From michael at jupiter.chaos.gwdg.de Fri Jan 2 04:35:24 2004 From: michael at jupiter.chaos.gwdg.de (Michael Herrmann) Date: Fri, 2 Jan 2004 10:35:24 +0100 (CET) Subject: PhD position at Goettingen, Germany Message-ID: Dear Connectionists, at the department of Nonlinear Dynamics of the Max-Planck-Institut fuer Stroemungsforschung, Goettingen, there is an immediate opening for a PhD student position (BAT IIa/2). The successful applicant will work in an international interdisciplinary project on neural mechanisms of motoric control including modeling issues and a robotic implementation. We provide a stimulating scientific environment in a dynamic interdisciplinary team, state-of-the-art computing facilities and qualified and individual supervision. Applicants are supposed to have finished a degree in the sciences and to have a background in computational neuroscience. The position is initially limited to six months. A prolongation and the opportunity to proceed with a PhD depends only on success of work. Knowledge of German language is not required. The institute is committed to Employment Equity and encourages applications from all qualified candidates, including persons with disabilities, members of visible minorities, and women. For a detailed description of the research projects of our group and information about the city of Goettingen, please visit our WWW homepage at http://www.chaos.gwdg.de/. For further question please contact the sender of this email. Please send your application (preferably electronically as PDF, including CV, list of publications, certificates, and the names and email addresses of three academic references) with the keyword "SensoMotorics" to Prof. Dr. T. Geisel Max-Planck-Institut fuer Stroemungsforschung Bunsenstr. 10, 37073 Goettingen, Germany http//:www.chaos.gwdg.de e-mail: geisel at chaos.gwdg.de ********************************************************************* * Dr. J. Michael Herrmann Georg August University Goettingen * * Tel. : +49 (0)551 5176424 Institute for Nonlinear Dynamics * * Fax : +49 (0)551 5176439 Bunsenstr. 10, D-37073 Goettingen * * EMail: michael at chaos.gwdg.de http://www.chaos.gwdg.de * ********************************************************************* From ckiw at inf.ed.ac.uk Mon Jan 5 08:12:05 2004 From: ckiw at inf.ed.ac.uk (Chris Williams) Date: Mon, 5 Jan 2004 13:12:05 +0000 (GMT) Subject: Faculty Positions at the University of Edinburgh Message-ID: [apologies if you receive this message multiple times] The School of Informatics is inviting applications for three Lecturer positions, one of which is earmarked for the Machine Learning area. [A Lecturer position is roughly equivalent to a US Assistant Professor.] We seek candidates specialising in any aspect of machine learning, including theoretical foundations, algorithm and model development, and applications. Interests include (but are not restricted to) probabilistic graphical modelling, pattern recognition, scientific data mining, and bioinformatics. The post is likely to be based in our Institute for Adaptive and Neural Computation (ANC), http://anc.ed.ac.uk/. See http://www.jobs.ed.ac.uk/jobs/index.cfm?action=jobdet&jobid=3001042 for further information. The closing date for applications is 30 January 2004. Informal enquiries may be addressed to c.k.i.williams at ed.ac.uk . Chris Williams Dr Chris Williams c.k.i.williams at ed.ac.uk Institute for Adaptive and Neural Computation School of Informatics, University of Edinburgh 5 Forrest Hill, Edinburgh EH1 2QL, Scotland, UK fax: +44 131 650 6899 tel: (direct) +44 131 651 1212 (department switchboard) +44 131 650 3100 http://anc.ed.ac.uk/ From tplate at acm.org Wed Jan 7 02:51:45 2004 From: tplate at acm.org (Tony Plate) Date: Wed, 07 Jan 2004 00:51:45 -0700 Subject: book announcement Message-ID: <5.1.0.14.2.20040107001451.02cbcdd8@pop6.attglobal.net> I'm pleased to announce the availability of my book: "Holographic Reduced Representation: Distributed Representation for Cognitive Structures" by Tony A. Plate CSLI Lecture Notes Number 150, CSLI Publications, Stanford, CA 2003 ISBN 1575864304 Contents: 1 Introduction 1 2 Review of connectionist and distributed memory models 25 3 Holographic Reduced Representation 93 4 HRRs in the frequency domain 145 5 Using convolution-based storage in systems that learn 153 6 Estimating analogical similarity 175 7 Discussion 221 It is available on Amazon.com in paperback for US$25. http://www.amazon.com/exec/obidos/tg/detail/-/1575864304 This book is a based on my PhD thesis. It has been significantly rewritten and updated for publishing as a book. The major changes include: * New related work described in chapter 2 * A new section surveying techniques for learning in distributed representations * Complete rewriting of the chapter on analogy processing, including: - redesigned experiments - discussion of the relationship between HRRs and kernel methods for computing similarity - clear exposition of how a HRR-based model can perform structure- sensitive analogy retrieval in a single-stage (cf 2-stage MAC/FAC model of human performance on analogy retrieval) * Many references to new work added * Subject and author indices added The back cover blurb: While neuroscientists garner success in identifying brain regions and in analyzing individual neurons, ground is still being broken at the intermediate scale of understanding how neurons combine to encode information. This book proposes a method of representing information in a computer that would be suited for modeling the brain's methods of processing information. In stark contrast to traditional computing where "every bit counts," the method proposed by Plate distributes information over large numbers of components, which are mathematically modeled by high-dimensional vectors. No single unit or even a small number of them means anything in particular. The meaningful entity is the total pattern over all the units. Superficially, the patterns appear random. Holographic Reduced Representations (HRRs) are introduced here to model how the brain could distribute each piece of information among thousands of neurons. It had been previously thought that the semantic structure of natural language sentences cannot be encoded practically in a distributed representation but HRRs can overcome problems of earlier proposals. This work has implications for psychology, neuroscience, linguistics, and computer science and artificial intelligence. More details available at http://pws.prserv.net/tap -- Tony Plate From pimh at nici.kun.nl Tue Jan 6 09:23:20 2004 From: pimh at nici.kun.nl (Pim Haselager) Date: Tue, 6 Jan 2004 15:23:20 +0100 (CET) Subject: VIII Brazilian Symposium on Artificial Neural Networks Message-ID: Allow me to ask your attention for a call for papers for the VIII Brazilian Symposium on Artificial Neural Networks (SBRN2004), taking place in Sao Luis, Maranhao, Brazil from September 22 to 24, 2004 http://www.inf.ufrgs.br/~mas/sbiarn04/ Important dates: Submission of full paper: April 15, 2004 Notification of acceptance: May 15, 2004 The proceedings of the SBRN are published by the IEEE Computer Society Press since 1998 and authors of selected best papers are invited to submit an extended version to a special issue of the International Journal of Neural Systems. From ahirose at eis.t.u-tokyo.ac.jp Wed Jan 7 06:28:20 2004 From: ahirose at eis.t.u-tokyo.ac.jp (Akira Hirose) Date: Wed, 07 Jan 2004 20:28:20 +0900 Subject: book announcement In-Reply-To: <5.1.0.14.2.20040107001451.02cbcdd8@pop6.attglobal.net> References: <5.1.0.14.2.20040107001451.02cbcdd8@pop6.attglobal.net> Message-ID: <3FFBED54.4090407@eis.t.u-tokyo.ac.jp> I'm pleased to announce the availability of the following book: "Complex-Valued Neural Networks: Theories and Applications" Editor: Akira Hirose (The University of Tokyo) Publisher: World Scientific Publishing Co. Pte. Ltd., Singapore, in the Series on Innovative Intelligence ISBN 981-238-464-2 Web site http://www.eis.t.u-tokyo.ac.jp/news/cvnn_book.html Amazon.com http://www.amazon.com/exec/obidos/tg/detail/-/9812384642/ Amazon.co.jp http://www.amazon.co.jp/exec/obidos/ASIN/9812384642/ In recent years, complex-valued neural networks have widened the scope of application in optoelectronics, imaging, remote sensing, quantum neural devices and systems, spatiotemporal analysis of physiological neural systems, and artificial neural information processing. In this first- ever book on complex-valued neural networks, the most active scientists at the forefront of the field describe theories and applications from various points of view to provide academic and industrial researchers with a comprehensive understanding of the fundamentals, features and prospects of the powerful complex-valued networks. Contents: George M. Georgiou (California State Univ.) Foreword 1 Akira Hirose (Univ. of Tokyo) "Complex-Valued Neural Networks: An introduction" 2 Tohru Nitta (AIST) "Critical points of the multi-layered complex-valued neural networks" 3 Dong Liang Lee (Ta-Hwa Inst. Tech.) "Complex-valued Neural Associative Memories: Learning Algorithm and Network Stability" 4 Yasuaki Kuroe (Kyoto Inst. Tech.) "A Model of Complex-Valued Associative Memories and Its Dynamics" 5 Justin Pearson (Uppsala Univ.) "Clifford Valued Neural Networks: Background, Theory and Applications" 6 Iku Nemoto (Tokyo Denki Univ.) "A complex-valued neuron model and its application to associative memory" 7 Danilo P. Mandic, S.L.Goh, A.Hanna (Imperial College of Science) "A data-reusing gradient descent algorithm for complex-valued recurrent neural networks" 8 Pritam Rajagopal, Subhash Kak (Louisiana State Univ.) "Instantaneously trained neural networks with complex-valued neurons" 9 Hiroyuki Aoki (Tokyo Coll. Tech.) "Applications of Complex-Valued Neural Networks for Image Processing" 10 Makoto Kinouchi, Masafumi Hagiwara (Keio Univ.) "Memorization of Melodies Using Complex-valued Recurrent Neural Network" 11 Yanwu Zhang (Aware Inc.) "Complex-Valued Generalized Hebbian Algorithm and Its Applications to Sensor Array Signal Processing" 12 Teruyuki Miyajima, Kazuo Yamanaka (Ibaraki Univ.) "Phasor models and their applications to communications" 13 Andriyan Bayu Suksmono (Bandung Inst. Tech.), Akira Hirose (Univ. of Tokyo) "Adaptive Processing of Interferometric Radar Images" 14 Mitsuo Takeda, Takaaki Kishigami (Univ. of Electro-Commun.) "Complex neural network model with an analogy to self-oscillation generated in an optical phase-conjugate resonator" 15 Sotaro Kawata, Akira Hirose (Univ. of Tokyo) "Coherent Lightwave Neural Network Systems: Use of frequency domain" -- From terry at salk.edu Wed Jan 7 21:15:24 2004 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 7 Jan 2004 18:15:24 -0800 (PST) Subject: NEURAL COMPUTATION 16:2 In-Reply-To: <200312170008.hBH08sQ59057@purkinje.salk.edu> Message-ID: <200401080215.i082FOu12798@purkinje.salk.edu> Neural Computation - Contents - Volume 16, Number 2 - February 1, 2004 ARTICLE Analyzing Neural Responses to Natural Signals: Maximally Informative Dimensions Tatyana Sharpee, Nicole C. Rust and William Bialek LETTERS Rapid Temporal Modulation of Synchrony by Competition in Cortical Interneuron Networks P.H.E. Tiesinga and T. J. Sejnowski Dynamic Analyses of Information Encoding in Neural Ensembles by Riccardo Barbieri, Loren M. Frank, David Nguyen, Michael C. Quirk, Victor Solo, Matthew A. Wilson and Emery N. Brown A Network Model of Perceptual Suppression Induced by Transcranial Magnetic Stimulation Yoichi Miyawaki and Masato Okada Adaptive Two-Pass Median Filter Based on Support Vector Machines for Image Restoration Tzu-Chao Lin and Pao-Ta Yu Improving Generalization Performance of Natural Gradient Learning Using Optimized Regularization by NIC Hyeyoung Park, Noboru Murata, Shun-ichi Amari One-Bit-Matching Conjecture for Independent Component Analysis Zhi-Yong Liu, Kai-Chun Chiu and Lei Xu Jacobian Conditioning Analysis for Model Validation Isabelle Rivals and Leon Personnaz Reply to the Comments on "Local Overfitting Control via Leverages" in "Jacobian Conditioning Analysis for Model Validation" by I. Rivals and L. Personnaz Yacine Oussar, Gaetan Monari, Gerard Dreyfus ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2004 - VOLUME 16 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $108 $54 $57.78 Individual $95 $101.65 $143 $85 $90.95 Institution $635 $679.45 $689 $572 $612.04 * 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 hennig at cn.stir.ac.uk Thu Jan 8 04:41:53 2004 From: hennig at cn.stir.ac.uk (Matthias H. Hennig) Date: Thu, 08 Jan 2004 09:41:53 +0000 Subject: EARLY COGNITIVE VISION Message-ID: <1073554912.20937.4.camel@nockerl.cn.stir.ac.uk> ---------------- SECOND ANNOUNCEMENT --------------- EARLY COGNITIVE VISION Location: Sabhal Mor Ostaig, Isle of Skye, Scotland Dates: 28.5. 1.6. 2004 Web: http://www.cn.stir.ac.uk/ecovision-ws Dear Colleague, You may have received this mail already. If so please accept our apologies. I would like to draw your attention to the ECOVISION Workshop taking place on the Isle of Skye in Scotland, end of May 2004 (for details see end of this message). This WS is concerned with the link between biologically motivated computer vision and visual neuroscience especially of higher visual functions. This workshop is now open for registration and paper submission at: http://www.cn.stir.ac.uk/ecovision-ws/ Invited participants will receive refund of their costs. The WS contains 14 keynote lectures as well as 32 shorter talks and one poster session. It includes a special session on Coding of Visual Information. The complete list of keynote speakers who have agreed to come is: Y. Aloimonos (Maryland) K. Boahen (Univ. of Pennsylvania) J.-O.-Eklundh (KTH Stockholm) J. Elder (York Univ.) U. Eysel (Univ. Bochum) O. Faugeras (INRIA) D. Fleet (Univ. of Toronto) L. Florack (Eindhoven Univ. of Technology) L. v. Gool (ETH Zuerich) D. Hogg (Univ. of Leeds) C. v.d. Malsburg (Univ. Bochum & USC) G. Orban (KU Leuven) S. Sarkar (Univ. of South Florida) R. Watt (Stirling Univ.) The conference site is located on the very scenic Isle of Skye (Real Scottish Rain inclusive..). The International Journal of Computer Vision (IJCV) has agreed to publish a special issue based on a refereed selection of papers from this workshop. We would like to invite you to register for this WS and to submit a paper. On behalf of the organizing committee. F. Wrgtter (Univ. of Stirling, Scotland, UK) DETAILSDETAILSDETAILSDETAILSDETAILSDETAILSDETAILSDETAILS Title of the Workshop: EARLY COGNITIVE VISION Location: Sabhal Mor Ostaig, Isle of Skye, Scotland Dates:28.5. 1.6. 2004 Web: http://www.cn.stir.ac.uk/ecovision-ws The WS is organized by the ECOVISON project group consisting of: G. Bisio (Genova) P. Hancock (Stirling) M. v. Hulle (Leuven, Publication Chair) A. Johnston (London) N. Krger (Aalborg) M. Lappe (Muenster) E. Ros. (Granada) S. Sabatini (Genova) F. Wrgtter (Stirling, Workshop Chair) M. Mhlenberg (HELLA Hueck KG,Lippstadt) From handzel at isrmail.isr.umd.edu Wed Jan 7 14:04:46 2004 From: handzel at isrmail.isr.umd.edu (handzel@isrmail.isr.umd.edu) Date: Wed, 7 Jan 2004 14:04:46 -0500 Subject: Job Opening Message-ID: <3afafe6c.fe92821f.81c1500@isrmail.isr.umd.edu> Position: Scientist - Data Mining / Statistical Learning Beyond Genomics Inc., a Waltham, MA based biotechnology company pioneering the field of Systems Biology, is conducting a search for candidates for its Computational Sciences Group. As a member of this Group, you will have an operational role in support of the Company's research collaboration and discovery programs, as well as a key role in the continued development of the Company's advanced data analysis and informatics platforms. The successful candidate will have a strong background in data mining, statistical pattern recognition or machine learning, as well as experience and interest in conducting exploratory data analysis. Suitable candidates at all experience levels are encouraged to apply. For more company information please visit our web site at www.BeyondGenomics.com. Required Skills and Experience: * Solid background in data mining, statistical pattern recognition, machine learning, signal processing, or similar field * Experience in working with large data sets * Ph.D. or M.Sc. combined with suitable experience in appropriate field * Expert level working knowledge of Matlab, Mathematica, or similar scientific programming environment * Experience analysing gene expression array data or equivalent using state-of-the-art methods is desirable * Ability to work in a fast-paced, multi-tasking, multi- disciplinary environment Beyond Genomics offers a competitive compensation and benefits package including medical and dental coverage and 401K plan. Please forward your CV or resume to: Amir Handzel, Ph.D. 40 BEAR HILL ROAD WALTHAM, MA 02451 Fax: 781-895-1119 AHandzel at BeyondGenomics.com ___ From d.mareschal at bbk.ac.uk Wed Jan 7 05:48:57 2004 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Wed, 7 Jan 2004 10:48:57 +0000 Subject: postdoctoral position in London Message-ID: Readers of this list may be interested in the following position. PLEASE DO NOT REPLY DIRECTLY TO ME. Denis ================================ Birkbeck College, University of London, UK Centre for Brain and Cognitive Development POSTDOCTORAL RESEARCH ASSISTANT Full-time Fixed-term 2-Years in the first instance We are seeking an individual to lead a component of an overall research program with external funding on the neurocomputational basis of individual variability in humans. The project will involve connectionist computational modelling of a diverse range of cognitive abilities. Simulation work will make contact with empirical data from several developmental disorders including dyslexia, autism, and schizophrenia. You will preferably need to have strong research background in cognitive psychology, developmental psychology, AI or Neural Computation. You should have experience of computational modelling techniques, good computer skills and the ability to communicate effectively in all media. Salary range: ?20,399 to ?29,473 p.a. inc. salary dependent on qualifications and experience. Closing date: 20 January 2004 For application forms and further details please see www.bbk.ac.uk or send an A4 sae (Ref:APS112), to the Human Resources Team, Birkbeck, Malet Street, Bloomsbury, London, WC1E 7HX or email: humanresources at bbk.ac.uk Informal enquiries to: m.thomas at bbk.ac.uk -- ========================= Dr. Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 (0)20 7631-6582/6226 reception: 6207 fax +44 (0)20 7631-6312 http://www.psyc.bbk.ac.uk/people/academic/mareschal_d/ ========================= From ckiw at inf.ed.ac.uk Tue Jan 13 08:49:18 2004 From: ckiw at inf.ed.ac.uk (Chris Williams) Date: Tue, 13 Jan 2004 13:49:18 +0000 (GMT) Subject: Postdoc position, PhD studentships at U of Edinburgh Message-ID: [apologies if you receive this message multiple times] 1) The School of Informatics, University of Edinburgh invites applications for one post of Research Fellow on the project Compilers that Learn to Optimise (COLO). COLO is an EPSRC funded project in the area of applying machine learning to program optimisation. This project is a collaboration between the Compiler group headed by Dr Michael O'Boyle and Machine Learning group led by Dr Chris Williams. The Research Fellow will be expected to work on developing methods for the following two problems (1) global optimisation methods for searching for the best compiler optimisation off-line, (2) supervised learning for predicting optimal compiler transformations at compile time. You should normally hold a PhD in a relevant area and be capable of developing new theory and contributing to tool development. The fellowship is of twenty-four months duration (in the first instance). See https://www.jobs.ed.ac.uk/jobs/index.cfm?action=jobdet&jobid=3001119 for further information and the application procedure. The closing date for applications is 16 February 2004. 2) We are also advertising two EPSRC funded PhD studentships on the COLO project. See http://www.dcs.ed.ac.uk/home/mob/phd.html for further information and the application procedure. Informal enquiries about the Research Fellowship and PhD studentships can be addressed to Chris Williams (c.k.i.williams at ed.ac.uk) or Mike O'Boyle (mob at inf.ed.ac.uk). Chris Williams Dr Chris Williams c.k.i.williams at ed.ac.uk Institute for Adaptive and Neural Computation School of Informatics, University of Edinburgh 5 Forrest Hill, Edinburgh EH1 2QL, Scotland, UK fax: +44 131 650 6899 tel: (direct) +44 131 651 1212 (department switchboard) +44 131 650 3100 http://anc.ed.ac.uk/ From krichmar at nsi.edu Tue Jan 13 21:51:08 2004 From: krichmar at nsi.edu (Jeff Krichmar) Date: Tue, 13 Jan 2004 18:51:08 -0800 Subject: POSTDOCTORAL FELLOWSHIP in Brain-Based Devices and Machine Vision Message-ID: <000a01c3da49$42fa8d10$c6b985c6@nsi.edu> Please post and circulate as you see fit. Thank you. POSTDOCTORAL FELLOWSHIP in Brain-Based Devices and Machine Vision The Neurosciences Institute, located in San Diego, California, invites applications for a POSTDOCTORAL FELLOWSHIP to build neurobiologically based models of vision for a robotic Segway platform (http://www.segway.com) as a part of ongoing research on Brain-Based Devices. Continuing previous research conducted at the Institute, the fellow will be focusing on the design of simulated models of large-scale neuronal networks that are capable of handling real world visual input and generating motor responses for the Segway RMP (Robotic Mobile Platform). Applicants should have a background in robotics, engineering, or computer science, and a strong interest in neuroscience. Fellows will receive stipends appropriate to their qualifications and experience. Submit a curriculum vitae, statement of research interests, and three references to: Dr. Jeffrey L. Krichmar The Neurosciences Institute 10640 John Jay Hopkins Drive San Diego, California 92121 Email: krichmar at nsi.edu Fax: 858-626-2099 For a description of the project, refer to http://www.nsi.edu/nomad/. For a description of The Neurosciences Institute, refer to http://www.nsi.edu. From planning at icsc.ab.ca Tue Jan 13 15:05:39 2004 From: planning at icsc.ab.ca (Jeanny S. Ryffel) Date: Tue, 13 Jan 2004 13:05:39 -0700 Subject: upcoming deadline BICS 2004, Scotland Message-ID: <5.1.0.14.2.20040113123721.00a47080@pop.interbaun.com> Submission deadline January 31, 2004 The science of neural computation focuses on mathematical aspects for solving complex practical problems. It also seeks to help neurology, brain theory and cognitive psychology in the understanding of the functioning of the nervous system by means of computational models of neurons, neural nets and sub-cellular processes. BICS2004 aims to become a major point of contact for research scientists, engineers and practitioners throughout the world in the fields of cognitive and computational systems inspired by the brain and biology. Participants will share the latest research, developments and ideas in the wide arena of disciplines encompassed under the heading of BICS2004: First International ICSC Symposium on Cognitive Neuro Science (CNS 2004) (from computationally inspired models to brain-inspired computation) Chair: Prof. Igor Aleksander, Imperial College London, U.K Second International ICSC Symposium on Biologically Inspired Systems (BIS 2004) Chair: Prof. Leslie Smith, University of Stirling, U.K. Third International ICSC Symposium on Neural Computation (NC'2004) Chair: Dr. Amir Hussain, University of Stirling, U.K. http://www.icsc-naiso.org/conferences/bics2004/bics-cfp.html if you do not wish to receive further information, please send message to: planning at icsc.ab.ca Planning Division ICSC Interdisciplinary Research NAISO Natural and Artificial Intelligence Systems Organization Canada --------------------------------------------------- Email: planning at icsc.ab.ca Website: www.icsc-naiso.org Tel: +1-780- 387 3546 Fax: +1-780- 387 4329 From niebur at jhu.edu Tue Jan 13 13:54:29 2004 From: niebur at jhu.edu (niebur@jhu.edu) Date: Tue, 13 Jan 2004 13:54:29 -0500 Subject: Postdoctoral fellow in computational neuroscience and primate single-unit recording: mechanisms of tactile selective attention Message-ID: <200401131854.i0DIsTn30641@russell.mindbrain> We are seeking a postdoctoral fellow to work on a project that involves both computational modelling and neurophysiological recordings in awake behaving monkeys. The goal of the project is to understand the neural mechanisms underlying attentional selection of tactile stimuli. A strong quantitative background is required and experience with neurophysiological recordings in awake behaving animals is desired. We will, however, consider candidates who are otherwise well-qualified but lack recording experience; they will need to be exceptionally motivated to learn the techniques of animal training and single-unit recordings. The work is a collaborative project involving the labs of Drs. Ernst Niebur, Steven Hsiao and Ken Johnson, at the Mind/Brain Institute of The Johns Hopkins University. If interested, please contact Ernst Niebur, niebur at jhu.edu, with a CV, a statement of research interest, and the names and email addresses of 2 or more references. All email should be sent in ASCII format. -- Dr. Ernst Niebur Krieger Mind/Brain Institute Assoc. Prof. of Neuroscience Johns Hopkins University niebur at jhu.edu http://cnslab.mb.jhu.edu 3400 N. Charles Street (410)516-8643, -8640 (secr), -8648 (fax), -3357 (lab) Baltimore, MD 21218 From rojas at inf.fu-berlin.de Wed Jan 14 08:36:33 2004 From: rojas at inf.fu-berlin.de (Raul Rojas) Date: Wed, 14 Jan 2004 14:36:33 +0100 Subject: Postdoc position in AI for women Message-ID: <000001c3daa3$6d0dc810$796e2da0@pcpool.mi.fuberlin.de> Dear colleagues, The Department of Computer Science at the Free University of Berlin is looking for female candidates for a Postdoc position. The position is funded within the framework of a grant with the purpose of increasing the percentage of women faculty in computer science. The position will be funded for at least two years and will collaborate with the AI group in our university (http://www.inf.fu-berlin.de/inst/ag-ki/ger/index.html) For those familiar with the German system, this is a C1 position. The general area of the candidate should be artificial intelligence, specially machine vision, handwriting recognition, cognitive robotics, connectionism. Candidates with a PhD in computer science or a related technical area (mathematics, physics, engineering)are welcome to apply. Please send an application by e-mail, with a CV, and a letter describing your areas of interest, as well as the names of two references. PDF files are better. And again: this is a program for women faculty development. Prof.Dr. Raul Rojas Freie Universit?t Berlin Takustr. 9 14195 Berlin Germany From mozer at colorado.edu Thu Jan 15 19:41:57 2004 From: mozer at colorado.edu (Michael C. Mozer) Date: Thu, 15 Jan 2004 17:41:57 -0700 Subject: Computational Linguistics position Message-ID: <40073355.9090406@colorado.edu> University or Organization: University of Colorado Department: ICS Rank of Job: Assistant Professor Specialty Areas: Computational Linguistics Description: Computational Linguist, Tenure Track Position The Institute of Cognitive Science at the University of Colorado invite applications for a full-time tenure-track position in computational linguistics/computational psycholinguistics at the Assistant level, with a starting date of Fall 2004. Appropriate degree areas include linguistics, psychology, computer science, and cognitive science. In exceptional cases, appointment at the early Associate level will be considered. We seek applicants with a strong record of research in an area that integrates linguistics, cognitive science, and computation. Duties include graduate and undergraduate teaching, research, research supervision, and Institute, Departmental, and college service assignments as appropriate for university faculty members. We will give strongest consideration to applicants whose research is empirically based, and makes use of corpus, psycholinguistic and computational methods. Applicants should send curriculum vitae, copies of representative publications, a teaching portfolio, a research summary, and the names of three referees to: Dr. Donna Caccamise, Associate Director Institute of Cognitive Science University of Colorado, Boulder 344 UCB Boulder, CO 80309-0344 Please apply by January 30, 2004. Applications will continue to be accepted after this date until the position is filled. E-mail inquiries may be sent to donnac at psych.Colorado.edu. The University of Colorado is an Equal Opportunity/Affirmative Action Employer. Address for Applications: Attn: Caccamise Donna Caccamise ICS, UCB 344 University of Colorado Boulder, CO 80309 United States of America Position is open until filled Contact Information: Caccamise Donna Caccamise Email: donnac at psych.colorado.edu Tel: 303 735-3602 Fax: 303 735-3602 Website: http://ics.colorado.edu From gary at cs.ucsd.edu Fri Jan 16 18:45:00 2004 From: gary at cs.ucsd.edu (Gary Cottrell) Date: Fri, 16 Jan 2004 15:45:00 -0800 (PST) Subject: Predoctoral fellowships available at UCSD Message-ID: <200401162345.i0GNj0T11120@fast.ucsd.edu> UCSD has obtained a $3.4M grant NSF IGERT grant for interdisciplinary predoctoral training in "Vision and Learning in Humans and Machines". Current Ph.D. applicants to UCSD should apply also to this program if they are interested in these topics. Please see my home page for details. The text below is extracted from the grant application: Consider creating a) a computer system to help physicians make a diagnosis using all of a patient's medical data and images along with millions of case histories; b) intelligent buildings and cars that are aware of their occupants activities; c) personal digital assistants that watch and learn your habits -- not only gathering information from the web but recalling where you had left your keys; or d) a computer tutor that watches a child as she performs a science experiment. Each of these scenarios requires machines that can see and learn, and while there have been tremendous advances in computer vision and computational learning, current computer vision and learning systems for many applications (such as face recognition) are still inferior to the visual and learning capabilities of a toddler. Meanwhile, great strides in understanding visual recognition and learning in humans have been made with psychophysical and neurophysiological experiments. The time is ripe to apply our knowledge of human vision to the application of computer vision algorithms. Simultaneously we believe that the consideration of why vision is difficult for computers can give great insight to experimentalists examining the human and animal visual systems. Similarly, new techniques from computational learning will advance computer vision, while the high dimensional nature of video data will challenge current learning algorithms. {\em The intellectual merit of this proposal is its focus on creating novel interactions between the four areas of: computer and human vision, and human and machine learning.} We believe these areas are intimately intertwined, and that the synergy of their simultaneous study will lead to breakthroughs in all four domains. Our goal in this IGERT is to train a new generation of scientists and engineers who are as versed in the mathematical and physical foundations of computer vision and computational learning as they are in the biological and psychological basis of natural vision and learning. On the one hand, students will be trained to propose a computational model for some aspect of biological vision and then design experiments (fMRI, single cell recordings, psychophysics) to validate this model. On the other hand, they will be ready to expand the frontiers of learning theory and embed the resulting techniques in real-world machine vision applications. Example research studies might include, but are not limited to, machine learning applied to machine vision; extensions of machine learning to well-known human learning methods, such as imitation; a study of how humans solve some of the hardest problems in machine vision -- e.g., viewpoint variation, lighting variation, deformation of non-rigid objects, etc.; or the study of how children learn to see. {\em The broader impact of this program will be the development of a generation of scholars who will bring new tools to bear upon fundamental problems in human and computer vision, and human and machine learning.} Our plan is to use the very successful dual mentor approach that has been employed here by the La Jolla Interfaces in Science Program to encourage students to use the techniques from at least two areas in their research. We will develop a new curriculum that introduces new cross-disciplinary courses to complement the current offerings. In addition, students accepted to the program will go through a two-week ``boot camp,'' before classes start, where they will receive intensive training in machine learning and vision using MatLab, perceptual psychophysics, and brain imaging. Monthly faculty/fellow dinner meetings with students presenting their individual projects will keep everyone informed of progress. We will balance on-campus training with summer internships in industry. Gary Cottrell 858-534-6640 FAX: 858-534-7029 Faculty Assistant: none assigned, but try: Jennifer Dickson at (858) 534-5948 jdickson at cs.ucsd.edu Computer Science and Engineering 0114 IF USING FED EX INCLUDE THE FOLLOWING LINE: "Only connect" 3101 Applied Physics and Math Building University of California San Diego -E.M. Forster La Jolla, Ca. 92093-0114 Email: gary at ucsd.edu Home page: http://www-cse.ucsd.edu/~gary/ Lab Phone: 858-822-3521 From terry at salk.edu Fri Jan 16 13:46:28 2004 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 16 Jan 2004 10:46:28 -0800 (PST) Subject: Telluride Neuromorphic Workshop Announcement In-Reply-To: <200401080215.i082FOu12798@purkinje.salk.edu> Message-ID: <200401161846.i0GIkSp35223@purkinje.salk.edu> Neuromorphic Engineering Workshop call for applications Sunday, JUNE 27 - Saturday, JULY 17, 2004 TELLURIDE, COLORADO Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Ralph ETIENNE-CUMMINGS (Johns Hopkins University) Timmer HORIUCHI (University of Maryland) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Christof KOCH (California Institute of Technology) Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) We invite applications for a three week summer workshop that will be held in Telluride, Colorado from Sunday, June 27 to Saturday, July 17, 2004. The application deadline is Friday, March 19, and application instructions are described at the bottom of this document. The 2003 Workshop and Summer School on Neuromorphic Engineering, sponsored by the National Science Foundation, the Whitaker Foundation, the Office of Naval Research, the Defence Advanced Research Projects Agency, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology, was an exciting event and a great success. We strongly encourage interested parties to browse through the previous workshop web pages. GOALS: Carver Mead introduced the term "Neuromorphic Engineering" for a new field based on the design and fabrication of artificial neural systems, such as vision systems, head-eye systems, and roving robots, whose architecture and design principles are based on those of biological nervous systems. The goal of this workshop is to bring together young investigators and more established researchers from academia with their counterparts in industry and national laboratories, working on both neurobiological as well as engineering aspects of sensory systems and sensory-motor integration. The focus of the workshop will be on active participation, with demonstration systems and hands on experience for all participants. Neuromorphic engineering has a wide range of applications from nonlinear adaptive control of complex systems to the design of smart sensors. Many of the fundamental principles in this field, such as the use of learning methods and the design of parallel hardware (with an emphasis on analog and asynchronous digital VLSI), are inspired by biological systems. However, existing applications are modest and the challenge of scaling up from small artificial neural networks and designing completely autonomous systems at the levels achieved by biological systems lies ahead. The assumption underlying this three week workshop is that the next generation of neuromorphic systems would benefit from closer attention to the principles found through experimental and theoretical studies of real biological nervous systems as whole systems. FORMAT: The three week summer workshop will include background lectures on systems neuroscience (in particular learning, oculo-motor and other motor systems and attention), practical tutorials on analog VLSI design, small mobile robots (Koalas, Kheperas, LEGO robots), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, the majority of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control * central pattern generator * robotics * multichip communication * analog VLSI * learning The active perception project group will emphasize vision and human sensory-motor coordination. Issues to be covered will include spatial localization and constancy, attention, motor planning, eye movements, and the use of visual motion information for motor control. The central pattern generator group will focus on small walking and undulating robots. It will look at characteristics and sources of parts for building robots, play with working examples of legged and segmented robots, and discuss CPG's and theories of nonlinear oscillators for locomotion. It will also explore the use of simple analog VLSI sensors for autonomous robots. The robotics group will use rovers and working digital vision boards as well as other possible sensors to investigate issues of sensorimotor integration, navigation and learning. The audition group aims to develop biologically plausible algorithms and aVLSI implementations of specific auditory tasks such as source localization and tracking, and sound pattern recognition. Projects will be integrated with visual and motor tasks in the context of a robot platform. The multichip communication project group will use existing interchip communication interfaces to program small networks of artificial neurons to exhibit particular behaviors such as amplification, oscillation, and associative memory. Issues in multichip communicationwill be discussed. This year we will also have some new robots kindly donated by the WowWee Toys division of Hasbro in Hong Kong. This will permit us to carry out experiments with WooWee/Hasboro hardware through Mark Tilden. LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350miles). Great Lakes Aviation and America West Express airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do not rent a car. Bring hiking boots, warm clothes, rain gear, and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around mid April 2004. Participants are expected to pay a $275.00 workshop fee at that time in order to reserve a place in the workshop. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. Travel reimbursement of up to $500 for US domestic travel and up to $800 for overseas travel will be possible if financial help is needed (please specify on the application). HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e.postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage qualified women and minority candidates to apply. Application should include: * First name, Last name, Affiliation, valid e-mail address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Two letters of recommendation. Complete applications should be sent to: Terrence Sejnowski The Salk Institute 10010 North Torrey Pines Road San Diego, CA 92037 e-mail: telluride at salk.edu FAX: (858) 587 0417 The application deadline is March 19, 2004. Applicants will be notified by e-mail around mid April. From nk at cs.aue.auc.dk Fri Jan 16 12:34:34 2004 From: nk at cs.aue.auc.dk (Norbert Kruger) Date: Fri, 16 Jan 2004 18:34:34 +0100 Subject: Final Call for Papers: Workshop on Coding of Visual Information in the Brain Message-ID: <400820AA.6090503@cs.aue.auc.dk> Workshop on Coding of Visual Information in the Brain June 1, 2004, Isle of Skye, Scotland Satellite event of the Early Cognitive Vision Workshop (28.5.-1.6.2004) http://www.cn.stir.ac.uk/ecovision-ws/ Call for Contributions How is visual Information coded in the human brain? How are statistical properties of natural images related to the internal representations/coding? What is the prior knowledge the human visual system is equipped with? In what sense does the actual task influence the internal state? What is the goal of the early visual processes and how can we achieve integration? What is the functional role of the temporal structure of neural firing patterns? These questions are relevant for research concerning the modelling of biological visual systems as well as building artificial systems. The workshop 'Coding of Visual Information in the Brain' has the aim to bring together scientists involved in neurophysiology, psychology and computer vision to discuss these issues under a multi-disciplinary perspective. As well as the contributed talks and posters, a number of leading scientists with strong interest in bridging the gap between human and artificial vision will be giving invited talks. The workshop will follow the tradition of the 'Information Theory and the Brain' workshops held in Stirling 1995 and in Newquay 1997. However, in contrast to its predecessors it is more focussed on vision. The workshop will be organised as a satellite event of the Early Cognitive Vision Workshop that will be held from May 28 to June 1 2004 (see http://www.cn.stir.ac.uk/ecovision-ws/). Please submit a one-page abstract, preferably by email to Peter Hancock (pjbh1 at psych.stir.ac.uk) or Norbert Krueger (nk at cs.aue.auc.dk) by 23.1.2004. Organising Committee Peter Hancock (Stirling, Scotland) Norbert Krueger (Esbjerg, Denmark) Florentin Woergoetter (Stirling, Scotland) Roland Baddeley (Sussex, England) Laurenz Wiskott (Berlin, Germany) James Elder (York, Canada) Invited Speakers James Elder (York, Canada) Christoph von der Malsburg (Bochum, Germany) Guy Orban (Leuven, Belgium) Roger Watt (Stirling, Scotland) From miguel at cs.toronto.edu Sat Jan 17 01:15:32 2004 From: miguel at cs.toronto.edu (Miguel . Carreira-Perpin) Date: Sat, 17 Jan 2004 01:15:32 -0500 Subject: TR on the number of modes of a Gaussian mixture Message-ID: <16392.54020.906061.753113@axon.ai> We would like to announce a new TR: An isotropic Gaussian mixture can have more modes than components Miguel Carreira-Perpinan and Chris Williams Available from http://www.inf.ed.ac.uk/publications/report/0185.html It is well known that in 1-d a mixture of isotropic Gaussians can have no more modes than components (see e.g. Silverman (1981), Yuille and Poggio (1986)). In this TR we show that in d dimensions (with d >= 2) a mixture of M > 2 isotropic Gaussians can have more than M modes. We first discuss a 3-component mixture in d = 2 where the Gaussians are located at the vertices of an equilateral triangle. For a certain range of variances modes are present near to the vertices and also at the centre of the triangle. (The equilateral triangle construction was suggested by Prof. J. J. Duistermaat, personal communication, 2003.) We also extend the construction to the regular simplex with M vertices and show that for M > 2 there is always a range of variances for which M+1 modes are present. Miguel Carreira-Perpinan Chris Williams -- Miguel A Carreira-Perpinan Dept. of Computer Science, Rm 283 Tel. (416) 9463986 University of Toronto Fax (416) 9781455 6 King's College Road mailto:miguel at cs.toronto.edu Toronto, ON M5S 3H5, Canada http://www.cs.toronto.edu/~miguel From oreilly at grey.colorado.edu Sun Jan 18 23:06:25 2004 From: oreilly at grey.colorado.edu (Randall C. O'Reilly) Date: Sun, 18 Jan 2004 21:06:25 -0700 Subject: Postdoc in Computational Cognitive Neuroscience Message-ID: <200401190406.i0J46PM13212@grey.colorado.edu> Postdoctoral Position Announcement: A postdoctoral research position in the computational cognitive neuroscience lab at the University of Colorado at Boulder is now open for applications. The ideal candidate is someone with a strong background in computational modeling of neural systems as applied to cognitive phenomena such as memory, perception, attention, language, problem solving, etc. The focus of the funding for this position is on developing a biologically-based cognitive architecture based on existing models of specialized brain areas including hippocampus, prefrontal cortex/basal ganglia, and posterior cortex. Although considerable progress has been made on these more specialized models, much work remains to be done on integrating them into an overall architecture that is capable of more complex cognitive functions. Our ultimate goal is to develop neural models capable of performing sophisticated temporally-extended tasks in complex, real-world environments (e.g., navigation, planning, problem solving). Initial steps include developing an interactive model of the visual system (dorsal-ventral pathways) that responds to top-down attentional/goal inputs from prefrontal cortex, and integrating this with prefrontal cortex/basal ganglia learning models. Throughout, the use of powerful learning mechanisms is emphasized, as is the inspiration from both neural and cognitive data, and the application of the models to simulating concrete empirical data. Due to the broad scope of this research and other work going on within the lab, there is considerable flexibility in the choice of specific research projects. This position is supervised by Randy O'Reilly, and collaborators include a number of researchers at CU Boulder (Yuko Munakata, Marie Banich, Tim Curran, Mike Mozer, Jerry Rudy, Dan Jurafsky) and at other institutions (Jonathan Cohen @ Princeton, Todd Braver @ Wash U St. Louis, David Noelle @ Vanderbilt, Nicolas Rougier @ Loria, Nancy, France). For more information, see http://psych.colorado.edu/~oreilly/lab.html. In addition to providing an exciting research environment, the greater Boulder area offers an exceptional quality of life. Spectacularly situated at the edge of the Rockies, this area provides a wide variety of extraordinary outdoor activities, an average of over 300 sunny days per year, and also affords a broad range of cultural activities. Interested individuals should send a vita, representative publications, and a statement of research interests. Three letters of recommendation should be sent separately. Materials can be sent electronically to oreilly at psych.colorado.edu or snail-mailed to: Randall O'Reilly Department of Psychology, 345 UCB University of Colorado, Boulder Boulder, CO 80309-0345 Review of applications will begin in February 2004, and will continue until the position is filled. The University of Colorado Boulder is an equal opportunity employer. From bert at snn.kun.nl Wed Jan 21 06:37:47 2004 From: bert at snn.kun.nl (Bert Kappen) Date: Wed, 21 Jan 2004 12:37:47 +0100 (CET) Subject: New journal Message-ID: Dear all, I would like to draw your attention to a new journal that has been lauched this month: Journal of Statistical Mechanics: Theory and Experiment (JSTAT). This is an online journal published by IOP and SISSA. JSTAT has a very broad scope, among which also topics relevant to the connectionist community: Phase transitions and critical phenomena. Non-equilibrium processes. Applications in biological physics, genomics. Information theory, combinatorial optimization, graphs and networks Collective phenomena in economic and social systems. New applications of statistical mechanics. For more information on the topics covered in JSTAT see https://jstat.sissa.it/index.jsp JSTAT has a fully electronic reviewing process, which assures fast response. I think that JSTAT is a good place to publish physics-style results from the connectionists community, and I am looking forward to your submissions. Bert Kappen SNN University of Nijmegen tel: +31 24 3614241 fax: +31 24 3541435 URL: www.snn.kun.nl/~bert The University of Nijmegen will be named Radboud University Nijmegen as of September 1st, 2004 From bogus@does.not.exist.com Wed Jan 21 12:53:01 2004 From: bogus@does.not.exist.com () Date: Wed, 21 Jan 2004 17:53:01 -0000 Subject: Call for Participation: Symposium: 'Human Language: cognitive, neuroscientific and dynamical systems perspectives' Message-ID: <5AAACCE7A24D9441963855051C57E2033DF656@pinewood.ncl.ac.uk> From joab at dcs.shef.ac.uk Thu Jan 22 03:10:31 2004 From: joab at dcs.shef.ac.uk (Joab Winkler) Date: Thu, 22 Jan 2004 08:10:31 +0000 (GMT) Subject: Sheffield Machine Learning Workshop Message-ID: <200401220810.i0M8AVnl016591@holly.dcs.shef.ac.uk> Preliminary announcement SHEFFIELD MACHINE LEARNING WORKSHOP Sheffield, United Kingdom Septemeber 7-10, 2004 www.dcs.shef.ac.uk/ml/workshop/ The Machine Learning Research Group in The Department of Computer Science at The University of Sheffield is organising a workshop on deterministic and statistical methods in machine learning, with a strong emphasis on mathematical and numerical methods. Confirmed invited speakers: Chris Bishop (Microsoft Research, UK) Andrew Blake (Microsoft Research, UK) Herve Bourlard (IDIAP, Switzerland) Andrzej Cichocki (RIKEN, Japan) Michael Elad (Stanford, USA) Jerry Eriksson (Umea, Sweden) Zoubin Ghahramani (University College London, UK) Gene Golub (Stanford, USA) Josef Kittler (Surrey University, UK) David Lowe (Aston University, UK) David Mackay (Cambridge University, UK) Ian Nabney (Aston University, UK) Manfred Opper (Southhampton University, UK) David Lowe (Aston University, UK) John Platt (Microsoft Research, USA) Stephen Roberts (Oxford University, UK) Bernard Schoelkopf (Max Planck Institute, Germany) Michael Tipping (Microsoft Research, UK) Chris Williams (Edinburgh University, UK) The refereed proceedings of the conference which will be published by Springer in the series Lecture Notes in Computer Science. The workshop is supported by grants from the Engineering and Physical Sciences Research Council, the London Mathematical Society and Sheffield University. The workshop is expected to form part of the thematic programme for the PASCAL European Network of Excellence. Registration will open on 2 April 2004, and early registration is encouraged because there is a limited number of places. For more details, contact the organisers: Joab Winkler Mahesan Niranjan Neil Lawrence E-mail: mlworkshop at dcs.shef.ac.uk Department of Computer Science The University of Sheffield United Kingdom From bischof at icg.tu-graz.ac.at Fri Jan 23 03:11:13 2004 From: bischof at icg.tu-graz.ac.at (Horst Bischof) Date: Fri, 23 Jan 2004 09:11:13 +0100 Subject: SLCV CfP Message-ID: <4010D721.60309@icg.tu-graz.ac.at> *** Last Call for Papers *** SLCV 2004 ECCV International Workshop on Statistical Learning in Computer Vision Workshop on Statistical Learning in Computer Vision http://slcv.icg.tu-graz.ac.at/ May 15, 2004 Prague, Czech Republic ----------------------------------------------------- SLCV 2004 is held in conjunction with ECCV 2004 http://cmp.felk.cvut.cz/eccv2004/ DATES Paper submission: 1 February 2004, 24:00 CET Author Notification: 15 March 2004 Camera ready paper: 5 April 2004 Workshop: 15 May 2004 SCOPE There is no doubt that learning will play a major role in developing intelligent visual and cognitive systems as it has also been emphasized by the Calls for project proposals on Cognitive systems both in Europe and United States. The goal of this workshop is to promote information exchange and technical interaction among researchers working on methods for visual learning, focusing on robust and adaptable techniques, capable of operating in unconstrained environments. Statistical methods have been carried over from the statistical pattern recognition to computer vision and have successfully been used in many applications. However, it is still to be determined how these methods can be used and adapted for multi-modal, continuous, robust learning. Several issues need closer investigation e.g., representations, types of learning (supervised, unsupervised, reinforcement), relations between generative and discriminative methods, etc. TOPICS OF INTEREST include but are not limited to the following: - new theoretical approaches to statistical learning - relations between supervised, unsupervised, reinforcement learning - learning of visual concepts - learning for recognition and categorization - continuous (life-long) learning - relations between generative and discriminative learning - multi-modal learning - generalization of learning across modalities, tasks - contextual visual learning - biologically motivated learning - applications of learning in computer vision WORKSHOP CO-CHAIRS Ales Leonardis, University of Ljubljana, Slovenia Horst Bischof, Graz University of Technology, Austria PROGRAM COMMITTEE Peter Auer, University of Leoben and Graz University of Technology, Austria Bir Bhanu, University of California, USA Horst Bischof, Graz University of Technology, Austria Joachim Buhmann, ETH, Switzerland Hilary Buxton, University of Sussex, UK Terry Caelli, University of Alberta, Canada Tim Cootes, University of Manchester, UK Fernando De la Torre, CMU, USA Bruce Draper, Colorado State University, USA Hany Farid, Dartmouth, USA Edwin Hancock, University of York, UK Bernd Heisele, MIT, USA David Hogg, University of Leeds, UK Nebojsa Jojic, Microsoft, USA Ales Leonardis, University of Ljubljana, Slovenia Jiri Matas, Czech Technical University, Czech Republic Lucas Paletta, Joanneum Research, Austria Bernt Schiele, ETH, Switzerland Anuj Srivastava, Florida State University, USA Antonio Torralba, MIT, USA Daphna Weinshall, The Hebrew University of Jerusalem, Israel John Weng, Michigan State University, USA CONTACT Ales Leonardis Horst Bischof alesl at fri.uni-lj.si bischof at icg.tu-graz.ac.at --- We apologise if you received multiple copies of this announcement --- -- ============================================== Univ. Prof. Dr. Horst Bischof Institute for Computer Graphics and Vision TU Graz Inffeldgasse 16 2. OG A-8010 Graz, AUSTRIA email: bischof at icg.tu-graz.ac.at web: www.icg.tu-graz.ac.at Tel.: +43-316-873-5014 Fax.: +43-316-873-5050 =============================================== From bogus@does.not.exist.com Fri Jan 23 11:07:35 2004 From: bogus@does.not.exist.com () Date: Fri, 23 Jan 2004 11:07:35 -0500 Subject: Post Doctorial Positions Message-ID: <64FB06AE9F2A204DA14763D7C45961CC28B5A3@ARLABML01.DS.ARL.ARMY.MIL> From nando at cs.ubc.ca Fri Jan 23 11:46:43 2004 From: nando at cs.ubc.ca (Nando de Freitas) Date: Fri, 23 Jan 2004 08:46:43 -0800 Subject: PhD positions at UBC Message-ID: <40114FF3.90902@cs.ubc.ca> The Computer Science department of the University of British Columbia is looking for outstanding PhD and Masters candidates in the areas of machine learning, robotics, artificial intelligence and computer vision. Studentships will provide full financial support to successful applicants. For more information, please contact Nando de Freitas (nando at cs.ubc.ca) or visit the following websites: http://www.cs.ubc.ca/ http://www.cs.ubc.ca/labs/lci/ http://www.cs.ubc.ca/prospective/grad/index.html Best, Nando From Alain.Destexhe at iaf.cnrs-gif.fr Wed Jan 28 09:08:52 2004 From: Alain.Destexhe at iaf.cnrs-gif.fr (Alain Destexhe) Date: Wed, 28 Jan 2004 15:08:52 +0100 Subject: Advanced Course in Computational Neuroscience - Obidos 2004 Message-ID: <4017C274.D18504D3@iaf.cnrs-gif.fr> ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE (AN IBRO NEUROSCIENCE SCHOOL) August 16th - September 10th, 2004 MUNICIPALITY OF OBIDOS, PORTUGAL DIRECTORS: Ad Aertsen (University of Freiburg, Germany) Peter Dayan (University College London, UK) Alain Destexhe (CNRS, Gif-sur-Yvette, France) Eilon Vaadia (Hebrew University, Jerusalem, Israel) The Advanced Course in Computational Neuroscience introduces students to the panoply of problems and methods of computational neuroscience, addressing issues of neural organization from sub-cellular to network and inter-areal levels. The course has two complementary parts. Mornings are devoted to lectures given by distinguished international faculty on topics across the breadth of experimental and computational neuroscience. During the rest of the day, students are given practical training in the art and practice of neural modeling, largely through the medium of their individual choice of model systems. The first week of the course introduces students to essential neurobiological concepts and to the most important techniques in modelling single cells, networks and neural systems. Students learn how to solve their research problems using software packages such as GENESIS, MATLAB, NEST, NEURON, XPP, etc. During the following three weeks the lectures cover specific brain areas and functions. Topics range from modelling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the brain. The course ends with project presentations by the students. The Advanced Course in Computational Neuroscience is designed for advanced graduate students and postdoctoral fellows in a variety of disciplines, including neuroscience, physics, electrical engineering, computer science, mathematics and psychology. Students are expected to have a keen interest and basic background in neurobiology as well as some computer experience. Students of any nationality can apply. A maximum of 30 students will be accepted. There will be a fee of EUR 800,- per student covering costs for lodging, meals and other course expenses. Depending on funding, there will be a limited limited number of tuition fee waivers and travel stipends available for students who need financial help for attending the course. We have received IBRO funding to provide full travel and fee support for 4-5 students from developing countries. These students will be accepted according to the normal selection procedure. We specifically encourage applications from researchers who work in the developing world. Applications, including a description of the target project must be submitted electronically (see below) and should be accompanied by two letters of recommendation (also sent electronically). Applications will be assessed by a committee, with selection being based on the following criteria: the scientific quality of the candidate (CV) and of the project, the letters, and evidence that the course affords substantial benefit to the candidate's training. More information and application forms can be obtained from: http://www.neuroinf.org/courses/EUCOURSE/EU04 Please apply electronically using a web browser. Contact address: - mail: Camilla Bruns, FR2-1, Fakultaet IV, Technical University of Berlin, Franklinstrasse 28/29, 10587 Berlin, Germany - e-mail: bruns at cs.tu-berlin.de APPLICATION DEADLINE: April 23, 2004 DEADLINE FOR LETTERS OF RECOMMENDATION: April 30, 2004 Applicants will be notified of the results of the selection procedures by end of May 2004. CONFIRMED FACULTY: Moshe Abeles, Hebrew University, Israel Ad Aertsen, University of Freiburg, Germany Amos Arieli, Weizmann Institute, Israel Peter Dayan, University College London, UK Erik de Schutter, University of Antwerp, Belgium Alain Destexhe, CNRS, France Marcus Diesmann, University of Freiburg, Germany Wulfram Gerstner, EPFL, Switzerland Mike Hausser, University College London, UK Michael Hines, Yale University, USA Gwendael LeMasson, University of Bordeaux, France Siegrid Lowel, Leibniz-Institute for Neurobiology, Germany Israel Nelken, Hebrew University, Israel Miguel Nicolelis, Duke University, USA John Rinzel, New York University, USA Arnd Roth, Max Planck Inst. Heidelberg, Germany Michael Rudolph, CNRS, France Edward Stern, Harvard University, USA Tali Tishby, Hebrew University, Israel Alex Thomson, University College London, UK Emo Todorov, University of California San Diego, USA Misha Tsodyks, Weizmann Institute, Israel Eilon Vaadia, Hebrew University, Israel Charlie Wilson, University of Texas San Antonio, USA Matt Wilson, MIT, USA Li Zhaoping, University College London, UK From guestrin at cs.stanford.edu Tue Jan 27 12:33:02 2004 From: guestrin at cs.stanford.edu (Carlos Ernesto Guestrin) Date: Tue, 27 Jan 2004 09:33:02 -0800 (PST) Subject: Intel Research - Berkeley Lab: positions in Machine Learning and Probabilistic AI Message-ID: Intel Research - Berkeley Lab: positions in Machine Learning and Probabilistic AI The Intel Research - Berkeley Lab is currently seeking candidates for Researcher and Senior Researcher positions. We are particularly interested in candidates with very strong background in the general areas of Machine Learning and Probabilistic Artificial Intelligence. Intel Research - Berkeley Lab represents a bold new form of partnership between industry and academia, with very close ties to UC Berkeley. Our mission is to conduct the highest quality research in emerging, vital areas of Computer Science and Information Technology. Current projects in the Lab focus on extreme networked systems -- the very large, the very small, and the very numerous -- from sensor nets to Internet-scale systems. This is a very open and exciting application area for machine learning and AI, as such systems provide large amounts of real-world data, and can be leveraged by effective learning, inference and decision making methods. Although previous experience with such systems and data is not required, the candidate is expected to explore potential collaborations in the area. A successful candidate should possess a very strong research record in the areas of Machine Learning or Probabilistic AI, and be open to collaborative projects with Intel Researchers, and with UC Berkeley faculty and students. Several researchers at the Lab also have appointments at UC Berkeley. Depending on the candidate's qualifications and experience, and on campus priorities, similar joint assignments are possible. A Ph.D. in Computer Science, Electrical Engineering, Statistics, or related fields is required. Positions are currently open for permanent and short-term appointments. Internship opportunities are also available. For immediate consideration, please email your resume or curriculum vita, a research statement, and the names and addresses of three or more individuals who will provide letters of recommendation to Carlos Guestrin, guestrin at intel-research.net, with CC to Brenda Mainland, brenda.k.mainland at intel.com. For more information, please visit: http://www.intel-research.net/berkeley/ From z.li at ucl.ac.uk Mon Jan 26 12:05:16 2004 From: z.li at ucl.ac.uk (Zhaoping Li) Date: Mon, 26 Jan 2004 17:05:16 +0000 Subject: postdoc in vision/neuroscience in University College London Message-ID: <5.2.0.9.1.20040126170308.00aab2a0@pop-server.ucl.ac.uk> Research Fellow Applications are invited for the post of Postdoctoral Research Fellow to work with Dr. Li Zhaoping (http://www.gatsby.ucl.ac.uk/~zhaoping) in the area of neuroscience, particularly on biological vision, using theoretical and/or psychophysical investigation tools. The candidate should have good experience in theoretical/modelling area or in visual psychophysical area. Interest and capability to engage in research activities in both areas would be preferable although not essential. The research fellow is expected to contribute to the research environment of the laboratory and should have the capability to work well in a team. The post is available for two years and may be extended. Salary is on the RA1A scale (?23,259-29,473 including London allowance) and will depend upon qualifications and experience. We particularly welcome women and black and ethnic minority applicants as they are under represented at this level within University College London (s.48 of the SDA 1975/s.38 of the RRA 1976 apply). Applications (e-mail or hard copy) by covering letter, CV and Personal Information form (the latter available at: http://www.psychol.ucl.ac.uk/info/Personal_Information.doc) to John Draper, Departmental Administrator, Department of Psychology, UCL, Gower Street, London WC1E 6BT, UK, j.draper at ucl.ac.uk. If applying by e-mail please submit all requested information in one .pdf file named by your surname eg Smith.pdf. Further information concerning the post are on the web at: http://www.psychol.ucl.ac.uk/info/psychophysics_li.htm while interested candidates can also contact Li Zhaoping, z.li at ucl.ac.uk, 44 20 7679 1174. From ebaum at fastmail.fm Mon Jan 26 16:16:47 2004 From: ebaum at fastmail.fm (Eric Baum) Date: Mon, 26 Jan 2004 16:16:47 -0500 Subject: What is Thought?: Book announcement Message-ID: <16405.33727.124560.364578@localhost.localdomain> New Book: What is Thought? Eric B. Baum MIT Press 478p Best price right now is at Barnesandnoble.com (BN.com) $32, with free shipping. To buy this book: Barnes and Noble.com: http://search.barnesandnoble.com/booksearch/isbnInquiry.asp?userid=2WI405VPJU&isbn=0262025485&itm=17 Amazon: http://www.amazon.com/exec/obidos/tg/detail/-/0262025485/qid=1074532277/sr=1-3/ref=sr_1_3/002-6265544-0286451?v=glance&s=books MIT Press: http://mitpress.mit.edu/catalog/item/default.asp?sid=AF8A6531-E5E9-4710-A781-CA47C6B64621&ttype=2&tid=9978 This reports on a 10+ year project to see whether what I viewed as the worldview of the connectionist/COLT community could extend in any plausible way to explain all the capabilities of mind. I found such an extension, but only after being constrained into conjectures that are at odds with what I would have expected. *What is Thought?* proposes a model that explains how mind is equivalent to execution of a computer program, addressing aspects such as understanding, meaning, creativity, language, reasoning, learning, and consciousness, that is consistent with extensive data from a variety of fields, and that makes empirical predictions. Meaning is the computational exploitation of the compact underlying structure of the world, and mind is execution of an evolved program that is all about meaning. Occam's Razor, as formalized in the recent computer science literature, is explained and extrapolated to argue that meaning results from finding a compact enough program behaving effectively in the world; such a program can only be compact by virtue of code reuse, factoring into interacting modules that capture real concepts and are reused metaphorically. For a variety of reasons, including arguments based on complexity theory, developmental biology, evolutionary programming, ethology, and simple inspection, this compact Occam program is most naturally seen to be in the DNA, rather than the brain. Learning and reasoning are then fast and almost automatic because they are constrained by the DNA programming to deal only with meaningful quantities. Evolution itself is argued to exploit meaning in related ways. Words are labels for meaningful computational modules. Using the abilility to pass along programs through speech, humans have made cumulative progress in constructing, as part of their minds, useful computational modules built on top of the ones supplied by evolution. The difference between human and chimp intelligence is largely in this additional programming, and thus can be regarded as due to better nurturing. Human written computer programs, however, are generally not highly compressed and thus don't display understanding in the same way as human thought, but experiments are described in which modular computer programs were evolved that achieve abilities giving insight into how programs can evolve understanding. The many aspects of consciousness are also naturally and consistently understood in this context. For example, although the brain is a distributed system and the mind is a complex program composed of many modules, the unitary self emerges naturally as a reification (manifestation) of the interest of the genes. Qualia (the sense of experience of sensations such as pain or redness) have exactly the appropriate nature and meaning that evolution coded in the DNA so that the compact program behaves effectively. No previous familiarity with computer science (or other fields) is assumed-- *What is Thought?* presents a pedagogical survey of the relevant background for its arguments. --------------------------------------- From baolshausen at ucdavis.edu Sat Jan 31 20:06:14 2004 From: baolshausen at ucdavis.edu (Bruno Olshausen) Date: Sat, 31 Jan 2004 17:06:14 -0800 Subject: Sensory Coding and the Natural Environment Message-ID: <401C5106.FCCF9416@ucdavis.edu> Gordon Research Conference: --------------------------- "Sensory coding and the natural environment" September 5-10, 2004 The Queen's College, Oxford, UK Bruno Olshausen, Chair Jack Gallant & Mike Lewicki, Vice-chairs This conference will bring together researchers from diverse disciplines to discuss the statistical structure of natural scenes, and how nervous systems exploit these statistics to form useful representations of the environment. Topics include sensory neurophysiology, perceptual psychology, and the mathematics of signal statistics, applied to a variety of sensory modalities and organisms. A list of speakers as well as instructions on how to apply are available at http://www.grc.org/programs/2004/senscod.htm Applications will be reviewed in April, at which point accepted applicants may register. All participants will have the opportunity to present their work in poster sessions. We hope to have funds available to subsize fees and travel for students and postdocs. -- Bruno A. Olshausen (530) 757-8749 Center for Neuroscience (530) 757-8827 (fax) UC Davis baolshausen at ucdavis.edu 1544 Newton Ct. http://redwood.ucdavis.edu/bruno Davis, CA 95616 & Redwood Neuroscience Institute (650) 321-8282 x233 1010 El Camino Real, suite 380 (650) 321-8585 (fax) Menlo Park, CA 94025 http://www.rni.org From lendasse at james.hut.fi Thu Jan 29 11:26:31 2004 From: lendasse at james.hut.fi (Amaury Lendasse) Date: Thu, 29 Jan 2004 18:26:31 +0200 Subject: TIME SERIES PREDICTION COMPETITION Message-ID: <20040129162712.7021A2838D60@james.hut.fi> Please post and circulate as you see fit. Thank you. 2004 International Joint Conference on Neural Networks Special session organized in collaboration with the European Neural Network Society, the Machine Learning Group of the Universite catholique de Louvain in Belgium and the Neural Networks Research Center of the Helsinki University of Technology TIME SERIES PREDICTION COMPETITION http://www.cis.hut.fi/~lendasse/competition/competition.html The CATS Benchmark The goal of this competition is to provide a new benchmark for the problem of time series prediction and to compare the different methods or models that can be used for the prediction. The proposed time series is the CATS benchmark (for Competition on Artificial Time Series). This artificial Time Series with 5,000 data is given. Within those 100 values are missing. These missing values are divided in 5 blocks: - elements 981 to 1,000; - elements 1,981 to 2,000; - elements 2,981 to 3,000; - elements 3,981 to 4,000; - elements 4,981 to 5,000; These 100 missing values have to be predicted. The Mean Square Error E will be computed on the 100 missing values. The authors are requested to provide their prediction for the 100 missing values. The submitted methods will be ranked using this Mean Square Error E. The best papers (according to the quality of the prediction and the quality of the paper itself) will be selected for the special session that will be held during IJCNN 2004. Furthermore, a limited number of those papers will be published in a special issue of an International Scientific Journal. The competition starts on February, 1st 2004 and the deadline for the submission is March, 7th 2004. Special session organised by Amaury Lendasse, Michel Verleysen, Erkki Oja and Olli Simula. Dr. Amaury Lendasse Helsinki University of Technology Laboratory of Computer and Information Science P.O. Box 5400 FIN-02015 HUT FINLAND tel. +358-9-451 4499 fax +358-9-451 3277 Email: lendasse at cis.hut.fi URL: http://www.cis.hut.fi/~lendasse From michael at jupiter.chaos.gwdg.de Fri Jan 2 04:35:24 2004 From: michael at jupiter.chaos.gwdg.de (Michael Herrmann) Date: Fri, 2 Jan 2004 10:35:24 +0100 (CET) Subject: PhD position at Goettingen, Germany Message-ID: Dear Connectionists, at the department of Nonlinear Dynamics of the Max-Planck-Institut fuer Stroemungsforschung, Goettingen, there is an immediate opening for a PhD student position (BAT IIa/2). The successful applicant will work in an international interdisciplinary project on neural mechanisms of motoric control including modeling issues and a robotic implementation. We provide a stimulating scientific environment in a dynamic interdisciplinary team, state-of-the-art computing facilities and qualified and individual supervision. Applicants are supposed to have finished a degree in the sciences and to have a background in computational neuroscience. The position is initially limited to six months. A prolongation and the opportunity to proceed with a PhD depends only on success of work. Knowledge of German language is not required. The institute is committed to Employment Equity and encourages applications from all qualified candidates, including persons with disabilities, members of visible minorities, and women. For a detailed description of the research projects of our group and information about the city of Goettingen, please visit our WWW homepage at http://www.chaos.gwdg.de/. For further question please contact the sender of this email. Please send your application (preferably electronically as PDF, including CV, list of publications, certificates, and the names and email addresses of three academic references) with the keyword "SensoMotorics" to Prof. Dr. T. Geisel Max-Planck-Institut fuer Stroemungsforschung Bunsenstr. 10, 37073 Goettingen, Germany http//:www.chaos.gwdg.de e-mail: geisel at chaos.gwdg.de ********************************************************************* * Dr. J. Michael Herrmann Georg August University Goettingen * * Tel. : +49 (0)551 5176424 Institute for Nonlinear Dynamics * * Fax : +49 (0)551 5176439 Bunsenstr. 10, D-37073 Goettingen * * EMail: michael at chaos.gwdg.de http://www.chaos.gwdg.de * ********************************************************************* From ckiw at inf.ed.ac.uk Mon Jan 5 08:12:05 2004 From: ckiw at inf.ed.ac.uk (Chris Williams) Date: Mon, 5 Jan 2004 13:12:05 +0000 (GMT) Subject: Faculty Positions at the University of Edinburgh Message-ID: [apologies if you receive this message multiple times] The School of Informatics is inviting applications for three Lecturer positions, one of which is earmarked for the Machine Learning area. [A Lecturer position is roughly equivalent to a US Assistant Professor.] We seek candidates specialising in any aspect of machine learning, including theoretical foundations, algorithm and model development, and applications. Interests include (but are not restricted to) probabilistic graphical modelling, pattern recognition, scientific data mining, and bioinformatics. The post is likely to be based in our Institute for Adaptive and Neural Computation (ANC), http://anc.ed.ac.uk/. See http://www.jobs.ed.ac.uk/jobs/index.cfm?action=jobdet&jobid=3001042 for further information. The closing date for applications is 30 January 2004. Informal enquiries may be addressed to c.k.i.williams at ed.ac.uk . Chris Williams Dr Chris Williams c.k.i.williams at ed.ac.uk Institute for Adaptive and Neural Computation School of Informatics, University of Edinburgh 5 Forrest Hill, Edinburgh EH1 2QL, Scotland, UK fax: +44 131 650 6899 tel: (direct) +44 131 651 1212 (department switchboard) +44 131 650 3100 http://anc.ed.ac.uk/ From tplate at acm.org Wed Jan 7 02:51:45 2004 From: tplate at acm.org (Tony Plate) Date: Wed, 07 Jan 2004 00:51:45 -0700 Subject: book announcement Message-ID: <5.1.0.14.2.20040107001451.02cbcdd8@pop6.attglobal.net> I'm pleased to announce the availability of my book: "Holographic Reduced Representation: Distributed Representation for Cognitive Structures" by Tony A. Plate CSLI Lecture Notes Number 150, CSLI Publications, Stanford, CA 2003 ISBN 1575864304 Contents: 1 Introduction 1 2 Review of connectionist and distributed memory models 25 3 Holographic Reduced Representation 93 4 HRRs in the frequency domain 145 5 Using convolution-based storage in systems that learn 153 6 Estimating analogical similarity 175 7 Discussion 221 It is available on Amazon.com in paperback for US$25. http://www.amazon.com/exec/obidos/tg/detail/-/1575864304 This book is a based on my PhD thesis. It has been significantly rewritten and updated for publishing as a book. The major changes include: * New related work described in chapter 2 * A new section surveying techniques for learning in distributed representations * Complete rewriting of the chapter on analogy processing, including: - redesigned experiments - discussion of the relationship between HRRs and kernel methods for computing similarity - clear exposition of how a HRR-based model can perform structure- sensitive analogy retrieval in a single-stage (cf 2-stage MAC/FAC model of human performance on analogy retrieval) * Many references to new work added * Subject and author indices added The back cover blurb: While neuroscientists garner success in identifying brain regions and in analyzing individual neurons, ground is still being broken at the intermediate scale of understanding how neurons combine to encode information. This book proposes a method of representing information in a computer that would be suited for modeling the brain's methods of processing information. In stark contrast to traditional computing where "every bit counts," the method proposed by Plate distributes information over large numbers of components, which are mathematically modeled by high-dimensional vectors. No single unit or even a small number of them means anything in particular. The meaningful entity is the total pattern over all the units. Superficially, the patterns appear random. Holographic Reduced Representations (HRRs) are introduced here to model how the brain could distribute each piece of information among thousands of neurons. It had been previously thought that the semantic structure of natural language sentences cannot be encoded practically in a distributed representation but HRRs can overcome problems of earlier proposals. This work has implications for psychology, neuroscience, linguistics, and computer science and artificial intelligence. More details available at http://pws.prserv.net/tap -- Tony Plate From pimh at nici.kun.nl Tue Jan 6 09:23:20 2004 From: pimh at nici.kun.nl (Pim Haselager) Date: Tue, 6 Jan 2004 15:23:20 +0100 (CET) Subject: VIII Brazilian Symposium on Artificial Neural Networks Message-ID: Allow me to ask your attention for a call for papers for the VIII Brazilian Symposium on Artificial Neural Networks (SBRN2004), taking place in Sao Luis, Maranhao, Brazil from September 22 to 24, 2004 http://www.inf.ufrgs.br/~mas/sbiarn04/ Important dates: Submission of full paper: April 15, 2004 Notification of acceptance: May 15, 2004 The proceedings of the SBRN are published by the IEEE Computer Society Press since 1998 and authors of selected best papers are invited to submit an extended version to a special issue of the International Journal of Neural Systems. From ahirose at eis.t.u-tokyo.ac.jp Wed Jan 7 06:28:20 2004 From: ahirose at eis.t.u-tokyo.ac.jp (Akira Hirose) Date: Wed, 07 Jan 2004 20:28:20 +0900 Subject: book announcement In-Reply-To: <5.1.0.14.2.20040107001451.02cbcdd8@pop6.attglobal.net> References: <5.1.0.14.2.20040107001451.02cbcdd8@pop6.attglobal.net> Message-ID: <3FFBED54.4090407@eis.t.u-tokyo.ac.jp> I'm pleased to announce the availability of the following book: "Complex-Valued Neural Networks: Theories and Applications" Editor: Akira Hirose (The University of Tokyo) Publisher: World Scientific Publishing Co. Pte. Ltd., Singapore, in the Series on Innovative Intelligence ISBN 981-238-464-2 Web site http://www.eis.t.u-tokyo.ac.jp/news/cvnn_book.html Amazon.com http://www.amazon.com/exec/obidos/tg/detail/-/9812384642/ Amazon.co.jp http://www.amazon.co.jp/exec/obidos/ASIN/9812384642/ In recent years, complex-valued neural networks have widened the scope of application in optoelectronics, imaging, remote sensing, quantum neural devices and systems, spatiotemporal analysis of physiological neural systems, and artificial neural information processing. In this first- ever book on complex-valued neural networks, the most active scientists at the forefront of the field describe theories and applications from various points of view to provide academic and industrial researchers with a comprehensive understanding of the fundamentals, features and prospects of the powerful complex-valued networks. Contents: George M. Georgiou (California State Univ.) Foreword 1 Akira Hirose (Univ. of Tokyo) "Complex-Valued Neural Networks: An introduction" 2 Tohru Nitta (AIST) "Critical points of the multi-layered complex-valued neural networks" 3 Dong Liang Lee (Ta-Hwa Inst. Tech.) "Complex-valued Neural Associative Memories: Learning Algorithm and Network Stability" 4 Yasuaki Kuroe (Kyoto Inst. Tech.) "A Model of Complex-Valued Associative Memories and Its Dynamics" 5 Justin Pearson (Uppsala Univ.) "Clifford Valued Neural Networks: Background, Theory and Applications" 6 Iku Nemoto (Tokyo Denki Univ.) "A complex-valued neuron model and its application to associative memory" 7 Danilo P. Mandic, S.L.Goh, A.Hanna (Imperial College of Science) "A data-reusing gradient descent algorithm for complex-valued recurrent neural networks" 8 Pritam Rajagopal, Subhash Kak (Louisiana State Univ.) "Instantaneously trained neural networks with complex-valued neurons" 9 Hiroyuki Aoki (Tokyo Coll. Tech.) "Applications of Complex-Valued Neural Networks for Image Processing" 10 Makoto Kinouchi, Masafumi Hagiwara (Keio Univ.) "Memorization of Melodies Using Complex-valued Recurrent Neural Network" 11 Yanwu Zhang (Aware Inc.) "Complex-Valued Generalized Hebbian Algorithm and Its Applications to Sensor Array Signal Processing" 12 Teruyuki Miyajima, Kazuo Yamanaka (Ibaraki Univ.) "Phasor models and their applications to communications" 13 Andriyan Bayu Suksmono (Bandung Inst. Tech.), Akira Hirose (Univ. of Tokyo) "Adaptive Processing of Interferometric Radar Images" 14 Mitsuo Takeda, Takaaki Kishigami (Univ. of Electro-Commun.) "Complex neural network model with an analogy to self-oscillation generated in an optical phase-conjugate resonator" 15 Sotaro Kawata, Akira Hirose (Univ. of Tokyo) "Coherent Lightwave Neural Network Systems: Use of frequency domain" -- From terry at salk.edu Wed Jan 7 21:15:24 2004 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 7 Jan 2004 18:15:24 -0800 (PST) Subject: NEURAL COMPUTATION 16:2 In-Reply-To: <200312170008.hBH08sQ59057@purkinje.salk.edu> Message-ID: <200401080215.i082FOu12798@purkinje.salk.edu> Neural Computation - Contents - Volume 16, Number 2 - February 1, 2004 ARTICLE Analyzing Neural Responses to Natural Signals: Maximally Informative Dimensions Tatyana Sharpee, Nicole C. Rust and William Bialek LETTERS Rapid Temporal Modulation of Synchrony by Competition in Cortical Interneuron Networks P.H.E. Tiesinga and T. J. Sejnowski Dynamic Analyses of Information Encoding in Neural Ensembles by Riccardo Barbieri, Loren M. Frank, David Nguyen, Michael C. Quirk, Victor Solo, Matthew A. Wilson and Emery N. Brown A Network Model of Perceptual Suppression Induced by Transcranial Magnetic Stimulation Yoichi Miyawaki and Masato Okada Adaptive Two-Pass Median Filter Based on Support Vector Machines for Image Restoration Tzu-Chao Lin and Pao-Ta Yu Improving Generalization Performance of Natural Gradient Learning Using Optimized Regularization by NIC Hyeyoung Park, Noboru Murata, Shun-ichi Amari One-Bit-Matching Conjecture for Independent Component Analysis Zhi-Yong Liu, Kai-Chun Chiu and Lei Xu Jacobian Conditioning Analysis for Model Validation Isabelle Rivals and Leon Personnaz Reply to the Comments on "Local Overfitting Control via Leverages" in "Jacobian Conditioning Analysis for Model Validation" by I. Rivals and L. Personnaz Yacine Oussar, Gaetan Monari, Gerard Dreyfus ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2004 - VOLUME 16 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $108 $54 $57.78 Individual $95 $101.65 $143 $85 $90.95 Institution $635 $679.45 $689 $572 $612.04 * 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 hennig at cn.stir.ac.uk Thu Jan 8 04:41:53 2004 From: hennig at cn.stir.ac.uk (Matthias H. Hennig) Date: Thu, 08 Jan 2004 09:41:53 +0000 Subject: EARLY COGNITIVE VISION Message-ID: <1073554912.20937.4.camel@nockerl.cn.stir.ac.uk> ---------------- SECOND ANNOUNCEMENT --------------- EARLY COGNITIVE VISION Location: Sabhal Mor Ostaig, Isle of Skye, Scotland Dates: 28.5. 1.6. 2004 Web: http://www.cn.stir.ac.uk/ecovision-ws Dear Colleague, You may have received this mail already. If so please accept our apologies. I would like to draw your attention to the ECOVISION Workshop taking place on the Isle of Skye in Scotland, end of May 2004 (for details see end of this message). This WS is concerned with the link between biologically motivated computer vision and visual neuroscience especially of higher visual functions. This workshop is now open for registration and paper submission at: http://www.cn.stir.ac.uk/ecovision-ws/ Invited participants will receive refund of their costs. The WS contains 14 keynote lectures as well as 32 shorter talks and one poster session. It includes a special session on Coding of Visual Information. The complete list of keynote speakers who have agreed to come is: Y. Aloimonos (Maryland) K. Boahen (Univ. of Pennsylvania) J.-O.-Eklundh (KTH Stockholm) J. Elder (York Univ.) U. Eysel (Univ. Bochum) O. Faugeras (INRIA) D. Fleet (Univ. of Toronto) L. Florack (Eindhoven Univ. of Technology) L. v. Gool (ETH Zuerich) D. Hogg (Univ. of Leeds) C. v.d. Malsburg (Univ. Bochum & USC) G. Orban (KU Leuven) S. Sarkar (Univ. of South Florida) R. Watt (Stirling Univ.) The conference site is located on the very scenic Isle of Skye (Real Scottish Rain inclusive..). The International Journal of Computer Vision (IJCV) has agreed to publish a special issue based on a refereed selection of papers from this workshop. We would like to invite you to register for this WS and to submit a paper. On behalf of the organizing committee. F. Wrgtter (Univ. of Stirling, Scotland, UK) DETAILSDETAILSDETAILSDETAILSDETAILSDETAILSDETAILSDETAILS Title of the Workshop: EARLY COGNITIVE VISION Location: Sabhal Mor Ostaig, Isle of Skye, Scotland Dates:28.5. 1.6. 2004 Web: http://www.cn.stir.ac.uk/ecovision-ws The WS is organized by the ECOVISON project group consisting of: G. Bisio (Genova) P. Hancock (Stirling) M. v. Hulle (Leuven, Publication Chair) A. Johnston (London) N. Krger (Aalborg) M. Lappe (Muenster) E. Ros. (Granada) S. Sabatini (Genova) F. Wrgtter (Stirling, Workshop Chair) M. Mhlenberg (HELLA Hueck KG,Lippstadt) From handzel at isrmail.isr.umd.edu Wed Jan 7 14:04:46 2004 From: handzel at isrmail.isr.umd.edu (handzel@isrmail.isr.umd.edu) Date: Wed, 7 Jan 2004 14:04:46 -0500 Subject: Job Opening Message-ID: <3afafe6c.fe92821f.81c1500@isrmail.isr.umd.edu> Position: Scientist - Data Mining / Statistical Learning Beyond Genomics Inc., a Waltham, MA based biotechnology company pioneering the field of Systems Biology, is conducting a search for candidates for its Computational Sciences Group. As a member of this Group, you will have an operational role in support of the Company's research collaboration and discovery programs, as well as a key role in the continued development of the Company's advanced data analysis and informatics platforms. The successful candidate will have a strong background in data mining, statistical pattern recognition or machine learning, as well as experience and interest in conducting exploratory data analysis. Suitable candidates at all experience levels are encouraged to apply. For more company information please visit our web site at www.BeyondGenomics.com. Required Skills and Experience: * Solid background in data mining, statistical pattern recognition, machine learning, signal processing, or similar field * Experience in working with large data sets * Ph.D. or M.Sc. combined with suitable experience in appropriate field * Expert level working knowledge of Matlab, Mathematica, or similar scientific programming environment * Experience analysing gene expression array data or equivalent using state-of-the-art methods is desirable * Ability to work in a fast-paced, multi-tasking, multi- disciplinary environment Beyond Genomics offers a competitive compensation and benefits package including medical and dental coverage and 401K plan. Please forward your CV or resume to: Amir Handzel, Ph.D. 40 BEAR HILL ROAD WALTHAM, MA 02451 Fax: 781-895-1119 AHandzel at BeyondGenomics.com ___ From d.mareschal at bbk.ac.uk Wed Jan 7 05:48:57 2004 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Wed, 7 Jan 2004 10:48:57 +0000 Subject: postdoctoral position in London Message-ID: Readers of this list may be interested in the following position. PLEASE DO NOT REPLY DIRECTLY TO ME. Denis ================================ Birkbeck College, University of London, UK Centre for Brain and Cognitive Development POSTDOCTORAL RESEARCH ASSISTANT Full-time Fixed-term 2-Years in the first instance We are seeking an individual to lead a component of an overall research program with external funding on the neurocomputational basis of individual variability in humans. The project will involve connectionist computational modelling of a diverse range of cognitive abilities. Simulation work will make contact with empirical data from several developmental disorders including dyslexia, autism, and schizophrenia. You will preferably need to have strong research background in cognitive psychology, developmental psychology, AI or Neural Computation. You should have experience of computational modelling techniques, good computer skills and the ability to communicate effectively in all media. Salary range: ?20,399 to ?29,473 p.a. inc. salary dependent on qualifications and experience. Closing date: 20 January 2004 For application forms and further details please see www.bbk.ac.uk or send an A4 sae (Ref:APS112), to the Human Resources Team, Birkbeck, Malet Street, Bloomsbury, London, WC1E 7HX or email: humanresources at bbk.ac.uk Informal enquiries to: m.thomas at bbk.ac.uk -- ========================= Dr. Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 (0)20 7631-6582/6226 reception: 6207 fax +44 (0)20 7631-6312 http://www.psyc.bbk.ac.uk/people/academic/mareschal_d/ ========================= From ckiw at inf.ed.ac.uk Tue Jan 13 08:49:18 2004 From: ckiw at inf.ed.ac.uk (Chris Williams) Date: Tue, 13 Jan 2004 13:49:18 +0000 (GMT) Subject: Postdoc position, PhD studentships at U of Edinburgh Message-ID: [apologies if you receive this message multiple times] 1) The School of Informatics, University of Edinburgh invites applications for one post of Research Fellow on the project Compilers that Learn to Optimise (COLO). COLO is an EPSRC funded project in the area of applying machine learning to program optimisation. This project is a collaboration between the Compiler group headed by Dr Michael O'Boyle and Machine Learning group led by Dr Chris Williams. The Research Fellow will be expected to work on developing methods for the following two problems (1) global optimisation methods for searching for the best compiler optimisation off-line, (2) supervised learning for predicting optimal compiler transformations at compile time. You should normally hold a PhD in a relevant area and be capable of developing new theory and contributing to tool development. The fellowship is of twenty-four months duration (in the first instance). See https://www.jobs.ed.ac.uk/jobs/index.cfm?action=jobdet&jobid=3001119 for further information and the application procedure. The closing date for applications is 16 February 2004. 2) We are also advertising two EPSRC funded PhD studentships on the COLO project. See http://www.dcs.ed.ac.uk/home/mob/phd.html for further information and the application procedure. Informal enquiries about the Research Fellowship and PhD studentships can be addressed to Chris Williams (c.k.i.williams at ed.ac.uk) or Mike O'Boyle (mob at inf.ed.ac.uk). Chris Williams Dr Chris Williams c.k.i.williams at ed.ac.uk Institute for Adaptive and Neural Computation School of Informatics, University of Edinburgh 5 Forrest Hill, Edinburgh EH1 2QL, Scotland, UK fax: +44 131 650 6899 tel: (direct) +44 131 651 1212 (department switchboard) +44 131 650 3100 http://anc.ed.ac.uk/ From krichmar at nsi.edu Tue Jan 13 21:51:08 2004 From: krichmar at nsi.edu (Jeff Krichmar) Date: Tue, 13 Jan 2004 18:51:08 -0800 Subject: POSTDOCTORAL FELLOWSHIP in Brain-Based Devices and Machine Vision Message-ID: <000a01c3da49$42fa8d10$c6b985c6@nsi.edu> Please post and circulate as you see fit. Thank you. POSTDOCTORAL FELLOWSHIP in Brain-Based Devices and Machine Vision The Neurosciences Institute, located in San Diego, California, invites applications for a POSTDOCTORAL FELLOWSHIP to build neurobiologically based models of vision for a robotic Segway platform (http://www.segway.com) as a part of ongoing research on Brain-Based Devices. Continuing previous research conducted at the Institute, the fellow will be focusing on the design of simulated models of large-scale neuronal networks that are capable of handling real world visual input and generating motor responses for the Segway RMP (Robotic Mobile Platform). Applicants should have a background in robotics, engineering, or computer science, and a strong interest in neuroscience. Fellows will receive stipends appropriate to their qualifications and experience. Submit a curriculum vitae, statement of research interests, and three references to: Dr. Jeffrey L. Krichmar The Neurosciences Institute 10640 John Jay Hopkins Drive San Diego, California 92121 Email: krichmar at nsi.edu Fax: 858-626-2099 For a description of the project, refer to http://www.nsi.edu/nomad/. For a description of The Neurosciences Institute, refer to http://www.nsi.edu. From planning at icsc.ab.ca Tue Jan 13 15:05:39 2004 From: planning at icsc.ab.ca (Jeanny S. Ryffel) Date: Tue, 13 Jan 2004 13:05:39 -0700 Subject: upcoming deadline BICS 2004, Scotland Message-ID: <5.1.0.14.2.20040113123721.00a47080@pop.interbaun.com> Submission deadline January 31, 2004 The science of neural computation focuses on mathematical aspects for solving complex practical problems. It also seeks to help neurology, brain theory and cognitive psychology in the understanding of the functioning of the nervous system by means of computational models of neurons, neural nets and sub-cellular processes. BICS2004 aims to become a major point of contact for research scientists, engineers and practitioners throughout the world in the fields of cognitive and computational systems inspired by the brain and biology. Participants will share the latest research, developments and ideas in the wide arena of disciplines encompassed under the heading of BICS2004: First International ICSC Symposium on Cognitive Neuro Science (CNS 2004) (from computationally inspired models to brain-inspired computation) Chair: Prof. Igor Aleksander, Imperial College London, U.K Second International ICSC Symposium on Biologically Inspired Systems (BIS 2004) Chair: Prof. Leslie Smith, University of Stirling, U.K. Third International ICSC Symposium on Neural Computation (NC'2004) Chair: Dr. Amir Hussain, University of Stirling, U.K. http://www.icsc-naiso.org/conferences/bics2004/bics-cfp.html if you do not wish to receive further information, please send message to: planning at icsc.ab.ca Planning Division ICSC Interdisciplinary Research NAISO Natural and Artificial Intelligence Systems Organization Canada --------------------------------------------------- Email: planning at icsc.ab.ca Website: www.icsc-naiso.org Tel: +1-780- 387 3546 Fax: +1-780- 387 4329 From niebur at jhu.edu Tue Jan 13 13:54:29 2004 From: niebur at jhu.edu (niebur@jhu.edu) Date: Tue, 13 Jan 2004 13:54:29 -0500 Subject: Postdoctoral fellow in computational neuroscience and primate single-unit recording: mechanisms of tactile selective attention Message-ID: <200401131854.i0DIsTn30641@russell.mindbrain> We are seeking a postdoctoral fellow to work on a project that involves both computational modelling and neurophysiological recordings in awake behaving monkeys. The goal of the project is to understand the neural mechanisms underlying attentional selection of tactile stimuli. A strong quantitative background is required and experience with neurophysiological recordings in awake behaving animals is desired. We will, however, consider candidates who are otherwise well-qualified but lack recording experience; they will need to be exceptionally motivated to learn the techniques of animal training and single-unit recordings. The work is a collaborative project involving the labs of Drs. Ernst Niebur, Steven Hsiao and Ken Johnson, at the Mind/Brain Institute of The Johns Hopkins University. If interested, please contact Ernst Niebur, niebur at jhu.edu, with a CV, a statement of research interest, and the names and email addresses of 2 or more references. All email should be sent in ASCII format. -- Dr. Ernst Niebur Krieger Mind/Brain Institute Assoc. Prof. of Neuroscience Johns Hopkins University niebur at jhu.edu http://cnslab.mb.jhu.edu 3400 N. Charles Street (410)516-8643, -8640 (secr), -8648 (fax), -3357 (lab) Baltimore, MD 21218 From rojas at inf.fu-berlin.de Wed Jan 14 08:36:33 2004 From: rojas at inf.fu-berlin.de (Raul Rojas) Date: Wed, 14 Jan 2004 14:36:33 +0100 Subject: Postdoc position in AI for women Message-ID: <000001c3daa3$6d0dc810$796e2da0@pcpool.mi.fuberlin.de> Dear colleagues, The Department of Computer Science at the Free University of Berlin is looking for female candidates for a Postdoc position. The position is funded within the framework of a grant with the purpose of increasing the percentage of women faculty in computer science. The position will be funded for at least two years and will collaborate with the AI group in our university (http://www.inf.fu-berlin.de/inst/ag-ki/ger/index.html) For those familiar with the German system, this is a C1 position. The general area of the candidate should be artificial intelligence, specially machine vision, handwriting recognition, cognitive robotics, connectionism. Candidates with a PhD in computer science or a related technical area (mathematics, physics, engineering)are welcome to apply. Please send an application by e-mail, with a CV, and a letter describing your areas of interest, as well as the names of two references. PDF files are better. And again: this is a program for women faculty development. Prof.Dr. Raul Rojas Freie Universit?t Berlin Takustr. 9 14195 Berlin Germany From mozer at colorado.edu Thu Jan 15 19:41:57 2004 From: mozer at colorado.edu (Michael C. Mozer) Date: Thu, 15 Jan 2004 17:41:57 -0700 Subject: Computational Linguistics position Message-ID: <40073355.9090406@colorado.edu> University or Organization: University of Colorado Department: ICS Rank of Job: Assistant Professor Specialty Areas: Computational Linguistics Description: Computational Linguist, Tenure Track Position The Institute of Cognitive Science at the University of Colorado invite applications for a full-time tenure-track position in computational linguistics/computational psycholinguistics at the Assistant level, with a starting date of Fall 2004. Appropriate degree areas include linguistics, psychology, computer science, and cognitive science. In exceptional cases, appointment at the early Associate level will be considered. We seek applicants with a strong record of research in an area that integrates linguistics, cognitive science, and computation. Duties include graduate and undergraduate teaching, research, research supervision, and Institute, Departmental, and college service assignments as appropriate for university faculty members. We will give strongest consideration to applicants whose research is empirically based, and makes use of corpus, psycholinguistic and computational methods. Applicants should send curriculum vitae, copies of representative publications, a teaching portfolio, a research summary, and the names of three referees to: Dr. Donna Caccamise, Associate Director Institute of Cognitive Science University of Colorado, Boulder 344 UCB Boulder, CO 80309-0344 Please apply by January 30, 2004. Applications will continue to be accepted after this date until the position is filled. E-mail inquiries may be sent to donnac at psych.Colorado.edu. The University of Colorado is an Equal Opportunity/Affirmative Action Employer. Address for Applications: Attn: Caccamise Donna Caccamise ICS, UCB 344 University of Colorado Boulder, CO 80309 United States of America Position is open until filled Contact Information: Caccamise Donna Caccamise Email: donnac at psych.colorado.edu Tel: 303 735-3602 Fax: 303 735-3602 Website: http://ics.colorado.edu From gary at cs.ucsd.edu Fri Jan 16 18:45:00 2004 From: gary at cs.ucsd.edu (Gary Cottrell) Date: Fri, 16 Jan 2004 15:45:00 -0800 (PST) Subject: Predoctoral fellowships available at UCSD Message-ID: <200401162345.i0GNj0T11120@fast.ucsd.edu> UCSD has obtained a $3.4M grant NSF IGERT grant for interdisciplinary predoctoral training in "Vision and Learning in Humans and Machines". Current Ph.D. applicants to UCSD should apply also to this program if they are interested in these topics. Please see my home page for details. The text below is extracted from the grant application: Consider creating a) a computer system to help physicians make a diagnosis using all of a patient's medical data and images along with millions of case histories; b) intelligent buildings and cars that are aware of their occupants activities; c) personal digital assistants that watch and learn your habits -- not only gathering information from the web but recalling where you had left your keys; or d) a computer tutor that watches a child as she performs a science experiment. Each of these scenarios requires machines that can see and learn, and while there have been tremendous advances in computer vision and computational learning, current computer vision and learning systems for many applications (such as face recognition) are still inferior to the visual and learning capabilities of a toddler. Meanwhile, great strides in understanding visual recognition and learning in humans have been made with psychophysical and neurophysiological experiments. The time is ripe to apply our knowledge of human vision to the application of computer vision algorithms. Simultaneously we believe that the consideration of why vision is difficult for computers can give great insight to experimentalists examining the human and animal visual systems. Similarly, new techniques from computational learning will advance computer vision, while the high dimensional nature of video data will challenge current learning algorithms. {\em The intellectual merit of this proposal is its focus on creating novel interactions between the four areas of: computer and human vision, and human and machine learning.} We believe these areas are intimately intertwined, and that the synergy of their simultaneous study will lead to breakthroughs in all four domains. Our goal in this IGERT is to train a new generation of scientists and engineers who are as versed in the mathematical and physical foundations of computer vision and computational learning as they are in the biological and psychological basis of natural vision and learning. On the one hand, students will be trained to propose a computational model for some aspect of biological vision and then design experiments (fMRI, single cell recordings, psychophysics) to validate this model. On the other hand, they will be ready to expand the frontiers of learning theory and embed the resulting techniques in real-world machine vision applications. Example research studies might include, but are not limited to, machine learning applied to machine vision; extensions of machine learning to well-known human learning methods, such as imitation; a study of how humans solve some of the hardest problems in machine vision -- e.g., viewpoint variation, lighting variation, deformation of non-rigid objects, etc.; or the study of how children learn to see. {\em The broader impact of this program will be the development of a generation of scholars who will bring new tools to bear upon fundamental problems in human and computer vision, and human and machine learning.} Our plan is to use the very successful dual mentor approach that has been employed here by the La Jolla Interfaces in Science Program to encourage students to use the techniques from at least two areas in their research. We will develop a new curriculum that introduces new cross-disciplinary courses to complement the current offerings. In addition, students accepted to the program will go through a two-week ``boot camp,'' before classes start, where they will receive intensive training in machine learning and vision using MatLab, perceptual psychophysics, and brain imaging. Monthly faculty/fellow dinner meetings with students presenting their individual projects will keep everyone informed of progress. We will balance on-campus training with summer internships in industry. Gary Cottrell 858-534-6640 FAX: 858-534-7029 Faculty Assistant: none assigned, but try: Jennifer Dickson at (858) 534-5948 jdickson at cs.ucsd.edu Computer Science and Engineering 0114 IF USING FED EX INCLUDE THE FOLLOWING LINE: "Only connect" 3101 Applied Physics and Math Building University of California San Diego -E.M. Forster La Jolla, Ca. 92093-0114 Email: gary at ucsd.edu Home page: http://www-cse.ucsd.edu/~gary/ Lab Phone: 858-822-3521 From terry at salk.edu Fri Jan 16 13:46:28 2004 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 16 Jan 2004 10:46:28 -0800 (PST) Subject: Telluride Neuromorphic Workshop Announcement In-Reply-To: <200401080215.i082FOu12798@purkinje.salk.edu> Message-ID: <200401161846.i0GIkSp35223@purkinje.salk.edu> Neuromorphic Engineering Workshop call for applications Sunday, JUNE 27 - Saturday, JULY 17, 2004 TELLURIDE, COLORADO Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Ralph ETIENNE-CUMMINGS (Johns Hopkins University) Timmer HORIUCHI (University of Maryland) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Christof KOCH (California Institute of Technology) Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) We invite applications for a three week summer workshop that will be held in Telluride, Colorado from Sunday, June 27 to Saturday, July 17, 2004. The application deadline is Friday, March 19, and application instructions are described at the bottom of this document. The 2003 Workshop and Summer School on Neuromorphic Engineering, sponsored by the National Science Foundation, the Whitaker Foundation, the Office of Naval Research, the Defence Advanced Research Projects Agency, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology, was an exciting event and a great success. We strongly encourage interested parties to browse through the previous workshop web pages. GOALS: Carver Mead introduced the term "Neuromorphic Engineering" for a new field based on the design and fabrication of artificial neural systems, such as vision systems, head-eye systems, and roving robots, whose architecture and design principles are based on those of biological nervous systems. The goal of this workshop is to bring together young investigators and more established researchers from academia with their counterparts in industry and national laboratories, working on both neurobiological as well as engineering aspects of sensory systems and sensory-motor integration. The focus of the workshop will be on active participation, with demonstration systems and hands on experience for all participants. Neuromorphic engineering has a wide range of applications from nonlinear adaptive control of complex systems to the design of smart sensors. Many of the fundamental principles in this field, such as the use of learning methods and the design of parallel hardware (with an emphasis on analog and asynchronous digital VLSI), are inspired by biological systems. However, existing applications are modest and the challenge of scaling up from small artificial neural networks and designing completely autonomous systems at the levels achieved by biological systems lies ahead. The assumption underlying this three week workshop is that the next generation of neuromorphic systems would benefit from closer attention to the principles found through experimental and theoretical studies of real biological nervous systems as whole systems. FORMAT: The three week summer workshop will include background lectures on systems neuroscience (in particular learning, oculo-motor and other motor systems and attention), practical tutorials on analog VLSI design, small mobile robots (Koalas, Kheperas, LEGO robots), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, the majority of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control * central pattern generator * robotics * multichip communication * analog VLSI * learning The active perception project group will emphasize vision and human sensory-motor coordination. Issues to be covered will include spatial localization and constancy, attention, motor planning, eye movements, and the use of visual motion information for motor control. The central pattern generator group will focus on small walking and undulating robots. It will look at characteristics and sources of parts for building robots, play with working examples of legged and segmented robots, and discuss CPG's and theories of nonlinear oscillators for locomotion. It will also explore the use of simple analog VLSI sensors for autonomous robots. The robotics group will use rovers and working digital vision boards as well as other possible sensors to investigate issues of sensorimotor integration, navigation and learning. The audition group aims to develop biologically plausible algorithms and aVLSI implementations of specific auditory tasks such as source localization and tracking, and sound pattern recognition. Projects will be integrated with visual and motor tasks in the context of a robot platform. The multichip communication project group will use existing interchip communication interfaces to program small networks of artificial neurons to exhibit particular behaviors such as amplification, oscillation, and associative memory. Issues in multichip communicationwill be discussed. This year we will also have some new robots kindly donated by the WowWee Toys division of Hasbro in Hong Kong. This will permit us to carry out experiments with WooWee/Hasboro hardware through Mark Tilden. LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350miles). Great Lakes Aviation and America West Express airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do not rent a car. Bring hiking boots, warm clothes, rain gear, and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around mid April 2004. Participants are expected to pay a $275.00 workshop fee at that time in order to reserve a place in the workshop. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. Travel reimbursement of up to $500 for US domestic travel and up to $800 for overseas travel will be possible if financial help is needed (please specify on the application). HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e.postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage qualified women and minority candidates to apply. Application should include: * First name, Last name, Affiliation, valid e-mail address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Two letters of recommendation. Complete applications should be sent to: Terrence Sejnowski The Salk Institute 10010 North Torrey Pines Road San Diego, CA 92037 e-mail: telluride at salk.edu FAX: (858) 587 0417 The application deadline is March 19, 2004. Applicants will be notified by e-mail around mid April. From nk at cs.aue.auc.dk Fri Jan 16 12:34:34 2004 From: nk at cs.aue.auc.dk (Norbert Kruger) Date: Fri, 16 Jan 2004 18:34:34 +0100 Subject: Final Call for Papers: Workshop on Coding of Visual Information in the Brain Message-ID: <400820AA.6090503@cs.aue.auc.dk> Workshop on Coding of Visual Information in the Brain June 1, 2004, Isle of Skye, Scotland Satellite event of the Early Cognitive Vision Workshop (28.5.-1.6.2004) http://www.cn.stir.ac.uk/ecovision-ws/ Call for Contributions How is visual Information coded in the human brain? How are statistical properties of natural images related to the internal representations/coding? What is the prior knowledge the human visual system is equipped with? In what sense does the actual task influence the internal state? What is the goal of the early visual processes and how can we achieve integration? What is the functional role of the temporal structure of neural firing patterns? These questions are relevant for research concerning the modelling of biological visual systems as well as building artificial systems. The workshop 'Coding of Visual Information in the Brain' has the aim to bring together scientists involved in neurophysiology, psychology and computer vision to discuss these issues under a multi-disciplinary perspective. As well as the contributed talks and posters, a number of leading scientists with strong interest in bridging the gap between human and artificial vision will be giving invited talks. The workshop will follow the tradition of the 'Information Theory and the Brain' workshops held in Stirling 1995 and in Newquay 1997. However, in contrast to its predecessors it is more focussed on vision. The workshop will be organised as a satellite event of the Early Cognitive Vision Workshop that will be held from May 28 to June 1 2004 (see http://www.cn.stir.ac.uk/ecovision-ws/). Please submit a one-page abstract, preferably by email to Peter Hancock (pjbh1 at psych.stir.ac.uk) or Norbert Krueger (nk at cs.aue.auc.dk) by 23.1.2004. Organising Committee Peter Hancock (Stirling, Scotland) Norbert Krueger (Esbjerg, Denmark) Florentin Woergoetter (Stirling, Scotland) Roland Baddeley (Sussex, England) Laurenz Wiskott (Berlin, Germany) James Elder (York, Canada) Invited Speakers James Elder (York, Canada) Christoph von der Malsburg (Bochum, Germany) Guy Orban (Leuven, Belgium) Roger Watt (Stirling, Scotland) From miguel at cs.toronto.edu Sat Jan 17 01:15:32 2004 From: miguel at cs.toronto.edu (Miguel . Carreira-Perpin) Date: Sat, 17 Jan 2004 01:15:32 -0500 Subject: TR on the number of modes of a Gaussian mixture Message-ID: <16392.54020.906061.753113@axon.ai> We would like to announce a new TR: An isotropic Gaussian mixture can have more modes than components Miguel Carreira-Perpinan and Chris Williams Available from http://www.inf.ed.ac.uk/publications/report/0185.html It is well known that in 1-d a mixture of isotropic Gaussians can have no more modes than components (see e.g. Silverman (1981), Yuille and Poggio (1986)). In this TR we show that in d dimensions (with d >= 2) a mixture of M > 2 isotropic Gaussians can have more than M modes. We first discuss a 3-component mixture in d = 2 where the Gaussians are located at the vertices of an equilateral triangle. For a certain range of variances modes are present near to the vertices and also at the centre of the triangle. (The equilateral triangle construction was suggested by Prof. J. J. Duistermaat, personal communication, 2003.) We also extend the construction to the regular simplex with M vertices and show that for M > 2 there is always a range of variances for which M+1 modes are present. Miguel Carreira-Perpinan Chris Williams -- Miguel A Carreira-Perpinan Dept. of Computer Science, Rm 283 Tel. (416) 9463986 University of Toronto Fax (416) 9781455 6 King's College Road mailto:miguel at cs.toronto.edu Toronto, ON M5S 3H5, Canada http://www.cs.toronto.edu/~miguel From oreilly at grey.colorado.edu Sun Jan 18 23:06:25 2004 From: oreilly at grey.colorado.edu (Randall C. O'Reilly) Date: Sun, 18 Jan 2004 21:06:25 -0700 Subject: Postdoc in Computational Cognitive Neuroscience Message-ID: <200401190406.i0J46PM13212@grey.colorado.edu> Postdoctoral Position Announcement: A postdoctoral research position in the computational cognitive neuroscience lab at the University of Colorado at Boulder is now open for applications. The ideal candidate is someone with a strong background in computational modeling of neural systems as applied to cognitive phenomena such as memory, perception, attention, language, problem solving, etc. The focus of the funding for this position is on developing a biologically-based cognitive architecture based on existing models of specialized brain areas including hippocampus, prefrontal cortex/basal ganglia, and posterior cortex. Although considerable progress has been made on these more specialized models, much work remains to be done on integrating them into an overall architecture that is capable of more complex cognitive functions. Our ultimate goal is to develop neural models capable of performing sophisticated temporally-extended tasks in complex, real-world environments (e.g., navigation, planning, problem solving). Initial steps include developing an interactive model of the visual system (dorsal-ventral pathways) that responds to top-down attentional/goal inputs from prefrontal cortex, and integrating this with prefrontal cortex/basal ganglia learning models. Throughout, the use of powerful learning mechanisms is emphasized, as is the inspiration from both neural and cognitive data, and the application of the models to simulating concrete empirical data. Due to the broad scope of this research and other work going on within the lab, there is considerable flexibility in the choice of specific research projects. This position is supervised by Randy O'Reilly, and collaborators include a number of researchers at CU Boulder (Yuko Munakata, Marie Banich, Tim Curran, Mike Mozer, Jerry Rudy, Dan Jurafsky) and at other institutions (Jonathan Cohen @ Princeton, Todd Braver @ Wash U St. Louis, David Noelle @ Vanderbilt, Nicolas Rougier @ Loria, Nancy, France). For more information, see http://psych.colorado.edu/~oreilly/lab.html. In addition to providing an exciting research environment, the greater Boulder area offers an exceptional quality of life. Spectacularly situated at the edge of the Rockies, this area provides a wide variety of extraordinary outdoor activities, an average of over 300 sunny days per year, and also affords a broad range of cultural activities. Interested individuals should send a vita, representative publications, and a statement of research interests. Three letters of recommendation should be sent separately. Materials can be sent electronically to oreilly at psych.colorado.edu or snail-mailed to: Randall O'Reilly Department of Psychology, 345 UCB University of Colorado, Boulder Boulder, CO 80309-0345 Review of applications will begin in February 2004, and will continue until the position is filled. The University of Colorado Boulder is an equal opportunity employer. From bert at snn.kun.nl Wed Jan 21 06:37:47 2004 From: bert at snn.kun.nl (Bert Kappen) Date: Wed, 21 Jan 2004 12:37:47 +0100 (CET) Subject: New journal Message-ID: Dear all, I would like to draw your attention to a new journal that has been lauched this month: Journal of Statistical Mechanics: Theory and Experiment (JSTAT). This is an online journal published by IOP and SISSA. JSTAT has a very broad scope, among which also topics relevant to the connectionist community: Phase transitions and critical phenomena. Non-equilibrium processes. Applications in biological physics, genomics. Information theory, combinatorial optimization, graphs and networks Collective phenomena in economic and social systems. New applications of statistical mechanics. For more information on the topics covered in JSTAT see https://jstat.sissa.it/index.jsp JSTAT has a fully electronic reviewing process, which assures fast response. I think that JSTAT is a good place to publish physics-style results from the connectionists community, and I am looking forward to your submissions. Bert Kappen SNN University of Nijmegen tel: +31 24 3614241 fax: +31 24 3541435 URL: www.snn.kun.nl/~bert The University of Nijmegen will be named Radboud University Nijmegen as of September 1st, 2004 From bogus@does.not.exist.com Wed Jan 21 12:53:01 2004 From: bogus@does.not.exist.com () Date: Wed, 21 Jan 2004 17:53:01 -0000 Subject: Call for Participation: Symposium: 'Human Language: cognitive, neuroscientific and dynamical systems perspectives' Message-ID: <5AAACCE7A24D9441963855051C57E2033DF656@pinewood.ncl.ac.uk> From joab at dcs.shef.ac.uk Thu Jan 22 03:10:31 2004 From: joab at dcs.shef.ac.uk (Joab Winkler) Date: Thu, 22 Jan 2004 08:10:31 +0000 (GMT) Subject: Sheffield Machine Learning Workshop Message-ID: <200401220810.i0M8AVnl016591@holly.dcs.shef.ac.uk> Preliminary announcement SHEFFIELD MACHINE LEARNING WORKSHOP Sheffield, United Kingdom Septemeber 7-10, 2004 www.dcs.shef.ac.uk/ml/workshop/ The Machine Learning Research Group in The Department of Computer Science at The University of Sheffield is organising a workshop on deterministic and statistical methods in machine learning, with a strong emphasis on mathematical and numerical methods. Confirmed invited speakers: Chris Bishop (Microsoft Research, UK) Andrew Blake (Microsoft Research, UK) Herve Bourlard (IDIAP, Switzerland) Andrzej Cichocki (RIKEN, Japan) Michael Elad (Stanford, USA) Jerry Eriksson (Umea, Sweden) Zoubin Ghahramani (University College London, UK) Gene Golub (Stanford, USA) Josef Kittler (Surrey University, UK) David Lowe (Aston University, UK) David Mackay (Cambridge University, UK) Ian Nabney (Aston University, UK) Manfred Opper (Southhampton University, UK) David Lowe (Aston University, UK) John Platt (Microsoft Research, USA) Stephen Roberts (Oxford University, UK) Bernard Schoelkopf (Max Planck Institute, Germany) Michael Tipping (Microsoft Research, UK) Chris Williams (Edinburgh University, UK) The refereed proceedings of the conference which will be published by Springer in the series Lecture Notes in Computer Science. The workshop is supported by grants from the Engineering and Physical Sciences Research Council, the London Mathematical Society and Sheffield University. The workshop is expected to form part of the thematic programme for the PASCAL European Network of Excellence. Registration will open on 2 April 2004, and early registration is encouraged because there is a limited number of places. For more details, contact the organisers: Joab Winkler Mahesan Niranjan Neil Lawrence E-mail: mlworkshop at dcs.shef.ac.uk Department of Computer Science The University of Sheffield United Kingdom From bischof at icg.tu-graz.ac.at Fri Jan 23 03:11:13 2004 From: bischof at icg.tu-graz.ac.at (Horst Bischof) Date: Fri, 23 Jan 2004 09:11:13 +0100 Subject: SLCV CfP Message-ID: <4010D721.60309@icg.tu-graz.ac.at> *** Last Call for Papers *** SLCV 2004 ECCV International Workshop on Statistical Learning in Computer Vision Workshop on Statistical Learning in Computer Vision http://slcv.icg.tu-graz.ac.at/ May 15, 2004 Prague, Czech Republic ----------------------------------------------------- SLCV 2004 is held in conjunction with ECCV 2004 http://cmp.felk.cvut.cz/eccv2004/ DATES Paper submission: 1 February 2004, 24:00 CET Author Notification: 15 March 2004 Camera ready paper: 5 April 2004 Workshop: 15 May 2004 SCOPE There is no doubt that learning will play a major role in developing intelligent visual and cognitive systems as it has also been emphasized by the Calls for project proposals on Cognitive systems both in Europe and United States. The goal of this workshop is to promote information exchange and technical interaction among researchers working on methods for visual learning, focusing on robust and adaptable techniques, capable of operating in unconstrained environments. Statistical methods have been carried over from the statistical pattern recognition to computer vision and have successfully been used in many applications. However, it is still to be determined how these methods can be used and adapted for multi-modal, continuous, robust learning. Several issues need closer investigation e.g., representations, types of learning (supervised, unsupervised, reinforcement), relations between generative and discriminative methods, etc. TOPICS OF INTEREST include but are not limited to the following: - new theoretical approaches to statistical learning - relations between supervised, unsupervised, reinforcement learning - learning of visual concepts - learning for recognition and categorization - continuous (life-long) learning - relations between generative and discriminative learning - multi-modal learning - generalization of learning across modalities, tasks - contextual visual learning - biologically motivated learning - applications of learning in computer vision WORKSHOP CO-CHAIRS Ales Leonardis, University of Ljubljana, Slovenia Horst Bischof, Graz University of Technology, Austria PROGRAM COMMITTEE Peter Auer, University of Leoben and Graz University of Technology, Austria Bir Bhanu, University of California, USA Horst Bischof, Graz University of Technology, Austria Joachim Buhmann, ETH, Switzerland Hilary Buxton, University of Sussex, UK Terry Caelli, University of Alberta, Canada Tim Cootes, University of Manchester, UK Fernando De la Torre, CMU, USA Bruce Draper, Colorado State University, USA Hany Farid, Dartmouth, USA Edwin Hancock, University of York, UK Bernd Heisele, MIT, USA David Hogg, University of Leeds, UK Nebojsa Jojic, Microsoft, USA Ales Leonardis, University of Ljubljana, Slovenia Jiri Matas, Czech Technical University, Czech Republic Lucas Paletta, Joanneum Research, Austria Bernt Schiele, ETH, Switzerland Anuj Srivastava, Florida State University, USA Antonio Torralba, MIT, USA Daphna Weinshall, The Hebrew University of Jerusalem, Israel John Weng, Michigan State University, USA CONTACT Ales Leonardis Horst Bischof alesl at fri.uni-lj.si bischof at icg.tu-graz.ac.at --- We apologise if you received multiple copies of this announcement --- -- ============================================== Univ. Prof. Dr. Horst Bischof Institute for Computer Graphics and Vision TU Graz Inffeldgasse 16 2. OG A-8010 Graz, AUSTRIA email: bischof at icg.tu-graz.ac.at web: www.icg.tu-graz.ac.at Tel.: +43-316-873-5014 Fax.: +43-316-873-5050 =============================================== From bogus@does.not.exist.com Fri Jan 23 11:07:35 2004 From: bogus@does.not.exist.com () Date: Fri, 23 Jan 2004 11:07:35 -0500 Subject: Post Doctorial Positions Message-ID: <64FB06AE9F2A204DA14763D7C45961CC28B5A3@ARLABML01.DS.ARL.ARMY.MIL> From nando at cs.ubc.ca Fri Jan 23 11:46:43 2004 From: nando at cs.ubc.ca (Nando de Freitas) Date: Fri, 23 Jan 2004 08:46:43 -0800 Subject: PhD positions at UBC Message-ID: <40114FF3.90902@cs.ubc.ca> The Computer Science department of the University of British Columbia is looking for outstanding PhD and Masters candidates in the areas of machine learning, robotics, artificial intelligence and computer vision. Studentships will provide full financial support to successful applicants. For more information, please contact Nando de Freitas (nando at cs.ubc.ca) or visit the following websites: http://www.cs.ubc.ca/ http://www.cs.ubc.ca/labs/lci/ http://www.cs.ubc.ca/prospective/grad/index.html Best, Nando From Alain.Destexhe at iaf.cnrs-gif.fr Wed Jan 28 09:08:52 2004 From: Alain.Destexhe at iaf.cnrs-gif.fr (Alain Destexhe) Date: Wed, 28 Jan 2004 15:08:52 +0100 Subject: Advanced Course in Computational Neuroscience - Obidos 2004 Message-ID: <4017C274.D18504D3@iaf.cnrs-gif.fr> ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE (AN IBRO NEUROSCIENCE SCHOOL) August 16th - September 10th, 2004 MUNICIPALITY OF OBIDOS, PORTUGAL DIRECTORS: Ad Aertsen (University of Freiburg, Germany) Peter Dayan (University College London, UK) Alain Destexhe (CNRS, Gif-sur-Yvette, France) Eilon Vaadia (Hebrew University, Jerusalem, Israel) The Advanced Course in Computational Neuroscience introduces students to the panoply of problems and methods of computational neuroscience, addressing issues of neural organization from sub-cellular to network and inter-areal levels. The course has two complementary parts. Mornings are devoted to lectures given by distinguished international faculty on topics across the breadth of experimental and computational neuroscience. During the rest of the day, students are given practical training in the art and practice of neural modeling, largely through the medium of their individual choice of model systems. The first week of the course introduces students to essential neurobiological concepts and to the most important techniques in modelling single cells, networks and neural systems. Students learn how to solve their research problems using software packages such as GENESIS, MATLAB, NEST, NEURON, XPP, etc. During the following three weeks the lectures cover specific brain areas and functions. Topics range from modelling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the brain. The course ends with project presentations by the students. The Advanced Course in Computational Neuroscience is designed for advanced graduate students and postdoctoral fellows in a variety of disciplines, including neuroscience, physics, electrical engineering, computer science, mathematics and psychology. Students are expected to have a keen interest and basic background in neurobiology as well as some computer experience. Students of any nationality can apply. A maximum of 30 students will be accepted. There will be a fee of EUR 800,- per student covering costs for lodging, meals and other course expenses. Depending on funding, there will be a limited limited number of tuition fee waivers and travel stipends available for students who need financial help for attending the course. We have received IBRO funding to provide full travel and fee support for 4-5 students from developing countries. These students will be accepted according to the normal selection procedure. We specifically encourage applications from researchers who work in the developing world. Applications, including a description of the target project must be submitted electronically (see below) and should be accompanied by two letters of recommendation (also sent electronically). Applications will be assessed by a committee, with selection being based on the following criteria: the scientific quality of the candidate (CV) and of the project, the letters, and evidence that the course affords substantial benefit to the candidate's training. More information and application forms can be obtained from: http://www.neuroinf.org/courses/EUCOURSE/EU04 Please apply electronically using a web browser. Contact address: - mail: Camilla Bruns, FR2-1, Fakultaet IV, Technical University of Berlin, Franklinstrasse 28/29, 10587 Berlin, Germany - e-mail: bruns at cs.tu-berlin.de APPLICATION DEADLINE: April 23, 2004 DEADLINE FOR LETTERS OF RECOMMENDATION: April 30, 2004 Applicants will be notified of the results of the selection procedures by end of May 2004. CONFIRMED FACULTY: Moshe Abeles, Hebrew University, Israel Ad Aertsen, University of Freiburg, Germany Amos Arieli, Weizmann Institute, Israel Peter Dayan, University College London, UK Erik de Schutter, University of Antwerp, Belgium Alain Destexhe, CNRS, France Marcus Diesmann, University of Freiburg, Germany Wulfram Gerstner, EPFL, Switzerland Mike Hausser, University College London, UK Michael Hines, Yale University, USA Gwendael LeMasson, University of Bordeaux, France Siegrid Lowel, Leibniz-Institute for Neurobiology, Germany Israel Nelken, Hebrew University, Israel Miguel Nicolelis, Duke University, USA John Rinzel, New York University, USA Arnd Roth, Max Planck Inst. Heidelberg, Germany Michael Rudolph, CNRS, France Edward Stern, Harvard University, USA Tali Tishby, Hebrew University, Israel Alex Thomson, University College London, UK Emo Todorov, University of California San Diego, USA Misha Tsodyks, Weizmann Institute, Israel Eilon Vaadia, Hebrew University, Israel Charlie Wilson, University of Texas San Antonio, USA Matt Wilson, MIT, USA Li Zhaoping, University College London, UK From guestrin at cs.stanford.edu Tue Jan 27 12:33:02 2004 From: guestrin at cs.stanford.edu (Carlos Ernesto Guestrin) Date: Tue, 27 Jan 2004 09:33:02 -0800 (PST) Subject: Intel Research - Berkeley Lab: positions in Machine Learning and Probabilistic AI Message-ID: Intel Research - Berkeley Lab: positions in Machine Learning and Probabilistic AI The Intel Research - Berkeley Lab is currently seeking candidates for Researcher and Senior Researcher positions. We are particularly interested in candidates with very strong background in the general areas of Machine Learning and Probabilistic Artificial Intelligence. Intel Research - Berkeley Lab represents a bold new form of partnership between industry and academia, with very close ties to UC Berkeley. Our mission is to conduct the highest quality research in emerging, vital areas of Computer Science and Information Technology. Current projects in the Lab focus on extreme networked systems -- the very large, the very small, and the very numerous -- from sensor nets to Internet-scale systems. This is a very open and exciting application area for machine learning and AI, as such systems provide large amounts of real-world data, and can be leveraged by effective learning, inference and decision making methods. Although previous experience with such systems and data is not required, the candidate is expected to explore potential collaborations in the area. A successful candidate should possess a very strong research record in the areas of Machine Learning or Probabilistic AI, and be open to collaborative projects with Intel Researchers, and with UC Berkeley faculty and students. Several researchers at the Lab also have appointments at UC Berkeley. Depending on the candidate's qualifications and experience, and on campus priorities, similar joint assignments are possible. A Ph.D. in Computer Science, Electrical Engineering, Statistics, or related fields is required. Positions are currently open for permanent and short-term appointments. Internship opportunities are also available. For immediate consideration, please email your resume or curriculum vita, a research statement, and the names and addresses of three or more individuals who will provide letters of recommendation to Carlos Guestrin, guestrin at intel-research.net, with CC to Brenda Mainland, brenda.k.mainland at intel.com. For more information, please visit: http://www.intel-research.net/berkeley/ From z.li at ucl.ac.uk Mon Jan 26 12:05:16 2004 From: z.li at ucl.ac.uk (Zhaoping Li) Date: Mon, 26 Jan 2004 17:05:16 +0000 Subject: postdoc in vision/neuroscience in University College London Message-ID: <5.2.0.9.1.20040126170308.00aab2a0@pop-server.ucl.ac.uk> Research Fellow Applications are invited for the post of Postdoctoral Research Fellow to work with Dr. Li Zhaoping (http://www.gatsby.ucl.ac.uk/~zhaoping) in the area of neuroscience, particularly on biological vision, using theoretical and/or psychophysical investigation tools. The candidate should have good experience in theoretical/modelling area or in visual psychophysical area. Interest and capability to engage in research activities in both areas would be preferable although not essential. The research fellow is expected to contribute to the research environment of the laboratory and should have the capability to work well in a team. The post is available for two years and may be extended. Salary is on the RA1A scale (?23,259-29,473 including London allowance) and will depend upon qualifications and experience. We particularly welcome women and black and ethnic minority applicants as they are under represented at this level within University College London (s.48 of the SDA 1975/s.38 of the RRA 1976 apply). Applications (e-mail or hard copy) by covering letter, CV and Personal Information form (the latter available at: http://www.psychol.ucl.ac.uk/info/Personal_Information.doc) to John Draper, Departmental Administrator, Department of Psychology, UCL, Gower Street, London WC1E 6BT, UK, j.draper at ucl.ac.uk. If applying by e-mail please submit all requested information in one .pdf file named by your surname eg Smith.pdf. Further information concerning the post are on the web at: http://www.psychol.ucl.ac.uk/info/psychophysics_li.htm while interested candidates can also contact Li Zhaoping, z.li at ucl.ac.uk, 44 20 7679 1174. From ebaum at fastmail.fm Mon Jan 26 16:16:47 2004 From: ebaum at fastmail.fm (Eric Baum) Date: Mon, 26 Jan 2004 16:16:47 -0500 Subject: What is Thought?: Book announcement Message-ID: <16405.33727.124560.364578@localhost.localdomain> New Book: What is Thought? Eric B. Baum MIT Press 478p Best price right now is at Barnesandnoble.com (BN.com) $32, with free shipping. To buy this book: Barnes and Noble.com: http://search.barnesandnoble.com/booksearch/isbnInquiry.asp?userid=2WI405VPJU&isbn=0262025485&itm=17 Amazon: http://www.amazon.com/exec/obidos/tg/detail/-/0262025485/qid=1074532277/sr=1-3/ref=sr_1_3/002-6265544-0286451?v=glance&s=books MIT Press: http://mitpress.mit.edu/catalog/item/default.asp?sid=AF8A6531-E5E9-4710-A781-CA47C6B64621&ttype=2&tid=9978 This reports on a 10+ year project to see whether what I viewed as the worldview of the connectionist/COLT community could extend in any plausible way to explain all the capabilities of mind. I found such an extension, but only after being constrained into conjectures that are at odds with what I would have expected. *What is Thought?* proposes a model that explains how mind is equivalent to execution of a computer program, addressing aspects such as understanding, meaning, creativity, language, reasoning, learning, and consciousness, that is consistent with extensive data from a variety of fields, and that makes empirical predictions. Meaning is the computational exploitation of the compact underlying structure of the world, and mind is execution of an evolved program that is all about meaning. Occam's Razor, as formalized in the recent computer science literature, is explained and extrapolated to argue that meaning results from finding a compact enough program behaving effectively in the world; such a program can only be compact by virtue of code reuse, factoring into interacting modules that capture real concepts and are reused metaphorically. For a variety of reasons, including arguments based on complexity theory, developmental biology, evolutionary programming, ethology, and simple inspection, this compact Occam program is most naturally seen to be in the DNA, rather than the brain. Learning and reasoning are then fast and almost automatic because they are constrained by the DNA programming to deal only with meaningful quantities. Evolution itself is argued to exploit meaning in related ways. Words are labels for meaningful computational modules. Using the abilility to pass along programs through speech, humans have made cumulative progress in constructing, as part of their minds, useful computational modules built on top of the ones supplied by evolution. The difference between human and chimp intelligence is largely in this additional programming, and thus can be regarded as due to better nurturing. Human written computer programs, however, are generally not highly compressed and thus don't display understanding in the same way as human thought, but experiments are described in which modular computer programs were evolved that achieve abilities giving insight into how programs can evolve understanding. The many aspects of consciousness are also naturally and consistently understood in this context. For example, although the brain is a distributed system and the mind is a complex program composed of many modules, the unitary self emerges naturally as a reification (manifestation) of the interest of the genes. Qualia (the sense of experience of sensations such as pain or redness) have exactly the appropriate nature and meaning that evolution coded in the DNA so that the compact program behaves effectively. No previous familiarity with computer science (or other fields) is assumed-- *What is Thought?* presents a pedagogical survey of the relevant background for its arguments. --------------------------------------- From baolshausen at ucdavis.edu Sat Jan 31 20:06:14 2004 From: baolshausen at ucdavis.edu (Bruno Olshausen) Date: Sat, 31 Jan 2004 17:06:14 -0800 Subject: Sensory Coding and the Natural Environment Message-ID: <401C5106.FCCF9416@ucdavis.edu> Gordon Research Conference: --------------------------- "Sensory coding and the natural environment" September 5-10, 2004 The Queen's College, Oxford, UK Bruno Olshausen, Chair Jack Gallant & Mike Lewicki, Vice-chairs This conference will bring together researchers from diverse disciplines to discuss the statistical structure of natural scenes, and how nervous systems exploit these statistics to form useful representations of the environment. Topics include sensory neurophysiology, perceptual psychology, and the mathematics of signal statistics, applied to a variety of sensory modalities and organisms. A list of speakers as well as instructions on how to apply are available at http://www.grc.org/programs/2004/senscod.htm Applications will be reviewed in April, at which point accepted applicants may register. All participants will have the opportunity to present their work in poster sessions. We hope to have funds available to subsize fees and travel for students and postdocs. -- Bruno A. Olshausen (530) 757-8749 Center for Neuroscience (530) 757-8827 (fax) UC Davis baolshausen at ucdavis.edu 1544 Newton Ct. http://redwood.ucdavis.edu/bruno Davis, CA 95616 & Redwood Neuroscience Institute (650) 321-8282 x233 1010 El Camino Real, suite 380 (650) 321-8585 (fax) Menlo Park, CA 94025 http://www.rni.org From lendasse at james.hut.fi Thu Jan 29 11:26:31 2004 From: lendasse at james.hut.fi (Amaury Lendasse) Date: Thu, 29 Jan 2004 18:26:31 +0200 Subject: TIME SERIES PREDICTION COMPETITION Message-ID: <20040129162712.7021A2838D60@james.hut.fi> Please post and circulate as you see fit. Thank you. 2004 International Joint Conference on Neural Networks Special session organized in collaboration with the European Neural Network Society, the Machine Learning Group of the Universite catholique de Louvain in Belgium and the Neural Networks Research Center of the Helsinki University of Technology TIME SERIES PREDICTION COMPETITION http://www.cis.hut.fi/~lendasse/competition/competition.html The CATS Benchmark The goal of this competition is to provide a new benchmark for the problem of time series prediction and to compare the different methods or models that can be used for the prediction. The proposed time series is the CATS benchmark (for Competition on Artificial Time Series). This artificial Time Series with 5,000 data is given. Within those 100 values are missing. These missing values are divided in 5 blocks: - elements 981 to 1,000; - elements 1,981 to 2,000; - elements 2,981 to 3,000; - elements 3,981 to 4,000; - elements 4,981 to 5,000; These 100 missing values have to be predicted. The Mean Square Error E will be computed on the 100 missing values. The authors are requested to provide their prediction for the 100 missing values. The submitted methods will be ranked using this Mean Square Error E. The best papers (according to the quality of the prediction and the quality of the paper itself) will be selected for the special session that will be held during IJCNN 2004. Furthermore, a limited number of those papers will be published in a special issue of an International Scientific Journal. The competition starts on February, 1st 2004 and the deadline for the submission is March, 7th 2004. Special session organised by Amaury Lendasse, Michel Verleysen, Erkki Oja and Olli Simula. Dr. Amaury Lendasse Helsinki University of Technology Laboratory of Computer and Information Science P.O. Box 5400 FIN-02015 HUT FINLAND tel. +358-9-451 4499 fax +358-9-451 3277 Email: lendasse at cis.hut.fi URL: http://www.cis.hut.fi/~lendasse