From bengio at idiap.ch Fri Apr 1 01:26:24 2005 From: bengio at idiap.ch (Samy Bengio) Date: Fri, 1 Apr 2005 08:26:24 +0200 (CEST) Subject: Connectionists: call for paper: MLMI'05 workshop Message-ID: CALL FOR PAPERS: 2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms MLMI'05 http://groups.inf.ed.ac.uk/mlmi05 11-13 July 2005, Royal College of Physicians, Edinburgh, UK The second MLMI workshop is coming to Edinburgh, UK, 11-13 July, 2005 follows from the first successful MLMI'04 held in Martigny, Switzerland, June 2004 (http://www.idiap.ch/events/workshop-mlmi04/). The topics covered by the MLMI'05 workshop are the following: * human-human communication modeling * speech and visual processing * multi-modal processing, fusion and fission * multi-modal dialog modeling * human-human interaction modeling * multi-modal data structuring and presentation * multimedia indexing and retrieval * meeting structure analysis * meeting summarizing * multimodal meeting annotation * machine learning applied to the above We particularly welcome all theoretical and applied machine learning papers targeting large and complex datasets such as those involved in multimodal interaction. The workshop will be sponsored by several european and national projects, including AMI, CHIL, HUMAINE, PASCAL, SIMILAR, IM2, etc. (more information on the sponsors available on the website). Key Dates: Submission deadline 13 May 2005 Accept/reject decisions 13 June 2005 Plenary workshop takes place 11-12 July 2005 Specialist workshops take place 13 July 2005 Guidelines for submissions: The submitted papers should follow the Springer LNCS format and be 12 pages maximum per full paper. Extended abstracts of 2 pages maximum can also be submitted to be considered as posters. The best papers will then be published in an edited book, similar to MLMI'04, published as LNCS-3361: http://www.springerlink.com/openurl.asp?genre=issue&issn=0302-9743&volume=3361&issue=preprint Organization: Co-chairs: * Steve Renals, University of Edinburgh * Samy Bengio, IDIAP Programme Committee (to be confirmed): * Herve Bourlard, IDIAP * Jean Carletta, University of Edinburgh * Franciska de Jong, University of Twente [tbc] * John Garofolo, NIST * Lori Lamel, LIMSI * Jan Larsen, Technical University of Denmark [tbc] * Benoit Macq, UCL-TELE * Johanna Moore, Universirty of Edinburgh * Laurence Nigay, CLIPS-IMAG * Barbara Peskin, ICSI * Thierry Pun, University of Geneva * Marc Schr?der, DFKI * Rainer Stiefelhagen, Universitaet Karlsruhe ---- Samy Bengio Senior Researcher in Machine Learning. IDIAP, CP 592, rue du Simplon 4, 1920 Martigny, Switzerland. tel: +41 27 721 77 39, fax: +41 27 721 77 12. mailto:bengio at idiap.ch, http://www.idiap.ch/~bengio From nnrev at atr.jp Fri Apr 1 03:29:11 2005 From: nnrev at atr.jp (Neural Networks Editorial Office) Date: Fri, 1 Apr 2005 17:29:11 +0900 Subject: Connectionists: Neural Networks 18(2) Message-ID: NEURAL NETWORKS 18(2) Contents - Volume 18, Number 2 - 2005 ------------------------------------------------------------------ NEURAL NETWORKS LETTERS: Cogent confabulation Robert Hecht-Nielsen Intelligent initialization of resource allocating RBF networks Manolis Wallace, Nicolas Tsapatsoulis, and Stefanos Kollias CONTRIBUTED ARTICLES: ***** Mathematical and Computational Analysis ***** Chaotic dynamics of a behavior-based miniature mobile robot: effects of environment and control structure Md. Monirul Islam and K. Murase Adaptive algorithms for first principal eigenvector computation Chanchal Chatterjee Analysis of global exponential stability and periodic solutions of neural networks with time-varying delays He Huang, Daniel W.C. Ho, and Jinde Cao On the global output convergence of a class of recurrent neural networks with time-varying inputs Sanqing Hu and Derong Liu ***** Engineering and Design ***** NEUROM: a ROM based RNS digital neuron Giuseppe Alia and Enrico Martinelli ***** Technology and Applications ***** TAO-robust backpropagation learning algorithm Alpha V. Pernia-Espinoza, Joaquin B. Ordieres-Mere, Francisco J. Martinez-de-Pison, and Ana Gonzalez-Marcos ***** Letter to the Editor ***** Experimentally optimal nu in support vector regression for different noise models and parameter settings Athanassia Chalimourda, Bernhard Scholkopf, Alex J. Smola 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 Y 13,000 Neural Networks (plus Y 2,000 enrollment fee) $20 (student) SEK 460 Y 11,000 (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- membership without $30 SEK 200 not available Neural Networks to non-students (subscribe through another society) Y 5,000 student (plus Y 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 7600 Terrace Avenue, Ste. 203 Middleton WI 53562 USA 608 831 0584, ext. 138 (phone) 608 831 5122 (fax) srees at reesgroupinc.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 Shozo Yasui Kyushu Institute of Technology Graduate School of Life Science and Engineering 2-4 Hibikino, Wakamatsu-ku Kitakyushu 808-0196 Japan 81 93 695 6108 (phone and fax) jnns at brain.kyutech.ac.jp http://www.jnns.org/ ---------------------------------------------------------------------------- -- """""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" NEURAL NETWORKS Editorial Office ATR Computational Neuroscience Laboratories 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan TEL +81-774-95-1204 FAX +81-774-95-1236 E-MAIL nnrev at atr.jp """"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" From oreilly at psych.colorado.edu Fri Apr 1 15:35:37 2005 From: oreilly at psych.colorado.edu (Randall C. O'Reilly) Date: Fri, 1 Apr 2005 13:35:37 -0700 Subject: Connectionists: Request: PDP++ software usage reports Message-ID: <200504011335.37667.oreilly@psych.colorado.edu> We are planning to write a grant proposal to support major enhancements to the PDP++ neural network simulation software, and need to collect some data on publications, teaching, and other usage of this software. If you have used PDP++ for simulations published in any form, please email me the reference(s) to these publications (APA format preferred, but any format will do). If you have used PDP++ for teaching, please send the name of the course, years taught, number of students, etc. (any information would be appreciated, the more the better). If you have used PDP++ for other purposes (e.g., business, forecasting, etc) please send any relevant information. Finally, if you have any feedback on the software for things that we should improve in the future, we would like to hear it. We have already begun the revisions and have a fairly detailed plan, which we will be announcing within a few weeks on the pdp-discuss email list, so your feedback would be most beneficial if it could be given in the context of these plans, but if you would rather just send feedback now, that would also be appreciated. To subscribe to the pdp-discuss email list, see the PDP++ website at: http://psych.colorado.edu/~oreilly/PDP++/PDP++.html *or* http://www.cnbc.cmu.edu/Resources/PDP++/PDP++.html Thanks! - Randy From kim at psy.mpg.de Sun Apr 3 09:52:49 2005 From: kim at psy.mpg.de (DaeEun Kim) Date: Sun, 03 Apr 2005 15:52:49 +0200 Subject: Connectionists: CFP for Workshop on Memory and Learning Mechanisms in Autonomous Robots Message-ID: <424FF531.AC6BFEC0@psy.mpg.de> Call for Papers: Workshop on Memory and Learning Mechanisms in Autonomous Robots co-located with ECAL 2005 (European Conf. on Artificial Life) http://www.ecal2005.org/workshops.html The aim of this workshop is to explore how to process memory for complex robotic tasks and how to represent/encode plasticity in robot controllers. The study of memory structure and the development of new learning algorithms to model neuronal plasticity are a central challenge for adaptive behaviour research. The workshop aims to bring together researchers interested in these topics to discuss new ideas and alternative solutions which might open up yet unexplored research lines. We encourage the submission of work which propose provocative new ideas, discuss controversial aspects on memory and learning mechanisms for autonomous adaptive agents. The topics of the workshop include, but are not limited to: mechanisms for memory and learning neural plasticity neuromodulation spiking neural networks gas-net homeostatic networks representational / non-representational memory evolution of short / long term memory evolution of learning mechanisms reinforcement learning in non-Markovian environment forward model / cerebellar network Important Dates Submission deadline: 15th May, 2005 Notification date: 15th June, 2005 Final date for camera-ready copies: 22nd, June, 2005 Organisers: Dr. Elio Tuci, IRIDIA, Universite Libre de Bruxelles, Belgium Email: etuci at ulb.ac.be Dr. DaeEun Kim, Max Planck Institute for Human Cognitive and Brain Sciences, Germany Email: daeeun at cbs.mpg.de Program committee (confirmed) Dr. Marco Dorigo, IRIDIA, Universite Libre de Bruxelles Dr. Dario Floreano, Ecole Polytechnique Federale de Lausanne Dr. John C.T. Hallam, University of Southern Denmark Dr. Pier Luca Lanzi, Politecnico di Milano Dr. Ralf Moeller, University of Bielefeld Dr. Stefano Nolfi, Institute of Cognitive Sciences and Tecnologies Dr. Ezequiel Di Paolo, University of Sussex Dr. Juergen Schmidhuber, Dalle Molle Inst. for Artificial Intelligence Dr. Tom Ziemke, University of Skoevde You may find more information at http://www.psy.mpg.de/home/kim/www/memory/memory_workshop.html Thank you. ------------------------------------------------------------------------------------------- DaeEun Kim Cognitive Robotics Max Planck Institute for Human Cognitive and Brain Sciences Amalienstr. 33 80799, Munich Germany Tel) +49-89-38602-333 Fax) +49-89-38602-199 ------------------------------------------------------------------------------------------- From ftupindr at ti.uni-bielefeld.de Mon Apr 4 04:17:18 2005 From: ftupindr at ti.uni-bielefeld.de (Ralf Moeller) Date: Mon, 04 Apr 2005 10:17:18 +0200 Subject: Connectionists: doctoral/postdoctoral researcher: local PCA Message-ID: <4250F80E.6010706@ti.uni-bielefeld.de> Doctoral/postdoctoral researcher Faculty of Technology Bielefeld University, Germany The Computer Engineering Group at the Faculty of Technology of Bielefeld University (http://www.ti.uni-bielefeld.de), offers a temporary position as doctoral or postdoctoral researcher (salary BAT IIa, for two years) in a DFG-funded research project "Local PCA methods for internal sensorimotor models", starting July 1, 2005. The project aims at improving and extending unsupervised neural learning methods where data manifolds are approximated based on local principal component analysis. The methods will be applied to the training of inverse and forward models in the context of robot control tasks. The applicant should hold a university's Master's or Diploma degree in computer science, engineering, mathematics, or physics. A background in image and signal processing, neuroinformatics and robotics is useful. Strong programming skills and advanced mathematical competences are expected. Bielefeld University encourages disabled people to apply. Applications by women are expressly requested; in the case of comparable competences and qualification, women will preferably be considered if there are no dominating reasons arising from the person of another applicant. Part-time employment is possible. Please send your application with the usual documents (including the name and email addresses of two referees) until April 30, 2005 to AG Technische Informatik Sekretariat, Frau Angelika Deister Technische Fakult?t Universit?t Bielefeld Postfach 100131 D-33501 Bielefeld Germany or by email to bewerbung-dfg at ti.uni-bielefeld.de From Nicolas.Rougier at loria.fr Tue Apr 5 10:47:47 2005 From: Nicolas.Rougier at loria.fr (Nicolas Rougier) Date: Tue, 05 Apr 2005 16:47:47 +0200 Subject: Connectionists: Postdoctoral position available at INRIA/Lorraine, France Message-ID: <4252A513.3020202@loria.fr> A postdoctoral position is available at INRIA/Lorraine, France. Deadline for submitting candidature is 22 of April 2005. (Sorry if you received multiple copies of this document). Context: -------- Cortex project with INRIA Lorraine is developping computational models of neural networks inspired by biology (computational neurosciences) which aimed at mixing knowledge from neuroscience together with robust and distributed computation at both structural and functional level. Our goals are to evaluate those models against experimental data from neurosciences but also to design some tecnological software that can be used, for example, in autonomous robotic. Recently, we designed a distributed and dynamic model of visual attention based on the Continuum Neural Field Theory that allows to sequentially focus salient locations in an image. A working memory system ensures that the corresponding objects are only focused once, even if they are moving around, such that the visual search is efficient. The model has been implemented on a robotic platform in order to search for objects such as fruits in a natural scene. Objectives: ----------- We now aim at evaluating and refining this model by introducing behavioral data because we think such data from psychology would help in a better control and memorization of fixation points while exploring a visual scene. More precisely, such data could help validate the model robustness and pinpoint the nature of information flows between posterior and frontal cortex. Ultimately, this study would help in the design of a model more closely related to our knowledge of the human attention circuitry. Methods: -------- In a first time, candidate will help in evaluating the model in terms of biological plausibility with focus on the implied structures and their respective role. This study would possibly lead to the re-organization of information flows within the model in order to fit neuro-anatomical data. In a second time, candidate would help evaluating the model against common human psychological experiments concerning selective visual attention by proposing and implementing some evaluation protocol. Finally, candidate will help in extending the model by considering the sequence of fixation points on a visual scene. An expertise in perception, spatial relationships and information integration is, thus required. Duration of the fellowship (months): ------------------------------------ 12.0 Sought profile of the candidate: -------------------------------- We aim at recruiting a post-doctoral fellow in neurosciences having a strong background in both visual attention domain and significant experience in computational modeling. Contact: -------- Nicolas Rougier, Nicolas.Rougier at loria.fr URL: ---- http://www.loria.fr/jobs/postdoc_inria/postdoc_inria?id=46 Conditions for applicants ------------------------- * Doctoral candidates must have defended their thesis before September 1, 2005. In case the thesis has not been defended at the time of application, the thesis defense date must be explicitly indicated in the application file. * The positions are devoted to the priority research themes of the Institute, as well as to the Incentive Concerted Initiatives on Data Masses and Computer Security. However, high level applications on non priority topics will also be considered. High priority will be given to French and foreign applicants who prepared their doctorate abroad, but again every high level application will be carefully considered. * No nationality requirement. * Please complete one application file per topic proposed by the research units. * If you have obtained your doctorate from within an INRIA research unit, you cannot apply to this unit. You may however apply to other research units. Nicolas Rougier From terry at salk.edu Tue Apr 5 17:23:12 2005 From: terry at salk.edu (Terry Sejnowski) Date: Tue, 5 Apr 2005 14:23:12 -0700 (PDT) Subject: Connectionists: NEURAL COMPUTATION 17:5 In-Reply-To: <200502020553.j125rKs06193@kepler.snl.salk.edu> Message-ID: <200504052123.j35LNCn69350@kepler.snl.salk.edu> Neural Computation - Contents - Volume 17, Number 5 - May 1, 2005 NOTE Gain Control by Concerted Changes in I_A and I_H Conductances Denis Burdakov Winner-Relaxing elf-Organizing Maps Jens Christian Claussen LETTERS Image Segmentation by Networks of Spiking Neurons Joachim M. Buhmann, Tilman Lange, and Ulrich Ramacher Neural Computation - Contents - Volume 17, Number 5 - May 1, 2005 NOTE Gain Control by Concerted Changes in I_A and I_H Conductances Denis Burdakov Winner-Relaxing elf-Organizing Maps Jens Christian Claussen LETTERS Image Segmentation by Networks of Spiking Neurons Joachim M. Buhmann, Tilman Lange, and Ulrich Ramacher Neural Modeling of an Internal Clock Tadashi Yamazaki and Shigeru Tanaka Mirror Symmetric Topographic Maps Can Arise from Activity-Dependent Synaptic Changes Reiner Schulz and James A. Reggia Stochastic Optimal Control and Estimation Methods Adapted to the Noise Characteristics of the Sensoromotor System Emanuel Todorov Universal Approximation Capability of Cascade Correlation for Structures Barbara Hammer, Alessio Micheli and Alessandro Sperduti SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming Qiang Wu and Ding-Xuan Zhou Leave-One-Out Bounds for Support Vector Regression Model Selection Ming-Wei Chang and Chih-Jen Lin ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2005 - VOLUME 17 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $143 $90 $96.30 Institution $680 $727.60 $734 $612 $654.84 * 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 ringger at microsoft.com Wed Apr 6 12:03:14 2005 From: ringger at microsoft.com (Eric Ringger) Date: Wed, 6 Apr 2005 09:03:14 -0700 Subject: Connectionists: ACL 2005 Workshop on Feature Engineering for Machine Learning in NLP Message-ID: <093830707D538448B1F337432D779BA1DB7E81@RED-MSG-61.redmond.corp.microsoft.com> ---------------------------------------------------------------- SECOND CALL FOR PAPERS Feature Engineering for Machine Learning in Natural Language Processing Workshop at the Annual Meeting of the Association of Computational Linguistics (ACL 2005) http://research.microsoft.com/~ringger/FeatureEngineeringWorkshop/ ** SUBMISSION DEADLINE: April 20, 2005 ** Ann Arbor, Michigan June 29, 2005 ---------------------------------------------------------------- As experience with machine learning for solving natural language processing tasks accumulates in the field, practitioners are finding that feature engineering is as critical as the choice of machine learning algorithm, if not more so. Feature design, feature selection, and feature impact (through ablation studies and the like) significantly affect the performance of systems and deserve greater attention. In the wake of the shift away from knowledge engineering and of the successes of data-driven and statistical methods, researchers in the field of NLP are likely to make further progress by incorporating additional, sometimes familiar, sources of knowledge as features. Although some experience in the area of feature engineering is to be found in the theoretical machine learning community, the particular demands of natural language processing leave much to be discovered. This workshop aims to bring together practitioners of NLP, machine learning, information extraction, speech processing, and related fields with the intention of sharing experimental evidence for successful approaches to feature engineering, including feature design and feature selection. We welcome papers that address these goals. We also seek to distill best practices and to discover new sources of knowledge and features previously untapped. Submissions are invited on all aspects of feature engineering for machine learning in NLP. Topics may include, but are not necessarily limited to: - Novel methods for discovering or inducing features, such as mining the web for closed classes, useful for indicator features. - Comparative studies of different feature selection algorithms for NLP tasks. - Interactive tools that help researchers to identify ambiguous cases that could be disambiguated by the addition of features. - Error analysis of various aspects of feature induction, selection, representation. - Issues with representation, e.g., strategies for handling hierarchical representations, including decomposing to atomic features or by employing statistical relational learning. - Techniques used in fields outside NLP that prove useful in NLP. - The impact of feature selection and feature design on such practical considerations as training time, experimental design, domain independence, and evaluation. - Analysis of feature engineering and its interaction with specific machine learning methods commonly used in NLP. - Combining classifiers that employ diverse types of features. - Studies of methods for defining a feature set,?for example?by iteratively expanding a base feature set. - Issues with representing and combining real-valued and categorical features for NLP tasks. INVITED TALK The workshop will include an invited talk by Andrew McCallum of the University of Massachusetts at Amherst. SUBMISSION INSTRUCTIONS The language of the workshop is English. Submitted papers should be prepared in PDF format (all fonts included) or Microsoft Word .doc format and not longer than 8 pages following the ACL style. More detailed information about the format of submissions can be found here: http://www.aclweb.org/acl2005/index.php?stylefiles Submissions should be sent as an attachment to the following email address: ringger AT microsoft DOT com . In the body of the submission email, please include the following identification information: * Title * Author(s) name(s), affiliation(s), and e-mail address(es) * Abstract: short summary (up to 5 lines) The papers themselves should contain no identifying information, and reviewing will be conducted in a blind fashion. All accepted papers will be presented in during the workshop and collected in the printed proceedings. IMPORTANT DATES - Paper submission deadline: April 20, 2005; Noon, PST (GMT-8) - Notification of acceptance: May 10, 2005 - Submission of camera-ready copy: May 17, 2005 - Workshop: June 29, 2005 ORGANIZATION Chair and contact person: Eric Ringger Microsoft Research One Microsoft Way Redmond, WA 98052 USA ringger AT microsoft DOT com Program Committee: - Simon Corston-Oliver, Microsoft Research, USA - Kevin Duh, University of Washington, USA - Matthew Richardson, Microsoft Research, USA - Oren Etzioni, University of Washington, USA - Andrew McCallum, University of Massachusetts at Amherst, USA - Dan Bikel, IBM Research, USA - Olac Fuentes, INAOE, Mexico - Chris Manning, Stanford University, USA - Kristina Toutanova, Stanford University, USA - Hideki Isozaki, NTT Communication Science Laboratories, Japan - Caroline Sporleder, University of Edinburgh, UK From ted.carnevale at yale.edu Wed Apr 6 10:16:19 2005 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Wed, 06 Apr 2005 10:16:19 -0400 Subject: Connectionists: NEURON Summer Course registration deadline approaching Message-ID: <4253EF33.50808@yale.edu> The registration deadline for the NEURON 2005 Summer Course is Monday, May 9. A few openings are still available in this course, which will be held Saturday, June 18, through Wednesday, June 22, at the Supercomputer Center on the campus of the University of California at San Diego, CA. For more information see http://www.neuron.yale.edu/neuron/sdsc2005/sdsc2005.htm or contact Ted Carnevale Psychology Dept. PO Box 208205 Yale University New Haven, CT 06520-8205 USA phone 203-432-7363 fax 203-432-7172 email ted.carnevale at yale.edu Supported in part by: National Institutes of Health National Science Foundation The San Diego Supercomputer Center Contractual terms require inclusion of the following statement: This course is not sponsored by the University of California. --Ted From Psycho.Comp at hunter.cuny.edu Wed Apr 6 17:38:07 2005 From: Psycho.Comp at hunter.cuny.edu (Aris Xanthos) Date: Wed, 06 Apr 2005 23:38:07 +0200 Subject: Connectionists: Final CFP - extended deadline: Psychocomputational Models of Language Acquisition Message-ID: <425456BF.1030307@hunter.cuny.edu> [Apologies for multiple postings] *** Final Call for Papers *** *** Extended Deadline: 11 April *** Psychocomputational Models of Human Language Acquisition Workshop at ACL 2005 29-30 June 2005 at University of Michigan Ann Arbor http://www.colag.cs.hunter.cuny.edu/psychocomp Workshop Topic -------------- The workshop, which is a follow-up to the successful workshop held at COLING in 2004, will be devoted to psychologically motivated computational models of language acquisition -- models that are compatible with, or motivated by research in psycholinguistics, developmental psychology with particular emphasis on the acquisition of syntax, though work on the acquisition of morphology, phonology and other levels of linguistic description is also welcome. The workshop will be taking place at the same time as CoNLL-2005 (http://cnts.uia.ac.be/conll/cfp.html) and we expect there to be sufficient interest for a plenary session of papers that are relevant to both audiences. There will also be a plenary session for Mark Steedman's invited talk. Invited Talks ------------- Mark Steedman, University of Edinburgh Brian MacWhinney, Carnegie Mellon University Workshop Description and Motivation ----------------------------------- In recent decades there has been a great deal of successful research that applies computational learning techniques to emerging natural language technologies, along with many meetings, conferences and workshops in which to present such research. These have generally been motivated primarily by engineering concerns. There have been only a few venues in which computational models of human (first) language acquisition are the focus. In the light of recent results in developmental psychology, indicating that very young infants are capable of detecting statistical patterns in an audible input stream, statistically motivated approaches have gained in plausibility. However, this raises the question of whether or not a psychologically credible statistical learning strategy can be successfully exploited in a full-blown psychocomputational acquisition model, and the extent to which such algorithms must use domain-specific knowledge. The principal goal of the workshop is to bring together researchers who work within computational linguistics, formal learning theory, grammatical inference, machine learning, artificial intelligence, linguistics, psycholinguistics and other fields, who have created or are investigating computational models of language acquisition. In particular, it will provide a forum for establishing links and common themes between diverse paradigms. Although research which directly addresses the acquisition of syntax is strongly encouraged, related studies that inform research on the acquisition of other areas of language are also welcome. Papers are invited on, but not limited to, the following topics: * Models that employ statistical/probabilistic grammars; * Formal learning theoretic and grammar induction models that incorporate psychologically plausible constraints; * Models that employ language models from corpus linguistics; * Models that address the question of learning bias in terms of innate linguistic knowledge versus domain general strategies * Models that can acquire natural language word-order; * Hybrid models that cross established paradigms; * Models that directly make use of or can be used to evaluate existing linguistic or developmental theories in a computational framework (e.g. the principles & parameters framework, Optimality Theory, or Construction Grammar); * Models that combine parsing and learning; * Models that have a cross-linguistic or bilingual perspective; * Empirical models that make use of child-directed corpora; * Comparative surveys, across multiple paradigms, that critique previously published studies; Paper Length: Submissions should be no longer than 8 pages (A4 or the equivalent). High-quality short papers or extended abstracts of 4 to 5 pages are encouraged. Submission and format details are below. Important Dates --------------- Please note that the turnaround time for accepted papers is quite short. Deadline for main session paper submission: April 11, 2005 Notification of acceptance: May 5, 2005 Deadline for camera-ready papers: May 17, 2005 Conference: June 29-30, 2005 Workshop Organizers ------------------- * William Gregory Sakas (Chair), City University of New York, USA (sakas at hunter.cuny.edu) * Alexander Clark, Royal Holloway, University of London, UK (alexc at cs.rhul.ac.uk) * James Cussens, University of York, UK (jc at cs.york.ac.uk) * Aris Xanthos, University of Lausanne, Switzerland (aris.xanthos at unil.ch) Program Committee ----------------- * Robert Berwick, MIT, USA * Antal van den Bosch, Tilburg University, The Netherlands * Ted Briscoe, University of Cambridge, UK * Damir Cavar, Indiana University, USA * Nick Chater, University of Warwick, UK * Stephen Clark, University of Edinburgh, UK * Walter Daelemans, University of Antwerp, Belgium and Tilburg University, The Netherlands * Elan Dresher, University of Toronto, Canada * Jeff Elman, University of California, San Diego, USA * Jerry Feldman, University of California, Berkeley, USA * John Goldsmith, University of Chicago, USA * John Hale, University of Michigan, USA * Mark Johnson, Brown University, USA * Vincenzo Lombardo, Universita di Torino, Italy * Paola Merlo, University of Geneva, Switzerland * Sandeep Prasada, City University of New York, USA * Dan Roth, University of Illinois at Urbana-Champaign, USA * Jenny Saffran, University of Wisconsin, Madison, USA * Ivan Sag, Stanford University, USA * Ed Stabler, University of California, Los Angeles, USA * Mark Steedman, University of Edinburgh, UK * Suzanne Stevenson, University of Toronto, Canada * Patrick Sturt, University of Glasgow, UK * Charles Yang, Yale University, USA Paper Submission ---------------- Submissions should follow the two-column format of ACL proceedings and should not exceed eight (8) pages, including references. We strongly recommend the use of ACL LaTeX style files or Microsoft Word Style files tailored for this year's conference. They are available at http://www.aclweb.org/acl2005/styles/. High-quality short papers or extended abstracts of 4 to 5 pages are encouraged. Electronic Submission: All submissions will be by email. Reviews will be blind, so be careful not to disclose authorship or affiliation. PDF submissions are preferred and will be required for the final camera-ready copy. Submissions should be sent as an attachment to: psycho.comp at hunter.cuny.edu. The subject line must contain the single word: Submission. Please be sure to include accurate contact information in the body of the email. Workshop contact: ----------------- email: psycho.comp at hunter.cuny.edu web: http://www.colag.cs.cuny.edu/psychocomp or William Gregory Sakas Department of Computer Science, North 1008 Hunter College, City University of New York 695 Park Avenue New York, NY 10021 USA 1 (212) 772.5211 - voice 1 (212) 772.5219 - fax sakas at hunter.cuny.edu From jst at ecs.soton.ac.uk Thu Apr 7 04:58:39 2005 From: jst at ecs.soton.ac.uk (John Shawe-Taylor) Date: Thu, 7 Apr 2005 09:58:39 +0100 Subject: Connectionists: Workshop announcements Message-ID: <200504070859.JAA14905@magpie.ecs.soton.ac.uk> Please note that two PASCAL workshops are planned back to back in early July: Statistics and Optimisation of Clustering Workshop 4-5th July, 2005, Cumberland Lodge, Windsor, UK Organisers: John Shawe-Taylor University of Southampton Shai Ben-David University of Waterloo, Canada Motivated by growing demand from many practical data management applications, clustering has recently emerged as a central research direction. While this research has resulted in many novel and sophisticated algorithms, the theory to support and evaluate these algorithms has been building up at a much slower pace. Common clustering techniques make a fundamental reliance on heuristics both in the definition of the task and the algorithms used to solve it. Many of the clustering tasks that have been formally analyzed turn out to be NP hard, and most of the theoretical work in this area has focused on finding polynomial time approximation algorithms for hard clustering problems. While such algorithms may work well for moderately sized data sets, the pattern of exponential growth of data sets suggests that even linear time algorithms may soon be too slow in practice. The next step is to consider sample-based clustering algorithms that rely on a statistical analysis of the problem. Such algorithms can be sub-linear since they can output a clustering of the data without being able to even read the entire data set. This workshop will bring together researchers from Machine Learning Statistics and Optimization Theory that have recently been developing algorithmic and statistical foundations for clustering. We wish to provide an opportunity for mutual exposure and interaction to a variety of research approaches that share the goal of providing the high efficiency required by current clustering applications while retaining a sound mathematical justification. In accordance with the PASCAL workshop programme, the workshop will be recorded on video and all presentations will be made available to PASCAL researchers. It is anticipated that contributions to the workshop will be published in an edited collection of papers. In conjunction with an agreement between the network and Springer-Verlag, the organisers are currently organising for the inclusion of the proceedings of the workshop in the Lecture Notes in Computer Science series. The workshop will include some invited contributions listed below, but also solicits submissions addressing the topics covered in the workshop. Invited contributions: Shai Ben-David, Olivier Bousquet, Joachim Buhmann, Moses Charikar, For more details follow the links. Principled methods of trading exploration and exploitation Workshop 6-7th July, 2005, Cumberland Lodge, Windsor, UK Organisers: Peter Auer University of Leoben Nicol? Cesa-Bianchi Universit? degli Studi di Milano Colin de la Higuera Universit? Jean Monnet - Saint-Etienne John Shawe-Taylor University of Southampton Chris Watkins Royal Holloway, University of London Traditional off-line learning methods are often not appropriate for applications in user modelling and user interfaces since to be useful the system must learn about the user or context during the process of interaction 'on the fly'. This immediately raises the fundamental problem of trading off exploration and exploitation in that as information is learnt the system may be tempted to act in line with this insight rather than further exploring alternatives. Machine learning has developed a number of models that attempt to capture and analyse this trade-off, from the simplest bandit problem to the full Markov decision processes underlying reinforcement learning. The workshop would include tutorials covering the bandit analysis as well as its relevance to user modelling. Reinforcement learning would also be included with particular emphasis on applications in user interfaces. It is also hoped to launch a challenge in this area. This workshop comes under the Thematic Programme 4: On-line User Modelling and Reinforcement Learning and is a core meeting of the PASCAL Network. In accordance with the PASCAL workshop programme, the workshop will be recorded on video and all presentations will be made available to PASCAL researchers. It is anticipated that contributions to the workshop will be published in an edited collection of papers. In conjunction with an agreement between the network and Springer-Verlag, the organisers are currently organising for the inclusion of the proceedings of the workshop in the Lecture Notes in Computer Science series. Invited contributions: Nicolo Cesa-Bianchi, Peter Auer, and further speakers TBA. For more information about the PASCAL Network please follow the link: http://www.pascal-network.org . From kamps at in.tum.de Fri Apr 8 09:16:49 2005 From: kamps at in.tum.de (Marc de Kamps) Date: Fri, 8 Apr 2005 15:16:49 +0200 Subject: Connectionists: 3rd European Neuro-IT and Neuroengineering School (hotel information included) Message-ID: <000c01c53c3d$38b932a0$383c9f83@atknoll3> 3rd European Neuro-IT and Neuroengineering School ? Neuroengineering of Cognitive Functions ? For hotel information: see below Faculty Igor Aleksander (London, UK) Helder Araujo (Coimbra, Portugal) Christian B?chel (Hamburg, Germany) Gabriel Curio (Berlin, Germany) Andreas Engel (Hamburg, Germany) Wolfram Erlhagen (Guimaraes, Portugal) Eduardo Fernandez (Alicante, Spain) Pascal Fries (Nijmegen, The Netherlands) Vittorio Gallese (Parma, Italy) Rainer Goebel (Maastricht, The Netherlands) Auke Ijspeert (Lausanne, Switzerland) Alois Knoll (M?nchen, Germany) Peter K?nig (Osnabr?ck, Germany) Andrej Kral (Hamburg, Germany) Henry Markram (Lausanne, Switzerland) Klaus-Robert M?ller (Berlin, Germany) Miguel Nicolelis (Durham, USA) Guy Orban (Leuven, Belgium) Frank Pasemann (St. Augustin, Germany) Tim Pearce (Leicester, UK) Rolf Pfeifer (Z?rich, Switzerland) Gulio Sandini (Genua, Italy) Vittorio Sanguineti (Genua, Italy) J?rgen Schmidhuber (M?nchen, Germany) Paul Verschure (Z?rich, Switzerland) Barbara Webb (Edinburgh, UK) Mathew Wilson (Boston, USA) Jonathan Wolpaw (Albany, USA) Conditions for Participation The school is open to postdocs, researchers and other professionals working in the field of Neuro-IT, as well as for PhD students of engineering, physics, computer science, robotics, neuroscience, medicine, biology, or psychology. A total of 50 participants will be admitted. Selection will be on a competitive basis. The program committee will select participants on the basis of their publication record (evaluated relative to career status) and the relatedness of the candidate?s own research to the theme of the school. Please register at: http://www.neuro-it.net/Activities/Venice2005 Registration fee PhD students (proof of student status required): Euro 100 Postdocs with affiliation to a public institution: Euro 200 Other professionals: Euro 300 After notification of acceptance, the registration fee needs to be prepaid until May 20. The registration fee includes: admission to all lectures, welcome reception, lunch catering, coffee and soft drinks during breaks, CD with abstracts and papers of faculty members, conference booklet with abstracts and key papers. The registration fee does not include: dinners, accomodation, travel costs. The programme will also feature student presentations. After acceptance, the programm committee will ask some of the students to present their ongoing work in short talks. The organizers wish to note that the registration fee does not cover the actual costs of attendance, but all slots are subsidized by funds from the Neuro-IT network. Admission to the school is granted on the basis that postdocs and students are attending the programme at all times. Because only 50 participants can be allowed, there will be a waiting list from which additional students will be admitted in case of cancellations. Prepayments will only be refunded if the cancelled participant slot has been filled. Please submit the following information Name Affiliation Complete contact information CV Publication record (including papers, chapters, abstracts, talks) One-page description of primary research interest or project Name of supervisor or head of group PhD students: please send proof of student status (fax a signed statement of your supervisor to Mrs. te Vehne +49 89 289 18107) Important deadlines Deadline for application: April 15 Notification of acceptance: April 29 Deadline for payment of registration fee: May 20 Hotel information: See: http://www.neuro-it.net/NeuroIT/Activities/Venice2005/HotelInformation _______________________________________________ General mailing list General at neuro-it.net https://www.neuro-it.net/mailman/listinfo/general From M.Denham at plymouth.ac.uk Fri Apr 8 06:11:11 2005 From: M.Denham at plymouth.ac.uk (Mike Denham) Date: Fri, 8 Apr 2005 11:11:11 +0100 Subject: Connectionists: Four-year PhD studentships in Theoretical and Computational Neuroscience Message-ID: <52A8091888A23F47A013223014B6E9FE040728AA@03-CSEXCH.uopnet.plymouth.ac.uk> University of Plymouth Centre for Theoretical and Computational Neuroscience Four-year PhD studentships in Theoretical and Computational Neuroscience Applications are invited for two 4-year PhD studentships in the Centre for Theoretical and Computational Neuroscience at the University of Plymouth, UK. These studentships form part of a major new 1.86M UK pounds five-year research project funded by the UK Engineering and Physical Sciences Research Council entitled: "A Novel Computing Architecture for Cognitive Systems based on the Laminar Microcircuitry of the Neocortex". Collaborators on the project include Plymouth University (Mike Denham, Sue Denham, Thomas Wennekers), Manchester University (Stefano Panzeri, Piotr Dudek, Steve Furber), University College London (Michael Hausser, Arnd Roth), Edinburgh University (Mark van Rossum, David Willshaw), Oxford University (Jan Schnupp), and London University School of Pharmacy (Alex Thomson), plus a number of leading European research groups. The persons appointed to these studentships will become part of a team of three postdocs and six PhD students engaged on the project in the collaborating institutions, and planned regular project meetings will ensure a close collaboration across this team and with the project investigators listed above. The two PhD studentships funded through the research project at Plymouth will be specifically related to the following research areas: 1. Learning rules for experience-dependent and adaptation-induced plasticity in the developed cortical microcircuit; 2. Spatiotemporal dynamics of feature selectivity in primary visual cortex. Applicants must also be able to demonstrate a capability to undertake and benefit from research training through to completion to the standard necessary to qualify for a PhD. Applicants for the studentships must therefore have a good first (bachelors) degree, or a masters degree, in a relevant subject area, strong academic references, and a demonstrable interest in carrying out research in the field of theoretical and computational neuroscience, eg through prior study in the area. Candidates must also possess basic mathematical and programming abilities. However, the four-year duration of the studentships will enable candidates to develop these abilities, and their knowledge and skills in neuroscience and relevant cross-disciplinary areas, in the first year of study through taught courses in the Centre and in the collaborating institutions. The studentships will be available to be taken up at the start of the Autumn Term at the end of September 2005. The studentships will cover the full costs of university tuition fees at the UK/EU level*, together with a tax-free stipend for living expenses (currently in the region of 12,000 UK pounds per annum). *In this respect, the studentships only cover the full tuition costs of candidates resident in the UK or other EU countries; however applications will be considered from non-EU candidates, for whom additional funding may be available to cover the shortfall in tuition fees. Informal enquiries about the studentships should be made in the first instance to Professor Mike Denham, Centre for Theoretical and Computational Neuroscience, University of Plymouth, Drake Circus, Plymouth, PL4 8AA, UK; tel: +44 (0)1752 232547; email: mdenham at plym.ac.uk. Professor Mike Denham Centre for Theoretical and Computational Neuroscience Room A223 Portland Square University of Plymouth Drake Circus Plymouth PL4 8AA UK tel: +44 (0)1752 232547/233359 fax: +44 (0)1752 233349 email: mdenham at plym.ac.uk www.plymneuro.org.uk From cottrell at univ-paris1.fr Mon Apr 11 18:15:04 2005 From: cottrell at univ-paris1.fr (Marie Cottrell) Date: Tue, 12 Apr 2005 00:15:04 +0200 Subject: Connectionists: Extended deadline for WSOM'2005 Message-ID: <5.0.2.1.2.20050412000742.03bf4688@asterix.univ-paris1.fr> ------------------------------------- WSOM'2005 deadline extended Due to numerous requests, the deadline for paper submission to the WSOM'2005 conference (Workshop on Self-Organizing Maps, Paris, 5-8 September 2005) has been extended. New (final) deadline: Tuesday 19 April, midnight More information about the WSOM conference, including topics and paper submission guidelines, may be found at http://samos.univ-paris1.fr/wsom/wsom05.html. Marie Cottrell, Organization chairman -------------------------------------- ************************************************ Marie Cottrell Tel et fax(prof): 33 1 44 07 89 22 SAMOS-MATISSE Universite Paris 1 E-mail : cottrell at univ-paris1.fr http://samos.univ-paris1.fr Postal address : 90, rue de Tolbiac 75634 PARIS CEDEX 13 Address of the laboratory : 72, rue Regnault 75013 Paris (m?tro Porte d'Ivry) From doya at irp.oist.jp Thu Apr 14 01:10:38 2005 From: doya at irp.oist.jp (Kenji Doya) Date: Thu, 14 Apr 2005 14:10:38 +0900 Subject: Connectionists: Okinawa Computational Neuroscience Course 2005: Final Call for Applications Message-ID: Apologies for multiple postings, but here is a reminder that the deadline of application for OCNC2005 is coming soon. Abstracts of all the lectures are now on the web. We will again have support for travel and lodging, at a seaside resort overlooking coral reefs. Best wishes, Kenji Doya **************************************************************** Call for Applications OKINAWA COMPUTATIONAL NEUROSCIENCE COURSE 2005 http://www.irp.oist.jp/ocnc/2005 Application deadline: APRIL 20TH, 2005 Date: July 1st to 10th, 2005 Place: Rizzan Sea-Park Hotel, Tancha Bay (http://www.rizzan.co.jp) Onna village, Okinawa, Japan Theme: Predictions and Decisions Lectures by leading theoretical and experimental neuroscientists will be given in the morning and afternoon, and the evening will be open for free discussions and student projects. Confirmed Lecturers: Bernard Balleine (UCLA) Andrew G. Barto (University of Massachusetts) Nathaniel Daw (Gatsby Computational Neuroscience Unit, UCL) Peter Dayan (Gatsby Computational Neuroscience Unit, UCL) Kenji Doya (Initial Research Project, OIST) Mitsuo Kawato (ATR, Computational Neuroscience Laboratories) Minoru Kimura (Kyoto Prefectural University of Medicine) Daeyeol Lee (University of Rochester) John O'Doherty (California Institute of Technology) Anitha Pasupathy (MIT) Masamichi Sakagami (Tamagawa University) Wolfram Schultz (University of Cambridge) Reza Shadmehr (Johns Hopkins University) Stefan Schaal (University of Southern California) Leo Sugrue (Stanford University) Jun Tanji (Tohoku University) Student Projects: a) basic computing (for students new to modeling) b) computational modeling c) psychophysical experiments Each student will present his/her current work at the beginning of the course and the summary of his/her project work at the end of the course. Co-organizers: Peter Dayan, Gatsby Computational Neuroscience Unit Kenji Doya, Okinawa Institute of Science and Technology Masamichi Sakagami, Tamagawa University Advisory Board: Sydney Brenner, Salk Institute Masao Ito, RIKEN Brain Science Institute Terrence Sejnowski, Salk Institute Susumu Tonegawa, MIT Torsten Wiesel, Rockfeller University Sponsors: Okinawa Institute of Science and Technology Project, Cabinet Office, Japan Integrative Research Project for Brain Function Center of Excellence Program, Tamagawa University Japanese Neural Network Society ******* Application ******* We invite graduate students and postgraduate researchers to participate in the course. Please send the following by e-mail (ocnc at irp.oist.jp) or the web application page by APRIL 20TH, 2005. 1) First name, 2) Middle initial (if any), 3) Family name, 4) Degree, 5) Date of birth, 6) Gender, 7) Nationality, 8) Affiliation, 9) Position, 10) Advisor, 11) Postal address, 12) Phone, 13) Fax, 14) E-mail, 15) Web page (if any), 16) Educational background, 17) Work experience, 18) List of publications, 19) Research interests (up to 500 words), 20) Motivations for attending the course (up to 500 words), 21) Two referees whom can ask recommendations (names, affiliations, e-mail addresses), 22) Need for travel support, 23) How you learned about the course. We will accept 30 students based primarily on their research interests (19) and motivations (20). We will also consider the balance of members' research disciplines, geographic origins, and genders. Recommendation letters are not required for application; we may contact some of the referees to help us make difficult decisions. The sponsor will provide lodging and meals during the course. Support for roundtrip airfare to Okinawa will be considered for students without funding. The result of selection will be informed to applicants via e-mail by May 10th. ******* Secretariat ******* Okinawa Computational Neuroscience Course c/o Initial Research Project, Okinawa Institute of Science and Technology 12-22 Suzaki, Gushikawa Okinawa 904-2234, Japan Phone: +81-98-921-3933 Fax: +81-98-921-3873 Email: ocnc at irp.oist.jp For more information, please visit the web page: http://www.irp.oist.jp/ocnc/2005 ---- Kenji Doya Initial Research Project, Okinawa Institute of Science and Technology 12-22 Suzaki, Uruma, Okinawa 904-2234, Japan Phone:+81-98-921-3843; Fax:+81-98-921-3873 http://www.irp.oist.jp/ From tino at jp.honda-ri.com Sun Apr 17 22:09:57 2005 From: tino at jp.honda-ri.com (Tino Lourens) Date: Mon, 18 Apr 2005 11:09:57 +0900 Subject: Connectionists: TiViPE: Spend more time on research and less on coding. Message-ID: <426316F5.8010205@jp.honda-ri.com> Dear all, I am pleased to announce visual programming environment TiViPE. If you would like to program faster, need a rapid prototyping tool, would like to modify a program while it is active, would like to integrate code (C, C++, Fortran, or Java) with minimal additonal effort then TiViPE might be the appropriate solution. Actually, I wanted a program that could wrap any routine into a graphical environment without programming and with little additional effort. Since, such a migration process is essential for users to move from textual programming to graphical programming. In this respect TiViPE provides a major difference to for instance AVS or Khoros. - TiViPE includes already a considerable number of useful icons for image processing and includes most of my research on early vision (center-surround, simple-, complex, endstopped cells, etc.) and graphmatching. - TiViPE has been developed under Linux, but uses the platform independent Qt-library. Ports to Mac, and Windows will be made in the second half of 2005. - TiViPE can be downloaded from: http://www.dei.brain.riken.jp/~emilia/Collaboration/Tino/TiViPE/index.html On that website, you will find more information about TiViPE, as well as two optional libraries can be used to provide the environment with 1. networking support through socket communication 2. merging support to compile a graphical program to a single icon and executable. Please enjoy. With kind regards, Tino Lourens -- Tino Lourens, Ph.D. Honda Research Institute Japan Co., Ltd. 8-1 Honcho, Wako-shi, Saitama, 351-0114, Japan Tel: +81-48-462-2121 (Ext.) 6806 mailto: tino at jp.honda-ri.com Fax: +81-48-462-5221 From masulli at disi.unige.it Mon Apr 18 06:57:08 2005 From: masulli at disi.unige.it (Francesco Masulli) Date: Mon, 18 Apr 2005 12:57:08 +0200 Subject: Connectionists: CFP: CIBB 2005 - Crema, ITALY Message-ID: <200504181257.08424.masulli@disi.unige.it> CALL FOR PAPERS CIBB 2005 Second International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics Crema, ITALY -- September 15-17, 2005 Meeting Website: http://cibb05.disi.unige.it/ CIBB 2005 addresses a cutting edge area of application of Neural Networks, Fuzzy Logic and Evolutionary Computation methods. Technical areas include, but are not limited to: - Data and methods for prognosis - Data and methods for diagnosis - Integration of clinical and genetic data - Proteomics - Pharmacogenetic CIBB 2005 is jointly organized by - BIOPATTERNS, European Network of Excellence on Computational Intelligence for Biopattern analysis in Support of eHealthcare - INNS, International Neural Network Society - SIREN, Italian Neural Networks Society CIBB 2005 will took place at Dipartimento di Tecnologie dell'Informazione Universita' degli Studi di Milano via Bramante 65, I-26013 Crema, ITALY in connection with WILF 2005 - Sixth International Workshop on Fuzzy Logic and Applications (http://dsa.uniparthenope.it/wilf2005/) All accepted papers submitted by registered participants to WILF 2005 will be included in the proceedings book of WILF 2005, that will be published by an international Publisher. Important Dates Submission deadline: 30 May 2005 Notification of acceptance: 30 June 2005 Camera ready papers due: 15 July 2005 Meeting: 15-17 September 2005 Submission of papers: Papers must not be longer than 6 pages, including a cover sheet stating: (1) Paper title; (2) Keywords; (3) Authors names and affiliations; (4) Corresponding author's name and contact details, including telephone/fax numbers and e-mail address. For electronic submission refer to the CIBB 2005 web site http://cibb05.disi.unige.it/. Chairs Francesco Masulli University of Pisa (Italy) Antonina Starita University of Pisa (Italy) Roberto Tagliaferri University of Salerno (Italy) International Program Committee Alexandru Floares, Oncological Institute Cluj-Napoca, Romania Jon Garibaldi, University of Nottingham, UK Nik Kasabov, Auckland University of Technology, NZ Natalio Krasnogor, University of Nottingham, UK Evangelia Micheli-Tzanakou, Rutgers University, NJ - USA Sushmita Mitra, Indian Statistical Institute Kolkata, India Alberto Paccanaro,Yale University, CT, USA David Alejandro Pelta, University of Granada, Spain Udo Seiffert, Leibniz Institute, Gatersleben, Germany L?onard Studer, ABMI SA, Dorigny Lausanne, Switzerland Anna Tramontano, University of Rome "La Sapienza", Italy From ted.carnevale at yale.edu Mon Apr 18 21:00:20 2005 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 18 Apr 2005 21:00:20 -0400 Subject: Connectionists: Reminder: NEURON Summer Course Message-ID: <42645824.50900@yale.edu> Only 4 weeks left to register for the NEURON Summer Course! A few seats remain open for this course, which will be held at the Supercomputer Center at UCSD, Saturday, June 18, through Wednesday, June 22. Avoid the last minute rush! For more information see http://www.neuron.yale.edu/neuron/sdsc2005/sdsc2005.htm or contact Ted Carnevale Psychology Dept. PO Box 208205 Yale University New Haven, CT 06520-8205 USA phone 203-432-7363 fax 203-432-7172 email ted.carnevale at yale.edu Supported in part by: National Institutes of Health National Science Foundation The San Diego Supercomputer Center Contractual terms require inclusion of the following statement: This course is not sponsored by the University of California. --Ted From skoenig at usc.edu Mon Apr 18 22:49:01 2005 From: skoenig at usc.edu (Sven Koenig) Date: Mon, 18 Apr 2005 19:49:01 -0700 (PDT) Subject: Connectionists: CFP: JMLR Special Topic on Learning in Large Probabilistic Environments Message-ID: CALL FOR PAPERS Journal of Machine Learning Research Special Topic on Learning in Large Probabilistic Environments Guest Editors Sven Koenig, Shie Mannor and Georgios Theocharous http://www.jmlr.org/cfp/llpe.html We invite papers on learning in large probabilistic environments for a special topic of the Journal of Machine Learning Research (JMLR). One of the fundamental problems of artificial Intelligence is how to enable systems (for example, mobile robots, manufacturing systems, or diagnostic systems) embedded in complex environments to achieve their long-term goals efficiently. A natural approach is to model such systems as agents that interact with their environment through actions, perceptions and rewards. These agents choose actions after every observation, aiming to maximize their long-term reward. Learning allows them to improve their initial strategy based on the history of successful and unsuccessful interactions with the environment. This special topic is intended to serve as an outlet for recent advances in learning in such environments, often called reinforcement learning. We welcome both theoretical advances in this field as well as detailed reports on applications of learning in large probabilistic domains. Topics of interest include: * Theoretical foundations of learning in large probabilistic environments. * Completely and partially observable Markov decision process models (MDPs) and similar models. Learning with factored state or action spaces, continuous state spaces, action spaces or time models, hybrid models, relational learning, concurrency. * Heuristics and approximations. Policy and value function approximations, Monte Carlo and advanced simulation methods. * Spatio-temporal abstractions. Dynamic factorization, hierarchy and relational structure. * Interactive learning. Guided exploration, combining supervised and unsupervised learning, shaping, and learning from very few examples. * Learning in complex systems. Function approximation, dimensionality reduction, feature selection for learning, and alternative state representations. * Cooperative and competitive multi-agent reinforcement learning. Learning in nonstationary domains and stochastic, network, and dynamic games. * Real world applications. Medicine, finance, robotics, manufacturing, security, etc. Submission procedure: Submit papers to the standard JMLR submission system http://jmlr.csail.mit.edu/manudb Please include a note stating that your submission is for the special topic on Learning in Large Probabilistic Environments. Accepted papers will be published in JMLR as they become available. Important Dates: * Submission due: June 1st, 2005 * Decision: September 1st, 2005 * Final version due: November 1st, 2005 Early submissions are encouraged, and will be handled immediately following the submission. For further details or enquiries, please contact the guest editors: Sven Koenig (skoenig at usc.edu) Shie Mannor (shie at ece.mcgill.ca) Georgios Theocharous (georgios.theocharous at intel.com) From masulli at disi.unige.it Thu Apr 21 06:06:33 2005 From: masulli at disi.unige.it (Francesco Masulli) Date: Thu, 21 Apr 2005 12:06:33 +0200 Subject: Connectionists: CFP: Post-IJCNN2005 workshop on COMPUTATIONAL INTELLIGENCE APPROACHES FOR THE ANALYSIS OF BIOINFORMATICS DATA Message-ID: <200504211206.33559.masulli@disi.unige.it> CALL FOR PAPERS Post-IJCNN2005 workshop on COMPUTATIONAL INTELLIGENCE APPROACHES FOR THE ANALYSIS OF BIOINFORMATICS DATA Hilton Montreal Bonaventure Hotel, Montr?al, Qu?bec, Canada August 5th, 2005 Workshop website http://ci-bio.disi.unige.it/ Important Dates Abstract submission deadline: 10 May 2005 Notification of acceptance: 20 May 2005 Papers due: 15 June 2005 Workshop: 5 August 2005 Scope & Topics Bioinformatics is a fast growing scientific area aimed at managing, analyzing and interpreting information from biological data, sequences and structures. In the past few years, many Computational Intelligence approaches have been successfully applied to the solution of complex problems typical of this field, including signal and image processing, clustering, feature selection, data visualization, and data mining. This workshop will present surveys and contributed papers covering differents areas where neural, fuzzy, and genetics approaches have been succesfully applied to the analysis of Bioinformatics data. Contributions to the Workshop We request two kinds of contributions: * surveys papers, giving overviews of innovative Computational Intelligence approaches to a specific Bioinformatics area * standard papers, presenting new results Standard papers accepted as oral will be presented in a slot of 15-20 min, while survey papers will have a slot of 30-60 min for oral presentation (details will be communicated to the authors by the end of June). Workshop organizers: Francesco Masulli Dept Computer Science Univ. Pisa Largo Pontecorvo 3 I-56127 Pisa - Italy Phone +39010 353 6604 fax +39010 353 6699 email Masulli at di.unipi.it Roberto Tagliaferri Dipartimento di Matematica ed Informatica, Universit? di Salerno 84084 Fisciano (Sa) - Italy Phone: +39 089 963357 fax: +39089 963307 e-mail: rtagliaferri at unisa.it ------------------------------------------------------- From cindy at bu.edu Mon Apr 25 09:54:22 2005 From: cindy at bu.edu (Cynthia Bradford) Date: Mon, 25 Apr 2005 09:54:22 -0400 Subject: Connectionists: Neural Networks 18(3) 2005 Message-ID: <200504251354.j3PDsN4F004480@kenmore.bu.edu> NEURAL NETWORKS 18(3) Contents - Volume 18, Number 3 - 2005 ------------------------------------------------------------------ ***** Neuroscience and Neuropsychology ***** A model of smooth pursuit in primates based on learning the target dynamics Tomohiro Shibata, Hiromitsu Tabata, Stefan Schaal, and Mitsuo Kawato Information theory, novelty, and hippocampal responses: Unpredicted or predictable? Bryan A. Strange, Andrew Duggins, William Penny, Raymond J. Dolan, and Karl J. Friston ***** Mathematical and Computational Analysis ***** Dynamical behaviors of Cohen-Grossberg neural networks with discontinuous activation functions Wenlian Lu and Tianping Chen Global exponential stability of delayed competitive neural networks with different time scales Hongtao Lu and Zhenya He An asymptotic statistical analysis of support vector machines with soft margins Kazushi Ikeda and Tsutomu Aoishi ***** Engineering and Design ***** Improved local learning rule for information maximization and related applications Ralph Linsker The dynamic wave expansion neural network model for robot motion planning in time-varying environments Dmitry V. Lebedev, Jochen J. Steil, and Helge J. Ritter ***** Technology and Applications ***** Self-organizing information fusion and hierarchical knowledge discovery: A new framework using ARTMAP neural networks Gail A. Carpenter, Siegfried Martens, and Ogi J. Ogas Predictive neural networks for gene expression data analysis Ah-Hwee Tan and Hong Pan ***** Book Review ***** Review of "Exploratory analysis and data modeling in functional neuroimaging", Friedrich T. Sommer and Andrzej Wichert (editors) by Alfonso Nieto-Castanon 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 Y 13,000 Neural Networks (plus Y 2,000 enrollment fee) $20 (student) SEK 460 Y 11,000 (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- membership without $30 SEK 200 not available Neural Networks to non-student (subscribe through another society) Y 5,000 student (plus Y 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 7600 Terrace Avenue, Ste. 203 Middleton WI 53562 USA 608 831 0584, ext. 138 (phone) 608 831 5122 (fax) srees at reesgroupinc.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 JNNS Secretariat c/o Fuzzy Logic Systems Institute 680-41 Kawazu, Iizuka Fukuoka 820-0067 Japan 81 948 24 2771 (phone) 81 948 24 3002 (fax) jnns at flsi.cird.or.jp http://www.jnns.org/ ---------------------------------------------------------------------------- From jain_shaloo at hotmail.com Tue Apr 26 18:54:42 2005 From: jain_shaloo at hotmail.com (pramod gupta) Date: Tue, 26 Apr 2005 18:54:42 -0400 Subject: Connectionists: Call for papers - reminder Message-ID: _______________________________________________________________________________ Verification, Validation and Certification of Neuro-Adaptive Controllers in Safety-Related Areas Montreal, Canada, Friday, August 5, 2005 A Workshop in conjunction with the International Joint Conference on Neural Networks 2005 Workshop Outline Over the recent years, artificial Neural Networks (NNs) have found their way into various safety-related and safety-critical areas, like transportation, avionics, environmental monitoring and control, and medical applications.Quite often, these applications (using NN techniques ranging from classification to monitoring and control) proved to be highly successful, leading from a pure research prototype into a serious experimental system (e.g., a neural-network-based flight-control system test-flown on a manned NASA F-15 aircraft) or a commercial product (e.g., Sharp's Logi-cook). However, the general question of how to make sure that the NN-based adaptive control system performs as expected in all cases has not yet been addressed satisfactorily. While theory and concepts of adaptive systems and intelligent control have been studied in depth over the past decade or so, only very little attention has been paid to the issue of validating the correctness and safety of their operation. All safety-related software applications require careful verification and validation (V\&V) of the software components, ranging from extended testing to full-fledged certification procedures (e.g., DO178-B). The adaptive nature of neural networks requires a significantly different approach to verification and validation than used for traditional software, since dynamic adaptation of parameters, iterative numerical algorithms, and complex control architectures renders traditional approaches to V\&V impracticable. Many prototypical/experimental application of neural networks in safety-related areas have demonstrated superior behavior and practical usefulness. Unless, however, methods and techniques have been developed which are capable of assuring the correctness and performance of a neural-network based system, NN applicability in safety-critical areas is substantially limited. The purpose of the workshop is to bring together researchers and users of learning and adaptive systems and control systems in order to create a forum for discussing recent advances in verification, validation, and testing of learning systems, to understand better the practical requirements for developing and deploying neuro-adaptive, and to inspire research on new methods and techniques for verification, validation, and testing. Topics of Interest Topics of interest include but are not limited to: applications of learing and adaptive methods and NNs in safety-critical areas and experience/lessons learned. applications of collaborative filtering problems, node modeling for belief networks and dependency networks, sequential decision making tasks, diagnosis problems, autonomous systems, robotics, and security, etc. techniques, tools, and methods to assess and guarantee the performance of a NN, e.g., statistical (Bayesian) methods, rule extraction with subsequent V&V, methods for convergence/stability analysis, dynamic monitoring of the NN behavior, etc., V&V techniques that are specifically suitable for on-line trained and adaptive systems, and software development, V\&V, and certification processes for learning and adaptive systems. Important Dates: Authors should submit a PDF file of their paper to schumann AT email.arc.nasa.gov Submission of papers: April 27, 2005 Notification of acceptance: May 4, 2005 Camera-ready copy: May 15, 2005 Workshop: August 5, 2005 Workshop organizers Johann Schumann, RIACS/NASA Ames, schumann AT email.arc.nasa.gov (650)604-0941 Pramod Gupta, QSS Inc/ NASA Ames, pgupta AT email.arc.nasa.gov (650)604-1824 Dragos Margineantu, The Boeing Company, dragos.d.margineantu AT boeing.com Program Committee B. Cukic, WVU S. Jacklin, NASA Ames T. Menzies, PSU A. Mili, NJIT M. Richard, NASA DFRC F. Sheldon, ORNL -------------------------------------------------------------------------------- For questions or comments, please send email to schumann AT email.arc.nasa.gov From robbie at bcs.rochester.edu Tue Apr 26 09:10:27 2005 From: robbie at bcs.rochester.edu (Robert Jacobs) Date: Tue, 26 Apr 2005 09:10:27 -0400 Subject: Connectionists: postdoc position available Message-ID: <5.1.1.6.0.20050426090822.01c30ac8@bcs.rochester.edu> A postdoctoral position is available in the lab of Robert Jacobs, Department of Brain and Cognitive Sciences, University of Rochester. The lab focuses on computational and experimental studies of learning, often in the context of visual or multisensory perception. For example, members of our lab work on defining statistically optimal models of aspects of perception, the development of novel machine learning algorithms for efficiently learning to perform perceptual tasks, and perceptual experiments with humans that compare human performance with Bayesian optimal performance and with the performance of relevant machine learning algorithms. The postdoctoral fellow will be part of a larger community dedicated to the study of learning and developmental plasticity. Applicants must be U.S. citizens or permanent residents. Applicants should send a vita, research statement, recent publications, and the names of three individuals who can write letters of recommendation to: LDB Postdoctoral Search Committee Department of Brain and Cognitive Sciences Meliora Hall, River Campus University of Rochester Rochester, NY 14627-0268 More information about our lab can be obtained at http://www.bcs.rochester.edu/people/robbie/robbie.html Information about the Department of Brain and Cognitive Sciences can be obtained at http://www.bcs.rochester.edu ---------------------------------------------------------------------------------------- Robert Jacobs Department of Brain and Cognitive Sciences University of Rochester Rochester, NY 14627-0268 phone: 585-275-0753 fax: 585-442-9216 email: robbie at bcs.rochester.edu web: http://www.bcs.rochester.edu/people/robbie/robbie.html From seiffert at ipk-gatersleben.de Tue Apr 26 06:13:30 2005 From: seiffert at ipk-gatersleben.de (Udo Seiffert) Date: Tue, 26 Apr 2005 12:13:30 +0200 Subject: Connectionists: Book Announcement: Bioinformatics using Computational Intelligence Paradigms Message-ID: <426E144A.5050103@ipk-gatersleben.de> Dear Connectionists, Please find attached an announcement of a new book on Bioinformatics using Computational Intelligence Paradigms recently published by Springer. Table of Contents: Medical Bioinformatics: Detecting Molecular Diseases with Case-Based Reasoning Ralf Hofestaedt and Thoralf Toepel Prototype Based Recognition of Splice Sites Barbara Hammer, Marc Strickert, and Thomas Villmann Content Based Image Compression in Biomedical High-Throughput Screening Using Artificial Neural Networks Udo Seiffert Discriminative Clustering of Yeast Stress Response Samuel Kaski, Janne Nikkilae, Eerika Savia, and Christophe Roos A Dynamic Model of Gene Regulatory Networks Based on Inertia Principle Florence d'Alch? Buc, Pierre-Jean Lahaye, Bruno-Edouard Perrin, Liva Ralaivola, Todor Vujasinovic, Aur?lien Mazurie, and Samuele Bottani Class Prediction with Microarray Datasets Simon Rogers, Richard D. Williams, and Colin Campbell Random Voronoi Ensembles for Gene Selection in DNA Microarray Data Francesco Masulli and Stefano Rovetta Cancer Classification with Microarray Data Using Support Vector Machines Feng Chu and Lipo Wang Artificial Neural Networks for Reducing the Dimensionality of Gene Expression Data Ajit Narayanan, Alan Cheung, Jonas Gamalielsson, Ed Keedwell, and Christophe Vercellone Further information may be obtained at: http://www.springeronline.com/sgw/cda/frontpage/0,11855,5-147-22-37888088-0,00.html For your convenience I add a suggestion for its BibTex entry: @BOOK{SffJainSchw05, editor = Udo Seiffert and Lakhmi C. Jain and Patrick Schweizer, title = Bioinformatics using Computational Intelligence Paradigms, publisher = Springer-Verlag, year = 2005, address = Heidelberg, volume = 176, series = Studies in Fuzziness and Soft Computing, ISBN = 3-540-22901-9, file = F } Kind regards, Udo Seiffert From myosioka at brain.riken.go.jp Thu Apr 28 01:15:59 2005 From: myosioka at brain.riken.go.jp (Masahiko Yoshioka) Date: Thu, 28 Apr 2005 14:15:59 +0900 (JST) Subject: Connectionists: Synchronization in an ensemble of neurons Message-ID: <20050428.141559.71092460.myosioka@brain.riken.go.jp> Dear all, We would like to announce a new paper on the theoretical study of spike synchronization in neural networks. We developed the analytical method to clarify stability of synchronization in a large ensemble neurons for arbitrary neuron dynamics and arbitrary strength of interactions. "Cluster synchronization in an ensemble of neurons interacting through chemical synapses" M. Yoshioka, Phys. Rev. E, in press. http://arxiv.org/abs/nlin.PS/0504057 In networks of periodically firing spiking neurons that are interconnected with chemical synapses, we analyze cluster state, where an ensemble of neurons are subdivided into a few clusters, in each of which neurons exhibit perfect synchronization. To clarify stability of cluster state, we decompose linear stability of the solution into two types of stabilities: stability of mean state and stabilities of clusters. Computing Floquet matrices for these stabilities, we clarify the total stability of cluster state for any types of neurons and any strength of interactions even if the size of networks is infinitely large. First, we apply this stability analysis to investigating synchronization in the large ensemble of integrate-and-fire (IF) neurons. In one-cluster state we find the bifurcation due to the change of stability of a cluster, which elucidates that in-phase synchronization of IF neurons occurs with only inhibitory synapses. Then, we investigate entrainment of two clusters of IF neurons with different excitability. IF neurons with fast decaying synapses show the low entrainment capability, which is explained by a pitchfork bifurcation appearing in two-cluster state with change of synapse decay time constant. Second, we analyze one-cluster state of Hodgkin-Huxley (HH) neurons and discuss the difference in synchronization properties between IF neurons and HH neurons. Best regards, Masahiko Yoshioka The Brain Science Institute The Institute of Physical and Chemical Research (RIKEN) From terry at salk.edu Thu Apr 28 13:00:34 2005 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 28 Apr 2005 10:00:34 -0700 (PDT) Subject: Connectionists: NEURAL COMPUTATION 17:6 In-Reply-To: <200504052123.j35LNCn69350@kepler.snl.salk.edu> Message-ID: <200504281700.j3SH0Y872819@kepler.snl.salk.edu> Neural Computation - Contents - Volume 17, Number 6 - June 1, 2005 REVIEW Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review Henrik Jacobsson NOTE Learning by Kernel Polarization Yoram Baram LETTERS A Unified Approach to Building and Controlling Spiking Attractor Networks Chris Eliasmith Synchronized Firings in the Networks of Class 1 Excitable Neurons with Excitatory and Inhibitory Connections, and their Dependences on the Forms of Interactions Takashi Kanamaru and Masatoshi Sekine A Hierarchy of Associations in Hippocampo-Cortical Systems: Cognitive Maps and Navigations Strategies J.P. Banquet, Ph.Gaussier, M. Quoy, A. Revel and Y. Burnod Evidence Evaluation for Bayesian Neural Networks Using Contour Monte Carlo Faming Liang An Ensemble of Cooperative Extended Kohonen Maps for Complex Robot Motion Tasks Kian Hsiang Low, Wee Kheng Leow, and Marcelo H. Ang, Jr. ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2005 - VOLUME 17 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $143 $90 $96.30 Institution $680 $727.60 $734 $612 $654.84 * 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 nip-lr at neuron.kaist.ac.kr Thu Apr 28 21:10:10 2005 From: nip-lr at neuron.kaist.ac.kr (Soo-Young Lee) Date: Fri, 29 Apr 2005 10:10:10 +0900 Subject: Connectionists: Volume 6 of Neural Information Processing - Letters and Reviews Message-ID: <200504290116.j3T1G2ZK019460@neuron.kaist.ac.kr> The printed version of Volume 6 (Numbers 1-3; from Januart to March 2005) of the NIP-LR (neural Information Processing - Letters and Reviews) is available. NIP-LR aims for high-quality timely-publication with double-blind review process. For online you may visit www.nip-lr.info or bsrc.kaist.ac.kr/NIP-LR. For your free sample copy of the printed version please send me an e-mail to nip-lr at neuron.kaist.ac.kr ---------------------------------------------------------------------------- --------- Contents: Vol. 6, No. 1, January 2005 Reviews Blind Source Separation and Independent Component Analysis: A Review Seungjin Choi, Andrzej Cichocki, Hyung-Min Park, and Soo-Young Lee Vol. 6, No. 2, February 2005 Letters Variable Discharge Pattern and Contrast Invariant Orientation Tuning of a Simple Cell: A Modeling Study Akhil R. Garg, Basabi Bhaumik, and Klaus Obermayer Vol. 6, No. 3, March 2005 Letters Modeling with Recurrent Neural Networks using Compensatory Neuron Model Gunjan Gupta, R. N. Yadav, P. K Kalra, and J. John Removal of Hidden Neurons by Crosswise Propagation Xun Liang From ted.carnevale at yale.edu Fri Apr 29 16:28:11 2005 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Fri, 29 Apr 2005 16:28:11 -0400 Subject: Connectionists: ModelDB now contains source code for 158 published models Message-ID: <427298DB.7020700@yale.edu> You are being contacted as a member of the computational neuroscience community to update you on resources currently available at ModelDB. Source code for 158 published models is freely available from ModelDB http://senselab.med.yale.edu/senselab/modeldb/ ModelDB is a searchable database for convenient storage, viewing, and retrieval of source code for published computational models of neurons and networks. It is designed to stimulate the wider acceptance and growth of computational neuroscience by facilitating reproducibility and attributed reuse of models. ModelDB is "programming language neutral." Currently it has entries written for C/C++, FORTRAN, GENESIS, MATLAB, NEURON, SNNAP, and XPP, most of which are ready to run. Each model entry has links to the scientific literature to put it in the broader context of neuroscience research. Authors of published models are invited to contact Michael Hines (michael.hines at yale.edu) for assistance with entering their code into ModelDB. If your published model is already available on the web, we'd like to link to it. Simply send Michael the URL and the PubMed ID number of your modeling paper (if the latter is not available, then a bibliographic reference is fine). ModelDB is part of the SenseLab Project http://senselab.med.yale.edu/senselab/ and has close links to NeuronDB http://senselab.med.yale.edu/senselab/NeuronDB/ which contains information about cellular properties that are relevant to computational modeling. --Michael Hines From bengio at idiap.ch Fri Apr 1 01:26:24 2005 From: bengio at idiap.ch (Samy Bengio) Date: Fri, 1 Apr 2005 08:26:24 +0200 (CEST) Subject: Connectionists: call for paper: MLMI'05 workshop Message-ID: CALL FOR PAPERS: 2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms MLMI'05 http://groups.inf.ed.ac.uk/mlmi05 11-13 July 2005, Royal College of Physicians, Edinburgh, UK The second MLMI workshop is coming to Edinburgh, UK, 11-13 July, 2005 follows from the first successful MLMI'04 held in Martigny, Switzerland, June 2004 (http://www.idiap.ch/events/workshop-mlmi04/). The topics covered by the MLMI'05 workshop are the following: * human-human communication modeling * speech and visual processing * multi-modal processing, fusion and fission * multi-modal dialog modeling * human-human interaction modeling * multi-modal data structuring and presentation * multimedia indexing and retrieval * meeting structure analysis * meeting summarizing * multimodal meeting annotation * machine learning applied to the above We particularly welcome all theoretical and applied machine learning papers targeting large and complex datasets such as those involved in multimodal interaction. The workshop will be sponsored by several european and national projects, including AMI, CHIL, HUMAINE, PASCAL, SIMILAR, IM2, etc. (more information on the sponsors available on the website). Key Dates: Submission deadline 13 May 2005 Accept/reject decisions 13 June 2005 Plenary workshop takes place 11-12 July 2005 Specialist workshops take place 13 July 2005 Guidelines for submissions: The submitted papers should follow the Springer LNCS format and be 12 pages maximum per full paper. Extended abstracts of 2 pages maximum can also be submitted to be considered as posters. The best papers will then be published in an edited book, similar to MLMI'04, published as LNCS-3361: http://www.springerlink.com/openurl.asp?genre=issue&issn=0302-9743&volume=3361&issue=preprint Organization: Co-chairs: * Steve Renals, University of Edinburgh * Samy Bengio, IDIAP Programme Committee (to be confirmed): * Herve Bourlard, IDIAP * Jean Carletta, University of Edinburgh * Franciska de Jong, University of Twente [tbc] * John Garofolo, NIST * Lori Lamel, LIMSI * Jan Larsen, Technical University of Denmark [tbc] * Benoit Macq, UCL-TELE * Johanna Moore, Universirty of Edinburgh * Laurence Nigay, CLIPS-IMAG * Barbara Peskin, ICSI * Thierry Pun, University of Geneva * Marc Schr?der, DFKI * Rainer Stiefelhagen, Universitaet Karlsruhe ---- Samy Bengio Senior Researcher in Machine Learning. IDIAP, CP 592, rue du Simplon 4, 1920 Martigny, Switzerland. tel: +41 27 721 77 39, fax: +41 27 721 77 12. mailto:bengio at idiap.ch, http://www.idiap.ch/~bengio From nnrev at atr.jp Fri Apr 1 03:29:11 2005 From: nnrev at atr.jp (Neural Networks Editorial Office) Date: Fri, 1 Apr 2005 17:29:11 +0900 Subject: Connectionists: Neural Networks 18(2) Message-ID: NEURAL NETWORKS 18(2) Contents - Volume 18, Number 2 - 2005 ------------------------------------------------------------------ NEURAL NETWORKS LETTERS: Cogent confabulation Robert Hecht-Nielsen Intelligent initialization of resource allocating RBF networks Manolis Wallace, Nicolas Tsapatsoulis, and Stefanos Kollias CONTRIBUTED ARTICLES: ***** Mathematical and Computational Analysis ***** Chaotic dynamics of a behavior-based miniature mobile robot: effects of environment and control structure Md. Monirul Islam and K. Murase Adaptive algorithms for first principal eigenvector computation Chanchal Chatterjee Analysis of global exponential stability and periodic solutions of neural networks with time-varying delays He Huang, Daniel W.C. Ho, and Jinde Cao On the global output convergence of a class of recurrent neural networks with time-varying inputs Sanqing Hu and Derong Liu ***** Engineering and Design ***** NEUROM: a ROM based RNS digital neuron Giuseppe Alia and Enrico Martinelli ***** Technology and Applications ***** TAO-robust backpropagation learning algorithm Alpha V. Pernia-Espinoza, Joaquin B. Ordieres-Mere, Francisco J. Martinez-de-Pison, and Ana Gonzalez-Marcos ***** Letter to the Editor ***** Experimentally optimal nu in support vector regression for different noise models and parameter settings Athanassia Chalimourda, Bernhard Scholkopf, Alex J. Smola 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 Y 13,000 Neural Networks (plus Y 2,000 enrollment fee) $20 (student) SEK 460 Y 11,000 (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- membership without $30 SEK 200 not available Neural Networks to non-students (subscribe through another society) Y 5,000 student (plus Y 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 7600 Terrace Avenue, Ste. 203 Middleton WI 53562 USA 608 831 0584, ext. 138 (phone) 608 831 5122 (fax) srees at reesgroupinc.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 Shozo Yasui Kyushu Institute of Technology Graduate School of Life Science and Engineering 2-4 Hibikino, Wakamatsu-ku Kitakyushu 808-0196 Japan 81 93 695 6108 (phone and fax) jnns at brain.kyutech.ac.jp http://www.jnns.org/ ---------------------------------------------------------------------------- -- """""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" NEURAL NETWORKS Editorial Office ATR Computational Neuroscience Laboratories 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan TEL +81-774-95-1204 FAX +81-774-95-1236 E-MAIL nnrev at atr.jp """"""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" From oreilly at psych.colorado.edu Fri Apr 1 15:35:37 2005 From: oreilly at psych.colorado.edu (Randall C. O'Reilly) Date: Fri, 1 Apr 2005 13:35:37 -0700 Subject: Connectionists: Request: PDP++ software usage reports Message-ID: <200504011335.37667.oreilly@psych.colorado.edu> We are planning to write a grant proposal to support major enhancements to the PDP++ neural network simulation software, and need to collect some data on publications, teaching, and other usage of this software. If you have used PDP++ for simulations published in any form, please email me the reference(s) to these publications (APA format preferred, but any format will do). If you have used PDP++ for teaching, please send the name of the course, years taught, number of students, etc. (any information would be appreciated, the more the better). If you have used PDP++ for other purposes (e.g., business, forecasting, etc) please send any relevant information. Finally, if you have any feedback on the software for things that we should improve in the future, we would like to hear it. We have already begun the revisions and have a fairly detailed plan, which we will be announcing within a few weeks on the pdp-discuss email list, so your feedback would be most beneficial if it could be given in the context of these plans, but if you would rather just send feedback now, that would also be appreciated. To subscribe to the pdp-discuss email list, see the PDP++ website at: http://psych.colorado.edu/~oreilly/PDP++/PDP++.html *or* http://www.cnbc.cmu.edu/Resources/PDP++/PDP++.html Thanks! - Randy From kim at psy.mpg.de Sun Apr 3 09:52:49 2005 From: kim at psy.mpg.de (DaeEun Kim) Date: Sun, 03 Apr 2005 15:52:49 +0200 Subject: Connectionists: CFP for Workshop on Memory and Learning Mechanisms in Autonomous Robots Message-ID: <424FF531.AC6BFEC0@psy.mpg.de> Call for Papers: Workshop on Memory and Learning Mechanisms in Autonomous Robots co-located with ECAL 2005 (European Conf. on Artificial Life) http://www.ecal2005.org/workshops.html The aim of this workshop is to explore how to process memory for complex robotic tasks and how to represent/encode plasticity in robot controllers. The study of memory structure and the development of new learning algorithms to model neuronal plasticity are a central challenge for adaptive behaviour research. The workshop aims to bring together researchers interested in these topics to discuss new ideas and alternative solutions which might open up yet unexplored research lines. We encourage the submission of work which propose provocative new ideas, discuss controversial aspects on memory and learning mechanisms for autonomous adaptive agents. The topics of the workshop include, but are not limited to: mechanisms for memory and learning neural plasticity neuromodulation spiking neural networks gas-net homeostatic networks representational / non-representational memory evolution of short / long term memory evolution of learning mechanisms reinforcement learning in non-Markovian environment forward model / cerebellar network Important Dates Submission deadline: 15th May, 2005 Notification date: 15th June, 2005 Final date for camera-ready copies: 22nd, June, 2005 Organisers: Dr. Elio Tuci, IRIDIA, Universite Libre de Bruxelles, Belgium Email: etuci at ulb.ac.be Dr. DaeEun Kim, Max Planck Institute for Human Cognitive and Brain Sciences, Germany Email: daeeun at cbs.mpg.de Program committee (confirmed) Dr. Marco Dorigo, IRIDIA, Universite Libre de Bruxelles Dr. Dario Floreano, Ecole Polytechnique Federale de Lausanne Dr. John C.T. Hallam, University of Southern Denmark Dr. Pier Luca Lanzi, Politecnico di Milano Dr. Ralf Moeller, University of Bielefeld Dr. Stefano Nolfi, Institute of Cognitive Sciences and Tecnologies Dr. Ezequiel Di Paolo, University of Sussex Dr. Juergen Schmidhuber, Dalle Molle Inst. for Artificial Intelligence Dr. Tom Ziemke, University of Skoevde You may find more information at http://www.psy.mpg.de/home/kim/www/memory/memory_workshop.html Thank you. ------------------------------------------------------------------------------------------- DaeEun Kim Cognitive Robotics Max Planck Institute for Human Cognitive and Brain Sciences Amalienstr. 33 80799, Munich Germany Tel) +49-89-38602-333 Fax) +49-89-38602-199 ------------------------------------------------------------------------------------------- From ftupindr at ti.uni-bielefeld.de Mon Apr 4 04:17:18 2005 From: ftupindr at ti.uni-bielefeld.de (Ralf Moeller) Date: Mon, 04 Apr 2005 10:17:18 +0200 Subject: Connectionists: doctoral/postdoctoral researcher: local PCA Message-ID: <4250F80E.6010706@ti.uni-bielefeld.de> Doctoral/postdoctoral researcher Faculty of Technology Bielefeld University, Germany The Computer Engineering Group at the Faculty of Technology of Bielefeld University (http://www.ti.uni-bielefeld.de), offers a temporary position as doctoral or postdoctoral researcher (salary BAT IIa, for two years) in a DFG-funded research project "Local PCA methods for internal sensorimotor models", starting July 1, 2005. The project aims at improving and extending unsupervised neural learning methods where data manifolds are approximated based on local principal component analysis. The methods will be applied to the training of inverse and forward models in the context of robot control tasks. The applicant should hold a university's Master's or Diploma degree in computer science, engineering, mathematics, or physics. A background in image and signal processing, neuroinformatics and robotics is useful. Strong programming skills and advanced mathematical competences are expected. Bielefeld University encourages disabled people to apply. Applications by women are expressly requested; in the case of comparable competences and qualification, women will preferably be considered if there are no dominating reasons arising from the person of another applicant. Part-time employment is possible. Please send your application with the usual documents (including the name and email addresses of two referees) until April 30, 2005 to AG Technische Informatik Sekretariat, Frau Angelika Deister Technische Fakult?t Universit?t Bielefeld Postfach 100131 D-33501 Bielefeld Germany or by email to bewerbung-dfg at ti.uni-bielefeld.de From Nicolas.Rougier at loria.fr Tue Apr 5 10:47:47 2005 From: Nicolas.Rougier at loria.fr (Nicolas Rougier) Date: Tue, 05 Apr 2005 16:47:47 +0200 Subject: Connectionists: Postdoctoral position available at INRIA/Lorraine, France Message-ID: <4252A513.3020202@loria.fr> A postdoctoral position is available at INRIA/Lorraine, France. Deadline for submitting candidature is 22 of April 2005. (Sorry if you received multiple copies of this document). Context: -------- Cortex project with INRIA Lorraine is developping computational models of neural networks inspired by biology (computational neurosciences) which aimed at mixing knowledge from neuroscience together with robust and distributed computation at both structural and functional level. Our goals are to evaluate those models against experimental data from neurosciences but also to design some tecnological software that can be used, for example, in autonomous robotic. Recently, we designed a distributed and dynamic model of visual attention based on the Continuum Neural Field Theory that allows to sequentially focus salient locations in an image. A working memory system ensures that the corresponding objects are only focused once, even if they are moving around, such that the visual search is efficient. The model has been implemented on a robotic platform in order to search for objects such as fruits in a natural scene. Objectives: ----------- We now aim at evaluating and refining this model by introducing behavioral data because we think such data from psychology would help in a better control and memorization of fixation points while exploring a visual scene. More precisely, such data could help validate the model robustness and pinpoint the nature of information flows between posterior and frontal cortex. Ultimately, this study would help in the design of a model more closely related to our knowledge of the human attention circuitry. Methods: -------- In a first time, candidate will help in evaluating the model in terms of biological plausibility with focus on the implied structures and their respective role. This study would possibly lead to the re-organization of information flows within the model in order to fit neuro-anatomical data. In a second time, candidate would help evaluating the model against common human psychological experiments concerning selective visual attention by proposing and implementing some evaluation protocol. Finally, candidate will help in extending the model by considering the sequence of fixation points on a visual scene. An expertise in perception, spatial relationships and information integration is, thus required. Duration of the fellowship (months): ------------------------------------ 12.0 Sought profile of the candidate: -------------------------------- We aim at recruiting a post-doctoral fellow in neurosciences having a strong background in both visual attention domain and significant experience in computational modeling. Contact: -------- Nicolas Rougier, Nicolas.Rougier at loria.fr URL: ---- http://www.loria.fr/jobs/postdoc_inria/postdoc_inria?id=46 Conditions for applicants ------------------------- * Doctoral candidates must have defended their thesis before September 1, 2005. In case the thesis has not been defended at the time of application, the thesis defense date must be explicitly indicated in the application file. * The positions are devoted to the priority research themes of the Institute, as well as to the Incentive Concerted Initiatives on Data Masses and Computer Security. However, high level applications on non priority topics will also be considered. High priority will be given to French and foreign applicants who prepared their doctorate abroad, but again every high level application will be carefully considered. * No nationality requirement. * Please complete one application file per topic proposed by the research units. * If you have obtained your doctorate from within an INRIA research unit, you cannot apply to this unit. You may however apply to other research units. Nicolas Rougier From terry at salk.edu Tue Apr 5 17:23:12 2005 From: terry at salk.edu (Terry Sejnowski) Date: Tue, 5 Apr 2005 14:23:12 -0700 (PDT) Subject: Connectionists: NEURAL COMPUTATION 17:5 In-Reply-To: <200502020553.j125rKs06193@kepler.snl.salk.edu> Message-ID: <200504052123.j35LNCn69350@kepler.snl.salk.edu> Neural Computation - Contents - Volume 17, Number 5 - May 1, 2005 NOTE Gain Control by Concerted Changes in I_A and I_H Conductances Denis Burdakov Winner-Relaxing elf-Organizing Maps Jens Christian Claussen LETTERS Image Segmentation by Networks of Spiking Neurons Joachim M. Buhmann, Tilman Lange, and Ulrich Ramacher Neural Computation - Contents - Volume 17, Number 5 - May 1, 2005 NOTE Gain Control by Concerted Changes in I_A and I_H Conductances Denis Burdakov Winner-Relaxing elf-Organizing Maps Jens Christian Claussen LETTERS Image Segmentation by Networks of Spiking Neurons Joachim M. Buhmann, Tilman Lange, and Ulrich Ramacher Neural Modeling of an Internal Clock Tadashi Yamazaki and Shigeru Tanaka Mirror Symmetric Topographic Maps Can Arise from Activity-Dependent Synaptic Changes Reiner Schulz and James A. Reggia Stochastic Optimal Control and Estimation Methods Adapted to the Noise Characteristics of the Sensoromotor System Emanuel Todorov Universal Approximation Capability of Cascade Correlation for Structures Barbara Hammer, Alessio Micheli and Alessandro Sperduti SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming Qiang Wu and Ding-Xuan Zhou Leave-One-Out Bounds for Support Vector Regression Model Selection Ming-Wei Chang and Chih-Jen Lin ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2005 - VOLUME 17 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $143 $90 $96.30 Institution $680 $727.60 $734 $612 $654.84 * 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 ringger at microsoft.com Wed Apr 6 12:03:14 2005 From: ringger at microsoft.com (Eric Ringger) Date: Wed, 6 Apr 2005 09:03:14 -0700 Subject: Connectionists: ACL 2005 Workshop on Feature Engineering for Machine Learning in NLP Message-ID: <093830707D538448B1F337432D779BA1DB7E81@RED-MSG-61.redmond.corp.microsoft.com> ---------------------------------------------------------------- SECOND CALL FOR PAPERS Feature Engineering for Machine Learning in Natural Language Processing Workshop at the Annual Meeting of the Association of Computational Linguistics (ACL 2005) http://research.microsoft.com/~ringger/FeatureEngineeringWorkshop/ ** SUBMISSION DEADLINE: April 20, 2005 ** Ann Arbor, Michigan June 29, 2005 ---------------------------------------------------------------- As experience with machine learning for solving natural language processing tasks accumulates in the field, practitioners are finding that feature engineering is as critical as the choice of machine learning algorithm, if not more so. Feature design, feature selection, and feature impact (through ablation studies and the like) significantly affect the performance of systems and deserve greater attention. In the wake of the shift away from knowledge engineering and of the successes of data-driven and statistical methods, researchers in the field of NLP are likely to make further progress by incorporating additional, sometimes familiar, sources of knowledge as features. Although some experience in the area of feature engineering is to be found in the theoretical machine learning community, the particular demands of natural language processing leave much to be discovered. This workshop aims to bring together practitioners of NLP, machine learning, information extraction, speech processing, and related fields with the intention of sharing experimental evidence for successful approaches to feature engineering, including feature design and feature selection. We welcome papers that address these goals. We also seek to distill best practices and to discover new sources of knowledge and features previously untapped. Submissions are invited on all aspects of feature engineering for machine learning in NLP. Topics may include, but are not necessarily limited to: - Novel methods for discovering or inducing features, such as mining the web for closed classes, useful for indicator features. - Comparative studies of different feature selection algorithms for NLP tasks. - Interactive tools that help researchers to identify ambiguous cases that could be disambiguated by the addition of features. - Error analysis of various aspects of feature induction, selection, representation. - Issues with representation, e.g., strategies for handling hierarchical representations, including decomposing to atomic features or by employing statistical relational learning. - Techniques used in fields outside NLP that prove useful in NLP. - The impact of feature selection and feature design on such practical considerations as training time, experimental design, domain independence, and evaluation. - Analysis of feature engineering and its interaction with specific machine learning methods commonly used in NLP. - Combining classifiers that employ diverse types of features. - Studies of methods for defining a feature set,?for example?by iteratively expanding a base feature set. - Issues with representing and combining real-valued and categorical features for NLP tasks. INVITED TALK The workshop will include an invited talk by Andrew McCallum of the University of Massachusetts at Amherst. SUBMISSION INSTRUCTIONS The language of the workshop is English. Submitted papers should be prepared in PDF format (all fonts included) or Microsoft Word .doc format and not longer than 8 pages following the ACL style. More detailed information about the format of submissions can be found here: http://www.aclweb.org/acl2005/index.php?stylefiles Submissions should be sent as an attachment to the following email address: ringger AT microsoft DOT com . In the body of the submission email, please include the following identification information: * Title * Author(s) name(s), affiliation(s), and e-mail address(es) * Abstract: short summary (up to 5 lines) The papers themselves should contain no identifying information, and reviewing will be conducted in a blind fashion. All accepted papers will be presented in during the workshop and collected in the printed proceedings. IMPORTANT DATES - Paper submission deadline: April 20, 2005; Noon, PST (GMT-8) - Notification of acceptance: May 10, 2005 - Submission of camera-ready copy: May 17, 2005 - Workshop: June 29, 2005 ORGANIZATION Chair and contact person: Eric Ringger Microsoft Research One Microsoft Way Redmond, WA 98052 USA ringger AT microsoft DOT com Program Committee: - Simon Corston-Oliver, Microsoft Research, USA - Kevin Duh, University of Washington, USA - Matthew Richardson, Microsoft Research, USA - Oren Etzioni, University of Washington, USA - Andrew McCallum, University of Massachusetts at Amherst, USA - Dan Bikel, IBM Research, USA - Olac Fuentes, INAOE, Mexico - Chris Manning, Stanford University, USA - Kristina Toutanova, Stanford University, USA - Hideki Isozaki, NTT Communication Science Laboratories, Japan - Caroline Sporleder, University of Edinburgh, UK From ted.carnevale at yale.edu Wed Apr 6 10:16:19 2005 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Wed, 06 Apr 2005 10:16:19 -0400 Subject: Connectionists: NEURON Summer Course registration deadline approaching Message-ID: <4253EF33.50808@yale.edu> The registration deadline for the NEURON 2005 Summer Course is Monday, May 9. A few openings are still available in this course, which will be held Saturday, June 18, through Wednesday, June 22, at the Supercomputer Center on the campus of the University of California at San Diego, CA. For more information see http://www.neuron.yale.edu/neuron/sdsc2005/sdsc2005.htm or contact Ted Carnevale Psychology Dept. PO Box 208205 Yale University New Haven, CT 06520-8205 USA phone 203-432-7363 fax 203-432-7172 email ted.carnevale at yale.edu Supported in part by: National Institutes of Health National Science Foundation The San Diego Supercomputer Center Contractual terms require inclusion of the following statement: This course is not sponsored by the University of California. --Ted From Psycho.Comp at hunter.cuny.edu Wed Apr 6 17:38:07 2005 From: Psycho.Comp at hunter.cuny.edu (Aris Xanthos) Date: Wed, 06 Apr 2005 23:38:07 +0200 Subject: Connectionists: Final CFP - extended deadline: Psychocomputational Models of Language Acquisition Message-ID: <425456BF.1030307@hunter.cuny.edu> [Apologies for multiple postings] *** Final Call for Papers *** *** Extended Deadline: 11 April *** Psychocomputational Models of Human Language Acquisition Workshop at ACL 2005 29-30 June 2005 at University of Michigan Ann Arbor http://www.colag.cs.hunter.cuny.edu/psychocomp Workshop Topic -------------- The workshop, which is a follow-up to the successful workshop held at COLING in 2004, will be devoted to psychologically motivated computational models of language acquisition -- models that are compatible with, or motivated by research in psycholinguistics, developmental psychology with particular emphasis on the acquisition of syntax, though work on the acquisition of morphology, phonology and other levels of linguistic description is also welcome. The workshop will be taking place at the same time as CoNLL-2005 (http://cnts.uia.ac.be/conll/cfp.html) and we expect there to be sufficient interest for a plenary session of papers that are relevant to both audiences. There will also be a plenary session for Mark Steedman's invited talk. Invited Talks ------------- Mark Steedman, University of Edinburgh Brian MacWhinney, Carnegie Mellon University Workshop Description and Motivation ----------------------------------- In recent decades there has been a great deal of successful research that applies computational learning techniques to emerging natural language technologies, along with many meetings, conferences and workshops in which to present such research. These have generally been motivated primarily by engineering concerns. There have been only a few venues in which computational models of human (first) language acquisition are the focus. In the light of recent results in developmental psychology, indicating that very young infants are capable of detecting statistical patterns in an audible input stream, statistically motivated approaches have gained in plausibility. However, this raises the question of whether or not a psychologically credible statistical learning strategy can be successfully exploited in a full-blown psychocomputational acquisition model, and the extent to which such algorithms must use domain-specific knowledge. The principal goal of the workshop is to bring together researchers who work within computational linguistics, formal learning theory, grammatical inference, machine learning, artificial intelligence, linguistics, psycholinguistics and other fields, who have created or are investigating computational models of language acquisition. In particular, it will provide a forum for establishing links and common themes between diverse paradigms. Although research which directly addresses the acquisition of syntax is strongly encouraged, related studies that inform research on the acquisition of other areas of language are also welcome. Papers are invited on, but not limited to, the following topics: * Models that employ statistical/probabilistic grammars; * Formal learning theoretic and grammar induction models that incorporate psychologically plausible constraints; * Models that employ language models from corpus linguistics; * Models that address the question of learning bias in terms of innate linguistic knowledge versus domain general strategies * Models that can acquire natural language word-order; * Hybrid models that cross established paradigms; * Models that directly make use of or can be used to evaluate existing linguistic or developmental theories in a computational framework (e.g. the principles & parameters framework, Optimality Theory, or Construction Grammar); * Models that combine parsing and learning; * Models that have a cross-linguistic or bilingual perspective; * Empirical models that make use of child-directed corpora; * Comparative surveys, across multiple paradigms, that critique previously published studies; Paper Length: Submissions should be no longer than 8 pages (A4 or the equivalent). High-quality short papers or extended abstracts of 4 to 5 pages are encouraged. Submission and format details are below. Important Dates --------------- Please note that the turnaround time for accepted papers is quite short. Deadline for main session paper submission: April 11, 2005 Notification of acceptance: May 5, 2005 Deadline for camera-ready papers: May 17, 2005 Conference: June 29-30, 2005 Workshop Organizers ------------------- * William Gregory Sakas (Chair), City University of New York, USA (sakas at hunter.cuny.edu) * Alexander Clark, Royal Holloway, University of London, UK (alexc at cs.rhul.ac.uk) * James Cussens, University of York, UK (jc at cs.york.ac.uk) * Aris Xanthos, University of Lausanne, Switzerland (aris.xanthos at unil.ch) Program Committee ----------------- * Robert Berwick, MIT, USA * Antal van den Bosch, Tilburg University, The Netherlands * Ted Briscoe, University of Cambridge, UK * Damir Cavar, Indiana University, USA * Nick Chater, University of Warwick, UK * Stephen Clark, University of Edinburgh, UK * Walter Daelemans, University of Antwerp, Belgium and Tilburg University, The Netherlands * Elan Dresher, University of Toronto, Canada * Jeff Elman, University of California, San Diego, USA * Jerry Feldman, University of California, Berkeley, USA * John Goldsmith, University of Chicago, USA * John Hale, University of Michigan, USA * Mark Johnson, Brown University, USA * Vincenzo Lombardo, Universita di Torino, Italy * Paola Merlo, University of Geneva, Switzerland * Sandeep Prasada, City University of New York, USA * Dan Roth, University of Illinois at Urbana-Champaign, USA * Jenny Saffran, University of Wisconsin, Madison, USA * Ivan Sag, Stanford University, USA * Ed Stabler, University of California, Los Angeles, USA * Mark Steedman, University of Edinburgh, UK * Suzanne Stevenson, University of Toronto, Canada * Patrick Sturt, University of Glasgow, UK * Charles Yang, Yale University, USA Paper Submission ---------------- Submissions should follow the two-column format of ACL proceedings and should not exceed eight (8) pages, including references. We strongly recommend the use of ACL LaTeX style files or Microsoft Word Style files tailored for this year's conference. They are available at http://www.aclweb.org/acl2005/styles/. High-quality short papers or extended abstracts of 4 to 5 pages are encouraged. Electronic Submission: All submissions will be by email. Reviews will be blind, so be careful not to disclose authorship or affiliation. PDF submissions are preferred and will be required for the final camera-ready copy. Submissions should be sent as an attachment to: psycho.comp at hunter.cuny.edu. The subject line must contain the single word: Submission. Please be sure to include accurate contact information in the body of the email. Workshop contact: ----------------- email: psycho.comp at hunter.cuny.edu web: http://www.colag.cs.cuny.edu/psychocomp or William Gregory Sakas Department of Computer Science, North 1008 Hunter College, City University of New York 695 Park Avenue New York, NY 10021 USA 1 (212) 772.5211 - voice 1 (212) 772.5219 - fax sakas at hunter.cuny.edu From jst at ecs.soton.ac.uk Thu Apr 7 04:58:39 2005 From: jst at ecs.soton.ac.uk (John Shawe-Taylor) Date: Thu, 7 Apr 2005 09:58:39 +0100 Subject: Connectionists: Workshop announcements Message-ID: <200504070859.JAA14905@magpie.ecs.soton.ac.uk> Please note that two PASCAL workshops are planned back to back in early July: Statistics and Optimisation of Clustering Workshop 4-5th July, 2005, Cumberland Lodge, Windsor, UK Organisers: John Shawe-Taylor University of Southampton Shai Ben-David University of Waterloo, Canada Motivated by growing demand from many practical data management applications, clustering has recently emerged as a central research direction. While this research has resulted in many novel and sophisticated algorithms, the theory to support and evaluate these algorithms has been building up at a much slower pace. Common clustering techniques make a fundamental reliance on heuristics both in the definition of the task and the algorithms used to solve it. Many of the clustering tasks that have been formally analyzed turn out to be NP hard, and most of the theoretical work in this area has focused on finding polynomial time approximation algorithms for hard clustering problems. While such algorithms may work well for moderately sized data sets, the pattern of exponential growth of data sets suggests that even linear time algorithms may soon be too slow in practice. The next step is to consider sample-based clustering algorithms that rely on a statistical analysis of the problem. Such algorithms can be sub-linear since they can output a clustering of the data without being able to even read the entire data set. This workshop will bring together researchers from Machine Learning Statistics and Optimization Theory that have recently been developing algorithmic and statistical foundations for clustering. We wish to provide an opportunity for mutual exposure and interaction to a variety of research approaches that share the goal of providing the high efficiency required by current clustering applications while retaining a sound mathematical justification. In accordance with the PASCAL workshop programme, the workshop will be recorded on video and all presentations will be made available to PASCAL researchers. It is anticipated that contributions to the workshop will be published in an edited collection of papers. In conjunction with an agreement between the network and Springer-Verlag, the organisers are currently organising for the inclusion of the proceedings of the workshop in the Lecture Notes in Computer Science series. The workshop will include some invited contributions listed below, but also solicits submissions addressing the topics covered in the workshop. Invited contributions: Shai Ben-David, Olivier Bousquet, Joachim Buhmann, Moses Charikar, For more details follow the links. Principled methods of trading exploration and exploitation Workshop 6-7th July, 2005, Cumberland Lodge, Windsor, UK Organisers: Peter Auer University of Leoben Nicol? Cesa-Bianchi Universit? degli Studi di Milano Colin de la Higuera Universit? Jean Monnet - Saint-Etienne John Shawe-Taylor University of Southampton Chris Watkins Royal Holloway, University of London Traditional off-line learning methods are often not appropriate for applications in user modelling and user interfaces since to be useful the system must learn about the user or context during the process of interaction 'on the fly'. This immediately raises the fundamental problem of trading off exploration and exploitation in that as information is learnt the system may be tempted to act in line with this insight rather than further exploring alternatives. Machine learning has developed a number of models that attempt to capture and analyse this trade-off, from the simplest bandit problem to the full Markov decision processes underlying reinforcement learning. The workshop would include tutorials covering the bandit analysis as well as its relevance to user modelling. Reinforcement learning would also be included with particular emphasis on applications in user interfaces. It is also hoped to launch a challenge in this area. This workshop comes under the Thematic Programme 4: On-line User Modelling and Reinforcement Learning and is a core meeting of the PASCAL Network. In accordance with the PASCAL workshop programme, the workshop will be recorded on video and all presentations will be made available to PASCAL researchers. It is anticipated that contributions to the workshop will be published in an edited collection of papers. In conjunction with an agreement between the network and Springer-Verlag, the organisers are currently organising for the inclusion of the proceedings of the workshop in the Lecture Notes in Computer Science series. Invited contributions: Nicolo Cesa-Bianchi, Peter Auer, and further speakers TBA. For more information about the PASCAL Network please follow the link: http://www.pascal-network.org . From kamps at in.tum.de Fri Apr 8 09:16:49 2005 From: kamps at in.tum.de (Marc de Kamps) Date: Fri, 8 Apr 2005 15:16:49 +0200 Subject: Connectionists: 3rd European Neuro-IT and Neuroengineering School (hotel information included) Message-ID: <000c01c53c3d$38b932a0$383c9f83@atknoll3> 3rd European Neuro-IT and Neuroengineering School ? Neuroengineering of Cognitive Functions ? For hotel information: see below Faculty Igor Aleksander (London, UK) Helder Araujo (Coimbra, Portugal) Christian B?chel (Hamburg, Germany) Gabriel Curio (Berlin, Germany) Andreas Engel (Hamburg, Germany) Wolfram Erlhagen (Guimaraes, Portugal) Eduardo Fernandez (Alicante, Spain) Pascal Fries (Nijmegen, The Netherlands) Vittorio Gallese (Parma, Italy) Rainer Goebel (Maastricht, The Netherlands) Auke Ijspeert (Lausanne, Switzerland) Alois Knoll (M?nchen, Germany) Peter K?nig (Osnabr?ck, Germany) Andrej Kral (Hamburg, Germany) Henry Markram (Lausanne, Switzerland) Klaus-Robert M?ller (Berlin, Germany) Miguel Nicolelis (Durham, USA) Guy Orban (Leuven, Belgium) Frank Pasemann (St. Augustin, Germany) Tim Pearce (Leicester, UK) Rolf Pfeifer (Z?rich, Switzerland) Gulio Sandini (Genua, Italy) Vittorio Sanguineti (Genua, Italy) J?rgen Schmidhuber (M?nchen, Germany) Paul Verschure (Z?rich, Switzerland) Barbara Webb (Edinburgh, UK) Mathew Wilson (Boston, USA) Jonathan Wolpaw (Albany, USA) Conditions for Participation The school is open to postdocs, researchers and other professionals working in the field of Neuro-IT, as well as for PhD students of engineering, physics, computer science, robotics, neuroscience, medicine, biology, or psychology. A total of 50 participants will be admitted. Selection will be on a competitive basis. The program committee will select participants on the basis of their publication record (evaluated relative to career status) and the relatedness of the candidate?s own research to the theme of the school. Please register at: http://www.neuro-it.net/Activities/Venice2005 Registration fee PhD students (proof of student status required): Euro 100 Postdocs with affiliation to a public institution: Euro 200 Other professionals: Euro 300 After notification of acceptance, the registration fee needs to be prepaid until May 20. The registration fee includes: admission to all lectures, welcome reception, lunch catering, coffee and soft drinks during breaks, CD with abstracts and papers of faculty members, conference booklet with abstracts and key papers. The registration fee does not include: dinners, accomodation, travel costs. The programme will also feature student presentations. After acceptance, the programm committee will ask some of the students to present their ongoing work in short talks. The organizers wish to note that the registration fee does not cover the actual costs of attendance, but all slots are subsidized by funds from the Neuro-IT network. Admission to the school is granted on the basis that postdocs and students are attending the programme at all times. Because only 50 participants can be allowed, there will be a waiting list from which additional students will be admitted in case of cancellations. Prepayments will only be refunded if the cancelled participant slot has been filled. Please submit the following information Name Affiliation Complete contact information CV Publication record (including papers, chapters, abstracts, talks) One-page description of primary research interest or project Name of supervisor or head of group PhD students: please send proof of student status (fax a signed statement of your supervisor to Mrs. te Vehne +49 89 289 18107) Important deadlines Deadline for application: April 15 Notification of acceptance: April 29 Deadline for payment of registration fee: May 20 Hotel information: See: http://www.neuro-it.net/NeuroIT/Activities/Venice2005/HotelInformation _______________________________________________ General mailing list General at neuro-it.net https://www.neuro-it.net/mailman/listinfo/general From M.Denham at plymouth.ac.uk Fri Apr 8 06:11:11 2005 From: M.Denham at plymouth.ac.uk (Mike Denham) Date: Fri, 8 Apr 2005 11:11:11 +0100 Subject: Connectionists: Four-year PhD studentships in Theoretical and Computational Neuroscience Message-ID: <52A8091888A23F47A013223014B6E9FE040728AA@03-CSEXCH.uopnet.plymouth.ac.uk> University of Plymouth Centre for Theoretical and Computational Neuroscience Four-year PhD studentships in Theoretical and Computational Neuroscience Applications are invited for two 4-year PhD studentships in the Centre for Theoretical and Computational Neuroscience at the University of Plymouth, UK. These studentships form part of a major new 1.86M UK pounds five-year research project funded by the UK Engineering and Physical Sciences Research Council entitled: "A Novel Computing Architecture for Cognitive Systems based on the Laminar Microcircuitry of the Neocortex". Collaborators on the project include Plymouth University (Mike Denham, Sue Denham, Thomas Wennekers), Manchester University (Stefano Panzeri, Piotr Dudek, Steve Furber), University College London (Michael Hausser, Arnd Roth), Edinburgh University (Mark van Rossum, David Willshaw), Oxford University (Jan Schnupp), and London University School of Pharmacy (Alex Thomson), plus a number of leading European research groups. The persons appointed to these studentships will become part of a team of three postdocs and six PhD students engaged on the project in the collaborating institutions, and planned regular project meetings will ensure a close collaboration across this team and with the project investigators listed above. The two PhD studentships funded through the research project at Plymouth will be specifically related to the following research areas: 1. Learning rules for experience-dependent and adaptation-induced plasticity in the developed cortical microcircuit; 2. Spatiotemporal dynamics of feature selectivity in primary visual cortex. Applicants must also be able to demonstrate a capability to undertake and benefit from research training through to completion to the standard necessary to qualify for a PhD. Applicants for the studentships must therefore have a good first (bachelors) degree, or a masters degree, in a relevant subject area, strong academic references, and a demonstrable interest in carrying out research in the field of theoretical and computational neuroscience, eg through prior study in the area. Candidates must also possess basic mathematical and programming abilities. However, the four-year duration of the studentships will enable candidates to develop these abilities, and their knowledge and skills in neuroscience and relevant cross-disciplinary areas, in the first year of study through taught courses in the Centre and in the collaborating institutions. The studentships will be available to be taken up at the start of the Autumn Term at the end of September 2005. The studentships will cover the full costs of university tuition fees at the UK/EU level*, together with a tax-free stipend for living expenses (currently in the region of 12,000 UK pounds per annum). *In this respect, the studentships only cover the full tuition costs of candidates resident in the UK or other EU countries; however applications will be considered from non-EU candidates, for whom additional funding may be available to cover the shortfall in tuition fees. Informal enquiries about the studentships should be made in the first instance to Professor Mike Denham, Centre for Theoretical and Computational Neuroscience, University of Plymouth, Drake Circus, Plymouth, PL4 8AA, UK; tel: +44 (0)1752 232547; email: mdenham at plym.ac.uk. Professor Mike Denham Centre for Theoretical and Computational Neuroscience Room A223 Portland Square University of Plymouth Drake Circus Plymouth PL4 8AA UK tel: +44 (0)1752 232547/233359 fax: +44 (0)1752 233349 email: mdenham at plym.ac.uk www.plymneuro.org.uk From cottrell at univ-paris1.fr Mon Apr 11 18:15:04 2005 From: cottrell at univ-paris1.fr (Marie Cottrell) Date: Tue, 12 Apr 2005 00:15:04 +0200 Subject: Connectionists: Extended deadline for WSOM'2005 Message-ID: <5.0.2.1.2.20050412000742.03bf4688@asterix.univ-paris1.fr> ------------------------------------- WSOM'2005 deadline extended Due to numerous requests, the deadline for paper submission to the WSOM'2005 conference (Workshop on Self-Organizing Maps, Paris, 5-8 September 2005) has been extended. New (final) deadline: Tuesday 19 April, midnight More information about the WSOM conference, including topics and paper submission guidelines, may be found at http://samos.univ-paris1.fr/wsom/wsom05.html. Marie Cottrell, Organization chairman -------------------------------------- ************************************************ Marie Cottrell Tel et fax(prof): 33 1 44 07 89 22 SAMOS-MATISSE Universite Paris 1 E-mail : cottrell at univ-paris1.fr http://samos.univ-paris1.fr Postal address : 90, rue de Tolbiac 75634 PARIS CEDEX 13 Address of the laboratory : 72, rue Regnault 75013 Paris (m?tro Porte d'Ivry) From doya at irp.oist.jp Thu Apr 14 01:10:38 2005 From: doya at irp.oist.jp (Kenji Doya) Date: Thu, 14 Apr 2005 14:10:38 +0900 Subject: Connectionists: Okinawa Computational Neuroscience Course 2005: Final Call for Applications Message-ID: Apologies for multiple postings, but here is a reminder that the deadline of application for OCNC2005 is coming soon. Abstracts of all the lectures are now on the web. We will again have support for travel and lodging, at a seaside resort overlooking coral reefs. Best wishes, Kenji Doya **************************************************************** Call for Applications OKINAWA COMPUTATIONAL NEUROSCIENCE COURSE 2005 http://www.irp.oist.jp/ocnc/2005 Application deadline: APRIL 20TH, 2005 Date: July 1st to 10th, 2005 Place: Rizzan Sea-Park Hotel, Tancha Bay (http://www.rizzan.co.jp) Onna village, Okinawa, Japan Theme: Predictions and Decisions Lectures by leading theoretical and experimental neuroscientists will be given in the morning and afternoon, and the evening will be open for free discussions and student projects. Confirmed Lecturers: Bernard Balleine (UCLA) Andrew G. Barto (University of Massachusetts) Nathaniel Daw (Gatsby Computational Neuroscience Unit, UCL) Peter Dayan (Gatsby Computational Neuroscience Unit, UCL) Kenji Doya (Initial Research Project, OIST) Mitsuo Kawato (ATR, Computational Neuroscience Laboratories) Minoru Kimura (Kyoto Prefectural University of Medicine) Daeyeol Lee (University of Rochester) John O'Doherty (California Institute of Technology) Anitha Pasupathy (MIT) Masamichi Sakagami (Tamagawa University) Wolfram Schultz (University of Cambridge) Reza Shadmehr (Johns Hopkins University) Stefan Schaal (University of Southern California) Leo Sugrue (Stanford University) Jun Tanji (Tohoku University) Student Projects: a) basic computing (for students new to modeling) b) computational modeling c) psychophysical experiments Each student will present his/her current work at the beginning of the course and the summary of his/her project work at the end of the course. Co-organizers: Peter Dayan, Gatsby Computational Neuroscience Unit Kenji Doya, Okinawa Institute of Science and Technology Masamichi Sakagami, Tamagawa University Advisory Board: Sydney Brenner, Salk Institute Masao Ito, RIKEN Brain Science Institute Terrence Sejnowski, Salk Institute Susumu Tonegawa, MIT Torsten Wiesel, Rockfeller University Sponsors: Okinawa Institute of Science and Technology Project, Cabinet Office, Japan Integrative Research Project for Brain Function Center of Excellence Program, Tamagawa University Japanese Neural Network Society ******* Application ******* We invite graduate students and postgraduate researchers to participate in the course. Please send the following by e-mail (ocnc at irp.oist.jp) or the web application page by APRIL 20TH, 2005. 1) First name, 2) Middle initial (if any), 3) Family name, 4) Degree, 5) Date of birth, 6) Gender, 7) Nationality, 8) Affiliation, 9) Position, 10) Advisor, 11) Postal address, 12) Phone, 13) Fax, 14) E-mail, 15) Web page (if any), 16) Educational background, 17) Work experience, 18) List of publications, 19) Research interests (up to 500 words), 20) Motivations for attending the course (up to 500 words), 21) Two referees whom can ask recommendations (names, affiliations, e-mail addresses), 22) Need for travel support, 23) How you learned about the course. We will accept 30 students based primarily on their research interests (19) and motivations (20). We will also consider the balance of members' research disciplines, geographic origins, and genders. Recommendation letters are not required for application; we may contact some of the referees to help us make difficult decisions. The sponsor will provide lodging and meals during the course. Support for roundtrip airfare to Okinawa will be considered for students without funding. The result of selection will be informed to applicants via e-mail by May 10th. ******* Secretariat ******* Okinawa Computational Neuroscience Course c/o Initial Research Project, Okinawa Institute of Science and Technology 12-22 Suzaki, Gushikawa Okinawa 904-2234, Japan Phone: +81-98-921-3933 Fax: +81-98-921-3873 Email: ocnc at irp.oist.jp For more information, please visit the web page: http://www.irp.oist.jp/ocnc/2005 ---- Kenji Doya Initial Research Project, Okinawa Institute of Science and Technology 12-22 Suzaki, Uruma, Okinawa 904-2234, Japan Phone:+81-98-921-3843; Fax:+81-98-921-3873 http://www.irp.oist.jp/ From tino at jp.honda-ri.com Sun Apr 17 22:09:57 2005 From: tino at jp.honda-ri.com (Tino Lourens) Date: Mon, 18 Apr 2005 11:09:57 +0900 Subject: Connectionists: TiViPE: Spend more time on research and less on coding. Message-ID: <426316F5.8010205@jp.honda-ri.com> Dear all, I am pleased to announce visual programming environment TiViPE. If you would like to program faster, need a rapid prototyping tool, would like to modify a program while it is active, would like to integrate code (C, C++, Fortran, or Java) with minimal additonal effort then TiViPE might be the appropriate solution. Actually, I wanted a program that could wrap any routine into a graphical environment without programming and with little additional effort. Since, such a migration process is essential for users to move from textual programming to graphical programming. In this respect TiViPE provides a major difference to for instance AVS or Khoros. - TiViPE includes already a considerable number of useful icons for image processing and includes most of my research on early vision (center-surround, simple-, complex, endstopped cells, etc.) and graphmatching. - TiViPE has been developed under Linux, but uses the platform independent Qt-library. Ports to Mac, and Windows will be made in the second half of 2005. - TiViPE can be downloaded from: http://www.dei.brain.riken.jp/~emilia/Collaboration/Tino/TiViPE/index.html On that website, you will find more information about TiViPE, as well as two optional libraries can be used to provide the environment with 1. networking support through socket communication 2. merging support to compile a graphical program to a single icon and executable. Please enjoy. With kind regards, Tino Lourens -- Tino Lourens, Ph.D. Honda Research Institute Japan Co., Ltd. 8-1 Honcho, Wako-shi, Saitama, 351-0114, Japan Tel: +81-48-462-2121 (Ext.) 6806 mailto: tino at jp.honda-ri.com Fax: +81-48-462-5221 From masulli at disi.unige.it Mon Apr 18 06:57:08 2005 From: masulli at disi.unige.it (Francesco Masulli) Date: Mon, 18 Apr 2005 12:57:08 +0200 Subject: Connectionists: CFP: CIBB 2005 - Crema, ITALY Message-ID: <200504181257.08424.masulli@disi.unige.it> CALL FOR PAPERS CIBB 2005 Second International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics Crema, ITALY -- September 15-17, 2005 Meeting Website: http://cibb05.disi.unige.it/ CIBB 2005 addresses a cutting edge area of application of Neural Networks, Fuzzy Logic and Evolutionary Computation methods. Technical areas include, but are not limited to: - Data and methods for prognosis - Data and methods for diagnosis - Integration of clinical and genetic data - Proteomics - Pharmacogenetic CIBB 2005 is jointly organized by - BIOPATTERNS, European Network of Excellence on Computational Intelligence for Biopattern analysis in Support of eHealthcare - INNS, International Neural Network Society - SIREN, Italian Neural Networks Society CIBB 2005 will took place at Dipartimento di Tecnologie dell'Informazione Universita' degli Studi di Milano via Bramante 65, I-26013 Crema, ITALY in connection with WILF 2005 - Sixth International Workshop on Fuzzy Logic and Applications (http://dsa.uniparthenope.it/wilf2005/) All accepted papers submitted by registered participants to WILF 2005 will be included in the proceedings book of WILF 2005, that will be published by an international Publisher. Important Dates Submission deadline: 30 May 2005 Notification of acceptance: 30 June 2005 Camera ready papers due: 15 July 2005 Meeting: 15-17 September 2005 Submission of papers: Papers must not be longer than 6 pages, including a cover sheet stating: (1) Paper title; (2) Keywords; (3) Authors names and affiliations; (4) Corresponding author's name and contact details, including telephone/fax numbers and e-mail address. For electronic submission refer to the CIBB 2005 web site http://cibb05.disi.unige.it/. Chairs Francesco Masulli University of Pisa (Italy) Antonina Starita University of Pisa (Italy) Roberto Tagliaferri University of Salerno (Italy) International Program Committee Alexandru Floares, Oncological Institute Cluj-Napoca, Romania Jon Garibaldi, University of Nottingham, UK Nik Kasabov, Auckland University of Technology, NZ Natalio Krasnogor, University of Nottingham, UK Evangelia Micheli-Tzanakou, Rutgers University, NJ - USA Sushmita Mitra, Indian Statistical Institute Kolkata, India Alberto Paccanaro,Yale University, CT, USA David Alejandro Pelta, University of Granada, Spain Udo Seiffert, Leibniz Institute, Gatersleben, Germany L?onard Studer, ABMI SA, Dorigny Lausanne, Switzerland Anna Tramontano, University of Rome "La Sapienza", Italy From ted.carnevale at yale.edu Mon Apr 18 21:00:20 2005 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 18 Apr 2005 21:00:20 -0400 Subject: Connectionists: Reminder: NEURON Summer Course Message-ID: <42645824.50900@yale.edu> Only 4 weeks left to register for the NEURON Summer Course! A few seats remain open for this course, which will be held at the Supercomputer Center at UCSD, Saturday, June 18, through Wednesday, June 22. Avoid the last minute rush! For more information see http://www.neuron.yale.edu/neuron/sdsc2005/sdsc2005.htm or contact Ted Carnevale Psychology Dept. PO Box 208205 Yale University New Haven, CT 06520-8205 USA phone 203-432-7363 fax 203-432-7172 email ted.carnevale at yale.edu Supported in part by: National Institutes of Health National Science Foundation The San Diego Supercomputer Center Contractual terms require inclusion of the following statement: This course is not sponsored by the University of California. --Ted From skoenig at usc.edu Mon Apr 18 22:49:01 2005 From: skoenig at usc.edu (Sven Koenig) Date: Mon, 18 Apr 2005 19:49:01 -0700 (PDT) Subject: Connectionists: CFP: JMLR Special Topic on Learning in Large Probabilistic Environments Message-ID: CALL FOR PAPERS Journal of Machine Learning Research Special Topic on Learning in Large Probabilistic Environments Guest Editors Sven Koenig, Shie Mannor and Georgios Theocharous http://www.jmlr.org/cfp/llpe.html We invite papers on learning in large probabilistic environments for a special topic of the Journal of Machine Learning Research (JMLR). One of the fundamental problems of artificial Intelligence is how to enable systems (for example, mobile robots, manufacturing systems, or diagnostic systems) embedded in complex environments to achieve their long-term goals efficiently. A natural approach is to model such systems as agents that interact with their environment through actions, perceptions and rewards. These agents choose actions after every observation, aiming to maximize their long-term reward. Learning allows them to improve their initial strategy based on the history of successful and unsuccessful interactions with the environment. This special topic is intended to serve as an outlet for recent advances in learning in such environments, often called reinforcement learning. We welcome both theoretical advances in this field as well as detailed reports on applications of learning in large probabilistic domains. Topics of interest include: * Theoretical foundations of learning in large probabilistic environments. * Completely and partially observable Markov decision process models (MDPs) and similar models. Learning with factored state or action spaces, continuous state spaces, action spaces or time models, hybrid models, relational learning, concurrency. * Heuristics and approximations. Policy and value function approximations, Monte Carlo and advanced simulation methods. * Spatio-temporal abstractions. Dynamic factorization, hierarchy and relational structure. * Interactive learning. Guided exploration, combining supervised and unsupervised learning, shaping, and learning from very few examples. * Learning in complex systems. Function approximation, dimensionality reduction, feature selection for learning, and alternative state representations. * Cooperative and competitive multi-agent reinforcement learning. Learning in nonstationary domains and stochastic, network, and dynamic games. * Real world applications. Medicine, finance, robotics, manufacturing, security, etc. Submission procedure: Submit papers to the standard JMLR submission system http://jmlr.csail.mit.edu/manudb Please include a note stating that your submission is for the special topic on Learning in Large Probabilistic Environments. Accepted papers will be published in JMLR as they become available. Important Dates: * Submission due: June 1st, 2005 * Decision: September 1st, 2005 * Final version due: November 1st, 2005 Early submissions are encouraged, and will be handled immediately following the submission. For further details or enquiries, please contact the guest editors: Sven Koenig (skoenig at usc.edu) Shie Mannor (shie at ece.mcgill.ca) Georgios Theocharous (georgios.theocharous at intel.com) From masulli at disi.unige.it Thu Apr 21 06:06:33 2005 From: masulli at disi.unige.it (Francesco Masulli) Date: Thu, 21 Apr 2005 12:06:33 +0200 Subject: Connectionists: CFP: Post-IJCNN2005 workshop on COMPUTATIONAL INTELLIGENCE APPROACHES FOR THE ANALYSIS OF BIOINFORMATICS DATA Message-ID: <200504211206.33559.masulli@disi.unige.it> CALL FOR PAPERS Post-IJCNN2005 workshop on COMPUTATIONAL INTELLIGENCE APPROACHES FOR THE ANALYSIS OF BIOINFORMATICS DATA Hilton Montreal Bonaventure Hotel, Montr?al, Qu?bec, Canada August 5th, 2005 Workshop website http://ci-bio.disi.unige.it/ Important Dates Abstract submission deadline: 10 May 2005 Notification of acceptance: 20 May 2005 Papers due: 15 June 2005 Workshop: 5 August 2005 Scope & Topics Bioinformatics is a fast growing scientific area aimed at managing, analyzing and interpreting information from biological data, sequences and structures. In the past few years, many Computational Intelligence approaches have been successfully applied to the solution of complex problems typical of this field, including signal and image processing, clustering, feature selection, data visualization, and data mining. This workshop will present surveys and contributed papers covering differents areas where neural, fuzzy, and genetics approaches have been succesfully applied to the analysis of Bioinformatics data. Contributions to the Workshop We request two kinds of contributions: * surveys papers, giving overviews of innovative Computational Intelligence approaches to a specific Bioinformatics area * standard papers, presenting new results Standard papers accepted as oral will be presented in a slot of 15-20 min, while survey papers will have a slot of 30-60 min for oral presentation (details will be communicated to the authors by the end of June). Workshop organizers: Francesco Masulli Dept Computer Science Univ. Pisa Largo Pontecorvo 3 I-56127 Pisa - Italy Phone +39010 353 6604 fax +39010 353 6699 email Masulli at di.unipi.it Roberto Tagliaferri Dipartimento di Matematica ed Informatica, Universit? di Salerno 84084 Fisciano (Sa) - Italy Phone: +39 089 963357 fax: +39089 963307 e-mail: rtagliaferri at unisa.it ------------------------------------------------------- From cindy at bu.edu Mon Apr 25 09:54:22 2005 From: cindy at bu.edu (Cynthia Bradford) Date: Mon, 25 Apr 2005 09:54:22 -0400 Subject: Connectionists: Neural Networks 18(3) 2005 Message-ID: <200504251354.j3PDsN4F004480@kenmore.bu.edu> NEURAL NETWORKS 18(3) Contents - Volume 18, Number 3 - 2005 ------------------------------------------------------------------ ***** Neuroscience and Neuropsychology ***** A model of smooth pursuit in primates based on learning the target dynamics Tomohiro Shibata, Hiromitsu Tabata, Stefan Schaal, and Mitsuo Kawato Information theory, novelty, and hippocampal responses: Unpredicted or predictable? Bryan A. Strange, Andrew Duggins, William Penny, Raymond J. Dolan, and Karl J. Friston ***** Mathematical and Computational Analysis ***** Dynamical behaviors of Cohen-Grossberg neural networks with discontinuous activation functions Wenlian Lu and Tianping Chen Global exponential stability of delayed competitive neural networks with different time scales Hongtao Lu and Zhenya He An asymptotic statistical analysis of support vector machines with soft margins Kazushi Ikeda and Tsutomu Aoishi ***** Engineering and Design ***** Improved local learning rule for information maximization and related applications Ralph Linsker The dynamic wave expansion neural network model for robot motion planning in time-varying environments Dmitry V. Lebedev, Jochen J. Steil, and Helge J. Ritter ***** Technology and Applications ***** Self-organizing information fusion and hierarchical knowledge discovery: A new framework using ARTMAP neural networks Gail A. Carpenter, Siegfried Martens, and Ogi J. Ogas Predictive neural networks for gene expression data analysis Ah-Hwee Tan and Hong Pan ***** Book Review ***** Review of "Exploratory analysis and data modeling in functional neuroimaging", Friedrich T. Sommer and Andrzej Wichert (editors) by Alfonso Nieto-Castanon 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 Y 13,000 Neural Networks (plus Y 2,000 enrollment fee) $20 (student) SEK 460 Y 11,000 (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- membership without $30 SEK 200 not available Neural Networks to non-student (subscribe through another society) Y 5,000 student (plus Y 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 7600 Terrace Avenue, Ste. 203 Middleton WI 53562 USA 608 831 0584, ext. 138 (phone) 608 831 5122 (fax) srees at reesgroupinc.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 JNNS Secretariat c/o Fuzzy Logic Systems Institute 680-41 Kawazu, Iizuka Fukuoka 820-0067 Japan 81 948 24 2771 (phone) 81 948 24 3002 (fax) jnns at flsi.cird.or.jp http://www.jnns.org/ ---------------------------------------------------------------------------- From jain_shaloo at hotmail.com Tue Apr 26 18:54:42 2005 From: jain_shaloo at hotmail.com (pramod gupta) Date: Tue, 26 Apr 2005 18:54:42 -0400 Subject: Connectionists: Call for papers - reminder Message-ID: _______________________________________________________________________________ Verification, Validation and Certification of Neuro-Adaptive Controllers in Safety-Related Areas Montreal, Canada, Friday, August 5, 2005 A Workshop in conjunction with the International Joint Conference on Neural Networks 2005 Workshop Outline Over the recent years, artificial Neural Networks (NNs) have found their way into various safety-related and safety-critical areas, like transportation, avionics, environmental monitoring and control, and medical applications.Quite often, these applications (using NN techniques ranging from classification to monitoring and control) proved to be highly successful, leading from a pure research prototype into a serious experimental system (e.g., a neural-network-based flight-control system test-flown on a manned NASA F-15 aircraft) or a commercial product (e.g., Sharp's Logi-cook). However, the general question of how to make sure that the NN-based adaptive control system performs as expected in all cases has not yet been addressed satisfactorily. While theory and concepts of adaptive systems and intelligent control have been studied in depth over the past decade or so, only very little attention has been paid to the issue of validating the correctness and safety of their operation. All safety-related software applications require careful verification and validation (V\&V) of the software components, ranging from extended testing to full-fledged certification procedures (e.g., DO178-B). The adaptive nature of neural networks requires a significantly different approach to verification and validation than used for traditional software, since dynamic adaptation of parameters, iterative numerical algorithms, and complex control architectures renders traditional approaches to V\&V impracticable. Many prototypical/experimental application of neural networks in safety-related areas have demonstrated superior behavior and practical usefulness. Unless, however, methods and techniques have been developed which are capable of assuring the correctness and performance of a neural-network based system, NN applicability in safety-critical areas is substantially limited. The purpose of the workshop is to bring together researchers and users of learning and adaptive systems and control systems in order to create a forum for discussing recent advances in verification, validation, and testing of learning systems, to understand better the practical requirements for developing and deploying neuro-adaptive, and to inspire research on new methods and techniques for verification, validation, and testing. Topics of Interest Topics of interest include but are not limited to: applications of learing and adaptive methods and NNs in safety-critical areas and experience/lessons learned. applications of collaborative filtering problems, node modeling for belief networks and dependency networks, sequential decision making tasks, diagnosis problems, autonomous systems, robotics, and security, etc. techniques, tools, and methods to assess and guarantee the performance of a NN, e.g., statistical (Bayesian) methods, rule extraction with subsequent V&V, methods for convergence/stability analysis, dynamic monitoring of the NN behavior, etc., V&V techniques that are specifically suitable for on-line trained and adaptive systems, and software development, V\&V, and certification processes for learning and adaptive systems. Important Dates: Authors should submit a PDF file of their paper to schumann AT email.arc.nasa.gov Submission of papers: April 27, 2005 Notification of acceptance: May 4, 2005 Camera-ready copy: May 15, 2005 Workshop: August 5, 2005 Workshop organizers Johann Schumann, RIACS/NASA Ames, schumann AT email.arc.nasa.gov (650)604-0941 Pramod Gupta, QSS Inc/ NASA Ames, pgupta AT email.arc.nasa.gov (650)604-1824 Dragos Margineantu, The Boeing Company, dragos.d.margineantu AT boeing.com Program Committee B. Cukic, WVU S. Jacklin, NASA Ames T. Menzies, PSU A. Mili, NJIT M. Richard, NASA DFRC F. Sheldon, ORNL -------------------------------------------------------------------------------- For questions or comments, please send email to schumann AT email.arc.nasa.gov From robbie at bcs.rochester.edu Tue Apr 26 09:10:27 2005 From: robbie at bcs.rochester.edu (Robert Jacobs) Date: Tue, 26 Apr 2005 09:10:27 -0400 Subject: Connectionists: postdoc position available Message-ID: <5.1.1.6.0.20050426090822.01c30ac8@bcs.rochester.edu> A postdoctoral position is available in the lab of Robert Jacobs, Department of Brain and Cognitive Sciences, University of Rochester. The lab focuses on computational and experimental studies of learning, often in the context of visual or multisensory perception. For example, members of our lab work on defining statistically optimal models of aspects of perception, the development of novel machine learning algorithms for efficiently learning to perform perceptual tasks, and perceptual experiments with humans that compare human performance with Bayesian optimal performance and with the performance of relevant machine learning algorithms. The postdoctoral fellow will be part of a larger community dedicated to the study of learning and developmental plasticity. Applicants must be U.S. citizens or permanent residents. Applicants should send a vita, research statement, recent publications, and the names of three individuals who can write letters of recommendation to: LDB Postdoctoral Search Committee Department of Brain and Cognitive Sciences Meliora Hall, River Campus University of Rochester Rochester, NY 14627-0268 More information about our lab can be obtained at http://www.bcs.rochester.edu/people/robbie/robbie.html Information about the Department of Brain and Cognitive Sciences can be obtained at http://www.bcs.rochester.edu ---------------------------------------------------------------------------------------- Robert Jacobs Department of Brain and Cognitive Sciences University of Rochester Rochester, NY 14627-0268 phone: 585-275-0753 fax: 585-442-9216 email: robbie at bcs.rochester.edu web: http://www.bcs.rochester.edu/people/robbie/robbie.html From seiffert at ipk-gatersleben.de Tue Apr 26 06:13:30 2005 From: seiffert at ipk-gatersleben.de (Udo Seiffert) Date: Tue, 26 Apr 2005 12:13:30 +0200 Subject: Connectionists: Book Announcement: Bioinformatics using Computational Intelligence Paradigms Message-ID: <426E144A.5050103@ipk-gatersleben.de> Dear Connectionists, Please find attached an announcement of a new book on Bioinformatics using Computational Intelligence Paradigms recently published by Springer. Table of Contents: Medical Bioinformatics: Detecting Molecular Diseases with Case-Based Reasoning Ralf Hofestaedt and Thoralf Toepel Prototype Based Recognition of Splice Sites Barbara Hammer, Marc Strickert, and Thomas Villmann Content Based Image Compression in Biomedical High-Throughput Screening Using Artificial Neural Networks Udo Seiffert Discriminative Clustering of Yeast Stress Response Samuel Kaski, Janne Nikkilae, Eerika Savia, and Christophe Roos A Dynamic Model of Gene Regulatory Networks Based on Inertia Principle Florence d'Alch? Buc, Pierre-Jean Lahaye, Bruno-Edouard Perrin, Liva Ralaivola, Todor Vujasinovic, Aur?lien Mazurie, and Samuele Bottani Class Prediction with Microarray Datasets Simon Rogers, Richard D. Williams, and Colin Campbell Random Voronoi Ensembles for Gene Selection in DNA Microarray Data Francesco Masulli and Stefano Rovetta Cancer Classification with Microarray Data Using Support Vector Machines Feng Chu and Lipo Wang Artificial Neural Networks for Reducing the Dimensionality of Gene Expression Data Ajit Narayanan, Alan Cheung, Jonas Gamalielsson, Ed Keedwell, and Christophe Vercellone Further information may be obtained at: http://www.springeronline.com/sgw/cda/frontpage/0,11855,5-147-22-37888088-0,00.html For your convenience I add a suggestion for its BibTex entry: @BOOK{SffJainSchw05, editor = Udo Seiffert and Lakhmi C. Jain and Patrick Schweizer, title = Bioinformatics using Computational Intelligence Paradigms, publisher = Springer-Verlag, year = 2005, address = Heidelberg, volume = 176, series = Studies in Fuzziness and Soft Computing, ISBN = 3-540-22901-9, file = F } Kind regards, Udo Seiffert From myosioka at brain.riken.go.jp Thu Apr 28 01:15:59 2005 From: myosioka at brain.riken.go.jp (Masahiko Yoshioka) Date: Thu, 28 Apr 2005 14:15:59 +0900 (JST) Subject: Connectionists: Synchronization in an ensemble of neurons Message-ID: <20050428.141559.71092460.myosioka@brain.riken.go.jp> Dear all, We would like to announce a new paper on the theoretical study of spike synchronization in neural networks. We developed the analytical method to clarify stability of synchronization in a large ensemble neurons for arbitrary neuron dynamics and arbitrary strength of interactions. "Cluster synchronization in an ensemble of neurons interacting through chemical synapses" M. Yoshioka, Phys. Rev. E, in press. http://arxiv.org/abs/nlin.PS/0504057 In networks of periodically firing spiking neurons that are interconnected with chemical synapses, we analyze cluster state, where an ensemble of neurons are subdivided into a few clusters, in each of which neurons exhibit perfect synchronization. To clarify stability of cluster state, we decompose linear stability of the solution into two types of stabilities: stability of mean state and stabilities of clusters. Computing Floquet matrices for these stabilities, we clarify the total stability of cluster state for any types of neurons and any strength of interactions even if the size of networks is infinitely large. First, we apply this stability analysis to investigating synchronization in the large ensemble of integrate-and-fire (IF) neurons. In one-cluster state we find the bifurcation due to the change of stability of a cluster, which elucidates that in-phase synchronization of IF neurons occurs with only inhibitory synapses. Then, we investigate entrainment of two clusters of IF neurons with different excitability. IF neurons with fast decaying synapses show the low entrainment capability, which is explained by a pitchfork bifurcation appearing in two-cluster state with change of synapse decay time constant. Second, we analyze one-cluster state of Hodgkin-Huxley (HH) neurons and discuss the difference in synchronization properties between IF neurons and HH neurons. Best regards, Masahiko Yoshioka The Brain Science Institute The Institute of Physical and Chemical Research (RIKEN) From terry at salk.edu Thu Apr 28 13:00:34 2005 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 28 Apr 2005 10:00:34 -0700 (PDT) Subject: Connectionists: NEURAL COMPUTATION 17:6 In-Reply-To: <200504052123.j35LNCn69350@kepler.snl.salk.edu> Message-ID: <200504281700.j3SH0Y872819@kepler.snl.salk.edu> Neural Computation - Contents - Volume 17, Number 6 - June 1, 2005 REVIEW Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review Henrik Jacobsson NOTE Learning by Kernel Polarization Yoram Baram LETTERS A Unified Approach to Building and Controlling Spiking Attractor Networks Chris Eliasmith Synchronized Firings in the Networks of Class 1 Excitable Neurons with Excitatory and Inhibitory Connections, and their Dependences on the Forms of Interactions Takashi Kanamaru and Masatoshi Sekine A Hierarchy of Associations in Hippocampo-Cortical Systems: Cognitive Maps and Navigations Strategies J.P. Banquet, Ph.Gaussier, M. Quoy, A. Revel and Y. Burnod Evidence Evaluation for Bayesian Neural Networks Using Contour Monte Carlo Faming Liang An Ensemble of Cooperative Extended Kohonen Maps for Complex Robot Motion Tasks Kian Hsiang Low, Wee Kheng Leow, and Marcelo H. Ang, Jr. ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2005 - VOLUME 17 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $143 $90 $96.30 Institution $680 $727.60 $734 $612 $654.84 * 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 nip-lr at neuron.kaist.ac.kr Thu Apr 28 21:10:10 2005 From: nip-lr at neuron.kaist.ac.kr (Soo-Young Lee) Date: Fri, 29 Apr 2005 10:10:10 +0900 Subject: Connectionists: Volume 6 of Neural Information Processing - Letters and Reviews Message-ID: <200504290116.j3T1G2ZK019460@neuron.kaist.ac.kr> The printed version of Volume 6 (Numbers 1-3; from Januart to March 2005) of the NIP-LR (neural Information Processing - Letters and Reviews) is available. NIP-LR aims for high-quality timely-publication with double-blind review process. For online you may visit www.nip-lr.info or bsrc.kaist.ac.kr/NIP-LR. For your free sample copy of the printed version please send me an e-mail to nip-lr at neuron.kaist.ac.kr ---------------------------------------------------------------------------- --------- Contents: Vol. 6, No. 1, January 2005 Reviews Blind Source Separation and Independent Component Analysis: A Review Seungjin Choi, Andrzej Cichocki, Hyung-Min Park, and Soo-Young Lee Vol. 6, No. 2, February 2005 Letters Variable Discharge Pattern and Contrast Invariant Orientation Tuning of a Simple Cell: A Modeling Study Akhil R. Garg, Basabi Bhaumik, and Klaus Obermayer Vol. 6, No. 3, March 2005 Letters Modeling with Recurrent Neural Networks using Compensatory Neuron Model Gunjan Gupta, R. N. Yadav, P. K Kalra, and J. John Removal of Hidden Neurons by Crosswise Propagation Xun Liang From ted.carnevale at yale.edu Fri Apr 29 16:28:11 2005 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Fri, 29 Apr 2005 16:28:11 -0400 Subject: Connectionists: ModelDB now contains source code for 158 published models Message-ID: <427298DB.7020700@yale.edu> You are being contacted as a member of the computational neuroscience community to update you on resources currently available at ModelDB. Source code for 158 published models is freely available from ModelDB http://senselab.med.yale.edu/senselab/modeldb/ ModelDB is a searchable database for convenient storage, viewing, and retrieval of source code for published computational models of neurons and networks. It is designed to stimulate the wider acceptance and growth of computational neuroscience by facilitating reproducibility and attributed reuse of models. ModelDB is "programming language neutral." Currently it has entries written for C/C++, FORTRAN, GENESIS, MATLAB, NEURON, SNNAP, and XPP, most of which are ready to run. Each model entry has links to the scientific literature to put it in the broader context of neuroscience research. Authors of published models are invited to contact Michael Hines (michael.hines at yale.edu) for assistance with entering their code into ModelDB. If your published model is already available on the web, we'd like to link to it. Simply send Michael the URL and the PubMed ID number of your modeling paper (if the latter is not available, then a bibliographic reference is fine). ModelDB is part of the SenseLab Project http://senselab.med.yale.edu/senselab/ and has close links to NeuronDB http://senselab.med.yale.edu/senselab/NeuronDB/ which contains information about cellular properties that are relevant to computational modeling. --Michael Hines