From bogus@does.not.exist.com Wed Jan 1 20:26:04 2003 From: bogus@does.not.exist.com () Date: Thu, 2 Jan 2003 09:26:04 +0800 Subject: Research positions in bioinformatics, BIRC, Singapore. Message-ID: <9CFE75F87A78564887952466CA3F4E4D0176C11A@exchange02.staff.main.ntu.edu.sg> From terry at salk.edu Thu Jan 2 18:30:48 2003 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 2 Jan 2003 15:30:48 -0800 (PST) Subject: NEURAL COMPUTATION 15:1 In-Reply-To: <200211220021.gAM0LdU25878@purkinje.salk.edu> Message-ID: <200301022330.h02NUmE66618@purkinje.salk.edu> Neural Computation - Contents - Volume 15, Number 1 - January 1, 2003 ARTICLE Asynchronous States and the Emergence of Synchrony in Large Networks of Interacting Excitatory and Inhibitory Neurons D. Hansel and G. Mato NOTE A Constrained EM Algorithm for Principal Component Analysis Jong-Hoon Ahn and Jong-Hoon Oh LETTERS Higher-Order Statistics of Input Ensembles and the Response of Simple Model Neurons Alexandre Kuhn, Ad Aertsen and Stefan Rotter Duality of Rate Coding and Temporal Coding in Multilayered Feedforward Networks Naoki Masuda and Kazuyuki Aihara Synchronous Firing and Higher-Order Interactions in Neuron Pool Shun-ichi Amari, Hiroyuki Nakahara, Si Wu and Yutaka Sakai Determination of Firing Times for the Stochastic Fitzhugh-Nagumo Neuronal Model Henry C. Tuckwell, Roger Rodriguez and Frederic Y.M. Wan Developmental Constraints Aid the Acquisition of Binocular Disparity Sensitivities Melissa Dominguez and Robert A. Jacobs A Quantified Sensitivity Measure for Multilayer Perceptron to Input Perturbation Xiaoqin Zeng and Daniel S. Yeung Variational Mixture of Bayesian Independent Component Analysers R. A. Choudrey and S. J. Roberts ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2003 - VOLUME 15 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $95 $101.65 $143 Institution $590 $631.30 $638 * 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 deniz at cnel.ufl.edu Thu Jan 2 14:55:37 2003 From: deniz at cnel.ufl.edu (Deniz Erdogmus) Date: Thu, 02 Jan 2003 14:55:37 -0500 Subject: IEEE-TNN Special Issue on Information Theoretic Learning Message-ID: <3E149939.72F07F4F@cnel.ufl.edu> Dear Colleagues, This is a reminder for the upcoming special issue of the IEEE Transactions on Neural Networks on Information Theoretic Learning. The call for papers of this special issue can be viewed at http://sonics.cnel.ufl.edu/cnel02/ Prospective authors can also register their intent to submit a paper and later submit their papers at the same website. The TNN notice for this issue is located at http://ieee-nns.org/pubs/tnn/special.html The paper submission deadline is March 15th, 2003. Happy new year and best regards, Deniz Erdogmus From bogus@does.not.exist.com Fri Jan 3 18:59:26 2003 From: bogus@does.not.exist.com () Date: Fri, 3 Jan 2003 15:59:26 -0800 Subject: R&D Openings at Fair Isaac & Company Message-ID: <5FF0FAAD57CE8845B79FD7B7CFF8F29E010C42@sdomsg00.corp.fairisaac.com> From cia at bsp.brain.riken.go.jp Fri Jan 3 13:18:52 2003 From: cia at bsp.brain.riken.go.jp (Andrzej CICHOCKI) Date: Sat, 04 Jan 2003 03:18:52 +0900 Subject: Book and software announcement - Cichocki Message-ID: <3E15D40C.1060209@bsp.brain.riken.go.jp> [Our sincere apologies if you receive multiple copies of this email] I am please to announce that Chapter 1, as well as, tables with algorithms, simulations examples, benchmarks and bibliography of revised and corrected version of the following book: ADAPTIVE BLIND SIGNAL and IMAGE PROCESSING: Learning Algorithms and Applications A. Cichocki and S. Amari Published by John Wiley & Sons, Chichester UK, 2002 are now available free at our web page: http://www.bsp.brain.riken.go.jp/ICAbookPAGE/ Moreover, versions 1.2 of associated ICALAB MATLAB Toolboxes for signals and images processing with revised on-line helps and with useful preprocessing are available at : http://www.bsp.brain.riken.go.jp/ICALAB/ http://www.bsp.brain.riken.go.jp/ICALAB/ICALABSignalProc/ http://www.bsp.brain.riken.go.jp/ICALAB/ICALABImageProc/ Version 1.4 with several new features and improved algorithms will be released soon. All comments and suggestions are welcome. Best regards, Andrzej Cichocki --------------------------------------------------- Laboratory for Advanced Brain Signal Processing, Brain Science Institute, Riken 2-1 Hirosawa, Wako-shi, Saitama 351-0198, JAPAN http://www.bsp.brain.riken.go.jp/ From nnk at his.atr.co.jp Sun Jan 5 19:28:00 2003 From: nnk at his.atr.co.jp (Neural Networks Japan Office) Date: Mon, 6 Jan 2003 09:28:00 +0900 Subject: Neural Networks 16(1) Message-ID: NEURAL NETWORKS 16(1) Contents - Volume 16, Number 1 - 2003 ------------------------------------------------------------------ Editorial for 2003: Celebrating the year with a special issue for IJCNN'03 Neural Networks Referees used in 2002 NEURAL NETWORKS LETTER: Reinforcement-learning of reinforcement learning. Nicolas Schweighofer, Kenji Doya CONTRIBUTED ARTICLES: ***** Psychology and Cognitive Science ***** Learning to generate articulated behavior through the bottom-up and the top-down interaction processes. Jun Tani Computational model for neural representation of multiple disparities. Osamu Watanabe, Masanori Idesawa ***** Neuroscience and Neuropsychology ***** A synfire chain in layered coincidence detectors with random synaptic delays. Kazushi Ikeda ***** Mathematical and Computational Analysis ***** Mathematical analysis of a correlation-based model for orientation map formation. Tadashi Yamazaki The functional localization of neural networks using genetic algorithms. Hiroshi Tsukimoto, Hisaaki Hatano A new EM-based training algorithm for RBF networks. Marcelino Lazaro, Ignacio Santamaria, Carlos Pantaleon Analysis of Tikhonov regularization for function approximation by neural networks. Martin Burger, Andreas Neubauer Predicting the behaviour of G-RAM networks. Geoffrey G. Lockwood, Igor Aleksander ***** Engineering and Design ***** On-line identification and reconstruction of finite automata with generalized recurrent neural networks. Ivan Gabrijel, Andrej Dobnikar ***** Technology and Applications ***** Classification of clustered microclacifications using a Shape Cognitron neural network. San-Kan Lee, Pau-choo Chung, Chein-I Chang, Chien-Shun Lo, Tain Lee Giu-Cheng Hsu, Chin-Wen Yang On learning to estimate the block directional image of a fingerprint using a hierarchical neural network. Khaled Ahmed Nagaty BOOK REVIEW Review of "Self-organizing Neural Networks: Recent Advances and Applications" (U. Seiffert, L.C. Jain, editors) by F. Azuaje ERRATUM Erratum to "Book Review:Learning Kernel Classifiers" [Neural Networks 15(7) 930] by R. Williamson CURRENT EVENTS ------------------------------------------------------------------ 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 (regular) SEK 660 (regular) Y 13,000 (regular) Neural Networks (plus 2,000 enrollment fee) $20 (student) SEK 460 (student) Y 11,000 (student) (plus 2,000 enrollment fee) ----------------------------------------------------------------------------- membership without $30 SEK 200 not available to Neural Networks non-students (subscribe through another society) Y 5,000 (student) (plus 2,000 enrollment fee) ----------------------------------------------------------------------------- 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 Takashi Nagano Faculty of Engineering Hosei University 3-7-2, Kajinocho, Koganei-shi Tokyo 184-8584 Japan 81 42 387 6350 (phone and fax) jnns at k.hosei.ac.jp http://jnns.inf.eng.tamagawa.ac.jp/home-j.html ----------------------------------------------------------------- From baluja at cs.cmu.edu Tue Jan 7 01:09:11 2003 From: baluja at cs.cmu.edu (Shumeet Baluja) Date: Tue, 07 Jan 2003 01:09:11 -0500 Subject: PAPER: Using a priori knowledge to create probabilistic models for optimization Message-ID: <19717.1041919751@ux4.sp.cs.cmu.edu> The following paper is available from: http://www.cs.cmu.edu/~baluja Using a priori knowledge to create probabilistic models for optimization ABSTRACT: Recent studies have examined the effectiveness of using probabilistic models to guide the sample generation process for searching high dimensional spaces. Although the simplest models, which do not account for parameter interdependencies, often perform well on many problems, they may perform poorly when used on problems that have a high degree of interdependence between parameters. More complex dependency networks that can account for the interactions between parameters are required. However, building these networks may necessitate enormous amounts of sampling. In this paper, we demonstrate how a priori knowledge of parameter dependencies, even incomplete knowledge, can be incorporated to efficiently obtain accurate models that account for parameter interdependencies. This is achieved by effectively putting priors on the network structures that are created. These more accurate models yield improved results when used to guide the sample generation process for search and also when used to initialize the starting points of other search algorithms. Please feel free to send questions/comments to baluja at cs.cmu.edu. best, shumeet From terry at salk.edu Tue Jan 7 17:58:04 2003 From: terry at salk.edu (Terry Sejnowski) Date: Tue, 7 Jan 2003 14:58:04 -0800 (PST) Subject: Telluride Neuromorphic Engineering Workshop Message-ID: <200301072258.h07Mw4g70837@purkinje.salk.edu> ------------------------------------------------------------------------ NEUROMORPHIC ENGINEERING WORKSHOP Sunday, JUNE 29 - Saturday, JULY 19, 2003 TELLURIDE, COLORADO http://www.ini.unizh.ch/telluride/ ------------------------------------------------------------------------ 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 the annual three week "Telluride Workshop and Summer School on Neuromorphic Engineering" that will be held in Telluride, Colorado from Sunday, June 29 to Saturday, July 19, 2002. The application deadline is FRIDAY, MARCH 14, and application instructions are described at the bottom of this document. Like each of these workshops that have taken place since 1994, the 2002 Workshop and Summer School on Neuromorphic Engineering, sponsored by the National Science Foundation, the Whitaker Foundation, the Office of Naval Research, the Defence Advanced Research Projects Agency, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology, was an exciting event and a great success. We strongly encourage interested parties to browse through the previous workshop web pages located at: http://www.ini.unizh.ch/telluride For a discussion of the underlying science and technology and a report on the 2001 workshop, see the September 20, 2001 issue of "The Economist": http://www.economist.com/science/tq/displayStory.cfm?Story_ID=779503 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, vision, speech understanding and robotics. 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 school 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, Kheperas, LEGO robots, and biobugs), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. 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. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control * central pattern generator * robotics * swarm 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. 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. This year we will also have *200* biobugs, kindly donated by the WowWee Toys division of Hasbro in Hong Kong. B.I.O.-Bugs, short for Bio-mechanical Integrated Organisms, are autonomous creatures, each measuring about one foot and weighing about one pound (www.wowwee.com/biobugs/biointerface.html). This will permit us to carry out experiments in collective/swarm robotics. LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350 miles). Great Lakes Aviation and America West Express 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 PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do NOT rent a car. Bring hiking boots, warm clothes, rain gear 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 mid April 2003. 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, Affiliation, valid e-mail address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Description of 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 e-mail: telluride at salk.edu FAX: (858) 587 0417 APPLICATION DEADLINE: MARCH 14, 2003 From nurban at cmu.edu Tue Jan 7 17:35:55 2003 From: nurban at cmu.edu (Nathan Urban) Date: Tue, 7 Jan 2003 17:35:55 -0500 Subject: Postdoctoral position: Physiology and modeling in the olfactory system Message-ID: <006e01c2b69d$241b3a00$712a0280@bio.cmu.edu> Postdoctoral position available immediately for combined physiological and computational studies of the neural circuitry mediating lateral inhibition in the mammalian olfactory system. This position is being offered jointly by Dr. Bard Ermentrout (Department of Mathematics, University of Pittsburgh) and Dr. Nathan Urban (Department of Biological Sciences, Carnegie Mellon University). The project involves the physiological study of the short term dynamics of lateral inhibitory connections between pairs of mitral cells, and the incorporation of these data into computational models of olfactory bulb in order to better understand the transformation of spatiotemporal patterns of glomerular activation by the circuitry of the olfactory bulb. Candidates should have strong interest in both physiological and computational approaches to the study of the olfactory system, but need not have experience in both these areas. Physiological studies will include whole-cell recordings from pairs of connected neurons in olfactory bulb slice preparations and optical recordings using calcium-sensitive dyes. Computational studies may include multicompartmental models of mitral cells and small network models. This position is funded for up to 3 years, and a highly competitive salary is available for qualified candidates. Pittsburgh is a medium-sized city with a relatively low cost of living and many of the amenities and cultural opportunities of a larger city (http://www.city.pittsburgh.pa.us/). The Neuroscience community in Pittsburgh is large and very diverse with more than 100 faculty members affiliated with the Center for Neuroscience at the University of Pittsburgh (CNUP, http://cnup.neurobio.pitt.edu/). Successful candidates would also have the opportunity to join the Center for the Neural Basis of Cognition (CNBC, http://www.cnbc.cmu.edu/) which is a joint University of Pittsburgh/CMU center that involves 70 Faculty from the two Universities. Interested candidates should send (preferably via e-mail) their c.v. and the names and addresses of three references to Professor Bard Ermentrout, Department of Mathematics, University of Pittsburgh Pittsburgh, PA 15260 e-mail: bard+ at pitt.edu. For more information contact: Dr. Bard Ermentrout bard+ at pitt.edu http://www.pitt.edu/~phase/ or Dr. Nathan Urban nurban at cmu.edu http://www.andrew.cmu.edu/user/nurban/Lab_pages/ From Jean-Philippe.Vert at mines.org Wed Jan 8 06:37:42 2003 From: Jean-Philippe.Vert at mines.org (Jean-Philippe Vert) Date: Wed, 08 Jan 2003 12:37:42 +0100 Subject: Wrokshop: kernel methods in computational biolog Message-ID: <3E1C0D86.3070904@mines.org> ******************************************************* ** Workshop: Kernel methods in computational biology ** ** Harnack-Haus, Berlin, April 14, 2003 ** ** http://cg.ensmp.fr/~vert/kmb03 ** ******************************************************* ** Presentation ** Computational biology aims at processing, analyzing and making sense out of huge amount of data produced by high-throughput technologies such as DNA sequencing technologies, DNA and protein microarrays, mass spectrometry or yeast two-hybrid systems. These data are heterogeneous by nature (vectors, strings, graphs...), and often noisy and high-dimensionnal. Kernel methods, such as support vector machines, are promising tools in this context, combining good performances with the ability to manipulate virtually any type of objects thanks to the kernel trick. A number or kernel functions for biological objects have been proposed recently, with encouraging results on several classification issues. The goal of this one-day workshop (which follows the Research in Computational Molecular Biology RECOMB 2003 conference) is to review the state-of-the-art in the application of kernel methods to biology in order to highlight promising research directions, and to foster communication between the computational biology and machine learning communities. No prior knowledge in kernel methods is expected: we explicitly encourage participation of researchers in computational biology interested in new algorithms and tools to process post-genomics data. The workshop will begin with a tutorial on kernel methods. Invited speakers include Nello Cristianini, William S. Noble, Yann Guermeur, Tommi Jaakkola, Imre Kondor, Christina Leslie, Alex Smola, Chris Watkins. ** Organizers ** Bernhard Schoelkopf Koji Tsuda Jean-Philippe Vert ** Call for paper ** We are accepting submissions for oral and/or poster presentation. The presentation should be related to the development of kernel methods for problems in biology or computational biology. Please submit a 2-pages abstract to koji.tsuda at aist.go.jp , in PS or PDF format. Submission deadline is March 14th, 2003. ** For more information, please check the workshop homepage ** http://cg.ensmp.fr/~vert/kmb03/ From fjavier at usp.br Wed Jan 8 20:12:37 2003 From: fjavier at usp.br (Javier Ropero) Date: Wed, 08 Jan 2003 23:12:37 -0200 Subject: [corrected] Neural networks models of brain disease, plasticity and rehabilitation [corrected version] Message-ID: <3.0.5.32.20030108231237.00862c30@pop.usp.br> [ Due to a software glitch, this announcement was truncated twice. I'm hoping the third time is successful. -- Dave Touretzky ] ================================ Dear Colleagues: Connectionist models for understanding brain disease (from trauma and degenerative illnesses to psychiatric disorders) constitute a new paradigm of enormous relevance that is shyly looking for its place in the medical arena. As the organizer of a KES2003 session on neural networks and brain disease, I would like to invite you to discuss with us about this interesting field of research by submitting your contribution. I would be very grateful if you could let know another interested researchers about this session. Looking forward to hearing from you. With my best wishes Javier Ropero 7th International Conference on Knowledge-Based Intelligent Information & Engineering Systems 3, 4 & 5 September 2003, St Anne's College, University of Oxford, U.K. Call for Papers : Neural networks models of brain disease, plasticity and rehabilitation Topic Neural networks models that were originally intended for engineering purposes are recently becoming a useful paradigm for understanding the human brain. The more biological the neural network, the more the number of its possible malfunctions that are similar to those in the real brain. As a consequence neural networks malfunction can be used as a metaphor for brain disease. These diseases range from brain injure like haemorrhage to psychiatric disorders like delusions [1], schizophrenia or bipolar and obsessive-compulsive disorders [2]. Drug addiction, alcohol abuse or even criminal tendencies can, in principle, be modelled by neural networks. Helped by computational neural models it is possible to find new approaches to healing and rehabilitation. Plasticity is a property of the human brain that potentially allows brain damaged persons to return to normality by means of rehabilitation. Rehabilitation methods can be benefited by knowing and applying the laws of brain plasticity previously tested in neural networks. Conversely, brain disease is a prelude of the failures that complex brain-like machines could undergo in the next decades. [1] Ropero Pel?ez, J. (2000) Towards a neural network based therapy for hallucinatory disorders. Neural Networks, 2000 Special Issue, 13(2000), 1047-1061. [2] Neural networks and psychopathology - connectionist models in practice and Research. Edited by Dan J. Stein and Jacques Ludik. Cambridge University Press. Instructions for Authors Only electronic copies of the papers in Microsoft Word, PDF or Postscript forms are acceptable for review purposes and must be sent to the session chair. However, please note that you will be required to send hard copy of the final version of your paper, if it is accepted; electronic submission of final papers is not allowed. Papers must correspond to the requirements detailed in the Instructions to Authors which will be placed on the Conference Web Site, http://www.kesinternational.com/kes2003 or http://www.bton.ac.uk/kes/kes2003 All papers must be presented by one of the authors, who must pay fees. Publication The Conference Proceedings will be published by a major publisher, for example IOS Press of Amsterdam. Extended versions of selected papers will be considered for publication in the International Journal of Knowledge-Based Intelligent Engineering Systems, www.bton.ac.uk/kes/journal/ Important Dates Deadline for submission intention : February 15, 2002 Deadline for receipt of papers by Session Chair : March 15, 2003 Notification of acceptance : April 1, 2003 Camera-ready papers to session chair by : April 15, 2003 (Session Chair must send final camera-ready papers to reach to KES Secretariat by 1 May 2003 or they will not appear in the proceedings). Contact Details Javier Ropero Pel?ez Phone: 55-11-36620847 Email: fjavier at usp.br From fjavier at usp.br Wed Jan 8 20:12:37 2003 From: fjavier at usp.br (Javier Ropero) Date: Wed, 08 Jan 2003 23:12:37 -0200 Subject: Neural networks models of brain disease, plasticity and rehabilitation [corrected version] Message-ID: <3.0.5.32.20030108231237.00862c30@pop.usp.br> Dear Colleagues: Connectionist models for understanding brain disease (from trauma and degenerative illnesses to psychiatric disorders) constitute a new paradigm of enormous relevance that is shyly looking for its place in the medical arena. As the organizer of a KES2003 session on neural networks and brain disease, I would like to invite you to discuss with us about this interesting field of research by submitting your contribution. I would be very grateful if you could let know another interested researchers about this session. Looking forward to hearing from you. With my best wishes Javier Ropero 7th International Conference on Knowledge-Based Intelligent Information & Engineering Systems 3, 4 & 5 September 2003, St Anne's College, University of Oxford, U.K. Call for Papers : Neural networks models of brain disease, plasticity and rehabilitation Topic Neural networks models that were originally intended for engineering purposes are recently becoming a useful paradigm for understanding the human brain. The more biological the neural network, the more the number of its possible malfunctions that are similar to those in the real brain. As a consequence neural networks malfunction can be used as a metaphor for brain disease. These diseases range from brain injure like haemorrhage to psychiatric disorders like delusions [1], schizophrenia or bipolar and obsessive-compulsive disorders [2]. Drug addiction, alcohol abuse or even criminal tendencies can, in principle, be modelled by neural networks. Helped by computational neural models it is possible to find new approaches to healing and rehabilitation. Plasticity is a property of the human brain that potentially allows brain damaged persons to return to normality by means of rehabilitation. Rehabilitation methods can be benefited by knowing and applying the laws of brain plasticity previously tested in neural networks. Conversely, brain disease is a prelude of the failures that complex brain-like machines could undergo in the next decades. [1] Ropero Pel?ez, J. (2000) Towards a neural network based therapy for hallucinatory disorders. Neural Networks, 2000 Special Issue, 13(2000), 1047-1061. [2] Neural networks and psychopathology - connectionist models in practice and Research. Edited by Dan J. Stein and Jacques Ludik. Cambridge University Press From zaki23 at pi.titech.ac.jp Fri Jan 10 02:20:22 2003 From: zaki23 at pi.titech.ac.jp (K.yamazaki) Date: Fri, 10 Jan 2003 16:20:22 +0900 Subject: paper announcement Message-ID: Dear connectionists, I am very glad to introduce that the following paper will appear in Neural Networks, K.Yamazakai, S.Watanabe, Singularities in mixture models and upper bounds of stochastic complexity http://watanabe-www.pi.titech.ac.jp/~zaki23/ which might be of interest to the readers of connectionists. The electric paper "nnk02011-RR.pdf(or ps)" is available on the above URL. Best regards, Keisuke Yamazaki ------------------------------------------- Keisuke Yamazaki Tokyo Institute of Technology http://watanabe-www.pi.titech.ac.jp/~zaki23 zaki23 at pi.titech.ac.jp From fjavier at usp.br Wed Jan 8 20:12:37 2003 From: fjavier at usp.br (Javier Ropero) Date: Wed, 08 Jan 2003 23:12:37 -0200 Subject: Neural networks models of brain disease, plasticity and rehabilitation Message-ID: <3.0.5.32.20030108231237.00862c30@pop.usp.br> Dear Colleagues: Connectionist models for understanding brain disease (from trauma and degenerative illnesses to psychiatric disorders) constitute a new paradigm of enormous relevance that is shyly looking for its place in the medical arena. As the organizer of a KES2003 session on neural networks and brain disease, I would like to invite you to discuss with us about this interesting field of research by submitting your contribution. I would be very grateful if you could let know another interested researchers about this session. Looking forward to hearing from you. With my best wishes Javier Ropero 7th International Conference on Knowledge-Based Intelligent Information & Engineering Systems 3, 4 & 5 September 2003, St Anne's College, University of Oxford, U.K. Call for Papers : Neural networks models of brain disease, plasticity and rehabilitation Topic Neural networks models that were originally intended for engineering purposes are recently becoming a useful paradigm for understanding the human brain. The more biological the neural network, the more the number of its possible malfunctions that are similar to those in the real brain. As a consequence neural networks malfunction can be used as a metaphor for brain disease. These diseases range from brain injure like haemorrhage to psychiatric disorders like delusions [1], schizophrenia or bipolar and obsessive-compulsive disorders [2]. Drug addiction, alcohol abuse or even criminal tendencies can, in principle, be modelled by neural networks. Helped by computational neural models it is possible to find new approaches to healing and rehabilitation. Plasticity is a property of the human brain that potentially allows brain damaged persons to return to normality by means of rehabilitation. Rehabilitation methods can be benefited by knowing and applying the laws of brain plasticity previously tested in neural networks. Conversely, brain disease is a prelude of the failures that complex brain-like machines could undergo in the next decades. [1] Ropero Pel?ez, J. (2000) Towards a neural network based therapy for hallucinatory disorders. Neural Networks, 2000 Special Issue, 13(2000), 1047-1061. [2] Neural networks and psychopathology - connectionist models in practice and Research. Edited by Dan J. Stein and Jacques Ludik. Cambridge University Press From smola at axiom.anu.edu.au Fri Jan 10 09:19:58 2003 From: smola at axiom.anu.edu.au (Alex Smola) Date: Sat, 11 Jan 2003 01:19:58 +1100 (EST) Subject: Machine Learning Summer School, February 2-14, 2003, ANU in Canberra Message-ID: We would like to inform you that The Australian National University will be hosting a Machine Learning Summer School. The Summer School is intended for students and researchers alike, who are interested in Machine Learning. Its goal is to present some of the topics which are at the core of modern Learning Theory. The school will be held in the Australian National University, Canberra, Australia between the 2nd and the 14th of February, 2003. During this time, we shall present three courses of 6 hours, each one covering one of the topics listed below. In addition, there will be special lectures which may focus on additional topics and which will provide background knowledge in machine learning and statistics. Our aim is to cover much of the spectrum of Machine Learning, from theory to practice. Courses: Information Geometry (Shun-Ichi Amari, RIKEN) Concentration Inequalities (Gabor Lugosi, Pompeu Fabra University) Unsupervised Learning (Zoubin Ghahramani, University College London) Short Courses: Eleazar Eskin, Hebrew University Peter Hall, Australian National Univesity Markus Hegland, Australian National University John Lloyd, RSISE, Australian National University Shahar Mendelson, RSISE, Australian National University Mike Osborne, MSI, Australian National University Gunnar Rtsch, RSISE, Australian National University Alex Smola, RSISE, Australian National University S.V.N. Vishwanathan, NICTA Bob Williamson, RSISE, Australian National University Upon request, attendants of the summer school are eligible to receive a Graduate Course Award of the ANU. For further details on obtaining the course award, please contact Michelle.Moravec at anu.edu.au before the commencement of the summer school. The registration cost of the school is $1600 per person for participants from industry and $600 per person for academics. Students are eligible for a further discount and may register for $200 per person. All prices are in Australian dollars and include GST. For further information (including registration form), visit our website at or send email to Michelle.Moravec at anu.edu.au. Regards, Alex Smola and Gunnar Raetsch ''~`` ( o o ) +------------------------------.oooO--(_)--Oooo.----------------------------+ | Alexander J. Smola http://mlg.anu.edu.au/~smola | | Australian National University Alex.Smola at anu.edu.au | | Research School for Information Tel: (+61) 2 6125-8652 | | Sciences and Engineering .oooO Fax: (+61) 2 6125-8651 | | Canberra, ACT 0200 (#00120C) ( ) Oooo. Cel: (+61) 410 457 686 | +---------------------------------\ (----( )------------------------------+ \_) ) / (_/ From wsenn at cns.unibe.ch Fri Jan 10 09:57:45 2003 From: wsenn at cns.unibe.ch (Walter Senn) Date: Fri, 10 Jan 2003 15:57:45 +0100 Subject: Hebb in perspective (Biol Cyb, issue 5-6, 2002) Message-ID: <3E1EDF69.5EED94E9@cns.unibe.ch> Dear colleagues We would like to draw your attention to the special issue "Hebb in perspective" of Biological Cybernetics, a collection of survey and research articles on Hebbian learning. It brings together experimental and theoretical aspects of synaptic plasticity in neocortex and hippocampus, with particular emphasis on spike-timing dependent plasticity. Leo van Hemmen and Walter Senn Biological Cybernetics Volume 87, Issue 5-6 (2002) http://link.springer.de/link/service/journals/00422/tocs/t2087005.htm or http://link.springer-ny.com/link/service/journals/00422/tocs/t2087005.htm (Abstracts freely downloadable) J. Leo van Hemmen, Walter Senn: Editorial: Hebb in perspective http://www.cns.unibe.ch/~wsenn/#pub, see also http://www.cns.unibe.ch/~wsenn/biol_cyb_index.html Guo-Qiang Bi: Spatiotemporal specificity of synaptic plasticity: cellular rules and mechanisms. http://www.neurobio.pitt.edu/faculty_lab/bi_pub.htm Michael P. Kilgard, Pritesh K. Pandya, Navzer D. Engineer, Raluca Moucha: Cortical network reorganization guided by sensory input features http://www.utdallas.edu/~kilgard/cv.html#PUBLICATIONS Walter Senn: Beyond spike timing: the role of nonlinear plasticity and unreliable synapses http://www.cns.unibe.ch/~wsenn/#pub Colin Lever, Neil Burgess, Francesca Cacucci, Tom Hartley, John O'Keefe: What can the hippocampal representation of environmental geometry tell us about Hebbian learning? http://www.icn.ucl.ac.uk/groups/JO/mempages/neil/papers/ Uma R. Karmarkar, Mark T. Najarian, Dean V. Buonomano: Mechanisms and significance of spike-timing dependent plasticity http://www.neurobio.ucla.edu/~dbuono/publications.html Harel Z. Shouval, Gastone C. Castellani, Brian S. Blais, Luk C. Yeung, Leon N Cooper: Converging evidence for a simplified biophysical model of synaptic plasticity http://www.physics.brown.edu/users/faculty/shouval/research.html Patrick D. Roberts, Curtis C. Bell: Spike timing dependent synaptic plasticity in biological systems http://www.proberts.net/research/ Wulfram Gerstner, Werner M. Kistler: Mathematical formulations of Hebbian learning http://diwww.epfl.ch/~gerstner/wg_pub.html Werner M. Kistler: Spike-timing dependent synaptic plasticity: a phenomenological framework http://www-fgg.eur.nl/anat/kistler/ C. Leibold, J.L. van Hemmen: Mapping time http://www1.physik.tu-muenchen.de/lehrstuehle/T35/t35/german/hebblearning.html Roland E. Suri, Terrence J. Sejnowski: Spike propagation synchronized by temporally asymmetric Hebbian learning http://www.cnl.salk.edu/~suri/ Adam Kepecs, Mark C.W. van Rossum, Sen Song, Jesper Tegner: Spike-timing-dependent plasticity: common themes and divergent vistas http://homepages.inf.ed.ac.uk/mvanross/ Stefano Fusi: Hebbian spike-driven synaptic plasticity for learning patterns of mean firing rates http://www.cns.unibe.ch/~fusi/#pub Jesper Tegner, Albert Compte, Xiao-Jing Wang: The dynamical stability of reverberatory neural circuits http://www.wanglab.brandeis.edu/webpages/publications.html From pizzi at ee.umanitoba.ca Fri Jan 10 11:57:04 2003 From: pizzi at ee.umanitoba.ca (Pizzi, Nick) Date: Fri, 10 Jan 2003 10:57:04 -0600 Subject: POSTDOCTORAL RESEARCH OPPORTUNITY - BIOMEDICAL DATA ANALYSIS Message-ID: <9D8DFE8AD5FCD21189990004ACE5276603E3DC72@nrcwpgex1.ibd.nrc.ca> POSTDOCTORAL RESEARCH OPPORTUNITY - BIOMEDICAL DATA ANALYSIS GRANULAR COMPUTING AND SPARSE CODING FOR THE MODELING, ANALYSIS, AND CLASSIFICATION OF HIGH-DIMENSIONAL BIOMEDICAL DATA Pending final approval, a postdoctoral position is available at the University of Manitoba to investigate sparse coding strategies for the modeling, analysis, and classification of high-dimensional biomedical data. This is an NSERC-funded strategic research project directed by Prof. W. Pedrycz (U. Alberta), Dr. N. Pizzi (National Research Council & U. Manitoba), and Dr. M. Alexander (National Research Council). The position, which will focus on sparse coding analysis, is for a one-year term with a possible one year renewal. Biomedical data classification demands a reduction of the original data's dimensionality without sacrificing domain-specific significance. Sparse representation (SR) addresses the former issue and granular computing the latter. The fundamental tasks of feature extraction, classification, and noise/artefact suppression all benefit by being carried out in a sparse domain. Since wavelets have become a powerful computational tool in signal processing, there has been a growing interest in the SR of data. The transformations that accomplish optimal sparseness will depend on the data itself, and may, for example, be defined by optimizing its entropy over a finitely- (or infinitely) over-complete "dictionary" of basis functions. The computational task of finding the optimal SR for given data is accomplished in two stages: (i) Defining an over-complete dictionary by constructing a sufficiently broad class of basis functions; (ii) Projecting the data onto a particular subset of the over-complete dictionary that optimizes a pre-defined measure of sparseness. Computationally efficient algorithms need to be considered for (i), and the optimization procedure for (ii) may in some cases involve substantial computation. Both (i) and (ii) are topics of ongoing research. Required background: - Recent Ph.D. graduate - Training and/or research experience in signal processing - Background and/or experience in wavelets and their application to data analysis - Training and/or research experience in statistics, including practical knowledge of analysis of large datasets - Proficiency in C/C++ and experience with using MatLab/IDL Please send a curriculum vitae, expression of interest (including earliest start date), and the names and e-mail addresses of two references to Dr. Pizzi at pizzi at nrc.ca. Your curriculum vitae should include a list of recent publications. Please outline your interest in this project, how it is related to work that you have done, and what special expertise you would bring to the project. ------------------------------------------------------------------- Nicolino Pizzi, PhD pizzi at nrc.ca Senior Research Officer Institute for Biodiagnostics National Research Council Canada 435 Ellice Avenue Ph: +1 204 983 8842 Winnipeg MB, R3B 1Y6, Canada Fx: +1 204 984 5472 Adjunct Professor Computer Science Department & Electrical and Computer Engineering Department University of Manitoba http://www.ee.umanitoba.ca/~pizzi ------------------------------------------------------------------- From barth at inb.uni-luebeck.de Fri Jan 10 16:59:24 2003 From: barth at inb.uni-luebeck.de (Erhardt Barth) Date: Fri, 10 Jan 2003 22:59:24 +0100 Subject: PhD positions in visual information processing Message-ID: <14713405355.20030110225924@inb.uni-luebeck.de> The Institute for Neuro- and Bioinformatics, University of Luebeck, Germany, seeks Research Scientists (PhD students) for an interdisciplinary project funded by the German Federal Ministry of Education and Research. The successful candidate will join an interdisciplinary research team and closely collaborate with two German companies. The goal of the project is to develop new forms of visual communication and interaction based on eye-tracking and gaze-contingent display. This involves high-speed image processing, tracking, and graphics, as well as modeling of visual function. Further information can be found at www.inb.uni-luebeck.de/Itap . We expect a strong background in Computer Science, Electrical Engineering, or Physics and enthusiasm for interdisciplinary research. Programming skills (mainly C++) would be a plus. We offer exciting new research topics and the possibility to obtain a PhD in computer science. The positions are initially funded for 36 month. The salary will be at the level of BAT IIa (appr. 38.000 EURO/year before tax). Please send applications including your curriculum vitae, a statement of interests, and names of references to Dr. Erhardt Barth (barth at inb.uni-luebeck.de) with a CC to Prof. Thomas Martinetz (martinetz at informatik.uni-luebeck.de ). Application deadline is February 15th. For further information contact E. Barth. From David.Cohn at acm.org Mon Jan 13 13:06:53 2003 From: David.Cohn at acm.org (David 'Pablo' Cohn) Date: 13 Jan 2003 10:06:53 -0800 Subject: jmlr-announce: ICML Special Issue Message-ID: <1042481214.32665.2332.camel@bitbox.corp.google.com> The Journal of Machine Learning Research is very pleased to announce publication of a Special Issue of invited papers from the Eighteenth International Conference on Machine Learning (ICML2001). This issue, edited by Carla Brodley and Andrea Danyluk, contains twelve papers expanded from their ICML form into fully refereed JMLR contributions. We believe they capture both the breadth and spirit of the machine learning conference and community. The new issue is available online at http://www.jmlr.org. David Cohn Managing Editor, JMLR --------------------------------------- Special Issue on the Eighteenth International Conference on Machine Learning (ICML2001) Carla E. Brodley, Andrea P. Danyluk; 3(Dec):619, 2002. Efficient Algorithms for Decision Tree Cross-validation Hendrik Blockeel, Jan Struyf; 3(Dec):621-650, 2002. Multiple-Instance Learning of Real-Valued Data Daniel R. Dooly, Qi Zhang, Sally A. Goldman, Robert A. Amar; 3(Dec):651-678, 2002. Learning Probabilistic Models of Link Structure Lisa Getoor, Nir Friedman, Daphne Koller, Ben Taskar; 3(Dec):679-707, 2002. The Representational Power of Discrete Bayesian Networks Charles X. Ling, Huajie Zhang; 3(Dec):709-721, 2002. The Set Covering Machine Mario Marchand, John Shawe-Taylor; 3(Dec):723-746, 2002. Coupled Clustering: A Method for Detecting Structural Correspondence Zvika Marx, Ido Dagan, Joachim M. Buhmann, Eli Shamir; 3(Dec):747-780, 2002. Some Greedy Learning Algorithms for Sparse Regression and Classification with Mercer Kernels Prasanth B. Nair, Arindam Choudhury, Andy J. Keane; 3(Dec):781-801, 2002. Lyapunov Design for Safe Reinforcement Learning Theodore J. Perkins, Andrew G. Barto; 3(Dec):803-832, 2002. Finding the Most Interesting Patterns in a Database Quickly by Using Sequential Sampling Tobias Scheffer, Stefan Wrobel; 3(Dec):833-862, 2002. Stopping Criterion for Boosting-Based Data Reduction Techniques: from Binary to Multiclass Problem Marc Sebban, Richard Nock, St?phane Lallich; 3(Dec):863-885, 2002. Learning to Construct Fast Signal Processing Implementations Bryan Singer, Manuela Veloso; 3(Dec):887-919, 2002. Policy Search using Paired Comparisons Malcolm J. A. Strens, Andrew W. Moore; 3(Dec):921-950, 2002. From malchiodi at dsi.unimi.it Mon Jan 13 13:13:02 2003 From: malchiodi at dsi.unimi.it (Dario Malchiodi) Date: Mon, 13 Jan 2003 19:13:02 +0100 Subject: WIRN 2003 - Call for papers Message-ID: ####################################################### WIRN 2003 C A L L F O R P A P E R S FIRST ANNOUNCEMENT %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% The 14-th Italian Workshop on Neural Networks and "Premio Caianiello" competition June 5 to 7, 2003,Vietri Sul Mare, Salerno ITALY ************************************************************************ ****** Homepage: http://siren.dsi.unimi.it/indice2.html ************************************************************************ * Sponsors International Institute for Advanced Scientific Studies (IIASS) "E.R. Caianiello" Dip. di Fisica "E.R. Caianiello", University of Salerno Dip. di Matematica ed Informatica, University of Salerno Dip. di Scienze dell'Informazione, University of Milano Societa' Italiana Reti Neuroniche (SIREN) IEEE Neural Network Council INNS/SIG Italy Istituto Italiano per gli Studi Filosofici, Napoli Provincia di Salerno Topics Mathematical Models, Architectures and Algorithms, Hardware and Software Design, Hybrid Systems, Pattern Recognition and Signal Processing, Industrial and Commercial Applications, Fuzzy Tecniques for Neural Networks Schedule Papers Due: February 28, 2003 Replies to Authors: April 30, 2003 Revised Papers Due: June 15, 2003 The three-day conference, to be held in the I.I.A.S.S., will feature both introductory tutorials and original, refereed papers, to be published by an International Publishing Company . Official languages are Italian and English, while papers must be in English. More detailed instructions and the On-Line Submission Form can be found from the WIRN 2003 homepage http://siren.dsi.unimi.it/indice2.html. During the Workshop the "Premio E.R. Caianiello" will be assigned to the best Ph.D. thesis in the area of Neural Nets and related fields of Italian researchers. The amount is of 1.000 Euros. The interested researchers (with the Ph.D degree obtained after January 1, 2000 and before March 31 2003) must send 3 copies of a c.v. and of the thesis to "Premio Caianiello" WIRN 2003 c/o IIASS before April 30,2003. A candidate can submit his Ph. D. thesis at most twice. Only SIREN associated are admitted (subscription forms can be downloaded from the SIREN site). For more information, contact the Secretary of I.I.A.S.S. "E.R. Caianiello", Via G.Pellegrino, 19, 84019 Vietri Sul Mare (SA), ITALY Tel. +39 89 761167 Fax +39 89 761189 E-Mail robtag at unisa.it Organizing - Scientific Committee B. Apolloni (Univ. Milano), A. Bertoni (Univ. Milano), N. A. Borghese (Univ. Milano), D. D. Caviglia (Univ. Genova), P. Campadelli (Univ. Milano), A. Chella (Univ. Palermo), A. Colla (ELSAG Genova), A. Esposito (I.I.A.S.S.), M. Frixione (Univ. Salerno), C. Furlanello (ITC-IRST Trento), G. M. Guazzo (I.I.A.S.S.), M. Gori (Univ. Siena), M. Marinaro (Univ. Salerno), F. Masulli (Univ. Pisa), C. Morabito (Univ. Reggio Calabria), P. Morasso (Univ. Genova), G. Orlandi (Univ. Roma), T. Parisini (Univ. Trieste), E. Pasero (Politecnico Torino), A. Petrosino (CNR Napoli), V. Piuri (Politecnico Milano), R. Serra (CRA Montecatini Ravenna), F. Sorbello (Univ. Palermo), A. Sperduti (Univ. Pisa), R. Tagliaferri (Univ. Salerno) -- From d.polani at herts.ac.uk Tue Jan 14 14:54:45 2003 From: d.polani at herts.ac.uk (Daniel Polani) Date: Tue, 14 Jan 2003 20:54:45 +0100 Subject: 2nd Call for Papers: Evolvability and Sensor Evolution Symposium Message-ID: <15908.27397.830992.168606@perm.feis.herts.ac.uk> //////////////////////////////////////////////////////////////////////// Call for Papers & Participation: EPSRC Network on Evolvability in Biological & Software Systems Evolvability and Sensor Evolution Symposium //////////////////////////////////////////////////////////////////////// sponsored by The Natural Computation Research Group (Univ. of Birmingham) The University of Hertfordshire Adaptive Systems Research Group EPSRC Network on Evolvability in Biological and Software Systems 24-25 April 2003 (Thursday-Friday), University of Birmingham, U.K. Invited Speakers: Peter Cariani (Harvard University, USA) Dan-Eric Nilsson (Lund University, Sweden) Mark Nelson (Beckmann Institute, University of Illinois, USA) John Messenger (University of Cambridge, UK) Gareth Jones (University of Bristol, UK) Program Chairs: Julian Miller (University of Birmingham) Daniel Polani (University of Hertfordshire) Co-Organizers: Chrystopher Nehaniv (University of Hertfordshire) Participation: Participation is open to all students, researchers, or industry representatives with interests in evolvability in biological and software systems. Please register by sending an e-mail j.miller at cs.bham.ac.uk giving your name and affiliation. There is no registration fee. For the full call, see web site: http://www.cs.bham.ac.uk/~jfm/evol-sensor.htm From bp1 at cn.stir.ac.uk Wed Jan 15 06:09:59 2003 From: bp1 at cn.stir.ac.uk (Bernd Porr) Date: Wed, 15 Jan 2003 11:09:59 +0000 Subject: Possibility for a PhD Message-ID: <3E254187.80606@cn.stir.ac.uk> Possibility for a PhD (sorry for multiple postings) DEADLINE FOR PRE-APPLICATIONS: Jan.31st. The Computational Neuroscience Group at the University of Stirling is offering a PhD in the field of autonomous robotics. Robotics is seen as a means for understanding the development of intelligence by getting insights about the living from constructing animats. Recent research at our group has focused on the (inner) perspective of the organism or the animat (see "Constructivism"). Thereby feedback from the environment to the animat becomes essential as only the feedback provides information if actions have been successful or not. However, simple reactive feedback control has the disadvantage that it reacts always too late. If you have to rely only on reflexes than you will have to burn your hand before you can pull it away. Predictions of stimuli (here: pain) are essential to improve behaviour. Learning to predict re-actions means that the organism is able to act pro-actively. The above ideas have been implemented in a closed-loop learning-scheme which we call ISO-learning: Isotropic Sequence Order Learning: http://www.cn.stir.ac.uk/predictor/ This type of learning has been so far only been applied to simple tasks (avoiding obstacles, targeting 'food') in order to provide a proof of concept. The PhD-thesis shall explore more complex situations with sequences of reflexes, hierachical structures and/or 'efference-copies'. Other possible areas of research relate to certain forms of preprocessing of the sensor-inputs ("place cells") or to post-processing of the motor-output. The mathematical framework of ISO-learning is control-theory and signal theory. We work with real and simulated robots which we program in C++ and which we modify by adapting the electronics. Knowledge of any of these areas would certainly be helpful for the successful candidate. As ISO-learning has a strong link to control-theory cooperations with the industry are possible. This announcement is meant to attract possible candidates, so at this stage a formal application is not required. If you are interested we would ask you to send your informal but complete application (CV, background, list of publications, statement of specific interest, etc., etc.) to us. We would then contact you about how to proceed further. Please feel free to contact us in case of any questions. Bernd Porr and Florentin Wrgtter Contact: Prof Florentin Wrgtter: worgott at cn.stir.ac.uk Bernd Porr: bp1 at cn.stir.ac.uk Computational Neuroscience Dept of Psychology Stirling FK9 4LA Scotland, UK Fax: +44 (0) 1786 46-7641 Tel: +44 (0) 1786 46-6369/6378 -- http://www.cn.stir.ac.uk From terry at salk.edu Wed Jan 15 17:07:26 2003 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 15 Jan 2003 14:07:26 -0800 (PST) Subject: NEURAL COMPUTATION 15:2 Message-ID: <200301152207.h0FM7QD79176@purkinje.salk.edu> Neural Computation - Contents - Volume 15, Number 2 - February 1, 2003 LETTERS Interspike Interval Correlations, Memory, Adaptation, and Refractoriness in a Leaky Integrate-and-Fire Model with Threshold Fatigue Maurice J. Chacron, Khashayar Pakdaman and Andre Longtin Reliability of Spike Timing Is a General Property of Spiking Model Neurons Romain Brette and Emmanuel Guigon The Dynamic Neural Filter: A Binary Model of Spatiotemporal Coding Brigitte Quenet and David Horn Modeling Short-Term Synaptic Depression in Silicon Malte Boegerhausen, Pascal Suter, and Shih-Chii Liu Dictionary Learning Algorithms for Sparse Representation Kenneth Kreutz-Delgado, Joseph F. Murray, Bhaskar D. Rao, Kjersti Engan, Te-Won Lee and Terrence J. Sejnowski Spatiochromatic Receptive Field Properties Derived From Information-Theoretic Analyses of Cone Mosaic Responses to Natural Scenes Eizaburo Doi, Toshio Inui, Te-Won Lee, Thomas Wachtler and Terrence J. Sejnowski Linear Geometric ICA: Fundamentals and Algorithms Fabian J. Theis, Andreas Jung, Carlos G. Puntonet and Elmar W. Lang Equivalence of Backpropagation and Contrastive Hebbian Learning in a Layered Network Xiaohui Xie and H. Sebastatian Seung Indexed Families of Functionals and Gaussian Radial Basis Functions Irwin W. Sandberg Efficient Greedy Learning of Gaussian Mixture Models J. J. Verbeek, N. Vlassis and B. Krose SMO Algorithm for Least-Squares SVM Formulations S. S. Keerthi and S. K. Shevade ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2003 - VOLUME 15 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $95 $101.65 $143 Institution $590 $631.30 $638 * 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 h.jaeger at iu-bremen.de Thu Jan 16 12:27:30 2003 From: h.jaeger at iu-bremen.de (Herbert Jaeger) Date: Thu, 16 Jan 2003 18:27:30 +0100 Subject: Job offer: stochastic system modeling Message-ID: <3E26EB82.6060001@iu-bremen.de> The School of Engineering and Science of International University Bremen (www.iu-bremen.de) invites applications for a Ph.D. or Post-Doc Position in Computational Science The candidate should have a strong background in modeling stochastic systems with machine learning techniques. Specifically, his/her research will be concerned with observable operator models (OOMs, see http://www.ais.fraunhofer.de/INDY/oom_research.html). OOMs are superficially similar to hidden Markov models, but arise from operator/state methods related to the quantum mechanics formalism. OOMs and related models are currently being investigated in areas as diverse as theoretical physics (J.P. Crutchfield, H. Honerkamp) and learning methods for robots (R. Sutton). The rigorous mathematical theory underlying OOMs gives rise to new, highly efficient learning algorithms which would be the object of both theoretical and applied research in the offered position. The School of Engineering and Science at IUB offers a research-oriented working environment with an informal and dynamic atmosphere and a high degree of interactions between students, faculty and staff. IUB offers highly competitive salaries based on qualifications and experience. The contract would initially run over 2 years. Interested candidates with a degree in mathematics, computer science, physics, or signal processing and control engineering please direct inquiries and applications to Prof. Herbert Jaeger International University Bremen P.O. Box 750 561 28725 Bremen Germany Electronic submissions may be sent to h.jaeger at iu-bremen.de -- ------------------------------------------------------------------ Dr. Herbert Jaeger International University Bremen Campus Ring 12 28759 Bremen, Germany Phone (+49) 421 200 3215 email h.jaeger at iu-bremen.de http://www.iu-bremen.de/directory/faculty/29979/ http://www.ais.fraunhofer.de/INDY/herbert/ ------------------------------------------------------------------ From hasselmo at bu.edu Thu Jan 16 18:03:35 2003 From: hasselmo at bu.edu (Michael Hasselmo) Date: Thu, 16 Jan 2003 18:03:35 -0500 Subject: [corrected] IJCNN 2003 final call for papers In-Reply-To: Message-ID: FINAL CALL FOR PAPERS (Deadline Approaching) **************************************************************** International Joint Conference on Neural Networks (IJCNN 2003) Portland, Oregon, July 20-24, 2003 http://www.ijcnn.net DEADLINE: January 29, 2003 **************************************************************** Co-sponsored by the International Neural Network Society (INNS) & IEEE Neural Networks Society. The International Joint Conference on Neural Networks provides an overview of state of the art research in Neural Networks, covering a wide range of topics (see topic list below). Paper submission deadline is January 29, 2003. Selected papers will be published in a special issue of the journal Neural Networks, in addition to publication of all papers in the conference proceedings. The IJCNN meeting is organized annually by the International Neural Network Society (INNS) and the IEEE Neural Networks Society. Conference attendees who are INNS or IEEE Neural Networks Society members, or who join one of these societies now will receive a reduced IJCNN conference registration fee, and those who are INNS members will receive the IJCNN special issue for free as part of their annual membership subscription to Neural Networks. Article submission: ------------------------------------ Authors should submit their articles electronically on the conference web site at http://www.ijcnn.net by the conference deadline of January 29, 2003. THE DEADLINE IS APPROACHING. Plenary speakers:=20 ------------------------------------ Kunihiko Fukushima, Tokyo University of Technology, Japan =20 Earl Miller, Massachusetts Institute of Technology, USA Terrence Sejnowski, Salk Institute and UCSD, USA Vladimir Vapnik, NEC Research Labs, USA Christoph von der Malsburg, USC, USA and Univ. Bochum, Germany Special sessions: ------------------------------------ Full schedules for the following sessions are posted on www.ijcnn.net. Csaba Rekeczky and Tamas Roska - Cellular visual microprocessors: Topographic array computing on data flows. Steve Grossberg - Visual cortex: How illusions represent reality Robi Polikar - Incremental Learning Antony Satyadas - Computational Intelligence for Homeland Security. Robert Kozma, Ali Minai and DeLiang Wang - Dynamical Aspects of Information Encoding in Neural Networks. Andreas A. Ioannides and John G. Taylor - Attention and Consciousness in Normal Brains: Theoretical models and phenomenological data from Magnetoencephalography (MEG). Mitra Basu - Biologically inspired/motivated computational models Jim DeLeo and Roberto Tagliaferri - Patient Care and Clinical Decision Support. F. Carlo Morabito and Sameer Antani - Knowledge Discovery, and Image and Signal Processing in Medicine. Harold Szu, Joel Davis, Harold Hawkins =AD Biomimetic Applications Francesco Masulli and Larry Reeker - Bioinformatics. Eduardo Bayro-Corrochano - Geometric Neurocomputing. Robert J. Marks and John Vian - Applications in Aerospace. Tutorials ------------------------------------ Tutorials will take place on Sunday, July 20, 2003. There will be six sequential two hour sessions. A single tutorial fee will pay for attendance of six different tutorials from the list below (the tutorial schedule will be posted on the registration page). Bernard Widrow - Neural control systems Pierre Baldi - Prediction of Protein Structures on a Proteomics Scale Using Machine Learning Approaches Jose C. Principe and Deniz Erdogmus, - Information Theoretic Learning Vladimir Cherkassky - Signal and image denoising using VC learning theory John G. Taylor - Attention and Consciousness as Control System Components in the Brain Martin McKeown - A survey of blind source separation techniques applied to clinical data=20 V. Beiu, J.M. Quintana, M.J. Avedillo - Threshold Logic From TTL To Quantum Computing Eytan Ruppin - Evolutionary Autonomous Agents: A Novel Neuroscience Research Paradigm Antonio Eleuteri, Francesco Masulli, Roberto Tagliaferro - Learning with multiple machines: ECOC models vs Bayesian Framework. Johan Suykens - Least Squares Support Vector Machines Asim Roy - Autonomous Learning: the New Connectionist Algorithms Robert Kozma and Walter J Freeman - Neuropercolation: Dynamical Memory Neural Networks =AD Biological Systems and Computer Implementations Nik Kasabov - Data Mining and Knowledge Discovery Using Adaptive Neural Networks Aurelio Uncini - Processing of audio signal by neural networks Lei Xu - Dependence Structure Mining, Statistical Approaches, and Bayesian Ying-Yang Learning Amie J. O=B9Brien - Fuzzy Logic and Expert Systems: An Introduction with BioMedical Applications Stephen Thaler - AI's Best Bet: The Creativity Machine Paradigm Wang Shoujue - Biomimetic Classifications Broad topics ------------------------------------ Regular oral and poster sessions will include papers in subtopics within the following broad topics. When submitting your paper you must choose two subtopics within these broad topics (see www.ijcnn.net). A. PERCEPTUAL AND MOTOR FUNCTION B. COGNITIVE FUNCTION C. COMPUTATIONAL NEUROSCIENCE D. INFORMATICS E. HARDWARE=20 F. REINFORCEMENT LEARNING AND CONTROL G. DYNAMICS=20 H. THEORY=20 I. APPLICATIONS Organizing committee: ------------------------------------ General Chair: Don Wunsch, University of Missouri - Rolla Program Chair: Michael Hasselmo, Boston University Program co-chairs:=20 DeLiang Wang, Ohio State University Ganesh K. Venayagamoorthy,University of Missouri - Rolla Tutorial co-chairs: F. Carlo Morabito, University of Reggio Calabria, Italy Harold Szu, Office of Naval Research Local Arrangements Chair: George Lendaris, Portland State University Publicity chair: Derong Liu, University of Illinois at Chicago Web chair: Tomasz Cholewo, Lexmark International Inc., Kentucky Exhibits chair: Karl Mathia, Brooks-PRI Automation Inc., California Student travel and volunteer chair: Slawo Wesolkowski, University of Waterloo, Canada International Liason: William N. Howell, Mining and Mineral Sciences Laboratories, Canada Program committee: ------------------------------------------ David Brown, FDA Gail Carpenter, Boston University David Casasent, Carnegie Mellon University Ke Chen , University of Birmingham, UK Michael Denham, University of Plymouth, UK Thomas G. Dietterich, Oregon State University Lee Feldkamp, Ford Motor Company Kunihiko Fukushima, Tokyo University of Technology, Japan Joydeep Ghosh, University of Texas at Austin Steven Grossberg, Boston University Fred Ham, Florida Institute of Technology Ron Harley, Georgia Institute of Technology Bart Kosko, University of Southern California Robert Kozma, University of Memphis Dan Levine, University of Texas at Dallas Xiuwen Liu, Florida State University F. Carlo Morabito, Universita di Reggio Calabria, Italy Ali Minai, University of Cincinnati Catherine Myers, Rutgers University Erikki Oja, Helsinki University of Technology, Finland Jose Principe, University of Florida Danil Prokhorov, Ford Motor Company Harold Szu, Office of Naval Research John Gerald Taylor, University College, London, UK Shiro Usui, Toyohashi Univ. of Technology, Japan Bernie Widrow, Stanford University Lei Xu, The Chinese University of Hong Kong Gary Yen, Oklahoma State University Lotfi Zadeh, University of California, Berkeley Registration: ------------------------------------------ Registration will be possible on the web site at www.ijcnn.net. Registration fees will be: INNS or IEEE Member Pre-reg $425.00 INNS or IEEE Member Onsite $525.00 Nonmember Pre-Reg $525.00 Nonmember Onsite $625.00 Student Pre-Reg $125.00 Student Onsite $175.00 Tutorial INNS or IEEE member Pre Reg $250.00 Tutorial INNS or IEEE member Onsite $300.00 Tutorial Nonmember Pre-Reg $275.00 Tutorial Nonmember Onsite $325.00 Tutorial Student Pre-Reg $125.00 Tutorial Student Onsite $175.00 For more information see the web page at http://www.ijcnn.net **************************************************** Prof. Michael Hasselmo e-mail: hasselmo at bu.edu Department of Psychology Tel: (617) 353-1397 and Program in Neuroscience or (617) 353-1431 Boston University FAX: (617) 353-1424 64 Cummington St. =20 Boston, MA 02215 http://people.bu.edu/hasselmo **************************************************** From nnsp03 at neuro.kuleuven.ac.be Thu Jan 16 06:46:55 2003 From: nnsp03 at neuro.kuleuven.ac.be (Neural Networks for Signal Processing 2003) Date: Thu, 16 Jan 2003 12:46:55 +0100 Subject: NNSP 2003 in Toulouse, France Message-ID: <3E269BAF.47A06B01@neuro.kuleuven.ac.be> 2003 IEEE International Workshop on Neural Networks for Signal Processing September 17-19, 2003 Toulouse, France Paper Submission by April 15 2003 -------------------------------------------http://isp.imm.dtu.dk/nnsp2003/ The thirteenth in a series of IEEE NNSP workshops, sponsored by the IEEE Signal Processing society will be held in Toulouse (www.mairie-toulouse.fr), France. The workshop will feature keynote addresses, technical presentations, and special sessions on * Bio-informatics * Neural Engineering * Aeronautics and a tutorial on Bayesian Learning that is included in the registration. Papers are solicited for, but not limited to, the following areas: Algorithms and Architectures: Artificial neural networks, kernel methods, committee models, Gaussian processes, independent component analysis, and a tutorial on Bayesian Learning that is included in the registration. Papers are solicited for, but not limited to, the following areas: Algorithms and Architectures: Artificial neural networks, kernel methods, committee models, Gaussian processes, independent component analysis, advanced (adaptive, nonlinear) signal processing, (hidden) Markov models, Bayesian modeling, parameter estimation, generalization, optimization, design algorithms. Applications: Speech processing, image processing (computer vision, OCR), multimodal interactions, multi-channel processing, intelligent multimedia and web processing, robotics, sonar and radar, bio-medical engineering, financial analysis, time series prediction, blind source separation, data fusion, data mining, adaptive filtering, communications, sensors, system identification, and other signal processing and pattern recognition applications. Implementations: Parallel and distributed implementation, hardware design, and other general implementation technologies. -------------------------NNSP'2003 webpage: http://isp.imm.dtu.dk/nnsp2003 -------------------------------------------------------------------------- From hasselmo at bu.edu Thu Jan 16 18:03:35 2003 From: hasselmo at bu.edu (Michael Hasselmo) Date: Thu, 16 Jan 2003 18:03:35 -0500 Subject: IJCNN 2003 final call for papers In-Reply-To: Message-ID: FINAL CALL FOR PAPERS (Deadline Approaching) **************************************************************** International Joint Conference on Neural Networks (IJCNN 2003) Portland, Oregon, July 20-24, 2003 http://www.ijcnn.net DEADLINE: January 29, 2003 **************************************************************** Co-sponsored by the International Neural Network Society (INNS) & IEEE Neural Networks Society. The International Joint Conference on Neural Networks provides an overview of state of the art research in Neural Networks, covering a wide range of topics (see topic list below). Paper submission deadline is January 29, 2003. Selected papers will be published in a special issue of the journal Neural Networks, in addition to publication of all papers in the conference proceedings. The IJCNN meeting is organized annually by the International Neural Network Society (INNS) and the IEEE Neural Networks Society. Conference attendees who are INNS or IEEE Neural Networks Society members, or who join one of these societies now will receive a reduced IJCNN conference registration fee, and those who are INNS members will receive the IJCNN special issue for free as part of their annual membership subscription to Neural Networks. Article submission: ------------------------------------ Authors should submit their articles electronically on the conference web site at http://www.ijcnn.net by the conference deadline of January 29, 2003 From dgw at MIT.EDU Fri Jan 17 16:34:13 2003 From: dgw at MIT.EDU (David Weininger) Date: Fri, 17 Jan 2003 16:34:13 -0500 Subject: book announcement--Arbib Message-ID: <200301171634134420@outgoing.mit.edu> I thought readers of the Connectionists List might be interested in this book. For more information, please visit http://mitpress.mit.edu/0262011972/ Thank you! Best, David The Handbook of Brain Theory and Neural Networks second edition edited by Michael A. Arbib Dramatically updating and extending the first edition, published in 1995, the second edition of The Handbook of Brain Theory and Neural Networks presents the enormous progress made in recent years in the many subfields related to the two great questions: How does the brain work? and, How can we build intelligent machines? Once again, the heart of the book is a set of almost 300 articles covering the whole spectrum of topics in brain theory and neural networks. The first two parts of the book, prepared by Michael Arbib, are designed to help readers orient themselves in this wealth of material. Part I provides general background on brain modeling and on both biological and artificial neural networks. Part II consists of "Road Maps" to help readers steer through articles in part III on specific topics of interest. The articles in part III are written so as to be accessible to readers of diverse backgrounds. They are cross-referenced and provide lists of pointers to Road Maps, background material, and related reading. The second edition greatly increases the coverage of models of fundamental neurobiology, cognitive neuroscience, and neural network approaches to language. It contains 287 articles, compared to the 266 in the first edition. Articles on topics from the first edition have been updated by the original authors or written anew by new authors, and there are 106 articles on new topics. Michael A. Arbib is University Professor; Fletcher Jones Professor of Computer Science; and Professor of Neuroscience, Biomedical Engineering, Electrical Engineering, and Psychology at the University of Southern California. 8 1/2 x 11, 1,344 pp., 1,000 illus., cloth, ISBN 0-262-01197-2 A Bradford Book ______________________ David Weininger Associate Publicist The MIT Press 5 Cambridge Center, 4th Floor Cambridge, MA 02142 617 253 2079 617 253 1709 fax http://mitpress.mit.edu From Dave_Touretzky at cs.cmu.edu Fri Jan 17 07:07:05 2003 From: Dave_Touretzky at cs.cmu.edu (Dave_Touretzky@cs.cmu.edu) Date: Fri, 17 Jan 2003 07:07:05 -0500 Subject: Hodgkin Huxley simulator -- executables available Message-ID: <28109.1042805225@ammon.boltz.cs.cmu.edu> Last semester I announced the first release of HHsim, an easy to use Hodgkin-Huxley simulator designed for neuroscience education. We have just released HHsim version 2.01, which is available in either Matlab source form or as a binary executable for Windows or Unix. The advantages of the executable version are (1) it does not require you to have Matlab installed on your machine, and (2) it executes slightly faster than the interpreted version. The executables were produced by the Matlab compiler. Other new features in HHsim version 2 are: - a Drugs button for applying TTX, TEA, or pronase - online documentation - sample exercises to try with the simulator You can download HHsim from here: http://www.cs.cmu.edu/~dst/HHsim HHsim is free software released under the GNU General Public License. The development of HHsim was funded in part by National Science Foundation grant DGE-9987588. -- Dave Touretzky From erik at bbf.uia.ac.be Fri Jan 17 10:56:56 2003 From: erik at bbf.uia.ac.be (Erik De Schutter) Date: Fri, 17 Jan 2003 16:56:56 +0100 Subject: CNS*03 CALL FOR PAPERS Message-ID: CALL FOR PAPERS: SUBMISSION DEADLINE: February 16, 2003 midnight Twelfth Annual Computational Neuroscience Meeting CNS*2003 July 5 - July 9, 2003 Alicante, Spain http://www.neuroinf.org/CNS.shtml Info at cp at bbf.uia.ac.be CNS*2003 will be held in Alicante from Saturday, July 5, 2003 to Wednesday, July 9. The main meeting will be July 5 - 7 at the Hotel Meli (poster sessions) and at the CAM Cultural Center (oral presentations). The main meeting consists of 6 oral sessions (one each morning and afternoon) and 3 early evening poster sessions. Workshops will be held at the University Miguel Hernndez (Medical School Campus) July 8 - 9. New is that some workshops will be mini-symposia or tutorials, a list of currently planned workshops can be found at the website. The conference dinner will take place in the Santa Brbara castle overlooking the city and the sea on Sunday, July 6. For tourist information see http://www.alicanteturismo.com, more specific practical information will be made available through the conference website. Papers can include experimental, model-based, as well as more abstract theoretical approaches to understanding neurobiological computation. We especially encourage papers that mix experimental and theoretical studies. We also accept papers that describe new technical approaches to theoretical and experimental issues in computational neuroscience or relevant software packages. The paper submission procedure is again completely electronic this year. There will not be any meeting announcement through surface mail, instead you find the meeting poster attached. PAPER SUBMISSION Papers for the meeting can be submitted ONLY through the web site at http://www.neuroinf.org/CNS.shtml Papers can be submitted either as a 1000 word summary or as a full paper (max 6 typeset pages). Full papers stand a better chance of being accepted for oral presentation. You will need to submit the paper in pdf format (if necessary Elsevier can help in converting your paper to pdf) and the 100 word abstract as text. You will also need to select two categories which describe your paper and which will guide the selection of reviewers. In addition we encourage you to also submit your paper to the Elsevier preprint server (http://www.computersciencepreprints.com). All submissions will be acknowledged by email. THE REVIEW PROCESS All submitted papers will be first reviewed by the program committee. Papers will be judged and accepted for the meeting based on the clarity with which the work is described and the biological relevance of the research. For this reason authors should be careful to make the connection to biology clear. We reject only a small fraction of the papers (~ 5%) and this usually based on absence of biological relevance (e.g. pure machine learning). We will notify authors of meeting acceptance before end of March. The second stage of review involves evaluation of submissions which requested an oral presentation by two independent referees. In addition to perceived quality as an oral presentation, the novelty of the research and the diversity and coherence of the overall program will be considered. To ensure diversity, those who have given talks in the recent past will not be selected and multiple oral presentations from the same lab will be discouraged. All accepted papers not selected for oral talks as well as papers explicitly submitted as poster presentations will be included in one of three evening poster sessions. Authors will be notified of the presentation format of their papers by begin of May. CONFERENCE PROCEEDINGS The proceedings volume is published each year as a special supplement to the journal Neurocomputing. In addition the proceedings are published in a hardbound edition by Elsevier Press. Only 200 papers will be published in the proceedings volume. If more than 200 papers are submitted (which is likely) the following rules will apply: each presenting author (who has to register for the meeting) can publish at most one paper in the proceedings book. In case of multi-author papers the same rule applies: one of the authors is considered presenting author and this person has to register at the meeting and cannot publish another paper. If more than 200 presenting authors wish to publish their papers in the proceedings volume the ranking based on the review process will be used to select the top 200 papers. Paper submissions to the conference proceedings are a process separate from the current call for papers: a new submission will need to be done in the early fall of 2003 for which authors will receive detailed instructions. For reference, papers presented at CNS*99 can be found in volumes 32-33 of Neurocomputing (2000), those of CNS*00 in volumes 38-40 (2001) and those of CNS*01 in volumes 44-46 (2002). INVITED SPEAKERS: Yang Dan (University of California Berkeley, USA) Peter Dayan (Gatsby Computational Neuroscience Unit, London, UK) Henry Markram (Brain Mind Institute Lausanne, Switzerland) ORGANIZING COMMITTEE: The CNS meeting is organized by the Computational Meeting Organization Program chair: Erik De Schutter (University of Antwerp, Belgium) Local organizer: Albert Compte (University Miguel Hernndez, Spain) Workshop organizer: Maneesh Sahani (University of California, San Francisco, USA) Government Liaison: Dennis Glanzman (NIMH/NIH, USA) and Yuan Liu (NINDS/NIH, USA) Program Committee: Upinder Bhalla (National Centre for Biological Sciences, India) Victoria Booth (New Jersey Institute of Technology, USA) Alain Destexhe (CNRS Gif-sur-Yvette, France) John Hertz (Nordita, Denmark) Hidetoshi Ikeno (Himeji Institute of Technology, Japan) Barry Richmond (NIMH, USA) Eytan Ruppin (Tel Aviv University) Frances Skinner (University Toronto, Canada) Todd Troyer (University of Maryland, USA) ---- From S.M.Bohte at cwi.nl Wed Jan 22 03:42:37 2003 From: S.M.Bohte at cwi.nl (Sander Bohte) Date: Wed, 22 Jan 2003 09:42:37 +0100 Subject: Call for papers: 1st International Workshop on Future of Neural Networks (FUNN 2003) @ ICALP 2003 Message-ID: <000801c2c1f2$38bc8300$80f4a8c0@cwiware> ======================================================================== 1st International Workshop on the Future of Neural Networks (FUNN 2003) July 5, 2003, Eindhoven, the Netherlands Workshop affiliated to ICALP 2003, June 30 - July 4, 2003 http://www.cwi.nl/~sbohte/funn/funn.html ======================================================================== SCOPE AND TOPICS Neural Networks are inspired by the highly interconnected neural structures in the brain and the nervous system. In the last twenty years the field has become popular and many of the neural networks have found their way into practical applications. On the more foundational level, there has been quite some recent development in the field. It is even to such an extent, that researchers that have not been in touch with the field for some years, have the feeling that it has completely changed. Some examples of developments: o The introduction of more biological plausible neural networks, like spiking neural networks. o The combination of several networks, possibly combined with other formalisms, into ensembles that can yield a better performance than networks in isolation. o The emergence of unifying frameworks for different types of networks, like the Support Vector Machines. o The integration with statistics, most noticeably in the shift towards graphical formalisms like Belief Networks. o The spin-off of successful new areas like Independent Component Analysis. The workshop will focus on the foundational aspects of new developments which include, but are not limited to the above mentioned topics. We hope to bring researchers together, have presentations on the latest developments and have discussions about the future of the field of neural networks. There will also be an invited presentation by Wolfgang Maass of the Technical University of Graz. SUBMISSION Authors are invited to send a contribution for review to funn at liacs.nl. Contributions should have a maximum length of 12 pages (llncs style) in 11 pt. font. See http://www.springer.de/comp/lncs/authors.html for further instructions. Contributions must be in postscript or pdf format. Accepted papers will be published in an informal workshop proceedings. We plan to have a special issue of the journal Natural Computing (Kluwer) based on extended versions of selected workshop papers. PARTICIPATION, REGISTRATION & COST The cost of participating in the workshop is 75 euro. This includes a lunch and the workshop proceedings. Further details can be found in the call for participation, which will be published well in advance of the workshop. IMPORTANT DATES April 27, 2003 : Submission deadline May 24, 2003 : Notification of acceptance July 5, 2003 : Meeting date From bogus@does.not.exist.com Wed Jan 22 10:57:05 2003 From: bogus@does.not.exist.com () Date: Wed, 22 Jan 2003 15:57:05 -0000 Subject: Postdoc job Message-ID: <20CC6C4061CBB04A98656ED3209B203C42FEEE@bond.ncl.ac.uk> From bogus@does.not.exist.com Wed Jan 22 07:56:58 2003 From: bogus@does.not.exist.com () Date: Wed, 22 Jan 2003 12:56:58 -0000 Subject: Natural object categorisation Message-ID: <736F0925D69F9941B3BA8AEED0F5E75CB2EA5B@02-CSEXCH.uopnet.plymouth.ac.uk> From bogus@does.not.exist.com Thu Jan 23 13:48:45 2003 From: bogus@does.not.exist.com () Date: Thu, 23 Jan 2003 18:48:45 -0000 Subject: Soft Computing Research at Cranfield and BT Exact Message-ID: <14D6AEAE08A23344848EF66421623C94014F9F9C@silver.sims.cranfield.ac.uk> A non-text attachment was scrubbed... Name: not available Type: multipart/alternative Size: 0 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/00000000/cfdefbd6/attachment.bin From dgw at MIT.EDU Thu Jan 23 12:28:39 2003 From: dgw at MIT.EDU (David Weininger) Date: Thu, 23 Jan 2003 12:28:39 -0500 Subject: book announcement--Dietterich Message-ID: <200301231228392279@outgoing.mit.edu> I thought readers of the Connectionists List might be interested in this book. For more information, please visit http://mitpress.mit.edu/0262042088/ Thank you! Best, David Advances in Neural Information Processing Systems 14 Proceedings of the 2001 Neural Information Processing Systems (NIPS) Conference. edited by Thomas G. Dietterich, Suzanna Becker, and Zoubin Ghahramani The annual conference on Neural Information Processing Systems (NIPS) is the flagship conference on neural computation. The conference is interdisciplinary, with contributions in algorithms, learning theory, cognitive science, neuroscience, vision, speech and signal processing, reinforcement learning and control, implementations, and diverse applications. Only about 30 percent of the papers submitted are accepted for presentation at NIPS, so the quality is exceptionally high. These proceedings contain all of the papers that were presented at the 2001 conference. Thomas G. Dietterich is Professor of Computer Science at Oregon State University. Suzanna Becker is Associate Professor of Psychology and an Associate Member of the Department of Computing and Software at McMaster University. Zoubin Ghahramani is Lecturer in the Gatsby Computational Neuroscience Unit at University College London. 7 x 10, 1600 pp. (2 volumes, not sold separately), cloth, ISBN 0-262-04208-8 A Bradford Book ______________________ David Weininger Associate Publicist The MIT Press 5 Cambridge Center, 4th Floor Cambridge, MA 02142 617 253 2079 617 253 1709 fax http://mitpress.mit.edu From ckrause at pc09.inb.uni-luebeck.de Fri Jan 24 07:23:28 2003 From: ckrause at pc09.inb.uni-luebeck.de (Christopher Krause) Date: Fri, 24 Jan 2003 13:23:28 +0100 Subject: PhD and System Dynamics Message-ID: <200301241223.h0OCNSi10082@pc09.inb.mu-luebeck.de> The Institute for Neuro- and Bioinformatics, University of Luebeck, Germany, seeks Research Scientists (PhD students) for an interdisciplinary project funded by the European Union. The successful candidate will join an international and interdisciplinary research team. The first goal of the project is to develop a new form of understanding complex dynamic systems, which involves the simulation and visualisation of nonlinear dynamic processes. The second goal is to develop a software tool for decision support for strategic development in politics, transport and logistics, and multinational companies. We expect a strong background in computer science, mathematics, and/or physics, experience in simulation-techniques and enthusiasm for interdisciplinary research. Programming skills (mainly Java) would be a plus. We offer exciting new research topics and the possibility to obtain a PhD in computer science. The positions are initially funded for 36 month. The salary will be at the level of BAT IIa (appr. 38.000 EURO/year before tax). Please send applications including your curriculum vitae, a statement of interests, and names of references to Prof. Thomas Martinetz (martinetz at informatik.uni-luebeck.de ). Application deadline is February 15th. For further information contact T. Martinetz. From ascoli at gmu.edu Fri Jan 24 12:45:26 2003 From: ascoli at gmu.edu (Giorgio Ascoli) Date: Fri, 24 Jan 2003 12:45:26 -0500 Subject: postdoc position available Message-ID: <3E317BB6.60408@gmu.edu> Please post and circulate (my apologies for cross-listing). Giorgio Ascoli COMPUTATIONAL NEUROSCIENCE: POST-DOC Position available immediately for computational modeling of neuronal morphology, connectivity, and electrophysiology. Post-doc will join dynamic and creative laboratory at George Mason Universitys Krasnow Institute, near Washington DC. Superb office space and research/computing facilities, salary based on NIH postdoctoral scale, full benefits. Research experience with either programming/modelling packages or experimental neuroanatomy/electrophysiology is desirable. Serious candidates with a PhD in biology, computer science, physics, psychology, or other areas related to neuroscience (including MD or engineering degree) should submit resume, (p)reprints, 1-page motivation, and 3 recommendation letters ASAP to: Dr. Giorgio Ascoli - Krasnow Institute for Advanced Study - George Mason University, MS2A1 - 4400 University Dr. - Fairfax, VA 22030 (ascoli at gmu.edu). Position will be filled as soon as a suitable candidate is found. Non-resident aliens welcome to apply. George Mason University is an affirmative action / equal opportunity employer. More info: http://www.krasnow.gmu.edu/ascoli/op.htm ------------------- Giorgio Ascoli, PhD Head, Computational Neuroanatomy Group Krasnow Institute for Advanced Study and Department of Psychology - MS2A1 George Mason University, Fairfax, VA 22030-4444 Web: www.krasnow.gmu.edu/ascoli Ph. (703)993-4383 Fax (703)993-4325 From hasselmo at bu.edu Fri Jan 24 14:10:55 2003 From: hasselmo at bu.edu (Michael Hasselmo) Date: Fri, 24 Jan 2003 14:10:55 -0500 Subject: Special Issue of Neural Networks In-Reply-To: <200301241904.OAA294026@acsn03.bu.edu> Message-ID: Call for submissions 2003 Special Issue of the journal Neural Networks This special issue will contain selected articles presented at the International Joint Conference on Neural Networks (IJCNN 2003) taking place in Portland, Oregon, U.S.A. from July 20-24, 2003. This conference provides an overview of state of the art research in Neural Networks, from which this special issue will publish a selection of over 300 pages of articles. These articles will cover a wide range of topics within Neural Networks. The full topic list can be viewed on the conference web page at: www.ijcnn.net. Authors should submit their articles electronically to the conference by the conference deadline of January 29, 2003. The review process of the conference will allow selection of a selected subset of the articles for inclusion in the special issue of Neural Networks. The selected authors will receive an invitation to be included in the special issue and must respond by the deadline to be included. Revised articles must then be submitted by March 21, 2003. Any invited articles which are not resubmitted by the deadline will not be included in the special issue, but will still be included in the conference. Co-Editors Prof. Donald Wunsch, University of Missouri - Rolla Prof. Michael E. Hasselmo, Boston University Prof. Kumar Venayagamoorthy, University of Missouri - Rolla Prof. DeLiang Wang, Ohio State University Submission Deadline for submission: January 29, 2003 Format: Double column, 4-6 pages. Must follow guidelines on the paper submission page at www.ijcnn.net. Address for Papers Papers should be submitted electronically for review on the IJCNN 2003 meeting web page at www.ijcnn.net (deadline Jan. 29, 2003). Accepted papers must be submitted in revised form to the IJCNN web site by March 21, 2003 and assembled by the special issue editors for publication. The IJCNN meeting is organized annually by the International Neural Network Society (INNS) and the IEEE Neural Networks Society. Conference attendees who join the INNS will receive a reduced IJCNN conference registration fee, and those who are INNS members will receive the IJCNN special issue for free as part of their annual membership subscription to Neural Networks. From cindy at cns.bu.edu Fri Jan 24 15:27:11 2003 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Fri, 24 Jan 2003 15:27:11 -0500 Subject: Call for Papers: 2004 Special Issue of Neural Networks on Vision and Brain Message-ID: <00eb01c2c3e6$fa407d60$573dc580@bu.edu> CALL FOR PAPERS 2004 Special Issue VISION AND BRAIN Understanding how the brain sees is one of the most active and exciting areas in perceptual science, neuroscience, and modeling. This is because vision is one of our most important sources of information about the world, and a large amount of brain is used to process visual signals, ranging from early filtering processes through perceptual grouping, surface formation, depth perception, texture perception, figure-ground separation, motion perception, navigation, search, and object recognition. This Special Issue will incorporate invited and contributed articles focused on recent experimental and modeling progress in unifying physiological, psychophysical and computational mechanisms of vision. The Special Issue will also include articles that summarize biologically inspired approaches to computer vision in technology, including hardware approaches to realizing neuromorphic vision algorithms. CO-EDITORS: Professor David Field, Cornell University Professor Leif Finkel, University of Pennsylvania Professor Stephen Grossberg, Boston University SUBMISSION: Deadline for submission: September 30, 2003 Notification of acceptance: January 31, 2004 Format: no longer than 10,000 words; APA reference format ADDRESS FOR SUBMISSION: Stephen Grossberg, Editor Neural Networks Department of Cognitive and Neural Systems Boston University 677 Beacon Street, Room 203 Boston, Massachusetts 02215 USA From alfredo at itam.mx Fri Jan 24 18:13:40 2003 From: alfredo at itam.mx (Alfredo) Date: Fri, 24 Jan 2003 17:13:40 -0600 Subject: book and software announcement - NSL3.0 Message-ID: <5.0.2.1.0.20030124170330.0359ccb0@lamport.rhon.itam.mx> Dear Connectionists: The following book may be of interest to you. For more information please visit: http://mitpress.mit.edu/catalog/item/default.asp?sid=68013B05-2E40-4A86-BB67-0A8964D7B663&ttype=2&tid=8815 Best wishes, Alfredo The Neural Simulation Language: A System for Brain Modeling by A. Weitzenfeld, M.A. Arbib and A. Alexander MIT Press Book Description: The book describes the Neural Simulation Language (NSL) developed by Alfredo Weitzenfeld, Michael Arbib, and Amanda Alexander. NSL is a simulation environment for modular brain modeling now in its third major release supporting two programming environments, one in Java and the other one in C++. NSL addresses the needs of a wide range of users. For novice users interested only in an introduction to neural networks, NSL provides user-friendly interfaces and a set of predefined artificial and biological neural models. For more advanced users well acquainted with the area of neural modeling NSL offers more sophistication through extended visualization tools and programming. NSL may easily be linked to other software by doing direct programming in either Java or C++, such as linking it to numerical libraries or robotic systems. NSL is especially suitable for academia and research where simulation and model development can complement theoretical courses in both biological and artificial neural networks. Models included in the book are examples of models that can be used for this purpose. Students are able to run these models and change their behavior by modifying input or network parameters. Researchers may extend these architectures in developing new neural models. The book is divided into two parts. The first part presents an overview of neural network and schema modeling, a brief history of NSL, and a discussion of the new version, NSL 3.0. It includes tutorials on several basic neural models. The second part presents models built in NSL by researchers from around the world, with models such as conditional learning, face recognition, associative search networks and visuomotor coordination. Each chapter provides an explanation of a model, an overview of the NSL 3.0 code, and a representative set of simulation results. Table of Contents: Part I. An Overview of NSL Modeling and Simulation 1 Introduction: Introduction to neural network modeling and simulation in NSL. 2 Simulation in NSL: Examples of biological and artificial neural network simulation in NSL, how to run them. 3 Modeling in NSL: Examples of biological and artificial neural network modeling in NSL, how to create them. 4 Schematic Capture System: Describes the Schematic Capture System visual tools for the design of neural models and model libraries. 5 User Interface and Graphical Windows: Describes the NSL Graphics and Window Interface environment. 6 The Modeling Language NSLM: Describes the NSLM high level modeling language for writing neural network models. 7 The Scripting Language NSLS: Describes the NSLS scripting language for specifying simulation interaction and control commands. Part II. Neural Modeling and Simulation Examples Using NSL 8 Adaptive Resonance Theory - Grossberg ART by T. Tanaka and A. Weitzenfeld 9 Depth Perception - Dev and House Depth Perception by A. Weitzenfeld and M. Arbib 10 Retina by R. Corbacho and A. Weitzenfeld 11 Receptive Fields by F. Moran, M.A. Andrade, Chacn and A. Weitzenfeld 12 The Associative Search Network: Landmark Learning and Hill Climbing - Barto and Sutton Landmark Learning by M. Bota and A. Guazelli 13 A Model of Primate Visual-Motor Conditional Learning: Reinforcement Learning by A. Fagg and A. Weitzenfeld 14 The Modular Design of the Oculomotor System in Monkeys by P. Dominey, M. Arbib, and A. Alexander 15 Crowley-Arbib Saccade Model by M. Crowley, E. Oztop, and S. Mrmol 16 A Cerebellar Model of Sensorimotor Adaptation by J. Spoelstra 17 Learing to Detour by F. Corbacho and A. Weitzenfeld 18 Face Recognition by Dynamic Link Matching by L. Wiskott, C. von der Malsburg and A. Weitzenfeld The NSL web site http://www.neuralsimulationlanguage.org includes all software and models described in the book as well as other relevant information. The NSL Java version can be downloaded from http://nsl.usc.edu as well. From bogus@does.not.exist.com Fri Jan 24 07:24:56 2003 From: bogus@does.not.exist.com () Date: Fri, 24 Jan 2003 12:24:56 -0000 Subject: Research Fellowship Message-ID: <736F0925D69F9941B3BA8AEED0F5E75C5F4042@02-CSEXCH.uopnet.plymouth.ac.uk> From bogus@does.not.exist.com Fri Jan 24 07:01:26 2003 From: bogus@does.not.exist.com () Date: Fri, 24 Jan 2003 12:01:26 -0000 Subject: Research Scholarships Message-ID: <736F0925D69F9941B3BA8AEED0F5E75C5F5136@02-CSEXCH.uopnet.plymouth.ac.uk> From schwabe at cs.tu-berlin.de Mon Jan 27 04:40:38 2003 From: schwabe at cs.tu-berlin.de (Lars Schwabe) Date: Mon, 27 Jan 2003 10:40:38 +0100 Subject: Advanced Course in Computational Neuroscience Message-ID: <000c01c2c5e8$28f69b50$5e109582@algieba> ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE (A FENS/IBRO NEUROSCIENCE SCHOOL) August 11th - September 5th, 2003 MUNICIPALITY OF OBIDOS, PORTUGAL DIRECTORS: Ad Aertsen (University of Freiburg, Germany) Alain Destexhe (CNRS, Gif-sur-Yvette, France) Klaus Obermayer (Technical University of Berlin, Germany) Eilon Vaadia (Hebrew University, Jerusalem, Israel) The Advanced Course in Computational Neuroscience introduces students to the panoply of problems and methods of computational neuroscience, simultaneously addressing several levels of neural organisation, from subcellular processes to operations of the entire brain. The course consists of two complementary parts. A distinguished international faculty gives morning lectures on topics in experimental and computational neuroscience. The rest of the day is devoted to practical training, including learning how to use simulation software and how to implement a model of the system the student wishes to study on individual UNIX workstations. The first week of the course introduces students to essential neurobiological concepts and to the most important techniques in modelling single cells, networks and neural systems. Students learn how to apply software packages like GENESIS, MATLAB, NEURON, XPP, etc. to the solution of their problems. During the following three weeks the lectures will cover specific brain functions. Each week topics ranging from modelling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the brain will be covered. The course ends with a presentation of the students' projects. The Advanced Course in Computational Neuroscience is designed for advanced graduate students and postdoctoral fellows in a variety of disciplines, including neuroscience, physics, electrical engineering, computer science and psychology. Students are expected to have a basic background in neurobiology as well as some computer experience. Students of any nationality can apply. A maximum total of 30 students will be accepted and we specifically encourage applications from researchers who work in less-favoured regions and women. There will be a fee of EUR 950,- per student covering costs for lodging, meals and other course expenses, but a limited number of fellowships for travel and tuition fee will be available. These fellowships will be given in priority to students from less favoured countries. More information and application forms can be obtained from: http://www.neuroinf.org/courses/EUCOURSE/EU03/ The application process will start on February 10th, 2003. Please apply electronically ONLY using a web browser. Contact address: - mail: Klaus Obermayer, FR2-1, Fakultaet IV, Technical University of Berlin, Franklinstrasse 28/29, 10587 Berlin, Germany phone: +49-(0)30-314-73442 fax: +49-(0)30-314-73121 - e-mail: obidos at cs.tu-berlin.de APPLICATION DEADLINE: April 13th, 2003 Applicants will be notified of the results of the selection procedures by May 23rd, 2003. From kegl at IRO.UMontreal.CA Mon Jan 27 11:59:11 2003 From: kegl at IRO.UMontreal.CA (Balazs Kegl) Date: Mon, 27 Jan 2003 11:59:11 -0500 Subject: Workshop on Advances in Machine Learning, Montreal, June 2-6, 2003 Message-ID: <200301271659.h0RGxBt30533@neumann.IRO.UMontreal.CA> ---- Please excuse us if you receive multiple copies of this message ----- Call for papers Workshop on Advances in Machine Learning Montreal, Canada, June 2-6, 2003 URL: www.iro.umontreal.ca/~lisa/workshop2003.html Organizers: Yoshua Bengio, Balazs Kegl (University of Montreal) Doina Precup (McGill University) Scope: Probabilities are at the core of recent advances in the theory and practice of machine learning algorithms. The workshop will focus on three broad areas where these advances are crucial: statistical learning theory, learning algorithms, and reinforcement learning. The workshop will therefore bring together experts from each of these three important domains. Among the sub-topics that will be covered, we note: variational methods, graphical models, the curse of dimensionality, empirical methods to take advantage of theories of generalization error, and some of the applications of these new methods. On the theoretical side, in recent years a lot of effort has been devoted to explain the generalization abilities of popular learning algorithms such as voting classifiers and kernel methods. Some of these results have given rise to general principles that can guide practical classifier design. Some (non-exclusive) sub-topics in this aspect of the workshop include Rademacher and Gaussian complexities, algorithmic stability and generalization, localized complexities and results on the generalization ability of voting classifiers and kernel-based methods. On the algorithmic side, one of the emphasis of recent years has been on probabilistic models that attempt to capture the complex structure in the data, often by discovering the main lower-dimensional features that explain the data. This raises interesting and difficult questions on how to train such models, but such algorithms may have wide ranging applications in domains in which the data has interesting structure that may be explained at multiple levels, such as in vision and language. In reinforcement learning (RL), recent research has brought significant advances in some of the traditional problems, such as understanding the interplay between RL algorithms and function approximation, and extending RL beyond MDPs. At the same time, new areas of research, such as computational game theory, have developed at the interface between RL and probabilistic learning methods. In this workshop, we invite presentations on all RL topics, ranging from theoretical development to practical applications. Invited speakers: Rich Sutton, U. Massachusetts, MA, USA Andy Barto, U. Massachusetts, MA, USA (to confirm) Satinder Singh, U. Michigan, Ann Arbour, MI, USA Michael Littman, Rutgers U., NJ, USA Leslie Pack Kaelbling, MIT (to confirm) Michael Kearns, U. Pennsylvania (to confirm) Sridhar Mahadevan, U. Massachusetts Peter Bartlett, U. California Berkeley, CA, USA Gabor Lugosi, Pompeu Fabra Univ., Spain (to confirm) Vladimir Koltchinskii, U. New Mexico, NM, USA Yann Le Cun, NEC Research, NJ, USA Paolo Frasconi, U. Firenze, Italy Dale Schuurmans, Waterloo U., Ontario, Canada Nando de Freitas, U. British Columbia, BC, Canada Sam Roweis, U. Toronto, Ontario, Canada Geoff Hinton, U. Toronto, Ontario, Canada Important dates: March 31, Paper submission deadline April 15, Notification of paper acceptance/rejection. Submission: Papers should be submitted electronically to kegl at iro.umontreal.ca. Papers can be submitted either as a postscript or a pdf (acrobat) file. No proceedings are currently planned. Registration: The registration fees are minimal: regular registration fees are 100$CAN. Reduced rate for students from a Canadian academic institution: 50$CAN. Venue: The workshop will take place at the Centre de Recherches Mathematiques, on the campus of Universite de Montreal, in lively and beautiful Montreal, Canada. The conference will be held in the Pavillon Andre Aisenstadt, 2920 chemin de la Tour. From jbednar at cs.utexas.edu Wed Jan 29 04:04:19 2003 From: jbednar at cs.utexas.edu (James A. Bednar) Date: Wed, 29 Jan 2003 04:04:19 -0500 (EST) Subject: Visual cortex dissertation (with software and web demos) Message-ID: <200301290904.h0T94JHs014617@ms-smtp-01.texas.rr.com> I am pleased to announce the availability of my Ph.D. dissertation, completed last year at the Department of Computer Sciences at the University of Texas at Austin under the supervision of Prof. Risto Miikkulainen. The thesis shows how the combination of spontaneous neural activity and visual patterns in the environment can help explain the development of orientation and face processing circuitry in the cortex. Early versions of this work appeared at the AAAI-2000, CogSci-2002, and CNS*02 conferences, and updated results will appear in Neural Computation, 2003 (in press). Jefferson Provost and I are also pleased to announce version 4.0 of the LISSOM software package for self-organization of laterally connected maps in visual cortex. This software supports the simulations in the dissertation, and is intended to serve as a starting point for computational studies of the development and function of perceptual maps in general. The software is available at topographica.org, and the dissertation and other papers and demos are available at http://www.cs.utexas.edu/users/nn/pages/research/visualcortex.html. -- James A. Bednar _______________________________________________________________________________ Publications: LEARNING TO SEE: GENETIC AND ENVIRONMENTAL INFLUENCES ON VISUAL DEVELOPMENT James A. Bednar Ph.D. Thesis, The University of Texas at Austin Technical Report~AI-TR-02-294, May 2002 (138 pages). http://www.cs.utexas.edu/users/nn/pages/publications/abstracts.html#bednar.phd02 How can a computing system as complex as the human visual system be specified and constructed? Recent discoveries of widespread spontaneous neural activity suggest a simple yet powerful explanation: genetic information may be expressed as internally generated training patterns for a general-purpose learning system. The thesis presents an implementation of this idea as a detailed, large-scale computational model of visual system development. Simulations show how newborn orientation processing and face detection can be specified in terms of training patterns, and how postnatal learning can extend these capabilities. The results explain experimental data from laboratory animals, human newborns, and older infants, and provide concrete predictions about infant behavior and neural activity for future experiments. They also suggest that combining a pattern generator with a learning algorithm is an efficient way to develop a complex adaptive system. SELF-ORGANIZATION OF SPATIOTEMPORAL RECEPTIVE FIELDS AND LATERALLY CONNECTED DIRECTION AND ORIENTATION MAPS James A. Bednar and Risto Miikkulainen To appear in Neurocomputing, 2003 (in press; 8 pages). http://www.cs.utexas.edu/users/nn/pages/publications/abstracts.html#bednar.cns02 Studies of orientation maps in primary visual cortex (V1) suggest that lateral connections mediate competition and cooperation between orientation-selective units, but their role in motion perception has not been established. Using a self-organizing model of V1 with moving oriented patterns, we show that (1) afferent weights of each neuron organize into Gabor-like spatiotemporal receptive fields with ON and OFF lobes, (2) these receptive fields form realistic joint direction and orientation maps, and (3) lateral connections develop between patches with similar orientation and direction preferences. These results suggest that a single self-organizing system may underlie the development of orientation selectivity, direction selectivity, and lateral connectivity. _______________________________________________________________________________ Software: LISSOM V4.0: HIERARCHICAL LATERALLY CONNECTED SELF-ORGANIZING MAPS Available from http://www.topographica.org James A. Bednar and Jefferson Provost The LISSOM package contains the C++ and Scheme source code and examples for training and testing LISSOM-based computational models. These self-organizing models support detailed simulation of the development and function of the mammalian visual system, and include parameter files used to generate the results in the publications listed above. Version 4.0 of the simulator provides a graphical user interface (GUI) for basic tasks, and full batch mode (using a command file) and remote mode (using a command line prompt) interfaces. The graphs and plots are available from any of the supported interfaces. Sample networks are provided for running orientation, ocular-dominance, motion direction, and face perception simulations. These existing models can be tested easily with new input patterns using the GUI, or the command files can be edited to produce new models based on other training patterns or different network configurations. Extensive documentation is included, and is also available via online help at the command line. The full package is freely available from our web site, and supports UNIX, Windows, and Mac systems. For more details see the tutorial, screenshots, and documentation at topographica.org. From geoff at cns.georgetown.edu Wed Jan 29 16:45:47 2003 From: geoff at cns.georgetown.edu (geoff@cns.georgetown.edu) Date: Wed, 29 Jan 2003 16:45:47 -0500 Subject: Faculty position available Message-ID: <200301292145.h0TLjlI17128@jacquet.cns.georgetown.edu> TENURE-TRACK FACULTY POSITION IN COMPUTATIONAL NEUROSCIENCE Georgetown University The Department of Neuroscience is recruiting a new tenure-track faculty member in computational neuroscience at the rank of either Assistant or Associate Professor. We offer an outstanding intellectual and collaborative environment with highly competitive salary and start-up packages. Successful candidates must have a Ph.D. or equivalent, evidence of productivity and innovation, and the potential to establish an independently funded research program. Applications are encouraged from women and underrepresented minorities. To apply send to the address below (hardcopies only please) a detailed CV, a two-page statement of research and teaching interests, and (3) no more than 3 preprints or reprints. Please also have three referees send recommendations to the same address. Faculty Search Committee Attention: Geoff Goodhill Department of Neuroscience Georgetown University Box 571464 Washington DC 20057-1464 http://neuro.georgetown.edu Application review will begin immediately and will continue until the position is filled. Georgetown University is an Equal Opportunity, Affirmation Action Employer. Qualified candidates will receive employment consideration without regard to race, sex, sexual orientations, age, religion, national origin, marital status, veteran status or disability. We are committed to diversity in the workplace. From bogus@does.not.exist.com Wed Jan 1 20:26:04 2003 From: bogus@does.not.exist.com () Date: Thu, 2 Jan 2003 09:26:04 +0800 Subject: Research positions in bioinformatics, BIRC, Singapore. Message-ID: <9CFE75F87A78564887952466CA3F4E4D0176C11A@exchange02.staff.main.ntu.edu.sg> From terry at salk.edu Thu Jan 2 18:30:48 2003 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 2 Jan 2003 15:30:48 -0800 (PST) Subject: NEURAL COMPUTATION 15:1 In-Reply-To: <200211220021.gAM0LdU25878@purkinje.salk.edu> Message-ID: <200301022330.h02NUmE66618@purkinje.salk.edu> Neural Computation - Contents - Volume 15, Number 1 - January 1, 2003 ARTICLE Asynchronous States and the Emergence of Synchrony in Large Networks of Interacting Excitatory and Inhibitory Neurons D. Hansel and G. Mato NOTE A Constrained EM Algorithm for Principal Component Analysis Jong-Hoon Ahn and Jong-Hoon Oh LETTERS Higher-Order Statistics of Input Ensembles and the Response of Simple Model Neurons Alexandre Kuhn, Ad Aertsen and Stefan Rotter Duality of Rate Coding and Temporal Coding in Multilayered Feedforward Networks Naoki Masuda and Kazuyuki Aihara Synchronous Firing and Higher-Order Interactions in Neuron Pool Shun-ichi Amari, Hiroyuki Nakahara, Si Wu and Yutaka Sakai Determination of Firing Times for the Stochastic Fitzhugh-Nagumo Neuronal Model Henry C. Tuckwell, Roger Rodriguez and Frederic Y.M. Wan Developmental Constraints Aid the Acquisition of Binocular Disparity Sensitivities Melissa Dominguez and Robert A. Jacobs A Quantified Sensitivity Measure for Multilayer Perceptron to Input Perturbation Xiaoqin Zeng and Daniel S. Yeung Variational Mixture of Bayesian Independent Component Analysers R. A. Choudrey and S. J. Roberts ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2003 - VOLUME 15 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $95 $101.65 $143 Institution $590 $631.30 $638 * 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 deniz at cnel.ufl.edu Thu Jan 2 14:55:37 2003 From: deniz at cnel.ufl.edu (Deniz Erdogmus) Date: Thu, 02 Jan 2003 14:55:37 -0500 Subject: IEEE-TNN Special Issue on Information Theoretic Learning Message-ID: <3E149939.72F07F4F@cnel.ufl.edu> Dear Colleagues, This is a reminder for the upcoming special issue of the IEEE Transactions on Neural Networks on Information Theoretic Learning. The call for papers of this special issue can be viewed at http://sonics.cnel.ufl.edu/cnel02/ Prospective authors can also register their intent to submit a paper and later submit their papers at the same website. The TNN notice for this issue is located at http://ieee-nns.org/pubs/tnn/special.html The paper submission deadline is March 15th, 2003. Happy new year and best regards, Deniz Erdogmus From bogus@does.not.exist.com Fri Jan 3 18:59:26 2003 From: bogus@does.not.exist.com () Date: Fri, 3 Jan 2003 15:59:26 -0800 Subject: R&D Openings at Fair Isaac & Company Message-ID: <5FF0FAAD57CE8845B79FD7B7CFF8F29E010C42@sdomsg00.corp.fairisaac.com> From cia at bsp.brain.riken.go.jp Fri Jan 3 13:18:52 2003 From: cia at bsp.brain.riken.go.jp (Andrzej CICHOCKI) Date: Sat, 04 Jan 2003 03:18:52 +0900 Subject: Book and software announcement - Cichocki Message-ID: <3E15D40C.1060209@bsp.brain.riken.go.jp> [Our sincere apologies if you receive multiple copies of this email] I am please to announce that Chapter 1, as well as, tables with algorithms, simulations examples, benchmarks and bibliography of revised and corrected version of the following book: ADAPTIVE BLIND SIGNAL and IMAGE PROCESSING: Learning Algorithms and Applications A. Cichocki and S. Amari Published by John Wiley & Sons, Chichester UK, 2002 are now available free at our web page: http://www.bsp.brain.riken.go.jp/ICAbookPAGE/ Moreover, versions 1.2 of associated ICALAB MATLAB Toolboxes for signals and images processing with revised on-line helps and with useful preprocessing are available at : http://www.bsp.brain.riken.go.jp/ICALAB/ http://www.bsp.brain.riken.go.jp/ICALAB/ICALABSignalProc/ http://www.bsp.brain.riken.go.jp/ICALAB/ICALABImageProc/ Version 1.4 with several new features and improved algorithms will be released soon. All comments and suggestions are welcome. Best regards, Andrzej Cichocki --------------------------------------------------- Laboratory for Advanced Brain Signal Processing, Brain Science Institute, Riken 2-1 Hirosawa, Wako-shi, Saitama 351-0198, JAPAN http://www.bsp.brain.riken.go.jp/ From nnk at his.atr.co.jp Sun Jan 5 19:28:00 2003 From: nnk at his.atr.co.jp (Neural Networks Japan Office) Date: Mon, 6 Jan 2003 09:28:00 +0900 Subject: Neural Networks 16(1) Message-ID: NEURAL NETWORKS 16(1) Contents - Volume 16, Number 1 - 2003 ------------------------------------------------------------------ Editorial for 2003: Celebrating the year with a special issue for IJCNN'03 Neural Networks Referees used in 2002 NEURAL NETWORKS LETTER: Reinforcement-learning of reinforcement learning. Nicolas Schweighofer, Kenji Doya CONTRIBUTED ARTICLES: ***** Psychology and Cognitive Science ***** Learning to generate articulated behavior through the bottom-up and the top-down interaction processes. Jun Tani Computational model for neural representation of multiple disparities. Osamu Watanabe, Masanori Idesawa ***** Neuroscience and Neuropsychology ***** A synfire chain in layered coincidence detectors with random synaptic delays. Kazushi Ikeda ***** Mathematical and Computational Analysis ***** Mathematical analysis of a correlation-based model for orientation map formation. Tadashi Yamazaki The functional localization of neural networks using genetic algorithms. Hiroshi Tsukimoto, Hisaaki Hatano A new EM-based training algorithm for RBF networks. Marcelino Lazaro, Ignacio Santamaria, Carlos Pantaleon Analysis of Tikhonov regularization for function approximation by neural networks. Martin Burger, Andreas Neubauer Predicting the behaviour of G-RAM networks. Geoffrey G. Lockwood, Igor Aleksander ***** Engineering and Design ***** On-line identification and reconstruction of finite automata with generalized recurrent neural networks. Ivan Gabrijel, Andrej Dobnikar ***** Technology and Applications ***** Classification of clustered microclacifications using a Shape Cognitron neural network. San-Kan Lee, Pau-choo Chung, Chein-I Chang, Chien-Shun Lo, Tain Lee Giu-Cheng Hsu, Chin-Wen Yang On learning to estimate the block directional image of a fingerprint using a hierarchical neural network. Khaled Ahmed Nagaty BOOK REVIEW Review of "Self-organizing Neural Networks: Recent Advances and Applications" (U. Seiffert, L.C. Jain, editors) by F. Azuaje ERRATUM Erratum to "Book Review:Learning Kernel Classifiers" [Neural Networks 15(7) 930] by R. Williamson CURRENT EVENTS ------------------------------------------------------------------ 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 (regular) SEK 660 (regular) Y 13,000 (regular) Neural Networks (plus 2,000 enrollment fee) $20 (student) SEK 460 (student) Y 11,000 (student) (plus 2,000 enrollment fee) ----------------------------------------------------------------------------- membership without $30 SEK 200 not available to Neural Networks non-students (subscribe through another society) Y 5,000 (student) (plus 2,000 enrollment fee) ----------------------------------------------------------------------------- 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 Takashi Nagano Faculty of Engineering Hosei University 3-7-2, Kajinocho, Koganei-shi Tokyo 184-8584 Japan 81 42 387 6350 (phone and fax) jnns at k.hosei.ac.jp http://jnns.inf.eng.tamagawa.ac.jp/home-j.html ----------------------------------------------------------------- From baluja at cs.cmu.edu Tue Jan 7 01:09:11 2003 From: baluja at cs.cmu.edu (Shumeet Baluja) Date: Tue, 07 Jan 2003 01:09:11 -0500 Subject: PAPER: Using a priori knowledge to create probabilistic models for optimization Message-ID: <19717.1041919751@ux4.sp.cs.cmu.edu> The following paper is available from: http://www.cs.cmu.edu/~baluja Using a priori knowledge to create probabilistic models for optimization ABSTRACT: Recent studies have examined the effectiveness of using probabilistic models to guide the sample generation process for searching high dimensional spaces. Although the simplest models, which do not account for parameter interdependencies, often perform well on many problems, they may perform poorly when used on problems that have a high degree of interdependence between parameters. More complex dependency networks that can account for the interactions between parameters are required. However, building these networks may necessitate enormous amounts of sampling. In this paper, we demonstrate how a priori knowledge of parameter dependencies, even incomplete knowledge, can be incorporated to efficiently obtain accurate models that account for parameter interdependencies. This is achieved by effectively putting priors on the network structures that are created. These more accurate models yield improved results when used to guide the sample generation process for search and also when used to initialize the starting points of other search algorithms. Please feel free to send questions/comments to baluja at cs.cmu.edu. best, shumeet From terry at salk.edu Tue Jan 7 17:58:04 2003 From: terry at salk.edu (Terry Sejnowski) Date: Tue, 7 Jan 2003 14:58:04 -0800 (PST) Subject: Telluride Neuromorphic Engineering Workshop Message-ID: <200301072258.h07Mw4g70837@purkinje.salk.edu> ------------------------------------------------------------------------ NEUROMORPHIC ENGINEERING WORKSHOP Sunday, JUNE 29 - Saturday, JULY 19, 2003 TELLURIDE, COLORADO http://www.ini.unizh.ch/telluride/ ------------------------------------------------------------------------ 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 the annual three week "Telluride Workshop and Summer School on Neuromorphic Engineering" that will be held in Telluride, Colorado from Sunday, June 29 to Saturday, July 19, 2002. The application deadline is FRIDAY, MARCH 14, and application instructions are described at the bottom of this document. Like each of these workshops that have taken place since 1994, the 2002 Workshop and Summer School on Neuromorphic Engineering, sponsored by the National Science Foundation, the Whitaker Foundation, the Office of Naval Research, the Defence Advanced Research Projects Agency, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology, was an exciting event and a great success. We strongly encourage interested parties to browse through the previous workshop web pages located at: http://www.ini.unizh.ch/telluride For a discussion of the underlying science and technology and a report on the 2001 workshop, see the September 20, 2001 issue of "The Economist": http://www.economist.com/science/tq/displayStory.cfm?Story_ID=779503 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, vision, speech understanding and robotics. 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 school 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, Kheperas, LEGO robots, and biobugs), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. 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. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control * central pattern generator * robotics * swarm 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. 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. This year we will also have *200* biobugs, kindly donated by the WowWee Toys division of Hasbro in Hong Kong. B.I.O.-Bugs, short for Bio-mechanical Integrated Organisms, are autonomous creatures, each measuring about one foot and weighing about one pound (www.wowwee.com/biobugs/biointerface.html). This will permit us to carry out experiments in collective/swarm robotics. LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350 miles). Great Lakes Aviation and America West Express 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 PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do NOT rent a car. Bring hiking boots, warm clothes, rain gear 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 mid April 2003. 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, Affiliation, valid e-mail address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Description of 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 e-mail: telluride at salk.edu FAX: (858) 587 0417 APPLICATION DEADLINE: MARCH 14, 2003 From nurban at cmu.edu Tue Jan 7 17:35:55 2003 From: nurban at cmu.edu (Nathan Urban) Date: Tue, 7 Jan 2003 17:35:55 -0500 Subject: Postdoctoral position: Physiology and modeling in the olfactory system Message-ID: <006e01c2b69d$241b3a00$712a0280@bio.cmu.edu> Postdoctoral position available immediately for combined physiological and computational studies of the neural circuitry mediating lateral inhibition in the mammalian olfactory system. This position is being offered jointly by Dr. Bard Ermentrout (Department of Mathematics, University of Pittsburgh) and Dr. Nathan Urban (Department of Biological Sciences, Carnegie Mellon University). The project involves the physiological study of the short term dynamics of lateral inhibitory connections between pairs of mitral cells, and the incorporation of these data into computational models of olfactory bulb in order to better understand the transformation of spatiotemporal patterns of glomerular activation by the circuitry of the olfactory bulb. Candidates should have strong interest in both physiological and computational approaches to the study of the olfactory system, but need not have experience in both these areas. Physiological studies will include whole-cell recordings from pairs of connected neurons in olfactory bulb slice preparations and optical recordings using calcium-sensitive dyes. Computational studies may include multicompartmental models of mitral cells and small network models. This position is funded for up to 3 years, and a highly competitive salary is available for qualified candidates. Pittsburgh is a medium-sized city with a relatively low cost of living and many of the amenities and cultural opportunities of a larger city (http://www.city.pittsburgh.pa.us/). The Neuroscience community in Pittsburgh is large and very diverse with more than 100 faculty members affiliated with the Center for Neuroscience at the University of Pittsburgh (CNUP, http://cnup.neurobio.pitt.edu/). Successful candidates would also have the opportunity to join the Center for the Neural Basis of Cognition (CNBC, http://www.cnbc.cmu.edu/) which is a joint University of Pittsburgh/CMU center that involves 70 Faculty from the two Universities. Interested candidates should send (preferably via e-mail) their c.v. and the names and addresses of three references to Professor Bard Ermentrout, Department of Mathematics, University of Pittsburgh Pittsburgh, PA 15260 e-mail: bard+ at pitt.edu. For more information contact: Dr. Bard Ermentrout bard+ at pitt.edu http://www.pitt.edu/~phase/ or Dr. Nathan Urban nurban at cmu.edu http://www.andrew.cmu.edu/user/nurban/Lab_pages/ From Jean-Philippe.Vert at mines.org Wed Jan 8 06:37:42 2003 From: Jean-Philippe.Vert at mines.org (Jean-Philippe Vert) Date: Wed, 08 Jan 2003 12:37:42 +0100 Subject: Wrokshop: kernel methods in computational biolog Message-ID: <3E1C0D86.3070904@mines.org> ******************************************************* ** Workshop: Kernel methods in computational biology ** ** Harnack-Haus, Berlin, April 14, 2003 ** ** http://cg.ensmp.fr/~vert/kmb03 ** ******************************************************* ** Presentation ** Computational biology aims at processing, analyzing and making sense out of huge amount of data produced by high-throughput technologies such as DNA sequencing technologies, DNA and protein microarrays, mass spectrometry or yeast two-hybrid systems. These data are heterogeneous by nature (vectors, strings, graphs...), and often noisy and high-dimensionnal. Kernel methods, such as support vector machines, are promising tools in this context, combining good performances with the ability to manipulate virtually any type of objects thanks to the kernel trick. A number or kernel functions for biological objects have been proposed recently, with encouraging results on several classification issues. The goal of this one-day workshop (which follows the Research in Computational Molecular Biology RECOMB 2003 conference) is to review the state-of-the-art in the application of kernel methods to biology in order to highlight promising research directions, and to foster communication between the computational biology and machine learning communities. No prior knowledge in kernel methods is expected: we explicitly encourage participation of researchers in computational biology interested in new algorithms and tools to process post-genomics data. The workshop will begin with a tutorial on kernel methods. Invited speakers include Nello Cristianini, William S. Noble, Yann Guermeur, Tommi Jaakkola, Imre Kondor, Christina Leslie, Alex Smola, Chris Watkins. ** Organizers ** Bernhard Schoelkopf Koji Tsuda Jean-Philippe Vert ** Call for paper ** We are accepting submissions for oral and/or poster presentation. The presentation should be related to the development of kernel methods for problems in biology or computational biology. Please submit a 2-pages abstract to koji.tsuda at aist.go.jp , in PS or PDF format. Submission deadline is March 14th, 2003. ** For more information, please check the workshop homepage ** http://cg.ensmp.fr/~vert/kmb03/ From fjavier at usp.br Wed Jan 8 20:12:37 2003 From: fjavier at usp.br (Javier Ropero) Date: Wed, 08 Jan 2003 23:12:37 -0200 Subject: [corrected] Neural networks models of brain disease, plasticity and rehabilitation [corrected version] Message-ID: <3.0.5.32.20030108231237.00862c30@pop.usp.br> [ Due to a software glitch, this announcement was truncated twice. I'm hoping the third time is successful. -- Dave Touretzky ] ================================ Dear Colleagues: Connectionist models for understanding brain disease (from trauma and degenerative illnesses to psychiatric disorders) constitute a new paradigm of enormous relevance that is shyly looking for its place in the medical arena. As the organizer of a KES2003 session on neural networks and brain disease, I would like to invite you to discuss with us about this interesting field of research by submitting your contribution. I would be very grateful if you could let know another interested researchers about this session. Looking forward to hearing from you. With my best wishes Javier Ropero 7th International Conference on Knowledge-Based Intelligent Information & Engineering Systems 3, 4 & 5 September 2003, St Anne's College, University of Oxford, U.K. Call for Papers : Neural networks models of brain disease, plasticity and rehabilitation Topic Neural networks models that were originally intended for engineering purposes are recently becoming a useful paradigm for understanding the human brain. The more biological the neural network, the more the number of its possible malfunctions that are similar to those in the real brain. As a consequence neural networks malfunction can be used as a metaphor for brain disease. These diseases range from brain injure like haemorrhage to psychiatric disorders like delusions [1], schizophrenia or bipolar and obsessive-compulsive disorders [2]. Drug addiction, alcohol abuse or even criminal tendencies can, in principle, be modelled by neural networks. Helped by computational neural models it is possible to find new approaches to healing and rehabilitation. Plasticity is a property of the human brain that potentially allows brain damaged persons to return to normality by means of rehabilitation. Rehabilitation methods can be benefited by knowing and applying the laws of brain plasticity previously tested in neural networks. Conversely, brain disease is a prelude of the failures that complex brain-like machines could undergo in the next decades. [1] Ropero Pel?ez, J. (2000) Towards a neural network based therapy for hallucinatory disorders. Neural Networks, 2000 Special Issue, 13(2000), 1047-1061. [2] Neural networks and psychopathology - connectionist models in practice and Research. Edited by Dan J. Stein and Jacques Ludik. Cambridge University Press. Instructions for Authors Only electronic copies of the papers in Microsoft Word, PDF or Postscript forms are acceptable for review purposes and must be sent to the session chair. However, please note that you will be required to send hard copy of the final version of your paper, if it is accepted; electronic submission of final papers is not allowed. Papers must correspond to the requirements detailed in the Instructions to Authors which will be placed on the Conference Web Site, http://www.kesinternational.com/kes2003 or http://www.bton.ac.uk/kes/kes2003 All papers must be presented by one of the authors, who must pay fees. Publication The Conference Proceedings will be published by a major publisher, for example IOS Press of Amsterdam. Extended versions of selected papers will be considered for publication in the International Journal of Knowledge-Based Intelligent Engineering Systems, www.bton.ac.uk/kes/journal/ Important Dates Deadline for submission intention : February 15, 2002 Deadline for receipt of papers by Session Chair : March 15, 2003 Notification of acceptance : April 1, 2003 Camera-ready papers to session chair by : April 15, 2003 (Session Chair must send final camera-ready papers to reach to KES Secretariat by 1 May 2003 or they will not appear in the proceedings). Contact Details Javier Ropero Pel?ez Phone: 55-11-36620847 Email: fjavier at usp.br From fjavier at usp.br Wed Jan 8 20:12:37 2003 From: fjavier at usp.br (Javier Ropero) Date: Wed, 08 Jan 2003 23:12:37 -0200 Subject: Neural networks models of brain disease, plasticity and rehabilitation [corrected version] Message-ID: <3.0.5.32.20030108231237.00862c30@pop.usp.br> Dear Colleagues: Connectionist models for understanding brain disease (from trauma and degenerative illnesses to psychiatric disorders) constitute a new paradigm of enormous relevance that is shyly looking for its place in the medical arena. As the organizer of a KES2003 session on neural networks and brain disease, I would like to invite you to discuss with us about this interesting field of research by submitting your contribution. I would be very grateful if you could let know another interested researchers about this session. Looking forward to hearing from you. With my best wishes Javier Ropero 7th International Conference on Knowledge-Based Intelligent Information & Engineering Systems 3, 4 & 5 September 2003, St Anne's College, University of Oxford, U.K. Call for Papers : Neural networks models of brain disease, plasticity and rehabilitation Topic Neural networks models that were originally intended for engineering purposes are recently becoming a useful paradigm for understanding the human brain. The more biological the neural network, the more the number of its possible malfunctions that are similar to those in the real brain. As a consequence neural networks malfunction can be used as a metaphor for brain disease. These diseases range from brain injure like haemorrhage to psychiatric disorders like delusions [1], schizophrenia or bipolar and obsessive-compulsive disorders [2]. Drug addiction, alcohol abuse or even criminal tendencies can, in principle, be modelled by neural networks. Helped by computational neural models it is possible to find new approaches to healing and rehabilitation. Plasticity is a property of the human brain that potentially allows brain damaged persons to return to normality by means of rehabilitation. Rehabilitation methods can be benefited by knowing and applying the laws of brain plasticity previously tested in neural networks. Conversely, brain disease is a prelude of the failures that complex brain-like machines could undergo in the next decades. [1] Ropero Pel?ez, J. (2000) Towards a neural network based therapy for hallucinatory disorders. Neural Networks, 2000 Special Issue, 13(2000), 1047-1061. [2] Neural networks and psychopathology - connectionist models in practice and Research. Edited by Dan J. Stein and Jacques Ludik. Cambridge University Press From zaki23 at pi.titech.ac.jp Fri Jan 10 02:20:22 2003 From: zaki23 at pi.titech.ac.jp (K.yamazaki) Date: Fri, 10 Jan 2003 16:20:22 +0900 Subject: paper announcement Message-ID: Dear connectionists, I am very glad to introduce that the following paper will appear in Neural Networks, K.Yamazakai, S.Watanabe, Singularities in mixture models and upper bounds of stochastic complexity http://watanabe-www.pi.titech.ac.jp/~zaki23/ which might be of interest to the readers of connectionists. The electric paper "nnk02011-RR.pdf(or ps)" is available on the above URL. Best regards, Keisuke Yamazaki ------------------------------------------- Keisuke Yamazaki Tokyo Institute of Technology http://watanabe-www.pi.titech.ac.jp/~zaki23 zaki23 at pi.titech.ac.jp From fjavier at usp.br Wed Jan 8 20:12:37 2003 From: fjavier at usp.br (Javier Ropero) Date: Wed, 08 Jan 2003 23:12:37 -0200 Subject: Neural networks models of brain disease, plasticity and rehabilitation Message-ID: <3.0.5.32.20030108231237.00862c30@pop.usp.br> Dear Colleagues: Connectionist models for understanding brain disease (from trauma and degenerative illnesses to psychiatric disorders) constitute a new paradigm of enormous relevance that is shyly looking for its place in the medical arena. As the organizer of a KES2003 session on neural networks and brain disease, I would like to invite you to discuss with us about this interesting field of research by submitting your contribution. I would be very grateful if you could let know another interested researchers about this session. Looking forward to hearing from you. With my best wishes Javier Ropero 7th International Conference on Knowledge-Based Intelligent Information & Engineering Systems 3, 4 & 5 September 2003, St Anne's College, University of Oxford, U.K. Call for Papers : Neural networks models of brain disease, plasticity and rehabilitation Topic Neural networks models that were originally intended for engineering purposes are recently becoming a useful paradigm for understanding the human brain. The more biological the neural network, the more the number of its possible malfunctions that are similar to those in the real brain. As a consequence neural networks malfunction can be used as a metaphor for brain disease. These diseases range from brain injure like haemorrhage to psychiatric disorders like delusions [1], schizophrenia or bipolar and obsessive-compulsive disorders [2]. Drug addiction, alcohol abuse or even criminal tendencies can, in principle, be modelled by neural networks. Helped by computational neural models it is possible to find new approaches to healing and rehabilitation. Plasticity is a property of the human brain that potentially allows brain damaged persons to return to normality by means of rehabilitation. Rehabilitation methods can be benefited by knowing and applying the laws of brain plasticity previously tested in neural networks. Conversely, brain disease is a prelude of the failures that complex brain-like machines could undergo in the next decades. [1] Ropero Pel?ez, J. (2000) Towards a neural network based therapy for hallucinatory disorders. Neural Networks, 2000 Special Issue, 13(2000), 1047-1061. [2] Neural networks and psychopathology - connectionist models in practice and Research. Edited by Dan J. Stein and Jacques Ludik. Cambridge University Press From smola at axiom.anu.edu.au Fri Jan 10 09:19:58 2003 From: smola at axiom.anu.edu.au (Alex Smola) Date: Sat, 11 Jan 2003 01:19:58 +1100 (EST) Subject: Machine Learning Summer School, February 2-14, 2003, ANU in Canberra Message-ID: We would like to inform you that The Australian National University will be hosting a Machine Learning Summer School. The Summer School is intended for students and researchers alike, who are interested in Machine Learning. Its goal is to present some of the topics which are at the core of modern Learning Theory. The school will be held in the Australian National University, Canberra, Australia between the 2nd and the 14th of February, 2003. During this time, we shall present three courses of 6 hours, each one covering one of the topics listed below. In addition, there will be special lectures which may focus on additional topics and which will provide background knowledge in machine learning and statistics. Our aim is to cover much of the spectrum of Machine Learning, from theory to practice. Courses: Information Geometry (Shun-Ichi Amari, RIKEN) Concentration Inequalities (Gabor Lugosi, Pompeu Fabra University) Unsupervised Learning (Zoubin Ghahramani, University College London) Short Courses: Eleazar Eskin, Hebrew University Peter Hall, Australian National Univesity Markus Hegland, Australian National University John Lloyd, RSISE, Australian National University Shahar Mendelson, RSISE, Australian National University Mike Osborne, MSI, Australian National University Gunnar Rtsch, RSISE, Australian National University Alex Smola, RSISE, Australian National University S.V.N. Vishwanathan, NICTA Bob Williamson, RSISE, Australian National University Upon request, attendants of the summer school are eligible to receive a Graduate Course Award of the ANU. For further details on obtaining the course award, please contact Michelle.Moravec at anu.edu.au before the commencement of the summer school. The registration cost of the school is $1600 per person for participants from industry and $600 per person for academics. Students are eligible for a further discount and may register for $200 per person. All prices are in Australian dollars and include GST. For further information (including registration form), visit our website at or send email to Michelle.Moravec at anu.edu.au. Regards, Alex Smola and Gunnar Raetsch ''~`` ( o o ) +------------------------------.oooO--(_)--Oooo.----------------------------+ | Alexander J. Smola http://mlg.anu.edu.au/~smola | | Australian National University Alex.Smola at anu.edu.au | | Research School for Information Tel: (+61) 2 6125-8652 | | Sciences and Engineering .oooO Fax: (+61) 2 6125-8651 | | Canberra, ACT 0200 (#00120C) ( ) Oooo. Cel: (+61) 410 457 686 | +---------------------------------\ (----( )------------------------------+ \_) ) / (_/ From wsenn at cns.unibe.ch Fri Jan 10 09:57:45 2003 From: wsenn at cns.unibe.ch (Walter Senn) Date: Fri, 10 Jan 2003 15:57:45 +0100 Subject: Hebb in perspective (Biol Cyb, issue 5-6, 2002) Message-ID: <3E1EDF69.5EED94E9@cns.unibe.ch> Dear colleagues We would like to draw your attention to the special issue "Hebb in perspective" of Biological Cybernetics, a collection of survey and research articles on Hebbian learning. It brings together experimental and theoretical aspects of synaptic plasticity in neocortex and hippocampus, with particular emphasis on spike-timing dependent plasticity. Leo van Hemmen and Walter Senn Biological Cybernetics Volume 87, Issue 5-6 (2002) http://link.springer.de/link/service/journals/00422/tocs/t2087005.htm or http://link.springer-ny.com/link/service/journals/00422/tocs/t2087005.htm (Abstracts freely downloadable) J. Leo van Hemmen, Walter Senn: Editorial: Hebb in perspective http://www.cns.unibe.ch/~wsenn/#pub, see also http://www.cns.unibe.ch/~wsenn/biol_cyb_index.html Guo-Qiang Bi: Spatiotemporal specificity of synaptic plasticity: cellular rules and mechanisms. http://www.neurobio.pitt.edu/faculty_lab/bi_pub.htm Michael P. Kilgard, Pritesh K. Pandya, Navzer D. Engineer, Raluca Moucha: Cortical network reorganization guided by sensory input features http://www.utdallas.edu/~kilgard/cv.html#PUBLICATIONS Walter Senn: Beyond spike timing: the role of nonlinear plasticity and unreliable synapses http://www.cns.unibe.ch/~wsenn/#pub Colin Lever, Neil Burgess, Francesca Cacucci, Tom Hartley, John O'Keefe: What can the hippocampal representation of environmental geometry tell us about Hebbian learning? http://www.icn.ucl.ac.uk/groups/JO/mempages/neil/papers/ Uma R. Karmarkar, Mark T. Najarian, Dean V. Buonomano: Mechanisms and significance of spike-timing dependent plasticity http://www.neurobio.ucla.edu/~dbuono/publications.html Harel Z. Shouval, Gastone C. Castellani, Brian S. Blais, Luk C. Yeung, Leon N Cooper: Converging evidence for a simplified biophysical model of synaptic plasticity http://www.physics.brown.edu/users/faculty/shouval/research.html Patrick D. Roberts, Curtis C. Bell: Spike timing dependent synaptic plasticity in biological systems http://www.proberts.net/research/ Wulfram Gerstner, Werner M. Kistler: Mathematical formulations of Hebbian learning http://diwww.epfl.ch/~gerstner/wg_pub.html Werner M. Kistler: Spike-timing dependent synaptic plasticity: a phenomenological framework http://www-fgg.eur.nl/anat/kistler/ C. Leibold, J.L. van Hemmen: Mapping time http://www1.physik.tu-muenchen.de/lehrstuehle/T35/t35/german/hebblearning.html Roland E. Suri, Terrence J. Sejnowski: Spike propagation synchronized by temporally asymmetric Hebbian learning http://www.cnl.salk.edu/~suri/ Adam Kepecs, Mark C.W. van Rossum, Sen Song, Jesper Tegner: Spike-timing-dependent plasticity: common themes and divergent vistas http://homepages.inf.ed.ac.uk/mvanross/ Stefano Fusi: Hebbian spike-driven synaptic plasticity for learning patterns of mean firing rates http://www.cns.unibe.ch/~fusi/#pub Jesper Tegner, Albert Compte, Xiao-Jing Wang: The dynamical stability of reverberatory neural circuits http://www.wanglab.brandeis.edu/webpages/publications.html From pizzi at ee.umanitoba.ca Fri Jan 10 11:57:04 2003 From: pizzi at ee.umanitoba.ca (Pizzi, Nick) Date: Fri, 10 Jan 2003 10:57:04 -0600 Subject: POSTDOCTORAL RESEARCH OPPORTUNITY - BIOMEDICAL DATA ANALYSIS Message-ID: <9D8DFE8AD5FCD21189990004ACE5276603E3DC72@nrcwpgex1.ibd.nrc.ca> POSTDOCTORAL RESEARCH OPPORTUNITY - BIOMEDICAL DATA ANALYSIS GRANULAR COMPUTING AND SPARSE CODING FOR THE MODELING, ANALYSIS, AND CLASSIFICATION OF HIGH-DIMENSIONAL BIOMEDICAL DATA Pending final approval, a postdoctoral position is available at the University of Manitoba to investigate sparse coding strategies for the modeling, analysis, and classification of high-dimensional biomedical data. This is an NSERC-funded strategic research project directed by Prof. W. Pedrycz (U. Alberta), Dr. N. Pizzi (National Research Council & U. Manitoba), and Dr. M. Alexander (National Research Council). The position, which will focus on sparse coding analysis, is for a one-year term with a possible one year renewal. Biomedical data classification demands a reduction of the original data's dimensionality without sacrificing domain-specific significance. Sparse representation (SR) addresses the former issue and granular computing the latter. The fundamental tasks of feature extraction, classification, and noise/artefact suppression all benefit by being carried out in a sparse domain. Since wavelets have become a powerful computational tool in signal processing, there has been a growing interest in the SR of data. The transformations that accomplish optimal sparseness will depend on the data itself, and may, for example, be defined by optimizing its entropy over a finitely- (or infinitely) over-complete "dictionary" of basis functions. The computational task of finding the optimal SR for given data is accomplished in two stages: (i) Defining an over-complete dictionary by constructing a sufficiently broad class of basis functions; (ii) Projecting the data onto a particular subset of the over-complete dictionary that optimizes a pre-defined measure of sparseness. Computationally efficient algorithms need to be considered for (i), and the optimization procedure for (ii) may in some cases involve substantial computation. Both (i) and (ii) are topics of ongoing research. Required background: - Recent Ph.D. graduate - Training and/or research experience in signal processing - Background and/or experience in wavelets and their application to data analysis - Training and/or research experience in statistics, including practical knowledge of analysis of large datasets - Proficiency in C/C++ and experience with using MatLab/IDL Please send a curriculum vitae, expression of interest (including earliest start date), and the names and e-mail addresses of two references to Dr. Pizzi at pizzi at nrc.ca. Your curriculum vitae should include a list of recent publications. Please outline your interest in this project, how it is related to work that you have done, and what special expertise you would bring to the project. ------------------------------------------------------------------- Nicolino Pizzi, PhD pizzi at nrc.ca Senior Research Officer Institute for Biodiagnostics National Research Council Canada 435 Ellice Avenue Ph: +1 204 983 8842 Winnipeg MB, R3B 1Y6, Canada Fx: +1 204 984 5472 Adjunct Professor Computer Science Department & Electrical and Computer Engineering Department University of Manitoba http://www.ee.umanitoba.ca/~pizzi ------------------------------------------------------------------- From barth at inb.uni-luebeck.de Fri Jan 10 16:59:24 2003 From: barth at inb.uni-luebeck.de (Erhardt Barth) Date: Fri, 10 Jan 2003 22:59:24 +0100 Subject: PhD positions in visual information processing Message-ID: <14713405355.20030110225924@inb.uni-luebeck.de> The Institute for Neuro- and Bioinformatics, University of Luebeck, Germany, seeks Research Scientists (PhD students) for an interdisciplinary project funded by the German Federal Ministry of Education and Research. The successful candidate will join an interdisciplinary research team and closely collaborate with two German companies. The goal of the project is to develop new forms of visual communication and interaction based on eye-tracking and gaze-contingent display. This involves high-speed image processing, tracking, and graphics, as well as modeling of visual function. Further information can be found at www.inb.uni-luebeck.de/Itap . We expect a strong background in Computer Science, Electrical Engineering, or Physics and enthusiasm for interdisciplinary research. Programming skills (mainly C++) would be a plus. We offer exciting new research topics and the possibility to obtain a PhD in computer science. The positions are initially funded for 36 month. The salary will be at the level of BAT IIa (appr. 38.000 EURO/year before tax). Please send applications including your curriculum vitae, a statement of interests, and names of references to Dr. Erhardt Barth (barth at inb.uni-luebeck.de) with a CC to Prof. Thomas Martinetz (martinetz at informatik.uni-luebeck.de ). Application deadline is February 15th. For further information contact E. Barth. From David.Cohn at acm.org Mon Jan 13 13:06:53 2003 From: David.Cohn at acm.org (David 'Pablo' Cohn) Date: 13 Jan 2003 10:06:53 -0800 Subject: jmlr-announce: ICML Special Issue Message-ID: <1042481214.32665.2332.camel@bitbox.corp.google.com> The Journal of Machine Learning Research is very pleased to announce publication of a Special Issue of invited papers from the Eighteenth International Conference on Machine Learning (ICML2001). This issue, edited by Carla Brodley and Andrea Danyluk, contains twelve papers expanded from their ICML form into fully refereed JMLR contributions. We believe they capture both the breadth and spirit of the machine learning conference and community. The new issue is available online at http://www.jmlr.org. David Cohn Managing Editor, JMLR --------------------------------------- Special Issue on the Eighteenth International Conference on Machine Learning (ICML2001) Carla E. Brodley, Andrea P. Danyluk; 3(Dec):619, 2002. Efficient Algorithms for Decision Tree Cross-validation Hendrik Blockeel, Jan Struyf; 3(Dec):621-650, 2002. Multiple-Instance Learning of Real-Valued Data Daniel R. Dooly, Qi Zhang, Sally A. Goldman, Robert A. Amar; 3(Dec):651-678, 2002. Learning Probabilistic Models of Link Structure Lisa Getoor, Nir Friedman, Daphne Koller, Ben Taskar; 3(Dec):679-707, 2002. The Representational Power of Discrete Bayesian Networks Charles X. Ling, Huajie Zhang; 3(Dec):709-721, 2002. The Set Covering Machine Mario Marchand, John Shawe-Taylor; 3(Dec):723-746, 2002. Coupled Clustering: A Method for Detecting Structural Correspondence Zvika Marx, Ido Dagan, Joachim M. Buhmann, Eli Shamir; 3(Dec):747-780, 2002. Some Greedy Learning Algorithms for Sparse Regression and Classification with Mercer Kernels Prasanth B. Nair, Arindam Choudhury, Andy J. Keane; 3(Dec):781-801, 2002. Lyapunov Design for Safe Reinforcement Learning Theodore J. Perkins, Andrew G. Barto; 3(Dec):803-832, 2002. Finding the Most Interesting Patterns in a Database Quickly by Using Sequential Sampling Tobias Scheffer, Stefan Wrobel; 3(Dec):833-862, 2002. Stopping Criterion for Boosting-Based Data Reduction Techniques: from Binary to Multiclass Problem Marc Sebban, Richard Nock, St?phane Lallich; 3(Dec):863-885, 2002. Learning to Construct Fast Signal Processing Implementations Bryan Singer, Manuela Veloso; 3(Dec):887-919, 2002. Policy Search using Paired Comparisons Malcolm J. A. Strens, Andrew W. Moore; 3(Dec):921-950, 2002. From malchiodi at dsi.unimi.it Mon Jan 13 13:13:02 2003 From: malchiodi at dsi.unimi.it (Dario Malchiodi) Date: Mon, 13 Jan 2003 19:13:02 +0100 Subject: WIRN 2003 - Call for papers Message-ID: ####################################################### WIRN 2003 C A L L F O R P A P E R S FIRST ANNOUNCEMENT %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% The 14-th Italian Workshop on Neural Networks and "Premio Caianiello" competition June 5 to 7, 2003,Vietri Sul Mare, Salerno ITALY ************************************************************************ ****** Homepage: http://siren.dsi.unimi.it/indice2.html ************************************************************************ * Sponsors International Institute for Advanced Scientific Studies (IIASS) "E.R. Caianiello" Dip. di Fisica "E.R. Caianiello", University of Salerno Dip. di Matematica ed Informatica, University of Salerno Dip. di Scienze dell'Informazione, University of Milano Societa' Italiana Reti Neuroniche (SIREN) IEEE Neural Network Council INNS/SIG Italy Istituto Italiano per gli Studi Filosofici, Napoli Provincia di Salerno Topics Mathematical Models, Architectures and Algorithms, Hardware and Software Design, Hybrid Systems, Pattern Recognition and Signal Processing, Industrial and Commercial Applications, Fuzzy Tecniques for Neural Networks Schedule Papers Due: February 28, 2003 Replies to Authors: April 30, 2003 Revised Papers Due: June 15, 2003 The three-day conference, to be held in the I.I.A.S.S., will feature both introductory tutorials and original, refereed papers, to be published by an International Publishing Company . Official languages are Italian and English, while papers must be in English. More detailed instructions and the On-Line Submission Form can be found from the WIRN 2003 homepage http://siren.dsi.unimi.it/indice2.html. During the Workshop the "Premio E.R. Caianiello" will be assigned to the best Ph.D. thesis in the area of Neural Nets and related fields of Italian researchers. The amount is of 1.000 Euros. The interested researchers (with the Ph.D degree obtained after January 1, 2000 and before March 31 2003) must send 3 copies of a c.v. and of the thesis to "Premio Caianiello" WIRN 2003 c/o IIASS before April 30,2003. A candidate can submit his Ph. D. thesis at most twice. Only SIREN associated are admitted (subscription forms can be downloaded from the SIREN site). For more information, contact the Secretary of I.I.A.S.S. "E.R. Caianiello", Via G.Pellegrino, 19, 84019 Vietri Sul Mare (SA), ITALY Tel. +39 89 761167 Fax +39 89 761189 E-Mail robtag at unisa.it Organizing - Scientific Committee B. Apolloni (Univ. Milano), A. Bertoni (Univ. Milano), N. A. Borghese (Univ. Milano), D. D. Caviglia (Univ. Genova), P. Campadelli (Univ. Milano), A. Chella (Univ. Palermo), A. Colla (ELSAG Genova), A. Esposito (I.I.A.S.S.), M. Frixione (Univ. Salerno), C. Furlanello (ITC-IRST Trento), G. M. Guazzo (I.I.A.S.S.), M. Gori (Univ. Siena), M. Marinaro (Univ. Salerno), F. Masulli (Univ. Pisa), C. Morabito (Univ. Reggio Calabria), P. Morasso (Univ. Genova), G. Orlandi (Univ. Roma), T. Parisini (Univ. Trieste), E. Pasero (Politecnico Torino), A. Petrosino (CNR Napoli), V. Piuri (Politecnico Milano), R. Serra (CRA Montecatini Ravenna), F. Sorbello (Univ. Palermo), A. Sperduti (Univ. Pisa), R. Tagliaferri (Univ. Salerno) -- From d.polani at herts.ac.uk Tue Jan 14 14:54:45 2003 From: d.polani at herts.ac.uk (Daniel Polani) Date: Tue, 14 Jan 2003 20:54:45 +0100 Subject: 2nd Call for Papers: Evolvability and Sensor Evolution Symposium Message-ID: <15908.27397.830992.168606@perm.feis.herts.ac.uk> //////////////////////////////////////////////////////////////////////// Call for Papers & Participation: EPSRC Network on Evolvability in Biological & Software Systems Evolvability and Sensor Evolution Symposium //////////////////////////////////////////////////////////////////////// sponsored by The Natural Computation Research Group (Univ. of Birmingham) The University of Hertfordshire Adaptive Systems Research Group EPSRC Network on Evolvability in Biological and Software Systems 24-25 April 2003 (Thursday-Friday), University of Birmingham, U.K. Invited Speakers: Peter Cariani (Harvard University, USA) Dan-Eric Nilsson (Lund University, Sweden) Mark Nelson (Beckmann Institute, University of Illinois, USA) John Messenger (University of Cambridge, UK) Gareth Jones (University of Bristol, UK) Program Chairs: Julian Miller (University of Birmingham) Daniel Polani (University of Hertfordshire) Co-Organizers: Chrystopher Nehaniv (University of Hertfordshire) Participation: Participation is open to all students, researchers, or industry representatives with interests in evolvability in biological and software systems. Please register by sending an e-mail j.miller at cs.bham.ac.uk giving your name and affiliation. There is no registration fee. For the full call, see web site: http://www.cs.bham.ac.uk/~jfm/evol-sensor.htm From bp1 at cn.stir.ac.uk Wed Jan 15 06:09:59 2003 From: bp1 at cn.stir.ac.uk (Bernd Porr) Date: Wed, 15 Jan 2003 11:09:59 +0000 Subject: Possibility for a PhD Message-ID: <3E254187.80606@cn.stir.ac.uk> Possibility for a PhD (sorry for multiple postings) DEADLINE FOR PRE-APPLICATIONS: Jan.31st. The Computational Neuroscience Group at the University of Stirling is offering a PhD in the field of autonomous robotics. Robotics is seen as a means for understanding the development of intelligence by getting insights about the living from constructing animats. Recent research at our group has focused on the (inner) perspective of the organism or the animat (see "Constructivism"). Thereby feedback from the environment to the animat becomes essential as only the feedback provides information if actions have been successful or not. However, simple reactive feedback control has the disadvantage that it reacts always too late. If you have to rely only on reflexes than you will have to burn your hand before you can pull it away. Predictions of stimuli (here: pain) are essential to improve behaviour. Learning to predict re-actions means that the organism is able to act pro-actively. The above ideas have been implemented in a closed-loop learning-scheme which we call ISO-learning: Isotropic Sequence Order Learning: http://www.cn.stir.ac.uk/predictor/ This type of learning has been so far only been applied to simple tasks (avoiding obstacles, targeting 'food') in order to provide a proof of concept. The PhD-thesis shall explore more complex situations with sequences of reflexes, hierachical structures and/or 'efference-copies'. Other possible areas of research relate to certain forms of preprocessing of the sensor-inputs ("place cells") or to post-processing of the motor-output. The mathematical framework of ISO-learning is control-theory and signal theory. We work with real and simulated robots which we program in C++ and which we modify by adapting the electronics. Knowledge of any of these areas would certainly be helpful for the successful candidate. As ISO-learning has a strong link to control-theory cooperations with the industry are possible. This announcement is meant to attract possible candidates, so at this stage a formal application is not required. If you are interested we would ask you to send your informal but complete application (CV, background, list of publications, statement of specific interest, etc., etc.) to us. We would then contact you about how to proceed further. Please feel free to contact us in case of any questions. Bernd Porr and Florentin Wrgtter Contact: Prof Florentin Wrgtter: worgott at cn.stir.ac.uk Bernd Porr: bp1 at cn.stir.ac.uk Computational Neuroscience Dept of Psychology Stirling FK9 4LA Scotland, UK Fax: +44 (0) 1786 46-7641 Tel: +44 (0) 1786 46-6369/6378 -- http://www.cn.stir.ac.uk From terry at salk.edu Wed Jan 15 17:07:26 2003 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 15 Jan 2003 14:07:26 -0800 (PST) Subject: NEURAL COMPUTATION 15:2 Message-ID: <200301152207.h0FM7QD79176@purkinje.salk.edu> Neural Computation - Contents - Volume 15, Number 2 - February 1, 2003 LETTERS Interspike Interval Correlations, Memory, Adaptation, and Refractoriness in a Leaky Integrate-and-Fire Model with Threshold Fatigue Maurice J. Chacron, Khashayar Pakdaman and Andre Longtin Reliability of Spike Timing Is a General Property of Spiking Model Neurons Romain Brette and Emmanuel Guigon The Dynamic Neural Filter: A Binary Model of Spatiotemporal Coding Brigitte Quenet and David Horn Modeling Short-Term Synaptic Depression in Silicon Malte Boegerhausen, Pascal Suter, and Shih-Chii Liu Dictionary Learning Algorithms for Sparse Representation Kenneth Kreutz-Delgado, Joseph F. Murray, Bhaskar D. Rao, Kjersti Engan, Te-Won Lee and Terrence J. Sejnowski Spatiochromatic Receptive Field Properties Derived From Information-Theoretic Analyses of Cone Mosaic Responses to Natural Scenes Eizaburo Doi, Toshio Inui, Te-Won Lee, Thomas Wachtler and Terrence J. Sejnowski Linear Geometric ICA: Fundamentals and Algorithms Fabian J. Theis, Andreas Jung, Carlos G. Puntonet and Elmar W. Lang Equivalence of Backpropagation and Contrastive Hebbian Learning in a Layered Network Xiaohui Xie and H. Sebastatian Seung Indexed Families of Functionals and Gaussian Radial Basis Functions Irwin W. Sandberg Efficient Greedy Learning of Gaussian Mixture Models J. J. Verbeek, N. Vlassis and B. Krose SMO Algorithm for Least-Squares SVM Formulations S. S. Keerthi and S. K. Shevade ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2003 - VOLUME 15 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $95 $101.65 $143 Institution $590 $631.30 $638 * 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 h.jaeger at iu-bremen.de Thu Jan 16 12:27:30 2003 From: h.jaeger at iu-bremen.de (Herbert Jaeger) Date: Thu, 16 Jan 2003 18:27:30 +0100 Subject: Job offer: stochastic system modeling Message-ID: <3E26EB82.6060001@iu-bremen.de> The School of Engineering and Science of International University Bremen (www.iu-bremen.de) invites applications for a Ph.D. or Post-Doc Position in Computational Science The candidate should have a strong background in modeling stochastic systems with machine learning techniques. Specifically, his/her research will be concerned with observable operator models (OOMs, see http://www.ais.fraunhofer.de/INDY/oom_research.html). OOMs are superficially similar to hidden Markov models, but arise from operator/state methods related to the quantum mechanics formalism. OOMs and related models are currently being investigated in areas as diverse as theoretical physics (J.P. Crutchfield, H. Honerkamp) and learning methods for robots (R. Sutton). The rigorous mathematical theory underlying OOMs gives rise to new, highly efficient learning algorithms which would be the object of both theoretical and applied research in the offered position. The School of Engineering and Science at IUB offers a research-oriented working environment with an informal and dynamic atmosphere and a high degree of interactions between students, faculty and staff. IUB offers highly competitive salaries based on qualifications and experience. The contract would initially run over 2 years. Interested candidates with a degree in mathematics, computer science, physics, or signal processing and control engineering please direct inquiries and applications to Prof. Herbert Jaeger International University Bremen P.O. Box 750 561 28725 Bremen Germany Electronic submissions may be sent to h.jaeger at iu-bremen.de -- ------------------------------------------------------------------ Dr. Herbert Jaeger International University Bremen Campus Ring 12 28759 Bremen, Germany Phone (+49) 421 200 3215 email h.jaeger at iu-bremen.de http://www.iu-bremen.de/directory/faculty/29979/ http://www.ais.fraunhofer.de/INDY/herbert/ ------------------------------------------------------------------ From hasselmo at bu.edu Thu Jan 16 18:03:35 2003 From: hasselmo at bu.edu (Michael Hasselmo) Date: Thu, 16 Jan 2003 18:03:35 -0500 Subject: [corrected] IJCNN 2003 final call for papers In-Reply-To: Message-ID: FINAL CALL FOR PAPERS (Deadline Approaching) **************************************************************** International Joint Conference on Neural Networks (IJCNN 2003) Portland, Oregon, July 20-24, 2003 http://www.ijcnn.net DEADLINE: January 29, 2003 **************************************************************** Co-sponsored by the International Neural Network Society (INNS) & IEEE Neural Networks Society. The International Joint Conference on Neural Networks provides an overview of state of the art research in Neural Networks, covering a wide range of topics (see topic list below). Paper submission deadline is January 29, 2003. Selected papers will be published in a special issue of the journal Neural Networks, in addition to publication of all papers in the conference proceedings. The IJCNN meeting is organized annually by the International Neural Network Society (INNS) and the IEEE Neural Networks Society. Conference attendees who are INNS or IEEE Neural Networks Society members, or who join one of these societies now will receive a reduced IJCNN conference registration fee, and those who are INNS members will receive the IJCNN special issue for free as part of their annual membership subscription to Neural Networks. Article submission: ------------------------------------ Authors should submit their articles electronically on the conference web site at http://www.ijcnn.net by the conference deadline of January 29, 2003. THE DEADLINE IS APPROACHING. Plenary speakers:=20 ------------------------------------ Kunihiko Fukushima, Tokyo University of Technology, Japan =20 Earl Miller, Massachusetts Institute of Technology, USA Terrence Sejnowski, Salk Institute and UCSD, USA Vladimir Vapnik, NEC Research Labs, USA Christoph von der Malsburg, USC, USA and Univ. Bochum, Germany Special sessions: ------------------------------------ Full schedules for the following sessions are posted on www.ijcnn.net. Csaba Rekeczky and Tamas Roska - Cellular visual microprocessors: Topographic array computing on data flows. Steve Grossberg - Visual cortex: How illusions represent reality Robi Polikar - Incremental Learning Antony Satyadas - Computational Intelligence for Homeland Security. Robert Kozma, Ali Minai and DeLiang Wang - Dynamical Aspects of Information Encoding in Neural Networks. Andreas A. Ioannides and John G. Taylor - Attention and Consciousness in Normal Brains: Theoretical models and phenomenological data from Magnetoencephalography (MEG). Mitra Basu - Biologically inspired/motivated computational models Jim DeLeo and Roberto Tagliaferri - Patient Care and Clinical Decision Support. F. Carlo Morabito and Sameer Antani - Knowledge Discovery, and Image and Signal Processing in Medicine. Harold Szu, Joel Davis, Harold Hawkins =AD Biomimetic Applications Francesco Masulli and Larry Reeker - Bioinformatics. Eduardo Bayro-Corrochano - Geometric Neurocomputing. Robert J. Marks and John Vian - Applications in Aerospace. Tutorials ------------------------------------ Tutorials will take place on Sunday, July 20, 2003. There will be six sequential two hour sessions. A single tutorial fee will pay for attendance of six different tutorials from the list below (the tutorial schedule will be posted on the registration page). Bernard Widrow - Neural control systems Pierre Baldi - Prediction of Protein Structures on a Proteomics Scale Using Machine Learning Approaches Jose C. Principe and Deniz Erdogmus, - Information Theoretic Learning Vladimir Cherkassky - Signal and image denoising using VC learning theory John G. Taylor - Attention and Consciousness as Control System Components in the Brain Martin McKeown - A survey of blind source separation techniques applied to clinical data=20 V. Beiu, J.M. Quintana, M.J. Avedillo - Threshold Logic From TTL To Quantum Computing Eytan Ruppin - Evolutionary Autonomous Agents: A Novel Neuroscience Research Paradigm Antonio Eleuteri, Francesco Masulli, Roberto Tagliaferro - Learning with multiple machines: ECOC models vs Bayesian Framework. Johan Suykens - Least Squares Support Vector Machines Asim Roy - Autonomous Learning: the New Connectionist Algorithms Robert Kozma and Walter J Freeman - Neuropercolation: Dynamical Memory Neural Networks =AD Biological Systems and Computer Implementations Nik Kasabov - Data Mining and Knowledge Discovery Using Adaptive Neural Networks Aurelio Uncini - Processing of audio signal by neural networks Lei Xu - Dependence Structure Mining, Statistical Approaches, and Bayesian Ying-Yang Learning Amie J. O=B9Brien - Fuzzy Logic and Expert Systems: An Introduction with BioMedical Applications Stephen Thaler - AI's Best Bet: The Creativity Machine Paradigm Wang Shoujue - Biomimetic Classifications Broad topics ------------------------------------ Regular oral and poster sessions will include papers in subtopics within the following broad topics. When submitting your paper you must choose two subtopics within these broad topics (see www.ijcnn.net). A. PERCEPTUAL AND MOTOR FUNCTION B. COGNITIVE FUNCTION C. COMPUTATIONAL NEUROSCIENCE D. INFORMATICS E. HARDWARE=20 F. REINFORCEMENT LEARNING AND CONTROL G. DYNAMICS=20 H. THEORY=20 I. APPLICATIONS Organizing committee: ------------------------------------ General Chair: Don Wunsch, University of Missouri - Rolla Program Chair: Michael Hasselmo, Boston University Program co-chairs:=20 DeLiang Wang, Ohio State University Ganesh K. Venayagamoorthy,University of Missouri - Rolla Tutorial co-chairs: F. Carlo Morabito, University of Reggio Calabria, Italy Harold Szu, Office of Naval Research Local Arrangements Chair: George Lendaris, Portland State University Publicity chair: Derong Liu, University of Illinois at Chicago Web chair: Tomasz Cholewo, Lexmark International Inc., Kentucky Exhibits chair: Karl Mathia, Brooks-PRI Automation Inc., California Student travel and volunteer chair: Slawo Wesolkowski, University of Waterloo, Canada International Liason: William N. Howell, Mining and Mineral Sciences Laboratories, Canada Program committee: ------------------------------------------ David Brown, FDA Gail Carpenter, Boston University David Casasent, Carnegie Mellon University Ke Chen , University of Birmingham, UK Michael Denham, University of Plymouth, UK Thomas G. Dietterich, Oregon State University Lee Feldkamp, Ford Motor Company Kunihiko Fukushima, Tokyo University of Technology, Japan Joydeep Ghosh, University of Texas at Austin Steven Grossberg, Boston University Fred Ham, Florida Institute of Technology Ron Harley, Georgia Institute of Technology Bart Kosko, University of Southern California Robert Kozma, University of Memphis Dan Levine, University of Texas at Dallas Xiuwen Liu, Florida State University F. Carlo Morabito, Universita di Reggio Calabria, Italy Ali Minai, University of Cincinnati Catherine Myers, Rutgers University Erikki Oja, Helsinki University of Technology, Finland Jose Principe, University of Florida Danil Prokhorov, Ford Motor Company Harold Szu, Office of Naval Research John Gerald Taylor, University College, London, UK Shiro Usui, Toyohashi Univ. of Technology, Japan Bernie Widrow, Stanford University Lei Xu, The Chinese University of Hong Kong Gary Yen, Oklahoma State University Lotfi Zadeh, University of California, Berkeley Registration: ------------------------------------------ Registration will be possible on the web site at www.ijcnn.net. Registration fees will be: INNS or IEEE Member Pre-reg $425.00 INNS or IEEE Member Onsite $525.00 Nonmember Pre-Reg $525.00 Nonmember Onsite $625.00 Student Pre-Reg $125.00 Student Onsite $175.00 Tutorial INNS or IEEE member Pre Reg $250.00 Tutorial INNS or IEEE member Onsite $300.00 Tutorial Nonmember Pre-Reg $275.00 Tutorial Nonmember Onsite $325.00 Tutorial Student Pre-Reg $125.00 Tutorial Student Onsite $175.00 For more information see the web page at http://www.ijcnn.net **************************************************** Prof. Michael Hasselmo e-mail: hasselmo at bu.edu Department of Psychology Tel: (617) 353-1397 and Program in Neuroscience or (617) 353-1431 Boston University FAX: (617) 353-1424 64 Cummington St. =20 Boston, MA 02215 http://people.bu.edu/hasselmo **************************************************** From nnsp03 at neuro.kuleuven.ac.be Thu Jan 16 06:46:55 2003 From: nnsp03 at neuro.kuleuven.ac.be (Neural Networks for Signal Processing 2003) Date: Thu, 16 Jan 2003 12:46:55 +0100 Subject: NNSP 2003 in Toulouse, France Message-ID: <3E269BAF.47A06B01@neuro.kuleuven.ac.be> 2003 IEEE International Workshop on Neural Networks for Signal Processing September 17-19, 2003 Toulouse, France Paper Submission by April 15 2003 -------------------------------------------http://isp.imm.dtu.dk/nnsp2003/ The thirteenth in a series of IEEE NNSP workshops, sponsored by the IEEE Signal Processing society will be held in Toulouse (www.mairie-toulouse.fr), France. The workshop will feature keynote addresses, technical presentations, and special sessions on * Bio-informatics * Neural Engineering * Aeronautics and a tutorial on Bayesian Learning that is included in the registration. Papers are solicited for, but not limited to, the following areas: Algorithms and Architectures: Artificial neural networks, kernel methods, committee models, Gaussian processes, independent component analysis, and a tutorial on Bayesian Learning that is included in the registration. Papers are solicited for, but not limited to, the following areas: Algorithms and Architectures: Artificial neural networks, kernel methods, committee models, Gaussian processes, independent component analysis, advanced (adaptive, nonlinear) signal processing, (hidden) Markov models, Bayesian modeling, parameter estimation, generalization, optimization, design algorithms. Applications: Speech processing, image processing (computer vision, OCR), multimodal interactions, multi-channel processing, intelligent multimedia and web processing, robotics, sonar and radar, bio-medical engineering, financial analysis, time series prediction, blind source separation, data fusion, data mining, adaptive filtering, communications, sensors, system identification, and other signal processing and pattern recognition applications. Implementations: Parallel and distributed implementation, hardware design, and other general implementation technologies. -------------------------NNSP'2003 webpage: http://isp.imm.dtu.dk/nnsp2003 -------------------------------------------------------------------------- From hasselmo at bu.edu Thu Jan 16 18:03:35 2003 From: hasselmo at bu.edu (Michael Hasselmo) Date: Thu, 16 Jan 2003 18:03:35 -0500 Subject: IJCNN 2003 final call for papers In-Reply-To: Message-ID: FINAL CALL FOR PAPERS (Deadline Approaching) **************************************************************** International Joint Conference on Neural Networks (IJCNN 2003) Portland, Oregon, July 20-24, 2003 http://www.ijcnn.net DEADLINE: January 29, 2003 **************************************************************** Co-sponsored by the International Neural Network Society (INNS) & IEEE Neural Networks Society. The International Joint Conference on Neural Networks provides an overview of state of the art research in Neural Networks, covering a wide range of topics (see topic list below). Paper submission deadline is January 29, 2003. Selected papers will be published in a special issue of the journal Neural Networks, in addition to publication of all papers in the conference proceedings. The IJCNN meeting is organized annually by the International Neural Network Society (INNS) and the IEEE Neural Networks Society. Conference attendees who are INNS or IEEE Neural Networks Society members, or who join one of these societies now will receive a reduced IJCNN conference registration fee, and those who are INNS members will receive the IJCNN special issue for free as part of their annual membership subscription to Neural Networks. Article submission: ------------------------------------ Authors should submit their articles electronically on the conference web site at http://www.ijcnn.net by the conference deadline of January 29, 2003 From dgw at MIT.EDU Fri Jan 17 16:34:13 2003 From: dgw at MIT.EDU (David Weininger) Date: Fri, 17 Jan 2003 16:34:13 -0500 Subject: book announcement--Arbib Message-ID: <200301171634134420@outgoing.mit.edu> I thought readers of the Connectionists List might be interested in this book. For more information, please visit http://mitpress.mit.edu/0262011972/ Thank you! Best, David The Handbook of Brain Theory and Neural Networks second edition edited by Michael A. Arbib Dramatically updating and extending the first edition, published in 1995, the second edition of The Handbook of Brain Theory and Neural Networks presents the enormous progress made in recent years in the many subfields related to the two great questions: How does the brain work? and, How can we build intelligent machines? Once again, the heart of the book is a set of almost 300 articles covering the whole spectrum of topics in brain theory and neural networks. The first two parts of the book, prepared by Michael Arbib, are designed to help readers orient themselves in this wealth of material. Part I provides general background on brain modeling and on both biological and artificial neural networks. Part II consists of "Road Maps" to help readers steer through articles in part III on specific topics of interest. The articles in part III are written so as to be accessible to readers of diverse backgrounds. They are cross-referenced and provide lists of pointers to Road Maps, background material, and related reading. The second edition greatly increases the coverage of models of fundamental neurobiology, cognitive neuroscience, and neural network approaches to language. It contains 287 articles, compared to the 266 in the first edition. Articles on topics from the first edition have been updated by the original authors or written anew by new authors, and there are 106 articles on new topics. Michael A. Arbib is University Professor; Fletcher Jones Professor of Computer Science; and Professor of Neuroscience, Biomedical Engineering, Electrical Engineering, and Psychology at the University of Southern California. 8 1/2 x 11, 1,344 pp., 1,000 illus., cloth, ISBN 0-262-01197-2 A Bradford Book ______________________ David Weininger Associate Publicist The MIT Press 5 Cambridge Center, 4th Floor Cambridge, MA 02142 617 253 2079 617 253 1709 fax http://mitpress.mit.edu From Dave_Touretzky at cs.cmu.edu Fri Jan 17 07:07:05 2003 From: Dave_Touretzky at cs.cmu.edu (Dave_Touretzky@cs.cmu.edu) Date: Fri, 17 Jan 2003 07:07:05 -0500 Subject: Hodgkin Huxley simulator -- executables available Message-ID: <28109.1042805225@ammon.boltz.cs.cmu.edu> Last semester I announced the first release of HHsim, an easy to use Hodgkin-Huxley simulator designed for neuroscience education. We have just released HHsim version 2.01, which is available in either Matlab source form or as a binary executable for Windows or Unix. The advantages of the executable version are (1) it does not require you to have Matlab installed on your machine, and (2) it executes slightly faster than the interpreted version. The executables were produced by the Matlab compiler. Other new features in HHsim version 2 are: - a Drugs button for applying TTX, TEA, or pronase - online documentation - sample exercises to try with the simulator You can download HHsim from here: http://www.cs.cmu.edu/~dst/HHsim HHsim is free software released under the GNU General Public License. The development of HHsim was funded in part by National Science Foundation grant DGE-9987588. -- Dave Touretzky From erik at bbf.uia.ac.be Fri Jan 17 10:56:56 2003 From: erik at bbf.uia.ac.be (Erik De Schutter) Date: Fri, 17 Jan 2003 16:56:56 +0100 Subject: CNS*03 CALL FOR PAPERS Message-ID: CALL FOR PAPERS: SUBMISSION DEADLINE: February 16, 2003 midnight Twelfth Annual Computational Neuroscience Meeting CNS*2003 July 5 - July 9, 2003 Alicante, Spain http://www.neuroinf.org/CNS.shtml Info at cp at bbf.uia.ac.be CNS*2003 will be held in Alicante from Saturday, July 5, 2003 to Wednesday, July 9. The main meeting will be July 5 - 7 at the Hotel Meli (poster sessions) and at the CAM Cultural Center (oral presentations). The main meeting consists of 6 oral sessions (one each morning and afternoon) and 3 early evening poster sessions. Workshops will be held at the University Miguel Hernndez (Medical School Campus) July 8 - 9. New is that some workshops will be mini-symposia or tutorials, a list of currently planned workshops can be found at the website. The conference dinner will take place in the Santa Brbara castle overlooking the city and the sea on Sunday, July 6. For tourist information see http://www.alicanteturismo.com, more specific practical information will be made available through the conference website. Papers can include experimental, model-based, as well as more abstract theoretical approaches to understanding neurobiological computation. We especially encourage papers that mix experimental and theoretical studies. We also accept papers that describe new technical approaches to theoretical and experimental issues in computational neuroscience or relevant software packages. The paper submission procedure is again completely electronic this year. There will not be any meeting announcement through surface mail, instead you find the meeting poster attached. PAPER SUBMISSION Papers for the meeting can be submitted ONLY through the web site at http://www.neuroinf.org/CNS.shtml Papers can be submitted either as a 1000 word summary or as a full paper (max 6 typeset pages). Full papers stand a better chance of being accepted for oral presentation. You will need to submit the paper in pdf format (if necessary Elsevier can help in converting your paper to pdf) and the 100 word abstract as text. You will also need to select two categories which describe your paper and which will guide the selection of reviewers. In addition we encourage you to also submit your paper to the Elsevier preprint server (http://www.computersciencepreprints.com). All submissions will be acknowledged by email. THE REVIEW PROCESS All submitted papers will be first reviewed by the program committee. Papers will be judged and accepted for the meeting based on the clarity with which the work is described and the biological relevance of the research. For this reason authors should be careful to make the connection to biology clear. We reject only a small fraction of the papers (~ 5%) and this usually based on absence of biological relevance (e.g. pure machine learning). We will notify authors of meeting acceptance before end of March. The second stage of review involves evaluation of submissions which requested an oral presentation by two independent referees. In addition to perceived quality as an oral presentation, the novelty of the research and the diversity and coherence of the overall program will be considered. To ensure diversity, those who have given talks in the recent past will not be selected and multiple oral presentations from the same lab will be discouraged. All accepted papers not selected for oral talks as well as papers explicitly submitted as poster presentations will be included in one of three evening poster sessions. Authors will be notified of the presentation format of their papers by begin of May. CONFERENCE PROCEEDINGS The proceedings volume is published each year as a special supplement to the journal Neurocomputing. In addition the proceedings are published in a hardbound edition by Elsevier Press. Only 200 papers will be published in the proceedings volume. If more than 200 papers are submitted (which is likely) the following rules will apply: each presenting author (who has to register for the meeting) can publish at most one paper in the proceedings book. In case of multi-author papers the same rule applies: one of the authors is considered presenting author and this person has to register at the meeting and cannot publish another paper. If more than 200 presenting authors wish to publish their papers in the proceedings volume the ranking based on the review process will be used to select the top 200 papers. Paper submissions to the conference proceedings are a process separate from the current call for papers: a new submission will need to be done in the early fall of 2003 for which authors will receive detailed instructions. For reference, papers presented at CNS*99 can be found in volumes 32-33 of Neurocomputing (2000), those of CNS*00 in volumes 38-40 (2001) and those of CNS*01 in volumes 44-46 (2002). INVITED SPEAKERS: Yang Dan (University of California Berkeley, USA) Peter Dayan (Gatsby Computational Neuroscience Unit, London, UK) Henry Markram (Brain Mind Institute Lausanne, Switzerland) ORGANIZING COMMITTEE: The CNS meeting is organized by the Computational Meeting Organization Program chair: Erik De Schutter (University of Antwerp, Belgium) Local organizer: Albert Compte (University Miguel Hernndez, Spain) Workshop organizer: Maneesh Sahani (University of California, San Francisco, USA) Government Liaison: Dennis Glanzman (NIMH/NIH, USA) and Yuan Liu (NINDS/NIH, USA) Program Committee: Upinder Bhalla (National Centre for Biological Sciences, India) Victoria Booth (New Jersey Institute of Technology, USA) Alain Destexhe (CNRS Gif-sur-Yvette, France) John Hertz (Nordita, Denmark) Hidetoshi Ikeno (Himeji Institute of Technology, Japan) Barry Richmond (NIMH, USA) Eytan Ruppin (Tel Aviv University) Frances Skinner (University Toronto, Canada) Todd Troyer (University of Maryland, USA) ---- From S.M.Bohte at cwi.nl Wed Jan 22 03:42:37 2003 From: S.M.Bohte at cwi.nl (Sander Bohte) Date: Wed, 22 Jan 2003 09:42:37 +0100 Subject: Call for papers: 1st International Workshop on Future of Neural Networks (FUNN 2003) @ ICALP 2003 Message-ID: <000801c2c1f2$38bc8300$80f4a8c0@cwiware> ======================================================================== 1st International Workshop on the Future of Neural Networks (FUNN 2003) July 5, 2003, Eindhoven, the Netherlands Workshop affiliated to ICALP 2003, June 30 - July 4, 2003 http://www.cwi.nl/~sbohte/funn/funn.html ======================================================================== SCOPE AND TOPICS Neural Networks are inspired by the highly interconnected neural structures in the brain and the nervous system. In the last twenty years the field has become popular and many of the neural networks have found their way into practical applications. On the more foundational level, there has been quite some recent development in the field. It is even to such an extent, that researchers that have not been in touch with the field for some years, have the feeling that it has completely changed. Some examples of developments: o The introduction of more biological plausible neural networks, like spiking neural networks. o The combination of several networks, possibly combined with other formalisms, into ensembles that can yield a better performance than networks in isolation. o The emergence of unifying frameworks for different types of networks, like the Support Vector Machines. o The integration with statistics, most noticeably in the shift towards graphical formalisms like Belief Networks. o The spin-off of successful new areas like Independent Component Analysis. The workshop will focus on the foundational aspects of new developments which include, but are not limited to the above mentioned topics. We hope to bring researchers together, have presentations on the latest developments and have discussions about the future of the field of neural networks. There will also be an invited presentation by Wolfgang Maass of the Technical University of Graz. SUBMISSION Authors are invited to send a contribution for review to funn at liacs.nl. Contributions should have a maximum length of 12 pages (llncs style) in 11 pt. font. See http://www.springer.de/comp/lncs/authors.html for further instructions. Contributions must be in postscript or pdf format. Accepted papers will be published in an informal workshop proceedings. We plan to have a special issue of the journal Natural Computing (Kluwer) based on extended versions of selected workshop papers. PARTICIPATION, REGISTRATION & COST The cost of participating in the workshop is 75 euro. This includes a lunch and the workshop proceedings. Further details can be found in the call for participation, which will be published well in advance of the workshop. IMPORTANT DATES April 27, 2003 : Submission deadline May 24, 2003 : Notification of acceptance July 5, 2003 : Meeting date From bogus@does.not.exist.com Wed Jan 22 10:57:05 2003 From: bogus@does.not.exist.com () Date: Wed, 22 Jan 2003 15:57:05 -0000 Subject: Postdoc job Message-ID: <20CC6C4061CBB04A98656ED3209B203C42FEEE@bond.ncl.ac.uk> From bogus@does.not.exist.com Wed Jan 22 07:56:58 2003 From: bogus@does.not.exist.com () Date: Wed, 22 Jan 2003 12:56:58 -0000 Subject: Natural object categorisation Message-ID: <736F0925D69F9941B3BA8AEED0F5E75CB2EA5B@02-CSEXCH.uopnet.plymouth.ac.uk> From bogus@does.not.exist.com Thu Jan 23 13:48:45 2003 From: bogus@does.not.exist.com () Date: Thu, 23 Jan 2003 18:48:45 -0000 Subject: Soft Computing Research at Cranfield and BT Exact Message-ID: <14D6AEAE08A23344848EF66421623C94014F9F9C@silver.sims.cranfield.ac.uk> A non-text attachment was scrubbed... Name: not available Type: multipart/alternative Size: 0 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/00000000/cfdefbd6/attachment-0001.bin From dgw at MIT.EDU Thu Jan 23 12:28:39 2003 From: dgw at MIT.EDU (David Weininger) Date: Thu, 23 Jan 2003 12:28:39 -0500 Subject: book announcement--Dietterich Message-ID: <200301231228392279@outgoing.mit.edu> I thought readers of the Connectionists List might be interested in this book. For more information, please visit http://mitpress.mit.edu/0262042088/ Thank you! Best, David Advances in Neural Information Processing Systems 14 Proceedings of the 2001 Neural Information Processing Systems (NIPS) Conference. edited by Thomas G. Dietterich, Suzanna Becker, and Zoubin Ghahramani The annual conference on Neural Information Processing Systems (NIPS) is the flagship conference on neural computation. The conference is interdisciplinary, with contributions in algorithms, learning theory, cognitive science, neuroscience, vision, speech and signal processing, reinforcement learning and control, implementations, and diverse applications. Only about 30 percent of the papers submitted are accepted for presentation at NIPS, so the quality is exceptionally high. These proceedings contain all of the papers that were presented at the 2001 conference. Thomas G. Dietterich is Professor of Computer Science at Oregon State University. Suzanna Becker is Associate Professor of Psychology and an Associate Member of the Department of Computing and Software at McMaster University. Zoubin Ghahramani is Lecturer in the Gatsby Computational Neuroscience Unit at University College London. 7 x 10, 1600 pp. (2 volumes, not sold separately), cloth, ISBN 0-262-04208-8 A Bradford Book ______________________ David Weininger Associate Publicist The MIT Press 5 Cambridge Center, 4th Floor Cambridge, MA 02142 617 253 2079 617 253 1709 fax http://mitpress.mit.edu From ckrause at pc09.inb.uni-luebeck.de Fri Jan 24 07:23:28 2003 From: ckrause at pc09.inb.uni-luebeck.de (Christopher Krause) Date: Fri, 24 Jan 2003 13:23:28 +0100 Subject: PhD and System Dynamics Message-ID: <200301241223.h0OCNSi10082@pc09.inb.mu-luebeck.de> The Institute for Neuro- and Bioinformatics, University of Luebeck, Germany, seeks Research Scientists (PhD students) for an interdisciplinary project funded by the European Union. The successful candidate will join an international and interdisciplinary research team. The first goal of the project is to develop a new form of understanding complex dynamic systems, which involves the simulation and visualisation of nonlinear dynamic processes. The second goal is to develop a software tool for decision support for strategic development in politics, transport and logistics, and multinational companies. We expect a strong background in computer science, mathematics, and/or physics, experience in simulation-techniques and enthusiasm for interdisciplinary research. Programming skills (mainly Java) would be a plus. We offer exciting new research topics and the possibility to obtain a PhD in computer science. The positions are initially funded for 36 month. The salary will be at the level of BAT IIa (appr. 38.000 EURO/year before tax). Please send applications including your curriculum vitae, a statement of interests, and names of references to Prof. Thomas Martinetz (martinetz at informatik.uni-luebeck.de ). Application deadline is February 15th. For further information contact T. Martinetz. From ascoli at gmu.edu Fri Jan 24 12:45:26 2003 From: ascoli at gmu.edu (Giorgio Ascoli) Date: Fri, 24 Jan 2003 12:45:26 -0500 Subject: postdoc position available Message-ID: <3E317BB6.60408@gmu.edu> Please post and circulate (my apologies for cross-listing). Giorgio Ascoli COMPUTATIONAL NEUROSCIENCE: POST-DOC Position available immediately for computational modeling of neuronal morphology, connectivity, and electrophysiology. Post-doc will join dynamic and creative laboratory at George Mason Universitys Krasnow Institute, near Washington DC. Superb office space and research/computing facilities, salary based on NIH postdoctoral scale, full benefits. Research experience with either programming/modelling packages or experimental neuroanatomy/electrophysiology is desirable. Serious candidates with a PhD in biology, computer science, physics, psychology, or other areas related to neuroscience (including MD or engineering degree) should submit resume, (p)reprints, 1-page motivation, and 3 recommendation letters ASAP to: Dr. Giorgio Ascoli - Krasnow Institute for Advanced Study - George Mason University, MS2A1 - 4400 University Dr. - Fairfax, VA 22030 (ascoli at gmu.edu). Position will be filled as soon as a suitable candidate is found. Non-resident aliens welcome to apply. George Mason University is an affirmative action / equal opportunity employer. More info: http://www.krasnow.gmu.edu/ascoli/op.htm ------------------- Giorgio Ascoli, PhD Head, Computational Neuroanatomy Group Krasnow Institute for Advanced Study and Department of Psychology - MS2A1 George Mason University, Fairfax, VA 22030-4444 Web: www.krasnow.gmu.edu/ascoli Ph. (703)993-4383 Fax (703)993-4325 From hasselmo at bu.edu Fri Jan 24 14:10:55 2003 From: hasselmo at bu.edu (Michael Hasselmo) Date: Fri, 24 Jan 2003 14:10:55 -0500 Subject: Special Issue of Neural Networks In-Reply-To: <200301241904.OAA294026@acsn03.bu.edu> Message-ID: Call for submissions 2003 Special Issue of the journal Neural Networks This special issue will contain selected articles presented at the International Joint Conference on Neural Networks (IJCNN 2003) taking place in Portland, Oregon, U.S.A. from July 20-24, 2003. This conference provides an overview of state of the art research in Neural Networks, from which this special issue will publish a selection of over 300 pages of articles. These articles will cover a wide range of topics within Neural Networks. The full topic list can be viewed on the conference web page at: www.ijcnn.net. Authors should submit their articles electronically to the conference by the conference deadline of January 29, 2003. The review process of the conference will allow selection of a selected subset of the articles for inclusion in the special issue of Neural Networks. The selected authors will receive an invitation to be included in the special issue and must respond by the deadline to be included. Revised articles must then be submitted by March 21, 2003. Any invited articles which are not resubmitted by the deadline will not be included in the special issue, but will still be included in the conference. Co-Editors Prof. Donald Wunsch, University of Missouri - Rolla Prof. Michael E. Hasselmo, Boston University Prof. Kumar Venayagamoorthy, University of Missouri - Rolla Prof. DeLiang Wang, Ohio State University Submission Deadline for submission: January 29, 2003 Format: Double column, 4-6 pages. Must follow guidelines on the paper submission page at www.ijcnn.net. Address for Papers Papers should be submitted electronically for review on the IJCNN 2003 meeting web page at www.ijcnn.net (deadline Jan. 29, 2003). Accepted papers must be submitted in revised form to the IJCNN web site by March 21, 2003 and assembled by the special issue editors for publication. The IJCNN meeting is organized annually by the International Neural Network Society (INNS) and the IEEE Neural Networks Society. Conference attendees who join the INNS will receive a reduced IJCNN conference registration fee, and those who are INNS members will receive the IJCNN special issue for free as part of their annual membership subscription to Neural Networks. From cindy at cns.bu.edu Fri Jan 24 15:27:11 2003 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Fri, 24 Jan 2003 15:27:11 -0500 Subject: Call for Papers: 2004 Special Issue of Neural Networks on Vision and Brain Message-ID: <00eb01c2c3e6$fa407d60$573dc580@bu.edu> CALL FOR PAPERS 2004 Special Issue VISION AND BRAIN Understanding how the brain sees is one of the most active and exciting areas in perceptual science, neuroscience, and modeling. This is because vision is one of our most important sources of information about the world, and a large amount of brain is used to process visual signals, ranging from early filtering processes through perceptual grouping, surface formation, depth perception, texture perception, figure-ground separation, motion perception, navigation, search, and object recognition. This Special Issue will incorporate invited and contributed articles focused on recent experimental and modeling progress in unifying physiological, psychophysical and computational mechanisms of vision. The Special Issue will also include articles that summarize biologically inspired approaches to computer vision in technology, including hardware approaches to realizing neuromorphic vision algorithms. CO-EDITORS: Professor David Field, Cornell University Professor Leif Finkel, University of Pennsylvania Professor Stephen Grossberg, Boston University SUBMISSION: Deadline for submission: September 30, 2003 Notification of acceptance: January 31, 2004 Format: no longer than 10,000 words; APA reference format ADDRESS FOR SUBMISSION: Stephen Grossberg, Editor Neural Networks Department of Cognitive and Neural Systems Boston University 677 Beacon Street, Room 203 Boston, Massachusetts 02215 USA From alfredo at itam.mx Fri Jan 24 18:13:40 2003 From: alfredo at itam.mx (Alfredo) Date: Fri, 24 Jan 2003 17:13:40 -0600 Subject: book and software announcement - NSL3.0 Message-ID: <5.0.2.1.0.20030124170330.0359ccb0@lamport.rhon.itam.mx> Dear Connectionists: The following book may be of interest to you. For more information please visit: http://mitpress.mit.edu/catalog/item/default.asp?sid=68013B05-2E40-4A86-BB67-0A8964D7B663&ttype=2&tid=8815 Best wishes, Alfredo The Neural Simulation Language: A System for Brain Modeling by A. Weitzenfeld, M.A. Arbib and A. Alexander MIT Press Book Description: The book describes the Neural Simulation Language (NSL) developed by Alfredo Weitzenfeld, Michael Arbib, and Amanda Alexander. NSL is a simulation environment for modular brain modeling now in its third major release supporting two programming environments, one in Java and the other one in C++. NSL addresses the needs of a wide range of users. For novice users interested only in an introduction to neural networks, NSL provides user-friendly interfaces and a set of predefined artificial and biological neural models. For more advanced users well acquainted with the area of neural modeling NSL offers more sophistication through extended visualization tools and programming. NSL may easily be linked to other software by doing direct programming in either Java or C++, such as linking it to numerical libraries or robotic systems. NSL is especially suitable for academia and research where simulation and model development can complement theoretical courses in both biological and artificial neural networks. Models included in the book are examples of models that can be used for this purpose. Students are able to run these models and change their behavior by modifying input or network parameters. Researchers may extend these architectures in developing new neural models. The book is divided into two parts. The first part presents an overview of neural network and schema modeling, a brief history of NSL, and a discussion of the new version, NSL 3.0. It includes tutorials on several basic neural models. The second part presents models built in NSL by researchers from around the world, with models such as conditional learning, face recognition, associative search networks and visuomotor coordination. Each chapter provides an explanation of a model, an overview of the NSL 3.0 code, and a representative set of simulation results. Table of Contents: Part I. An Overview of NSL Modeling and Simulation 1 Introduction: Introduction to neural network modeling and simulation in NSL. 2 Simulation in NSL: Examples of biological and artificial neural network simulation in NSL, how to run them. 3 Modeling in NSL: Examples of biological and artificial neural network modeling in NSL, how to create them. 4 Schematic Capture System: Describes the Schematic Capture System visual tools for the design of neural models and model libraries. 5 User Interface and Graphical Windows: Describes the NSL Graphics and Window Interface environment. 6 The Modeling Language NSLM: Describes the NSLM high level modeling language for writing neural network models. 7 The Scripting Language NSLS: Describes the NSLS scripting language for specifying simulation interaction and control commands. Part II. Neural Modeling and Simulation Examples Using NSL 8 Adaptive Resonance Theory - Grossberg ART by T. Tanaka and A. Weitzenfeld 9 Depth Perception - Dev and House Depth Perception by A. Weitzenfeld and M. Arbib 10 Retina by R. Corbacho and A. Weitzenfeld 11 Receptive Fields by F. Moran, M.A. Andrade, Chacn and A. Weitzenfeld 12 The Associative Search Network: Landmark Learning and Hill Climbing - Barto and Sutton Landmark Learning by M. Bota and A. Guazelli 13 A Model of Primate Visual-Motor Conditional Learning: Reinforcement Learning by A. Fagg and A. Weitzenfeld 14 The Modular Design of the Oculomotor System in Monkeys by P. Dominey, M. Arbib, and A. Alexander 15 Crowley-Arbib Saccade Model by M. Crowley, E. Oztop, and S. Mrmol 16 A Cerebellar Model of Sensorimotor Adaptation by J. Spoelstra 17 Learing to Detour by F. Corbacho and A. Weitzenfeld 18 Face Recognition by Dynamic Link Matching by L. Wiskott, C. von der Malsburg and A. Weitzenfeld The NSL web site http://www.neuralsimulationlanguage.org includes all software and models described in the book as well as other relevant information. The NSL Java version can be downloaded from http://nsl.usc.edu as well. From bogus@does.not.exist.com Fri Jan 24 07:24:56 2003 From: bogus@does.not.exist.com () Date: Fri, 24 Jan 2003 12:24:56 -0000 Subject: Research Fellowship Message-ID: <736F0925D69F9941B3BA8AEED0F5E75C5F4042@02-CSEXCH.uopnet.plymouth.ac.uk> From bogus@does.not.exist.com Fri Jan 24 07:01:26 2003 From: bogus@does.not.exist.com () Date: Fri, 24 Jan 2003 12:01:26 -0000 Subject: Research Scholarships Message-ID: <736F0925D69F9941B3BA8AEED0F5E75C5F5136@02-CSEXCH.uopnet.plymouth.ac.uk> From schwabe at cs.tu-berlin.de Mon Jan 27 04:40:38 2003 From: schwabe at cs.tu-berlin.de (Lars Schwabe) Date: Mon, 27 Jan 2003 10:40:38 +0100 Subject: Advanced Course in Computational Neuroscience Message-ID: <000c01c2c5e8$28f69b50$5e109582@algieba> ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE (A FENS/IBRO NEUROSCIENCE SCHOOL) August 11th - September 5th, 2003 MUNICIPALITY OF OBIDOS, PORTUGAL DIRECTORS: Ad Aertsen (University of Freiburg, Germany) Alain Destexhe (CNRS, Gif-sur-Yvette, France) Klaus Obermayer (Technical University of Berlin, Germany) Eilon Vaadia (Hebrew University, Jerusalem, Israel) The Advanced Course in Computational Neuroscience introduces students to the panoply of problems and methods of computational neuroscience, simultaneously addressing several levels of neural organisation, from subcellular processes to operations of the entire brain. The course consists of two complementary parts. A distinguished international faculty gives morning lectures on topics in experimental and computational neuroscience. The rest of the day is devoted to practical training, including learning how to use simulation software and how to implement a model of the system the student wishes to study on individual UNIX workstations. The first week of the course introduces students to essential neurobiological concepts and to the most important techniques in modelling single cells, networks and neural systems. Students learn how to apply software packages like GENESIS, MATLAB, NEURON, XPP, etc. to the solution of their problems. During the following three weeks the lectures will cover specific brain functions. Each week topics ranging from modelling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the brain will be covered. The course ends with a presentation of the students' projects. The Advanced Course in Computational Neuroscience is designed for advanced graduate students and postdoctoral fellows in a variety of disciplines, including neuroscience, physics, electrical engineering, computer science and psychology. Students are expected to have a basic background in neurobiology as well as some computer experience. Students of any nationality can apply. A maximum total of 30 students will be accepted and we specifically encourage applications from researchers who work in less-favoured regions and women. There will be a fee of EUR 950,- per student covering costs for lodging, meals and other course expenses, but a limited number of fellowships for travel and tuition fee will be available. These fellowships will be given in priority to students from less favoured countries. More information and application forms can be obtained from: http://www.neuroinf.org/courses/EUCOURSE/EU03/ The application process will start on February 10th, 2003. Please apply electronically ONLY using a web browser. Contact address: - mail: Klaus Obermayer, FR2-1, Fakultaet IV, Technical University of Berlin, Franklinstrasse 28/29, 10587 Berlin, Germany phone: +49-(0)30-314-73442 fax: +49-(0)30-314-73121 - e-mail: obidos at cs.tu-berlin.de APPLICATION DEADLINE: April 13th, 2003 Applicants will be notified of the results of the selection procedures by May 23rd, 2003. From kegl at IRO.UMontreal.CA Mon Jan 27 11:59:11 2003 From: kegl at IRO.UMontreal.CA (Balazs Kegl) Date: Mon, 27 Jan 2003 11:59:11 -0500 Subject: Workshop on Advances in Machine Learning, Montreal, June 2-6, 2003 Message-ID: <200301271659.h0RGxBt30533@neumann.IRO.UMontreal.CA> ---- Please excuse us if you receive multiple copies of this message ----- Call for papers Workshop on Advances in Machine Learning Montreal, Canada, June 2-6, 2003 URL: www.iro.umontreal.ca/~lisa/workshop2003.html Organizers: Yoshua Bengio, Balazs Kegl (University of Montreal) Doina Precup (McGill University) Scope: Probabilities are at the core of recent advances in the theory and practice of machine learning algorithms. The workshop will focus on three broad areas where these advances are crucial: statistical learning theory, learning algorithms, and reinforcement learning. The workshop will therefore bring together experts from each of these three important domains. Among the sub-topics that will be covered, we note: variational methods, graphical models, the curse of dimensionality, empirical methods to take advantage of theories of generalization error, and some of the applications of these new methods. On the theoretical side, in recent years a lot of effort has been devoted to explain the generalization abilities of popular learning algorithms such as voting classifiers and kernel methods. Some of these results have given rise to general principles that can guide practical classifier design. Some (non-exclusive) sub-topics in this aspect of the workshop include Rademacher and Gaussian complexities, algorithmic stability and generalization, localized complexities and results on the generalization ability of voting classifiers and kernel-based methods. On the algorithmic side, one of the emphasis of recent years has been on probabilistic models that attempt to capture the complex structure in the data, often by discovering the main lower-dimensional features that explain the data. This raises interesting and difficult questions on how to train such models, but such algorithms may have wide ranging applications in domains in which the data has interesting structure that may be explained at multiple levels, such as in vision and language. In reinforcement learning (RL), recent research has brought significant advances in some of the traditional problems, such as understanding the interplay between RL algorithms and function approximation, and extending RL beyond MDPs. At the same time, new areas of research, such as computational game theory, have developed at the interface between RL and probabilistic learning methods. In this workshop, we invite presentations on all RL topics, ranging from theoretical development to practical applications. Invited speakers: Rich Sutton, U. Massachusetts, MA, USA Andy Barto, U. Massachusetts, MA, USA (to confirm) Satinder Singh, U. Michigan, Ann Arbour, MI, USA Michael Littman, Rutgers U., NJ, USA Leslie Pack Kaelbling, MIT (to confirm) Michael Kearns, U. Pennsylvania (to confirm) Sridhar Mahadevan, U. Massachusetts Peter Bartlett, U. California Berkeley, CA, USA Gabor Lugosi, Pompeu Fabra Univ., Spain (to confirm) Vladimir Koltchinskii, U. New Mexico, NM, USA Yann Le Cun, NEC Research, NJ, USA Paolo Frasconi, U. Firenze, Italy Dale Schuurmans, Waterloo U., Ontario, Canada Nando de Freitas, U. British Columbia, BC, Canada Sam Roweis, U. Toronto, Ontario, Canada Geoff Hinton, U. Toronto, Ontario, Canada Important dates: March 31, Paper submission deadline April 15, Notification of paper acceptance/rejection. Submission: Papers should be submitted electronically to kegl at iro.umontreal.ca. Papers can be submitted either as a postscript or a pdf (acrobat) file. No proceedings are currently planned. Registration: The registration fees are minimal: regular registration fees are 100$CAN. Reduced rate for students from a Canadian academic institution: 50$CAN. Venue: The workshop will take place at the Centre de Recherches Mathematiques, on the campus of Universite de Montreal, in lively and beautiful Montreal, Canada. The conference will be held in the Pavillon Andre Aisenstadt, 2920 chemin de la Tour. From jbednar at cs.utexas.edu Wed Jan 29 04:04:19 2003 From: jbednar at cs.utexas.edu (James A. Bednar) Date: Wed, 29 Jan 2003 04:04:19 -0500 (EST) Subject: Visual cortex dissertation (with software and web demos) Message-ID: <200301290904.h0T94JHs014617@ms-smtp-01.texas.rr.com> I am pleased to announce the availability of my Ph.D. dissertation, completed last year at the Department of Computer Sciences at the University of Texas at Austin under the supervision of Prof. Risto Miikkulainen. The thesis shows how the combination of spontaneous neural activity and visual patterns in the environment can help explain the development of orientation and face processing circuitry in the cortex. Early versions of this work appeared at the AAAI-2000, CogSci-2002, and CNS*02 conferences, and updated results will appear in Neural Computation, 2003 (in press). Jefferson Provost and I are also pleased to announce version 4.0 of the LISSOM software package for self-organization of laterally connected maps in visual cortex. This software supports the simulations in the dissertation, and is intended to serve as a starting point for computational studies of the development and function of perceptual maps in general. The software is available at topographica.org, and the dissertation and other papers and demos are available at http://www.cs.utexas.edu/users/nn/pages/research/visualcortex.html. -- James A. Bednar _______________________________________________________________________________ Publications: LEARNING TO SEE: GENETIC AND ENVIRONMENTAL INFLUENCES ON VISUAL DEVELOPMENT James A. Bednar Ph.D. Thesis, The University of Texas at Austin Technical Report~AI-TR-02-294, May 2002 (138 pages). http://www.cs.utexas.edu/users/nn/pages/publications/abstracts.html#bednar.phd02 How can a computing system as complex as the human visual system be specified and constructed? Recent discoveries of widespread spontaneous neural activity suggest a simple yet powerful explanation: genetic information may be expressed as internally generated training patterns for a general-purpose learning system. The thesis presents an implementation of this idea as a detailed, large-scale computational model of visual system development. Simulations show how newborn orientation processing and face detection can be specified in terms of training patterns, and how postnatal learning can extend these capabilities. The results explain experimental data from laboratory animals, human newborns, and older infants, and provide concrete predictions about infant behavior and neural activity for future experiments. They also suggest that combining a pattern generator with a learning algorithm is an efficient way to develop a complex adaptive system. SELF-ORGANIZATION OF SPATIOTEMPORAL RECEPTIVE FIELDS AND LATERALLY CONNECTED DIRECTION AND ORIENTATION MAPS James A. Bednar and Risto Miikkulainen To appear in Neurocomputing, 2003 (in press; 8 pages). http://www.cs.utexas.edu/users/nn/pages/publications/abstracts.html#bednar.cns02 Studies of orientation maps in primary visual cortex (V1) suggest that lateral connections mediate competition and cooperation between orientation-selective units, but their role in motion perception has not been established. Using a self-organizing model of V1 with moving oriented patterns, we show that (1) afferent weights of each neuron organize into Gabor-like spatiotemporal receptive fields with ON and OFF lobes, (2) these receptive fields form realistic joint direction and orientation maps, and (3) lateral connections develop between patches with similar orientation and direction preferences. These results suggest that a single self-organizing system may underlie the development of orientation selectivity, direction selectivity, and lateral connectivity. _______________________________________________________________________________ Software: LISSOM V4.0: HIERARCHICAL LATERALLY CONNECTED SELF-ORGANIZING MAPS Available from http://www.topographica.org James A. Bednar and Jefferson Provost The LISSOM package contains the C++ and Scheme source code and examples for training and testing LISSOM-based computational models. These self-organizing models support detailed simulation of the development and function of the mammalian visual system, and include parameter files used to generate the results in the publications listed above. Version 4.0 of the simulator provides a graphical user interface (GUI) for basic tasks, and full batch mode (using a command file) and remote mode (using a command line prompt) interfaces. The graphs and plots are available from any of the supported interfaces. Sample networks are provided for running orientation, ocular-dominance, motion direction, and face perception simulations. These existing models can be tested easily with new input patterns using the GUI, or the command files can be edited to produce new models based on other training patterns or different network configurations. Extensive documentation is included, and is also available via online help at the command line. The full package is freely available from our web site, and supports UNIX, Windows, and Mac systems. For more details see the tutorial, screenshots, and documentation at topographica.org. From geoff at cns.georgetown.edu Wed Jan 29 16:45:47 2003 From: geoff at cns.georgetown.edu (geoff@cns.georgetown.edu) Date: Wed, 29 Jan 2003 16:45:47 -0500 Subject: Faculty position available Message-ID: <200301292145.h0TLjlI17128@jacquet.cns.georgetown.edu> TENURE-TRACK FACULTY POSITION IN COMPUTATIONAL NEUROSCIENCE Georgetown University The Department of Neuroscience is recruiting a new tenure-track faculty member in computational neuroscience at the rank of either Assistant or Associate Professor. We offer an outstanding intellectual and collaborative environment with highly competitive salary and start-up packages. Successful candidates must have a Ph.D. or equivalent, evidence of productivity and innovation, and the potential to establish an independently funded research program. Applications are encouraged from women and underrepresented minorities. To apply send to the address below (hardcopies only please) a detailed CV, a two-page statement of research and teaching interests, and (3) no more than 3 preprints or reprints. Please also have three referees send recommendations to the same address. Faculty Search Committee Attention: Geoff Goodhill Department of Neuroscience Georgetown University Box 571464 Washington DC 20057-1464 http://neuro.georgetown.edu Application review will begin immediately and will continue until the position is filled. Georgetown University is an Equal Opportunity, Affirmation Action Employer. Qualified candidates will receive employment consideration without regard to race, sex, sexual orientations, age, religion, national origin, marital status, veteran status or disability. We are committed to diversity in the workplace.