayesian networks have shown to be able to represent such dependencies and to exploit them, although in other applications (diagnosis). We want to investigate to which extent Bayesian networks can be applied to this area, whether the dependencies can be learned and whether these networks can be used in a multi-agent system. The project is funded by the Dutch Technology Foundation STW. Desired profile: The highly qualified applicant should possess a masters degree in the field of multi-agent systems, neural networks, image processing or statistics. Programming skills are an asset (C, Matlab, ...), as is a familiarity with UNIX and PC platforms. We offer: 1) A challenging research environment. The IAS group consists three staff members, a postdoc and 7 Ph.D. students working in the field of robotics, vision and probabilistic models. We collaborate within the Foundation for Neural Networks with the probabilistic modeling group at Nijmegen University 2) An attractive income. Dutch Ph.D. students get a salary which starts at DFL 3.055,- a month for the first year, growing up to DFL 4.362,- per month. 3) The Ph.D. student will be a member of the ASCI research school providing Ph.D-level training. Information: Dr. ir. B.J.A. Krse, tel 020-525 7461, email: krose at science.uva.nl More about the project: http://www.science.uva.nl/research/learn/ Applications for this position close on February 15, 2001. Please write to: afdeling Personeelszaken Computer Science Department Kruislaan 403, 1098 SJ, Amsterdam, The Netherlands, referring to job opening nr 15114 -- dr. ir. B.J.A. Kr\"ose Department of Computer Science University of Amsterdam, Kruislaan 403, 1098 SJ Amsterdam, NL. tel: +31 20 525 7520/7463/(7490 fax) http://www.science.uva.nl/~krose/ From wriggers at scripps.edu Wed Jan 17 23:17:27 2001 From: wriggers at scripps.edu (Willy Wriggers) Date: Wed, 17 Jan 2001 20:17:27 -0800 Subject: Postdoc: TRN Applications in Multi-Resolution Molecular Modeling Message-ID: <3A666E57.DFAE71BB@scripps.edu> ------------------------------------------------------- Postdoctoral Positions: TRN Applications in Multi-Resolution Molecular Modeling ------------------------------------------------------- The Scripps Research Institute (La Jolla, California) and its Computational Structural Biology Group in the Department of Molecular Biology (http://www.scripps.edu/wriggers) are seeking highly qualified Postdoctoral Research Associates to develop and apply multi-resolution modeling techniques based on topology-representing networks (TRN) for the determination of 3D atomic structures of proteins and large biomolecular assemblies. Highly qualified applicants should hold a Ph.D. degree in physics, chemistry, computer science, or a related quantitative discipline. Research experience in image-processing, neural networks, or visualization are an essential asset. We expect a strong programming background, organizational skills, and a desire to learn principles of structural biology. The successful candidates may choose among the following research topics: - neural network-based shape characterization and query; - shape-based docking of multi-resolution biomolecular data; - flexible docking with force-field methods (molecular dynamics and normal mode analysis); - spline-based warping (morphing) of 3D structural data; - interactive visualization (computer graphics) of atomic and low-resolution data. The developed algorithms will be applied in challenging collaborations with world leaders in Electron Microscopy involving structures of virus capsids, RNA polymerase, cytoskeletal filaments and the ribosome. Initial appointments are for one year, but are extendable to the full time frame of the projects (up to 5 years). Application review begins immediately until the positions are filled. Ideally, candidates should be able to start by April, 2001, although highly qualified candidates who seek a later start date should not hesitate to apply. We offer a competitive salary and benefits. If you are interested in applying for a position, please email your CV, a letter of application (research interests and publication list), and a list of references (with name, email, and phone number) to me. There are no citizenship restrictions. Qualified women and minority candidates are encouraged to apply. TSRI is an Equal Opportunity employer. Willy Wriggers Assistant Professor Department of Molecular Biology, TPC6 The Scripps Research Institute 10550 North Torrey Pines Road La Jolla, California 92037 E-mail: wriggers at scripps.edu URL: http://www.scripps.edu/wriggers Tel: (858)784-8823 Fax: (858)784-8688 From doya at isd.atr.co.jp Thu Jan 18 06:22:00 2001 From: doya at isd.atr.co.jp (Kenji Doya) Date: Thu, 18 Jan 2001 20:22:00 +0900 Subject: CREST Workshop on Metalearning and Neuromodulation Message-ID: CREST WORKSHOP ON METALEARNING AND NEUROMODULATION April 6th and 7th, 2001 Keihanna Plaza, Seika, Kyoto, Japan Sponsored by Metalearning, Neuromodulation, and Emotion Project CREST, Japan Science and Technology Corporation The goal of this workshop is to bring together neuroscientists as well as theorists who work on the regulatory mechanisms of adaptive systems, either biological or artificial. We invite researchers in the fields the computational theory of 'metalearning' as well as the biological mechanism of neuromodulators, such as dopamine, serotonin, norepinephrine, and acetylcholine. Please visit our workshop home page for details: http://www.isd.atr.co.jp/nip/crest/workshop/ This workshop is scheduled after the 9th International Catecholamine Symposium (http://mc-net.jtbcom.co.jp/ics2001/) held in downtown Kyoto from March 31st to April 5th, 2001. INVITED SPEAKERS Minoru Asada, Osaka University Gary Aston-Jones, University of Pennsylvania Kenji Doya, CREST, JST & ATR International Barry J. Everitt, University of Cambridge Michael Hasselmo, Boston University Okihide Hikosaka, Juntendo University Shin Ishii, Nara Institute of Science and Technology Sham Kakade, University College London Takashi Matsumoto, Waseda University Toshiyuki Sawaguchi, Hokkaido University Wolfram Schultz, University of Fribourg Yuko Sekino, Gumma University Shigeto Yamawaki, Hiroshima University CALL FOR POSTERS A poster session will be held in the evening of April 6th. Please send 1) title, 2) author(s), 3) affiliation(s), 4) abstract up to 500 words, 5) postal address, 6) phone, 7) fax, and 8) e-mail address of the presenting author by e-mail to the secretariat by February 15th, 2001. REGISTRATION Please send 1) name, 2) affiliation, 3) postal address, 4) phone, 5) fax, and 6) e-mail address by e-mail to the secretariat by March 1st, 2001. Registration is free. However, the numbers of attendees will be limited by capacity of the conference room. So please register early. HOTEL RESERVATION Please visit our home page (http://www.isd.atr.co.jp/nip/crest/workshop/) to download a reservation form, and send it by fax directly to a hotel. Note that early April is the high season for cherry blossoms in Kyoto, so please reserve early. SECRETARIAT Naomi Katayama Metalearning, Neuromodulation and Emotion, CREST, JST 2-2-2 Hikaridai, Seika, Soraku, Kyoto 619-0288, Japan Phone: +81-774-95-1251 Fax: +81-774-95-1259 E-mail: nip-info at isd.atr.co.jp URL: http://www.isd.atr.co.jp/nip/crest/ ---- Kenji Doya Information Sciences Division, ATR International; CREST, JST 2-2-2 Hikaridai, Seika, Soraku, Kyoto 619-0288, Japan Phone:+81-774-95-1251; Fax:+81-774-95-1259; http://www.isd.atr.co.jp/~doya From schumann at ptolemy.arc.nasa.gov Thu Jan 18 14:48:21 2001 From: schumann at ptolemy.arc.nasa.gov (Johann Schumann) Date: Thu, 18 Jan 2001 11:48:21 -0800 (PST) Subject: Reasearch Position at NASA/Ames on V&V of Neural Networks Message-ID: <200101181948.LAA15339@karg.arc.nasa.gov> The Automated Software Engineering Group at NASA Ames Research Center is inviting applications for a research position in a project on Verification and Validation of Controllers based upon on-line trained ANNs. The ASE group performs research and development in the areas of automated reasoning and formal methods for software synthesis and verification. We have ongoing collaborations with several NASA application groups (e.g., ANN-based flight controller for F-15/ACTIVE) as well as academic research groups. The ideal candidate must have experience in the theoretical foundations of ANNs and their learing algorithms. We are focusing on feed-forward architectures, but RBF-based networks are also of interest. A strong background in numerical algorithms and control theory as a plus. A PhD in Computer Science, Mathematics, Physics or a releated area is required. To be considered for this position, please send a resume (URL ok) and contact information for three references to Johann Schumann schumann at ptolemy.arc.nasa.gov and cc to Michael Lowry lowry at ptolemy.arc.nasa.gov For more information on the ASE group, see http://ase.arc.nasa.gov/ We are also considering applications for a student summer internship. Please see http://www.riacs.edu/ssrp for further details. --------------------------------------- Johann Schumann Automated Software Engineering NASA Ames / RIACS Moffet Field, Ca 94035 Phone: (650) 604-0941 email: schumann at ptolemy.arc.nasa.gov From gomi at idea.brl.ntt.co.jp Thu Jan 18 21:02:20 2001 From: gomi at idea.brl.ntt.co.jp (Hiroaki GOMI) Date: Fri, 19 Jan 2001 11:02:20 +0900 Subject: RESEARCH POSITIONS AVAILABLE at NTT Communication Sci. Labs. Message-ID: <20010119110220F.gomi@idea.brl.ntt.co.jp> RESEARCH POSITIONS AVAILABLE NTT (Nippon Telegraph and Telephone Corporation) Communication Science Labs. Research associate (post doctoral fellow) and research specialist positions are currently available in the human speech & motor control group at NTT Communication Science Laboratories. One research topic focuses on the human motor control mechanisms in the mechanical interaction with environments, and its brain information processing. The candidate should have a strong background in human motor control studies. Some skills of C programming for controlling experimental system and Matlab for data analyses are desirable but not required. Candidates with training in psychological approaches to motor control are particularly encouraged to apply. Another topic focuses on information processing for speech and language. The candidate should have a strong background in the fields of speech and language. The position requires strong programming skills in C and/or C++ with experience in programming mathematical algorithms, and knowledge of signal processing and machine learning. The salary will be decided according to company regulation. The research center for these topics is located in Atsugi near Tokyo, Japan (see our web page). The positions are tenable for one year and are renewable every year until the limit of two years. Please send curriculum vitae including research and programming experiences, names and contact details of referees, and representative publications to the address listed below. Curriculum vitae should be sent until March 23, 2001. Informal inquiries should be set to the e-mail address. E-mail inquiries and applications are encouraged. We prefer a starting date of April 1, 2001 but this is open to negotiation. Application should be sent to: Dr. Eisaku Maeda soukatsu at cslab.kecl.ntt.co.jp Senior Manager of NTT Communication Science Laboratories Tel: +81-774-93-5040 Fax: +81-774-93-5045 address: NTT Communication Science Labs. Hikaridai 2-4, Seika-cho, Soraku-gun, Kyoto-pref. 619-0237, Japan web page: http://www.kecl.ntt.co.jp From Dave_Touretzky at cs.cmu.edu Fri Jan 19 03:15:55 2001 From: Dave_Touretzky at cs.cmu.edu (Dave_Touretzky@cs.cmu.edu) Date: Fri, 19 Jan 2001 03:15:55 -0500 Subject: undergraduate summer research opportunities Message-ID: <2079.979892155@skinner.boltz.cs.cmu.edu> Summer Undergraduate Research at the Center for the Neural Basis of Cognition University of Pittsburgh / Carnegie Mellon University If you are a faculty member who advises undergraduates with an interest in cognitive or computational neuroscience, kindly encourage your best students to apply for an undergraduate summer internship at the Center for the Neural Basis of Cognition, a joint project of Carnegie Mellon University and the University of Pittsburgh. A ten-week program beginning in early June features intensive involvement in laboratory research supervised by one of the program's faculty, plus a series of lectures and lab tours, and a weekly journal club. Each student's individualized plan of research is determined in consultation with their faculty mentor. Potential research activities include functional brain imaging, computer simulations of cognitive phenomena, neurophysiological recording from the brains of behaving animals, neuroanatomical studies, and neuropsychological assessment of clinical patients. Students receive a $2500 stipend, free housing, and some travel support. Applications are requested from highly motivated students with interests in neuroscience, psychology, engineering, physics, mathematics, or computer science. STUDENTS MUST NOT YET HAVE COMPLETED THEIR UNDERGRADUATE DEGREE AT THE TIME THEY PARTICIPATE IN THE PROGRAM. Hence, graduating seniors are ineligible to apply. Application information is available on the web at http://www.cnbc.cmu.edu/Training/summer Applicants must include a personal statement, a recent school transcript, one letter of recommendation from a faculty member, and a selection of two choices of research areas they would like to explore. The personal statement should be 2 pages in length and include the following information: scientific interests and professional goals, prior research experience, and relevant laboratory and computer skills. APPLICATION DEADLINE: FEBRUARY 15, 2001. For further information, please visit the web site listed above, or send email to cncb-admissions at cnbc.cmu.edu From icann at ai.univie.ac.at Wed Jan 17 08:58:55 2001 From: icann at ai.univie.ac.at (ICANN 2001 conference) Date: Wed, 17 Jan 2001 14:58:55 +0100 Subject: ICANN 2001: Final Call for Papers Message-ID: <3A65A51F.F3458FE3@ai.univie.ac.at> Final Call for Papers ============================================================ ICANN 2001 International Conference on Artificial Neural Networks Aug. 21-25, 2001 Vienna, Austria http://www.ai.univie.ac.at/icann the annual conference of the European Neural Network Society ============================================================ We invite submission of full-length papers on work in neural computation covering theory, algorithms, applications or implementation in one of the following areas: - Computational Neuroscience - Data Analysis and Pattern Recognition - Vision and Image Processing - Signal and Time Series Processing - Robotics and Control - Connectionist Cognitive Science - Selforganization and Dynamical Systems Deadline for receipt of papers: !!!!!!!!!!!!!!! Feb 16, 2001 !!!!!!!!!!!!!!! (electronic submission is possible) Please see our web page for more details. http://www.ai.univie.ac.at/icann ___________________________________________________________ Furthermore, we invite proposals for tutorials, special sessions or workshops on selected topics in neural computation. Deadline for receipt of proposals: !!!!!!!!!!!!! Feb 1, 2001 !!!!!!!!!!!!! Please see our web page for more details http://www.ai.univie.ac.at/icann ___________________________________________________________ ICANN 2001 is organized by the Austrian Research Institute for Artificial Intelligence in cooperation with the Vienna University of Technology's Pattern Recognition and Image Processing Group and Center for Computational Intelligence. For questions contact icann at ai.univie.ac.at From v.kecman at auckland.ac.nz Sun Jan 21 04:28:29 2001 From: v.kecman at auckland.ac.nz (Vojislav KECMAN) Date: Sun, 21 Jan 2001 22:28:29 +1300 Subject: book announcement: LEARNING AND SOFT COMPUTING Message-ID: <3A6AABBD.5EA96EA@auckland.ac.nz> Dear Colleague, I would like to announce the new The MIT Press book (to appear in March, 2001) on LEARNING AND SOFT COMPUTING Support Vector Machines, Neural Networks and Fuzzy Logic Models authored by me - Vojislav KECMAN The MIT Press, Cambridge, MA, 2001 ISBN 0-262-11255-8 608 pp., 268 illus., 47 examples, 155 problems $US60.00/=A2G41.50 (Hardcover) Please do check the following sites: www.support-vector.ws http://mitpress.mit.edu/book-home.tcl?isbn=3D0262112558 You will find the whole information about the book as well as powerful software and slides to download. Software accompanying the book is MATLAB 5 and 6 compatible. Learn the SVMs, NNs and FLMs by playing and enjoying. Best regards, VK -- Prof. Vojislav Kecman Phone: ++ 64 9 37 37 599 ext. 8178 The University of Auckland FAX: ++ 64 9 37 37 479 Department of Mech. Eng. Email: v.kecman at auckland.ac.nz Private Bag 92019 Auckland, New Zealand Web sites: http://www.support-vector.ws http://www.auckland.ac.nz/eme/staff/profiles/kecman.htm From wichert at neuro.informatik.uni-ulm.de Mon Jan 22 05:36:37 2001 From: wichert at neuro.informatik.uni-ulm.de (Andreas Wichert) Date: Mon, 22 Jan 2001 11:36:37 +0100 (MET) Subject: OSoftware for Simulating a Connectionistic Production System Message-ID: Object Oriented Software for Simulating a Connectionistic Production System Abstract C++ class library for simulating an associative computer is introduced. Associative computer is a connectionistic production system with benefits of distributed representation in problem solving. These benefits include the ability to learn from experience, heuristics resulting from picture representation and the ability to deal with noisy information. The behavior of the model is demonstrated by empirical experiments in block world. The model is the first effort to fill the gape between the statistical models like the artificial neural networks and models of logical reasoning. A manual in postcript and pdf format is present. Available at: 1) web site, in gzipped tar format: http://www.informatik.uni-ulm.de/ni/mitarbeiter/AWichert.html ... Miscellaneous: [M5].. Associative Computer: The Software 2) anonymous ftp, in gzipped tar format: ftp.neuro.informatik.uni-ulm.de, directory /ni/wichert File ASSOCOMP.tar.gz 3) cdrom upon request Andrzej Wichert PS For more information about associative computation read my Phd thesis, also avalable on the web site. From: esann To: "Connectionists at cs.cmu.edu" References: From bogus@does.not.exist.com Mon Jan 22 11:23:48 2001 From: bogus@does.not.exist.com () Date: Mon, 22 Jan 2001 17:23:48 +0100 Subject: ESANN'2000 proceedings available on-line Message-ID: Dear connectionists, We are pleased to announce the on-line availability of the ESANN'2000 proceedings (European Symposium on Artificial Neural Networks). Full-text version of all contributions may be downloaded in PDF (v. 4.0) format. An author index and a searchable abstract page are also available. The electronic proceedings may be accessed through the ESANN main page (http://www.dice.ucl.ac.be/esann/) or directly (http://www.dice.ucl.ac.be/esann/proceedings/index.html). This is a free service to the scientific community (no login required). We hope that you will take benefit from this service. Please do not hesitate to send us your comments/suggestions. Michel Verleysen ===================================================== ESANN - European Symposium on Artificial Neural Networks http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews,... Michel Verleysen Univ. Cath. de Louvain - Microelectronics Laboratory 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at dice.ucl.ac.be * Conference secretariat D facto conference services 27 rue du Laekenveld - B-1080 Brussels - Belgium tel: + 32 2 420 37 57 - fax: + 32 2 420 02 55 mailto:esann at dice.ucl.ac.be ===================================================== From harnad at coglit.ecs.soton.ac.uk Tue Jan 23 13:59:02 2001 From: harnad at coglit.ecs.soton.ac.uk (Stevan Harnad) Date: Tue, 23 Jan 2001 18:59:02 +0000 (GMT) Subject: How and Why to Free the Refereed Research Literature Now Message-ID: For the motivation behind the eprints.org initiative, see: "How and Why to Free the Refereed Research Literature Online Through Author/Institution Self-Archiving, Now" http://www.cogsci.soton.ac.uk/~harnad/Tp/resolution.htm This is to announce that, to coincide with today's Open Meeting in Washington announcing the release of OAI 1.0: http://www.openarchives.org/DC2001/OpenMeeting.html we at Southampton have simultaneously released the OAI 1.0-compliant version of the eprints.org archive-creating software Eprints Version 1.1.1 http://www.eprints.org/ The eprints software is free, of course. Originally created by Matt Hemus as CogPrints , and then extensively re-designed for OA-compliance and generality by Robert Tansley, and recently upgraded to OAI 1.0 by Chris Gutteridge (all at Southampton University), the software has been made as flexible and adaptable as possible, so that all universities and research institutions can immediately adopt and configure it with minimal effort for all disciplines. Hence it complements centralised, discipline-based archiving with distributed, institution-based archiving. The generic version of eprints is fully interoperable with all other OAI-compliant Open Archives. This means that it no longer matters where papers are archived: The papers in all OAI-compliant Archives can be harvested using the OAI protocol into one global "virtual archive" by Open Archives Service Providers such as the Cross Archive Searching Service Below are (1) a testimonial from California Digital Libraries, one of the early adopters of the eprints.org software , (2) the most recent features of eprints 1.1.1 (3) some relevant chronology and URLs. Note that all existing Eprints Archives can be upgraded to OAI 1.0-compliance with the new release. The eprints.org archive-creating software is free, draws only on free software, and will shortly be open-sourced. -------------------------------------------------------------------- Stevan Harnad harnad at cogsci.soton.ac.uk Professor of Cognitive Science harnad at princeton.edu Department of Electronics and phone: +44 23-80 592-582 Computer Science fax: +44 23-80 592-865 University of Southampton http://www.cogsci.soton.ac.uk/~harnad/ Highfield, Southampton http://www.princeton.edu/~harnad/ SO17 1BJ UNITED KINGDOM ------------------------------------------------------------------ EPRINTS 1.1 New features should be regarded as stable; they have been well tested but they have not yet been extensively tested "in the field". Key Upgrades include: OAI 1.0 compliance support for MySQL not running on localhost support for multiple instances of eprints running on one mod_perl/apache server (1.0 claimed to do this but had some problems) new datafield "username" representing users to associate the item with. Bugfixes: mod_perl namespace collisions with multiple eprints (mentioned above). removed GNU-only command options from installation scripts. Please remember to use the online bug tracking system for reporting problems: http://bugs.eprints.org Note the new logo (symbolic of piecing together the global Eprint Archive out of the individual OAI-compliant ones) ---------- Forwarded message ---------- From catherine.candee at ucop.edu Thu Jan 18 08:06:41 2001 From: catherine.candee at ucop.edu (Catherine Candee) Date: Thu, 18 Jan 2001 21:06:41 +0800 Subject: ePrints and eScholarship Message-ID: Stevan, Though we haven't met, I wanted to write you personally to thank you for making ePrints available. Your software is a major contribution to our mutual effort to transform the scholarly communication cycle. I am the CDL director responsible for the eScholarship program, where we are making good use of ePrints. Our repositories provide the foundation of the eScholarship infrastructure. We are providing the first three repositories to scholars in International and Area Studies, Dermatology, and Tobacco Control Research beginning tomorrow, Jan 19, 2001. We expect we will have some interesting findings as they begin to actively test and use these prototype repositories. We have some models for how the repositories will logically fit together with the kind of wider sphere of surrounding scholarly products we envision (e.g., DOJ as overlay journal), but there are many particular issues still to be resolved which may have implications for how the software is developed. We will try to report as much as we can what we learn in our experiment with ePrints. So, on behalf of the eScholarship team and the open archive community, I thank you for this wonderful piece of code. You will be receiving a more formal letter tomorrow, addressed to all eScholarship partners and contributors, which will detail more of the CDL and eScholarship activities. ePrints will be prominently featured in the letter. Best regards, Catherine Candee Director, Scholarly Communication Initiatives California Digital Library University of California 300 Lakeside Drive 6th Floor Oakland, CA 94612-3550 510.987.0425 510.893.5212 (Fax) Catherine.Candee at ucop.edu ______________________________________ SOME RELEVANT CHRONOLOGY AND URLs Psycoloquy (Refereed On-Line-Only Journal) (1989) http://www.cogsci.soton.ac.uk/psycoloquy "Scholarly Skywriting" (1990) http://cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad90.skywriting.html Physics Archive (1991) http://arxiv.org "PostGutenberg Galaxy" (1991) http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad91.postgutenberg.html "Interactive Publication" (1992) http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad92.interactivpub.html Self-Archiving ("Subversive") Proposal (1994) http://www.arl.org/scomm/subversive/toc.html "Tragic Loss" (Odlyzko) (1995) http://www.research.att.com/~amo/doc/tragic.loss.txt "Last Writes" (Hibbitts) (1996) http://www.law.pitt.edu/hibbitts/lastrev.htm NCSTRL: Networked Computer Science Technical Reference Library (1996) http://cs-tr.cs.cornell.edu University Provosts' Initiative (1997) http://library.caltech.edu/publications/ScholarsForum/ CogPrints: Cognitive Sciences Archive (1998) http://cogprints.soton.ac.uk Journal of High Energy Physics (Refereed On-Line-Only Journal) (1998) http://jhep.cern.ch/ Science Policy Forum (1998) http://www.sciencemag.org/cgi/content/full/281/5382/1459 American Scientist Forum (1998) http://amsci-forum.amsci.org/archives/september98-forum.html OpCit:Open Citation Linking Project (1999) http://opcit.eprints.org E-biomed: Varmus (NIH) Proposal (1999) http://www.nih.gov/about/director/pubmedcentral/pubmedcentral.htm Open Archives Initiative (1999) http://www.openarchives.org Cross-Archive Searching Service (2000) http://arc.cs.odu.edu Eprints: Free OAI 1.0-compliant Eprint-Archive-creating software (2001) http://www.eprints.org Harnad Home Pages http://cogsci.soton.ac.uk/harnad/ http://www.princeton.edu/~harnad/ NOTE: A complete archive of the ongoing discussion of providing free access to the refereed journal literature online is available at the American Scientist September Forum (98 & 99 & 00 & 01): http://amsci-forum.amsci.org/archives/september98-forum.html You may join the list at the site above. Discussion can be posted to: september98-forum at amsci-forum.amsci.org From gary at cs.ucsd.edu Wed Jan 24 21:24:03 2001 From: gary at cs.ucsd.edu (Gary Cottrell) Date: Wed, 24 Jan 2001 18:24:03 -0800 (PST) Subject: International Conference on Cognitive Modeling Message-ID: <200101250224.SAA12126@gremlin.ucsd.edu> Fourth International Conference of Cognitive Modeling ICCM-2001 http://www.hfac.gmu.edu/~iccm/ To be held July 26 - 28, 2001, at George Mason University, Fairfax, Virginia, USA. DEADLINE FOR SUBMISSIONS: MARCH 1st 2001 THEME Computational modeling has emerged as a central, but complex and sometimes fractionated theme in research on cognition. ICCM provides a worldwide forum for cognitive scientists who build such computational cognitive models and test them against empirical cognitive data. The goal of ICCM-2001 is to bring researchers from diverse backgrounds together to compare cognitive models, to evaluate models using human data, and to further the development, accumulation, and integration of cognitive theory. SUBMISSION CATEGORIES -- http://www.hfac.gmu.edu/~iccm/ Doctoral Consortium Full day session 1 day prior to main conference for doctoral students to present dissertation proposal ideas to one another and receive feedback from experts from a variety of modeling approaches. Student participants receive complimentary conference registration as well as lodging and travel reimbursement-maximum amounts will be determined at a later date. Newell Prize for Best Student Paper Award given to the paper first-authored by a student that provides the most innovative or complete account of cognition in a particular domain. The winner of the award will receive full reimbursement for the conference fees, lodging costs, and a $1,000 stipend. The Best Applied Research Paper Award To be eligible, 1) the paper should capture behavioral data not gathered in the psychology lab OR the paper should capture behavioral data in a task that has high external validity; 2) the best paper is the one that one from this category that provides the most innovative or complete solution to a real-world, practical problem. Competitive symposia Three to six participants submit a symposium in which they all present models relating to the same domain or phenomenon. The participants must agree upon a set of fundamental issues in their domain that all participants must address or discuss. Papers and Posters Papers and posters will follow the 6-page 10-point double-column single-spaced US-letter format used by the Annual Cognitive Science Society Meeting. Formatting templates and examples will be made available in February 2001. ICCM-2001 http://www.hfac.gmu.edu/~iccm/ DEADLINE FOR SUBMISSIONS: MARCH 1st 2001 -- _/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/ Wayne D. Gray, Program Director HUMAN FACTORS & APPLIED COGNITIVE PROGRAM SNAIL-MAIL ADDRESS (FedX et al) VOICE: +1 (703) 993-1357 George Mason University FAX: +1 (703) 993-1330 ARCH Lab/HFAC Program ********************* MSN 3f5 * Work is infinite, * Fairfax, VA 22030-4444 * time is finite, * http://hfac.gmu.edu/~gray * plan accordingly. * _/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/ From kruschke at indiana.edu Fri Jan 26 08:21:58 2001 From: kruschke at indiana.edu (John K. Kruschke) Date: Fri, 26 Jan 2001 08:21:58 -0500 Subject: postdoc in modeling of cognitive processes Message-ID: <3A7179F6.3A653E8A@indiana.edu> POSTDOCTORAL TRAINING FELLOWSHIPS in the COGNITIVE SCIENCE PROGRAM INDIANA UNIVERSITY in MODELING OF COGNITIVE PROCESSES The Psychology Department and Cognitive Science Program at Indiana University anticipate one or more Postdoctoral Traineeships in the area of Modeling of Cognitive Processes, funded by the National Institutes of Health. Appointments will pay rates appropriate for a new or recent Ph.D. and will be for one or two years, beginning July 1, 2001 or earlier. Traineeships will be offered to qualified individuals who wish to further their training in mathematical modeling or computer simulation modeling, in any substantive area of cognitive psychology or Cognitive Science. Trainees will be expected to carry out original theoretical and empirical research in association with one or more of these faculty and their laboratories, and to interact with other relevant faculty and other pre- and postdoctoral trainees. In addition, they should plan to take or audit courses offered within the Cognitive Modeling Program. We are particularly interested in applicants with strong mathematical, scientific, and research credentials. Indiana University has superb computational and research facilities, and faculty with outstanding credentials in this area of research, including James Townsend, director of the training program, and Jerome Busemeyer, Robert Nosofsky, John Kruschke, Michael Gasser, Robert Goldstone, Geoffrey Bingham, Tom Busey, Donald Robinson, Robert Port, Olaf Sporns, Richard Shiffrin. Applicants should send an up-to-date vita, relevant reprints and preprints, a personal letter describing their research interests, background, goals, and career plans, and reference letters from two individuals. Women, minority group members, and handicapped individuals are urged to apply. Deadline for submission of application materials is April 1, 2001, but we encourage earlier applications. PLEASE NOTE: The conditions of our grant restrict all awards to U.S. citizens or current green card holders. Awards also have a 'payback' provision, generally requiring awardees to carry out research or teach (not necessarily at IU) for a minimum period after termination of the traineeship. Cognitive Science information may be obtained at http://www.psych.indiana.edu/ Send Materials to Professor James T. Townsend Department of Psychology, Rm 367 Indiana University 1101 E. 10th St. Bloomington, IN 47405-7007 Voice: 812-855-4882 Fax: 812-855-1086 email: jtownsen at indiana.edu Indiana University is an Affirmative Action Employer From hans.liljenstrom at sdi.slu.se Fri Jan 26 10:45:01 2001 From: hans.liljenstrom at sdi.slu.se (Hans Liljenstrom) Date: Fri, 26 Jan 2001 16:45:01 +0100 Subject: Workshop on Olfaction - Facts and Models Message-ID: <016701c087af$24142360$abef43c3@lcu1m> Dear Colleagues, A workshop on Olfaction - Facts and Models, is organized in Sigtuna, Sweden, on 8-10 March 2001. For more information, please see websites, www.sdi.slu.se/~hanslil/meetings/olfact2001 or www.agora.kva.se/meetings/olfact2001. Anyone interested in participating is welcome to register. Yours sincerely, Hans Liljenstrm, organizer Dept. of Biometry and Informatics, SLU and Agora for Biosystems ================================================================ Hans Liljenstrm, Assoc. Prof. Dept. of Biometry and Informatics Swedish University of Agricultural Sciences P. O. Box 7013, 750 07 Uppsala, Sweden Phone: +46 (0)18-671728, +46 (0)73-654 7977 Fax: +46 (0)18 673502, email: Hans.Liljenstrom at sdi.slu.se Home page: www.sdi.slu.se ================================================================ From gary at cs.ucsd.edu Fri Jan 26 17:44:55 2001 From: gary at cs.ucsd.edu (Gary Cottrell) Date: Fri, 26 Jan 2001 14:44:55 -0800 (PST) Subject: Student submissions for ICCM-2001 Message-ID: <200101262244.OAA07297@gremlin.ucsd.edu> My apologies, but this update will be important for graduate students who plan to submit papers to the Fourth International Conference on Cognitive Modeling: You'll get free registration, lodging & travel reimbursement if your paper or poster gets in! DEADLINE FOR SUBMISSIONS: MARCH 1st 2001 Web site: http://www.hfac.gmu.edu/~iccm/ From rsun at cecs.missouri.edu Sat Jan 27 17:14:51 2001 From: rsun at cecs.missouri.edu (Ron Sun) Date: Sat, 27 Jan 2001 16:14:51 -0600 Subject: new book on sequence learning Message-ID: <200101272214.QAA18826@pc113.cecs.missouri.edu> Book announcement: SEQUENCE LEARNING: PARADIGMS, ALGORITHMS, AND APPLICATIONS edited by: Ron Sun and C. L. Giles published by Springer-Verlag: LNAI 1828 This book is intended for use by scientists, engineers, and students interested in sequence learning in artificial intelligence, neural networks, and cognitive science. The book will introduce essential algorithms and methods of sequence learning and further develop them in various ways. With the help of these concepts, a variety of applications will be examined. This book will allow the reader to acquire an appreciation of the breadth and variety sequence learning and its potential as an interesting area of research and application. The reader is assumed to have basic knowledge of neural networks and AI concepts. Sequential behavior is essential to intelligence and a fundamental part of human activities ranging from reasoning to language, and from everyday skills to complex problem solving. Sequence learning is an important component of learning in many task domains --- planning, reasoning, robotics, natural language processing, speech recognition, adaptive control, time series prediction, and so on. Naturally, there are many different approaches towards sequence learning. These approaches deal with somewhat differently formulated sequential learning problems, and/or different aspects of sequence learning. This book will provide an overall framework for this field of study. --------------------------------------------------------- Table of Contents Introduction to Sequence Learning by Ron Sun Part 1: Sequence Clustering and Learning with Markov Models Sequence Learning via Bayesian Clustering by Dynamics by Paola Sebastiani, Marco Ramoni, Paul Cohen Using Dynamic Time Warping to Bootstrap HMM-Based Clustering of Time Series by Tim Oates, Laura Firoiu, Paul Cohen Part 2: Sequence Prediction and Recognition with Neural Networks Anticipation Model for Sequential Learning of Complex Sequences by DeLiang Wang Bidirectional Dynamics for Protein Secondary Structure Prediction by Pierre Baldi, Soren Brunak, Paolo Frasconi, Gianluca Pollastri, Gio- vanni Soda Time in Connectionist Models by Jean-Cedric Chappelier, Marco Gori, Alain Grumbach On the Need for a Neural Abstract Machine by Diego Sona, Alessandro Sperduti Part 3: Sequence Discovery with Symbolic Methods Sequence Mining in Categorical Domains: Algorithms and Applications by Mohammed J. Zaki Sequence Learning in the ACT-R Cognitive Architecture: Empirical Anal- ysis of a Hybrid Model by Christian Lebiere, Dieter Wallach Part 4: Sequential Decision Making Sequential Decision Making Based on Direct Search by Jurgen Schmidhuber Automatic Segmentation of Sequences through Hierarchical Reinforcement Learning by Ron Sun, Chad Sessions Hidden-Mode Markov Decision Processes for Nonstationary Sequential De- cision Making by Samuel P. M. Choi, Dit-Yan Yeung, Nevin L. Zhang Pricing in Agent Economies Using Neural Networks and Multi-agent Q- learning by Gerald Tesauro Part 5: Biologically Inspired Sequence Learning Models Multiple Forward Model Architecture for Sequence Processing by Raju S. Bapi, Kenji Doya Integration of Biologically Inspired Temporal Mechanisms into a Cortical Framework for Sequence Processing by Herve Frezza-Buet, Nicolas Rougier, Frederic Alexandre Attentive Learning of Sequential Handwriting Movements: A Neural Net- work Model by Stephen Grossberg, Rainer Paine About Editors Author Index ------------------------------------------------------------ To order, go to http://www.cecs.missouri.edu/~rsun/book5-ann.html http://www.springer.de/cgi-bin/search_book.pl?isbn=3-540-41597-1 http://www.springer.de/comp/lncs/ http://www.cecs.missouri.edu/~rsun/ 2001. XII, 391 pp. Softcover 3-540-41597-1 DM 82, Recommended List Price http://www.springer.de/contact.html phone +49 6221 487 0 =========================================================================== Prof. Ron Sun http://www.cecs.missouri.edu/~rsun CECS Department phone: (573) 884-7662 University of Missouri-Columbia fax: (573) 882 8318 201 Engineering Building West Columbia, MO 65211-2060 email: rsun at cecs.missouri.edu http://www.cecs.missouri.edu/~rsun http://www.cecs.missouri.edu/~rsun/journal.html http://www.elsevier.com/locate/cogsys =========================================================================== From lunga at ifi.unizh.ch Sat Jan 27 12:38:08 2001 From: lunga at ifi.unizh.ch (Max Lungarella) Date: 27 Jan 2001 18:38:08 +0100 Subject: CALL FOR CONTRIBUTIONS - EDEC2001 Message-ID: <3A730780.CDD8875C@ifi.unizh.ch> CALL FOR CONTRIBUTIONS EDEC2001 - EMERGENCE AND DEVELOPMENT OF EMBODIED COGNITION Symposium at the 3rd International Conference on Cognitive Science August 27-31, 2001, Beijing, China SCOPE The objective of the symposium is to bring together researchers from cognitive science, psychology, engineering, robotics, artificial intelligence, philosophy, and related fields so as to further our understanding of embodiment and development, in particular their mutual relationship. Ultimately, the goal is to understand the emergence of high-level cognition of an organism interacting with its physical and social environment over extended periods of time. FOCUS The symposium will focus on research that explicitly takes embodiment into account, either at the level of computational models, or real-world devices, and on empirical work that explicitly attempts to explain the relation of developmental processes to embodiment. Finally, contributions giving a broad and novel philosophical or methodological view on embodied cognition are welcome. CONTRIBUTIONS Contributions are solicited from the following areas (but not restricted to this list): - Cognitive developmental robotics - Neural mechanisms of learning and development (e.g. neural networks, statistical, information theoretic) - Development of sensory and motor systems - Perception-action coupling, sensory-motor coordination - Categorization, object exploration - Communication and Social interaction - Methodologies - Debates and philosophical issues (e.g. constructivism vs. selectionism, nature nurture, scalability, symbol grounding) ORGANIZATION This will be a one-day symposium with a number of talks, with a lot of room for discussion, and a poster session. The poster session will be over a cocktail to ensure relaxed atmosphere. FORM OF CONTRIBUTION Contributions can be in the form of full papers, or abstracts for posters. Full papers must be 5 pages maximum, with fonts at least 12 pt. For posters and work in progress, please submit a one-page abstract. Accepted contributions will be published in the proceedings of the ICCS 2001. GUIDELINES FOR ABSTRACT/PAPER SUBMISSION The contribution should be submitted electronically to lunga at ifi.unizh.ch (Max Lungarella) in pdf, or MS Word files. IMPORTANT DATES Full papers submission: March 30, 2001 One-page abstracts submission: April 30, 2001: Notice of acceptance: May 30, 2001 PROGRAM COMMITTEE Rolf Pfeifer (AI Lab, University of Zurich, chair) Max Lungarella (AI Lab, University of Zurich, Switzerland) Yasuo Kuniyoshi (Electrotechnical Laboratory, Tsukuba, Japan) Olaf Sporns (Department of Psychology, Indiana University, Bloomington, IN, USA) Giorgio Metta (LIRA-Lab, University of Genova, Italy) Giulio Sandini (LIRA-Lab, University of Genova, Italy) Rafael Nunez (University of Fribourg, Switzerland, and University of California, Berkeley) FOR MORE INFORMATION email: lunga at ifi.unizh.ch From arenart at delta.ft.uam.es Mon Jan 29 10:25:48 2001 From: arenart at delta.ft.uam.es (arenart) Date: Mon, 29 Jan 2001 15:25:48 +0000 (GMT) Subject: PhD Scolarship in Computational Neuroscience in Madrid. Message-ID: PhD SCHOLARSHIP IN COMPUTATIONAL NEUROSCIENCE DEPARTMENT OF THEORETICAL PHYSICS UNIVERSIDAD AUTONOMA DE MADRID MADRID - SPAIN One PhD scholarship is available at the group of Computational Neuroscience of the Universidad Autonoma de Madrid (UAM) for thesis research on computational approaches to brain function. The scholarship is to work with Prof Nestor Parga and colleagues to develop and apply theoretical techniques to study information processing in the brain. The appointee will be working collaboratively as part of a team. Highly motivated candidates should have a degree in a relevant scientific discipline such as Physics, Mathematics, Computer Science, or a Neuroscience-related discipline, have knowledge of basic computer programming and an interest in computational approaches to brain function (information theory, statistical physics, numerical simulations). The scholarship is for a period of four years, starting after the summer of 2001. Candidates should be citizens from countries members of the European Union. For more information about the group activities see: http://ket.ft.uam.es/~neurociencia/GRUPO/grupo_english.html or, in spanish: http://ket.ft.uam.es/~neurociencia/GRUPO/grupo.html Candidates should contact us as soon as possible (in any case before February the 8th) by sending their CV together with the name of two references by email or fax to: Jaime de la Rocha: E-mail: jrocha at delta.ft.uam.es Fax: (+34) 91 397-3936 ------------------------------------------------------------------- | Jaime de la Rocha | | | Phone : (+34) 91-397-4884 | | Dpto. de Fisica Teorica, C-XI | Fax : (+34) 91-397-3936 | | Universidad Autonoma de Madrid | E-mail: jrocha at delta.ft.uam.es| | 28049 Madrid, SPAIN | | | | | http://ket.ft.uam.es/~neurociencia/GRUPO/grupo_english.html | ------------------------------------------------------------------- From nolfi at www.ip.rm.cnr.it Mon Jan 29 11:49:01 2001 From: nolfi at www.ip.rm.cnr.it (Stefano Nolfi) Date: Mon, 29 Jan 2001 17:49:01 +0100 Subject: Evolutionary Robotics: new book and software available Message-ID: <3.0.2.32.20010129174901.00efb96c@www.ip.rm.cnr.it> (Our apologies for multiple copies of this message) EVOLUTIONARY ROBOTICS THE BIOLOGY, INTELLIGENCE, AND TECHNOLOGY OF SELF-ORGANIZING MACHINES Stefano Nolfi and Dario Floreano MIT Press/ Bradford Books Evolutionary robotics is a new technique for the automatic creation of autonomous robots. Inspired by the Darwinian principle of selective reproduction of the fittest, it views robots as autonomous artificial organisms that develop their own skills in close interaction with the environment and without human intervention. Drawing heavily on biology and ethology, it uses the tools of neural networks, genetic algorithms, dynamic systems, and biomorphic engineering. The resulting robots share with simple biological systems the characteristics of robustness, simplicity, small size, flexibility, and modularity. In evolutionary robotics, an initial population of artificial chromosomes, each encoding the control system of a robot, is randomly created and put into the environment. Each robot is then free to act (move, look around, manipulate) according to its genetically specified controller while its performance on various tasks is automatically evaluated. The fittest robots then "reproduce" by swapping parts of their genetic material with small random mutations. The process is repeated until the "birth" of a robot that satisfies the performance criteria. This book describes the basic concepts and methodologies of evolutionary robotics and the results achieved so far. An important feature is the clear presentation of a set of empirical experiments of increasing complexity. Software with a graphic interface, freely available on a Web page (http://gral.ip.rm.cnr.it/evorobot/simulator.html), allows the reader to replicate and vary (in simulation and on real robots) most of the experiments. Stefano Nolfi is Coordinator of the Division of Neural Systems and Artificial Life, Institute of Psychology, National Research Council, Rome. Dario Floreano is Assistant Professor of Evolutionary and Adaptive Systems at the Swiss Federal Institute of Technology in Lausanne (EPFL). CONTENTS 1. The Role of Self-organization for the Synthesis and the Understanding of Behavioral Systems 2. Evolutionary and Neural Techniques 3. How to Evolve Robots 4. Evolution of Simple Navigation 5. Power and Limits of Reactive Intelligence 6. Beyond Reactive Intelligence 7. Learning and Evolution 8. Competitive Co-Evolution 9. Encoding, Mapping, and Development 10. Complex Hardware Morphologies: Walking Machines 11. Evolvable Hardware Intelligent Robots and Autonomous Agents series edited by Ronald C. Arkin, MIT Press. November 2000 ISBN 0-262-14070-5 384 pp., 157 illus. The book is distributed by MIT Press: http://mitpress.mit.edu/book-home.tcl?isbn=0262140705 It is also available trough amazon: http://www.amazon.com/exec/obidos/ASIN/0262140705/qid%253D967489468/sr%253D1 -2/105-3677959-5763124 To download the Evorobot software visit: http://gral.ip.rm.cnr.it/evorobot/simulator.html For more information about Evolutionary Robotics visit: http://gral.ip.rm.cnr.it/evorobot/ -------------------------------------------------------------------------- Stefano Nolfi Institute of Psychology, C.N.R. Viale Marx, 15 - 00137 - Rome - Italy voice: 0039-06-86090231 fax: 0039-06-824737 e-mail: nolfi at ip.rm.cnr.it www: http://gral.ip.rm.cnr.it/nolfi From ken at phy.ucsf.edu Mon Jan 29 15:49:05 2001 From: ken at phy.ucsf.edu (Ken Miller) Date: Mon, 29 Jan 2001 12:49:05 -0800 (PST) Subject: Paper Available: Model of cat V1 nonlinear response properties Message-ID: <14965.55105.406468.602701@coltrane.ucsf.edu> The following paper is now available from: http://www.keck.ucsf.edu/~ken [click on 'publications', then click on 'models of neuronal integration and circuits'] or directly by ftp: ftp://ftp.keck.ucsf.edu/pub/ken/kayser_etal.pdf (pdf file) ftp://ftp.keck.ucsf.edu/pub/ken/kayser_etal.ps.gz (gzipped postscript) "Contrast-Dependent Nonlinearities Arise Locally in a Model of Contrast-Invariant Orientation Tuning" by Andrew Kayser, Nicholas J. Priebe, and Kenneth D. Miller In Press, Journal of Neurophysiology ABSTRACT: We study a recently proposed ``correlation-based'', push-pull model of the circuitry of layer 4 of cat visual cortex (Troyer et al., 1998). This model was previously shown to explain the contrast-invariance of cortical orientation tuning. Here we show that it can simultaneously account for several contrast-dependent (c-d) ``nonlinearities'' in cortical responses. These include an advance with increasing contrast in the temporal phase of response to a sinusoidally modulated stimulus; a change in shape of the temporal frequency tuning curve, so that higher temporal frequencies may give little or no response at low contrast but reasonable responses at high contrast; and contrast saturation that occurs at lower contrasts in cortex than in the lateral geniculate nucleus (LGN). In the context of the model circuit, these properties arise from a mixture of nonlinear cellular and synaptic mechanisms: short-term synaptic depression, spike-rate adaptation, contrast-induced changes in cellular conductance, and the nonzero spike threshold. The former three mechanisms are sufficient to explain the experimentally observed increase in c-d phase advance in cortex relative to LGN. The c-d changes in temporal frequency tuning arise as a threshold effect: voltage modulations in response to higher-frequency inputs are only slightly above threshold at lower contrast, but become robustly suprathreshold at higher contrast. The other three nonlinear mechanisms also play a crucial role in this result, allowing contrast-dependence of temporal frequency tuning to coexist with contrast-invariance of orientation tuning. Contrast saturation, and the observation that responses to stimuli of increasing temporal frequency saturate at increasingly high contrasts, can be induced both by the model's push-pull inhibition and by synaptic depression. Previous proposals explained these nonlinear response properties by assuming contrast-invariant orientation tuning as a starting point, and adding normalization by shunting inhibition derived equally from cells of all preferred orientations. The present proposal simultaneously explains both contrast-invariant orientation tuning and these contrast-dependent nonlinearities, and requires only processing that is local in orientation, in agreement with intracellular measurements (Ferster, 1986; Anderson et al., 2000). Ken Kenneth D. Miller telephone: (415) 476-8217 Associate Professor fax: (415) 476-4929 Dept. of Physiology, UCSF internet: ken at phy.ucsf.edu 513 Parnassus www: http://www.keck.ucsf.edu/~ken San Francisco, CA 94143-0444 From ml_conn at infrm.kiev.ua Mon Jan 29 17:17:14 2001 From: ml_conn at infrm.kiev.ua (Dmitri Rachkovskij) Date: Tue, 30 Jan 2001 00:17:14 +0200 (UKR) Subject: Connectionist symbol processing: any progress? References: <200101230057.CWA74441@kozlik.carrier.kiev.ua> Message-ID: <2.07b5.23A15.G7Y38Q@infrm.kiev.ua> Keywords: distributed representation, sparse coding, binary coding, binding, variable binding, representation of structure, structured representation, recursive representation, nested representation, compositional distributed representations, connectionist symbol processing Dear Colleagues, The following paper (abstract enclosed): Rachkovskij, Dmitri A. and Kussul, Ernst M. (2001) Binding and Normalization of Binary Sparse Distributed Representations by Context-Dependent Thinning. Neural Computation 13(2): 411-45 will be on-line for NC subscribers at http://neco.mitpress.org/. For those without access to Neural Computation, a draft is available at: http://cogprints.soton.ac.uk/documents/disk0/00/00/12/40/index.html or by ID code: cog00001240 at http://cogprints.soton.ac.uk/ Thank you and best regards, Dmitri Rachkovskij ************************************************************************* Dmitri A. Rachkovskij, Ph.D. Net: dar at infrm.kiev.ua Senior Researcher, V.M.Glushkov Cybernetics Center, Tel: 380 (44) 266-4119 Pr. Acad. Glushkova 40, Kiev 03680, UKRAINE Fax: 380 (44) 266-1570 ************************************************************************* Encl: Abstract Distributed representations were often criticized as inappropriate for encoding of data with a complex structure. However Plate's Holographic Reduced Representations and Kanerva's Binary Spatter Codes are recent schemes that allow on-the-fly encoding of nested compositional structures by real-valued or dense binary vectors of fixed dimensionality. In this paper we consider procedures of the Context-Dependent Thinning which were developed for representation of complex hierarchical items in the architecture of Associative-Projective Neural Networks. These procedures provide binding of items represented by sparse binary codevectors (with low probability of 1s). Such an encoding is biologically plausible and allows a high storage capacity of distributed associative memory where the codevectors may be stored. In contrast to known binding procedures, Context-Dependent Thinning preserves the same low density (or sparseness) of the bound codevector for varied number of component codevectors. Besides, a bound codevector is not only similar to another one with similar component codevectors (as in other schemes), but it is also similar to the component codevectors themselves. This allows the similarity of structures to be estimated just by the overlap of their codevectors, without retrieval of the component codevectors. This also allows an easy retrieval of the component codevectors. Examples of algorithmic and neural-network implementations of the thinning procedures are considered. We also present representation examples for various types of nested structured data (propositions using role-filler and predicate-arguments representation schemes, trees, directed acyclic graphs) using sparse codevectors of fixed dimension. Such representations may provide a fruitful alternative to the symbolic representations of traditional AI, as well as to the localist and microfeature-based connectionist representations. From oby at cs.tu-berlin.de Tue Jan 30 09:13:52 2001 From: oby at cs.tu-berlin.de (Klaus Obermayer) Date: Tue, 30 Jan 2001 15:13:52 +0100 (MET) Subject: papers available Message-ID: <200101301413.PAA24205@pollux.cs.tu-berlin.de> Dear Connectionists, attached please find abstracts and preprint locations of two manuscripts with results in the neuronformatics area (confocal microscopy). Comments are welcome! Cheers Klaus ------------------------------------------------------------------------- Prof. Dr. Klaus Obermayer phone: 49-30-314-73442 FR2-1, NI, Informatik 49-30-314-73120 Technische Universitaet Berlin fax: 49-30-314-73121 Franklinstrasse 28/29 e-mail: oby at cs.tu-berlin.de 10587 Berlin, Germany http://ni.cs.tu-berlin.de/ ========================================================================= Visualization of synaptic markers in the optic neuropils of Drosophila using a new constrained deconvolution method. P. R. Hiesinger^1, M. Scholz^2, I. A. Meinertzhagen^3, K.-F. Fischbach^1, and K. Obermayer^2. ^1 Institut fuer Biologie III, Universitaet Freiburg, Freiburg, Germany ^2 Fakultaet fuer Elektrotechnik und Informatik, TU Berlin, Berlin, Germany ^3 Neuroscience Institute, Dalhousie University, Halifax, Canada The fruitfly Drosophila melanogaster offers compelling genetic advantages for the analysis of its nervous system, but cell size precludes immunocytochemical analysis of wild-type structure and mutant phenotypes beyond the level of neuronal arborizations. For many antibodies, especially when immunoelectron microscopy is not feasible, it would therefore be desirable to extend the resolution limit of confocal microscopy as far as possible. Because high-resolution confocal microscopy suffers from considerable blurring, so-called deconvolution algorithms are needed to remove, at least partially, the blur introduced by the microscope and by the specimen itself. Here, we present the establishment and application of a new deconvolution method to visualize synaptic markers in Drosophila optic neuropils at the resolution limit of light. We ascertained all necessary parameters experimentally and verified them by deconvolving injected fluorescent microshperes in immunostained optic lobe tissue. The resulting deconvolution method was used to analyze colocalization between the synaptic vesicle marker neuronal synaptobrevin and synaptic and putative synaptic markers in photoreceptor terminals. We report differential localization of these near the resolution limit of light, which could not be distinguished without deconvolution. in: Journal of Comparative Neurology 429, 277ff. available at: http://ni.cs.tu-berlin.de/publications/ ------------------------------------------------------------------------- Corrections methods for three-dimensional reconstructions from confocal images: I. tissue shrinking and axial scaling. D. Bucher^1, M. Scholz^2, M. Stetter^2, K. Obermayer^2, and H.-J. Pflueger^1 ^1 Institut fuer Biologie, FU Berlin, Berlin, Germany ^2 Fakultaet fuer Elektrotechnik und Informatik, TU Berlin, Berlin, Germany We show here, using locust wholemount ganglia as an example, that scaling artifacts in three-dimensional reconstructions from confocal microscopic images due to refractive index mismatch in the light path and tissue shrinking, can account for dramatic errors in measurements of morphometric values. Refractive index mismatch leads to considerable alteration of the axial dimension, and true dimensions must be restored by rescaling the z-axis of the image stack. The appropriate scaling factor depends on the refractive indices of the media in the light path and the numerical aperture of the objective used and can be determined by numerical simulations, as we show here. In addition, different histochemical procedures were tested in regard to their effect on tissue dimensions. Reconstructions of scans at different stages of these protocols show that shrinking can be avoided prior to clearing when dehydrating ethanol series are carefully applied. Fixation and mismatching buffer osmolarity have no effect. We demonstrate procedures to reduce artifacts during mounting and clearing in methyl salicylate, such that only isometric shrinkage occurs, which can easily be corrected by rescaling the image dimensions. Glycerol-based clearing agents produced severe anisometric and nonlinear shrinkage and we could not find a way to overcome this. in: Journal of Neuroscience Methods 100, 135ff available at: http://ni.cs.tu-berlin.de/publications/ From d.mareschal at bbk.ac.uk Tue Jan 30 11:17:54 2001 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Tue, 30 Jan 2001 17:17:54 +0100 Subject: Phd Studentships Message-ID: Dear all, The School of Psychology, Birkbeck College, University of London has a number of studentships on offer for students beginning MPhil/Phd programmes in October 2001. Details of the studentships available can be found at the following web page http://www.psyc.bbk.ac.uk/announce/studentship2001.htm The School of Psychology (which includes the Centre for Brain and Cognitive Development and the Centre for Psychosocial Studies) has strong research interests in a range of areas including Cognitive Science, Child and Family Studies, Cognition and Action. Details of the research interests of staff in the school can be obtained from: http://www.psyc.bbk.ac.uk ================================================= Dr. Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 020 7631-6582/6207 fax +44 020 7631-6312 http://www.psyc.bbk.ac.uk/staff/dm.html ================================================= From mccallum at whizbang.com Wed Jan 31 13:22:09 2001 From: mccallum at whizbang.com (Andrew McCallum) Date: Wed, 31 Jan 2001 13:22:09 -0500 Subject: CFP IJCAI'01 Workshop on "Text Learning: Beyond Supervision" Message-ID: <200101311822.NAA09303@slide.whizbang.com> CALL FOR PAPERS IJCAI-01 Workshop on "Text Learning: Beyond Supervision" Monday, 6 August 2001 Seattle, Washington, USA www.cs.cmu.edu/~mccallum/textbeyond Submission deadline: March 23, 2001 Due to the rapidly increasing amount of textual data available and the range of interesting and important problems arising in text analysis, there has been growing interest in applying machine learning methods to text. There has also been significant recent interest in research that combines supervised and unsupervised learning. This research is especially relevant to text learning because the inherent complexity of natural language usually requires models with many parameters: estimating those parameters requires a lot of data, and obtaining labeled data is difficult and expensive. By combining unsupervised learning with supervised learning, the need for labeled training data can often be greatly reduced, allowing for the development of more powerful models and methods. The workshop will explore machine learning methods for solving supervised text learning tasks that exploit training methods beyond straightforward supervised learning. Relevant topics include: * Text classification with labeled and unlabeled data: EM, co-training, transduction with SVMs, discriminative maximum entropy with unlabeled data. * Information extraction with unlabeled data: bootstrapping, co-boosting. * Part-of-speech tagging, parsing and other NLP with unlabeled data. * Active learning: uncertainty sampling, query-by-committee, version space reduction. * Model selection with unlabeled data. * Word clustering for language modeling, distributional clustering, feature generation by clustering. * Semi-supervised clustering, document clustering with user-feedback. * Integrating prior knowledge into supervised learning, integrating distantly labeled data. * Unsupervised methods for learning segmentation models, translation models, lexicons, etc. * Link analysis for supervised learning. The goal of this workshop is to bring together researchers from the machine learning, information retrieval, computational linguistics and language modeling to talk about their different perspectives and to share their latest ideas. INVITED SPEAKERS ---------------- David Yarowsky Assistant Professor Department of Computer Science Johns Hopkins University http://www.cs.jhu.edu/~yarowsky Tommi Jaakkola Assistant Professor Department of Computer Science Massachusetts Institute of Technology http://www.ai.mit.edu/people/tommi/tommi.html SCHEDULE AND SUBMISSION PROCEDURE --------------------------------- Friday, Mar 23 2001 Paper submissions due Friday, Apr 06 2001 Acceptance notification Friday, Apr 20 2001 Camera ready papers due Authors are asked to prepare a paper in Postscript or PDF format. Submissions should conform to the IJCAI-2001 format, and be 8 pages or less. We encourage submissions containing original theoretical and applied concepts. Experimental results are also encouraged, even if they are only preliminary. To submit a paper, email it to textbeyond at whizbang.com before 6pm on the day of the deadline. ORGANIZING COMMITTEE -------------------- Andrew McCallum WhizBang Labs - Research, 4616 Henry Street, Pittsburgh, PA 15218 T: 412-683-9132 F: 412-683-4436 mccallum at whizbang.com http://www.cs.cmu.edu/~mccallum Kamal Nigam School of Computer Science, Carnegie Mellon, Pittsburgh, PA 15213 T: 412-268-3070 F: 412-268-5576 knigam at cs.cmu.edu http://www.cs.cmu.edu/~knigam Tony Jebara MIT, Media Laboratory - 20 Ames Street, E15-390, Cambridge, MA 02138 T: 617-253-0326 F: 617-253-8874 jebara at media.mit.edu http://www.media.mit.edu/~jebara Lillian Lee Department of Computer Science, Cornell University, Ithaca, NY 14853 T: 607-255-8119 F: 607-255-4428 llee at cs.cornell.edu http://www.cs.cornell.edu/home/llee From mike at soc.plym.ac.uk Tue Jan 2 06:47:15 2001 From: mike at soc.plym.ac.uk (Mike Denham) Date: Tue, 02 Jan 2001 11:47:15 +0000 Subject: Position in Auditory Psychophysics/Computational Neuroscience Message-ID: <200101021147.LAA15045@hebe.soc.plym.ac.uk> University of Plymouth, UK School of Computing, Centre for Neural and Adaptive Systems Plymouth Institute of Neuroscience Readership / Professorship in Auditory Psychophysics/Computational Neuroscience Applications are invited for a permanent academic position in the School of Computing. The successful candidate will have a strong current research activity in the area of auditory psychophysics, with an interest in theoretical and computational modelling of the auditory system. He/she will join the Centre for Neural and Adaptive Systems, a well-established research group with an international reputation, and the newly formed Plymouth Institute of Neuroscience. For appointment as a Reader or Professor, it will be necessary to meet the criteria set out by the University's Professorial Appointments Committee, with respect to academic standing and achievements. Further information about the post can be obtained via e-mail or telephone, from Professor Mike Denham (mike at soc.plym.ac.uk; tel: +44 (0)1752 232547). Michael J Denham Invensys Professor of Neural and Adaptive Systems Centre for Neural and Adaptive Systems School of Computing University of Plymouth Plymouth PL4 8AA England tel: +44 1752 232541 fax: +44 1752 232540 e-mail: mike @soc.plym.ac.uk; mdenham at plym.ac.uk http://www.tech.plym.ac.uk/soc/research/neural/index.html From mike at soc.plym.ac.uk Tue Jan 2 06:43:40 2001 From: mike at soc.plym.ac.uk (Mike Denham) Date: Tue, 02 Jan 2001 11:43:40 +0000 Subject: Position in Neural Computation / Computational Neuroscience Message-ID: <200101021143.LAA15035@hebe.soc.plym.ac.uk> University of Plymouth, UK School of Computing Centre for Neural and Adaptive Systems Readership / Professorship in Neural Computation / Computational Neuroscience Applications are invited for a permanent academic position in the School of Computing of the University of Plymouth. The successful candidate will have a strong current research activity in the area of neural and adaptive computation and/ or computational neuroscience, and an interest in contributing to the further development of the academic work of the School in this area. He/she will join the Centre for Neural and Adaptive Systems, a well-established research group with an international reputation. For appointment as a Reader or Professor, it will be necessary to meet the criteria set out by the University's Professorial Appointments Committee, with respect to academic standing and achievements. Further information about the post can be obtained via e-mail or telephone, from Professor Mike Denham (mike at soc.plym.ac.uk; tel: +44 (0)1752 232547). Michael J Denham Invensys Professor of Neural and Adaptive Systems Centre for Neural and Adaptive Systems School of Computing University of Plymouth Plymouth PL4 8AA England tel: +44 1752 232541 fax: +44 1752 232540 e-mail: mike @soc.plym.ac.uk; mdenham at plym.ac.uk http://www.tech.plym.ac.uk/soc/research/neural/index.html From P.McKevitt at ulst.ac.uk Wed Jan 3 14:40:51 2001 From: P.McKevitt at ulst.ac.uk (Prof Paul Mc Kevitt) Date: Wed, 3 Jan 2001 19:40:51 +0000 (GMT) Subject: University of Ulster (Magee): 2 Research Studentships Message-ID: Research Studentships Intelligent Systems/Intelligent Digital MultiMedia Interfaces Faculty of Informatics Intelligent Digital MultiMedia Interfaces The University of Ulster invites applicants for the above full-time Research Studentship to be situated at the Magee College campus and held within the MultiMedia Systems and Artificial Intelligence research groups of the Faculty of Informatics. The focus of the research will be to investigate the integration of the computational processing of digital multimedia (e.g. spoken dialogue, natural language and visual advanced interfaces) incorporating the modelling of emotions and automated storytelling with application to e.g. intelligent web-browsing and medical informatics. The studentship consists of an annual maintenance allowance of 10,000 pounds and payment of fees for up to three years. The successful candidate will be registered on a programme of study leading, subject to satisfactory progress, to the award of the degree of Doctor of Philosophy. Applicants should hold a minimum of an upper second Bachelor's and/or Master's degree in intelligent digital multimedia, computer science, cognitive science or a related subject and have good experience in, and be prepared for, computer programming, scientific experimentation and the use of existing software tools. Further information is available from: Professor Paul Mc Kevitt, http://www.infc.ulst.ac.uk/staff/p.mckevitt E-mail: p.mckevitt at ulst.ac.uk Phone: (+44) 028 71375433 Faculty of Engineering Intelligent Systems Applications are invited for a full-time research studentship, to investigate the application of intelligent systems technology in bionics. The research project is specifically concerned with the application of intelligent techniques and evolvable hardware to the design of self-adaptive medical prosthetics. The project will be supervised by Professor Martin McGinnity and Dr. Liam Maguire, and will involve collaboration with medical practitioners. The student will be based in the Intelligent Systems Engineering Laboratory, in the Faculty of Engineering on the Magee campus of the University. The laboratory is currently the base for 16 researchers engaged in a range of projects in the general area of intelligent systems. Further information is available at http://isel.scim.ulst.ac.uk. The studentship consists of an annual maintenance allowance of 10,000 pounds and payment of fees for up to three years. The successful candidate will be registered on a programme of study leading, subject to satisfactory progress, to the award of the degree of Doctor of Philosophy. Interested applicants may arrange to visit the laboratory by telephoning for an appointment (tel + 44 028-71375616). Applicants should hold a minimum of an upper second class honours degree in electronics, computing or closely related discipline. Preference may be given to candidates with first class degrees or a postgraduate qualification. Application materials for either award are available from: Angela Rippey, Research Office, University of Ulster, Cromore Road, Coleraine. E-mail: a.rippey at ulst.ac.uk Fax: (+44) 028 70324905 Phone: (+44) 028 70324592 The closing date for receipt of completed applications is Tuesday 6 February 2001. also found at: http://jobs.ac.uk/jobfiles/HH159.html LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL Professor Paul Mc Kevitt Chair in Digital MultiMedia School of Computing & Electronics Faculty of Informatics University of Ulster, Magee College BT48 7JL, Derry (Londonderry) NORTHERN IRELAND E-mail: p.mckevitt at ulst.ac.uk WWW: http://www.infc.ulst.ac.uk/staff/p.mckevitt FaX: (+44) 28 71375470 Phone: (+44) 28 71375433 (Office MG-221) (+44) 28 71375382 (School Office) LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL From cindy at cns.bu.edu Thu Jan 4 09:37:52 2001 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Thu, 4 Jan 2001 09:37:52 -0500 Subject: Neural Networks 14(1) Message-ID: <200101041437.JAA23594@retina.bu.edu> NEURAL NETWORKS 14(1) Contents - Volume 14, Number 1 - 2001 ------------------------------------------------------------------ CONTRIBUTED ARTICLES: ***** Neuroscience and Neuropsychology ***** A pattern correlation model of vestibulo-ocular reflex habituation T.J. Anastasio ***** Mathematical and Computational Analysis ***** Optimal control by least squares support vector machines J.A.K. Suykens, J. Vandewalle, and B. DeMoor Signal estimation and denoising using VC-theory V. Cherkassky and X. Shao Incremental projection learning for optimal generalization M. Sugiyama and H. Ogawa Properties of incremental projection learning M. Sugiyama and H. Ogawa Error correcting memorization learning for noisy training examples A. Nakashima, A. Hirabayashi, and H. Ogawa A real-coded genetic algorithm for training recurrent neural networks A. Blanco, M. Delgado, and M.C. Pegalajar A synthesis procedure for associative memories based on space-varying cellular neural networks J. Park, H.-Y. Kim, Y. Park, and S.-W. Lee The bifurcating neuron network 1 G. Lee and N.H. Farhat ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 or 660 SEK or Y 15,000 [including Neural Networks 2,000 entrance fee] or $55 (student) 460 SEK (student) Y 13,000 (student) [including 2,000 entrance fee] ----------------------------------------------------------------------------- membership without $30 200 SEK not available to Neural Networks non-students (subscribe through another society) Y 5,000 (student) [including 2,000 entrance fee] ----------------------------------------------------------------------------- Institutional rates $1132 2230 NLG Y 149,524 ----------------------------------------------------------------------------- Name: _____________________________________ Title: _____________________________________ Address: _____________________________________ _____________________________________ _____________________________________ Phone: _____________________________________ Fax: _____________________________________ Email: _____________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number ____________________________ expiration date ________________________ INNS Membership 19 Mantua Road Mount Royal NJ 08061 USA 856 423 0162 (phone) 856 423 3420 (fax) innshq at talley.com http://www.inns.org ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership c/o Professor Tsukada Faculty of Engineering Tamagawa University 6-1-1, Tamagawa Gakuen, Machida-city Tokyo 113-8656 Japan 81 42 739 8431 (phone) 81 42 739 8858 (fax) jnns at jnns.inf.eng.tamagawa.ac.jp http://jnns.inf.eng.tamagawa.ac.jp/home-j.html ----------------------------------------------------------------- From Thomas.Trappenberg at psy.ox.ac.uk Thu Jan 4 11:17:27 2001 From: Thomas.Trappenberg at psy.ox.ac.uk (Thomas Trappenberg) Date: Thu, 4 Jan 2001 16:17:27 -0000 Subject: Postdoctoral Position and Studentship in Computational Neuroscience in Oxford Message-ID: <000601c07669$d4f45580$200f4381@cogneuro.ox.ac.uk> Dear Colleagues, I want to bring to your attention an opening of a research position in computational neuroscience in Oxford. Further details are attached below. In addition, there is a full Studentship for UK citizens (or a partial Studentship for other nationalities) in our D.Phil program available. However, a rapid response to this Studentship (within two days) is required. Please write directly to Prof. Edmund Rolls (edmund.rolls at psy.ox.ac.uk). Regards, Thomas Trappenberg UNIVERSITY OF OXFORD DEPARTMENT OF EXPERIMENTAL PSYCHOLOGY Centre for Computational Neuroscience Postdoctoral post in Neural Computation Academic-Related Research Staff Grade 1A: Salary 16,775 - 25,213 A post is available as part of a long-term research programme for research combining neurophysiological and computational approaches to brain function. The post is to work with Prof E T Rolls and colleagues to develop and apply information theoretic and statistical methods to analyse data acquired from simultaneously recorded neurons, and to assist in the development of software to help acquire such data. The postholder will contribute to research aimed at understanding how information is represented in the primate visual system (see Appendix 2 of Rolls and Treves, 1998). Applicants should have a degree in a relevant scientific discipline (e.g. maths, physics, statistics or a neuroscience-related discipline), be able to program in C, and willing to work on Unix and PC systems. The appointee will be working collaboratively as part of a team. The appointment will be on the RS1A (postdoctoral) scale or RS1B scale (according to experience) for three years in the first instance. Before submitting an application, candidates should obtain further particulars from the Administrator, Department of Experimental Psychology, South Parks Road, Oxford OX1 3UD (email applications at psy.ox.ac.uk) or telephone 01865 271399 quoting Ref: CQ/etr/036 (neurophysiology post) or 037 (computational post). Further information on the research group may be found on the web-site http://www.cns.ox.ac.uk/ and on the Department at http://www.psych.ox.ac.uk/. Initial scientific enquiries about the post may be directed to Professor Edmund T. Rolls (email: edmund.rolls at psy.ox.ac.uk), who will be pleased to send papers to prospective applicants. From ckiw at dai.ed.ac.uk Thu Jan 4 11:27:42 2001 From: ckiw at dai.ed.ac.uk (Chris Williams) Date: Thu, 4 Jan 2001 16:27:42 +0000 (GMT) Subject: 2 Research fellow positions at the University of Edinburgh, UK Message-ID: The University of Edinburgh seeks to hire two research fellows in the area of astronomical databases/datamining. The position within the Division of Informatics will be based in the Institute for Adaptive and Neural Computation, where research in machine learning/probabilistic modelling is led by Dr. Chris Williams, Dr. David Barber (joining Spring 2001) and Prof. Chris Bishop. See http://www.roe.ac.uk/wfau/vacancy.html for further particulars on the jobs. Informal questions and requests for information can be sent to c.k.i.williams at ed.ac.uk Apologies if you receive this message multiple times. Dr Chris Williams c.k.i.williams at ed.ac.uk Institute for Adaptive and Neural Computation Division of Informatics, University of Edinburgh 5 Forrest Hill, Edinburgh EH1 2QL, Scotland, UK fax: +44 131 650 6899 tel: (direct) +44 131 651 1212 (department switchboard) +44 131 650 3090 http://anc.ed.ac.uk/ ------------------------------------------------------------------------- Two Postdoctoral Research Fellowships in Astronomical Databases and Datamining The University of Edinburgh seeks two postdoctoral researchers to join an interdisciplinary team working on astronomical databases and datamining. This new initiative brings together wide field astronomers from the Institute for Astronomy, computer scientists/applied mathematicians from the Division of Informatics and high performance computing specialists from the Edinburgh Parallel Computing Centre, to address issues ranging from the design and implementation of large astronomical databases to the use of machine learning and computational geometry techniques to characterise their contents. Candidates with a background in either astronomy or informatics are encouraged to apply. The posts are tenable for 2 years from 1 March 2001 (or soon thereafter), although this research is likely to be supported in the longer term through the Astro-Grid project expected to be funded by the UK Government's e-science initiative. The salary for each post will be on the AR1A (16,775-25,213 pounds pa) or AR2 (23,256 - 30,967 pounds pa) salary scale depending on age, qualifications and experience. Further particulars, including details of the application procedure, should be obtained from the Personnel Department, 9-16 Chambers Street, Edinburgh EH8 9TB or Tel: 0131 650 2511 (24 hour answering service) or www.personnel.ed.ac.uk/recruit.htm (advert will be posted in week beginning 8 January). The further particulars are also available at http://www.roe.ac.uk/wfau/vacancy.html. Closing date for receipt of applications is 31 January 2001. We cannot guarantee to consider late applications. Please quote ref 307014 (Institute for Astrnomy) or ref 307016 (Division of Informatics). Informal enquiries can be made to Dr Bob Mann (rgm at roe.ac.uk) in the Institute for Astronomy or Dr Chris Williams (c.k.i.williams at ed.ac.uk) in the Division of Informatics. From nello at dcs.rhbnc.ac.uk Thu Jan 4 18:36:14 2001 From: nello at dcs.rhbnc.ac.uk (Nello Cristianini) Date: Thu, 4 Jan 2001 23:36:14 +0000 (GMT) Subject: JMLR: Special Issue on Kernel Methods Message-ID: CALL FOR PAPERS Journal of Machine Learning Research Special Issue on "New Perspectives on Kernel Based Learning Methods" http://www.cs.rhbnc.ac.uk/colt/JMLRspecissue.html Guest Editors: Nello Cristianini, John Shawe-Taylor, Bob Williamson Important dates: Submission deadline: March 15th, 2001 Decision : May 15th, 2001 Final Versions : June 15th, 2001 Submission procedure: see webpage: http://www.cs.rhbnc.ac.uk/colt/JMLRspecissue.html Background: Recent theoretical advances and experimental results have drawn considerable attention to the use of kernel functions in learning systems. Support Vector Machines, Gaussian Processes, kernel PCA, kernel Gram-Schmidt, Bayes Point Machines, Relevance and Leverage Vector Machines, are just some of the algorithms that make crucial use of kernels for problems of classification, regression, density estimation, novelty detection and clustering. At the same time as these algorithms have been under development, novel techniques specifically designed for kernel-based systems have resulted in methods for assessing generalisation, implementing model selection, and analysing performance. The choice of model may be simply determined by parameters of the kernel, as for example the width of a Gaussian kernel. More recently, however, methods for designing and combining kernels have created a toolkit of options for choosing a kernel in a particular application. These methods have extended the applicability of the techniques beyond the natural Euclidean spaces to more general discrete structures. The field is witnessing growth on a number of fronts, with the publication of books, editing of special issues, organization of special sessions and web-sites. Moreover, a convergence of ideas and concepts from different disciplines is occurring. This special issue will accept papers in any of the following main research directions: 1) design of novel kernel-based algorithms 2) design of novel types of kernel functions 3) development of new learning theory concepts 4) application of the techniques to new problem areas More information at: http://www.cs.rhbnc.ac.uk/colt/JMLRspecissue.html Or: nello at dcs.rhbnc.ac.uk From grb at neuralt.com Fri Jan 5 15:19:18 2001 From: grb at neuralt.com (George Bolt) Date: Fri, 5 Jan 2001 20:19:18 -0000 Subject: Job Vacancy in UK's leading neural software products company - Ne ural Technologies Message-ID: <6156D7F3719BD3119D2A005004E99DAD65C388@ntl-exc1.neuralt.com> Neural Technologies Limited is the leading UK company working in the application and exploitation of neural computing and other advanced technologies across a wide range of industrial and commercial environments. Our continued growth has led to the requirement of an applied Neural Scientist to join our highly motivated team to help in the development and deployment of practical advanced computing solutions on a high profile projects. Do you want to apply your neural computing skills to solve real-world problems? Neural Technologies can offer you this opportunity - just some of the areas we work in are: * Telecommunications - fraud, churn, etc. * Finance - credit scoring, risk management, instrument trading, etc. * Marketing - modelling and analysis * * You will be expected to demonstrate not only high standards of professionalism but technical innovation second to none. Self-confidence, adaptability, proactivity and communication skills are as important as the technical skills. * * Required skills are: * Well versed in neural network and other advanced algorithm development and their practical application, should have at least 2 years applied knowledge of at least 2 of the following: * Feed-forward networks for classification and regression (e.g. MLP, RBF) * Feature mapping and clustering (e.g. VQ/LVQ, Kohonen/SOM, GTM) * Non-neural classification or regression methods (e.g. genetic algorithms, rule induction/decision trees, support vector machines, case based reasoning) * Basic statistical modelling techniques (e.g. linear/logistic regression, discriminant analysis, kernel techniques) * Proven problem solving abilities * Good mathematical background * * Experience of the following would also be an advantage: * Advanced statistical concepts (e.g. information theory, Bayesian statistics) * Data preparation (e.g. pre-processing techniques, imputation, data mining) * Application domains (credit scoring, fraud analysis, telecommunications, banking and finance) * Coding in MATLAB or C/C++ within the PC environment All candidates should be working at a practical research level or have extensive industrial experience. A keen view to the commercial realities of working within a small, but fast growing, company is required. Neural Technologies Limited operate a non-smoking policy. Please send your application & CV to Kathryn Cooper (kc at neuralt.com) together with any other enquiries. George Bolt Director of Product Innovation Neural Technologies Cafe Neural: http://www.neuralt.com Tel: +44 (0) 1730 260 256 Fax: +44 (0) 1730 260 466 NOTE Any views expressed in this message are those of the Individual sender, except where the sender specifically states them to be the views of Neural Technologies Limited This email contains information that is confidential and is for the exclusive use of the addressee. If you are not the addressee, please note that any distribution, dissemination, copying or use of this communication or the information in it is prohibited. From baolshausen at ucdavis.edu Sun Jan 7 16:40:47 2001 From: baolshausen at ucdavis.edu (Bruno Olshausen) Date: Sun, 07 Jan 2001 13:40:47 -0800 Subject: graduate/postdoctoral fellowships, UC Davis Message-ID: <3A58E25F.FD2B4B29@ucdavis.edu> GRADUATE AND POSTDOCTORAL TRAINING IN NEUROSCIENCE UNIVERSITY OF CALIFORNIA, DAVIS The Graduate Program in Neuroscience at the University of California, Davis offers interdisciplinary training in areas spanning from molecular to cognitive neuroscience. Many research opportunities exist for students and postdocs interested in computational modeling approaches to problems in neuroscience. The Center for Neuroscience and the Institute for Theoretical Dynamics provide students and faculty with numerous research facilities and an excellent environment for combining theoretical and experimental approaches. The Center for Neuroscience also offers postdoctoral training via an NIH sponsored training grant. Relevant faculty include: David Amaral - structure and function of hippocampus, amygdala Marie Burns - photoreceptors, molecular mechanisms of transduction Ken Britten - visual cortex, neural basis of motion perception Leo Chalupa - retinal neurophysiology, development Barbara Chapman - development and plasticity of sensory systems Will DeBello - auditory system development Fred Gorin - molecular neurobiology, neuroinformatics Andrew Ishida - retinal ganglion cells, synaptic integration Ted Jones - thalamo-cortical interactions, neuroinformatics Leah Krubitzer - cortical organization, comparative anatomy Kim McAllister - synaptic physiology, development Brian Mulloney - central pattern generator circuits for locomotion Bruno Olshausen - computational models of vision, efficient coding Gregg Recanzone - plasticity in auditory cortex Karen Sigvart - neural control of locomotion, Parkinson's disease Mitch Sutter - cortical mechanisms of auditory perception Marty Usrey - retina/LGN/V1 physiology, neural circuits and spike timing Jack Werner - color vision and aging Martin Wilson - synaptic transmission in the retina Ewa Wojciulik - visual attention, functional imaging Andy Yonelinas - memory, functional imaging *** Application deadline for fall admissions is January 15, 2001. *** The application deadline may be nominally met by submitting an online application and fee, along with a form letter, via the web site: http://neuroscience.ucdavis.edu/grad Further information and appplication materials may be obtained from: Nikki Larramendy tel: (530) 757-8845 Center for Neuroscience fax: (530) 757-8827 University of California, Davis e-mail: nslarramendy at ucdavis.edu 1544 Newton Ct. Davis, California 95616-8599 or Karen Sigvardt, Program Chair kasigvardt at ucdavis.edu (530) 757-8820 Those interested in postdoctoral fellowships should contact the potential sponsor (faculty member) directly. Email addresses/web pages of faculty may be obtained from the Center for Neuroscience web page: http://neuroscience.ucdavis.edu/ Davis is located approximately 15 miles west of Sacramento, the state capital. It is a unique community with miles of bicycle paths and beautiful parks, and in close proximity to the Napa and Sonoma wine country, the San Francisco bay area, Lake Tahoe and the High Sierra. From marley at ele.puc-rio.br Mon Jan 8 10:55:11 2001 From: marley at ele.puc-rio.br (Marley Vellasco) Date: Mon, 08 Jan 2001 12:55:11 -0300 Subject: Neuro-Fuzzy Special Session in IWANN2001 Conference Message-ID: <3A59E2DF.456B9912@ele.puc-rio.br> I apologize, in advance, if you receive more than one copy of this message. ________________________________________________________ Call for Papers to the special session, called "NEURO-FUZZY SYSTEMS",of the IWANN2001 - 6th. International Work-Conference on Artificial and Natural Neural Networks "Biological and Artificial Computation: Methodologies, Neural Modeling and Bioengineering Applications" which will be held in Palacio de Exposiciones y Congresos, Granada, Spain from June 13-15, 2001 This special session aims to present new developments in Neuro-Fuzzy modelling, as well as new applications. Important Dates: Final Date for Submission - February 28, 2001 Acceptance notification and start of inscription - March 31, 2001 End of reduction fee for early inscription - April 30, 2001 One hard copy of each paper should be sent to: Marley Vellasco Depto. Eng. El=E9trica - PUC-RIO Rua Marques de Sao Vicente, 225 - Gavea Rio de Janeiro - RJ - BRAZIL - 22453-900 and two extra copies should be sent to the General Chairman: Jose Mira Mira Depto. Inteligencia Artificial - UNED Senda Del Rey, 9 E-28040 Madrid - Spain I would appreciate if you could divulge this special session as widely as possible. All details for the submission of papers can be found at: http://iwann.dia.uned.es/ Looking forward to seeing you in Granada. Marley Vellasco From smithmt at MIT.EDU Mon Jan 8 10:42:09 2001 From: smithmt at MIT.EDU (Marilyn T. Smith) Date: Mon, 8 Jan 2001 10:42:09 -0500 Subject: Faculty Position Search Message-ID: FACULTY POSITION AT MIT MCGOVERN INSTITUTE FOR BRAIN RESEARCH AND DEPARTMENT OF BRAIN AND COGNITIVE SCIENCES McGovern Institute is seeking outstanding scientists with a strong record of research accomplishments for positions at any level. Positions are joint appointments with the MIT Department of Brain and Cognitive Sciences and Assistant Professor positions are tenure-track. Successful applicants will be expected to develop a significant and independent research program and have a commitment to excellence in undergraduate and graduate education. The applicant's research program should address issues pertinent to the higher functions of the brain. We are particularly interested in candidates pursuing research in the area of experimental and computational investigations of integrated neural systems in animals with complex behavior. Investigators using imaging techniques to explore dynamic neuronal functions are specifically encouraged to apply. Applicants should submit a curriculum vitae, including a summary of current and proposed research programs, and should arrange for three letters of recommendation to be sent to: MIBR Search Committee Attn: Marilyn Smith Massachusetts Institute of Technology, Room E17-529 77 Massachusetts Avenue Cambridge, MA 02139 Consideration of completed applications will begin on March 1, 2001. MIT is an Affirmative Action/Equal Opportunity employer. Qualified women and minority candidates are especially encouraged to apply. --============_-1233153965==_ma============ Content-Type: text/enriched; charset="us-ascii" FACULTY POSITION AT MIT MCGOVERN INSTITUTE FOR BRAIN RESEARCH AND DEPARTMENT OF BRAIN AND COGNITIVE SCIENCES McGovern Institute is seeking outstanding scientists with a strong record of research accomplishments for positions at any level. Positions are joint appointments with the MIT Department of Brain and Cognitive Sciences and Assistant Professor positions are tenure-track. Successful applicants will be expected to develop a significant and independent research program and have a commitment to excellence in undergraduate and graduate education. The applicant's research program should address issues pertinent to the higher functions of the brain. We are particularly interested in candidates pursuing research in the area of experimental and computational investigations of integrated neural systems in animals with complex behavior. Investigators using imaging techniques to explore dynamic neuronal functions are specifically encouraged to apply. Applicants should submit a curriculum vitae, including a summary of current and proposed research programs, and should arrange for three letters of recommendation to be sent to: MIBR Search Committee Attn: Marilyn Smith Massachusetts Institute of Technology, Room E17-529 77 Massachusetts Avenue Cambridge, MA 02139 Consideration of completed applications will begin on March 1, 2001. MIT is an Affirmative Action/Equal Opportunity employer. Qualified women and minority candidates are especially encouraged to apply. From smyth at sifnos.ICS.UCI.EDU Mon Jan 8 19:21:25 2001 From: smyth at sifnos.ICS.UCI.EDU (Padhraic Smyth) Date: Mon, 08 Jan 2001 16:21:25 -0800 Subject: Call for Papers and Announcement for INTERFACE '01 Message-ID: <200101081621.aa12556@gremlin-relay.ics.uci.edu> INTERFACE '01 ANNOUNCEMENT AND CALL FOR PAPERS JUNE 13-16, 2001, ORANGE COUNTY, CA http://www.ics.uci.edu/interface PAPER DEADLINE: MARCH 15th 2001 The 33rd Annual Symposium on the Interface of Computer Science and Statistics will be held June 13-16, 2001 in Orange County, CA. The Interface is the premier annual conference at the increasingly active intersection of computer science and statistics, attracting 300 or more attendees. This year's themes are data mining and bioinformatics with invited speakers on massive data sets, graphical models, support vector machines, Bayesian methods in bioinformatics, analyzing Web data, statistical models for text, model-based clustering, computational finance, data visualization, and many more. A special day on bioinformatics will be scheduled on June 16th with invited sessions on biological sequence analysis, gene expression data, brain imaging, and medical data management and analysis. You are cordially invited to submit a contributed paper for presentation at the Symposium. We welcome papers on all topics of potential relevance to the interface of computer science and statistics. This year, we are particularly interested in increasing submissions from computer scientists active in machine learning and related areas. Submissions should consist of a 200-word abstract with a 4-page short paper, and are due by MARCH 15th. Electronic submission of abstracts and papers will be required, with the details appearing shortly on the conference Web site at www.ics.uci.edu/interface. The complete text of papers presented at the Symposium will appear in the Interface '01 Proceedings to be published as a CD-ROM by IFNA (The Interface Foundation for North America). Arnold Goodman Padhraic Smyth [Interface '01 Program Chairs] [University of California, Irvine] From berthold at cs.berkeley.edu Mon Jan 8 19:23:01 2001 From: berthold at cs.berkeley.edu (Michael Berthold) Date: Mon, 8 Jan 2001 16:23:01 -0800 (PST) Subject: Spring School on Intelligent Data Analysis in Palermo, Sicily Message-ID: >>>> Funding for Young Researchers available! <<<< >>>> Deadline for Funding Applications: 15. Jan 2001 <<<< Call for Participation SPRING SCHOOL ON INTELLIGENT DATA ANALYSIS March 26-30, 2001 Palermo, Sicily Over the last decade or so, the size of machine-readable data sets has increased dramatically and the problem of "data explosion" has become apparent. In parallel with this recent developments in computing have provided the basic infrastructure for fast access to online data. In particular many advanced computational methods for extracting information from large quantities of heterogeneous data and for data representation are now beginning to mature. These developments have created a new range of problems and challenges for the analysts, as well as new opportunities for intelligent systems in data analysis. All this has led to the emergence of the field of Intelligent Data Analysis (IDA), a combination of diverse disciplines including Artificial Intelligence and Statistics in particular. The School on Intelligent Data Analysis (IDA) will focus on the core techniques of this exciting new area: - Statistics, - Bayesian Networks, - Neural networks, - Time Series Analysis, - Rule Induction, - Fuzzy Logic, - Evolutionary Computation. All courses are organized as to provide a wide description of the theoretical and practical aspects of each discipline. For this purpose also speakers from industry are invited to show practical and already implemented applications of Intelligent Data Analysis techniques. The target audience of the IDA Summer School are advanced undergraduate students, PhD students, postdoctoral students and academic and industrial researchers and developers. The Summer School will take place at the University of Palermo (Italy) from March, 26th until March, 30th, 2001. More information - including the preliminary program and the list of speakers - is available on IDA spring school's web page: http://www.cere.pa.cnr.it/IDAschool/ FINANCIAL SUPPORT: The Spring School is supported by the European Commission under HPCF-2000-00401 subject to contract. Some financial support will be available for young researchers (<35) to attend the school. This support will cover the registration fee and all or part of the travel and subsistence expenses. Limited funding is also available for young researchers from non-european countries, provided they are nationals of an EU memberstate. If you are interested in attending the school or would like to apply for financial support please fill out the form available on our web site. The deadline for applications is January, 15th, 2001. If you have questions or comments please send e-mail to ida at cere.pa.cnr.it. From zemel at cs.toronto.edu Tue Jan 9 15:44:05 2001 From: zemel at cs.toronto.edu (Richard Zemel) Date: Tue, 9 Jan 2001 15:44:05 -0500 Subject: postdoc position: U. of Toronto Message-ID: ************************************************************************ POSTDOCTORAL RESEARCH ASSOCIATE DEPARTMENT OF COMPUTER SCIENCE UNIVERSITY OF TORONTO A postdoctoral position is available in the Machine and Neurobiological Learning laboratory in the Department of Computer Science at the University of Toronto. For more details on research in this lab, see http://www.cs.toronto.edu/~zemel/research.html. The University of Toronto is a prominent research institute in all areas of computer science, and a world leader in artificial intelligence. We are seeking someone whose research focus lies primarily in at least one of these areas: machine learning, neural computation, or probabilistic reasoning. A strong background and education in a quantitative discipline, such as physics, mathematics, statistics, engineering, or computer science, is required. Knowledge of neuroscience or psychophysics is a plus. This position is available immediately and for a duration of 1-2 years depending on accomplishment. A competitive salary package will be offered. Please send a CV, a brief statement of research experience and interests, and the names and contact information of two references to: zemel at cs.toronto.edu. Applications can also be mailed (or faxed) to: Dr. Richard Zemel Tel: (416) 978-7497 Departmet of Computer Science Fax: (416) 978-1455 University of Toronto Email: zemel at cs.toronto.edu Toronto, ON M5S 1A4 CANADA URL: www.cs.toronto.edu/~zemel ************************************************************************ From takane at takane2.psych.mcgill.ca Tue Jan 9 13:17:52 2001 From: takane at takane2.psych.mcgill.ca (Yoshio Takane) Date: Tue, 9 Jan 2001 13:17:52 -0500 (EST) Subject: No subject Message-ID: <200101091817.NAA02950@takane2.psych.mcgill.ca> Dear Colleagues, I am organizing a symposium on "Knowledge integration in neural network models" at the International Meeting of the Psychometric Society (IMPS-2001) to be held in Osaka, Japan on July 15-19, 2001. Information about the meeting can be found at http://www.ir.rikkyo.ac.jp/imps2001/ I would like to invite anyone interested in presenting a paper on the topic to submit the title and the abstract (of no more than 300 words) of the paper to me as soon as possible. You will be notified of acceptance within one week or so of submission. Some prospective speakers so far are: Shultz, T. R., & Rivest, F. Knowledge based cascade-correlation network. --- This paper presents a method of incorporating prior knowledge learned previously into a cascade-correlation network learning new but related material. Asoh, H. An approximation of nonlinear canonical correlation analysis using neural network. --- This paper presents an approximation method for nonlinear canonical correlation analysis put forward by Becker & Hinton (1992). Takane, Y., & Oshima-Takane, Y. Nonlinear generalized canonical correlation analysis by neural network models. --- This paper presents nonlinear K-set canonical correlation analysis as a method for integrating information from K concurrent sources. Yoshio Takane Professor McGill University From cesabian at aspic.usr.dsi.unimi.it Tue Jan 9 03:33:04 2001 From: cesabian at aspic.usr.dsi.unimi.it (Nicolo` Cesa-Bianchi) Date: Tue, 9 Jan 2001 09:33:04 +0100 Subject: School on Principles of Nonparametric Learning Message-ID: <20010109093304.D10851@dsi.unimi.it> Principles of Nonparametric Learning Udine (Italy), July 9-13, 2001 Advanced School coordinated by L. Gyrfi Budapest University of Technology and Economics Hungary Modern nonparametric methods have become the most important tools in various fields of applications of pattern recognition, density and regression function estimation, data compression, on-line learning and prediction. The common feature in these problems is that some unknown underlying system generates data and the best action is to be learnt from these data. The purpose of the course is to teach the basic principles of nonparametric inference with emphasis on the cited areas. Leading international experts of these areas will introduce the participants into the theory and advanced methods of inference. A prototype problem to be discussed in depth is the problem of pattern recognition in which an observation is to be classified into one of a finite number of classes. The optimal classification must be approximated based on training data. Classical nonparametric methods such as nearest neighbor and kernel methods, as well as modern methodologies including neural networks, support vector machines, and binary tree classifiers will be studied in the course. Evolutionary optimization methodologies, e.g. genetic programming, will also be considered as they allow nonparametric learning to handle complex data and explore structured model spaces. The methodologies covered by this course have found applications in various fields such as identification of biological and mechanical systems, data mining, forecasting, universal data compression, optimal portfolio strategies for stock markets, and measurement-based call admission control for high-speed communication networks. The course is addressed to postgraduates in engineering, mathematics, and computer science, and researchers in universities and research institutions. Please visit the school home page (www.cism.it/c2001/c03/) for information on program, admission, and accomodation. From bengio at idiap.ch Wed Jan 10 03:42:40 2001 From: bengio at idiap.ch (Samy Bengio) Date: Wed, 10 Jan 2001 09:42:40 +0100 (MET) Subject: open postdoc position at IDIAP, Switzerland Message-ID: Open Postdoctoral position in Machine Learning The Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP, http://www.idiap.ch) seeks qualified applicants for a Postdoctoral position in its Machine Learning group. The research project would involve several extensions of mixture and ensemble models specifically tailored for large databases, including: - Mixture of Support Vector Machines, - Mixture of binary classifiers for multiclass problems, - Feature selection for mixture models, - Others. The ideal candidate should have strong background in statistical learning theory in general, including SVMs, neural networks, and mixture models; the candidate should also be familiar with C/C++ programming under a Unix environment. Although IDIAP is located in the French part of Switzerland, English is the main working language at IDIAP. Free English and French courses are also provided. IDIAP is located in the town of Martigny (http://www.martigny.ch) in Valais, a scenic region in the south of Switzerland, surrounded by the highest mountains of Europe, and offering exciting recreational activities, including hiking, climbing and skiing, as well as varied cultural activities. It is within close proximity to Montreux (Jazz Festival) and Lausanne (EPFL, http://www.epfl.ch). Candidates should send their detailed CV (preferably by email) to Dr. Samy Bengio Research Director. Machine Learning Group Leader. IDIAP, CP 592, rue du Simplon 4, 1920 Martigny, Switzerland. tel: +41 27 721 77 39, fax: +41 27 721 77 12. mailto:bengio at idiap.ch, http://www.idiap.ch/~bengio ----- Samy Bengio Research Director. Machine Learning Group Leader. IDIAP, CP 592, rue du Simplon 4, 1920 Martigny, Switzerland. tel: +41 27 721 77 39, fax: +41 27 721 77 12. mailto:bengio at idiap.ch, http://www.idiap.ch/~bengio From wolfskil at MIT.EDU Thu Jan 11 10:46:05 2001 From: wolfskil at MIT.EDU (Jud Wolfskill) Date: Thu, 11 Jan 2001 10:46:05 -0500 Subject: book announcement--Smola Message-ID: I thought readers of the Connectionists List might be interested in this book. For table of contents and more information please visit http://mitpress.mit.edu/promotions/books/SMOAHF00. Best, Jud Advances in Large-Margin Classifiers edited by Alexander J. Smola, Peter J. Bartlett, Bernhard Schlkopf, and Dale Schuurmans The concept of large margins is a unifying principle for the analysis of many different approaches to the classification of data from examples, including boosting, mathematical programming, neural networks, and support vector machines. The fact that it is the margin, or confidence level, of a classification --that is, a scale parameter--rather than a raw training error that matters has become a key tool for dealing with classifiers. This book shows how this idea applies to both the theoretical analysis and the design of algorithms. The book provides an overview of recent developments in large margin classifiers, examines connections with other methods (e.g., Bayesian inference), and identifies strengths and weaknesses of the method, as well as directions for future research. Among the contributors are Manfred Opper, Vladimir Vapnik, and Grace Wahba. Alexander J. Smola is a Postdoctoral Fellow at GMD-FIRST, Berlin. Peter L. Bartlett is Senior Fellow, Computer Sciences Laboratory, Australian National University. Bernhard Schlkopf is a Researcher at Microsoft Research Ltd., Cambridge, UK. Dale Schuurmans is Assistant Professor of Computer Science at the University of Waterloo, Ontario, Canada. 8 x 10, 412 pp., cloth ISBN 0-262-19448-1 Neural Information Processing series -------------------------------------------------------------------------------- Jud Wolfskill 617.253.2079 phone Associate Publicist 617.253.1709 fax MIT Press wolfskil at mit.edu 5 Cambridge Center http://mitpress.mit.edu Fourth Floor Cambridge, MA 02142 From giacomo at ini.phys.ethz.ch Fri Jan 12 14:18:43 2001 From: giacomo at ini.phys.ethz.ch (Giacomo Indiveri) Date: Fri, 12 Jan 2001 20:18:43 +0100 Subject: Telluride 2001 Workshop on Neuromoprhic Engineering References: <200101110350.f0B3oxt07285@purkinje.salk.edu> Message-ID: <3A5F5893.A486292B@ini.phys.ethz.ch> Please accept our apology for cross-postings. Workshop application announcement: http://www.ini.unizh.ch/telluride2000/tell2001_announcement.html ---------------------------------------------------------------------- NEUROMORPHIC ENGINEERING WORKSHOP Sunday, JULY 1 - Saturday, JULY 21, 2001 TELLURIDE, COLORADO ------------------------------------------------------------------------ Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Timmer HORIUCHI (Johns Hopkins University) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Christof KOCH (California Institute of Technology) Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) ------------------------------------------------------------------------ We invite applications for a three week summer workshop that will be held in Telluride, Colorado from Sunday, July 1 to Sunday, July 21, 2001. The application deadline is Friday, February 23, and application instructions are described at the bottom of this document. The 2000 summer workshop on "Neuromorphic Engineering", sponsored by the National Science Foundation, the Gatsby Foundation, Whitaker Foundation, the Office of Naval Research, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology, was an exciting event and a great success. A detailed report on the workshop is available at http://www.ini.unizh.ch/telluride2000. We strongly encourage interested parties to browse through the previous workshop web pages: http://www.ini.unizh.ch/telluride2000/ GOALS: Carver Mead introduced the term "Neuromorphic Engineering" for a new field based on the design and fabrication of artificial neural systems, such as vision systems, head-eye systems, and roving robots, whose architecture and design principles are based on those of biological nervous systems. The goal of this workshop is to bring together young investigators and more established researchers from academia with their counterparts in industry and national laboratories, working on both neurobiological as well as engineering aspects of sensory systems and sensory-motor integration. The focus of the workshop will be on active participation, with demonstration systems and hands-on-experience for all participants. Neuromorphic engineering has a wide range of applications from nonlinear adaptive control of complex systems to the design of smart sensors. Many of the fundamental principles in this field, such as the use of learning methods and the design of parallel hardware (with an emphasis on analog and asynchronous digital VLSI), are inspired by biological systems. However, existing applications are modest and the challenge of scaling up from small artificial neural networks and designing completely autonomous systems at the levels achieved by biological systems lies ahead. The assumption underlying this three week workshop is that the next generation of neuromorphic systems would benefit from closer attention to the principles found through experimental and theoretical studies of real biological nervous systems as whole systems. FORMAT: The three week summer workshop will include background lectures on systems neuroscience (in particular learning, oculo-motor and other motor systems and attention), practical tutorials on analog VLSI design, small mobile robots (Koalas and Kheperas), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed (soon to be defined). They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, the majority of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. The analog VLSI practical tutorials will cover all aspects of analog VLSI design, simulation, layout, and testing during the three weeks of the workshop. The first week covers basics of transistors, simple circuit design and simulation. This material is intended for participants who have no experience with analog VLSI. The second week will focus on design frames for silicon retinas, from the silicon compilation and layout of on-chip video scanners, to building the peripheral boards necessary for interfacing analog VLSI retinas to video output monitors. Retina chips will be provided. The third week will feature sessions on floating gates, including lectures on the physics of tunneling and injection, and on inter-chip communication systems. We will also feature a tutorial on the use of small, mobile robots, focusing on Koala's, as an ideal platform for vision, auditory and sensory-motor circuits. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * olfaction * motor control * central pattern generator * robotics, multichip communication * analog VLSI * learning The active perception project group will emphasize vision and human sensory-motor coordination. Issues to be covered will include spatial localization and constancy, attention, motor planning, eye movements, and the use of visual motion information for motor control. Demonstrations will include a robot head active vision system consisting of a three degree-of-freedom binocular camera system that is fully programmable. The central pattern generator group will focus on small walking and undulating robots. It will look at characteristics and sources of parts for building robots, play with working examples of legged and segmented robots, and discuss CPG's and theories of nonlinear oscillators for locomotion. It will also explore the use of simple analog VLSI sensors for autonomous robots. The robotics group will use rovers and working digital vision boards as well as other possible sensors to investigate issues of sensorimotor integration, navigation and learning. The audition group aims to develop biologically plausible algorithms and aVLSI implementations of specific auditory tasks such as source localization and tracking, and sound pattern recognition. Projects will be integrated with visual and motor tasks in the context of a robot platform. The multichip communication project group will use existing interchip communication interfaces to program small networks of artificial neurons to exhibit particular behaviors such as amplification, oscillation, and associative memory. Issues in multichip communication will be discussed. LOCATION AND ARRANGEMENTS: The workshop will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350 miles). America West and United Airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of workstations running UNIX and PCs running LINUX and Microsoft Windows. No cars are required. Bring hiking boots, warm clothes and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around March 9, 2001. Participants are expected to pay a $275.00 workshop fee at that time in order to reserve a place in the workshop. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. Travel reimbursement of up to $500 for US domestic travel and up to $800 for overseas travel will be possible if financial help is needed (Please specify on the application). HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e. postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage qualified women and minority candidates to apply. Application should include: * First name, Last name, valid email address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Description of special equipment needed for demonstrations that could be brought to the workshop. * Two letters of recommendation Complete applications should be sent to: Terrence Sejnowski The Salk Institute 10010 North Torrey Pines Road San Diego, CA 92037 email: telluride at salk.edu FAX: (858) 587 0417 DEADLINE: February 23, 2001 Applicants will be notified by email around March 9, 2001 From terry at salk.edu Sat Jan 13 02:43:09 2001 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 12 Jan 2001 23:43:09 -0800 (PST) Subject: NEURAL COMPUTATION 132 In-Reply-To: <3A59E2DF.456B9912@ele.puc-rio.br> Message-ID: <200101130743.f0D7h9v12640@purkinje.salk.edu> Neural Computation - Contents - Volume 13, Number 2 - February 1, 2001 Review Spatio-Temporal Connectionist Networks: A Taxonomy and Review Stefan C. Kremer Notes Formulations of Support Vector Machines: A Note from an Optimization Point of View Chih-Jen Lin Minimal Feedforward Parity Networks Using Threshold Gates Hon-Kwok Fung and Leong Kwan Li Letters Does Corticothalamic Feedback Control Cortical Velocity Tuning? Ulrich Hillenbrand and J. Leo van Hemmen A Competitive Layer Model for Feature Binding and Sensory Segmentation Heiko Wersing, Jochen J. Steil, and Helge Ritter Visual Learning Using A Priori Constraints Within ORASSYLL Norbert Kruger Binding and Normalization of Binary Sparse Distributed Representations Context-Dependent Thinning by Dmitri A. Rachkovskij and Enrst M. Kussul Resolution-Based Complexity Control for Gaussian Mixture Models Peter Meinicke and Helge Ritter ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2001 - VOLUME 13 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $88 $94.16 $136 Institution $460 $492.20 $508 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From amari at brain.riken.go.jp Mon Jan 15 00:02:38 2001 From: amari at brain.riken.go.jp (Shun-ichi Amari) Date: Mon, 15 Jan 2001 14:02:38 +0900 Subject: new book on Information Geometry Message-ID: Dear Connectionists It is my pleasure to announce the publication of a book on Information Geometry. I have been often asked if there is a good book on information geometry to know its general perspectives. Here it is. S.Amari and H.Nagaoka, Methods of Information Geometry, AMS Translations of Mathematical Monographs, vol 191 (translated by Daishi Harada) American Mathematical Society (AMS) and Oxford University Press, 206 + x pages, 2000. (See http://www.ams.org/) ******************** Shun-ichi Amari Vice Director, RIKEN Brain Science Institute Laboratory for Mathematical Neuroscience Research Group on Brain-Style Information Systems tel: +81-(0)48-467-9669; fax: +81-(0)48-467-9687 amari at brain.riken.go.jp http://www.bsis.brain.riken.go.jp/ From nic at idsia.ch Sun Jan 14 13:32:32 2001 From: nic at idsia.ch (Nici Schraudolph) Date: Sun, 14 Jan 2001 19:32:32 +0100 (CET) Subject: new institute at ETH Zurich - Ph.D. and postdoc positions Message-ID: Dear colleagues, we are building up a machine learning research group at the new Institute of Computational Sciences (ICOS) at ETH Zurich, and thus have several openings for Ph.D. students and postdoctoral researchers. ICOS (www.icos.ethz.ch) is a new multidisciplinary institute within ETH's Department of Computer Science. Our goal is to bring the latest advances in computer science to bear on challenging problems in all areas of science and technology, with a special focus on the emerging interfaces of fields such as life sciences, nanotechnology, and computation. We have initiated several collaborative projects in the above areas, within ETH as well as nationally and internationally, and are seeking creative individuals who wish to expand on this basis in a stimulating research environment. One initial focus of the machine learning group at ICOS will be the development of advanced algorithms for stochastic gradient descent. In addition to candidates that want to pursue this line of research, however, we strongly welcome applications from researchers with com- plementary orientations (e.g., kernel methods or Bayesian inference). What we are looking for is a) the ability to work with, and improve upon, the latest learning algorithms in your specialty; b) an interest in applying your work to large scale, challenging real-world problems; and c) the wish to explore the opportunities inherent in the highly interdisciplinary environment of the ETH Zurich. The ETH (Swiss Federal Institute of Technology) Zurich is considered one of the world's foremost technical universities, and offers a first-class academic environment. Zurich is the commercial center of Switzerland, fast becoming one of the hubs of information technology in the heart of Europe. It combines a high standard of living with a beautiful lakeside setting, with ample leisure opportunities (the Alps, for one) within easy reach. ETH offers highly competitive salaries with initial appointments for up to two years for post-doctoral positions and up to four years for Ph.D. positions. Renewal of these positions is possible for successful programs. To apply, please provide the following information: - a cover letter describing your research interest, - your c.v. including a list of publications, - one or two sample publications, and - e-mails and telephone numbers of three colleagues familiar with you and your work. Applications should be sent to the address: Daniela Wiesli Institute of Computational Science Weinbergstrasse 43 ETH Zentrum Zurich, CH-8092 Switzerland We welcome applications by email (in Word, PDF, or Postscript format) to wiesli at inf.ethz.ch, with the phrase "ML application" in the subject. Best regards, -- Dr. Nicol N. Schraudolph mobile: +41-76-585-3877 IDSIA, Galleria 2 home: -91-970-3877 CH-6928 Manno, Switzerland work: -91-610-8669 http://www.idsia.ch/~nic/ fax: -8661 From kenm at julian.uwo.ca Mon Jan 15 11:54:57 2001 From: kenm at julian.uwo.ca (Ken McRae) Date: Mon, 15 Jan 2001 11:54:57 -0500 Subject: Postdoc Opportunity Message-ID: Postdoctoral Fellowship in Psycholinguistics & Computational Modeling We have funding for a two-year Postdoctoral Fellowship in my lab at the University of Western Ontario in London, Ontario, Canada. The stipend is for $32,500 per year plus $2,500 per year for travel. There are no citizenship restrictions. Our research focuses on the interrelated issues of noun meaning, verb meaning, and sentence processing. Central to this work is connectionist modeling of the computation of noun and verb meaning, as well as competition-integration modeling of on-line sentence reading times. Our research integrates theories and methodologies from a number of areas, including: word recognition, concepts and categorization, sentence processing, connectionist modeling, neuroscience, and patients with acquired disorders. Thus, a PDF has the opportunity to participate in projects in a number of areas of Cognitive Science. Our department has seven Cognition faculty, all of whom conduct research related to language processing. Thus, our faculty and graduate students provide a rich research environment. I am also involved in a number of collaborations with researchers from other universities. My lab is well-equipped for both human experimentation and computational modeling. UWO also has a 4T magnet that is used for research only. London is a pleasant city of approximately 350,000, and is located 2 hours from both Toronto and Detroit. Note that a reasonable apartment in London costs approximately $500 per month. For further information on our lab and Cognition at UWO, see: http://www.sscl.uwo.ca/psychology/cognitive/faculty.html If you are interested in this position, please contact Ken McRae. *********************************************************** Ken McRae Associate Professor Department of Psychology Social Science Centre University of Western Ontario London, Ontario CANADA N6A 5C2 email: mcrae at uwo.ca http://www.sscl.uwo.ca/psychology/cognitive/mcrae/mcrae.html phone: (519) 661-2111 ext. 84688 fax: (519) 661-3961 *********************************************************** From juergen at idsia.ch Mon Jan 15 04:07:28 2001 From: juergen at idsia.ch (juergen@idsia.ch) Date: Mon, 15 Jan 2001 10:07:28 +0100 Subject: IDSIA JOBS: 2 POSTDOCS, 1 PHD STUDENT Message-ID: <200101150907.KAA16944@ruebe.idsia.ch> We are seeking two outstanding postdocs and one PhD student in the fields of artificial neural networks, unsupervised learning, reinforcement learning, and/or related areas. The initial appointment would be for 2 years, starting 2001, with possibility of prolongation. Please see http://www.idsia.ch/jobs.html IDSIA is the smallest among the world's top ten AI labs identified by Business Week, and number 4 in the category "Computer Science - Biologically Inspired." Our research focuses on recurrent and other neural networks, reinforcement learning, complexity and generalization issues, unsupervised learning and information theory, forecasting, artificial ants, combinatorial optimization, evolutionary computation. IDSIA's algorithms hold the world records for several important operations research benchmarks. We are located near the beautiful city of Lugano in Ticino, the scenic southernmost province of Switzerland, origin of special relativity and the WWW. Milano, Italy's center of fashion and finance, is 1 hour away, Venice 3 hours. Our collaborators at CSCS (the Swiss supercomputing center) are right beneath us; we are also affiliated with the University of Lugano and SUPSI. Switzerland boasts the highest citation impact factor, the most Nobel prizes per capita, the highest income per capita, and some of the best chocolate. Applicants should submit : (i) Detailed curriculum vitae, (ii) List of three references and their email addresses, (iii) Concise statement of their research interests (two pages max). Please send all documents to: Juergen Schmidhuber, IDSIA, Galleria 2, 6928 Manno (Lugano), Switzerland. Applications in plain ASCII format can also be submitted by email (only small files please) to juergen at idsia.ch. Do NOT send doc or pdf or large postscript files. Instead send WWW pointers to postscript files. Please connect your first and last name by a dot "." in the subject header, and add a meaningful extension. For instance, if your name is John Smith, then your messages could have headers such as: From krose at science.uva.nl Wed Jan 17 12:20:55 2001 From: krose at science.uva.nl (Ben Krose) Date: Wed, 17 Jan 2001 18:20:55 +0100 Subject: Ph.D. position available Message-ID: <3A65D477.8F62C6CE@science.uva.nl> I would like to announce the following job opening on the connectionists list: The Intelligent Autonomous Systems group of the Research Institute Computer Science of the University of Amsterdam, Netherlands (http://www.science.uva.nl/research/ias/) invites applications for a ------------------------------------------------------------------------- Ph.D. position "Probabilistic models for distributed surveillance systems" ------------------------------------------------------------------------- The project focusses on 'Networked Intelligent Devices' systems: autonomous functioning camera's in a network environment. Here we have to deal with several fundamental problems: the identification problem (`is the object which is observed by one camera the same as the object observed by some other camera some time ago?') and the representation problem (`how can probabilistic information be integrated in a distributed system?'). Recently Bayesian networks have shown to be able to represent such dependencies and to exploit them, although in other applications (diagnosis). We want to investigate to which extent Bayesian networks can be applied to this area, whether the dependencies can be learned and whether these networks can be used in a multi-agent system. The project is funded by the Dutch Technology Foundation STW. Desired profile: The highly qualified applicant should possess a masters degree in the field of multi-agent systems, neural networks, image processing or statistics. Programming skills are an asset (C, Matlab, ...), as is a familiarity with UNIX and PC platforms. We offer: 1) A challenging research environment. The IAS group consists three staff members, a postdoc and 7 Ph.D. students working in the field of robotics, vision and probabilistic models. We collaborate within the Foundation for Neural Networks with the probabilistic modeling group at Nijmegen University 2) An attractive income. Dutch Ph.D. students get a salary which starts at DFL 3.055,- a month for the first year, growing up to DFL 4.362,- per month. 3) The Ph.D. student will be a member of the ASCI research school providing Ph.D-level training. Information: Dr. ir. B.J.A. Krse, tel 020-525 7461, email: krose at science.uva.nl More about the project: http://www.science.uva.nl/research/learn/ Applications for this position close on February 15, 2001. Please write to: afdeling Personeelszaken Computer Science Department Kruislaan 403, 1098 SJ, Amsterdam, The Netherlands, referring to job opening nr 15114 -- dr. ir. B.J.A. Kr\"ose Department of Computer Science University of Amsterdam, Kruislaan 403, 1098 SJ Amsterdam, NL. tel: +31 20 525 7520/7463/(7490 fax) http://www.science.uva.nl/~krose/ From wriggers at scripps.edu Wed Jan 17 23:17:27 2001 From: wriggers at scripps.edu (Willy Wriggers) Date: Wed, 17 Jan 2001 20:17:27 -0800 Subject: Postdoc: TRN Applications in Multi-Resolution Molecular Modeling Message-ID: <3A666E57.DFAE71BB@scripps.edu> ------------------------------------------------------- Postdoctoral Positions: TRN Applications in Multi-Resolution Molecular Modeling ------------------------------------------------------- The Scripps Research Institute (La Jolla, California) and its Computational Structural Biology Group in the Department of Molecular Biology (http://www.scripps.edu/wriggers) are seeking highly qualified Postdoctoral Research Associates to develop and apply multi-resolution modeling techniques based on topology-representing networks (TRN) for the determination of 3D atomic structures of proteins and large biomolecular assemblies. Highly qualified applicants should hold a Ph.D. degree in physics, chemistry, computer science, or a related quantitative discipline. Research experience in image-processing, neural networks, or visualization are an essential asset. We expect a strong programming background, organizational skills, and a desire to learn principles of structural biology. The successful candidates may choose among the following research topics: - neural network-based shape characterization and query; - shape-based docking of multi-resolution biomolecular data; - flexible docking with force-field methods (molecular dynamics and normal mode analysis); - spline-based warping (morphing) of 3D structural data; - interactive visualization (computer graphics) of atomic and low-resolution data. The developed algorithms will be applied in challenging collaborations with world leaders in Electron Microscopy involving structures of virus capsids, RNA polymerase, cytoskeletal filaments and the ribosome. Initial appointments are for one year, but are extendable to the full time frame of the projects (up to 5 years). Application review begins immediately until the positions are filled. Ideally, candidates should be able to start by April, 2001, although highly qualified candidates who seek a later start date should not hesitate to apply. We offer a competitive salary and benefits. If you are interested in applying for a position, please email your CV, a letter of application (research interests and publication list), and a list of references (with name, email, and phone number) to me. There are no citizenship restrictions. Qualified women and minority candidates are encouraged to apply. TSRI is an Equal Opportunity employer. Willy Wriggers Assistant Professor Department of Molecular Biology, TPC6 The Scripps Research Institute 10550 North Torrey Pines Road La Jolla, California 92037 E-mail: wriggers at scripps.edu URL: http://www.scripps.edu/wriggers Tel: (858)784-8823 Fax: (858)784-8688 From doya at isd.atr.co.jp Thu Jan 18 06:22:00 2001 From: doya at isd.atr.co.jp (Kenji Doya) Date: Thu, 18 Jan 2001 20:22:00 +0900 Subject: CREST Workshop on Metalearning and Neuromodulation Message-ID: CREST WORKSHOP ON METALEARNING AND NEUROMODULATION April 6th and 7th, 2001 Keihanna Plaza, Seika, Kyoto, Japan Sponsored by Metalearning, Neuromodulation, and Emotion Project CREST, Japan Science and Technology Corporation The goal of this workshop is to bring together neuroscientists as well as theorists who work on the regulatory mechanisms of adaptive systems, either biological or artificial. We invite researchers in the fields the computational theory of 'metalearning' as well as the biological mechanism of neuromodulators, such as dopamine, serotonin, norepinephrine, and acetylcholine. Please visit our workshop home page for details: http://www.isd.atr.co.jp/nip/crest/workshop/ This workshop is scheduled after the 9th International Catecholamine Symposium (http://mc-net.jtbcom.co.jp/ics2001/) held in downtown Kyoto from March 31st to April 5th, 2001. INVITED SPEAKERS Minoru Asada, Osaka University Gary Aston-Jones, University of Pennsylvania Kenji Doya, CREST, JST & ATR International Barry J. Everitt, University of Cambridge Michael Hasselmo, Boston University Okihide Hikosaka, Juntendo University Shin Ishii, Nara Institute of Science and Technology Sham Kakade, University College London Takashi Matsumoto, Waseda University Toshiyuki Sawaguchi, Hokkaido University Wolfram Schultz, University of Fribourg Yuko Sekino, Gumma University Shigeto Yamawaki, Hiroshima University CALL FOR POSTERS A poster session will be held in the evening of April 6th. Please send 1) title, 2) author(s), 3) affiliation(s), 4) abstract up to 500 words, 5) postal address, 6) phone, 7) fax, and 8) e-mail address of the presenting author by e-mail to the secretariat by February 15th, 2001. REGISTRATION Please send 1) name, 2) affiliation, 3) postal address, 4) phone, 5) fax, and 6) e-mail address by e-mail to the secretariat by March 1st, 2001. Registration is free. However, the numbers of attendees will be limited by capacity of the conference room. So please register early. HOTEL RESERVATION Please visit our home page (http://www.isd.atr.co.jp/nip/crest/workshop/) to download a reservation form, and send it by fax directly to a hotel. Note that early April is the high season for cherry blossoms in Kyoto, so please reserve early. SECRETARIAT Naomi Katayama Metalearning, Neuromodulation and Emotion, CREST, JST 2-2-2 Hikaridai, Seika, Soraku, Kyoto 619-0288, Japan Phone: +81-774-95-1251 Fax: +81-774-95-1259 E-mail: nip-info at isd.atr.co.jp URL: http://www.isd.atr.co.jp/nip/crest/ ---- Kenji Doya Information Sciences Division, ATR International; CREST, JST 2-2-2 Hikaridai, Seika, Soraku, Kyoto 619-0288, Japan Phone:+81-774-95-1251; Fax:+81-774-95-1259; http://www.isd.atr.co.jp/~doya From schumann at ptolemy.arc.nasa.gov Thu Jan 18 14:48:21 2001 From: schumann at ptolemy.arc.nasa.gov (Johann Schumann) Date: Thu, 18 Jan 2001 11:48:21 -0800 (PST) Subject: Reasearch Position at NASA/Ames on V&V of Neural Networks Message-ID: <200101181948.LAA15339@karg.arc.nasa.gov> The Automated Software Engineering Group at NASA Ames Research Center is inviting applications for a research position in a project on Verification and Validation of Controllers based upon on-line trained ANNs. The ASE group performs research and development in the areas of automated reasoning and formal methods for software synthesis and verification. We have ongoing collaborations with several NASA application groups (e.g., ANN-based flight controller for F-15/ACTIVE) as well as academic research groups. The ideal candidate must have experience in the theoretical foundations of ANNs and their learing algorithms. We are focusing on feed-forward architectures, but RBF-based networks are also of interest. A strong background in numerical algorithms and control theory as a plus. A PhD in Computer Science, Mathematics, Physics or a releated area is required. To be considered for this position, please send a resume (URL ok) and contact information for three references to Johann Schumann schumann at ptolemy.arc.nasa.gov and cc to Michael Lowry lowry at ptolemy.arc.nasa.gov For more information on the ASE group, see http://ase.arc.nasa.gov/ We are also considering applications for a student summer internship. Please see http://www.riacs.edu/ssrp for further details. --------------------------------------- Johann Schumann Automated Software Engineering NASA Ames / RIACS Moffet Field, Ca 94035 Phone: (650) 604-0941 email: schumann at ptolemy.arc.nasa.gov From gomi at idea.brl.ntt.co.jp Thu Jan 18 21:02:20 2001 From: gomi at idea.brl.ntt.co.jp (Hiroaki GOMI) Date: Fri, 19 Jan 2001 11:02:20 +0900 Subject: RESEARCH POSITIONS AVAILABLE at NTT Communication Sci. Labs. Message-ID: <20010119110220F.gomi@idea.brl.ntt.co.jp> RESEARCH POSITIONS AVAILABLE NTT (Nippon Telegraph and Telephone Corporation) Communication Science Labs. Research associate (post doctoral fellow) and research specialist positions are currently available in the human speech & motor control group at NTT Communication Science Laboratories. One research topic focuses on the human motor control mechanisms in the mechanical interaction with environments, and its brain information processing. The candidate should have a strong background in human motor control studies. Some skills of C programming for controlling experimental system and Matlab for data analyses are desirable but not required. Candidates with training in psychological approaches to motor control are particularly encouraged to apply. Another topic focuses on information processing for speech and language. The candidate should have a strong background in the fields of speech and language. The position requires strong programming skills in C and/or C++ with experience in programming mathematical algorithms, and knowledge of signal processing and machine learning. The salary will be decided according to company regulation. The research center for these topics is located in Atsugi near Tokyo, Japan (see our web page). The positions are tenable for one year and are renewable every year until the limit of two years. Please send curriculum vitae including research and programming experiences, names and contact details of referees, and representative publications to the address listed below. Curriculum vitae should be sent until March 23, 2001. Informal inquiries should be set to the e-mail address. E-mail inquiries and applications are encouraged. We prefer a starting date of April 1, 2001 but this is open to negotiation. Application should be sent to: Dr. Eisaku Maeda soukatsu at cslab.kecl.ntt.co.jp Senior Manager of NTT Communication Science Laboratories Tel: +81-774-93-5040 Fax: +81-774-93-5045 address: NTT Communication Science Labs. Hikaridai 2-4, Seika-cho, Soraku-gun, Kyoto-pref. 619-0237, Japan web page: http://www.kecl.ntt.co.jp From Dave_Touretzky at cs.cmu.edu Fri Jan 19 03:15:55 2001 From: Dave_Touretzky at cs.cmu.edu (Dave_Touretzky@cs.cmu.edu) Date: Fri, 19 Jan 2001 03:15:55 -0500 Subject: undergraduate summer research opportunities Message-ID: <2079.979892155@skinner.boltz.cs.cmu.edu> Summer Undergraduate Research at the Center for the Neural Basis of Cognition University of Pittsburgh / Carnegie Mellon University If you are a faculty member who advises undergraduates with an interest in cognitive or computational neuroscience, kindly encourage your best students to apply for an undergraduate summer internship at the Center for the Neural Basis of Cognition, a joint project of Carnegie Mellon University and the University of Pittsburgh. A ten-week program beginning in early June features intensive involvement in laboratory research supervised by one of the program's faculty, plus a series of lectures and lab tours, and a weekly journal club. Each student's individualized plan of research is determined in consultation with their faculty mentor. Potential research activities include functional brain imaging, computer simulations of cognitive phenomena, neurophysiological recording from the brains of behaving animals, neuroanatomical studies, and neuropsychological assessment of clinical patients. Students receive a $2500 stipend, free housing, and some travel support. Applications are requested from highly motivated students with interests in neuroscience, psychology, engineering, physics, mathematics, or computer science. STUDENTS MUST NOT YET HAVE COMPLETED THEIR UNDERGRADUATE DEGREE AT THE TIME THEY PARTICIPATE IN THE PROGRAM. Hence, graduating seniors are ineligible to apply. Application information is available on the web at http://www.cnbc.cmu.edu/Training/summer Applicants must include a personal statement, a recent school transcript, one letter of recommendation from a faculty member, and a selection of two choices of research areas they would like to explore. The personal statement should be 2 pages in length and include the following information: scientific interests and professional goals, prior research experience, and relevant laboratory and computer skills. APPLICATION DEADLINE: FEBRUARY 15, 2001. For further information, please visit the web site listed above, or send email to cncb-admissions at cnbc.cmu.edu From icann at ai.univie.ac.at Wed Jan 17 08:58:55 2001 From: icann at ai.univie.ac.at (ICANN 2001 conference) Date: Wed, 17 Jan 2001 14:58:55 +0100 Subject: ICANN 2001: Final Call for Papers Message-ID: <3A65A51F.F3458FE3@ai.univie.ac.at> Final Call for Papers ============================================================ ICANN 2001 International Conference on Artificial Neural Networks Aug. 21-25, 2001 Vienna, Austria http://www.ai.univie.ac.at/icann the annual conference of the European Neural Network Society ============================================================ We invite submission of full-length papers on work in neural computation covering theory, algorithms, applications or implementation in one of the following areas: - Computational Neuroscience - Data Analysis and Pattern Recognition - Vision and Image Processing - Signal and Time Series Processing - Robotics and Control - Connectionist Cognitive Science - Selforganization and Dynamical Systems Deadline for receipt of papers: !!!!!!!!!!!!!!! Feb 16, 2001 !!!!!!!!!!!!!!! (electronic submission is possible) Please see our web page for more details. http://www.ai.univie.ac.at/icann ___________________________________________________________ Furthermore, we invite proposals for tutorials, special sessions or workshops on selected topics in neural computation. Deadline for receipt of proposals: !!!!!!!!!!!!! Feb 1, 2001 !!!!!!!!!!!!! Please see our web page for more details http://www.ai.univie.ac.at/icann ___________________________________________________________ ICANN 2001 is organized by the Austrian Research Institute for Artificial Intelligence in cooperation with the Vienna University of Technology's Pattern Recognition and Image Processing Group and Center for Computational Intelligence. For questions contact icann at ai.univie.ac.at From v.kecman at auckland.ac.nz Sun Jan 21 04:28:29 2001 From: v.kecman at auckland.ac.nz (Vojislav KECMAN) Date: Sun, 21 Jan 2001 22:28:29 +1300 Subject: book announcement: LEARNING AND SOFT COMPUTING Message-ID: <3A6AABBD.5EA96EA@auckland.ac.nz> Dear Colleague, I would like to announce the new The MIT Press book (to appear in March, 2001) on LEARNING AND SOFT COMPUTING Support Vector Machines, Neural Networks and Fuzzy Logic Models authored by me - Vojislav KECMAN The MIT Press, Cambridge, MA, 2001 ISBN 0-262-11255-8 608 pp., 268 illus., 47 examples, 155 problems $US60.00/=A2G41.50 (Hardcover) Please do check the following sites: www.support-vector.ws http://mitpress.mit.edu/book-home.tcl?isbn=3D0262112558 You will find the whole information about the book as well as powerful software and slides to download. Software accompanying the book is MATLAB 5 and 6 compatible. Learn the SVMs, NNs and FLMs by playing and enjoying. Best regards, VK -- Prof. Vojislav Kecman Phone: ++ 64 9 37 37 599 ext. 8178 The University of Auckland FAX: ++ 64 9 37 37 479 Department of Mech. Eng. Email: v.kecman at auckland.ac.nz Private Bag 92019 Auckland, New Zealand Web sites: http://www.support-vector.ws http://www.auckland.ac.nz/eme/staff/profiles/kecman.htm From wichert at neuro.informatik.uni-ulm.de Mon Jan 22 05:36:37 2001 From: wichert at neuro.informatik.uni-ulm.de (Andreas Wichert) Date: Mon, 22 Jan 2001 11:36:37 +0100 (MET) Subject: OSoftware for Simulating a Connectionistic Production System Message-ID: Object Oriented Software for Simulating a Connectionistic Production System Abstract C++ class library for simulating an associative computer is introduced. Associative computer is a connectionistic production system with benefits of distributed representation in problem solving. These benefits include the ability to learn from experience, heuristics resulting from picture representation and the ability to deal with noisy information. The behavior of the model is demonstrated by empirical experiments in block world. The model is the first effort to fill the gape between the statistical models like the artificial neural networks and models of logical reasoning. A manual in postcript and pdf format is present. Available at: 1) web site, in gzipped tar format: http://www.informatik.uni-ulm.de/ni/mitarbeiter/AWichert.html ... Miscellaneous: [M5].. Associative Computer: The Software 2) anonymous ftp, in gzipped tar format: ftp.neuro.informatik.uni-ulm.de, directory /ni/wichert File ASSOCOMP.tar.gz 3) cdrom upon request Andrzej Wichert PS For more information about associative computation read my Phd thesis, also avalable on the web site. From: esann To: "Connectionists at cs.cmu.edu" References: From bogus@does.not.exist.com Mon Jan 22 11:23:48 2001 From: bogus@does.not.exist.com () Date: Mon, 22 Jan 2001 17:23:48 +0100 Subject: ESANN'2000 proceedings available on-line Message-ID: Dear connectionists, We are pleased to announce the on-line availability of the ESANN'2000 proceedings (European Symposium on Artificial Neural Networks). Full-text version of all contributions may be downloaded in PDF (v. 4.0) format. An author index and a searchable abstract page are also available. The electronic proceedings may be accessed through the ESANN main page (http://www.dice.ucl.ac.be/esann/) or directly (http://www.dice.ucl.ac.be/esann/proceedings/index.html). This is a free service to the scientific community (no login required). We hope that you will take benefit from this service. Please do not hesitate to send us your comments/suggestions. Michel Verleysen ===================================================== ESANN - European Symposium on Artificial Neural Networks http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews,... Michel Verleysen Univ. Cath. de Louvain - Microelectronics Laboratory 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at dice.ucl.ac.be * Conference secretariat D facto conference services 27 rue du Laekenveld - B-1080 Brussels - Belgium tel: + 32 2 420 37 57 - fax: + 32 2 420 02 55 mailto:esann at dice.ucl.ac.be ===================================================== From harnad at coglit.ecs.soton.ac.uk Tue Jan 23 13:59:02 2001 From: harnad at coglit.ecs.soton.ac.uk (Stevan Harnad) Date: Tue, 23 Jan 2001 18:59:02 +0000 (GMT) Subject: How and Why to Free the Refereed Research Literature Now Message-ID: For the motivation behind the eprints.org initiative, see: "How and Why to Free the Refereed Research Literature Online Through Author/Institution Self-Archiving, Now" http://www.cogsci.soton.ac.uk/~harnad/Tp/resolution.htm This is to announce that, to coincide with today's Open Meeting in Washington announcing the release of OAI 1.0: http://www.openarchives.org/DC2001/OpenMeeting.html we at Southampton have simultaneously released the OAI 1.0-compliant version of the eprints.org archive-creating software Eprints Version 1.1.1 http://www.eprints.org/ The eprints software is free, of course. Originally created by Matt Hemus as CogPrints , and then extensively re-designed for OA-compliance and generality by Robert Tansley, and recently upgraded to OAI 1.0 by Chris Gutteridge (all at Southampton University), the software has been made as flexible and adaptable as possible, so that all universities and research institutions can immediately adopt and configure it with minimal effort for all disciplines. Hence it complements centralised, discipline-based archiving with distributed, institution-based archiving. The generic version of eprints is fully interoperable with all other OAI-compliant Open Archives. This means that it no longer matters where papers are archived: The papers in all OAI-compliant Archives can be harvested using the OAI protocol into one global "virtual archive" by Open Archives Service Providers such as the Cross Archive Searching Service Below are (1) a testimonial from California Digital Libraries, one of the early adopters of the eprints.org software , (2) the most recent features of eprints 1.1.1 (3) some relevant chronology and URLs. Note that all existing Eprints Archives can be upgraded to OAI 1.0-compliance with the new release. The eprints.org archive-creating software is free, draws only on free software, and will shortly be open-sourced. -------------------------------------------------------------------- Stevan Harnad harnad at cogsci.soton.ac.uk Professor of Cognitive Science harnad at princeton.edu Department of Electronics and phone: +44 23-80 592-582 Computer Science fax: +44 23-80 592-865 University of Southampton http://www.cogsci.soton.ac.uk/~harnad/ Highfield, Southampton http://www.princeton.edu/~harnad/ SO17 1BJ UNITED KINGDOM ------------------------------------------------------------------ EPRINTS 1.1 New features should be regarded as stable; they have been well tested but they have not yet been extensively tested "in the field". Key Upgrades include: OAI 1.0 compliance support for MySQL not running on localhost support for multiple instances of eprints running on one mod_perl/apache server (1.0 claimed to do this but had some problems) new datafield "username" representing users to associate the item with. Bugfixes: mod_perl namespace collisions with multiple eprints (mentioned above). removed GNU-only command options from installation scripts. Please remember to use the online bug tracking system for reporting problems: http://bugs.eprints.org Note the new logo (symbolic of piecing together the global Eprint Archive out of the individual OAI-compliant ones) ---------- Forwarded message ---------- From catherine.candee at ucop.edu Thu Jan 18 08:06:41 2001 From: catherine.candee at ucop.edu (Catherine Candee) Date: Thu, 18 Jan 2001 21:06:41 +0800 Subject: ePrints and eScholarship Message-ID: Stevan, Though we haven't met, I wanted to write you personally to thank you for making ePrints available. Your software is a major contribution to our mutual effort to transform the scholarly communication cycle. I am the CDL director responsible for the eScholarship program, where we are making good use of ePrints. Our repositories provide the foundation of the eScholarship infrastructure. We are providing the first three repositories to scholars in International and Area Studies, Dermatology, and Tobacco Control Research beginning tomorrow, Jan 19, 2001. We expect we will have some interesting findings as they begin to actively test and use these prototype repositories. We have some models for how the repositories will logically fit together with the kind of wider sphere of surrounding scholarly products we envision (e.g., DOJ as overlay journal), but there are many particular issues still to be resolved which may have implications for how the software is developed. We will try to report as much as we can what we learn in our experiment with ePrints. So, on behalf of the eScholarship team and the open archive community, I thank you for this wonderful piece of code. You will be receiving a more formal letter tomorrow, addressed to all eScholarship partners and contributors, which will detail more of the CDL and eScholarship activities. ePrints will be prominently featured in the letter. Best regards, Catherine Candee Director, Scholarly Communication Initiatives California Digital Library University of California 300 Lakeside Drive 6th Floor Oakland, CA 94612-3550 510.987.0425 510.893.5212 (Fax) Catherine.Candee at ucop.edu ______________________________________ SOME RELEVANT CHRONOLOGY AND URLs Psycoloquy (Refereed On-Line-Only Journal) (1989) http://www.cogsci.soton.ac.uk/psycoloquy "Scholarly Skywriting" (1990) http://cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad90.skywriting.html Physics Archive (1991) http://arxiv.org "PostGutenberg Galaxy" (1991) http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad91.postgutenberg.html "Interactive Publication" (1992) http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad92.interactivpub.html Self-Archiving ("Subversive") Proposal (1994) http://www.arl.org/scomm/subversive/toc.html "Tragic Loss" (Odlyzko) (1995) http://www.research.att.com/~amo/doc/tragic.loss.txt "Last Writes" (Hibbitts) (1996) http://www.law.pitt.edu/hibbitts/lastrev.htm NCSTRL: Networked Computer Science Technical Reference Library (1996) http://cs-tr.cs.cornell.edu University Provosts' Initiative (1997) http://library.caltech.edu/publications/ScholarsForum/ CogPrints: Cognitive Sciences Archive (1998) http://cogprints.soton.ac.uk Journal of High Energy Physics (Refereed On-Line-Only Journal) (1998) http://jhep.cern.ch/ Science Policy Forum (1998) http://www.sciencemag.org/cgi/content/full/281/5382/1459 American Scientist Forum (1998) http://amsci-forum.amsci.org/archives/september98-forum.html OpCit:Open Citation Linking Project (1999) http://opcit.eprints.org E-biomed: Varmus (NIH) Proposal (1999) http://www.nih.gov/about/director/pubmedcentral/pubmedcentral.htm Open Archives Initiative (1999) http://www.openarchives.org Cross-Archive Searching Service (2000) http://arc.cs.odu.edu Eprints: Free OAI 1.0-compliant Eprint-Archive-creating software (2001) http://www.eprints.org Harnad Home Pages http://cogsci.soton.ac.uk/harnad/ http://www.princeton.edu/~harnad/ NOTE: A complete archive of the ongoing discussion of providing free access to the refereed journal literature online is available at the American Scientist September Forum (98 & 99 & 00 & 01): http://amsci-forum.amsci.org/archives/september98-forum.html You may join the list at the site above. Discussion can be posted to: september98-forum at amsci-forum.amsci.org From gary at cs.ucsd.edu Wed Jan 24 21:24:03 2001 From: gary at cs.ucsd.edu (Gary Cottrell) Date: Wed, 24 Jan 2001 18:24:03 -0800 (PST) Subject: International Conference on Cognitive Modeling Message-ID: <200101250224.SAA12126@gremlin.ucsd.edu> Fourth International Conference of Cognitive Modeling ICCM-2001 http://www.hfac.gmu.edu/~iccm/ To be held July 26 - 28, 2001, at George Mason University, Fairfax, Virginia, USA. DEADLINE FOR SUBMISSIONS: MARCH 1st 2001 THEME Computational modeling has emerged as a central, but complex and sometimes fractionated theme in research on cognition. ICCM provides a worldwide forum for cognitive scientists who build such computational cognitive models and test them against empirical cognitive data. The goal of ICCM-2001 is to bring researchers from diverse backgrounds together to compare cognitive models, to evaluate models using human data, and to further the development, accumulation, and integration of cognitive theory. SUBMISSION CATEGORIES -- http://www.hfac.gmu.edu/~iccm/ Doctoral Consortium Full day session 1 day prior to main conference for doctoral students to present dissertation proposal ideas to one another and receive feedback from experts from a variety of modeling approaches. Student participants receive complimentary conference registration as well as lodging and travel reimbursement-maximum amounts will be determined at a later date. Newell Prize for Best Student Paper Award given to the paper first-authored by a student that provides the most innovative or complete account of cognition in a particular domain. The winner of the award will receive full reimbursement for the conference fees, lodging costs, and a $1,000 stipend. The Best Applied Research Paper Award To be eligible, 1) the paper should capture behavioral data not gathered in the psychology lab OR the paper should capture behavioral data in a task that has high external validity; 2) the best paper is the one that one from this category that provides the most innovative or complete solution to a real-world, practical problem. Competitive symposia Three to six participants submit a symposium in which they all present models relating to the same domain or phenomenon. The participants must agree upon a set of fundamental issues in their domain that all participants must address or discuss. Papers and Posters Papers and posters will follow the 6-page 10-point double-column single-spaced US-letter format used by the Annual Cognitive Science Society Meeting. Formatting templates and examples will be made available in February 2001. ICCM-2001 http://www.hfac.gmu.edu/~iccm/ DEADLINE FOR SUBMISSIONS: MARCH 1st 2001 -- _/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/ Wayne D. Gray, Program Director HUMAN FACTORS & APPLIED COGNITIVE PROGRAM SNAIL-MAIL ADDRESS (FedX et al) VOICE: +1 (703) 993-1357 George Mason University FAX: +1 (703) 993-1330 ARCH Lab/HFAC Program ********************* MSN 3f5 * Work is infinite, * Fairfax, VA 22030-4444 * time is finite, * http://hfac.gmu.edu/~gray * plan accordingly. * _/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/ From kruschke at indiana.edu Fri Jan 26 08:21:58 2001 From: kruschke at indiana.edu (John K. Kruschke) Date: Fri, 26 Jan 2001 08:21:58 -0500 Subject: postdoc in modeling of cognitive processes Message-ID: <3A7179F6.3A653E8A@indiana.edu> POSTDOCTORAL TRAINING FELLOWSHIPS in the COGNITIVE SCIENCE PROGRAM INDIANA UNIVERSITY in MODELING OF COGNITIVE PROCESSES The Psychology Department and Cognitive Science Program at Indiana University anticipate one or more Postdoctoral Traineeships in the area of Modeling of Cognitive Processes, funded by the National Institutes of Health. Appointments will pay rates appropriate for a new or recent Ph.D. and will be for one or two years, beginning July 1, 2001 or earlier. Traineeships will be offered to qualified individuals who wish to further their training in mathematical modeling or computer simulation modeling, in any substantive area of cognitive psychology or Cognitive Science. Trainees will be expected to carry out original theoretical and empirical research in association with one or more of these faculty and their laboratories, and to interact with other relevant faculty and other pre- and postdoctoral trainees. In addition, they should plan to take or audit courses offered within the Cognitive Modeling Program. We are particularly interested in applicants with strong mathematical, scientific, and research credentials. Indiana University has superb computational and research facilities, and faculty with outstanding credentials in this area of research, including James Townsend, director of the training program, and Jerome Busemeyer, Robert Nosofsky, John Kruschke, Michael Gasser, Robert Goldstone, Geoffrey Bingham, Tom Busey, Donald Robinson, Robert Port, Olaf Sporns, Richard Shiffrin. Applicants should send an up-to-date vita, relevant reprints and preprints, a personal letter describing their research interests, background, goals, and career plans, and reference letters from two individuals. Women, minority group members, and handicapped individuals are urged to apply. Deadline for submission of application materials is April 1, 2001, but we encourage earlier applications. PLEASE NOTE: The conditions of our grant restrict all awards to U.S. citizens or current green card holders. Awards also have a 'payback' provision, generally requiring awardees to carry out research or teach (not necessarily at IU) for a minimum period after termination of the traineeship. Cognitive Science information may be obtained at http://www.psych.indiana.edu/ Send Materials to Professor James T. Townsend Department of Psychology, Rm 367 Indiana University 1101 E. 10th St. Bloomington, IN 47405-7007 Voice: 812-855-4882 Fax: 812-855-1086 email: jtownsen at indiana.edu Indiana University is an Affirmative Action Employer From hans.liljenstrom at sdi.slu.se Fri Jan 26 10:45:01 2001 From: hans.liljenstrom at sdi.slu.se (Hans Liljenstrom) Date: Fri, 26 Jan 2001 16:45:01 +0100 Subject: Workshop on Olfaction - Facts and Models Message-ID: <016701c087af$24142360$abef43c3@lcu1m> Dear Colleagues, A workshop on Olfaction - Facts and Models, is organized in Sigtuna, Sweden, on 8-10 March 2001. For more information, please see websites, www.sdi.slu.se/~hanslil/meetings/olfact2001 or www.agora.kva.se/meetings/olfact2001. Anyone interested in participating is welcome to register. Yours sincerely, Hans Liljenstrm, organizer Dept. of Biometry and Informatics, SLU and Agora for Biosystems ================================================================ Hans Liljenstrm, Assoc. Prof. Dept. of Biometry and Informatics Swedish University of Agricultural Sciences P. O. Box 7013, 750 07 Uppsala, Sweden Phone: +46 (0)18-671728, +46 (0)73-654 7977 Fax: +46 (0)18 673502, email: Hans.Liljenstrom at sdi.slu.se Home page: www.sdi.slu.se ================================================================ From gary at cs.ucsd.edu Fri Jan 26 17:44:55 2001 From: gary at cs.ucsd.edu (Gary Cottrell) Date: Fri, 26 Jan 2001 14:44:55 -0800 (PST) Subject: Student submissions for ICCM-2001 Message-ID: <200101262244.OAA07297@gremlin.ucsd.edu> My apologies, but this update will be important for graduate students who plan to submit papers to the Fourth International Conference on Cognitive Modeling: You'll get free registration, lodging & travel reimbursement if your paper or poster gets in! DEADLINE FOR SUBMISSIONS: MARCH 1st 2001 Web site: http://www.hfac.gmu.edu/~iccm/ From rsun at cecs.missouri.edu Sat Jan 27 17:14:51 2001 From: rsun at cecs.missouri.edu (Ron Sun) Date: Sat, 27 Jan 2001 16:14:51 -0600 Subject: new book on sequence learning Message-ID: <200101272214.QAA18826@pc113.cecs.missouri.edu> Book announcement: SEQUENCE LEARNING: PARADIGMS, ALGORITHMS, AND APPLICATIONS edited by: Ron Sun and C. L. Giles published by Springer-Verlag: LNAI 1828 This book is intended for use by scientists, engineers, and students interested in sequence learning in artificial intelligence, neural networks, and cognitive science. The book will introduce essential algorithms and methods of sequence learning and further develop them in various ways. With the help of these concepts, a variety of applications will be examined. This book will allow the reader to acquire an appreciation of the breadth and variety sequence learning and its potential as an interesting area of research and application. The reader is assumed to have basic knowledge of neural networks and AI concepts. Sequential behavior is essential to intelligence and a fundamental part of human activities ranging from reasoning to language, and from everyday skills to complex problem solving. Sequence learning is an important component of learning in many task domains --- planning, reasoning, robotics, natural language processing, speech recognition, adaptive control, time series prediction, and so on. Naturally, there are many different approaches towards sequence learning. These approaches deal with somewhat differently formulated sequential learning problems, and/or different aspects of sequence learning. This book will provide an overall framework for this field of study. --------------------------------------------------------- Table of Contents Introduction to Sequence Learning by Ron Sun Part 1: Sequence Clustering and Learning with Markov Models Sequence Learning via Bayesian Clustering by Dynamics by Paola Sebastiani, Marco Ramoni, Paul Cohen Using Dynamic Time Warping to Bootstrap HMM-Based Clustering of Time Series by Tim Oates, Laura Firoiu, Paul Cohen Part 2: Sequence Prediction and Recognition with Neural Networks Anticipation Model for Sequential Learning of Complex Sequences by DeLiang Wang Bidirectional Dynamics for Protein Secondary Structure Prediction by Pierre Baldi, Soren Brunak, Paolo Frasconi, Gianluca Pollastri, Gio- vanni Soda Time in Connectionist Models by Jean-Cedric Chappelier, Marco Gori, Alain Grumbach On the Need for a Neural Abstract Machine by Diego Sona, Alessandro Sperduti Part 3: Sequence Discovery with Symbolic Methods Sequence Mining in Categorical Domains: Algorithms and Applications by Mohammed J. Zaki Sequence Learning in the ACT-R Cognitive Architecture: Empirical Anal- ysis of a Hybrid Model by Christian Lebiere, Dieter Wallach Part 4: Sequential Decision Making Sequential Decision Making Based on Direct Search by Jurgen Schmidhuber Automatic Segmentation of Sequences through Hierarchical Reinforcement Learning by Ron Sun, Chad Sessions Hidden-Mode Markov Decision Processes for Nonstationary Sequential De- cision Making by Samuel P. M. Choi, Dit-Yan Yeung, Nevin L. Zhang Pricing in Agent Economies Using Neural Networks and Multi-agent Q- learning by Gerald Tesauro Part 5: Biologically Inspired Sequence Learning Models Multiple Forward Model Architecture for Sequence Processing by Raju S. Bapi, Kenji Doya Integration of Biologically Inspired Temporal Mechanisms into a Cortical Framework for Sequence Processing by Herve Frezza-Buet, Nicolas Rougier, Frederic Alexandre Attentive Learning of Sequential Handwriting Movements: A Neural Net- work Model by Stephen Grossberg, Rainer Paine About Editors Author Index ------------------------------------------------------------ To order, go to http://www.cecs.missouri.edu/~rsun/book5-ann.html http://www.springer.de/cgi-bin/search_book.pl?isbn=3-540-41597-1 http://www.springer.de/comp/lncs/ http://www.cecs.missouri.edu/~rsun/ 2001. XII, 391 pp. Softcover 3-540-41597-1 DM 82, Recommended List Price http://www.springer.de/contact.html phone +49 6221 487 0 =========================================================================== Prof. Ron Sun http://www.cecs.missouri.edu/~rsun CECS Department phone: (573) 884-7662 University of Missouri-Columbia fax: (573) 882 8318 201 Engineering Building West Columbia, MO 65211-2060 email: rsun at cecs.missouri.edu http://www.cecs.missouri.edu/~rsun http://www.cecs.missouri.edu/~rsun/journal.html http://www.elsevier.com/locate/cogsys =========================================================================== From lunga at ifi.unizh.ch Sat Jan 27 12:38:08 2001 From: lunga at ifi.unizh.ch (Max Lungarella) Date: 27 Jan 2001 18:38:08 +0100 Subject: CALL FOR CONTRIBUTIONS - EDEC2001 Message-ID: <3A730780.CDD8875C@ifi.unizh.ch> CALL FOR CONTRIBUTIONS EDEC2001 - EMERGENCE AND DEVELOPMENT OF EMBODIED COGNITION Symposium at the 3rd International Conference on Cognitive Science August 27-31, 2001, Beijing, China SCOPE The objective of the symposium is to bring together researchers from cognitive science, psychology, engineering, robotics, artificial intelligence, philosophy, and related fields so as to further our understanding of embodiment and development, in particular their mutual relationship. Ultimately, the goal is to understand the emergence of high-level cognition of an organism interacting with its physical and social environment over extended periods of time. FOCUS The symposium will focus on research that explicitly takes embodiment into account, either at the level of computational models, or real-world devices, and on empirical work that explicitly attempts to explain the relation of developmental processes to embodiment. Finally, contributions giving a broad and novel philosophical or methodological view on embodied cognition are welcome. CONTRIBUTIONS Contributions are solicited from the following areas (but not restricted to this list): - Cognitive developmental robotics - Neural mechanisms of learning and development (e.g. neural networks, statistical, information theoretic) - Development of sensory and motor systems - Perception-action coupling, sensory-motor coordination - Categorization, object exploration - Communication and Social interaction - Methodologies - Debates and philosophical issues (e.g. constructivism vs. selectionism, nature nurture, scalability, symbol grounding) ORGANIZATION This will be a one-day symposium with a number of talks, with a lot of room for discussion, and a poster session. The poster session will be over a cocktail to ensure relaxed atmosphere. FORM OF CONTRIBUTION Contributions can be in the form of full papers, or abstracts for posters. Full papers must be 5 pages maximum, with fonts at least 12 pt. For posters and work in progress, please submit a one-page abstract. Accepted contributions will be published in the proceedings of the ICCS 2001. GUIDELINES FOR ABSTRACT/PAPER SUBMISSION The contribution should be submitted electronically to lunga at ifi.unizh.ch (Max Lungarella) in pdf, or MS Word files. IMPORTANT DATES Full papers submission: March 30, 2001 One-page abstracts submission: April 30, 2001: Notice of acceptance: May 30, 2001 PROGRAM COMMITTEE Rolf Pfeifer (AI Lab, University of Zurich, chair) Max Lungarella (AI Lab, University of Zurich, Switzerland) Yasuo Kuniyoshi (Electrotechnical Laboratory, Tsukuba, Japan) Olaf Sporns (Department of Psychology, Indiana University, Bloomington, IN, USA) Giorgio Metta (LIRA-Lab, University of Genova, Italy) Giulio Sandini (LIRA-Lab, University of Genova, Italy) Rafael Nunez (University of Fribourg, Switzerland, and University of California, Berkeley) FOR MORE INFORMATION email: lunga at ifi.unizh.ch From arenart at delta.ft.uam.es Mon Jan 29 10:25:48 2001 From: arenart at delta.ft.uam.es (arenart) Date: Mon, 29 Jan 2001 15:25:48 +0000 (GMT) Subject: PhD Scolarship in Computational Neuroscience in Madrid. Message-ID: PhD SCHOLARSHIP IN COMPUTATIONAL NEUROSCIENCE DEPARTMENT OF THEORETICAL PHYSICS UNIVERSIDAD AUTONOMA DE MADRID MADRID - SPAIN One PhD scholarship is available at the group of Computational Neuroscience of the Universidad Autonoma de Madrid (UAM) for thesis research on computational approaches to brain function. The scholarship is to work with Prof Nestor Parga and colleagues to develop and apply theoretical techniques to study information processing in the brain. The appointee will be working collaboratively as part of a team. Highly motivated candidates should have a degree in a relevant scientific discipline such as Physics, Mathematics, Computer Science, or a Neuroscience-related discipline, have knowledge of basic computer programming and an interest in computational approaches to brain function (information theory, statistical physics, numerical simulations). The scholarship is for a period of four years, starting after the summer of 2001. Candidates should be citizens from countries members of the European Union. For more information about the group activities see: http://ket.ft.uam.es/~neurociencia/GRUPO/grupo_english.html or, in spanish: http://ket.ft.uam.es/~neurociencia/GRUPO/grupo.html Candidates should contact us as soon as possible (in any case before February the 8th) by sending their CV together with the name of two references by email or fax to: Jaime de la Rocha: E-mail: jrocha at delta.ft.uam.es Fax: (+34) 91 397-3936 ------------------------------------------------------------------- | Jaime de la Rocha | | | Phone : (+34) 91-397-4884 | | Dpto. de Fisica Teorica, C-XI | Fax : (+34) 91-397-3936 | | Universidad Autonoma de Madrid | E-mail: jrocha at delta.ft.uam.es| | 28049 Madrid, SPAIN | | | | | http://ket.ft.uam.es/~neurociencia/GRUPO/grupo_english.html | ------------------------------------------------------------------- From nolfi at www.ip.rm.cnr.it Mon Jan 29 11:49:01 2001 From: nolfi at www.ip.rm.cnr.it (Stefano Nolfi) Date: Mon, 29 Jan 2001 17:49:01 +0100 Subject: Evolutionary Robotics: new book and software available Message-ID: <3.0.2.32.20010129174901.00efb96c@www.ip.rm.cnr.it> (Our apologies for multiple copies of this message) EVOLUTIONARY ROBOTICS THE BIOLOGY, INTELLIGENCE, AND TECHNOLOGY OF SELF-ORGANIZING MACHINES Stefano Nolfi and Dario Floreano MIT Press/ Bradford Books Evolutionary robotics is a new technique for the automatic creation of autonomous robots. Inspired by the Darwinian principle of selective reproduction of the fittest, it views robots as autonomous artificial organisms that develop their own skills in close interaction with the environment and without human intervention. Drawing heavily on biology and ethology, it uses the tools of neural networks, genetic algorithms, dynamic systems, and biomorphic engineering. The resulting robots share with simple biological systems the characteristics of robustness, simplicity, small size, flexibility, and modularity. In evolutionary robotics, an initial population of artificial chromosomes, each encoding the control system of a robot, is randomly created and put into the environment. Each robot is then free to act (move, look around, manipulate) according to its genetically specified controller while its performance on various tasks is automatically evaluated. The fittest robots then "reproduce" by swapping parts of their genetic material with small random mutations. The process is repeated until the "birth" of a robot that satisfies the performance criteria. This book describes the basic concepts and methodologies of evolutionary robotics and the results achieved so far. An important feature is the clear presentation of a set of empirical experiments of increasing complexity. Software with a graphic interface, freely available on a Web page (http://gral.ip.rm.cnr.it/evorobot/simulator.html), allows the reader to replicate and vary (in simulation and on real robots) most of the experiments. Stefano Nolfi is Coordinator of the Division of Neural Systems and Artificial Life, Institute of Psychology, National Research Council, Rome. Dario Floreano is Assistant Professor of Evolutionary and Adaptive Systems at the Swiss Federal Institute of Technology in Lausanne (EPFL). CONTENTS 1. The Role of Self-organization for the Synthesis and the Understanding of Behavioral Systems 2. Evolutionary and Neural Techniques 3. How to Evolve Robots 4. Evolution of Simple Navigation 5. Power and Limits of Reactive Intelligence 6. Beyond Reactive Intelligence 7. Learning and Evolution 8. Competitive Co-Evolution 9. Encoding, Mapping, and Development 10. Complex Hardware Morphologies: Walking Machines 11. Evolvable Hardware Intelligent Robots and Autonomous Agents series edited by Ronald C. Arkin, MIT Press. November 2000 ISBN 0-262-14070-5 384 pp., 157 illus. The book is distributed by MIT Press: http://mitpress.mit.edu/book-home.tcl?isbn=0262140705 It is also available trough amazon: http://www.amazon.com/exec/obidos/ASIN/0262140705/qid%253D967489468/sr%253D1 -2/105-3677959-5763124 To download the Evorobot software visit: http://gral.ip.rm.cnr.it/evorobot/simulator.html For more information about Evolutionary Robotics visit: http://gral.ip.rm.cnr.it/evorobot/ -------------------------------------------------------------------------- Stefano Nolfi Institute of Psychology, C.N.R. Viale Marx, 15 - 00137 - Rome - Italy voice: 0039-06-86090231 fax: 0039-06-824737 e-mail: nolfi at ip.rm.cnr.it www: http://gral.ip.rm.cnr.it/nolfi From ken at phy.ucsf.edu Mon Jan 29 15:49:05 2001 From: ken at phy.ucsf.edu (Ken Miller) Date: Mon, 29 Jan 2001 12:49:05 -0800 (PST) Subject: Paper Available: Model of cat V1 nonlinear response properties Message-ID: <14965.55105.406468.602701@coltrane.ucsf.edu> The following paper is now available from: http://www.keck.ucsf.edu/~ken [click on 'publications', then click on 'models of neuronal integration and circuits'] or directly by ftp: ftp://ftp.keck.ucsf.edu/pub/ken/kayser_etal.pdf (pdf file) ftp://ftp.keck.ucsf.edu/pub/ken/kayser_etal.ps.gz (gzipped postscript) "Contrast-Dependent Nonlinearities Arise Locally in a Model of Contrast-Invariant Orientation Tuning" by Andrew Kayser, Nicholas J. Priebe, and Kenneth D. Miller In Press, Journal of Neurophysiology ABSTRACT: We study a recently proposed ``correlation-based'', push-pull model of the circuitry of layer 4 of cat visual cortex (Troyer et al., 1998). This model was previously shown to explain the contrast-invariance of cortical orientation tuning. Here we show that it can simultaneously account for several contrast-dependent (c-d) ``nonlinearities'' in cortical responses. These include an advance with increasing contrast in the temporal phase of response to a sinusoidally modulated stimulus; a change in shape of the temporal frequency tuning curve, so that higher temporal frequencies may give little or no response at low contrast but reasonable responses at high contrast; and contrast saturation that occurs at lower contrasts in cortex than in the lateral geniculate nucleus (LGN). In the context of the model circuit, these properties arise from a mixture of nonlinear cellular and synaptic mechanisms: short-term synaptic depression, spike-rate adaptation, contrast-induced changes in cellular conductance, and the nonzero spike threshold. The former three mechanisms are sufficient to explain the experimentally observed increase in c-d phase advance in cortex relative to LGN. The c-d changes in temporal frequency tuning arise as a threshold effect: voltage modulations in response to higher-frequency inputs are only slightly above threshold at lower contrast, but become robustly suprathreshold at higher contrast. The other three nonlinear mechanisms also play a crucial role in this result, allowing contrast-dependence of temporal frequency tuning to coexist with contrast-invariance of orientation tuning. Contrast saturation, and the observation that responses to stimuli of increasing temporal frequency saturate at increasingly high contrasts, can be induced both by the model's push-pull inhibition and by synaptic depression. Previous proposals explained these nonlinear response properties by assuming contrast-invariant orientation tuning as a starting point, and adding normalization by shunting inhibition derived equally from cells of all preferred orientations. The present proposal simultaneously explains both contrast-invariant orientation tuning and these contrast-dependent nonlinearities, and requires only processing that is local in orientation, in agreement with intracellular measurements (Ferster, 1986; Anderson et al., 2000). Ken Kenneth D. Miller telephone: (415) 476-8217 Associate Professor fax: (415) 476-4929 Dept. of Physiology, UCSF internet: ken at phy.ucsf.edu 513 Parnassus www: http://www.keck.ucsf.edu/~ken San Francisco, CA 94143-0444 From ml_conn at infrm.kiev.ua Mon Jan 29 17:17:14 2001 From: ml_conn at infrm.kiev.ua (Dmitri Rachkovskij) Date: Tue, 30 Jan 2001 00:17:14 +0200 (UKR) Subject: Connectionist symbol processing: any progress? References: <200101230057.CWA74441@kozlik.carrier.kiev.ua> Message-ID: <2.07b5.23A15.G7Y38Q@infrm.kiev.ua> Keywords: distributed representation, sparse coding, binary coding, binding, variable binding, representation of structure, structured representation, recursive representation, nested representation, compositional distributed representations, connectionist symbol processing Dear Colleagues, The following paper (abstract enclosed): Rachkovskij, Dmitri A. and Kussul, Ernst M. (2001) Binding and Normalization of Binary Sparse Distributed Representations by Context-Dependent Thinning. Neural Computation 13(2): 411-45 will be on-line for NC subscribers at http://neco.mitpress.org/. For those without access to Neural Computation, a draft is available at: http://cogprints.soton.ac.uk/documents/disk0/00/00/12/40/index.html or by ID code: cog00001240 at http://cogprints.soton.ac.uk/ Thank you and best regards, Dmitri Rachkovskij ************************************************************************* Dmitri A. Rachkovskij, Ph.D. Net: dar at infrm.kiev.ua Senior Researcher, V.M.Glushkov Cybernetics Center, Tel: 380 (44) 266-4119 Pr. Acad. Glushkova 40, Kiev 03680, UKRAINE Fax: 380 (44) 266-1570 ************************************************************************* Encl: Abstract Distributed representations were often criticized as inappropriate for encoding of data with a complex structure. However Plate's Holographic Reduced Representations and Kanerva's Binary Spatter Codes are recent schemes that allow on-the-fly encoding of nested compositional structures by real-valued or dense binary vectors of fixed dimensionality. In this paper we consider procedures of the Context-Dependent Thinning which were developed for representation of complex hierarchical items in the architecture of Associative-Projective Neural Networks. These procedures provide binding of items represented by sparse binary codevectors (with low probability of 1s). Such an encoding is biologically plausible and allows a high storage capacity of distributed associative memory where the codevectors may be stored. In contrast to known binding procedures, Context-Dependent Thinning preserves the same low density (or sparseness) of the bound codevector for varied number of component codevectors. Besides, a bound codevector is not only similar to another one with similar component codevectors (as in other schemes), but it is also similar to the component codevectors themselves. This allows the similarity of structures to be estimated just by the overlap of their codevectors, without retrieval of the component codevectors. This also allows an easy retrieval of the component codevectors. Examples of algorithmic and neural-network implementations of the thinning procedures are considered. We also present representation examples for various types of nested structured data (propositions using role-filler and predicate-arguments representation schemes, trees, directed acyclic graphs) using sparse codevectors of fixed dimension. Such representations may provide a fruitful alternative to the symbolic representations of traditional AI, as well as to the localist and microfeature-based connectionist representations. From oby at cs.tu-berlin.de Tue Jan 30 09:13:52 2001 From: oby at cs.tu-berlin.de (Klaus Obermayer) Date: Tue, 30 Jan 2001 15:13:52 +0100 (MET) Subject: papers available Message-ID: <200101301413.PAA24205@pollux.cs.tu-berlin.de> Dear Connectionists, attached please find abstracts and preprint locations of two manuscripts with results in the neuronformatics area (confocal microscopy). Comments are welcome! Cheers Klaus ------------------------------------------------------------------------- Prof. Dr. Klaus Obermayer phone: 49-30-314-73442 FR2-1, NI, Informatik 49-30-314-73120 Technische Universitaet Berlin fax: 49-30-314-73121 Franklinstrasse 28/29 e-mail: oby at cs.tu-berlin.de 10587 Berlin, Germany http://ni.cs.tu-berlin.de/ ========================================================================= Visualization of synaptic markers in the optic neuropils of Drosophila using a new constrained deconvolution method. P. R. Hiesinger^1, M. Scholz^2, I. A. Meinertzhagen^3, K.-F. Fischbach^1, and K. Obermayer^2. ^1 Institut fuer Biologie III, Universitaet Freiburg, Freiburg, Germany ^2 Fakultaet fuer Elektrotechnik und Informatik, TU Berlin, Berlin, Germany ^3 Neuroscience Institute, Dalhousie University, Halifax, Canada The fruitfly Drosophila melanogaster offers compelling genetic advantages for the analysis of its nervous system, but cell size precludes immunocytochemical analysis of wild-type structure and mutant phenotypes beyond the level of neuronal arborizations. For many antibodies, especially when immunoelectron microscopy is not feasible, it would therefore be desirable to extend the resolution limit of confocal microscopy as far as possible. Because high-resolution confocal microscopy suffers from considerable blurring, so-called deconvolution algorithms are needed to remove, at least partially, the blur introduced by the microscope and by the specimen itself. Here, we present the establishment and application of a new deconvolution method to visualize synaptic markers in Drosophila optic neuropils at the resolution limit of light. We ascertained all necessary parameters experimentally and verified them by deconvolving injected fluorescent microshperes in immunostained optic lobe tissue. The resulting deconvolution method was used to analyze colocalization between the synaptic vesicle marker neuronal synaptobrevin and synaptic and putative synaptic markers in photoreceptor terminals. We report differential localization of these near the resolution limit of light, which could not be distinguished without deconvolution. in: Journal of Comparative Neurology 429, 277ff. available at: http://ni.cs.tu-berlin.de/publications/ ------------------------------------------------------------------------- Corrections methods for three-dimensional reconstructions from confocal images: I. tissue shrinking and axial scaling. D. Bucher^1, M. Scholz^2, M. Stetter^2, K. Obermayer^2, and H.-J. Pflueger^1 ^1 Institut fuer Biologie, FU Berlin, Berlin, Germany ^2 Fakultaet fuer Elektrotechnik und Informatik, TU Berlin, Berlin, Germany We show here, using locust wholemount ganglia as an example, that scaling artifacts in three-dimensional reconstructions from confocal microscopic images due to refractive index mismatch in the light path and tissue shrinking, can account for dramatic errors in measurements of morphometric values. Refractive index mismatch leads to considerable alteration of the axial dimension, and true dimensions must be restored by rescaling the z-axis of the image stack. The appropriate scaling factor depends on the refractive indices of the media in the light path and the numerical aperture of the objective used and can be determined by numerical simulations, as we show here. In addition, different histochemical procedures were tested in regard to their effect on tissue dimensions. Reconstructions of scans at different stages of these protocols show that shrinking can be avoided prior to clearing when dehydrating ethanol series are carefully applied. Fixation and mismatching buffer osmolarity have no effect. We demonstrate procedures to reduce artifacts during mounting and clearing in methyl salicylate, such that only isometric shrinkage occurs, which can easily be corrected by rescaling the image dimensions. Glycerol-based clearing agents produced severe anisometric and nonlinear shrinkage and we could not find a way to overcome this. in: Journal of Neuroscience Methods 100, 135ff available at: http://ni.cs.tu-berlin.de/publications/ From d.mareschal at bbk.ac.uk Tue Jan 30 11:17:54 2001 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Tue, 30 Jan 2001 17:17:54 +0100 Subject: Phd Studentships Message-ID: Dear all, The School of Psychology, Birkbeck College, University of London has a number of studentships on offer for students beginning MPhil/Phd programmes in October 2001. Details of the studentships available can be found at the following web page http://www.psyc.bbk.ac.uk/announce/studentship2001.htm The School of Psychology (which includes the Centre for Brain and Cognitive Development and the Centre for Psychosocial Studies) has strong research interests in a range of areas including Cognitive Science, Child and Family Studies, Cognition and Action. Details of the research interests of staff in the school can be obtained from: http://www.psyc.bbk.ac.uk ================================================= Dr. Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 020 7631-6582/6207 fax +44 020 7631-6312 http://www.psyc.bbk.ac.uk/staff/dm.html ================================================= From mccallum at whizbang.com Wed Jan 31 13:22:09 2001 From: mccallum at whizbang.com (Andrew McCallum) Date: Wed, 31 Jan 2001 13:22:09 -0500 Subject: CFP IJCAI'01 Workshop on "Text Learning: Beyond Supervision" Message-ID: <200101311822.NAA09303@slide.whizbang.com> CALL FOR PAPERS IJCAI-01 Workshop on "Text Learning: Beyond Supervision" Monday, 6 August 2001 Seattle, Washington, USA www.cs.cmu.edu/~mccallum/textbeyond Submission deadline: March 23, 2001 Due to the rapidly increasing amount of textual data available and the range of interesting and important problems arising in text analysis, there has been growing interest in applying machine learning methods to text. There has also been significant recent interest in research that combines supervised and unsupervised learning. This research is especially relevant to text learning because the inherent complexity of natural language usually requires models with many parameters: estimating those parameters requires a lot of data, and obtaining labeled data is difficult and expensive. By combining unsupervised learning with supervised learning, the need for labeled training data can often be greatly reduced, allowing for the development of more powerful models and methods. The workshop will explore machine learning methods for solving supervised text learning tasks that exploit training methods beyond straightforward supervised learning. Relevant topics include: * Text classification with labeled and unlabeled data: EM, co-training, transduction with SVMs, discriminative maximum entropy with unlabeled data. * Information extraction with unlabeled data: bootstrapping, co-boosting. * Part-of-speech tagging, parsing and other NLP with unlabeled data. * Active learning: uncertainty sampling, query-by-committee, version space reduction. * Model selection with unlabeled data. * Word clustering for language modeling, distributional clustering, feature generation by clustering. * Semi-supervised clustering, document clustering with user-feedback. * Integrating prior knowledge into supervised learning, integrating distantly labeled data. * Unsupervised methods for learning segmentation models, translation models, lexicons, etc. * Link analysis for supervised learning. The goal of this workshop is to bring together researchers from the machine learning, information retrieval, computational linguistics and language modeling to talk about their different perspectives and to share their latest ideas. INVITED SPEAKERS ---------------- David Yarowsky Assistant Professor Department of Computer Science Johns Hopkins University http://www.cs.jhu.edu/~yarowsky Tommi Jaakkola Assistant Professor Department of Computer Science Massachusetts Institute of Technology http://www.ai.mit.edu/people/tommi/tommi.html SCHEDULE AND SUBMISSION PROCEDURE --------------------------------- Friday, Mar 23 2001 Paper submissions due Friday, Apr 06 2001 Acceptance notification Friday, Apr 20 2001 Camera ready papers due Authors are asked to prepare a paper in Postscript or PDF format. Submissions should conform to the IJCAI-2001 format, and be 8 pages or less. We encourage submissions containing original theoretical and applied concepts. Experimental results are also encouraged, even if they are only preliminary. To submit a paper, email it to textbeyond at whizbang.com before 6pm on the day of the deadline. ORGANIZING COMMITTEE -------------------- Andrew McCallum WhizBang Labs - Research, 4616 Henry Street, Pittsburgh, PA 15218 T: 412-683-9132 F: 412-683-4436 mccallum at whizbang.com http://www.cs.cmu.edu/~mccallum Kamal Nigam School of Computer Science, Carnegie Mellon, Pittsburgh, PA 15213 T: 412-268-3070 F: 412-268-5576 knigam at cs.cmu.edu http://www.cs.cmu.edu/~knigam Tony Jebara MIT, Media Laboratory - 20 Ames Street, E15-390, Cambridge, MA 02138 T: 617-253-0326 F: 617-253-8874 jebara at media.mit.edu http://www.media.mit.edu/~jebara Lillian Lee Department of Computer Science, Cornell University, Ithaca, NY 14853 T: 607-255-8119 F: 607-255-4428 llee at cs.cornell.edu http://www.cs.cornell.edu/home/llee