From gjm at maths.uq.edu.au Sun Dec 3 22:14:32 2000 From: gjm at maths.uq.edu.au (Geoff McLachlan) Date: Mon, 4 Dec 2000 13:14:32 +1000 (EST) Subject: New Wiley book on Mixture Models Message-ID: <200012040314.NAA19161@fisher.maths.uq.edu.au> Announcing the recent publication of the Wiley monograph ... Title: FINITE MIXTURE MODELS Authors: Geoff McLachlan and David Peel This book gives an up-to-date, comprehensive account of the major issues in modeling via finite mixture distributions. Links statistical literature with the machine learning and pattern recognition literature in the related areas. Considers how the EM algorithm can be scaled to handle the fitting of mixture models to very large databases, as in data mining applications. Provides more than 800 references -- 40% published since 1995. FOR MORE INFORMATION SEE http://www.maths.uq.edu.au/~gjm From tgd at cs.orst.edu Sun Dec 3 23:01:06 2000 From: tgd at cs.orst.edu (Thomas G. Dietterich) Date: Sun, 3 Dec 2000 20:01:06 -0800 Subject: JAIR: MAXQ Hierarchical Reinforcement Learning Message-ID: <3556-Sun03Dec2000200106-0800-tgd@cs.orst.edu> JAIR is pleased to announce the publication of the following article: Dietterich, T.G. (2000) "Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition", Volume 13, pages 227-303. Available in PDF, PostScript and compressed PostScript. For quick access via your WWW browser, use this URL: http://www.jair.org/abstracts/dietterich00a.html More detailed instructions are below. Abstract: This paper presents a new approach to hierarchical reinforcement learning based on decomposing the target Markov decision process (MDP) into a hierarchy of smaller MDPs and decomposing the value function of the target MDP into an additive combination of the value functions of the smaller MDPs. The decomposition, known as the MAXQ decomposition, has both a procedural semantics---as a subroutine hierarchy---and a declarative semantics---as a representation of the value function of a hierarchical policy. MAXQ unifies and extends previous work on hierarchical reinforcement learning by Singh, Kaelbling, and Dayan and Hinton. It is based on the assumption that the programmer can identify useful subgoals and define subtasks that achieve these subgoals. By defining such subgoals, the programmer constrains the set of policies that need to be considered during reinforcement learning. The MAXQ value function decomposition can represent the value function of any policy that is consistent with the given hierarchy. The decomposition also creates opportunities to exploit state abstractions, so that individual MDPs within the hierarchy can ignore large parts of the state space. This is important for the practical application of the method. This paper defines the MAXQ hierarchy, proves formal results on its representational power, and establishes five conditions for the safe use of state abstractions. The paper presents an online model-free learning algorithm, MAXQ-Q, and proves that it converges with probability 1 to a kind of locally-optimal policy known as a recursively optimal policy, even in the presence of the five kinds of state abstraction. The paper evaluates the MAXQ representation and MAXQ-Q through a series of experiments in three domains and shows experimentally that MAXQ-Q (with state abstractions) converges to a recursively optimal policy much faster than flat Q learning. The fact that MAXQ learns a representation of the value function has an important benefit: it makes it possible to compute and execute an improved, non-hierarchical policy via a procedure similar to the policy improvement step of policy iteration. The paper demonstrates the effectiveness of this non-hierarchical execution experimentally. Finally, the paper concludes with a comparison to related work and a discussion of the design tradeoffs in hierarchical reinforcement learning. The article is available via: -- comp.ai.jair.papers (also see comp.ai.jair.announce) -- World Wide Web: The URL for our World Wide Web server is http://www.jair.org/ For direct access to this article and related files try: http://www.jair.org/abstracts/dietterich00a.html -- Anonymous FTP from either of the two sites below. Carnegie-Mellon University (USA): ftp://ftp.cs.cmu.edu/project/jair/volume13/dietterich00a.ps The University of Genoa (Italy): ftp://ftp.mrg.dist.unige.it/pub/jair/pub/volume13/dietterich00a.ps The compressed PostScript file is named dietterich00a.ps.Z (464K) For more information about JAIR, visit our WWW or FTP sites, or contact jair-ed at isi.edu From robtag at unisa.it Mon Dec 4 05:44:35 2000 From: robtag at unisa.it (Roberto Tagliaferri) Date: Mon, 04 Dec 2000 11:44:35 +0100 Subject: Call for papers WIRN 2001 Message-ID: <3A2B7593.A08CB19C@dia.unisa.it> The 12-th Italian Workshop on Neural Nets WIRN VIETRI-2001 May 17-19, 2001,Vietri Sul Mare, Salerno ITALY CALL FOR PAPERS - FIRST ANNOUNCEMENT Organizing - Scientific Committee B. Apolloni (Univ. Milano), A. Bertoni (Univ. Milano), N. A. Borghese (CNR Milano), D. D. Caviglia (Univ. Genova), P. Campadelli (Univ. Milano), A. Chella (Univ. Palermo), A. Colla (ELSAG Genova), A. Esposito (I.I.A.S.S.), M. Frixione (Univ. Salerno), C. Furlanello (ITC-IRST Trento), G. M. Guazzo (I.I.A.S.S.), M. Gori (Univ. Siena), F. Lauria (Univ. Napoli), M. Marinaro (Univ. Salerno), F. Masulli (Univ. Genova), C. Morabito (Univ. Reggio Calabria), P. Morasso (Univ. Genova), G. Orlandi (Univ. Roma), T. Parisini (Politecnico Milano), E. Pasero (Politecnico Torino), A. Petrosino (I.I.A.S.S.), V. Piuri (Politecnico Milano), R. Serra (CRA Montecatini Ravenna), F. Sorbello (Univ. Palermo), R. Tagliaferri (Univ. Salerno) Topics Mathematical Models, Architectures and Algorithms, Hardware and Software Design, Hybrid Systems, Pattern Recognition and Signal Processing, Industrial and Commercial Applications, Fuzzy Tecniques for Neural Networks Schedule Papers Due: January 31, 2001 Replies to Authors: March 31, 2001 Revised Papers Due: May 19, 2001 Sponsors International Institute for Advanced Scientific Studies (IIASS) "E.R. Caianiello") Dept. of Scienze Fisiche "E.R. Caianiello", University of Salerno Dept. of Matematica ed Informatica, University of Salerno Dept. of Scienze dell'Informazione, University of Milano Societa' Italiana Reti Neuroniche (SIREN) IEEE Neural Network Council INNS/SIG Italy Istituto Italiano per gli Studi Filosofici, Napoli The three-day conference, to be held in the I.I.A.S.S., will feature both introductory tutorials and original, refereed papers, to be published by an International Publishing. Official languages are Italian and English, while papers must be in English. Papers should be 6 pages, including title, figures, tables, and bibliography. The accompanying letter should give keywords, postal and electronic mailing addresses, telephone and FAX numbers, indicating oral or poster presentation. Submit 3 copies and a 1 page abstract (containing keywords, postal and electronic mailing addresses, telephone, and FAX numbers with no more than 300 words) to the address shown (WIRN 2001 c/o IIASS). An electronic copy of the abstract should be sent to the E-mail address below. During the Workshop the "Premio E.R. Caianiello" will be assigned to the best Ph.D. thesis in the area of Neural Nets and related fields of Italian researchers. The amount is of 2.000.000 Italian Lire. The interested researchers (with the Ph.D degree got in 1998,1999,2000 until February 28 2001) must send 3 copies of a c.v. and of the thesis to "Premio Caianiello" WIRN 2001 c/o IIASS before February 28,2001. It is possible to partecipate to the prize at most twice and the association to SIREN is required (modules can be downloaded from the SIREN site). For more information, contact the Secretary of I.I.A.S.S. "E.R. Caianiello", Via G.Pellegrino, 19, 84019 Vietri Sul Mare (SA), ITALY Tel. +39 89 761167 Fax +39 89 761189 E-Mail robtag at unisa.it or the SIREN www pages at: http://www-dsi.ing.unifi.it/neural -------------- next part -------------- A non-text attachment was scrubbed... Name: robtag.vcf Type: text/x-vcard Size: 245 bytes Desc: Card for Roberto Tagliaferri Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/00000000/735b491f/robtag.vcf From Sebastian_Thrun at heaven.learning.cs.cmu.edu Mon Dec 4 08:25:40 2000 From: Sebastian_Thrun at heaven.learning.cs.cmu.edu (Sebastian Thrun) Date: Mon, 04 Dec 2000 08:25:40 -0500 Subject: Faculty Opportunities at CMU Message-ID: The School of Computer Science at Carnegie Mellon University is seeking applications for tenure track positions in all areas related to data and text mining, statistics, and machine learning. We are looking for candidates with excellent research and teaching records and a strong commitment to cross-disciplinary research. Other areas of interest to the School include algorithms, computer graphics, computer systems, human computer interaction, robotics, and software engineering. The starting date can be as early as July 1, 2001. Priority will be given to applications received before February 15, 2001. To apply please send a C.V., statement of research and teaching interests, copies of 1-3 representative papers, and the names of at least three references to: Faculty Search Committee ATTENTION: Sharon Burks School of Computer Science Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA 15213-3891 The applicant should request their references to forward a letter of reference directly to the same address to arrive before February 15, 2001. These letters will NOT be requested directly by the department. Electronic applications and reference letters (in postscript or .pdf format) may be directed to: faculty-search at cs.cmu.edu Carnegie Mellon is an affirmative action/equal opportunity employer, who encourages applications from women and minorities. More information can be found at at http://www.cs.cmu.edu/afs/cs/usr/burks/www/facultysearch.html From cindy at cns.bu.edu Mon Dec 4 15:17:13 2000 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Mon, 4 Dec 2000 15:17:13 -0500 Subject: Neural Networks 13(8/9) Message-ID: <200012042017.PAA12870@retina.bu.edu> NEURAL NETWORKS 13(8/9) Special Issue on "The Global Brain: Imaging and Neural Modelling" Contents - Volume 13, Numbers 8/9 - 2000 ------------------------------------------------------------------ Editorial J.G. Taylor Neural modeling and functional brain imaging: An overview B. Horwitz, K.J. Friston, and J.G. Taylor Imaging and neural modelling in episodic and working memory processes B.J. Krause, J.G. Taylor, D. Schmidt, H. Hautzel, F.M. Mottaghy, and H.-W. Mueller-Gaertner Towards a network theory of cognition A.R. McIntosh Assessing interactions among neuronal systems using functional neuroimaging C. Buchel and K. Friston Tracking functions of cortical networks on a millisecond timescale V. Jousmaki Independence: A new criterion for the analysis of the electromagnetic fields in the global brain? R. Vigario and E. Oja Connectivity and complexity: The relationship between neuroanatomy and brain dynamics O. Sporns, G. Tononi, and G.M. Edelman Decomposing memory: Functional assignments and brain traffic in paired word associate learning J.G. Taylor, B. Horwitz, N.J. Shah, W.A. Fellenz, H.-W. Mueller-Gaertner, and J.B. Krause A model of working memory: Bridging the gap between electrophysiology and human brain imaging M.-A. Tagamets and B. Horwitz A neural model of working memory processes in normal subjects, Parkinson's disease, and schizophrenia for fMRI design and predictions O. Monchi, J.G. Taylor, and A. Dagher Synthetic brain imaging: Grasping, mirror neurons, and imitation M.A. Arbib, A. Billard, M. Iacoboni, and E. Oztop A neural model of cortico-cerebellar interactions during attentive imitation and predictive learning of sequential handwriting movements S. Grossberg and R.W. Paine Towards a neural network based therapy for hallucinatory disorders J.R. Pelaez ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 or 660 SEK or Y 15,000 [including Neural Networks 2,000 entrance fee] or $55 (student) 460 SEK (student) Y 13,000 (student) [including 2,000 entrance fee] ----------------------------------------------------------------------------- membership without $30 200 SEK not available to Neural Networks non-students (subscribe through another society) Y 5,000 (student) [including 2,000 entrance fee] ----------------------------------------------------------------------------- Institutional rates $1132 2230 NLG Y 149,524 ----------------------------------------------------------------------------- Name: _____________________________________ Title: _____________________________________ Address: _____________________________________ _____________________________________ _____________________________________ Phone: _____________________________________ Fax: _____________________________________ Email: _____________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number ____________________________ expiration date ________________________ INNS Membership 19 Mantua Road Mount Royal NJ 08061 USA 856 423 0162 (phone) 856 423 3420 (fax) innshq at talley.com http://www.inns.org ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership c/o Professor Tsukada Faculty of Engineering Tamagawa University 6-1-1, Tamagawa Gakuen, Machida-city Tokyo 113-8656 Japan 81 42 739 8431 (phone) 81 42 739 8858 (fax) jnns at jnns.inf.eng.tamagawa.ac.jp http://jnns.inf.eng.tamagawa.ac.jp/home-j.html ----------------------------------------------------------------- From maasen at mpipf-muenchen.mpg.de Mon Dec 4 10:53:51 2000 From: maasen at mpipf-muenchen.mpg.de (Sabine Maasen) Date: Mon, 4 Dec 2000 16:53:51 +0100 Subject: Job Announcement MPI for Psychological Research Message-ID: THE MAX PLANCK INSTITUTE FOR PSYCHOLOGICAL RESEARCH, MUNICH, GERMANY invites applications for the following positions in the newly established Junior Research Group "Cognitive Robotics": 1 postdoctoral researcher (5-year appointment, salary appr. DEM 71k p.a.) 2 doctoral students (3-year appointment, salary appr. DEM 71k or DEM 35k p.a.) The group will study novel, behavior-based approaches to visual perpection, specifically approaches to functional categorization based on anticipation of the sensory consequences of actions. Artificial neural network techniques will be used for learning sensorimotor associations during the interaction with the environment. Models will be implemented on mobile robots and robot arms and tested in the real world. Candidates should have a background in cognitive science, computational vision, neural network theory, and robotics, as well as strong technical and computer skills. Earliest starting date for all positions is January 1, 2001. Applications are accepted until the positions are filled. The Max Planck Institute is an equal-opportunity employer and especially encourages women to apply. Please send full CV, complete academic records, statement of interests, and the names and email addresses of two academic referees to: Administration Max Planck Institute for Psychological Research Amalienstr. 33, D-80799 Munich, Germany web site: http://www.mpipf-muenchen.mpg.de For further information, please contact: Dr. Ralf Moeller, email: moeller at mpipf-muenchen.mpg.de -- ------------------------------------------------- Dr. Sabine Maasen ++ Forschungsreferentin / research coordinator ++ Max-Planck-Institut fuer psychologische Forschung Amalienstr.33 +++ 80799 Muenchen Tel +49 89 38602-251 +++ Fax -290 email: maasen at mpipf-muenchen.mpg.de homepage:http://www.mpipf-muenchen.mpg.de/~maasen ------------------------------------------------- From tim.sibley at streamsage.com Mon Dec 4 13:28:18 2000 From: tim.sibley at streamsage.com (Tim V. Sibley) Date: Mon, 04 Dec 2000 13:28:18 -0500 Subject: Research position in spoken language modeling at StreamSage Message-ID: <200012041848.eB4Imls99359@ren-5.cais.net> RESEARCH POSITION AVAILABLE StreamSage, Inc. Speech Interpretation Laboratory _____ A lead research position is available immediately (starting date flexible) in the speech interpretation laboratory at StreamSage. Research focuses on time-based modeling of spoken language for the purpose of automated digital media manipulation via intelligent, adaptive algorithms, neural networks, and rule-based frameworks. The candidate should have a strong background in neural networks and computational linguistics. A sufficiently independent spirit is necessary for use within a young startup that develops state-of-the-art technology. Familiarity with Java is a plus. Proficient knowledge of the English language is required. Compensation will be commensurate with level of experience. Please send resume, 2 recommendations, and representative publications to the address listed below, or inquire with any questions or comments. E-mail inquiries and applications are encouraged. _____ Tim V. Sibley tim.sibley at streamsage.com StreamSage, Inc. 1900 M St. NW Suite 810 Washington, DC 20036 phone: 202.833.8050 fax: 360.838.7203 From kap-listman at wkap.nl Tue Dec 5 20:17:25 2000 From: kap-listman at wkap.nl (kap-listman@wkap.nl) Date: Wed, 06 Dec 2000 02:17:25 +0100 (MET) Subject: New Issue: Neural Processing Letters. Vol. 12, Issue 3 Message-ID: <200012060117.CAA22275@wkap.nl> Kluwer ALERT, the free notification service from Kluwer Academic/PLENUM Publishers and Kluwer Law International ------------------------------------------------------------ Neural Processing Letters ISSN 1370-4621 http://www.wkap.nl/issuetoc.htm/1370-4621+12+3+2000 Vol. 12, Issue 3, December 2000. TITLE: Self-Organization by Temporal Inhibition (SOTI) AUTHOR(S): P. Martin-Smith, F. J. Pelayo, E. Ros, A. Prieto KEYWORD(S): temporal inhibition, competitive learning, self-organizing maps, learning vector quantization. PAGE(S): 199-213 TITLE: Parametric Amplification of Signals by Noise in Neurons and Neural Networks AUTHOR(S): Yu. I. Balkarey, V. O. Nagoutchev, M. G. Evtikhov, M. I. Elinson KEYWORD(S): amplification of signals in neural networks (NN), positive role of parametric noise in NN, spike trains and noise. PAGE(S): 215-223 TITLE: Using a Neural Network to Approximate an Ensemble of Classifiers AUTHOR(S): X. Zeng, T. R. Martinez KEYWORD(S): approximator, bagging, boosting, ensemble of classifiers, neural networks. PAGE(S): 225-237 TITLE: An Analysis of the Fundamental Structure of Complex-Valued Neurons AUTHOR(S): Tohru Nitta KEYWORD(S): complex numbers, complex-valued neurons, learning, decision boundary. PAGE(S): 239-246 TITLE: On the Internal Representations of Product Units AUTHOR(S): Jung-Hua Wang, Yi-Wei Yu, Jia-Horng Tsai KEYWORD(S): product unit, internal representations, recurrent neural networks, perceptrons, backpropagation training. PAGE(S): 247-254 TITLE: A Direct Link Minimal Resource Allocation Network for Adaptive Noise Cancellation AUTHOR(S): Sun Yonghong, P. Saratchandran, N. Sundararajan KEYWORD(S): direct link MRAN, extended Kalman filter, noise cancellation, RBF network, sequential learning. PAGE(S): 255-265 TITLE: A Neural Chaos Model of Multistable Perception AUTHOR(S): Natsuki Nagao, Haruhiko Nishimura, Nobuyuki Matsui KEYWORD(S): perceptual alternation, ambiguous figure, chaos, neural network, stimulus-response. PAGE(S): 267-276 TITLE: Bayesian Sampling and Ensemble Learning in Generative Topographic Mapping AUTHOR(S): Akio Utsugi KEYWORD(S): elastic net, evidence, Gibbs sampler, hyperparameter search, Laplace method, Markov chain Monte Carlo, self-organizing map, variational free energy. PAGE(S): 277-290 TITLE: Nonlinear System Identification Using Lyapunov Based Fully Tuned Dynamic RBF Networks AUTHOR(S): Li Yan, N. Sundararajan, P. Saratchandran KEYWORD(S): Growing and Pruning (GAP), Lyapunov stability theory, neural network, nonlinear dynamic system, Radial Basis Function (RBF) network, stable identification. PAGE(S): 291-303 TITLE: Author Index, Volume 12, 2000 AUTHOR(S): PAGE(S): 305-305 TITLE: Contents, Volume 12, 2000 AUTHOR(S): PAGE(S): 307-308 -------------------------------------------------------------- Thank you for your interest in Kluwer's books and journals. NORTH, CENTRAL AND SOUTH AMERICA Kluwer Academic Publishers Order Department, PO Box 358 Accord Station, Hingham, MA 02018-0358 USA Telephone (781) 871-6600 Fax (781) 681-9045 E-Mail: kluwer at wkap.com Kluwer Law International Order Department 675 Massachusetts Avenue Cambridge, MA 02139 USA Telephone: (617) 354-0140 Toll-free (US customers only): 800 577-8118 Fax: (617) 354-8595 E-mail: sales at kluwerlaw.com EUROPE, ASIA AND AFRICA Kluwer Academic Publishers Distribution Center PO Box 322 3300 AH Dordrecht The Netherlands Telephone 31-78-6392392 Fax 31-78-6546474 E-Mail: orderdept at wkap.nl From sylee at ee.kaist.ac.kr Wed Dec 6 04:59:26 2000 From: sylee at ee.kaist.ac.kr (Soo-Young Lee) Date: Wed, 6 Dec 2000 18:59:26 +0900 Subject: Neurocomputing Special Issue on ICA/BSS Message-ID: <00c301c05f6b$37f36010$0100a8c0@kaistsylee2> Neurocomputing (Elsevier; http://www.elsevier.nl/locate/neucom) Special Issue on Blind Signal Separation and Independent Component Analysis Paper Submission Deadline: March 1st, 2001 The Neurocomputing Journal plans a special issue on Blind Signal Separation and Independent Component Analysis, and papers are solicited until March 1st, 2001. Recently, blind signal separation (BSS) and independent component analysis (ICA) have received a lot of attention from the neural networks and signal processing communities. Based on probability and information theories, several unsupervised learning algorithms have been developed to separate mixed signals and extract their independent components. Several important applications have also emerged for speech enhancement, efficient coding of natural scenes and sounds, telecommunications, and medical signal processing. It is therefore worthwhile to organize a special issue on these important topics. From arthur at mail4.ai.univie.ac.at Wed Dec 6 12:05:29 2000 From: arthur at mail4.ai.univie.ac.at (Arthur Flexer) Date: Wed, 6 Dec 2000 18:05:29 +0100 (MET) Subject: Three papers on analysis of EEG Message-ID: <200012061705.SAA17795@korb.ai.univie.ac.at> Dear all, the following three recent papers dealing with the analysis of EEG can be downloaded from my web-site. Comments are of course welcome, all the best, Arthur. ----------------------------------------------------------------------------- Arthur Flexer arthur at ai.univie.ac.at http://www.ai.univie.ac.at/~arthur/ Austrian Research Inst. for Artificial Intelligence +43-1-5336112 (Tel) Schottengasse 3, A-1010 Vienna, Austria +43-1-5336112-77 (Fax) ----------------------------------------------------------------------------- Flexer A..: Data mining and electroencephalography, Statistical Methods in Medical Research, 9: 395-413, 2000. also available as: TR-2000-12. ftp://ftp.ai.univie.ac.at/papers/oefai-tr-2000-12.ps.gz An overview of Data Mining (DM) and its application to the analysis of EEG is given by (i) presenting a working definition of DM, (ii) motivating why EEG analysis is a challenging field of application for DM technology and (iii) by reviewing exemplary work on DM applied to EEG analysis. The current status of work on DM and EEG is discussed and some general conclusions are drawn. ----------------------------------------------------------------------------- Flexer A., Sykacek P., Rezek I., Dorffner G.: Using Hidden Markov Models to build an automatic, continuous and probabilistic sleep stager, in Amari S.-I., et al.(eds.), Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, IJCNN 2000, Como, Italy, IEEE Computer Society, Vol. III, 627-631, 2000. also available as: TR-99-21. ftp://ftp.ai.univie.ac.at/papers/oefai-tr-99-21.ps.gz We report about an automatic continuous sleep stager which is based on probabilistic principles employing Hidden Markov Models (HMM). Our sleep stager offers the advantage of being objective by not relying on human scorers, having much finer temporal resolution (1 second instead of 30 second), and being based on solid probabilistic principles rather than a predefined set of rules (Rechtschaffen & Kales). Results obtained for nine whole night sleep recordings are reported. ----------------------------------------------------------------------------- Flexer A., Bauer H.: Monitoring human information processing via intelligent data analysis of EEG recordings, Intelligent Data Analysis, 4: 113-128, 2000. also available as: TR-2000-34. ftp://ftp.ai.univie.ac.at/papers/oefai-tr-2000-34.ps.gz Human information processing can be monitored by analysing cognitive evoked potentials (EP) measurable in the electro encephalogram (EEG) during cognitive activities. In technical terms, both visualization of high dimensional sequential data and unsupervised discovery of patterns within this multivariate set of real valued time series is needed. Our approach towards visualization is to discretize the sequences via vector quantization and to perform a Sammon mapping of the codebook. Instead of having to conduct a time-consuming search for common subsequences in the set of multivariate sequential data, a multiple sequence alignment procedure can be applied to the set of one-dimensional discrete time series. The methods are described in detail and results obtained for spatial and verbal information processing are shown to be statistically valid, to yield an improvement in terms of noise attenuation and to be well in line with psychophysiological literature. ----------------------------------------------------------------------------- From Alain.Destexhe at iaf.cnrs-gif.fr Wed Dec 6 12:58:35 2000 From: Alain.Destexhe at iaf.cnrs-gif.fr (Alain Destexhe) Date: Wed, 06 Dec 2000 18:58:35 +0100 Subject: postdoc position in computational neuroscience Message-ID: <3A2E7E4B.15FB7483@iaf.cnrs-gif.fr> --------------------------------------------------------------------- Postdoc position available - January 1st, 2001 --------------------------------------------------------------------- A postdoc position is available for a computational study of neocortical pyramidal neurons in vivo. This project will be conducted in collaboration between two laboratories, A. Destexhe (CNRS, Gif-sur-Yvette) for the computational part, and D. Pare (Laval University, Quebec) for the experimental part. A collaboration with Y. Fregnac (CNRS, Gif-sur-Yvette) is also possible. The candidate will have access to intracellular data from neocortical neurons in vivo, obtained in the aforementioned labs. The project will consist, in a first phase, of evaluating the impact of the intense synaptic activity in vivo on dendritic integration in neocortical pyramidal cells. The morphology of intracellularly-recorded neurons will be reconstructed using a Neurolucida system and incorporated in the NEURON simulator (http://www.neuron.yale.edu), to design biophysical models that will be matched precisely to the intracellular recordings. Because models and experimental data correspond to the same cellular morphologies, we expect that this method will allow us to characterize various aspects of synaptic activity in vivo, and estimate its consequences on dendritic integration. In a second phase, these biophysical models will be simplified, in order to build large-scale networks based on the integrative properties estimated from in vivo measurements. --------------------------------------------------------------------- The CNRS facility of Gif-sur-Yvette is a campus entirely devoted to research and situated in the vicinity of Paris. The department (UPR CNRS 2191, Dir. Y. Fregnac) consists in an integrated and very interactive environment comprising in vivo electrophysiology (L. Borg-Graham, Y. Fregnac, M. Pananceau, D. Shulz), in vitro electrophysiology (T. Bal, K. Grant), comparative anatomy (J-P. Denizot), psychophysics (J. Lorenceau) and computational neuroscience (A. Destexhe). --------------------------------------------------------------------- The candidate should have a Doctoral degree, experience in neuroscience and computer programming, and ideally, a sufficient knowledge of electrophysiology. There is no restriction on nationality. --------------------------------------------------------------------- The salary will be paid by a grant from NIH, which will available on January 1st, 2001, for a period of 2 years. --------------------------------------------------------------------- Candidates should contact Alain Destexhe for more details, or consult the site http://cns.iaf.cnrs-gif.fr --------------------------------------------------------------------- Alain Destexhe Unite de Neurosciences Integratives et Computationnelles, CNRS, Avenue de la Terrasse, 91198 Gif-sur-Yvette, France Tel: 33-1-69-82-34-35 Fax: 33-1-69-82-34-27 URL: http://cns.iaf.cnrs-gif.fr email: Destexhe at iaf.cnrs-gif.fr From geoff at giccs.georgetown.edu Wed Dec 6 17:43:29 2000 From: geoff at giccs.georgetown.edu (Geoff Goodhill) Date: Wed, 6 Dec 2000 17:43:29 -0500 Subject: Postdoc position available Message-ID: <200012062243.RAA19956@brecker.giccs.georgetown.edu> POSTDOCTORAL POSITION IN EXPERIMENTAL NEUROSCIENCE A postdoctoral position in now available to join a small team of physicists, biologists and computational neuroscientists investigating mechanisms of axon guidance in the developing nervous system. We are developing new experimental and theoretical tools to better quantitatively understand axonal chemotaxis, and are seeking a researcher to assist in developing and implementing a novel bioengineering technology for the generation of precisely controlled chemical gradients. In addition to creativity and independence, the successful applicant should possess experience in one or more of the following: image acquisition and processing, quantitative fluorescence imaging, computer automation, diffusion modeling, statistical analysis of complex systems. For more information see http://www.giccs.georgetown.edu/labs/cns/axon.html Send a CV and contact information for at least two referees, preferably be email, to Geoffrey J Goodhill, PhD Assistant Professor, Department of Neuroscience & Georgetown Institute for Cognitive and Computational Sciences Georgetown University Medical Center 3900 Reservoir Road NW, Washington DC 20007 Tel: (202) 687 6889, Fax: (202) 687 0617 Email: geoff at giccs.georgetown.edu Homepage: www.giccs.georgetown.edu/labs/cns From sml at essex.ac.uk Thu Dec 7 09:52:45 2000 From: sml at essex.ac.uk (Lucas, Simon M) Date: Thu, 7 Dec 2000 14:52:45 -0000 Subject: OCR Competition Winner Message-ID: <6A8CC2D6487ED411A39F00D0B7847B66E77F81@sernt14.essex.ac.uk> Dear All, I am pleased to announce that the OCR competition that I posted here a few weeks ago has now been won by Chih-Chung Chang and the SVM group of Department of Computer Science and Information Engineering of National Taiwan University. ( http://www.csie.ntu.edu.tw/~cjlin/group.html ) Congratulations! More details can be found at http://algoval.essex.ac.uk Best regards, Simon Lucas -------------------------------------------------- Dr. Simon Lucas Senior Lecturer and MSc E-commerce Director Department of Computer Science University of Essex Colchester CO4 3SQ United Kingdom Email: sml at essex.ac.uk http://cswww.essex.ac.uk -------------------------------------------------- From Peter.Bartlett at anu.edu.au Thu Dec 7 17:00:47 2000 From: Peter.Bartlett at anu.edu.au (Peter Bartlett) Date: Fri, 08 Dec 2000 09:00:47 +1100 Subject: neural network learning: theoretical foundations Message-ID: <3A30088F.EE3CD507@anu.edu.au> Hi all, Cambridge University Press is about to start a second printing of our book "Neural Network Learning: Theoretical Foundations." If you've spotted any errors/typos/out-of-date citations, please let us know. Thanks in advance for your help. -- Martin Anthony and Peter Bartlett. From terry at salk.edu Thu Dec 7 21:23:17 2000 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 7 Dec 2000 18:23:17 -0800 (PST) Subject: NEURAL COMPUTATION 12:11 Message-ID: <200012080223.eB82NHo08011@purkinje.salk.edu> Neural Computation - Contents - Volume 12, Number 11 - November 1, 2000 Article Dynamical Mechanism for Sharp Orientation Tuning in an Integrate-and-Fire Model of a Cortical Hypercolumn P.C. Bressloff, N. W. Bressloff, and J. D. Cowan Notes Statistical Signs of Common Inhibitory Feedback with Delay Quentin Pauluis On the Computational Power of Winner-Take-All Wolfgang Maass Reclassification as Supervised Clustering A. Sierra and F. Corbacho Letters A Model of Invariant Object Recognition in the Visual System: Learning Rules, Activation Functions, Lateral Inhibition and Information-Based Performance Measures Edmund T. Rolls and T. Milward An Analysis of Orientation and Ocular Dominance Patterns in the Visual Cortex of Cats and Ferrets T. Muller, M. Stetter, B. Chapman, K. Obermayer, M. Hubener, F. Sengpiel, T. Bonhoeffer, I. Godecke, S. Lowel Improvements to the Sensitivity of Gravitational Clustering for Multiple Neuron Recordings Stuart N. Baker and George L. Gerstein Neural Coding: Higher-Order Temporal Patterns in the Neurostatistics of Cell Assemblies Laura Martignon, Gustavo Deco, Kathryn Laskey, Mathew Diamond, Winrich A. Freiwald, and Eilon Vaadia Gaussian Processes for Classification: Mean Field Algorithms Manfred Opper and Ole Winther The Bayesian Evidence Scheme for Regularising Probability-Density Estimating Neural Networks Dirk Husmeier A Bayesian Committee Machine Volker Tresp ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2000 - VOLUME 12 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $88 $94.16 $136 Institution $430 $460.10 $478 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 258-6779 mitpress-orders at mit.edu ----- From ronitt at research.nj.nec.com Fri Dec 8 17:18:39 2000 From: ronitt at research.nj.nec.com (Ronitt Rubinfeld) Date: Fri, 8 Dec 2000 17:18:39 -0500 Subject: job opportunity at NECI Message-ID: <200012082218.RAA04273@localhost.localdomain> The NEC Research Institute (NECI) in Princeton, New Jersey, has immediate openings for outstanding researchers in Computer Science. Candidates are required to have a Ph.D. degree and are expected to establish a basic research program of international stature. We are seeking applicants in cryptography, theory, machine learning, bioinformatics, data mining and other systems relevant to web applications, but will consider exceptional applicants in other areas of Computer Science. NECI, founded eleven years ago, has as its mission basic research in Computer Science and Physical Sciences underlying future technologies relevant to NEC. The Institute has research programs in theory, machine learning, computer vision, computational linguistics, web characterization and applications, bioinformatics, as well as research activities in Physical Sciences. NECI offers unique and unusual opportunities to its scientists including, great freedom in deciding basic research directions and projects; budgets for research, travel, equipment, and support staff that are directly controlled by principal researchers; and publication of all research results in the open literature. The Institute's laboratories are state-of-the-art and include several high-end parallel compute servers. NECI has close ties with outstanding research universities in and outside the Princeton area and with NEC's Central Research Laboratory (CRL) in Japan. Collaborations with university and CRL research groups are encouraged. Full applications should include resumes, copies of selected publications, names of at least three references, and a two-page statement of proposed research directions. Applications will be reviewed beginning January 1, 2001. NECI is an equal opportunity employer. For more details about NECI, please see http://www.neci.nj.nec.com. Please send applications or inquiries to: CS Search Committee Chair NEC Research Institute 4 Independence Way Princeton, NJ 08540 email: compsci-candidates at research.nj.nec.com From cindy at cns.bu.edu Mon Dec 11 11:18:00 2000 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Mon, 11 Dec 2000 11:18:00 -0500 Subject: ICCNS'2001: invited speaker program and call for abstracts Message-ID: <200012111618.LAA25222@retina.bu.edu> Apologies if you receive this more than once. ***** FINAL INVITED SPEAKER PROGRAM AND CALL FOR ABSTRACTS ***** FIFTH INTERNATIONAL CONFERENCE ON COGNITIVE AND NEURAL SYSTEMS Tutorials: May 30, 2001; Meeting: May 31 - June 2, 2001 Boston University http://www.cns.bu.edu/meetings/ This interdisciplinary conference focuses on two fundamental questions: How Does the Brain Control Behavior? How Can Technology Emulate Biological Intelligence? A single oral or poster session enables all presented work to be highly visible. Contributed talks will be presented on each of the three conference days. Three-hour poster sessions with no conflicting events will be held on two of the conference days. All posters will be up all day, and can also be viewed during breaks in the talk schedule. CONFIRMED INVITED SPEAKERS TUTORIAL SPEAKERS: Wednesday, May 30, 2001 Ted Adelson: The perception of surface properties Yiannis Aloimonos: What geometry and statistics tell us about the motion pathway Gail A. Carpenter: Adaptive resonance theory Michael Jordan: Inference and learning in graphical models INVITED SPEAKERS Thursday, May 31, 2001 Larry Abbott: Spike-timing effects in Hebbian synaptic plasticity Wulfram Gerstner: Rapid signal transmission by populations of spiking neurons Wolfgang Maass: Towards a computational theory for spiking neurons Nancy Kopell: Rhythms and cell assemblies in the nervous system Henry Markram: Neuronal, synaptic, and network mechanisms of perception, attention, and memory Victor Lamme: The role of recurrent processing in visual awareness Wolf Singer: Neuronal synchrony in cerebral cortex and its functional implications (keynote lecture) Friday, June 1, 2001 Ralph D. Freeman: Organization of receptive fields of neurons in the primary visual cortex Nikos Logothetis: Functional magnetic resonance imaging of the monkey brain David J. Heeger: Linking visual perception with human brain activity Maggie Shiffrar: The visual analysis of moving bodies Stephen Grossberg: What and where fusion: Motion, number, and object recognition Allen Waxman: Multi-sensor image fusion technologies Saturday, June 2, 2001 Peter L. Strick: Basal ganglia and cerebellar "loops" with the cerebral cortex: Motor and cognitive circuits Richard Ivry: Timing, temporal coupling, and response selection Daniel Bullock: Action selection and reinforcement learning in a model of laminar frontal cortex and the basal ganglia Christoph Schreiner: Spectro-temporal receptive field transformation in auditory thalamo-cortical system Rochel Gelman: Continuity and discontinuity in cognitive development: Numerical cognition as a case Maja Mataric: From what you see to what you do: Imitation in humans and humanoid robots Leon Cooper: Bi-directionally modifiable synapses: From theoretical fantasy to experimental fact (keynote lecture) CALL FOR ABSTRACTS Session Topics: * vision * object recognition * image understanding * audition * speech and language * unsupervised learning * supervised learning * reinforcement and emotion * sensory-motor control * spatial mapping and navigation * neural circuit models * neural system models * mathematics of neural systems * robotics * hybrid systems (fuzzy, evolutionary, digital) * neuromorphic VLSI * industrial applications * cognition, planning, and attention * other Contributed abstracts must be received, in English, by January 31, 2001. Notification of acceptance will be provided by email by February 28, 2001. A meeting registration fee of $50 for regular attendees and $35 for students must accompany each Abstract. See Registration Information for details. The fee will be returned if the Abstract is not accepted for presentation and publication in the meeting proceedings. Registration fees of accepted abstracts will be returned on request only until April 20, 2001. Each Abstract should fit on one 8.5" x 11" white page with 1" margins on all sides, single-column format, single-spaced, Times Roman or similar font of 10 points or larger, printed on one side of the page only. Fax submissions will not be accepted. Abstract title, author name(s), affiliation(s), mailing, and email address(es) should begin each Abstract. An accompanying cover letter should include: Full title of Abstract; corresponding author and presenting author name, address, telephone, fax, and email address; and a first and second choice from among the topics above, including whether it is biological (B) or technological (T) work. Example: first choice: vision (T); second choice: neural system models (B). (Talks will be 15 minutes long. Posters will be up for a full day. Overhead, slide, and VCR facilities will be available for talks.) Abstracts which do not meet these requirements or which are submitted with insufficient funds will be returned. Accepted Abstracts will be printed in the conference proceedings volume. No longer paper will be required. The original and 3 copies of each Abstract should be sent to: Cynthia Bradford, Boston University, Department of Cognitive and Neural Systems, 677 Beacon Street, Boston, MA 02215. REGISTRATION INFORMATION: Early registration is recommended. To register, please fill out the registration form below. Student registrations must be accompanied by a letter of verification from a department chairperson or faculty/research advisor. If accompanied by an Abstract or if paying by check, mail to the address above. If paying by credit card, mail as above, or fax to (617) 353-7755, or email to cindy at cns.bu.edu. The registration fee will help to pay for a reception, 6 coffee breaks, and the meeting proceedings. STUDENT FELLOWSHIPS: Fellowships for PhD candidates and postdoctoral fellows are available to help cover meeting travel and living costs. The deadline to apply for fellowship support is January 31, 2001. Applicants will be notified by email by February 28, 2001. Each application should include the applicant's CV, including name; mailing address; email address; current student status; faculty or PhD research advisor's name, address, and email address; relevant courses and other educational data; and a list of research articles. A letter from the listed faculty or PhD advisor on official institutional stationery should accompany the application and summarize how the candidate may benefit from the meeting. Fellowship applicants who also submit an Abstract need to include the registration fee with their submission. Fellowship checks will be distributed after the meeting. REGISTRATION FORM Fifth International Conference on Cognitive and Neural Systems Department of Cognitive and Neural Systems Boston University 677 Beacon Street Boston, Massachusetts 02215 Tutorials: May 30, 2001 Meeting: May 31 - June 2, 2001 FAX: (617) 353-7755 http://www.cns.bu.edu/meetings/ (Please Type or Print) Mr/Ms/Dr/Prof: _____________________________________________________ Name: ______________________________________________________________ Affiliation: _______________________________________________________ Address: ___________________________________________________________ City, State, Postal Code: __________________________________________ Phone and Fax: _____________________________________________________ Email: _____________________________________________________________ The conference registration fee includes the meeting program, reception, two coffee breaks each day, and meeting proceedings. The tutorial registration fee includes tutorial notes and two coffee breaks. CHECK ONE: ( ) $75 Conference plus Tutorial (Regular) ( ) $50 Conference plus Tutorial (Student) ( ) $50 Conference Only (Regular) ( ) $35 Conference Only (Student) ( ) $25 Tutorial Only (Regular) ( ) $15 Tutorial Only (Student) METHOD OF PAYMENT (please fax or mail): [ ] Enclosed is a check made payable to "Boston University". Checks must be made payable in US dollars and issued by a US correspondent bank. Each registrant is responsible for any and all bank charges. [ ] I wish to pay my fees by credit card (MasterCard, Visa, or Discover Card only). Name as it appears on the card: _____________________________________ Type of card: _______________________________________________________ Account number: _____________________________________________________ Expiration date: ____________________________________________________ Signature: __________________________________________________________ From raetsch at first.gmd.de Tue Dec 12 10:24:39 2000 From: raetsch at first.gmd.de (Gunnar Raetsch) Date: Tue, 12 Dec 2000 16:24:39 +0100 Subject: New Website on Boosting and Ensemble Learning Message-ID: <3A364337.CD4E134@first.gmd.de> We are pleased to announce a new web-site on Boosting and related ensemble learning methods. It can be found at http://www.boosting.org Compared to other pages on Boosting, the main difference is that we have enlarged the scope to form a repository not only for research on Boosting, but also on Ensemble Learning in general, Learning Theory, Large Margin Classifiers, Mathematical Programming, and related topics. The aim is to serve as a central information source by providing links to papers, upcoming events, datasets, code, a discussion board, etc. We have strived to create a forum for providing a balanced representation of the field of Boosting and ensemble learning research. It is our hope that this forum will contribute its share to the exciting developments in this field that all of us have been and are witnessing these years. On the technical side, features include fully automatic data entry, papers can be uploaded to the website, there exists a search option for papers, and data can also be provided in BibTeX format which should make it easier referencing to papers available at the site. If you would like to add a paper of yours, please feel free to do so by following the instructions on http://www.boosting.org/publications.html We would like to express thanks to Central Research Institute of Electric Power Industry for allowing us to host the web-site in Tokyo. Furthermore, we thank Alex Smola for providing a copy of the Kernel-Machines-Site which served as a basis for creating this new site. We also thank GMD-FIRST for providing resources to maintain this site. -- ----------------------------------------- Gunnar R"atsch, GMD First Berlin Tel : +49 30 6392 1906 WWW : http://www.first.gmd.de/~raetsch From shultz at psych.mcgill.ca Wed Dec 13 14:19:05 2000 From: shultz at psych.mcgill.ca (Thomas R. Shultz) Date: Wed, 13 Dec 2000 14:19:05 -0500 Subject: Human Cognitive Neuroscience position at McGill Message-ID: <4.3.1.0.20001213141420.00a82e80@127.0.0.1> McGill University Department of Psychology Assistant or junior Associate Professor Position in Human Cognitive Neuroscience The Department of Psychology of McGill University seeks applicants for a tenure-track position at the Assistant or junior Associate Professor level in Human Cognitive Neuroscience. The deadline for receipt of completed applications is January 15, 2001, with an anticipated starting date of September 1, 2001. Preference will be given to applicants with interests in the cognitive neuroscience of higher order cognitive processes, such as language, reasoning, problem solving, categorization, decision making. Our current strengths within this broad domain are language, higher order reasoning, learning, memory, and speech and music cognition. The Department has excellent facilities for interdisciplinary research through its links with related academic departments at McGill and other universities in Montreal, research units in the McGill University Health Centre including the Montreal Neurological Institute, and McGill Cognitive Science. Applicants at the Assistant Professor level should present early evidence of the ability to establish a record of significant, externally funded research productivity, and applicants at the Associate Professor level should have such a record. All applicants are expected to have an aptitude for undergraduate and graduate teaching. Applicants should arrange for three confidential letters of recommendation to be sent to the address below. A curriculum vitae, description of current and proposed areas of research, selected reprints of published or in press research articles, a description of areas of teaching competency, interest, and approaches, and other relevant material, should also be sent to Chair, Human Cognitive Neuroscience Search Committee Department of Psychology McGill University 1205 Dr. Penfield Avenue Montreal, Quebec, Canada H3A 1B1 In accordance with Canadian immigration requirements, priority will be given to Canadian citizens and permanent residents of Canada. McGill University is committed to equity in employment. All academically qualified candidates are encouraged to apply. -------------------------------------------------------- Thomas R. Shultz, Professor, Department of Psychology, McGill University, 1205 Penfield Ave., Montreal, Quebec, Canada H3A 1B1. E-mail: shultz at psych.mcgill.ca NEW http://www.psych.mcgill.ca/perpg/fac/shultz/default.htm Phone: 514 398-6139 Fax: 514 398-4896 -------------------------------------------------------- From rdybowski at btinternet.com Wed Dec 13 14:55:02 2000 From: rdybowski at btinternet.com (Richard Dybowski) Date: Wed, 13 Dec 2000 19:55:02 +0000 Subject: Machine Learning Journal Special Issue on Fusion of Knowledge with Data: First Call for Papers Message-ID: <4.2.0.58.20001213195343.03c42e00@mail.btinternet.com> Please accept my apologies if you receive multiple copies of this call. ----------------------------------------------------------------------------- Machine Learning Journal Special Issue on Fusion of Domain Knowledge with Data for Decision Support ----------------------------------------------------------------------------- >>> First Call for Papers <<< Statistics and machine learning are data-oriented tasks in which domain models are induced from data. The bulk of research in these fields concentrates on inducing models from data archived in computer databases. However, for many problem domains, human expertise forms an essential part of the corpus of knowledge needed to construct models of the domain. The discipline of knowledge engineering has focused on encoding the knowledge of experts in a form that can be encoded into computational models of a domain. At present, knowledge engineering and machine learning remain largely separate disciplines. Yet in many fields of endeavor, substantial human expertise exists alongside data archives. When both data and domain knowledge are available, how can these two resources effectively be combined to construct decision support systems? The aim of this special issue of the Machine Learning journal is to allow researchers to communicate their work on integrating domain knowledge with data (knowledge-data fusion; theory revision; theory refinement) to a general machine learning audience. Emphasis is on sound theoretical frameworks rather than ad hoc approaches. Of particular interest are papers that combine clear theoretical discussion with practical examples, and papers that compare different approaches. Possible frameworks for knowledge-data fusion include probabilistic (Bayesian/belief) networks, possibilistic logics and networks, hybrid neuro-fuzzy networks, and inductive logic programming. Topics of interest include (but are not limited to): * Practical applications of knowledge-data fusion. What lessons have been learnt from attempts to apply knowledge-data fusion to real-world decision problems? * How are the various knowledge representation and inference frameworks that permit induction theoretically related to each other? * What frameworks enable an existing induced model, such as a neural network, to be incorporated into a proposed knowledge-based system? * How can knowledge-data fusion be applied to temporal data? Submitted papers must not exceed 30 pages and must conform to the Machine Learning journal style. Please see the associated Web site for further submission details: http://www.umds.ac.uk/microbio/richard/kdf/ This Call for Papers is *not* restricted to those who presented at the UAI 2000 Workshop on Knowledge-Data Fusion: it is open to everyone who has an interest in this topic. Please direct any enquiries to Richard Dybowski: rdybowski at btinternet.com Schedule -------------- Paper submission deadline: June 1, 2001 Authors' notification of decisions: September 1, 2001 Final revised papers due: December 15, 2001 Guest Editors -------------------- Richard Dybowski (King's College London) Kathryn Blackmond Laskey (George Mason University) James Myers (Ballistic Missile Defense Organization) Simon Parsons (Liverpool University) From terry at salk.edu Thu Dec 14 01:05:32 2000 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 13 Dec 2000 22:05:32 -0800 (PST) Subject: NEURAL COMPUTATION 12:12 In-Reply-To: <200012080223.eB82NHo08011@purkinje.salk.edu> Message-ID: <200012140605.eBE65WV24409@purkinje.salk.edu> Neural Computation - Contents - Volume 12, Number 12 - December 1, 2000 Article Evolution of Cooperative Problem-Solving in an Artificial Economy Eric B. Baum and Igor Durdanovic View Cortical Potential Distributions and Information Processing Henry C. Tuckwell Note Asymptotic Bias in Information Estimates and The Exponential (Bell) Polynomials Jonathan D. Victor Letters Relating Macroscopic Measures of Brain Activity to Fast Dynamic Neuronal Interactions D. Chawla, E. D. Lumer and K. J. Friston Analysis of Pointing Errors Reveals Properties of Data Representations and Coordinate Transformations within the Central Nervous System J. McIntyre, F. Stratta, J. Droulez, and F. Lacquaniti Modeling Selective Attention Using a Neuromorphic Analog VLSI Device Giacomo Indiveri Asymptotic Convergence Rate of the EM Algorithm for Gaussian Mixtures Jinwen Ma, Lei Xu, and Michael Jordan Incremental Active Learning for Optimal Generalization Masashi Sugiyama, and Hidemitsu Ogawa A Quantitative Study of Fault Tolerance, Noise Immunity and Generalization Ability of MLPs J. L. Bernier, J. Ortega, E. Ros, I. Rojas, and A. Prieto On the Computational Complexity of Binary and Analog Symmetric Hopfield Nets Jiri Sima, Pekka K. Orponen, and Teemu Antti-Poika ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2000 - VOLUME 12 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $88 $94.16 $136 Institution $430 $460.10 $478 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 258-6779 mitpress-orders at mit.edu ----- From Wulfram.Gerstner at epfl.ch Thu Dec 14 12:15:18 2000 From: Wulfram.Gerstner at epfl.ch (Wulfram Gerstner) Date: Thu, 14 Dec 2000 18:15:18 +0100 Subject: PostDoc and PhD student positions Message-ID: <3A390026.BA04A49C@epfl.ch> The Neural Computation Group at the Swiss Federal Institute of Technology in Lausanne is expanding its activities and looking for several PhD-students and PostDocs in the area of Computational Neuroscience/Neural Computation. In particular, we seek to strengthen activities on problems such as - Neural coding with spiking neurons - Spike-time dependent plasticity - Reinforcement learning and biological models of conditioning - Hippocampal models of spatial representation - Validating biological models with Khepera robots - Models of vision (e.g. saccades, attention, motion) - Implications of Machine Learning concepts for biological information processing For further details on current activities, see http://diwww.epfl.ch/mantra/ Applicants should have a strong background in mathematical modeling, a keen interest in questions of neuroscience, and the capacity to relate model results to experimental data. Collaborations with experimental groups exist and will be further developped. The Swiss Federal Institute of Technology in Lausanne is the sister institution of the ETH Zurich and offers excellent working conditions. Lausanne is located on the shores of the lake of Geneva with beautiful surroundings for hiking, climbing, skiing and water sports. The city of Lausanne has the flair of an old university town with lots of theaters, music and other cultural activities. Geneva is only 35 minutes by train. Berne 1 hour, Zurich 2 and a half hours, Paris 3 and a half hours. http://www.lausanne-tourisme.ch/ Applications should include CV, list of publications, names of at least two references, and a one-page statement of research interests. starting date: between January and October 2001 Please send applications to: Wulfram Gerstner Center for Neuromimetic Systems Swiss Federal Institute of Technology Lausanne Computer Science Department, EPFL-DI 1015 Lausanne, Switzerland If you want to send the applications by email, please mark clearly - application - in the subject line and send to wulfram.gerstner at epfl.ch -- --------------------------------------------------------------------- Wulfram Gerstner Swiss Federal Institute of Technology Lausanne Assistant Professor Centre for Neuro-mimetic Systems, Mantra Computer Science Department, EPFL, IN-J, 032 1015 Lausanne EPFL Tel. +41-21-693 6713 wulfram.gerstner at epfl.ch Fax. +41-21-693 5263 http://diwww.epfl.ch/mantra --------------------------------------------------------------------- From R.Poli at cs.bham.ac.uk Thu Dec 14 09:00:39 2000 From: R.Poli at cs.bham.ac.uk (Riccardo Poli) Date: Thu, 14 Dec 2000 14:00:39 GMT Subject: PERMANENT LECTURESHIP IN NATURAL COMPUTATION Message-ID: <200012141400.OAA01717@sonic.cs.bham.ac.uk> Dear All, We invite applications from outstanding candidates for three open-ended lectureships (equivalent to tenure-track assistant professorship in North America) in the School of Computer Science, the University of Birmingham, UK (see the advertisment appended). One of the three posts is particularly relevant to members of this list, i.e., for someone with a strong background in natural computation (including evolutionary, neural and other nature-inspired computations). However, all three lectureships are open to all outstanding candidates. The School of Computer Science has an active and strong research group in evolutionary and neural computations, the EEBIC group, consisting of four permanent academic staff (faculty) and two research fellows: Julian Miller (Evolutionary Computation, Machine Learning) Riccardo Poli (Evolutionary Computation, GP, Computer Vision, NNs, AI) Jon Rowe (Evolutionary Computation, AI) Thorsten Schnier (Evolutionary Computation, Engineering Design) Xin Yao (Evolutionary Computation, NNs, Machine Learning) Jun He (Evolutionary Computation, from 1 Feb 2001) There are other staff members in the school who are in the areas of evolvable architectures of mind, medical imaging, robotics, and reinforcement learning. The School has a strong AI group. Our research has been supported by EPSRC, Marconi Communications, EU, BT, DERA, and the Royal Society. Further information about the new MSc mentioned in the following ad can be found at: http://www.cs.bham.ac.uk/~xin/courses/mtp/ More information about the school and the posts can be obtained from our web site or by contacting the head of school (not me), although I'm happy to answer questions about research activities in natural computation in the school. Additional research posts in Computer Science and Artificial Intelligence in this School can be found at: http://www.cs.bham.ac.uk/school/jobvacancies Riccardo ====================================================================== SCHOOL OF COMPUTER SCIENCE THE UNIVERSITY OF BIRMINGHAM England Three Lecturership Posts Applications are invited for three lectureship posts in Computer Science, starting as soon as possible (September 2001 latest). Postholders will be expected to contribute strongly to research, teaching and administration within the School. As an exception, consideration will be given for one of the posts to applicants whose strength is mainly in teaching in an area of special benefit to the School, for example systems analysis, software design, information systems, human-computer interaction or natural computation (taken to include evolutionary, neurally-inspired, and other nature-based computational styles). We intend one of the positions to be filled by someone able to contribute to teaching in our new EPSRC-funded MSc in Natural Computation. Applicants may be in any area of research in computational science. Generally, applicants should have, or soon expect to have, a PhD in computer science or an appropriate, closely related field, together with research experience as evidenced by publications in leading international journals or conference proceedings. However, teaching-orientated applicants may be acceptable if they have an appropriate, strong educational or industrial background and have a good university degree in an appropriate field. ---------------------------------------------------------------------- For further information please see http://www.cs.bham.ac.uk/research/jobs/lect01/ For the formal application procedure please see that webpage. CLOSING DATE: 31 January 2001. (Late applications may be considered.) Interviews are tentatively planned for late February / early March. It may be possible to negotiate part-time work in special cases. Informal enquiries may be made to Prof. John Barnden (Head of School) Tel: (+44) (0)121 414-3711 Email: J.A.Barnden at cs.bham.ac.uk ====================================================================== From ttroyer at psyc.umd.edu Thu Dec 14 17:55:02 2000 From: ttroyer at psyc.umd.edu (Todd Troyer) Date: Thu, 14 Dec 2000 17:55:02 -0500 Subject: Interdisciplinary training at the University of Maryland, College Park Message-ID: The Neuroscience and Cognitive Science (NACS) program at the University of Maryland (http://www.life.umd.edu/nacs) solicits applications for students interested in interdisciplinary graduate training. The NACS program offers a breadth of research and training, and offers courses in the neural, cognitive, and computational sciences. Students have the opportunity to work across disciplines, across labs, and even at multiple sites (such as NIH or UM Baltimore). In addition to the over 70 NACS faculty distributed among 14 departments, there is the potential of working with scientists at NIH, USDA, NIST, the National Zoo and the Smithsonian Institution. The program offers competitive, multi-year stipends that may include family health insurance and full tuition remission. Many NACS faculty take a computational or combined computational/experimental approach to the study of neural and cognitive function. A selected sample of research strengths on campus includes: Neuroethological and comparative approaches to auditory processing. Sensorimotor integration in animal, human, and neuromorphic systems. Dynamical approaches to neural processing and motor behavior. Linguistics and the cognitive neuroscience of language. Affective and cognitive approaches to human development. Interested students are encouraged to visit the NACS web site at http://www.life.umd.edu/nacs/ or to write to NACS, Biology/Psychology Building University of Maryland College Park, MD 20742 Phone: 301-405-8910 e-mail: sd136 at umail.umd.edu College Park is located close to Washington DC, with easy access by Metro or car to the rich cultural life of the DC metropolitan area. From tabor at uconnvm.uconn.edu Fri Dec 15 09:43:32 2000 From: tabor at uconnvm.uconn.edu (tabor@uconnvm.uconn.edu) Date: Fri, 15 Dec 2000 09:43:32 -0500 Subject: PhD Openings: Psychology Dept., University of Connecticut Message-ID: <3.0.3.32.20001215094332.0137b7e0@psych.psy.uconn.edu> ******************************************************************* GRADUATE TRAINING IN LANGUAGE AND COGNITION AT THE UNIVERSITY OF CONNECTICUT ******************************************************************* The Language and Cognition Program in the Department of Psychology at the University of Connecticut has openings for at least 4 PhD studentships to start in Fall, 2001. The program is centered around the experimental study of language processing, and has done excellent work on speech perception and production, word identification, sentence processing, skilled reading, and the process of learning to read. It has close ties with the Center for the Ecological Study of Perception and Action (CESPA), which is in the same division of the University of Connecticut Department of Psychology. Over the past several years, a unique synthesis has been occurring between the ecological work, which has focused on the development of dynamical systems models of human physical movement (e.g. limb coordination, postural control, gait, etc.), and the language work, which has been emphasizing the use of dynamical connectionist models to study language as action. An important element in the mix is Haskins laboratories, an independent research lab located nearby in New Haven. For over 60 years, Haskins has done pathbreaking research on speech and reading and maintained an environment where people from many places and backgrounds meet regularly to explore ideas creatively and work on joint projects. Important deadline: January 15: Graduate Applications due. The brochure is available on line at: http://www.sp.uconn.edu/~wwwpsyc/Experimental.html/ For admission guidelines and to download application forms, see: http://www.sp.uconn.edu/~wwwpsyc/GradAd.html/ To obtain a printed brochure and a set of application materials, write, telephone, fax, or email: Ms. Nicole Dolat, Department of Psychology, University of Connecticut, 406 Babbidge Road, Unit 1030, Storrs, CT 06269-1030 Phone: (860) 486-3528 FAX: (860) 486-2760 E-Mail: futuregr at psych.psy.uconn.edu ******************************************************************* Description of the Program in Language and Cognition: The Program in Language and Cognition focuses on those aspects of language that make it a uniquely versatile vehicle for communication and thought. There is thus a strong focus on the dynamical aspects of language, including experimental studies of language processing, learning, and change at the phoneme, word, and sentence level, modeling of language processes using artificial neural (connectionist) networks and symbolic computational models, and mathematical analysis using dynamical systems theory and statistics. There is particular interest in an ecological approach, which emphasizes continual interaction between speaker/hearers and their environments. There is much interest in the biological basis of language, both in pursuit of innate endowment questions and in studies of neural mechanisms using state-of-the-art neuroimaging tools. The group has long conducted basic research on the reading process; some members of the group are also engaged in the translation of research findings to the classroom. The Program has close ties to the Center for the Study of Perception and Action (CESPA---http://ione.psy.uconn.edu/~cespaweb/), the Developmental and Behavioral Neuroscience Divisions in the Dept. of Psychology (http://www.sp.uconn.edu/~wwwpsyc/), the Linguistics Department (http://vm.uconn.edu/~wwwling/), and the Cognitive Science Focus (http://cogsci.uconn.edu/) at the University of Connecticut. In addition, Haskins Laboratories (http://www.haskins.yale.edu), located nearby in New Haven, provides a stimulating environment for research and training. The program prepares students for careers in research and teaching. A student's research activity begins immediately on entry to the program. In addition, three courses are typically taken each semester. A student's schedule also includes attendance at colloquia and informal weekly group meetings for discussion of problems in theory and research. Course work for the Ph.D. degree can often be completed in two-and-a-half to three years. Another year or two is needed to complete the dissertation. Applicants should have an excellent academic record. Research experience is helpful but not necessary. Applicants may have an undergraduate major in psychology, linguistics, computer science, mathematics, cognitive science, or other related fields of study. ***** CAROL FOWLER, Professor of Psychology. Dr. Fowler works on speech perception and production within the developing direct-realist framework. In addition, she has begun collaborative research on cross-person coordination and cooperation in language use. This is part of an effort to develop an ecological theory of language-that is, an understanding of how language is used in ordinary contexts in which speech occurs. Dr. Fowler is the Director of Haskins Laboratories. LEONARD KATZ, Professor of Psychology. Dr. Katz studies reading, focusing on the process of printed word recognition. Cross-language experiments are often used to reveal in which ways word recognition is shaped by a language's particular characteristics and in which ways it is more general. Languages studied include English, Hebrew, Russian, Serbo-Croatian and Turkish. In addition, functional Magnetic Resonance Imaging studies (carried out in conjunction with Haskins Laboratories and Yale Medical School) explore the brain mechanisms that support the word recognition process. Finally, behavioral experiments in English are used to study the effects on word recognition of the reader's lexicon (i.e., neighborhood factors) and reader strategies. JAY RUECKL, Associate Professor of Psychology. A primary goal of Dr. Rueckl's research is to use connectionist networks to forge a link between theories of implicit memory and models of word identification. His research focuses on the interaction of phonological, morphological, and semantic factors in the influence of implicit memory on work identification in reading, the role of perceptual detail (e.g. the characteristics of a speaker's voice) in visual and spoken word identification. In addition, together with his colleagues at Haskins Laboratories, Dr. Rueckl has recently begun to apply artificial neural network models to the investigation of the cognitive neuropsychology of reading. DONALD SHANKWEILER, Professor of Psychology. The broad aim of Dr. Shankweiler's research is to understand how the language apparatus, which is biologically specialized for speech, becomes adapted to reading and writing. In studies carried out in the 1970's, he and Dr. I. Y. Liberman discovered that there is an important association between children's abilities to analyze speech into its components (phonemes, syllables, and morphemes) and their progress in reading. Recent research has pursued the implications of this association for the operation of short-term verbal memory; for children who lack phonologically analytic skills, short-term memory function is also impaired. Dr. Shankweiler, with Stephen Crain and their students, have developed a model of the role of short-term memory in language comprehension. WHITNEY TABOR, Assistant Professor of Psychology. Dr. Tabor's research focuses on the coexistence of structure and flexibility in complex systems. He uses artificial neural networks and dynamical systems theory to develop models of human language processing, learning, and change. He has worked on the role of semantic information in sentence processing, evidence for ungrammatical influences in sentence processing, attractor models of syntactic category structure, the learning of complex phrase structure grammars, and the evolution of grammatical categories over historical time. * * * * * AFFILIATED FACULTY CLAUDIA CARELLO, Professor of Psychology, Director of CESPA: Ecological study of human movement, printed word recognition in English, Korean, Serbo-Croatian. ROGER CHAFFIN, Professor of Psychology (Hartford): Semantic memory, memory for skilled performance. ELENA LEVY, Associate Professor of Psychology (Stamford): Language and gesture, language development. DIANE LILLO-MARTIN, Professor of Linguistics and Psychology: The structure of American Sign Language, its acquisition and processing, and the processes deaf people use to read. GEORGIJE LUKATELA, Visiting Professor: The phonological basis of printed word recognition. LETITIA NAIGLES, Associate Professor of Psychology: Language acquisition, word learning. KENNETH PUGH, Associate Professor, Yale University and Haskins Laboratories: Brain imaging studies of reading. WILLIAM SNYDER, Assistant Professor of Linguistics: Cross-linguistic studies of language acquisition; sentence processing. MICHAEL TURVEY, Professor of Psychology: Ecological study of human movement, the phonological basis of printed word recognition. ////////\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\\\\\\\\ Whitney Tabor (860) 486-4910 (office) Department of Psychology (860) 486-2760 (fax) University of Connecticut (860) 486-6080 (lab) Storrs, CT 06269-1020 tabor at uconnvm.uconn.edu USA WAB Room 124 (office) http://www.sp.uconn.edu/~wwwpsyc/Faculty/Tabor/Tabor.html \\\\\\\\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\//////// From harnad at coglit.ecs.soton.ac.uk Mon Dec 18 12:01:32 2000 From: harnad at coglit.ecs.soton.ac.uk (Stevan Harnad) Date: Mon, 18 Dec 2000 17:01:32 +0000 (GMT) Subject: Universities can now download Eprints 1.0 from eprints.org Message-ID: The operational release of the Eprints archive-creating software is now down-loadable from http://www.eprints.org The eprints.org software will create Eprints Archives that are interoperable and compliant with the current Open Archives protocol. The software is free, uses only free software, and can be installed and maintained easily. It is modular, and written to be easily upgraded with each upgrade of the Open Archives protocol: http://www.openarchives.org All Eprint Archives created with the eprints.org software are fully interoperable, and can be registered as Open Archive Data Providers: http://www.openarchives.org/sfc/sfc_archives.htm This means that their contents can then in turn all be harvested, jointly indexed, and jointly searched with all the other Eprint Archives through Open Archive Service Providers such as http://arc.cs.odu.edu All Eprints can also be citation-interlinked: http://opcit.eprints.org so that the research literature can be navigated by citation. It will also be possible to monitor research impact in powerful new ways, once the eprints are up there: http://cogsci.soton.ac.uk/harnad/Papers/Harnad/harnad00.citation.htm The Eprints software was expressly designed so that universities and research institutions worldwide can now immediately create their own Open Archives, in which their researchers in all disciplines can (immediately) self-archive their research -- both pre-refereeing preprints and refereed postprints. http://cogsci.soton.ac.uk/harnad/Tp/1-Anomalous-Picture/sld001.htm http://cogsci.soton.ac.uk/harnad/Tp/2-Resolving-the-Anomaly/sld001.htm As soon as universities create their own Eprint Archives and their researchers self-archive their papers in them, the world's refereed research literature will be freed from all its current needless access-barriers and impact-barriers. Footnote: HISTORY IS WATCHING. The means of freeing the entire refereed research literature (within a matter of days, in principle!) is now within the reach of the world research community. If you have a published paper of your own that has not reached its full potential readership, if there is a published paper by someone else that you or your university cannot afford to access, or cannot access immediately, or if your university has a "serials crisis" preventing its researchers from accessing the entire refereed research corpus -- AND you have NOT self-archived your own papers -- then, as of now, you have only yourself to blame (and history will be the judge, in hindsight)! -------------------------------------------------------------------- Stevan Harnad harnad at cogsci.soton.ac.uk Professor of Cognitive Science harnad at princeton.edu Department of Electronics and phone: +44 23-80 592-582 Computer Science fax: +44 23-80 592-865 University of Southampton http://www.cogsci.soton.ac.uk/~harnad/ Highfield, Southampton http://www.princeton.edu/~harnad/ SO17 1BJ UNITED KINGDOM NOTE: A complete archive of the ongoing discussion of providing free access to the refereed journal literature online is available at the American Scientist September Forum (98 & 99 & 00): http://amsci-forum.amsci.org/archives/september98-forum.html You may join the list at the site above. Discussion can be posted to: september98-forum at amsci-forum.amsci.org From tp at ai.mit.edu Mon Dec 18 12:12:11 2000 From: tp at ai.mit.edu (Tommy Poggio) Date: Mon, 18 Dec 2000 12:12:11 -0500 Subject: Post-doc position Message-ID: <4.3.2.7.2.20001218121119.021b0ab8@pop6.attglobal.net> An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/00000000/24a82347/attachment.html From jrauch at MIT.EDU Mon Dec 18 15:41:51 2000 From: jrauch at MIT.EDU (Judy) Date: Mon, 18 Dec 2000 15:41:51 -0500 Subject: faculty position available Message-ID: <4.3.2.20001218153657.00bd2580@hesiod> MASSACHUSETTS INSTITUTE OF TECHNOLOGY DEPARTMENT OF BRAIN & COGNITIVE SCIENCES The MIT Department of Brain and Cognitive Sciences anticipates making a new tenure-track appointment in theoretical/experimental neuroscience at the Assistant Professor level. Candidates should combine a strong mathematical background and an active research interest in the modeling of specific cellular- or systems-level phenomena with appropriate experiments. Individuals whose research focuses on properties of single neurons or networks of neurons are especially encouraged to apply. We are also interested in individuals working on bioinformatics in neuroscience. Responsibilities include graduate and undergraduate teaching and research supervision. Applications should include a brief cover letter stating the candidate's research and teaching interests, a vita, three letters of recommendation, and representative reprints, and should be sent to: Theoretical/Experimental Neuroscience Search Committee, Dept. of Brain & Cognitive Sciences, E25-406, MIT, Cambridge, MA 02139. Review of applications will begin December 15, 2000. Qualified women and minority candidates are especially encouraged to apply. MIT is an Affirmative Action/Equal Opportunity employer. From bengioy at IRO.UMontreal.CA Mon Dec 18 16:56:51 2000 From: bengioy at IRO.UMontreal.CA (Yoshua Bengio) Date: Mon, 18 Dec 2000 16:56:51 -0500 Subject: TR: neural statistical language model beats trigram Message-ID: <20001218165651.A556@euclide.IRO.UMontreal.CA> Hello, The following tech. report that is a long version of the recently presented NIPS'2000 oral is now available on the web: A Neural Probabilistic Language Model Y. Bengio, R. Ducharme, P. Vincent Tech. Rep. 1178, Dept. of CS&OR / CRM, U of Montreal A goal of statistical language modeling is to learn the joint probability function of sequences of words in a language. This is intrinsically difficult because of the curse of dimensionality: a word sequence on which the model will be tested is likely to be different from all the word sequences seen during training. Traditional but very successful approaches based on N-grams obtain generalization by gluing very short sequences seen in the training set. Instead, we propose to fight the curse of dimensionality with its own weapons. In the proposed approach one learns simultaneously (1) a distributed representation for each word along with (2) the probability function for word sequences, expressed in terms of these representations. Generalization is obtained because a sequence of words that has never been seen before gets high probability if it is made of words that are similar to words forming an already seen sentence. We report on experiments using neural networks for the probability function, showing on two text corpora that the proposed approach very significantly improves on a state-of-the-art trigram model, and that the proposed approach allows to take advantage of much longer context. postscript file available at: http://www.iro.umontreal.ca/~lisa/pointeurs/TR1178.ps (or through my web page: follow publications -> tech. reports) -- Yoshua Bengio Professeur agrg Dpartement d'Informatique et Recherche Oprationnelle Universit de Montral, adresse postale: C.P. 6128 Succ. Centre-Ville, Montral, Qubec, Canada H3C 3J7 adresse civique: 2920 Chemin de la Tour, Montral, Qubec, Canada H3T 1J8, #2194 Tel: 514-343-6804. Fax: 514-343-5834. Bureau 3339. http://www.iro.umontreal.ca/~bengioy http://www.iro.umontreal.ca/~lisa From sylee at ee.kaist.ac.kr Tue Dec 19 04:06:47 2000 From: sylee at ee.kaist.ac.kr (Soo-Young Lee) Date: Tue, 19 Dec 2000 18:06:47 +0900 Subject: Bio+Electronics Faculty Position at KAIST EE References: <20001205015253.3E0342B229@endor.bbb.caltech.edu> Message-ID: <00c101c0699b$05820bb0$0100a8c0@kaistsylee2> PLEASE DO NOT USE 'REPLY'; FOR MORE INFO VISIT KAIST WEB SITE (www.kaist.ac.kr) OR CONTACT TO THE ADDRESSES AT THE END OF THIS E_MAIL. The Department of Electrical Engineering at Korea Advanced Institute of Science and Technology (KAIST) solicits applications for faculty position. Although all areas of electrical and computer engineering are welcome, we are particularly interested in faculties working on both/between electrical engineering and biology including Bio-Electronics and Brain Science. Unlike BK'21 Research Faculty positions with limited responsibilty, this faculty position will have all previleages of KAIST regular faculties. Also the faculty may join the Brain Science Research Center, which is currently leading the National Research Program on Brain Sciene and Engineering. The research program is sponsored by Korean Ministry of Science and Technology, and about 140 professors are working on interdisciplinary research projects. The application deadline is January 12, 2001. For more information, please contact to Department of Electrical Engineering Korea Advanced Institute of Science and Technology 373-1 Kusong-dong, Yusong-gu Taejon 305-701 Korea (South) or Prof. Soo-Young Lee Director, Brain Science Research Center Korea Advanced Institute of Science and Technology 373-1 Kusong-dong, Yusong-gu Taejon 305-701 Korea (South) E-mail: sylee at ee.kaist.ac.kr From adrian at olsen.ch Tue Dec 19 08:26:16 2000 From: adrian at olsen.ch (Adrian Trapletti) Date: Tue, 19 Dec 2000 14:26:16 +0100 Subject: PhD Thesis available: On Neural Networks as Statistical Time Series Models Message-ID: <3A3F61F8.3CBFB079@olsen.ch> Dear colleagues, I am pleased to announce that my PhD thesis, titled 'On Neural Networks as Statistical Time Series Models' is now available for electronic download at: http://www.olsen.ch/people/adrian/adrian.html Abstract: This thesis provides a rigorous mathematical analysis of the stochastic properties for what probably are the most popular classes of neural networks for time series analysis and forecasting: feedforward autoregressive neural networks and recurrent autoregressive moving average neural networks. In particular, it is shown that the characteristic roots of the shortcuts, the standard conditions from linear time series analysis, determine the stochastic behaviour of both feedforward and recurrent neural network models. If, e.g., all the characteristic roots are outside the unit circle, then the neural network models are geometrically ergodic and asymptotically stationary. This thesis also investigates training and testing of neural network models. In particular, it is shown that the least squares estimators are consistent and asymptotically normal provided the neural network model is stationary. Furthermore, training of nonstationary neural network models is considered. In particular, the hypothesis test for a unit root of Phillips and Perron is introduced as a tool to discriminate between stationary and integrated neural network models and a new neural network based unit root test is constructed which can be seen as a nonlinear extension of the augmented Dickey-Fuller test. Long abstract: in the thesis Best regards and merry Xmas Adrian Trapletti -- Adrian Trapletti, Olsen & Associates Ltd., See- feldstrasse 233, CH-8008 Zrich, Switzerland Phone: +41 (1) 386 48 48 Fax: +41 (1) 422 22 82 E-mail: adrian at olsen.ch WWW: http://www.olsen.ch From terry at salk.edu Wed Dec 20 20:25:59 2000 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 20 Dec 2000 17:25:59 -0800 (PST) Subject: NEURAL COMPUTATION 13:1 In-Reply-To: <200012140605.eBE65WV24409@purkinje.salk.edu> Message-ID: <200012210125.eBL1Px940973@purkinje.salk.edu> Neural Computation - Contents - Volume 13, Number 1 - January 1, 2001 Review Detecting and Estimating Signals over Noisy and Unreliable Synapses: Information-Theoretic Analysis Amit Manwani and Christof Koch Letters An Algorithm for Modifying Neurotransmitter Release Probability Based on Pre- and Postsynaptic Spike Timing Walter Senn, Henry Markram, and Misha Tsodyks Differential Filtering of Two Presynaptic Depression Mechanisms Richard Bertram A Statistical Theory of Long-Term Potentiation and Depression John M. Beggs Minimal Model for Intracellular Calcium Oscillations and Electrical Bursting in Melanotrope Cells of Xenopus Laevis L. Niels Cornelisse, Wim J. J. M. Scheenen, Werner J. H. Koopman, Eric W. Roubos, and Stan C. A. M. Gielen Neural Field Model of Receptive Field Restructuring in Primary Visual Cortex Katrin Suder, Florentin Worgotter and Thomas Wennekers On The Phase-Space Dynamics of Systems of Spiking Neurons. I: Model and Experiments Arunava Banerjee On The Phase-Space Dynamics of Systems of Spiking Neurons. II. Formal Analysis Arunava Banerjee Subtractive and Divisive Inhibition: Effect of Voltage-Dependent Inhibitory Conductances and Noise Brent Doiron, Andre Longtin, Neil Berman and Leonard Maler ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2000 - VOLUME 13 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $88 $94.16 $136 Institution $460 $492.20 $508 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From bruns at cs.tu-berlin.de Thu Dec 21 06:43:47 2000 From: bruns at cs.tu-berlin.de (Camilla Bruns) Date: Thu, 21 Dec 2000 12:43:47 +0100 Subject: EU Summerschool on Computational Neuroscience 2001 Message-ID: <200012211142.MAA15748@mail.cs.tu-berlin.de> This is the first call for the EU Summerschool on Computational Neuroscience 2001. EU ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE (AN I.B.R.O. NEUROSCIENCE SCHOOL) July 30 - August 24, 2001 INTERNATIONAL CENTRE FOR THEORETICAL PHYSICS, TRIESTE, ITALY DIRECTORS: Klaus Obermayer (Technical University Berlin, Germany) Alessandro Treves (SISSA, Trieste, Italy) Eilon Vaadia (Hebrew University, Jerusalem, Israel) Alain Destexhe (CNRS, Gif-sur-Yvette, France) The EU Advanced Course in Computational Neuroscience introduces students to the panoply of problems and methods of computational neuroscience, simultaneously addressing several levels of neural organisation, from subcellular processes to operations of the entire brain. The course consists of two complementary parts. A distinguished international faculty gives morning lectures on topics in experimental and computational neuroscience. The rest of the day is devoted to practical training, including learning how to use simulation software and how to implement a model of the system the student wishes to study on individual unix workstations. The first week of the course introduces students to essential neurobiological concepts and to the most important techniques in modelling single cells, networks and neural systems. Students learn how to apply software packages like GENESIS, MATLAB, NEURON, XPP, etc. to the solution of their problems. During the following three weeks the lectures will cover specific brain functions. Each week topics ranging from modelling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the brain will be covered. The course ends with a presentation of the students' projects. The EU Advanced Course in Computational Neuroscience is designed for advanced graduate students and postdoctoral fellows in a variety of disciplines, including neuroscience, physics, electrical engineering, computer science and psychology. Students are expected to have a basic background in neurobiology as well as some computer experience. Students of any nationality can apply. A total of 32 students will be accepted. About 20 students will be from the European Union and affiliated countries (Iceland, Israel, Liechtenstein and Norway plus all countries which are negotiating future membership with the EU). These students are supported by the European Commission and we specifically encourage applications from researchers who work in less- favoured regions of the EU and women. IBRO, ICTP and the Boehringer Ingelheim Foundation provide support for participation from students of non-European countries all over the world, IBRO and ICTP in particular countries from the former Soviet Union, Africa, Asia and South America, while The Brain Science Foundation supports Japanese students. Students receiving support from the mentioned sources will receive travel grants and free full board at the Adriatico Guest House in Trieste. More information and application forms can be obtained: http://www.neuroinf.org/courses/trieste2001.shtml Please apply electronically using a web browser if possible. - e-mail: bruns at cs.tu-berlin.de - mail: Camilla Bruns, Technical University Berlin, Department of Computer Science, Franklinstr, 28/29, 10587 Berlin, Germany Phone: +49-(0)30-314-73442 Fax: +49-(0)30-314-73121 APPLICATION DEADLINE: March 31st , 2001 Applicants will be notified of the results of the selection procedures by April 30, 2001. From Timxb at Colorado.EDU Thu Dec 21 13:53:21 2000 From: Timxb at Colorado.EDU (Brown Tim) Date: Thu, 21 Dec 2000 11:53:21 -0700 (MST) Subject: Positions in statistics and applied probability at Colorado Message-ID: <200012211853.eBLIrLu25419@pingan.Colorado.EDU> This may be of interest to connectionist in the Bayesian, Guassian Processes, MCMC, etc. side of the field. The applied math department is a mix of mathematicians, OR, CS and engnieering faculty that maintains contacts and shares students with engineering and sciences. Regards, Timothy X Brown Interdisciplinary Telecommunications Program Department of Electrical and Computer Engineering ECOT 331 Campus Box 530 University of Colorado Boulder, CO 80309-0530 Tel: (303) 492-1630 Fax: (303) 492-1112 http://ece-www.colorado.edu/~timxb Assistant Professor Applications are invited for a tenure-track assistant professorship to begin August 2001. Preference will be given to those candidates whose research emphasis is in statistics, stochastic partial differential equations or other areas of applied probability. The teaching load is three courses per year. Areas of research expertise within the Department include computational mathematics, nonlinear waves and dynamics, analysis of differential equations, physical applied mathematics, and applied probability. Further information can be found on the Department's web page, http://amath.colorado.edu/appm/. Applicants should send a letter of application, a current curriculum vitae, a statement of research interests, an AMS Standard Cover Sheet (see http://www.ams.org/employment/cover-template.doc) and three letters of recommendation (sent directly) to: Chair, Search Committee Department of Applied Mathematics 526 UCB University of Colorado Boulder CO 80309-0526 Review of applications will begin November 15, 2000 and will continue until the position is filled. The University of Colorado at Boulder is committed to diversity and equality in education and employment. >Received: from mail.fudan.edu.cn by mouse.fudan.edu.cn (5.x/SMI-SVR4) id AA04862; Fri, 22 Dec 2000 09:32:24 +0800 From ICONIP2001 at fudan.edu.cn Thu Dec 21 20:35:01 2000 From: ICONIP2001 at fudan.edu.cn (ICONIP 2001) Date: Fri, 22 Dec 2000 09:35:01 +0800 Subject: ICONIP2001 Message-ID: <3A42AFC5.6511ED03@fudan.edu.cn> Dear Colleague, The attached is the First Announcement and Call for Paper for the 8th International Conference on Neural Information Processing 2001 (ICONIP 2001) Which will be held in Shanghai, China next November. We are expecting your actively contributing. Merry Christmas and a Happy New Year Sincerely yours Fanji Gu, Prof. Chairman of Organization Committee, ICONIP 2001 First Announcement and Call for Paper for ICONIP2001 The 8th International Conference on Neural Information Processing (ICONIP2001), the annual conference sponsored by Asia-Pacific Neural Network Assembly (APNNA), IEEE Beijing Section, IEEE NN Council, INNS and China Neural Network Council (CNNC), will be held in Shanghai, China, from November 14 to 18, 2001. The local organizer is Brain Science Research Center, Fudan University, co- organized by Shanghai Biophysics Society. The theme of the conference, Neural Information Processing, is broad enough to promote wide interactions among researchers in many academic disciplines. The conference will consist of 3 and a half day oral and poster presentation, and a half-day tour. Six leading scientists in this field was invited to give keynote lectures at the conference. They are: S. Amari (Japan), W. J. Freeman (USA), E. Oja (Finland), H. Szu (USA), L. Xu (Hong Kong, China) and X. Yang (China). In addition to mathematical and engineering approaches we also include brain science and cognitive science in the main stream. The conference topics include but are not limited to: 1 Brain and Cognitive Science 1.1 Dynamic brain 1.2 Data representation and neural coding 1.3 Learning and memory 1.4 Brain imaging in cognition and behavior 1.5 Perception, emotion, and cognition 1.6 Selective attention 1.7 Vision and auditory models 1.8 Consciousness 2 Models and Algorithms 2.1 Spiking Neuron 2.2 Learning algorithms 2.3 Neural network architectures 2.4 Neurodynamics & chaotic networks 2.5 Statistical neural network models 3 Hybrid Systems 3.1 Evolutionary neural systems 3.2 Fuzzy neural systems 3.3 Soft computing 3.4 Symbolic-neural hybrid systems 4. Hardware Implementation 4.1 Analog, digital, optical & hybrid neuro-systems 4.2 Artificial retina & cochlear chips 4.3 DSP & software implementation 5 Application 5.1 Computer vision 5.2 image processing 5.3 Data mining 5.4 Expert system 5.5 Finance & electronic commerce 5.6 Human-computer interaction 5.7 Intelligent control 5.8 Natural language processing 5.9 Pattern recognition 5.10 Robotics 5.11 Sensorimotor systems 5.12 Signal processing 5.13 Speech recognization 5.14 Time series prediction 5.15 Knowledge & Rule extraction 6 Others The list of the organizing committee of the conference is as follows: Honorary Chairs S.Amari, RIKEN, Japan C.Gu, Fudan Univ., China Conference Chairs K.Fukushima, Univ. of Electro-Com, Japan Y.Wu, Tsinghua Univ., China Steering Committee Chairs T. Shou, Fudan Univ. China Y. Zhong, China Post & Telecommunication Univ., China International Advisory Committee Chairs: Z. He, South-Eastern Univ., China N. Kasabov, Univ. Of Otago, New Zealand Program Committee Chairs A. Guo, Institute of Neuroscience, China M. Tsukada, Tamagawa University, Japan L. Zhang, Fudan Univ., China Organization Committee Chairs F. Gu, Fudan Univ., China M. Zhou, CNNC, China Finance Chair Y. Shi, Fudan Univ., China The registration fee is US$420 for regular participants before the deadline, including hard copies of the proceedings, reception, one evening entertainment, free lunch, banquette, and one half-day's city tour. The registration fee for students is US$230 before the deadline, including hard copies of the proceedings, reception, one evening entertainment, free lunch. Students should pay US$70 for participating in banquette, and one half-day's city tour. Important deadlines May 1, 2001 Paper submission June 30, 2001 Acceptance notification July 31, 2001 Camera-ready manuscripts Sept. 30, 2001 Advanced registration Shanghai is the biggest city in China, and a harmonic mixture of the traditional and the modern, the east and the west. Shanghai has completely changed in the last decade. After the conference, a satellite workshop C China C Japan C Korea joint workshop on Neurobiology and Neuroinformatics co-sponsored by School of Life Sciences & Brain Science Research Center, Fudan Univ. China; Zhejiang Univ. China; BSI RIKEN, Japan and Brain Science Research Center, KAIST, Korea, will be held in Hangzhou, China, a beautiful resort city, from Nov. 20 C22. The organizers will be S. Amari (Japan), F. Gu (China), S. Lee (Korea) and Q. Tong (China). The total participants are limited to fifty, Scientists from the other countries are also welcome to participate in the workshop as disscusants. Another satellite workshop "Nonlinear signal Processing and Neural computing science" held in Nanjing, a historical resort in China, after the conference is also in organizing. The organizer is Prof. Zhenya He from South East University, China. Anyone who are interested in participating in ICONIP2001, or any of its satellite workshops, please contact the person with the following address, so that he can put your name and address into his mailing address and give you further information in time: Fanji Gu, Prof. Chairperson of the Organization Committee of ICONIP2001 Organizer of China C Japan C Korea joint workshop on Neurobiology and Neuroinformatiocs Department of Physiology & Biophysics Fudan University Shanghai 200433 P. R. China Tel: +86-21-65642813 (O) +86-21-65298260 (H) Fax: +86-21-65298260 E-mail: ICONIP2001 at fudan.edu.cn For more details, please use the following Web address: http://www.cie-china.org/ICONIP2001 or http://EE.fudan.edu.cn/ICONIP2001 From mieko at isd.atr.co.jp Fri Dec 22 00:49:41 2000 From: mieko at isd.atr.co.jp (Mieko Namba) Date: Fri, 22 Dec 2000 14:49:41 +0900 Subject: Neural Networks 13(10) Message-ID: NEURAL NETWORKS 13(10) --------------------------------------------------------- CONTRIBUTED ARTICLES: ***** Mathematical and Computational Analysis ***** Independent component analysis for noisy data - MEG data analysis S. Ikeda, K. Toyama Generalized radial basis function networks for classification and novelty detection: self-organization of optimal Bayesian decision S. Albrecht, J. Busch, M. Kloppenburg, F. Metze, P. Tavan Nonlinear canonical correlation analysis by neural networks W.W. Hsieh Modular neural networks for non-linearity recovering by the Haar approximation Z. Hasiewicz On stability of nonlinear continuous-time neural networks with delays H. Lu Fuzzy lattice neurocomputing (FLN) models V.G. Kaburlasos, V. Petridis ***** Engineering and Design ***** Rule extraction by successive regularization M. Ishikawa ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 or 660 SEK or Y 15,000 [including Neural Networks 2,000 entrance fee] or $55 (student) 460 SEK (student) Y 13,000 (student) [including 2,000 entrance fee] ----------------------------------------------------------------------------- membership without $30 200 SEK not available to Neural Networks non-students (subscribe through another society) Y 5,000 (student) [including 2,000 entrance fee] ----------------------------------------------------------------------------- Institutional rates $1132 2230 NLG Y 149,524 ----------------------------------------------------------------------------- Name: _____________________________________ Title: _____________________________________ Address: _____________________________________ _____________________________________ _____________________________________ Phone: _____________________________________ Fax: _____________________________________ Email: _____________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number ____________________________ expiration date ________________________ INNS Membership 19 Mantua Road Mount Royal NJ 08061 USA 856 423 0162 (phone) 856 423 3420 (fax) innshq at talley.com http://www.inns.org ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership c/o Professor Tsukada Faculty of Engineering Tamagawa University 6-1-1, Tamagawa Gakuen, Machida-city Tokyo 113-8656 Japan 81 42 739 8431 (phone) 81 42 739 8858 (fax) jnns at jnns.inf.eng.tamagawa.ac.jp http://jnns.inf.eng.tamagawa.ac.jp/home-j.html ----------------------------------------------------------------- From georg at ai.univie.ac.at Fri Dec 22 05:53:24 2000 From: georg at ai.univie.ac.at (Georg Dorffner) Date: Fri, 22 Dec 2000 11:53:24 +0100 Subject: Open post-doc in economic modeling Message-ID: <3A4332A4.2CD437D0@ai.univie.ac.at> Merry Christmas to everyone!! The Neural Networks Group at the Austrian Research Institute for Artificial Intelligence in Vienna, Austria, has an immediate opening for a post-doc position in Agent-based economic modeling as part of the larger initiative "Adaptive Models in Economics and Management Science" (http://www.wu-wien.ac.at/am/). The goal is to investigate different approaches to modeling learning economic agents, among them neural networks, in a larger-scale simulation of partial economics including customers, firms and a financial market. A particular focus is on cognitvely plausible models of learning and knowledge. Some background on our own previous work, as well as on related work world-wide can be found at http://www.wu-wien.ac.at/am/ae.htm. Required background: - an education in computer science, mathematics or economics - programming experience (e.g. C++ or, in particular, Matlab) - a basic background in economics - a doctorate degree - research experience (preferably in agent-based simulation, complex systems, or related areas) Desired (but optional) background: - publications in the field - basic knowledge in neural networks and machine learning - basic knowledge in cognitive modeling - basic understanding knowledge of German The position will be limited to a little more than 2 years (March 2003), but with a good option to be extended thereafter. The monthly salary offered amounts to approx. ATS 24.500 (Euro 1780) after tax. Interested applicants should apply by email, mail or fax, no later than January 15, 2001, at the address below. Include a short vita, a list of publications, and any other information demonstrating your qualification. Send applications to: Georg Dorffner Austrian Research Institute for Artificial Intelligence Schottengasse 3 A-1010 Vienna phone: +43-1-4277-63116 fax: +43-1-4277-9631 email: georg at ai.univie.ac.at This position is funded by the Austrian Fonds zur Foerderung der wissenschaftlichen Forschung (FWF). From ijspeert at usc.edu Fri Dec 22 06:18:59 2000 From: ijspeert at usc.edu (ijspeert) Date: Fri, 22 Dec 2000 03:18:59 -0800 (PST) Subject: PhD studentships in computational motor control at USC, Los Angeles Message-ID: ---------------------------------------------------------------------------- Ph.D. Graduate Research Assistantships Available in Computational Motor Control, Rehabilitation Robotics and Humanoid Robotics at the University of Southern California ----------------------------------------------------------------------------- We are looking for outstanding Ph.D. graduate students for interdisciplinary projects in the area of computational motor control, rehabilitation robotics, and humanoid robotics. The projects will be conducted in collaboration with Dr. Auke Ijspeert (USC, Computer Science and Neuroscience), Dr. Stefan Schaal (USC, Computer Science and Neuroscience), and Dr. Carolee Winstein (USC, Kinesiology, Rehabiliation, and Neuroscience) and also the Kawato Dynamic Brain Project at ATR in Japan. The Ph.D. graduate students will receive a Research Assistantship and join and interdisciplinary team of researchers to work on topics of movement imitation, developing graphical simulations for motor control, movement rehabilitation with stroke-patients, models of human motor control and learning, and computational neuroscience for motor control in general. In the course of this work, a Ph.D. can be obtained in either Computer Science (with focus Neural Computation), Biomedical Engineering, Computational Neuroscience, or Biokinesiology and Physical Therapy. The successful candidate should have a good background in basic mathematics and statistics and a strong interest in the topics of motor control and computational neuroscience. Experimental skills are highly desirable, and proficiency in the use of computers, C-programming, and use of tools like Matlab and Mathematica are needed. The candidate will be required to pass the graduate admission of the department of her/his choice. The openings will be filled ASAP. Please, contact Dr. Ijspeert (ijspeert at usc.edu), Dr. Schaal (sschaal at usc.edu), or Dr. Winstein (winstein at hsc.usc.edu) for inquiries. An official application including an up-to-date CV, statement of interest, transcripts, and three letters of recommendation will be required and sent to: Dr Auke Ijspeert University of Southern California Hedco Neuroscience Bdg, 3641 Watt Way, MC 2520 Los Angeles, CA 90089-2520, USA Please, also visit our web pages at: http://www-slab.usc.edu From luciano at if.sc.usp.br Fri Dec 22 12:15:51 2000 From: luciano at if.sc.usp.br (Luciano Da Fontoura Costa) Date: Fri, 22 Dec 2000 15:15:51 -0200 (EDT) Subject: research opportunities Message-ID: Dear Sir/Madam: Please help disseminating the following message: ==================================================================== *** OPPORTUNITY FOR POST-GRAD, POST-DOC AND SABBATICAL STUDIES *** *** FOR 2001 *** COMPUTER VISION VISUAL INSPECTION PATTERN RECOGNITION DATAMINING DIGITAL SIGNAL PROCESSING NEUROMORPHIC MODELING NEUROMORPHOMETRY SHAPE ANALYSIS BIOINFORMATICS Cybernetic Vision Research Group IFSC, University of Sao Paulo, Caixa Postal 369 Sao Carlos, SP, 13560-970, Brazil http://cyvision.if.sc.usp.br/ ____________________________________________________________________ THE CYBERNETIC VISION RESEARCH GROUP: Started in 1993, the Cybernetic Vision Research Group has become nationally and internationally renowned for research in the areas of shape analysis, computer and biological vision, and computational neuroscience. The group currently includes 15 researchers, most of them MSc and PhD students, each with access to individual computational resources. The group is part of the Instituto de Fisica de Sao Carlos, which has modern computational and network resources (alpha workstations) as well as a well-equipped library. The group has many collaborators and has an active participation in publishing and consulting, including major companies and publishers. Additional information can be found at the following homepages: *** Group homepage: http://cyvision.if.sc.usp.br/ *** Luciano's personal homepage: http://www.if.sc.usp.br/visao/group/members/luciano/luciano.htm SAO CARLOS: Sao Carlos, where the group is based, is a small and quiet town (about 150 000 inhabitants) in the heart of the state of Sao Paulo, in Brazil. The university campus is within a residential area, where accommodation is very affordable. Our town, which includes two major Brazilian universities as well as many industries, is know as one of the most prominent Brazilian high-technology centers. Sao Carlos is not far from Sao Paulo (230km), the state capital, where flights to most Brazilian and international destinations can be found. Weather is mild (no snow throughout the year), with an average temperature around 20C. RESEARCH POSSIBILITIES: Well-motivated and dynamic students and researchers, with background in the most diverse areas - including Physics, Mathematics, Computer Science, Engineering, Biology, and Medicine - are welcome to apply for studies in the group. The full time MSc and PhD programs last up to 2 and 4 years, respectively, but it is possible to proceed directly to PhD. Post-doc and sabbatical programs can last from a few months to one year or more. It is possible to apply for Brazilian sponsorship covering travelling and/or the basic living expenses. The approximated grant values are as follows (please note these are maximum values that can vary substantially depending on the exchange rate and grant sponsor): Master (1st year): US$ 500 per month Master (2nd year): US$ 520 per month PhD (initial years): US$ 700 per month PhD (initial years): US$ 850 per month Post-Doc: US$ 1250 per month Living expenses can be as low as US$ 150 per month (shared accomodation near the university). Medical assistance and is available free of charge for some student categories. All the above courses are free and involve no bech or other fees. Research possibilities include but are not limited to the following: *1* Neuromorphology and neuromorphic modeling: development of new neural shape measures, validation, and application to classification of neural cells and neuromorphic modeling. We are particularly interested in investigating how neural shapes constrain and help define neural behavior; *2* Scale space shape representations in 2D and 3D, including multiresolution curvature and skeletonization, singularity theory, differential geometry and differential equations; *3* Visual inspection and image analysis applied to microscopy; *4* Mathematical physics applications to image analysis and vision; *5* Datamining and its applications to visual design, visual quality assessment, bioinformatics, neural modeling, and shape analysis. Well-motivated candidates should contact Prof Luciano da F. Costa at luciano at if.sc.usp.br, indicating the specific interests and including curricular information as well as at least two addresses for recommendation purposes. Please observe there is a limited number of places, to be filled according to the students previous performance and research interests. ===================================================================== Prof. Luciano da Fontoura Costa Coordinator - Cybernetic Vision Research Group DFI-IFSC, Universidade de Sao Paulo Caixa Postal 369 Sao Carlos, SP 13560-970 Brazil FAX: +55 162 73 9879 or +55 162 71 3616 e-mail: luciano at if.sc.usp.br Group homepage: http://cyvision.if.sc.usp.br/ Personal homepage: http://cyvision.if.sc.usp.br/~luciano --------------------------------------------------------------------- The forthcoming book "Shape Analysis and Classification" (CRC Press) can already be ordered from Amazon: http://www.amazon.com/exec/obidos/ASIN/0849334934/o/qid=970355824/ sr=8-1/ref=aps_sr_b_1_3/002-1526960-8848802 See also: http://www.ime.usp.br/~cesar/shape_crc/ ===================================================================== END OF MESSAGE ============== From shai at cs.Technion.AC.IL Wed Dec 27 07:46:26 2000 From: shai at cs.Technion.AC.IL (Shai Ben-David) Date: Wed, 27 Dec 2000 14:46:26 +0200 (IST) Subject: Workshop on Computational Complexity of Learning Message-ID: <200012271246.OAA18200@cs.Technion.AC.IL> Alpine Workshop on Computational Complexity Aspects of Learning. March 26-29, 2001. Sestriere, Italy. While being recognized as an important component of Computational Learning, the computational complexity of learning has seen very few definite answers (as opposed to the pretty clear picture that we have of sample complexity and generalization issues). The aim of the workshop is to bring together active researchers in the COLT area to outline the current knowledge on these questions, and to stimulate ideas for further research. The workshop will include three invited talks, by Avrim Blum, Sanjoy Dasgupta and Phil Long, as well as an inroductory tutorial. Most of the time will be devoted to contributed talks by the workshop participants. We plan to have morning sessions and afternoon sessions with generous ski breaks between them. The workshop will be held in Sestriere (www.stm.it/sestriere), one of the most famous Italian ski resorts, located in the Western Alps. To participate, please complete the registration form below and send it to Nicolo` Cesa-Bianchi (cesabian at dsi.unimi.it) before January 20, 2001. Registration fees are 50eu per person. If you want to buy a ski-pass at a discounted price, please check the box in the registration form. We have made an arrangement with "Hotel Biancaneve", Via Cesana, 12. Sestriere, +39-0122-755176. To book a room there please send a fax *BEFORE JANUARY 20* at +39-0122-755152 mentioning "Neurocolt" as group name and including a credit card number for the deposit. The rates (half-board) are: Single room from 3/25 to 3/29 (4 nights): ITL 440,000 per person Double room from 3/25 to 3/29(4 nights): ITL 300,000 per person Extra days: ITL 115,000 (single) and ITL 80,000 (double) You are welcome to contact us for any further information Nicolo' (cesabian at dsi.unimi.it) and Shai (shai at cs.technion.ac.il) ---------------------------------------------------------------- NeuroCOLT Workshop at Sestriere - Registration Form (mail to: cesabian at dsi.unimi.it) =================================================== First name: Last name: Affiliation: Email: Arrival date: Departure date: Giving a talk (yes/no): Title of the talk: Skipass (yes/no): From juergen at idsia.ch Wed Dec 27 10:47:37 2000 From: juergen at idsia.ch (juergen@idsia.ch) Date: Wed, 27 Dec 2000 16:47:37 +0100 Subject: inductive inference, fast computations, Kolmogorov, Occam Message-ID: <200012271547.QAA21385@ruebe.idsia.ch> We generalize Kolmogorov complexity and study the fastest way of computing all computable objects, with consequences for inductive inference, Occam's razor, and the big picture. This might be of interest to machine learners, theoretical computer scientists, mathematicians, physicists, and philosophers. All comments are welcome. Algorithmic Theories of Everything Juergen Schmidhuber http://www.idsia.ch/~juergen The probability distribution P from which the history of our universe is sampled represents a theory of everything or TOE. We assume P is formally describable. Since most (uncountably many) distributions are not, this imposes a strong inductive bias. We show that P(x) is small for any universe x lacking a short description, and study the spectrum of TOEs spanned by two Ps, one reflecting the most compact constructive descriptions, the other the fastest way of computing everything. The former derives from generalizations of traditional computability, Solomonoff's algorithmic probability, Kolmogorov complexity, and objects more random than Chaitin's "number of wisdom" Omega, the latter from Levin's universal search and a natural resource-oriented postulate: the cumulative prior probability of all x incomputable within time t by this optimal algorithm should be 1/t. Between both Ps we find a universal cumulatively enumerable measure that dominates traditional enumerable measures; any such CEM must assign low probability to any universe lacking a short enumerating program. We derive P-specific consequences for observers evolving in computable universes, inductive reasoning, quantum physics, and philosophy, predicting that whatever seems random (e.g., beta decay) is not, but in fact is computed by a short and fast algorithm which will probably halt before our universe is many times older than it is now. ------------------------------------------------------------------------ TR IDSIA-20-00, Version 2.0, 20 Dec 2000; 10 theorems, 50 pages, 100 refs (minor revision of 1.0, Nov 2000, http://arXiv.org/abs/quant-ph/0011122) ftp://ftp.idsia.ch/pub/juergen/toesv2.ps.gz (gzipped postscript, 156K) ftp://ftp.idsia.ch/pub/juergen/toesv2.ps (postscript, 515K) ftp://ftp.idsia.ch/pub/juergen/toesv2.tex.gz (gzipped latex, 52K) ftp://ftp.idsia.ch/pub/juergen/toesv2.tex (latex, 155K) ftp://ftp.idsia.ch/pub/juergen/toesv2.dvi.gz (gzipped dvi, 91K) ftp://ftp.idsia.ch/pub/juergen/toesv2.dvi (dvi, 244K) ftp://ftp.idsia.ch/pub/juergen/toesv2.pdf.gz (gzipped pdf, 395K) ftp://ftp.idsia.ch/pub/juergen/toesv2.pdf (pdf, 539K) http://www.idsia.ch/~juergen/onlinepub.html (various formats) PS: I am also seeking two new postdocs, please see the announcement in http://www.idsia.ch/~juergen/postdocs2001.html From patrickw at cs.monash.edu.au Wed Dec 27 22:48:28 2000 From: patrickw at cs.monash.edu.au (Patrick Wilken) Date: Thu, 28 Dec 2000 13:48:28 +1000 Subject: CFP: ASSC5 - The Contents of Consciousness Message-ID: ASSOCIATION FOR THE SCIENTIFIC STUDY OF CONSCIOUSNESS 5TH ANNUAL MEETING CALL FOR PAPERS & WORKSHOPS THE CONTENTS OF CONSCIOUSNESS Perception, Attention, and Phenomenology May 27-30, 2001 Duke University Durham, North Carolina, USA Consciousness has rich and diverse contents, from sensory experiences such as vision, audition, and bodily sensations such as pain, to non-sensory aspects such as volition, emotion, memory, and thought. All of these conscious states can be seen as part of the contents of consciousness. Furthermore, most conscious states can be seen as having representational contents of their own, in the sense that they are about something: objects and states of affairs in the world, or states of our own body. The contents of these states are all presented to us, in William James's powerful metaphor, as part of a "stream of consciousness". The contents of consciousness raise many important questions: Just how rich is the content present in conscious experience? Do the contents of attention exhaust the contents of consciousness, or is there consciousness outside attention? What is the neural basis of the representation of conscious content? How does consciousness of our own body differ from consciousness of the external world? What methods are available to monitor the contents of consciousness in an experimental context? What is the relationship between consciousness and representation? All of these questions have been actively discussed in recent years by neuroscientists, psychologists, philosophers, and other researchers. The fifth conference of the Association for the Scientific Study of Consciousness will bring together researchers from numerous disciplines to discuss the contents of consciousness through an intensive series of workshops, plenary lectures, symposia, paper presentations and poster contributions extending over four days from May 27 through May 30, 2001. The meeting will take place in Durham, North Carolina, on the campus of Duke University. Topics that will be addressed include (among many others): * The relationship between attention and consciousness * The neural basis of attention and consciousness * The neural mechanisms of conscious representation * Current directions in inattentional and change blindness * The relationship between conscious and unconscious contents * Bodily awareness and pain perception * The relationship between consciousness, qualia, and representation * First-person and third-person methods for monitoring conscious contents A partial list of plenary speakers (to be expanded) includes: Larry Weiskrantz (OXFORD, Experimental Psychology) Earl Miller (MIT, Brain and Cognitive Sciences) Greg McCarthy (DUKE, Brain Imaging and Analysis Center) Ralph Adolphs (IOWA, Neurology) Jeremy Wolfe (HARVARD, Center for Ophthalmic Research) Ron Rensink (UBC, Psychology and Computer Science) Owen Flanagan (DUKE, Philosophy) William Lycan (UNC, Philosophy) For latest updates, please check our website: http://www.duke.edu/philosophy/assc5.html The web site will be continually evolving, so please visit often for updated information about the conference. -------------------------- CALL FOR PAPER SUBMISSIONS -------------------------- Although the main theme of ASSC5 is "The Contents of Consciousness" and plenary sessions will deal largely with this theme, speakers in concurrent sessions are invited to talk on any topic relevant to the scientific study of consciousness. Submissions that include physiological, psychological, philosophical, and computational perspectives are welcome. Submissions for both posters and talks will be accepted. Any person may present only one submission, but may be co-author on several. The first author should be the presenting author. Oral presentations will be limited to 20 minutes, to be followed by a 10-minute discussion period. Plenary lectures, symposia, concurrent sessions, and poster sessions will all be held on the Duke University campus. --------------------------- CALL FOR WORKSHOP PROPOSALS --------------------------- This is also a call for workshops. One of the aims of this meeting is to allow researchers to gain a background in areas that they may know little about. Towards that end a number of workshops are planned. Some participants in the conference would be very interested in learning about technical matters such as fMRI or other important brain imaging techniques. Others might enjoy a seminar on a philosophical topic. As with papers, the focus of all workshops should naturally fit within the overall theme of the conference. A non-exclusive list of possible topics might include: -- Brain imaging techniques (e.g. fMRI, EEG, MEG, ERP) -- Blindsight, neglect, or other neuropsychological syndromes -- Computational and other theoretical models of conscious processes -- Conscious and unconscious processing -- Neural basis of attention and consciousness -- Current models of the visual system -- Consciousness and metacognition -- Criteria for the ascription of consciousness -- Philosophical issues concerning consciousness and representation -- Phenomenological methods for investigating consciousness Workshops will be held in parallel sessions on the morning and afternoon of May 27th. Each workshop is intended to last approximately three hours. The sizes of workshops will vary between a minimum of 10 to a maximum of around 25 people. Workshops that do not achieve the minimum enrollment of 10 people will not be offered. Workshop presenters will receive a $500 honorarium. ----------------------------------------- SUBMISSION OF PAPERS & WORKSHOP PROPOSALS ----------------------------------------- WORKSHOP PROPOSALS MUST BE RECEIVED BY JANUARY 31, 2001. Send Workshop presentation abstracts to: metzinger at uni-mainz.de PAPER SUBMISSIONS MUST BE RECEIVED BY FEBRUARY 15th, 2001. Send Oral (paper) or Poster presentation abstracts to: assc5 at duke.edu All submissions must include the following information in the order listed below and MUST BE SUBMITTED ELECTRONICALLY. Please note that there are two different addresses for paper and workshop proposal submissions: *** Note: Please reserve these addresses exclusively for submission of abstracts. Questions concerning the conference can be sent to: fb3 at duke.edu --------------------- SUBMISSION GUIDELINES --------------------- 1. Conference ID (i.e., ASSC5), SURNAME of first author and descriptor (WORKSHOP or PAPER/POSTER) in the "subject" field of the email header. e.g.: ASSC5, Smith, WORKSHOP 2. Name (first line), affiliation (second line), and ASSC membership status of each co-author indicated with asterisk (asterisk = member). e.g.: Smith, A.B.* and Jones, C.D. University of Oxford, U.K. 3. An abstract of up to 200 words for paper and poster submissions or of up to 500 words for workshop proposals. 4. Complete contact information for the author with whom the scientific program committee will interact with about the submission: - Name - Institutional affiliation - Postal address - Email address - Telephone and fax numbers In addition paper and poster proposals should include the following information: 5. One or two keywords describing the domain of your contribution 6. An indication of whether an ORAL or POSTER presentation is requested. 7. An indication of your willingness to present in the other format if your proposal cannot be included in the program as per your stated preference. 8. If you do not receive confirmation of receipt of your submission in 10 days, send an e-mail inquiry to: fb3 at duke.edu. ------------ REGISTRATION ------------ Deadline for early registration: April 1, 2001. Registration fees: Early Late Non-members: $ 175 $ 225 ASSC members: $ 140 $ 190 Students/Postdocs: $ 75 $ 125 Student ASSC members: $ 40 $ 90 Note: All fees should be paid in U.S. dollars. Payment with credit cards will be possible. To register, please follow the instructions available from the conference website as they become available: http://www.duke.edu/philosophy/assc5.html ------------------- FURTHER INFORMATION ------------------- All meetings and poster presentations will be held at the Duke University campus. Accommodations will be available both at Durham hotels at discounted rates and at air-conditioned single/double Duke dormitories. Please check the website for information about accommodation options, as well as for further information about the paper and poster submissions; registration and submission forms; information about travel to Durham, North Carolina; and information about the scientific Program of the meeting. Tune in frequently -- the site will be constantly updated to reflect the latest information. To inquire about any aspect of the conference, please write to the local organizer at: fb3 at duke.edu To find out more about the Association for the Scientific Study of Consciousness, and to apply for membership, please consult: http://assc.caltech.edu The ASSC publishes two scientific journals about which further information is available from the following websites: Consciousness & Cognition: http://www.apnet.com/www/journal/cc.htm PSYCHE: http://psyche.cs.monash.edu.au/ ASSC-5 Conference Committee: Guven Guzeldere (Duke University, co-chair) Ron Mangun (Duke University, co-chair) David Chalmers (University of Arizona) Philip Merikle (University of Waterloo) Thomas Metzinger (Johannes Gutenberg-Universitat Mainz) From Marc.VanHulle at med.kuleuven.ac.be Thu Dec 28 07:46:30 2000 From: Marc.VanHulle at med.kuleuven.ac.be (Marc Van Hulle) Date: Thu, 28 Dec 2000 13:46:30 +0100 Subject: postdoc in biomedical signal-processing and neuroimaging Message-ID: <3A4B3626.C95895A1@neuro.kuleuven.ac.be> ------------------------------------------------------------------- Postdoctoral position biomedical signal-processing and neuroimaging ------------------------------------------------------------------- Deadline for application: 30 January 2001 The Computational Neuroscience Group of the Laboratory of Neuro- and Psychophysiology, Medical School of the Catholic University of Leuven, Belgium (http:\\simone.neuro.kuleuven.ac.be), invites applications for a post-doctoral position in the area of biomedical signal-processing and neuroimaging (functional Magnetic Resonance Imaging). Desired profile: The highly qualified applicant should possess a Ph.D. degree in the field of signal-processing, image-processing, statistics, or neural networks. He/she should be familiar with Independent Components Analysis (ICA), and have a profound knowledge of both uni-variate statistics and multi-variate statistics. Programming skills are an asset (C, Matlab, ...), as is a familiarity with UNIX and PC platforms. We offer: 1) A challenging research environment. The applicant will have access to data from state-of-the-art Magnetic Resonance scanners and advanced statistical tools such as SPM (Statistical Parameter Mapping) for examining brain activity in both human and monkey. 2) An attractive income. The applicant will receive 2000 USD or 2375 Euro per month, including a full social security coverage. This is comparable to the salary of an associate Professor at the University. Housing will be taken care of by the host institute. 3) Free return airline ticket, economy class (maximum 1250 USD or 1500 Euro) and a reimbursement of all costs incurred for shipping luggage to Belgium (maximum 850 USD or 1000 Euro). Send before the deadline of 15 January 2001 your CV (including the names and contact information of three references), bibliography and how to contact you by mail/fax/email/phone to: Prof. Dr. Marc M. Van Hulle K.U.Leuven Laboratorium voor Neuro- en Psychofysiologie Faculteit Geneeskunde Campus Gasthuisberg Herestraat 49 B-3000 Leuven Belgium Phone: + 32 16 345961 Fax: + 32 16 345993 E-mail: marc at neuro.kuleuven.ac.be URL: http://simone.neuro.kuleuven.ac.be From gjm at maths.uq.edu.au Sun Dec 3 22:14:32 2000 From: gjm at maths.uq.edu.au (Geoff McLachlan) Date: Mon, 4 Dec 2000 13:14:32 +1000 (EST) Subject: New Wiley book on Mixture Models Message-ID: <200012040314.NAA19161@fisher.maths.uq.edu.au> Announcing the recent publication of the Wiley monograph ... Title: FINITE MIXTURE MODELS Authors: Geoff McLachlan and David Peel This book gives an up-to-date, comprehensive account of the major issues in modeling via finite mixture distributions. Links statistical literature with the machine learning and pattern recognition literature in the related areas. Considers how the EM algorithm can be scaled to handle the fitting of mixture models to very large databases, as in data mining applications. Provides more than 800 references -- 40% published since 1995. FOR MORE INFORMATION SEE http://www.maths.uq.edu.au/~gjm From tgd at cs.orst.edu Sun Dec 3 23:01:06 2000 From: tgd at cs.orst.edu (Thomas G. Dietterich) Date: Sun, 3 Dec 2000 20:01:06 -0800 Subject: JAIR: MAXQ Hierarchical Reinforcement Learning Message-ID: <3556-Sun03Dec2000200106-0800-tgd@cs.orst.edu> JAIR is pleased to announce the publication of the following article: Dietterich, T.G. (2000) "Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition", Volume 13, pages 227-303. Available in PDF, PostScript and compressed PostScript. For quick access via your WWW browser, use this URL: http://www.jair.org/abstracts/dietterich00a.html More detailed instructions are below. Abstract: This paper presents a new approach to hierarchical reinforcement learning based on decomposing the target Markov decision process (MDP) into a hierarchy of smaller MDPs and decomposing the value function of the target MDP into an additive combination of the value functions of the smaller MDPs. The decomposition, known as the MAXQ decomposition, has both a procedural semantics---as a subroutine hierarchy---and a declarative semantics---as a representation of the value function of a hierarchical policy. MAXQ unifies and extends previous work on hierarchical reinforcement learning by Singh, Kaelbling, and Dayan and Hinton. It is based on the assumption that the programmer can identify useful subgoals and define subtasks that achieve these subgoals. By defining such subgoals, the programmer constrains the set of policies that need to be considered during reinforcement learning. The MAXQ value function decomposition can represent the value function of any policy that is consistent with the given hierarchy. The decomposition also creates opportunities to exploit state abstractions, so that individual MDPs within the hierarchy can ignore large parts of the state space. This is important for the practical application of the method. This paper defines the MAXQ hierarchy, proves formal results on its representational power, and establishes five conditions for the safe use of state abstractions. The paper presents an online model-free learning algorithm, MAXQ-Q, and proves that it converges with probability 1 to a kind of locally-optimal policy known as a recursively optimal policy, even in the presence of the five kinds of state abstraction. The paper evaluates the MAXQ representation and MAXQ-Q through a series of experiments in three domains and shows experimentally that MAXQ-Q (with state abstractions) converges to a recursively optimal policy much faster than flat Q learning. The fact that MAXQ learns a representation of the value function has an important benefit: it makes it possible to compute and execute an improved, non-hierarchical policy via a procedure similar to the policy improvement step of policy iteration. The paper demonstrates the effectiveness of this non-hierarchical execution experimentally. Finally, the paper concludes with a comparison to related work and a discussion of the design tradeoffs in hierarchical reinforcement learning. The article is available via: -- comp.ai.jair.papers (also see comp.ai.jair.announce) -- World Wide Web: The URL for our World Wide Web server is http://www.jair.org/ For direct access to this article and related files try: http://www.jair.org/abstracts/dietterich00a.html -- Anonymous FTP from either of the two sites below. Carnegie-Mellon University (USA): ftp://ftp.cs.cmu.edu/project/jair/volume13/dietterich00a.ps The University of Genoa (Italy): ftp://ftp.mrg.dist.unige.it/pub/jair/pub/volume13/dietterich00a.ps The compressed PostScript file is named dietterich00a.ps.Z (464K) For more information about JAIR, visit our WWW or FTP sites, or contact jair-ed at isi.edu From robtag at unisa.it Mon Dec 4 05:44:35 2000 From: robtag at unisa.it (Roberto Tagliaferri) Date: Mon, 04 Dec 2000 11:44:35 +0100 Subject: Call for papers WIRN 2001 Message-ID: <3A2B7593.A08CB19C@dia.unisa.it> The 12-th Italian Workshop on Neural Nets WIRN VIETRI-2001 May 17-19, 2001,Vietri Sul Mare, Salerno ITALY CALL FOR PAPERS - FIRST ANNOUNCEMENT Organizing - Scientific Committee B. Apolloni (Univ. Milano), A. Bertoni (Univ. Milano), N. A. Borghese (CNR Milano), D. D. Caviglia (Univ. Genova), P. Campadelli (Univ. Milano), A. Chella (Univ. Palermo), A. Colla (ELSAG Genova), A. Esposito (I.I.A.S.S.), M. Frixione (Univ. Salerno), C. Furlanello (ITC-IRST Trento), G. M. Guazzo (I.I.A.S.S.), M. Gori (Univ. Siena), F. Lauria (Univ. Napoli), M. Marinaro (Univ. Salerno), F. Masulli (Univ. Genova), C. Morabito (Univ. Reggio Calabria), P. Morasso (Univ. Genova), G. Orlandi (Univ. Roma), T. Parisini (Politecnico Milano), E. Pasero (Politecnico Torino), A. Petrosino (I.I.A.S.S.), V. Piuri (Politecnico Milano), R. Serra (CRA Montecatini Ravenna), F. Sorbello (Univ. Palermo), R. Tagliaferri (Univ. Salerno) Topics Mathematical Models, Architectures and Algorithms, Hardware and Software Design, Hybrid Systems, Pattern Recognition and Signal Processing, Industrial and Commercial Applications, Fuzzy Tecniques for Neural Networks Schedule Papers Due: January 31, 2001 Replies to Authors: March 31, 2001 Revised Papers Due: May 19, 2001 Sponsors International Institute for Advanced Scientific Studies (IIASS) "E.R. Caianiello") Dept. of Scienze Fisiche "E.R. Caianiello", University of Salerno Dept. of Matematica ed Informatica, University of Salerno Dept. of Scienze dell'Informazione, University of Milano Societa' Italiana Reti Neuroniche (SIREN) IEEE Neural Network Council INNS/SIG Italy Istituto Italiano per gli Studi Filosofici, Napoli The three-day conference, to be held in the I.I.A.S.S., will feature both introductory tutorials and original, refereed papers, to be published by an International Publishing. Official languages are Italian and English, while papers must be in English. Papers should be 6 pages, including title, figures, tables, and bibliography. The accompanying letter should give keywords, postal and electronic mailing addresses, telephone and FAX numbers, indicating oral or poster presentation. Submit 3 copies and a 1 page abstract (containing keywords, postal and electronic mailing addresses, telephone, and FAX numbers with no more than 300 words) to the address shown (WIRN 2001 c/o IIASS). An electronic copy of the abstract should be sent to the E-mail address below. During the Workshop the "Premio E.R. Caianiello" will be assigned to the best Ph.D. thesis in the area of Neural Nets and related fields of Italian researchers. The amount is of 2.000.000 Italian Lire. The interested researchers (with the Ph.D degree got in 1998,1999,2000 until February 28 2001) must send 3 copies of a c.v. and of the thesis to "Premio Caianiello" WIRN 2001 c/o IIASS before February 28,2001. It is possible to partecipate to the prize at most twice and the association to SIREN is required (modules can be downloaded from the SIREN site). For more information, contact the Secretary of I.I.A.S.S. "E.R. Caianiello", Via G.Pellegrino, 19, 84019 Vietri Sul Mare (SA), ITALY Tel. +39 89 761167 Fax +39 89 761189 E-Mail robtag at unisa.it or the SIREN www pages at: http://www-dsi.ing.unifi.it/neural -------------- next part -------------- A non-text attachment was scrubbed... Name: robtag.vcf Type: text/x-vcard Size: 245 bytes Desc: Card for Roberto Tagliaferri Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/00000000/735b491f/robtag-0001.vcf From Sebastian_Thrun at heaven.learning.cs.cmu.edu Mon Dec 4 08:25:40 2000 From: Sebastian_Thrun at heaven.learning.cs.cmu.edu (Sebastian Thrun) Date: Mon, 04 Dec 2000 08:25:40 -0500 Subject: Faculty Opportunities at CMU Message-ID: The School of Computer Science at Carnegie Mellon University is seeking applications for tenure track positions in all areas related to data and text mining, statistics, and machine learning. We are looking for candidates with excellent research and teaching records and a strong commitment to cross-disciplinary research. Other areas of interest to the School include algorithms, computer graphics, computer systems, human computer interaction, robotics, and software engineering. The starting date can be as early as July 1, 2001. Priority will be given to applications received before February 15, 2001. To apply please send a C.V., statement of research and teaching interests, copies of 1-3 representative papers, and the names of at least three references to: Faculty Search Committee ATTENTION: Sharon Burks School of Computer Science Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA 15213-3891 The applicant should request their references to forward a letter of reference directly to the same address to arrive before February 15, 2001. These letters will NOT be requested directly by the department. Electronic applications and reference letters (in postscript or .pdf format) may be directed to: faculty-search at cs.cmu.edu Carnegie Mellon is an affirmative action/equal opportunity employer, who encourages applications from women and minorities. More information can be found at at http://www.cs.cmu.edu/afs/cs/usr/burks/www/facultysearch.html From cindy at cns.bu.edu Mon Dec 4 15:17:13 2000 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Mon, 4 Dec 2000 15:17:13 -0500 Subject: Neural Networks 13(8/9) Message-ID: <200012042017.PAA12870@retina.bu.edu> NEURAL NETWORKS 13(8/9) Special Issue on "The Global Brain: Imaging and Neural Modelling" Contents - Volume 13, Numbers 8/9 - 2000 ------------------------------------------------------------------ Editorial J.G. Taylor Neural modeling and functional brain imaging: An overview B. Horwitz, K.J. Friston, and J.G. Taylor Imaging and neural modelling in episodic and working memory processes B.J. Krause, J.G. Taylor, D. Schmidt, H. Hautzel, F.M. Mottaghy, and H.-W. Mueller-Gaertner Towards a network theory of cognition A.R. McIntosh Assessing interactions among neuronal systems using functional neuroimaging C. Buchel and K. Friston Tracking functions of cortical networks on a millisecond timescale V. Jousmaki Independence: A new criterion for the analysis of the electromagnetic fields in the global brain? R. Vigario and E. Oja Connectivity and complexity: The relationship between neuroanatomy and brain dynamics O. Sporns, G. Tononi, and G.M. Edelman Decomposing memory: Functional assignments and brain traffic in paired word associate learning J.G. Taylor, B. Horwitz, N.J. Shah, W.A. Fellenz, H.-W. Mueller-Gaertner, and J.B. Krause A model of working memory: Bridging the gap between electrophysiology and human brain imaging M.-A. Tagamets and B. Horwitz A neural model of working memory processes in normal subjects, Parkinson's disease, and schizophrenia for fMRI design and predictions O. Monchi, J.G. Taylor, and A. Dagher Synthetic brain imaging: Grasping, mirror neurons, and imitation M.A. Arbib, A. Billard, M. Iacoboni, and E. Oztop A neural model of cortico-cerebellar interactions during attentive imitation and predictive learning of sequential handwriting movements S. Grossberg and R.W. Paine Towards a neural network based therapy for hallucinatory disorders J.R. Pelaez ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 or 660 SEK or Y 15,000 [including Neural Networks 2,000 entrance fee] or $55 (student) 460 SEK (student) Y 13,000 (student) [including 2,000 entrance fee] ----------------------------------------------------------------------------- membership without $30 200 SEK not available to Neural Networks non-students (subscribe through another society) Y 5,000 (student) [including 2,000 entrance fee] ----------------------------------------------------------------------------- Institutional rates $1132 2230 NLG Y 149,524 ----------------------------------------------------------------------------- Name: _____________________________________ Title: _____________________________________ Address: _____________________________________ _____________________________________ _____________________________________ Phone: _____________________________________ Fax: _____________________________________ Email: _____________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number ____________________________ expiration date ________________________ INNS Membership 19 Mantua Road Mount Royal NJ 08061 USA 856 423 0162 (phone) 856 423 3420 (fax) innshq at talley.com http://www.inns.org ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership c/o Professor Tsukada Faculty of Engineering Tamagawa University 6-1-1, Tamagawa Gakuen, Machida-city Tokyo 113-8656 Japan 81 42 739 8431 (phone) 81 42 739 8858 (fax) jnns at jnns.inf.eng.tamagawa.ac.jp http://jnns.inf.eng.tamagawa.ac.jp/home-j.html ----------------------------------------------------------------- From maasen at mpipf-muenchen.mpg.de Mon Dec 4 10:53:51 2000 From: maasen at mpipf-muenchen.mpg.de (Sabine Maasen) Date: Mon, 4 Dec 2000 16:53:51 +0100 Subject: Job Announcement MPI for Psychological Research Message-ID: THE MAX PLANCK INSTITUTE FOR PSYCHOLOGICAL RESEARCH, MUNICH, GERMANY invites applications for the following positions in the newly established Junior Research Group "Cognitive Robotics": 1 postdoctoral researcher (5-year appointment, salary appr. DEM 71k p.a.) 2 doctoral students (3-year appointment, salary appr. DEM 71k or DEM 35k p.a.) The group will study novel, behavior-based approaches to visual perpection, specifically approaches to functional categorization based on anticipation of the sensory consequences of actions. Artificial neural network techniques will be used for learning sensorimotor associations during the interaction with the environment. Models will be implemented on mobile robots and robot arms and tested in the real world. Candidates should have a background in cognitive science, computational vision, neural network theory, and robotics, as well as strong technical and computer skills. Earliest starting date for all positions is January 1, 2001. Applications are accepted until the positions are filled. The Max Planck Institute is an equal-opportunity employer and especially encourages women to apply. Please send full CV, complete academic records, statement of interests, and the names and email addresses of two academic referees to: Administration Max Planck Institute for Psychological Research Amalienstr. 33, D-80799 Munich, Germany web site: http://www.mpipf-muenchen.mpg.de For further information, please contact: Dr. Ralf Moeller, email: moeller at mpipf-muenchen.mpg.de -- ------------------------------------------------- Dr. Sabine Maasen ++ Forschungsreferentin / research coordinator ++ Max-Planck-Institut fuer psychologische Forschung Amalienstr.33 +++ 80799 Muenchen Tel +49 89 38602-251 +++ Fax -290 email: maasen at mpipf-muenchen.mpg.de homepage:http://www.mpipf-muenchen.mpg.de/~maasen ------------------------------------------------- From tim.sibley at streamsage.com Mon Dec 4 13:28:18 2000 From: tim.sibley at streamsage.com (Tim V. Sibley) Date: Mon, 04 Dec 2000 13:28:18 -0500 Subject: Research position in spoken language modeling at StreamSage Message-ID: <200012041848.eB4Imls99359@ren-5.cais.net> RESEARCH POSITION AVAILABLE StreamSage, Inc. Speech Interpretation Laboratory _____ A lead research position is available immediately (starting date flexible) in the speech interpretation laboratory at StreamSage. Research focuses on time-based modeling of spoken language for the purpose of automated digital media manipulation via intelligent, adaptive algorithms, neural networks, and rule-based frameworks. The candidate should have a strong background in neural networks and computational linguistics. A sufficiently independent spirit is necessary for use within a young startup that develops state-of-the-art technology. Familiarity with Java is a plus. Proficient knowledge of the English language is required. Compensation will be commensurate with level of experience. Please send resume, 2 recommendations, and representative publications to the address listed below, or inquire with any questions or comments. E-mail inquiries and applications are encouraged. _____ Tim V. Sibley tim.sibley at streamsage.com StreamSage, Inc. 1900 M St. NW Suite 810 Washington, DC 20036 phone: 202.833.8050 fax: 360.838.7203 From kap-listman at wkap.nl Tue Dec 5 20:17:25 2000 From: kap-listman at wkap.nl (kap-listman@wkap.nl) Date: Wed, 06 Dec 2000 02:17:25 +0100 (MET) Subject: New Issue: Neural Processing Letters. Vol. 12, Issue 3 Message-ID: <200012060117.CAA22275@wkap.nl> Kluwer ALERT, the free notification service from Kluwer Academic/PLENUM Publishers and Kluwer Law International ------------------------------------------------------------ Neural Processing Letters ISSN 1370-4621 http://www.wkap.nl/issuetoc.htm/1370-4621+12+3+2000 Vol. 12, Issue 3, December 2000. TITLE: Self-Organization by Temporal Inhibition (SOTI) AUTHOR(S): P. Martin-Smith, F. J. Pelayo, E. Ros, A. Prieto KEYWORD(S): temporal inhibition, competitive learning, self-organizing maps, learning vector quantization. PAGE(S): 199-213 TITLE: Parametric Amplification of Signals by Noise in Neurons and Neural Networks AUTHOR(S): Yu. I. Balkarey, V. O. Nagoutchev, M. G. Evtikhov, M. I. Elinson KEYWORD(S): amplification of signals in neural networks (NN), positive role of parametric noise in NN, spike trains and noise. PAGE(S): 215-223 TITLE: Using a Neural Network to Approximate an Ensemble of Classifiers AUTHOR(S): X. Zeng, T. R. Martinez KEYWORD(S): approximator, bagging, boosting, ensemble of classifiers, neural networks. PAGE(S): 225-237 TITLE: An Analysis of the Fundamental Structure of Complex-Valued Neurons AUTHOR(S): Tohru Nitta KEYWORD(S): complex numbers, complex-valued neurons, learning, decision boundary. PAGE(S): 239-246 TITLE: On the Internal Representations of Product Units AUTHOR(S): Jung-Hua Wang, Yi-Wei Yu, Jia-Horng Tsai KEYWORD(S): product unit, internal representations, recurrent neural networks, perceptrons, backpropagation training. PAGE(S): 247-254 TITLE: A Direct Link Minimal Resource Allocation Network for Adaptive Noise Cancellation AUTHOR(S): Sun Yonghong, P. Saratchandran, N. Sundararajan KEYWORD(S): direct link MRAN, extended Kalman filter, noise cancellation, RBF network, sequential learning. PAGE(S): 255-265 TITLE: A Neural Chaos Model of Multistable Perception AUTHOR(S): Natsuki Nagao, Haruhiko Nishimura, Nobuyuki Matsui KEYWORD(S): perceptual alternation, ambiguous figure, chaos, neural network, stimulus-response. PAGE(S): 267-276 TITLE: Bayesian Sampling and Ensemble Learning in Generative Topographic Mapping AUTHOR(S): Akio Utsugi KEYWORD(S): elastic net, evidence, Gibbs sampler, hyperparameter search, Laplace method, Markov chain Monte Carlo, self-organizing map, variational free energy. PAGE(S): 277-290 TITLE: Nonlinear System Identification Using Lyapunov Based Fully Tuned Dynamic RBF Networks AUTHOR(S): Li Yan, N. Sundararajan, P. Saratchandran KEYWORD(S): Growing and Pruning (GAP), Lyapunov stability theory, neural network, nonlinear dynamic system, Radial Basis Function (RBF) network, stable identification. PAGE(S): 291-303 TITLE: Author Index, Volume 12, 2000 AUTHOR(S): PAGE(S): 305-305 TITLE: Contents, Volume 12, 2000 AUTHOR(S): PAGE(S): 307-308 -------------------------------------------------------------- Thank you for your interest in Kluwer's books and journals. NORTH, CENTRAL AND SOUTH AMERICA Kluwer Academic Publishers Order Department, PO Box 358 Accord Station, Hingham, MA 02018-0358 USA Telephone (781) 871-6600 Fax (781) 681-9045 E-Mail: kluwer at wkap.com Kluwer Law International Order Department 675 Massachusetts Avenue Cambridge, MA 02139 USA Telephone: (617) 354-0140 Toll-free (US customers only): 800 577-8118 Fax: (617) 354-8595 E-mail: sales at kluwerlaw.com EUROPE, ASIA AND AFRICA Kluwer Academic Publishers Distribution Center PO Box 322 3300 AH Dordrecht The Netherlands Telephone 31-78-6392392 Fax 31-78-6546474 E-Mail: orderdept at wkap.nl From sylee at ee.kaist.ac.kr Wed Dec 6 04:59:26 2000 From: sylee at ee.kaist.ac.kr (Soo-Young Lee) Date: Wed, 6 Dec 2000 18:59:26 +0900 Subject: Neurocomputing Special Issue on ICA/BSS Message-ID: <00c301c05f6b$37f36010$0100a8c0@kaistsylee2> Neurocomputing (Elsevier; http://www.elsevier.nl/locate/neucom) Special Issue on Blind Signal Separation and Independent Component Analysis Paper Submission Deadline: March 1st, 2001 The Neurocomputing Journal plans a special issue on Blind Signal Separation and Independent Component Analysis, and papers are solicited until March 1st, 2001. Recently, blind signal separation (BSS) and independent component analysis (ICA) have received a lot of attention from the neural networks and signal processing communities. Based on probability and information theories, several unsupervised learning algorithms have been developed to separate mixed signals and extract their independent components. Several important applications have also emerged for speech enhancement, efficient coding of natural scenes and sounds, telecommunications, and medical signal processing. It is therefore worthwhile to organize a special issue on these important topics. From arthur at mail4.ai.univie.ac.at Wed Dec 6 12:05:29 2000 From: arthur at mail4.ai.univie.ac.at (Arthur Flexer) Date: Wed, 6 Dec 2000 18:05:29 +0100 (MET) Subject: Three papers on analysis of EEG Message-ID: <200012061705.SAA17795@korb.ai.univie.ac.at> Dear all, the following three recent papers dealing with the analysis of EEG can be downloaded from my web-site. Comments are of course welcome, all the best, Arthur. ----------------------------------------------------------------------------- Arthur Flexer arthur at ai.univie.ac.at http://www.ai.univie.ac.at/~arthur/ Austrian Research Inst. for Artificial Intelligence +43-1-5336112 (Tel) Schottengasse 3, A-1010 Vienna, Austria +43-1-5336112-77 (Fax) ----------------------------------------------------------------------------- Flexer A..: Data mining and electroencephalography, Statistical Methods in Medical Research, 9: 395-413, 2000. also available as: TR-2000-12. ftp://ftp.ai.univie.ac.at/papers/oefai-tr-2000-12.ps.gz An overview of Data Mining (DM) and its application to the analysis of EEG is given by (i) presenting a working definition of DM, (ii) motivating why EEG analysis is a challenging field of application for DM technology and (iii) by reviewing exemplary work on DM applied to EEG analysis. The current status of work on DM and EEG is discussed and some general conclusions are drawn. ----------------------------------------------------------------------------- Flexer A., Sykacek P., Rezek I., Dorffner G.: Using Hidden Markov Models to build an automatic, continuous and probabilistic sleep stager, in Amari S.-I., et al.(eds.), Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, IJCNN 2000, Como, Italy, IEEE Computer Society, Vol. III, 627-631, 2000. also available as: TR-99-21. ftp://ftp.ai.univie.ac.at/papers/oefai-tr-99-21.ps.gz We report about an automatic continuous sleep stager which is based on probabilistic principles employing Hidden Markov Models (HMM). Our sleep stager offers the advantage of being objective by not relying on human scorers, having much finer temporal resolution (1 second instead of 30 second), and being based on solid probabilistic principles rather than a predefined set of rules (Rechtschaffen & Kales). Results obtained for nine whole night sleep recordings are reported. ----------------------------------------------------------------------------- Flexer A., Bauer H.: Monitoring human information processing via intelligent data analysis of EEG recordings, Intelligent Data Analysis, 4: 113-128, 2000. also available as: TR-2000-34. ftp://ftp.ai.univie.ac.at/papers/oefai-tr-2000-34.ps.gz Human information processing can be monitored by analysing cognitive evoked potentials (EP) measurable in the electro encephalogram (EEG) during cognitive activities. In technical terms, both visualization of high dimensional sequential data and unsupervised discovery of patterns within this multivariate set of real valued time series is needed. Our approach towards visualization is to discretize the sequences via vector quantization and to perform a Sammon mapping of the codebook. Instead of having to conduct a time-consuming search for common subsequences in the set of multivariate sequential data, a multiple sequence alignment procedure can be applied to the set of one-dimensional discrete time series. The methods are described in detail and results obtained for spatial and verbal information processing are shown to be statistically valid, to yield an improvement in terms of noise attenuation and to be well in line with psychophysiological literature. ----------------------------------------------------------------------------- From Alain.Destexhe at iaf.cnrs-gif.fr Wed Dec 6 12:58:35 2000 From: Alain.Destexhe at iaf.cnrs-gif.fr (Alain Destexhe) Date: Wed, 06 Dec 2000 18:58:35 +0100 Subject: postdoc position in computational neuroscience Message-ID: <3A2E7E4B.15FB7483@iaf.cnrs-gif.fr> --------------------------------------------------------------------- Postdoc position available - January 1st, 2001 --------------------------------------------------------------------- A postdoc position is available for a computational study of neocortical pyramidal neurons in vivo. This project will be conducted in collaboration between two laboratories, A. Destexhe (CNRS, Gif-sur-Yvette) for the computational part, and D. Pare (Laval University, Quebec) for the experimental part. A collaboration with Y. Fregnac (CNRS, Gif-sur-Yvette) is also possible. The candidate will have access to intracellular data from neocortical neurons in vivo, obtained in the aforementioned labs. The project will consist, in a first phase, of evaluating the impact of the intense synaptic activity in vivo on dendritic integration in neocortical pyramidal cells. The morphology of intracellularly-recorded neurons will be reconstructed using a Neurolucida system and incorporated in the NEURON simulator (http://www.neuron.yale.edu), to design biophysical models that will be matched precisely to the intracellular recordings. Because models and experimental data correspond to the same cellular morphologies, we expect that this method will allow us to characterize various aspects of synaptic activity in vivo, and estimate its consequences on dendritic integration. In a second phase, these biophysical models will be simplified, in order to build large-scale networks based on the integrative properties estimated from in vivo measurements. --------------------------------------------------------------------- The CNRS facility of Gif-sur-Yvette is a campus entirely devoted to research and situated in the vicinity of Paris. The department (UPR CNRS 2191, Dir. Y. Fregnac) consists in an integrated and very interactive environment comprising in vivo electrophysiology (L. Borg-Graham, Y. Fregnac, M. Pananceau, D. Shulz), in vitro electrophysiology (T. Bal, K. Grant), comparative anatomy (J-P. Denizot), psychophysics (J. Lorenceau) and computational neuroscience (A. Destexhe). --------------------------------------------------------------------- The candidate should have a Doctoral degree, experience in neuroscience and computer programming, and ideally, a sufficient knowledge of electrophysiology. There is no restriction on nationality. --------------------------------------------------------------------- The salary will be paid by a grant from NIH, which will available on January 1st, 2001, for a period of 2 years. --------------------------------------------------------------------- Candidates should contact Alain Destexhe for more details, or consult the site http://cns.iaf.cnrs-gif.fr --------------------------------------------------------------------- Alain Destexhe Unite de Neurosciences Integratives et Computationnelles, CNRS, Avenue de la Terrasse, 91198 Gif-sur-Yvette, France Tel: 33-1-69-82-34-35 Fax: 33-1-69-82-34-27 URL: http://cns.iaf.cnrs-gif.fr email: Destexhe at iaf.cnrs-gif.fr From geoff at giccs.georgetown.edu Wed Dec 6 17:43:29 2000 From: geoff at giccs.georgetown.edu (Geoff Goodhill) Date: Wed, 6 Dec 2000 17:43:29 -0500 Subject: Postdoc position available Message-ID: <200012062243.RAA19956@brecker.giccs.georgetown.edu> POSTDOCTORAL POSITION IN EXPERIMENTAL NEUROSCIENCE A postdoctoral position in now available to join a small team of physicists, biologists and computational neuroscientists investigating mechanisms of axon guidance in the developing nervous system. We are developing new experimental and theoretical tools to better quantitatively understand axonal chemotaxis, and are seeking a researcher to assist in developing and implementing a novel bioengineering technology for the generation of precisely controlled chemical gradients. In addition to creativity and independence, the successful applicant should possess experience in one or more of the following: image acquisition and processing, quantitative fluorescence imaging, computer automation, diffusion modeling, statistical analysis of complex systems. For more information see http://www.giccs.georgetown.edu/labs/cns/axon.html Send a CV and contact information for at least two referees, preferably be email, to Geoffrey J Goodhill, PhD Assistant Professor, Department of Neuroscience & Georgetown Institute for Cognitive and Computational Sciences Georgetown University Medical Center 3900 Reservoir Road NW, Washington DC 20007 Tel: (202) 687 6889, Fax: (202) 687 0617 Email: geoff at giccs.georgetown.edu Homepage: www.giccs.georgetown.edu/labs/cns From sml at essex.ac.uk Thu Dec 7 09:52:45 2000 From: sml at essex.ac.uk (Lucas, Simon M) Date: Thu, 7 Dec 2000 14:52:45 -0000 Subject: OCR Competition Winner Message-ID: <6A8CC2D6487ED411A39F00D0B7847B66E77F81@sernt14.essex.ac.uk> Dear All, I am pleased to announce that the OCR competition that I posted here a few weeks ago has now been won by Chih-Chung Chang and the SVM group of Department of Computer Science and Information Engineering of National Taiwan University. ( http://www.csie.ntu.edu.tw/~cjlin/group.html ) Congratulations! More details can be found at http://algoval.essex.ac.uk Best regards, Simon Lucas -------------------------------------------------- Dr. Simon Lucas Senior Lecturer and MSc E-commerce Director Department of Computer Science University of Essex Colchester CO4 3SQ United Kingdom Email: sml at essex.ac.uk http://cswww.essex.ac.uk -------------------------------------------------- From Peter.Bartlett at anu.edu.au Thu Dec 7 17:00:47 2000 From: Peter.Bartlett at anu.edu.au (Peter Bartlett) Date: Fri, 08 Dec 2000 09:00:47 +1100 Subject: neural network learning: theoretical foundations Message-ID: <3A30088F.EE3CD507@anu.edu.au> Hi all, Cambridge University Press is about to start a second printing of our book "Neural Network Learning: Theoretical Foundations." If you've spotted any errors/typos/out-of-date citations, please let us know. Thanks in advance for your help. -- Martin Anthony and Peter Bartlett. From terry at salk.edu Thu Dec 7 21:23:17 2000 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 7 Dec 2000 18:23:17 -0800 (PST) Subject: NEURAL COMPUTATION 12:11 Message-ID: <200012080223.eB82NHo08011@purkinje.salk.edu> Neural Computation - Contents - Volume 12, Number 11 - November 1, 2000 Article Dynamical Mechanism for Sharp Orientation Tuning in an Integrate-and-Fire Model of a Cortical Hypercolumn P.C. Bressloff, N. W. Bressloff, and J. D. Cowan Notes Statistical Signs of Common Inhibitory Feedback with Delay Quentin Pauluis On the Computational Power of Winner-Take-All Wolfgang Maass Reclassification as Supervised Clustering A. Sierra and F. Corbacho Letters A Model of Invariant Object Recognition in the Visual System: Learning Rules, Activation Functions, Lateral Inhibition and Information-Based Performance Measures Edmund T. Rolls and T. Milward An Analysis of Orientation and Ocular Dominance Patterns in the Visual Cortex of Cats and Ferrets T. Muller, M. Stetter, B. Chapman, K. Obermayer, M. Hubener, F. Sengpiel, T. Bonhoeffer, I. Godecke, S. Lowel Improvements to the Sensitivity of Gravitational Clustering for Multiple Neuron Recordings Stuart N. Baker and George L. Gerstein Neural Coding: Higher-Order Temporal Patterns in the Neurostatistics of Cell Assemblies Laura Martignon, Gustavo Deco, Kathryn Laskey, Mathew Diamond, Winrich A. Freiwald, and Eilon Vaadia Gaussian Processes for Classification: Mean Field Algorithms Manfred Opper and Ole Winther The Bayesian Evidence Scheme for Regularising Probability-Density Estimating Neural Networks Dirk Husmeier A Bayesian Committee Machine Volker Tresp ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2000 - VOLUME 12 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $88 $94.16 $136 Institution $430 $460.10 $478 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 258-6779 mitpress-orders at mit.edu ----- From ronitt at research.nj.nec.com Fri Dec 8 17:18:39 2000 From: ronitt at research.nj.nec.com (Ronitt Rubinfeld) Date: Fri, 8 Dec 2000 17:18:39 -0500 Subject: job opportunity at NECI Message-ID: <200012082218.RAA04273@localhost.localdomain> The NEC Research Institute (NECI) in Princeton, New Jersey, has immediate openings for outstanding researchers in Computer Science. Candidates are required to have a Ph.D. degree and are expected to establish a basic research program of international stature. We are seeking applicants in cryptography, theory, machine learning, bioinformatics, data mining and other systems relevant to web applications, but will consider exceptional applicants in other areas of Computer Science. NECI, founded eleven years ago, has as its mission basic research in Computer Science and Physical Sciences underlying future technologies relevant to NEC. The Institute has research programs in theory, machine learning, computer vision, computational linguistics, web characterization and applications, bioinformatics, as well as research activities in Physical Sciences. NECI offers unique and unusual opportunities to its scientists including, great freedom in deciding basic research directions and projects; budgets for research, travel, equipment, and support staff that are directly controlled by principal researchers; and publication of all research results in the open literature. The Institute's laboratories are state-of-the-art and include several high-end parallel compute servers. NECI has close ties with outstanding research universities in and outside the Princeton area and with NEC's Central Research Laboratory (CRL) in Japan. Collaborations with university and CRL research groups are encouraged. Full applications should include resumes, copies of selected publications, names of at least three references, and a two-page statement of proposed research directions. Applications will be reviewed beginning January 1, 2001. NECI is an equal opportunity employer. For more details about NECI, please see http://www.neci.nj.nec.com. Please send applications or inquiries to: CS Search Committee Chair NEC Research Institute 4 Independence Way Princeton, NJ 08540 email: compsci-candidates at research.nj.nec.com From cindy at cns.bu.edu Mon Dec 11 11:18:00 2000 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Mon, 11 Dec 2000 11:18:00 -0500 Subject: ICCNS'2001: invited speaker program and call for abstracts Message-ID: <200012111618.LAA25222@retina.bu.edu> Apologies if you receive this more than once. ***** FINAL INVITED SPEAKER PROGRAM AND CALL FOR ABSTRACTS ***** FIFTH INTERNATIONAL CONFERENCE ON COGNITIVE AND NEURAL SYSTEMS Tutorials: May 30, 2001; Meeting: May 31 - June 2, 2001 Boston University http://www.cns.bu.edu/meetings/ This interdisciplinary conference focuses on two fundamental questions: How Does the Brain Control Behavior? How Can Technology Emulate Biological Intelligence? A single oral or poster session enables all presented work to be highly visible. Contributed talks will be presented on each of the three conference days. Three-hour poster sessions with no conflicting events will be held on two of the conference days. All posters will be up all day, and can also be viewed during breaks in the talk schedule. CONFIRMED INVITED SPEAKERS TUTORIAL SPEAKERS: Wednesday, May 30, 2001 Ted Adelson: The perception of surface properties Yiannis Aloimonos: What geometry and statistics tell us about the motion pathway Gail A. Carpenter: Adaptive resonance theory Michael Jordan: Inference and learning in graphical models INVITED SPEAKERS Thursday, May 31, 2001 Larry Abbott: Spike-timing effects in Hebbian synaptic plasticity Wulfram Gerstner: Rapid signal transmission by populations of spiking neurons Wolfgang Maass: Towards a computational theory for spiking neurons Nancy Kopell: Rhythms and cell assemblies in the nervous system Henry Markram: Neuronal, synaptic, and network mechanisms of perception, attention, and memory Victor Lamme: The role of recurrent processing in visual awareness Wolf Singer: Neuronal synchrony in cerebral cortex and its functional implications (keynote lecture) Friday, June 1, 2001 Ralph D. Freeman: Organization of receptive fields of neurons in the primary visual cortex Nikos Logothetis: Functional magnetic resonance imaging of the monkey brain David J. Heeger: Linking visual perception with human brain activity Maggie Shiffrar: The visual analysis of moving bodies Stephen Grossberg: What and where fusion: Motion, number, and object recognition Allen Waxman: Multi-sensor image fusion technologies Saturday, June 2, 2001 Peter L. Strick: Basal ganglia and cerebellar "loops" with the cerebral cortex: Motor and cognitive circuits Richard Ivry: Timing, temporal coupling, and response selection Daniel Bullock: Action selection and reinforcement learning in a model of laminar frontal cortex and the basal ganglia Christoph Schreiner: Spectro-temporal receptive field transformation in auditory thalamo-cortical system Rochel Gelman: Continuity and discontinuity in cognitive development: Numerical cognition as a case Maja Mataric: From what you see to what you do: Imitation in humans and humanoid robots Leon Cooper: Bi-directionally modifiable synapses: From theoretical fantasy to experimental fact (keynote lecture) CALL FOR ABSTRACTS Session Topics: * vision * object recognition * image understanding * audition * speech and language * unsupervised learning * supervised learning * reinforcement and emotion * sensory-motor control * spatial mapping and navigation * neural circuit models * neural system models * mathematics of neural systems * robotics * hybrid systems (fuzzy, evolutionary, digital) * neuromorphic VLSI * industrial applications * cognition, planning, and attention * other Contributed abstracts must be received, in English, by January 31, 2001. Notification of acceptance will be provided by email by February 28, 2001. A meeting registration fee of $50 for regular attendees and $35 for students must accompany each Abstract. See Registration Information for details. The fee will be returned if the Abstract is not accepted for presentation and publication in the meeting proceedings. Registration fees of accepted abstracts will be returned on request only until April 20, 2001. Each Abstract should fit on one 8.5" x 11" white page with 1" margins on all sides, single-column format, single-spaced, Times Roman or similar font of 10 points or larger, printed on one side of the page only. Fax submissions will not be accepted. Abstract title, author name(s), affiliation(s), mailing, and email address(es) should begin each Abstract. An accompanying cover letter should include: Full title of Abstract; corresponding author and presenting author name, address, telephone, fax, and email address; and a first and second choice from among the topics above, including whether it is biological (B) or technological (T) work. Example: first choice: vision (T); second choice: neural system models (B). (Talks will be 15 minutes long. Posters will be up for a full day. Overhead, slide, and VCR facilities will be available for talks.) Abstracts which do not meet these requirements or which are submitted with insufficient funds will be returned. Accepted Abstracts will be printed in the conference proceedings volume. No longer paper will be required. The original and 3 copies of each Abstract should be sent to: Cynthia Bradford, Boston University, Department of Cognitive and Neural Systems, 677 Beacon Street, Boston, MA 02215. REGISTRATION INFORMATION: Early registration is recommended. To register, please fill out the registration form below. Student registrations must be accompanied by a letter of verification from a department chairperson or faculty/research advisor. If accompanied by an Abstract or if paying by check, mail to the address above. If paying by credit card, mail as above, or fax to (617) 353-7755, or email to cindy at cns.bu.edu. The registration fee will help to pay for a reception, 6 coffee breaks, and the meeting proceedings. STUDENT FELLOWSHIPS: Fellowships for PhD candidates and postdoctoral fellows are available to help cover meeting travel and living costs. The deadline to apply for fellowship support is January 31, 2001. Applicants will be notified by email by February 28, 2001. Each application should include the applicant's CV, including name; mailing address; email address; current student status; faculty or PhD research advisor's name, address, and email address; relevant courses and other educational data; and a list of research articles. A letter from the listed faculty or PhD advisor on official institutional stationery should accompany the application and summarize how the candidate may benefit from the meeting. Fellowship applicants who also submit an Abstract need to include the registration fee with their submission. Fellowship checks will be distributed after the meeting. REGISTRATION FORM Fifth International Conference on Cognitive and Neural Systems Department of Cognitive and Neural Systems Boston University 677 Beacon Street Boston, Massachusetts 02215 Tutorials: May 30, 2001 Meeting: May 31 - June 2, 2001 FAX: (617) 353-7755 http://www.cns.bu.edu/meetings/ (Please Type or Print) Mr/Ms/Dr/Prof: _____________________________________________________ Name: ______________________________________________________________ Affiliation: _______________________________________________________ Address: ___________________________________________________________ City, State, Postal Code: __________________________________________ Phone and Fax: _____________________________________________________ Email: _____________________________________________________________ The conference registration fee includes the meeting program, reception, two coffee breaks each day, and meeting proceedings. The tutorial registration fee includes tutorial notes and two coffee breaks. CHECK ONE: ( ) $75 Conference plus Tutorial (Regular) ( ) $50 Conference plus Tutorial (Student) ( ) $50 Conference Only (Regular) ( ) $35 Conference Only (Student) ( ) $25 Tutorial Only (Regular) ( ) $15 Tutorial Only (Student) METHOD OF PAYMENT (please fax or mail): [ ] Enclosed is a check made payable to "Boston University". Checks must be made payable in US dollars and issued by a US correspondent bank. Each registrant is responsible for any and all bank charges. [ ] I wish to pay my fees by credit card (MasterCard, Visa, or Discover Card only). Name as it appears on the card: _____________________________________ Type of card: _______________________________________________________ Account number: _____________________________________________________ Expiration date: ____________________________________________________ Signature: __________________________________________________________ From raetsch at first.gmd.de Tue Dec 12 10:24:39 2000 From: raetsch at first.gmd.de (Gunnar Raetsch) Date: Tue, 12 Dec 2000 16:24:39 +0100 Subject: New Website on Boosting and Ensemble Learning Message-ID: <3A364337.CD4E134@first.gmd.de> We are pleased to announce a new web-site on Boosting and related ensemble learning methods. It can be found at http://www.boosting.org Compared to other pages on Boosting, the main difference is that we have enlarged the scope to form a repository not only for research on Boosting, but also on Ensemble Learning in general, Learning Theory, Large Margin Classifiers, Mathematical Programming, and related topics. The aim is to serve as a central information source by providing links to papers, upcoming events, datasets, code, a discussion board, etc. We have strived to create a forum for providing a balanced representation of the field of Boosting and ensemble learning research. It is our hope that this forum will contribute its share to the exciting developments in this field that all of us have been and are witnessing these years. On the technical side, features include fully automatic data entry, papers can be uploaded to the website, there exists a search option for papers, and data can also be provided in BibTeX format which should make it easier referencing to papers available at the site. If you would like to add a paper of yours, please feel free to do so by following the instructions on http://www.boosting.org/publications.html We would like to express thanks to Central Research Institute of Electric Power Industry for allowing us to host the web-site in Tokyo. Furthermore, we thank Alex Smola for providing a copy of the Kernel-Machines-Site which served as a basis for creating this new site. We also thank GMD-FIRST for providing resources to maintain this site. -- ----------------------------------------- Gunnar R"atsch, GMD First Berlin Tel : +49 30 6392 1906 WWW : http://www.first.gmd.de/~raetsch From shultz at psych.mcgill.ca Wed Dec 13 14:19:05 2000 From: shultz at psych.mcgill.ca (Thomas R. Shultz) Date: Wed, 13 Dec 2000 14:19:05 -0500 Subject: Human Cognitive Neuroscience position at McGill Message-ID: <4.3.1.0.20001213141420.00a82e80@127.0.0.1> McGill University Department of Psychology Assistant or junior Associate Professor Position in Human Cognitive Neuroscience The Department of Psychology of McGill University seeks applicants for a tenure-track position at the Assistant or junior Associate Professor level in Human Cognitive Neuroscience. The deadline for receipt of completed applications is January 15, 2001, with an anticipated starting date of September 1, 2001. Preference will be given to applicants with interests in the cognitive neuroscience of higher order cognitive processes, such as language, reasoning, problem solving, categorization, decision making. Our current strengths within this broad domain are language, higher order reasoning, learning, memory, and speech and music cognition. The Department has excellent facilities for interdisciplinary research through its links with related academic departments at McGill and other universities in Montreal, research units in the McGill University Health Centre including the Montreal Neurological Institute, and McGill Cognitive Science. Applicants at the Assistant Professor level should present early evidence of the ability to establish a record of significant, externally funded research productivity, and applicants at the Associate Professor level should have such a record. All applicants are expected to have an aptitude for undergraduate and graduate teaching. Applicants should arrange for three confidential letters of recommendation to be sent to the address below. A curriculum vitae, description of current and proposed areas of research, selected reprints of published or in press research articles, a description of areas of teaching competency, interest, and approaches, and other relevant material, should also be sent to Chair, Human Cognitive Neuroscience Search Committee Department of Psychology McGill University 1205 Dr. Penfield Avenue Montreal, Quebec, Canada H3A 1B1 In accordance with Canadian immigration requirements, priority will be given to Canadian citizens and permanent residents of Canada. McGill University is committed to equity in employment. All academically qualified candidates are encouraged to apply. -------------------------------------------------------- Thomas R. Shultz, Professor, Department of Psychology, McGill University, 1205 Penfield Ave., Montreal, Quebec, Canada H3A 1B1. E-mail: shultz at psych.mcgill.ca NEW http://www.psych.mcgill.ca/perpg/fac/shultz/default.htm Phone: 514 398-6139 Fax: 514 398-4896 -------------------------------------------------------- From rdybowski at btinternet.com Wed Dec 13 14:55:02 2000 From: rdybowski at btinternet.com (Richard Dybowski) Date: Wed, 13 Dec 2000 19:55:02 +0000 Subject: Machine Learning Journal Special Issue on Fusion of Knowledge with Data: First Call for Papers Message-ID: <4.2.0.58.20001213195343.03c42e00@mail.btinternet.com> Please accept my apologies if you receive multiple copies of this call. ----------------------------------------------------------------------------- Machine Learning Journal Special Issue on Fusion of Domain Knowledge with Data for Decision Support ----------------------------------------------------------------------------- >>> First Call for Papers <<< Statistics and machine learning are data-oriented tasks in which domain models are induced from data. The bulk of research in these fields concentrates on inducing models from data archived in computer databases. However, for many problem domains, human expertise forms an essential part of the corpus of knowledge needed to construct models of the domain. The discipline of knowledge engineering has focused on encoding the knowledge of experts in a form that can be encoded into computational models of a domain. At present, knowledge engineering and machine learning remain largely separate disciplines. Yet in many fields of endeavor, substantial human expertise exists alongside data archives. When both data and domain knowledge are available, how can these two resources effectively be combined to construct decision support systems? The aim of this special issue of the Machine Learning journal is to allow researchers to communicate their work on integrating domain knowledge with data (knowledge-data fusion; theory revision; theory refinement) to a general machine learning audience. Emphasis is on sound theoretical frameworks rather than ad hoc approaches. Of particular interest are papers that combine clear theoretical discussion with practical examples, and papers that compare different approaches. Possible frameworks for knowledge-data fusion include probabilistic (Bayesian/belief) networks, possibilistic logics and networks, hybrid neuro-fuzzy networks, and inductive logic programming. Topics of interest include (but are not limited to): * Practical applications of knowledge-data fusion. What lessons have been learnt from attempts to apply knowledge-data fusion to real-world decision problems? * How are the various knowledge representation and inference frameworks that permit induction theoretically related to each other? * What frameworks enable an existing induced model, such as a neural network, to be incorporated into a proposed knowledge-based system? * How can knowledge-data fusion be applied to temporal data? Submitted papers must not exceed 30 pages and must conform to the Machine Learning journal style. Please see the associated Web site for further submission details: http://www.umds.ac.uk/microbio/richard/kdf/ This Call for Papers is *not* restricted to those who presented at the UAI 2000 Workshop on Knowledge-Data Fusion: it is open to everyone who has an interest in this topic. Please direct any enquiries to Richard Dybowski: rdybowski at btinternet.com Schedule -------------- Paper submission deadline: June 1, 2001 Authors' notification of decisions: September 1, 2001 Final revised papers due: December 15, 2001 Guest Editors -------------------- Richard Dybowski (King's College London) Kathryn Blackmond Laskey (George Mason University) James Myers (Ballistic Missile Defense Organization) Simon Parsons (Liverpool University) From terry at salk.edu Thu Dec 14 01:05:32 2000 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 13 Dec 2000 22:05:32 -0800 (PST) Subject: NEURAL COMPUTATION 12:12 In-Reply-To: <200012080223.eB82NHo08011@purkinje.salk.edu> Message-ID: <200012140605.eBE65WV24409@purkinje.salk.edu> Neural Computation - Contents - Volume 12, Number 12 - December 1, 2000 Article Evolution of Cooperative Problem-Solving in an Artificial Economy Eric B. Baum and Igor Durdanovic View Cortical Potential Distributions and Information Processing Henry C. Tuckwell Note Asymptotic Bias in Information Estimates and The Exponential (Bell) Polynomials Jonathan D. Victor Letters Relating Macroscopic Measures of Brain Activity to Fast Dynamic Neuronal Interactions D. Chawla, E. D. Lumer and K. J. Friston Analysis of Pointing Errors Reveals Properties of Data Representations and Coordinate Transformations within the Central Nervous System J. McIntyre, F. Stratta, J. Droulez, and F. Lacquaniti Modeling Selective Attention Using a Neuromorphic Analog VLSI Device Giacomo Indiveri Asymptotic Convergence Rate of the EM Algorithm for Gaussian Mixtures Jinwen Ma, Lei Xu, and Michael Jordan Incremental Active Learning for Optimal Generalization Masashi Sugiyama, and Hidemitsu Ogawa A Quantitative Study of Fault Tolerance, Noise Immunity and Generalization Ability of MLPs J. L. Bernier, J. Ortega, E. Ros, I. Rojas, and A. Prieto On the Computational Complexity of Binary and Analog Symmetric Hopfield Nets Jiri Sima, Pekka K. Orponen, and Teemu Antti-Poika ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2000 - VOLUME 12 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $88 $94.16 $136 Institution $430 $460.10 $478 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 258-6779 mitpress-orders at mit.edu ----- From Wulfram.Gerstner at epfl.ch Thu Dec 14 12:15:18 2000 From: Wulfram.Gerstner at epfl.ch (Wulfram Gerstner) Date: Thu, 14 Dec 2000 18:15:18 +0100 Subject: PostDoc and PhD student positions Message-ID: <3A390026.BA04A49C@epfl.ch> The Neural Computation Group at the Swiss Federal Institute of Technology in Lausanne is expanding its activities and looking for several PhD-students and PostDocs in the area of Computational Neuroscience/Neural Computation. In particular, we seek to strengthen activities on problems such as - Neural coding with spiking neurons - Spike-time dependent plasticity - Reinforcement learning and biological models of conditioning - Hippocampal models of spatial representation - Validating biological models with Khepera robots - Models of vision (e.g. saccades, attention, motion) - Implications of Machine Learning concepts for biological information processing For further details on current activities, see http://diwww.epfl.ch/mantra/ Applicants should have a strong background in mathematical modeling, a keen interest in questions of neuroscience, and the capacity to relate model results to experimental data. Collaborations with experimental groups exist and will be further developped. The Swiss Federal Institute of Technology in Lausanne is the sister institution of the ETH Zurich and offers excellent working conditions. Lausanne is located on the shores of the lake of Geneva with beautiful surroundings for hiking, climbing, skiing and water sports. The city of Lausanne has the flair of an old university town with lots of theaters, music and other cultural activities. Geneva is only 35 minutes by train. Berne 1 hour, Zurich 2 and a half hours, Paris 3 and a half hours. http://www.lausanne-tourisme.ch/ Applications should include CV, list of publications, names of at least two references, and a one-page statement of research interests. starting date: between January and October 2001 Please send applications to: Wulfram Gerstner Center for Neuromimetic Systems Swiss Federal Institute of Technology Lausanne Computer Science Department, EPFL-DI 1015 Lausanne, Switzerland If you want to send the applications by email, please mark clearly - application - in the subject line and send to wulfram.gerstner at epfl.ch -- --------------------------------------------------------------------- Wulfram Gerstner Swiss Federal Institute of Technology Lausanne Assistant Professor Centre for Neuro-mimetic Systems, Mantra Computer Science Department, EPFL, IN-J, 032 1015 Lausanne EPFL Tel. +41-21-693 6713 wulfram.gerstner at epfl.ch Fax. +41-21-693 5263 http://diwww.epfl.ch/mantra --------------------------------------------------------------------- From R.Poli at cs.bham.ac.uk Thu Dec 14 09:00:39 2000 From: R.Poli at cs.bham.ac.uk (Riccardo Poli) Date: Thu, 14 Dec 2000 14:00:39 GMT Subject: PERMANENT LECTURESHIP IN NATURAL COMPUTATION Message-ID: <200012141400.OAA01717@sonic.cs.bham.ac.uk> Dear All, We invite applications from outstanding candidates for three open-ended lectureships (equivalent to tenure-track assistant professorship in North America) in the School of Computer Science, the University of Birmingham, UK (see the advertisment appended). One of the three posts is particularly relevant to members of this list, i.e., for someone with a strong background in natural computation (including evolutionary, neural and other nature-inspired computations). However, all three lectureships are open to all outstanding candidates. The School of Computer Science has an active and strong research group in evolutionary and neural computations, the EEBIC group, consisting of four permanent academic staff (faculty) and two research fellows: Julian Miller (Evolutionary Computation, Machine Learning) Riccardo Poli (Evolutionary Computation, GP, Computer Vision, NNs, AI) Jon Rowe (Evolutionary Computation, AI) Thorsten Schnier (Evolutionary Computation, Engineering Design) Xin Yao (Evolutionary Computation, NNs, Machine Learning) Jun He (Evolutionary Computation, from 1 Feb 2001) There are other staff members in the school who are in the areas of evolvable architectures of mind, medical imaging, robotics, and reinforcement learning. The School has a strong AI group. Our research has been supported by EPSRC, Marconi Communications, EU, BT, DERA, and the Royal Society. Further information about the new MSc mentioned in the following ad can be found at: http://www.cs.bham.ac.uk/~xin/courses/mtp/ More information about the school and the posts can be obtained from our web site or by contacting the head of school (not me), although I'm happy to answer questions about research activities in natural computation in the school. Additional research posts in Computer Science and Artificial Intelligence in this School can be found at: http://www.cs.bham.ac.uk/school/jobvacancies Riccardo ====================================================================== SCHOOL OF COMPUTER SCIENCE THE UNIVERSITY OF BIRMINGHAM England Three Lecturership Posts Applications are invited for three lectureship posts in Computer Science, starting as soon as possible (September 2001 latest). Postholders will be expected to contribute strongly to research, teaching and administration within the School. As an exception, consideration will be given for one of the posts to applicants whose strength is mainly in teaching in an area of special benefit to the School, for example systems analysis, software design, information systems, human-computer interaction or natural computation (taken to include evolutionary, neurally-inspired, and other nature-based computational styles). We intend one of the positions to be filled by someone able to contribute to teaching in our new EPSRC-funded MSc in Natural Computation. Applicants may be in any area of research in computational science. Generally, applicants should have, or soon expect to have, a PhD in computer science or an appropriate, closely related field, together with research experience as evidenced by publications in leading international journals or conference proceedings. However, teaching-orientated applicants may be acceptable if they have an appropriate, strong educational or industrial background and have a good university degree in an appropriate field. ---------------------------------------------------------------------- For further information please see http://www.cs.bham.ac.uk/research/jobs/lect01/ For the formal application procedure please see that webpage. CLOSING DATE: 31 January 2001. (Late applications may be considered.) Interviews are tentatively planned for late February / early March. It may be possible to negotiate part-time work in special cases. Informal enquiries may be made to Prof. John Barnden (Head of School) Tel: (+44) (0)121 414-3711 Email: J.A.Barnden at cs.bham.ac.uk ====================================================================== From ttroyer at psyc.umd.edu Thu Dec 14 17:55:02 2000 From: ttroyer at psyc.umd.edu (Todd Troyer) Date: Thu, 14 Dec 2000 17:55:02 -0500 Subject: Interdisciplinary training at the University of Maryland, College Park Message-ID: The Neuroscience and Cognitive Science (NACS) program at the University of Maryland (http://www.life.umd.edu/nacs) solicits applications for students interested in interdisciplinary graduate training. The NACS program offers a breadth of research and training, and offers courses in the neural, cognitive, and computational sciences. Students have the opportunity to work across disciplines, across labs, and even at multiple sites (such as NIH or UM Baltimore). In addition to the over 70 NACS faculty distributed among 14 departments, there is the potential of working with scientists at NIH, USDA, NIST, the National Zoo and the Smithsonian Institution. The program offers competitive, multi-year stipends that may include family health insurance and full tuition remission. Many NACS faculty take a computational or combined computational/experimental approach to the study of neural and cognitive function. A selected sample of research strengths on campus includes: Neuroethological and comparative approaches to auditory processing. Sensorimotor integration in animal, human, and neuromorphic systems. Dynamical approaches to neural processing and motor behavior. Linguistics and the cognitive neuroscience of language. Affective and cognitive approaches to human development. Interested students are encouraged to visit the NACS web site at http://www.life.umd.edu/nacs/ or to write to NACS, Biology/Psychology Building University of Maryland College Park, MD 20742 Phone: 301-405-8910 e-mail: sd136 at umail.umd.edu College Park is located close to Washington DC, with easy access by Metro or car to the rich cultural life of the DC metropolitan area. From tabor at uconnvm.uconn.edu Fri Dec 15 09:43:32 2000 From: tabor at uconnvm.uconn.edu (tabor@uconnvm.uconn.edu) Date: Fri, 15 Dec 2000 09:43:32 -0500 Subject: PhD Openings: Psychology Dept., University of Connecticut Message-ID: <3.0.3.32.20001215094332.0137b7e0@psych.psy.uconn.edu> ******************************************************************* GRADUATE TRAINING IN LANGUAGE AND COGNITION AT THE UNIVERSITY OF CONNECTICUT ******************************************************************* The Language and Cognition Program in the Department of Psychology at the University of Connecticut has openings for at least 4 PhD studentships to start in Fall, 2001. The program is centered around the experimental study of language processing, and has done excellent work on speech perception and production, word identification, sentence processing, skilled reading, and the process of learning to read. It has close ties with the Center for the Ecological Study of Perception and Action (CESPA), which is in the same division of the University of Connecticut Department of Psychology. Over the past several years, a unique synthesis has been occurring between the ecological work, which has focused on the development of dynamical systems models of human physical movement (e.g. limb coordination, postural control, gait, etc.), and the language work, which has been emphasizing the use of dynamical connectionist models to study language as action. An important element in the mix is Haskins laboratories, an independent research lab located nearby in New Haven. For over 60 years, Haskins has done pathbreaking research on speech and reading and maintained an environment where people from many places and backgrounds meet regularly to explore ideas creatively and work on joint projects. Important deadline: January 15: Graduate Applications due. The brochure is available on line at: http://www.sp.uconn.edu/~wwwpsyc/Experimental.html/ For admission guidelines and to download application forms, see: http://www.sp.uconn.edu/~wwwpsyc/GradAd.html/ To obtain a printed brochure and a set of application materials, write, telephone, fax, or email: Ms. Nicole Dolat, Department of Psychology, University of Connecticut, 406 Babbidge Road, Unit 1030, Storrs, CT 06269-1030 Phone: (860) 486-3528 FAX: (860) 486-2760 E-Mail: futuregr at psych.psy.uconn.edu ******************************************************************* Description of the Program in Language and Cognition: The Program in Language and Cognition focuses on those aspects of language that make it a uniquely versatile vehicle for communication and thought. There is thus a strong focus on the dynamical aspects of language, including experimental studies of language processing, learning, and change at the phoneme, word, and sentence level, modeling of language processes using artificial neural (connectionist) networks and symbolic computational models, and mathematical analysis using dynamical systems theory and statistics. There is particular interest in an ecological approach, which emphasizes continual interaction between speaker/hearers and their environments. There is much interest in the biological basis of language, both in pursuit of innate endowment questions and in studies of neural mechanisms using state-of-the-art neuroimaging tools. The group has long conducted basic research on the reading process; some members of the group are also engaged in the translation of research findings to the classroom. The Program has close ties to the Center for the Study of Perception and Action (CESPA---http://ione.psy.uconn.edu/~cespaweb/), the Developmental and Behavioral Neuroscience Divisions in the Dept. of Psychology (http://www.sp.uconn.edu/~wwwpsyc/), the Linguistics Department (http://vm.uconn.edu/~wwwling/), and the Cognitive Science Focus (http://cogsci.uconn.edu/) at the University of Connecticut. In addition, Haskins Laboratories (http://www.haskins.yale.edu), located nearby in New Haven, provides a stimulating environment for research and training. The program prepares students for careers in research and teaching. A student's research activity begins immediately on entry to the program. In addition, three courses are typically taken each semester. A student's schedule also includes attendance at colloquia and informal weekly group meetings for discussion of problems in theory and research. Course work for the Ph.D. degree can often be completed in two-and-a-half to three years. Another year or two is needed to complete the dissertation. Applicants should have an excellent academic record. Research experience is helpful but not necessary. Applicants may have an undergraduate major in psychology, linguistics, computer science, mathematics, cognitive science, or other related fields of study. ***** CAROL FOWLER, Professor of Psychology. Dr. Fowler works on speech perception and production within the developing direct-realist framework. In addition, she has begun collaborative research on cross-person coordination and cooperation in language use. This is part of an effort to develop an ecological theory of language-that is, an understanding of how language is used in ordinary contexts in which speech occurs. Dr. Fowler is the Director of Haskins Laboratories. LEONARD KATZ, Professor of Psychology. Dr. Katz studies reading, focusing on the process of printed word recognition. Cross-language experiments are often used to reveal in which ways word recognition is shaped by a language's particular characteristics and in which ways it is more general. Languages studied include English, Hebrew, Russian, Serbo-Croatian and Turkish. In addition, functional Magnetic Resonance Imaging studies (carried out in conjunction with Haskins Laboratories and Yale Medical School) explore the brain mechanisms that support the word recognition process. Finally, behavioral experiments in English are used to study the effects on word recognition of the reader's lexicon (i.e., neighborhood factors) and reader strategies. JAY RUECKL, Associate Professor of Psychology. A primary goal of Dr. Rueckl's research is to use connectionist networks to forge a link between theories of implicit memory and models of word identification. His research focuses on the interaction of phonological, morphological, and semantic factors in the influence of implicit memory on work identification in reading, the role of perceptual detail (e.g. the characteristics of a speaker's voice) in visual and spoken word identification. In addition, together with his colleagues at Haskins Laboratories, Dr. Rueckl has recently begun to apply artificial neural network models to the investigation of the cognitive neuropsychology of reading. DONALD SHANKWEILER, Professor of Psychology. The broad aim of Dr. Shankweiler's research is to understand how the language apparatus, which is biologically specialized for speech, becomes adapted to reading and writing. In studies carried out in the 1970's, he and Dr. I. Y. Liberman discovered that there is an important association between children's abilities to analyze speech into its components (phonemes, syllables, and morphemes) and their progress in reading. Recent research has pursued the implications of this association for the operation of short-term verbal memory; for children who lack phonologically analytic skills, short-term memory function is also impaired. Dr. Shankweiler, with Stephen Crain and their students, have developed a model of the role of short-term memory in language comprehension. WHITNEY TABOR, Assistant Professor of Psychology. Dr. Tabor's research focuses on the coexistence of structure and flexibility in complex systems. He uses artificial neural networks and dynamical systems theory to develop models of human language processing, learning, and change. He has worked on the role of semantic information in sentence processing, evidence for ungrammatical influences in sentence processing, attractor models of syntactic category structure, the learning of complex phrase structure grammars, and the evolution of grammatical categories over historical time. * * * * * AFFILIATED FACULTY CLAUDIA CARELLO, Professor of Psychology, Director of CESPA: Ecological study of human movement, printed word recognition in English, Korean, Serbo-Croatian. ROGER CHAFFIN, Professor of Psychology (Hartford): Semantic memory, memory for skilled performance. ELENA LEVY, Associate Professor of Psychology (Stamford): Language and gesture, language development. DIANE LILLO-MARTIN, Professor of Linguistics and Psychology: The structure of American Sign Language, its acquisition and processing, and the processes deaf people use to read. GEORGIJE LUKATELA, Visiting Professor: The phonological basis of printed word recognition. LETITIA NAIGLES, Associate Professor of Psychology: Language acquisition, word learning. KENNETH PUGH, Associate Professor, Yale University and Haskins Laboratories: Brain imaging studies of reading. WILLIAM SNYDER, Assistant Professor of Linguistics: Cross-linguistic studies of language acquisition; sentence processing. MICHAEL TURVEY, Professor of Psychology: Ecological study of human movement, the phonological basis of printed word recognition. ////////\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\\\\\\\\ Whitney Tabor (860) 486-4910 (office) Department of Psychology (860) 486-2760 (fax) University of Connecticut (860) 486-6080 (lab) Storrs, CT 06269-1020 tabor at uconnvm.uconn.edu USA WAB Room 124 (office) http://www.sp.uconn.edu/~wwwpsyc/Faculty/Tabor/Tabor.html \\\\\\\\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\//////// From harnad at coglit.ecs.soton.ac.uk Mon Dec 18 12:01:32 2000 From: harnad at coglit.ecs.soton.ac.uk (Stevan Harnad) Date: Mon, 18 Dec 2000 17:01:32 +0000 (GMT) Subject: Universities can now download Eprints 1.0 from eprints.org Message-ID: The operational release of the Eprints archive-creating software is now down-loadable from http://www.eprints.org The eprints.org software will create Eprints Archives that are interoperable and compliant with the current Open Archives protocol. The software is free, uses only free software, and can be installed and maintained easily. It is modular, and written to be easily upgraded with each upgrade of the Open Archives protocol: http://www.openarchives.org All Eprint Archives created with the eprints.org software are fully interoperable, and can be registered as Open Archive Data Providers: http://www.openarchives.org/sfc/sfc_archives.htm This means that their contents can then in turn all be harvested, jointly indexed, and jointly searched with all the other Eprint Archives through Open Archive Service Providers such as http://arc.cs.odu.edu All Eprints can also be citation-interlinked: http://opcit.eprints.org so that the research literature can be navigated by citation. It will also be possible to monitor research impact in powerful new ways, once the eprints are up there: http://cogsci.soton.ac.uk/harnad/Papers/Harnad/harnad00.citation.htm The Eprints software was expressly designed so that universities and research institutions worldwide can now immediately create their own Open Archives, in which their researchers in all disciplines can (immediately) self-archive their research -- both pre-refereeing preprints and refereed postprints. http://cogsci.soton.ac.uk/harnad/Tp/1-Anomalous-Picture/sld001.htm http://cogsci.soton.ac.uk/harnad/Tp/2-Resolving-the-Anomaly/sld001.htm As soon as universities create their own Eprint Archives and their researchers self-archive their papers in them, the world's refereed research literature will be freed from all its current needless access-barriers and impact-barriers. Footnote: HISTORY IS WATCHING. The means of freeing the entire refereed research literature (within a matter of days, in principle!) is now within the reach of the world research community. If you have a published paper of your own that has not reached its full potential readership, if there is a published paper by someone else that you or your university cannot afford to access, or cannot access immediately, or if your university has a "serials crisis" preventing its researchers from accessing the entire refereed research corpus -- AND you have NOT self-archived your own papers -- then, as of now, you have only yourself to blame (and history will be the judge, in hindsight)! -------------------------------------------------------------------- Stevan Harnad harnad at cogsci.soton.ac.uk Professor of Cognitive Science harnad at princeton.edu Department of Electronics and phone: +44 23-80 592-582 Computer Science fax: +44 23-80 592-865 University of Southampton http://www.cogsci.soton.ac.uk/~harnad/ Highfield, Southampton http://www.princeton.edu/~harnad/ SO17 1BJ UNITED KINGDOM NOTE: A complete archive of the ongoing discussion of providing free access to the refereed journal literature online is available at the American Scientist September Forum (98 & 99 & 00): http://amsci-forum.amsci.org/archives/september98-forum.html You may join the list at the site above. Discussion can be posted to: september98-forum at amsci-forum.amsci.org From tp at ai.mit.edu Mon Dec 18 12:12:11 2000 From: tp at ai.mit.edu (Tommy Poggio) Date: Mon, 18 Dec 2000 12:12:11 -0500 Subject: Post-doc position Message-ID: <4.3.2.7.2.20001218121119.021b0ab8@pop6.attglobal.net> An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/00000000/24a82347/attachment-0001.html From jrauch at MIT.EDU Mon Dec 18 15:41:51 2000 From: jrauch at MIT.EDU (Judy) Date: Mon, 18 Dec 2000 15:41:51 -0500 Subject: faculty position available Message-ID: <4.3.2.20001218153657.00bd2580@hesiod> MASSACHUSETTS INSTITUTE OF TECHNOLOGY DEPARTMENT OF BRAIN & COGNITIVE SCIENCES The MIT Department of Brain and Cognitive Sciences anticipates making a new tenure-track appointment in theoretical/experimental neuroscience at the Assistant Professor level. Candidates should combine a strong mathematical background and an active research interest in the modeling of specific cellular- or systems-level phenomena with appropriate experiments. Individuals whose research focuses on properties of single neurons or networks of neurons are especially encouraged to apply. We are also interested in individuals working on bioinformatics in neuroscience. Responsibilities include graduate and undergraduate teaching and research supervision. Applications should include a brief cover letter stating the candidate's research and teaching interests, a vita, three letters of recommendation, and representative reprints, and should be sent to: Theoretical/Experimental Neuroscience Search Committee, Dept. of Brain & Cognitive Sciences, E25-406, MIT, Cambridge, MA 02139. Review of applications will begin December 15, 2000. Qualified women and minority candidates are especially encouraged to apply. MIT is an Affirmative Action/Equal Opportunity employer. From bengioy at IRO.UMontreal.CA Mon Dec 18 16:56:51 2000 From: bengioy at IRO.UMontreal.CA (Yoshua Bengio) Date: Mon, 18 Dec 2000 16:56:51 -0500 Subject: TR: neural statistical language model beats trigram Message-ID: <20001218165651.A556@euclide.IRO.UMontreal.CA> Hello, The following tech. report that is a long version of the recently presented NIPS'2000 oral is now available on the web: A Neural Probabilistic Language Model Y. Bengio, R. Ducharme, P. Vincent Tech. Rep. 1178, Dept. of CS&OR / CRM, U of Montreal A goal of statistical language modeling is to learn the joint probability function of sequences of words in a language. This is intrinsically difficult because of the curse of dimensionality: a word sequence on which the model will be tested is likely to be different from all the word sequences seen during training. Traditional but very successful approaches based on N-grams obtain generalization by gluing very short sequences seen in the training set. Instead, we propose to fight the curse of dimensionality with its own weapons. In the proposed approach one learns simultaneously (1) a distributed representation for each word along with (2) the probability function for word sequences, expressed in terms of these representations. Generalization is obtained because a sequence of words that has never been seen before gets high probability if it is made of words that are similar to words forming an already seen sentence. We report on experiments using neural networks for the probability function, showing on two text corpora that the proposed approach very significantly improves on a state-of-the-art trigram model, and that the proposed approach allows to take advantage of much longer context. postscript file available at: http://www.iro.umontreal.ca/~lisa/pointeurs/TR1178.ps (or through my web page: follow publications -> tech. reports) -- Yoshua Bengio Professeur agrg Dpartement d'Informatique et Recherche Oprationnelle Universit de Montral, adresse postale: C.P. 6128 Succ. Centre-Ville, Montral, Qubec, Canada H3C 3J7 adresse civique: 2920 Chemin de la Tour, Montral, Qubec, Canada H3T 1J8, #2194 Tel: 514-343-6804. Fax: 514-343-5834. Bureau 3339. http://www.iro.umontreal.ca/~bengioy http://www.iro.umontreal.ca/~lisa From sylee at ee.kaist.ac.kr Tue Dec 19 04:06:47 2000 From: sylee at ee.kaist.ac.kr (Soo-Young Lee) Date: Tue, 19 Dec 2000 18:06:47 +0900 Subject: Bio+Electronics Faculty Position at KAIST EE References: <20001205015253.3E0342B229@endor.bbb.caltech.edu> Message-ID: <00c101c0699b$05820bb0$0100a8c0@kaistsylee2> PLEASE DO NOT USE 'REPLY'; FOR MORE INFO VISIT KAIST WEB SITE (www.kaist.ac.kr) OR CONTACT TO THE ADDRESSES AT THE END OF THIS E_MAIL. The Department of Electrical Engineering at Korea Advanced Institute of Science and Technology (KAIST) solicits applications for faculty position. Although all areas of electrical and computer engineering are welcome, we are particularly interested in faculties working on both/between electrical engineering and biology including Bio-Electronics and Brain Science. Unlike BK'21 Research Faculty positions with limited responsibilty, this faculty position will have all previleages of KAIST regular faculties. Also the faculty may join the Brain Science Research Center, which is currently leading the National Research Program on Brain Sciene and Engineering. The research program is sponsored by Korean Ministry of Science and Technology, and about 140 professors are working on interdisciplinary research projects. The application deadline is January 12, 2001. For more information, please contact to Department of Electrical Engineering Korea Advanced Institute of Science and Technology 373-1 Kusong-dong, Yusong-gu Taejon 305-701 Korea (South) or Prof. Soo-Young Lee Director, Brain Science Research Center Korea Advanced Institute of Science and Technology 373-1 Kusong-dong, Yusong-gu Taejon 305-701 Korea (South) E-mail: sylee at ee.kaist.ac.kr From adrian at olsen.ch Tue Dec 19 08:26:16 2000 From: adrian at olsen.ch (Adrian Trapletti) Date: Tue, 19 Dec 2000 14:26:16 +0100 Subject: PhD Thesis available: On Neural Networks as Statistical Time Series Models Message-ID: <3A3F61F8.3CBFB079@olsen.ch> Dear colleagues, I am pleased to announce that my PhD thesis, titled 'On Neural Networks as Statistical Time Series Models' is now available for electronic download at: http://www.olsen.ch/people/adrian/adrian.html Abstract: This thesis provides a rigorous mathematical analysis of the stochastic properties for what probably are the most popular classes of neural networks for time series analysis and forecasting: feedforward autoregressive neural networks and recurrent autoregressive moving average neural networks. In particular, it is shown that the characteristic roots of the shortcuts, the standard conditions from linear time series analysis, determine the stochastic behaviour of both feedforward and recurrent neural network models. If, e.g., all the characteristic roots are outside the unit circle, then the neural network models are geometrically ergodic and asymptotically stationary. This thesis also investigates training and testing of neural network models. In particular, it is shown that the least squares estimators are consistent and asymptotically normal provided the neural network model is stationary. Furthermore, training of nonstationary neural network models is considered. In particular, the hypothesis test for a unit root of Phillips and Perron is introduced as a tool to discriminate between stationary and integrated neural network models and a new neural network based unit root test is constructed which can be seen as a nonlinear extension of the augmented Dickey-Fuller test. Long abstract: in the thesis Best regards and merry Xmas Adrian Trapletti -- Adrian Trapletti, Olsen & Associates Ltd., See- feldstrasse 233, CH-8008 Zrich, Switzerland Phone: +41 (1) 386 48 48 Fax: +41 (1) 422 22 82 E-mail: adrian at olsen.ch WWW: http://www.olsen.ch From terry at salk.edu Wed Dec 20 20:25:59 2000 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 20 Dec 2000 17:25:59 -0800 (PST) Subject: NEURAL COMPUTATION 13:1 In-Reply-To: <200012140605.eBE65WV24409@purkinje.salk.edu> Message-ID: <200012210125.eBL1Px940973@purkinje.salk.edu> Neural Computation - Contents - Volume 13, Number 1 - January 1, 2001 Review Detecting and Estimating Signals over Noisy and Unreliable Synapses: Information-Theoretic Analysis Amit Manwani and Christof Koch Letters An Algorithm for Modifying Neurotransmitter Release Probability Based on Pre- and Postsynaptic Spike Timing Walter Senn, Henry Markram, and Misha Tsodyks Differential Filtering of Two Presynaptic Depression Mechanisms Richard Bertram A Statistical Theory of Long-Term Potentiation and Depression John M. Beggs Minimal Model for Intracellular Calcium Oscillations and Electrical Bursting in Melanotrope Cells of Xenopus Laevis L. Niels Cornelisse, Wim J. J. M. Scheenen, Werner J. H. Koopman, Eric W. Roubos, and Stan C. A. M. Gielen Neural Field Model of Receptive Field Restructuring in Primary Visual Cortex Katrin Suder, Florentin Worgotter and Thomas Wennekers On The Phase-Space Dynamics of Systems of Spiking Neurons. I: Model and Experiments Arunava Banerjee On The Phase-Space Dynamics of Systems of Spiking Neurons. II. Formal Analysis Arunava Banerjee Subtractive and Divisive Inhibition: Effect of Voltage-Dependent Inhibitory Conductances and Noise Brent Doiron, Andre Longtin, Neil Berman and Leonard Maler ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2000 - VOLUME 13 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $88 $94.16 $136 Institution $460 $492.20 $508 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From bruns at cs.tu-berlin.de Thu Dec 21 06:43:47 2000 From: bruns at cs.tu-berlin.de (Camilla Bruns) Date: Thu, 21 Dec 2000 12:43:47 +0100 Subject: EU Summerschool on Computational Neuroscience 2001 Message-ID: <200012211142.MAA15748@mail.cs.tu-berlin.de> This is the first call for the EU Summerschool on Computational Neuroscience 2001. EU ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE (AN I.B.R.O. NEUROSCIENCE SCHOOL) July 30 - August 24, 2001 INTERNATIONAL CENTRE FOR THEORETICAL PHYSICS, TRIESTE, ITALY DIRECTORS: Klaus Obermayer (Technical University Berlin, Germany) Alessandro Treves (SISSA, Trieste, Italy) Eilon Vaadia (Hebrew University, Jerusalem, Israel) Alain Destexhe (CNRS, Gif-sur-Yvette, France) The EU Advanced Course in Computational Neuroscience introduces students to the panoply of problems and methods of computational neuroscience, simultaneously addressing several levels of neural organisation, from subcellular processes to operations of the entire brain. The course consists of two complementary parts. A distinguished international faculty gives morning lectures on topics in experimental and computational neuroscience. The rest of the day is devoted to practical training, including learning how to use simulation software and how to implement a model of the system the student wishes to study on individual unix workstations. The first week of the course introduces students to essential neurobiological concepts and to the most important techniques in modelling single cells, networks and neural systems. Students learn how to apply software packages like GENESIS, MATLAB, NEURON, XPP, etc. to the solution of their problems. During the following three weeks the lectures will cover specific brain functions. Each week topics ranging from modelling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the brain will be covered. The course ends with a presentation of the students' projects. The EU Advanced Course in Computational Neuroscience is designed for advanced graduate students and postdoctoral fellows in a variety of disciplines, including neuroscience, physics, electrical engineering, computer science and psychology. Students are expected to have a basic background in neurobiology as well as some computer experience. Students of any nationality can apply. A total of 32 students will be accepted. About 20 students will be from the European Union and affiliated countries (Iceland, Israel, Liechtenstein and Norway plus all countries which are negotiating future membership with the EU). These students are supported by the European Commission and we specifically encourage applications from researchers who work in less- favoured regions of the EU and women. IBRO, ICTP and the Boehringer Ingelheim Foundation provide support for participation from students of non-European countries all over the world, IBRO and ICTP in particular countries from the former Soviet Union, Africa, Asia and South America, while The Brain Science Foundation supports Japanese students. Students receiving support from the mentioned sources will receive travel grants and free full board at the Adriatico Guest House in Trieste. More information and application forms can be obtained: http://www.neuroinf.org/courses/trieste2001.shtml Please apply electronically using a web browser if possible. - e-mail: bruns at cs.tu-berlin.de - mail: Camilla Bruns, Technical University Berlin, Department of Computer Science, Franklinstr, 28/29, 10587 Berlin, Germany Phone: +49-(0)30-314-73442 Fax: +49-(0)30-314-73121 APPLICATION DEADLINE: March 31st , 2001 Applicants will be notified of the results of the selection procedures by April 30, 2001. From Timxb at Colorado.EDU Thu Dec 21 13:53:21 2000 From: Timxb at Colorado.EDU (Brown Tim) Date: Thu, 21 Dec 2000 11:53:21 -0700 (MST) Subject: Positions in statistics and applied probability at Colorado Message-ID: <200012211853.eBLIrLu25419@pingan.Colorado.EDU> This may be of interest to connectionist in the Bayesian, Guassian Processes, MCMC, etc. side of the field. The applied math department is a mix of mathematicians, OR, CS and engnieering faculty that maintains contacts and shares students with engineering and sciences. Regards, Timothy X Brown Interdisciplinary Telecommunications Program Department of Electrical and Computer Engineering ECOT 331 Campus Box 530 University of Colorado Boulder, CO 80309-0530 Tel: (303) 492-1630 Fax: (303) 492-1112 http://ece-www.colorado.edu/~timxb Assistant Professor Applications are invited for a tenure-track assistant professorship to begin August 2001. Preference will be given to those candidates whose research emphasis is in statistics, stochastic partial differential equations or other areas of applied probability. The teaching load is three courses per year. Areas of research expertise within the Department include computational mathematics, nonlinear waves and dynamics, analysis of differential equations, physical applied mathematics, and applied probability. Further information can be found on the Department's web page, http://amath.colorado.edu/appm/. Applicants should send a letter of application, a current curriculum vitae, a statement of research interests, an AMS Standard Cover Sheet (see http://www.ams.org/employment/cover-template.doc) and three letters of recommendation (sent directly) to: Chair, Search Committee Department of Applied Mathematics 526 UCB University of Colorado Boulder CO 80309-0526 Review of applications will begin November 15, 2000 and will continue until the position is filled. The University of Colorado at Boulder is committed to diversity and equality in education and employment. >Received: from mail.fudan.edu.cn by mouse.fudan.edu.cn (5.x/SMI-SVR4) id AA04862; Fri, 22 Dec 2000 09:32:24 +0800 From ICONIP2001 at fudan.edu.cn Thu Dec 21 20:35:01 2000 From: ICONIP2001 at fudan.edu.cn (ICONIP 2001) Date: Fri, 22 Dec 2000 09:35:01 +0800 Subject: ICONIP2001 Message-ID: <3A42AFC5.6511ED03@fudan.edu.cn> Dear Colleague, The attached is the First Announcement and Call for Paper for the 8th International Conference on Neural Information Processing 2001 (ICONIP 2001) Which will be held in Shanghai, China next November. We are expecting your actively contributing. Merry Christmas and a Happy New Year Sincerely yours Fanji Gu, Prof. Chairman of Organization Committee, ICONIP 2001 First Announcement and Call for Paper for ICONIP2001 The 8th International Conference on Neural Information Processing (ICONIP2001), the annual conference sponsored by Asia-Pacific Neural Network Assembly (APNNA), IEEE Beijing Section, IEEE NN Council, INNS and China Neural Network Council (CNNC), will be held in Shanghai, China, from November 14 to 18, 2001. The local organizer is Brain Science Research Center, Fudan University, co- organized by Shanghai Biophysics Society. The theme of the conference, Neural Information Processing, is broad enough to promote wide interactions among researchers in many academic disciplines. The conference will consist of 3 and a half day oral and poster presentation, and a half-day tour. Six leading scientists in this field was invited to give keynote lectures at the conference. They are: S. Amari (Japan), W. J. Freeman (USA), E. Oja (Finland), H. Szu (USA), L. Xu (Hong Kong, China) and X. Yang (China). In addition to mathematical and engineering approaches we also include brain science and cognitive science in the main stream. The conference topics include but are not limited to: 1 Brain and Cognitive Science 1.1 Dynamic brain 1.2 Data representation and neural coding 1.3 Learning and memory 1.4 Brain imaging in cognition and behavior 1.5 Perception, emotion, and cognition 1.6 Selective attention 1.7 Vision and auditory models 1.8 Consciousness 2 Models and Algorithms 2.1 Spiking Neuron 2.2 Learning algorithms 2.3 Neural network architectures 2.4 Neurodynamics & chaotic networks 2.5 Statistical neural network models 3 Hybrid Systems 3.1 Evolutionary neural systems 3.2 Fuzzy neural systems 3.3 Soft computing 3.4 Symbolic-neural hybrid systems 4. Hardware Implementation 4.1 Analog, digital, optical & hybrid neuro-systems 4.2 Artificial retina & cochlear chips 4.3 DSP & software implementation 5 Application 5.1 Computer vision 5.2 image processing 5.3 Data mining 5.4 Expert system 5.5 Finance & electronic commerce 5.6 Human-computer interaction 5.7 Intelligent control 5.8 Natural language processing 5.9 Pattern recognition 5.10 Robotics 5.11 Sensorimotor systems 5.12 Signal processing 5.13 Speech recognization 5.14 Time series prediction 5.15 Knowledge & Rule extraction 6 Others The list of the organizing committee of the conference is as follows: Honorary Chairs S.Amari, RIKEN, Japan C.Gu, Fudan Univ., China Conference Chairs K.Fukushima, Univ. of Electro-Com, Japan Y.Wu, Tsinghua Univ., China Steering Committee Chairs T. Shou, Fudan Univ. China Y. Zhong, China Post & Telecommunication Univ., China International Advisory Committee Chairs: Z. He, South-Eastern Univ., China N. Kasabov, Univ. Of Otago, New Zealand Program Committee Chairs A. Guo, Institute of Neuroscience, China M. Tsukada, Tamagawa University, Japan L. Zhang, Fudan Univ., China Organization Committee Chairs F. Gu, Fudan Univ., China M. Zhou, CNNC, China Finance Chair Y. Shi, Fudan Univ., China The registration fee is US$420 for regular participants before the deadline, including hard copies of the proceedings, reception, one evening entertainment, free lunch, banquette, and one half-day's city tour. The registration fee for students is US$230 before the deadline, including hard copies of the proceedings, reception, one evening entertainment, free lunch. Students should pay US$70 for participating in banquette, and one half-day's city tour. Important deadlines May 1, 2001 Paper submission June 30, 2001 Acceptance notification July 31, 2001 Camera-ready manuscripts Sept. 30, 2001 Advanced registration Shanghai is the biggest city in China, and a harmonic mixture of the traditional and the modern, the east and the west. Shanghai has completely changed in the last decade. After the conference, a satellite workshop C China C Japan C Korea joint workshop on Neurobiology and Neuroinformatics co-sponsored by School of Life Sciences & Brain Science Research Center, Fudan Univ. China; Zhejiang Univ. China; BSI RIKEN, Japan and Brain Science Research Center, KAIST, Korea, will be held in Hangzhou, China, a beautiful resort city, from Nov. 20 C22. The organizers will be S. Amari (Japan), F. Gu (China), S. Lee (Korea) and Q. Tong (China). The total participants are limited to fifty, Scientists from the other countries are also welcome to participate in the workshop as disscusants. Another satellite workshop "Nonlinear signal Processing and Neural computing science" held in Nanjing, a historical resort in China, after the conference is also in organizing. The organizer is Prof. Zhenya He from South East University, China. Anyone who are interested in participating in ICONIP2001, or any of its satellite workshops, please contact the person with the following address, so that he can put your name and address into his mailing address and give you further information in time: Fanji Gu, Prof. Chairperson of the Organization Committee of ICONIP2001 Organizer of China C Japan C Korea joint workshop on Neurobiology and Neuroinformatiocs Department of Physiology & Biophysics Fudan University Shanghai 200433 P. R. China Tel: +86-21-65642813 (O) +86-21-65298260 (H) Fax: +86-21-65298260 E-mail: ICONIP2001 at fudan.edu.cn For more details, please use the following Web address: http://www.cie-china.org/ICONIP2001 or http://EE.fudan.edu.cn/ICONIP2001 From mieko at isd.atr.co.jp Fri Dec 22 00:49:41 2000 From: mieko at isd.atr.co.jp (Mieko Namba) Date: Fri, 22 Dec 2000 14:49:41 +0900 Subject: Neural Networks 13(10) Message-ID: NEURAL NETWORKS 13(10) --------------------------------------------------------- CONTRIBUTED ARTICLES: ***** Mathematical and Computational Analysis ***** Independent component analysis for noisy data - MEG data analysis S. Ikeda, K. Toyama Generalized radial basis function networks for classification and novelty detection: self-organization of optimal Bayesian decision S. Albrecht, J. Busch, M. Kloppenburg, F. Metze, P. Tavan Nonlinear canonical correlation analysis by neural networks W.W. Hsieh Modular neural networks for non-linearity recovering by the Haar approximation Z. Hasiewicz On stability of nonlinear continuous-time neural networks with delays H. Lu Fuzzy lattice neurocomputing (FLN) models V.G. Kaburlasos, V. Petridis ***** Engineering and Design ***** Rule extraction by successive regularization M. Ishikawa ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 or 660 SEK or Y 15,000 [including Neural Networks 2,000 entrance fee] or $55 (student) 460 SEK (student) Y 13,000 (student) [including 2,000 entrance fee] ----------------------------------------------------------------------------- membership without $30 200 SEK not available to Neural Networks non-students (subscribe through another society) Y 5,000 (student) [including 2,000 entrance fee] ----------------------------------------------------------------------------- Institutional rates $1132 2230 NLG Y 149,524 ----------------------------------------------------------------------------- Name: _____________________________________ Title: _____________________________________ Address: _____________________________________ _____________________________________ _____________________________________ Phone: _____________________________________ Fax: _____________________________________ Email: _____________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number ____________________________ expiration date ________________________ INNS Membership 19 Mantua Road Mount Royal NJ 08061 USA 856 423 0162 (phone) 856 423 3420 (fax) innshq at talley.com http://www.inns.org ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership c/o Professor Tsukada Faculty of Engineering Tamagawa University 6-1-1, Tamagawa Gakuen, Machida-city Tokyo 113-8656 Japan 81 42 739 8431 (phone) 81 42 739 8858 (fax) jnns at jnns.inf.eng.tamagawa.ac.jp http://jnns.inf.eng.tamagawa.ac.jp/home-j.html ----------------------------------------------------------------- From georg at ai.univie.ac.at Fri Dec 22 05:53:24 2000 From: georg at ai.univie.ac.at (Georg Dorffner) Date: Fri, 22 Dec 2000 11:53:24 +0100 Subject: Open post-doc in economic modeling Message-ID: <3A4332A4.2CD437D0@ai.univie.ac.at> Merry Christmas to everyone!! The Neural Networks Group at the Austrian Research Institute for Artificial Intelligence in Vienna, Austria, has an immediate opening for a post-doc position in Agent-based economic modeling as part of the larger initiative "Adaptive Models in Economics and Management Science" (http://www.wu-wien.ac.at/am/). The goal is to investigate different approaches to modeling learning economic agents, among them neural networks, in a larger-scale simulation of partial economics including customers, firms and a financial market. A particular focus is on cognitvely plausible models of learning and knowledge. Some background on our own previous work, as well as on related work world-wide can be found at http://www.wu-wien.ac.at/am/ae.htm. Required background: - an education in computer science, mathematics or economics - programming experience (e.g. C++ or, in particular, Matlab) - a basic background in economics - a doctorate degree - research experience (preferably in agent-based simulation, complex systems, or related areas) Desired (but optional) background: - publications in the field - basic knowledge in neural networks and machine learning - basic knowledge in cognitive modeling - basic understanding knowledge of German The position will be limited to a little more than 2 years (March 2003), but with a good option to be extended thereafter. The monthly salary offered amounts to approx. ATS 24.500 (Euro 1780) after tax. Interested applicants should apply by email, mail or fax, no later than January 15, 2001, at the address below. Include a short vita, a list of publications, and any other information demonstrating your qualification. Send applications to: Georg Dorffner Austrian Research Institute for Artificial Intelligence Schottengasse 3 A-1010 Vienna phone: +43-1-4277-63116 fax: +43-1-4277-9631 email: georg at ai.univie.ac.at This position is funded by the Austrian Fonds zur Foerderung der wissenschaftlichen Forschung (FWF). From ijspeert at usc.edu Fri Dec 22 06:18:59 2000 From: ijspeert at usc.edu (ijspeert) Date: Fri, 22 Dec 2000 03:18:59 -0800 (PST) Subject: PhD studentships in computational motor control at USC, Los Angeles Message-ID: ---------------------------------------------------------------------------- Ph.D. Graduate Research Assistantships Available in Computational Motor Control, Rehabilitation Robotics and Humanoid Robotics at the University of Southern California ----------------------------------------------------------------------------- We are looking for outstanding Ph.D. graduate students for interdisciplinary projects in the area of computational motor control, rehabilitation robotics, and humanoid robotics. The projects will be conducted in collaboration with Dr. Auke Ijspeert (USC, Computer Science and Neuroscience), Dr. Stefan Schaal (USC, Computer Science and Neuroscience), and Dr. Carolee Winstein (USC, Kinesiology, Rehabiliation, and Neuroscience) and also the Kawato Dynamic Brain Project at ATR in Japan. The Ph.D. graduate students will receive a Research Assistantship and join and interdisciplinary team of researchers to work on topics of movement imitation, developing graphical simulations for motor control, movement rehabilitation with stroke-patients, models of human motor control and learning, and computational neuroscience for motor control in general. In the course of this work, a Ph.D. can be obtained in either Computer Science (with focus Neural Computation), Biomedical Engineering, Computational Neuroscience, or Biokinesiology and Physical Therapy. The successful candidate should have a good background in basic mathematics and statistics and a strong interest in the topics of motor control and computational neuroscience. Experimental skills are highly desirable, and proficiency in the use of computers, C-programming, and use of tools like Matlab and Mathematica are needed. The candidate will be required to pass the graduate admission of the department of her/his choice. The openings will be filled ASAP. Please, contact Dr. Ijspeert (ijspeert at usc.edu), Dr. Schaal (sschaal at usc.edu), or Dr. Winstein (winstein at hsc.usc.edu) for inquiries. An official application including an up-to-date CV, statement of interest, transcripts, and three letters of recommendation will be required and sent to: Dr Auke Ijspeert University of Southern California Hedco Neuroscience Bdg, 3641 Watt Way, MC 2520 Los Angeles, CA 90089-2520, USA Please, also visit our web pages at: http://www-slab.usc.edu From luciano at if.sc.usp.br Fri Dec 22 12:15:51 2000 From: luciano at if.sc.usp.br (Luciano Da Fontoura Costa) Date: Fri, 22 Dec 2000 15:15:51 -0200 (EDT) Subject: research opportunities Message-ID: Dear Sir/Madam: Please help disseminating the following message: ==================================================================== *** OPPORTUNITY FOR POST-GRAD, POST-DOC AND SABBATICAL STUDIES *** *** FOR 2001 *** COMPUTER VISION VISUAL INSPECTION PATTERN RECOGNITION DATAMINING DIGITAL SIGNAL PROCESSING NEUROMORPHIC MODELING NEUROMORPHOMETRY SHAPE ANALYSIS BIOINFORMATICS Cybernetic Vision Research Group IFSC, University of Sao Paulo, Caixa Postal 369 Sao Carlos, SP, 13560-970, Brazil http://cyvision.if.sc.usp.br/ ____________________________________________________________________ THE CYBERNETIC VISION RESEARCH GROUP: Started in 1993, the Cybernetic Vision Research Group has become nationally and internationally renowned for research in the areas of shape analysis, computer and biological vision, and computational neuroscience. The group currently includes 15 researchers, most of them MSc and PhD students, each with access to individual computational resources. The group is part of the Instituto de Fisica de Sao Carlos, which has modern computational and network resources (alpha workstations) as well as a well-equipped library. The group has many collaborators and has an active participation in publishing and consulting, including major companies and publishers. Additional information can be found at the following homepages: *** Group homepage: http://cyvision.if.sc.usp.br/ *** Luciano's personal homepage: http://www.if.sc.usp.br/visao/group/members/luciano/luciano.htm SAO CARLOS: Sao Carlos, where the group is based, is a small and quiet town (about 150 000 inhabitants) in the heart of the state of Sao Paulo, in Brazil. The university campus is within a residential area, where accommodation is very affordable. Our town, which includes two major Brazilian universities as well as many industries, is know as one of the most prominent Brazilian high-technology centers. Sao Carlos is not far from Sao Paulo (230km), the state capital, where flights to most Brazilian and international destinations can be found. Weather is mild (no snow throughout the year), with an average temperature around 20C. RESEARCH POSSIBILITIES: Well-motivated and dynamic students and researchers, with background in the most diverse areas - including Physics, Mathematics, Computer Science, Engineering, Biology, and Medicine - are welcome to apply for studies in the group. The full time MSc and PhD programs last up to 2 and 4 years, respectively, but it is possible to proceed directly to PhD. Post-doc and sabbatical programs can last from a few months to one year or more. It is possible to apply for Brazilian sponsorship covering travelling and/or the basic living expenses. The approximated grant values are as follows (please note these are maximum values that can vary substantially depending on the exchange rate and grant sponsor): Master (1st year): US$ 500 per month Master (2nd year): US$ 520 per month PhD (initial years): US$ 700 per month PhD (initial years): US$ 850 per month Post-Doc: US$ 1250 per month Living expenses can be as low as US$ 150 per month (shared accomodation near the university). Medical assistance and is available free of charge for some student categories. All the above courses are free and involve no bech or other fees. Research possibilities include but are not limited to the following: *1* Neuromorphology and neuromorphic modeling: development of new neural shape measures, validation, and application to classification of neural cells and neuromorphic modeling. We are particularly interested in investigating how neural shapes constrain and help define neural behavior; *2* Scale space shape representations in 2D and 3D, including multiresolution curvature and skeletonization, singularity theory, differential geometry and differential equations; *3* Visual inspection and image analysis applied to microscopy; *4* Mathematical physics applications to image analysis and vision; *5* Datamining and its applications to visual design, visual quality assessment, bioinformatics, neural modeling, and shape analysis. Well-motivated candidates should contact Prof Luciano da F. Costa at luciano at if.sc.usp.br, indicating the specific interests and including curricular information as well as at least two addresses for recommendation purposes. Please observe there is a limited number of places, to be filled according to the students previous performance and research interests. ===================================================================== Prof. Luciano da Fontoura Costa Coordinator - Cybernetic Vision Research Group DFI-IFSC, Universidade de Sao Paulo Caixa Postal 369 Sao Carlos, SP 13560-970 Brazil FAX: +55 162 73 9879 or +55 162 71 3616 e-mail: luciano at if.sc.usp.br Group homepage: http://cyvision.if.sc.usp.br/ Personal homepage: http://cyvision.if.sc.usp.br/~luciano --------------------------------------------------------------------- The forthcoming book "Shape Analysis and Classification" (CRC Press) can already be ordered from Amazon: http://www.amazon.com/exec/obidos/ASIN/0849334934/o/qid=970355824/ sr=8-1/ref=aps_sr_b_1_3/002-1526960-8848802 See also: http://www.ime.usp.br/~cesar/shape_crc/ ===================================================================== END OF MESSAGE ============== From shai at cs.Technion.AC.IL Wed Dec 27 07:46:26 2000 From: shai at cs.Technion.AC.IL (Shai Ben-David) Date: Wed, 27 Dec 2000 14:46:26 +0200 (IST) Subject: Workshop on Computational Complexity of Learning Message-ID: <200012271246.OAA18200@cs.Technion.AC.IL> Alpine Workshop on Computational Complexity Aspects of Learning. March 26-29, 2001. Sestriere, Italy. While being recognized as an important component of Computational Learning, the computational complexity of learning has seen very few definite answers (as opposed to the pretty clear picture that we have of sample complexity and generalization issues). The aim of the workshop is to bring together active researchers in the COLT area to outline the current knowledge on these questions, and to stimulate ideas for further research. The workshop will include three invited talks, by Avrim Blum, Sanjoy Dasgupta and Phil Long, as well as an inroductory tutorial. Most of the time will be devoted to contributed talks by the workshop participants. We plan to have morning sessions and afternoon sessions with generous ski breaks between them. The workshop will be held in Sestriere (www.stm.it/sestriere), one of the most famous Italian ski resorts, located in the Western Alps. To participate, please complete the registration form below and send it to Nicolo` Cesa-Bianchi (cesabian at dsi.unimi.it) before January 20, 2001. Registration fees are 50eu per person. If you want to buy a ski-pass at a discounted price, please check the box in the registration form. We have made an arrangement with "Hotel Biancaneve", Via Cesana, 12. Sestriere, +39-0122-755176. To book a room there please send a fax *BEFORE JANUARY 20* at +39-0122-755152 mentioning "Neurocolt" as group name and including a credit card number for the deposit. The rates (half-board) are: Single room from 3/25 to 3/29 (4 nights): ITL 440,000 per person Double room from 3/25 to 3/29(4 nights): ITL 300,000 per person Extra days: ITL 115,000 (single) and ITL 80,000 (double) You are welcome to contact us for any further information Nicolo' (cesabian at dsi.unimi.it) and Shai (shai at cs.technion.ac.il) ---------------------------------------------------------------- NeuroCOLT Workshop at Sestriere - Registration Form (mail to: cesabian at dsi.unimi.it) =================================================== First name: Last name: Affiliation: Email: Arrival date: Departure date: Giving a talk (yes/no): Title of the talk: Skipass (yes/no): From juergen at idsia.ch Wed Dec 27 10:47:37 2000 From: juergen at idsia.ch (juergen@idsia.ch) Date: Wed, 27 Dec 2000 16:47:37 +0100 Subject: inductive inference, fast computations, Kolmogorov, Occam Message-ID: <200012271547.QAA21385@ruebe.idsia.ch> We generalize Kolmogorov complexity and study the fastest way of computing all computable objects, with consequences for inductive inference, Occam's razor, and the big picture. This might be of interest to machine learners, theoretical computer scientists, mathematicians, physicists, and philosophers. All comments are welcome. Algorithmic Theories of Everything Juergen Schmidhuber http://www.idsia.ch/~juergen The probability distribution P from which the history of our universe is sampled represents a theory of everything or TOE. We assume P is formally describable. Since most (uncountably many) distributions are not, this imposes a strong inductive bias. We show that P(x) is small for any universe x lacking a short description, and study the spectrum of TOEs spanned by two Ps, one reflecting the most compact constructive descriptions, the other the fastest way of computing everything. The former derives from generalizations of traditional computability, Solomonoff's algorithmic probability, Kolmogorov complexity, and objects more random than Chaitin's "number of wisdom" Omega, the latter from Levin's universal search and a natural resource-oriented postulate: the cumulative prior probability of all x incomputable within time t by this optimal algorithm should be 1/t. Between both Ps we find a universal cumulatively enumerable measure that dominates traditional enumerable measures; any such CEM must assign low probability to any universe lacking a short enumerating program. We derive P-specific consequences for observers evolving in computable universes, inductive reasoning, quantum physics, and philosophy, predicting that whatever seems random (e.g., beta decay) is not, but in fact is computed by a short and fast algorithm which will probably halt before our universe is many times older than it is now. ------------------------------------------------------------------------ TR IDSIA-20-00, Version 2.0, 20 Dec 2000; 10 theorems, 50 pages, 100 refs (minor revision of 1.0, Nov 2000, http://arXiv.org/abs/quant-ph/0011122) ftp://ftp.idsia.ch/pub/juergen/toesv2.ps.gz (gzipped postscript, 156K) ftp://ftp.idsia.ch/pub/juergen/toesv2.ps (postscript, 515K) ftp://ftp.idsia.ch/pub/juergen/toesv2.tex.gz (gzipped latex, 52K) ftp://ftp.idsia.ch/pub/juergen/toesv2.tex (latex, 155K) ftp://ftp.idsia.ch/pub/juergen/toesv2.dvi.gz (gzipped dvi, 91K) ftp://ftp.idsia.ch/pub/juergen/toesv2.dvi (dvi, 244K) ftp://ftp.idsia.ch/pub/juergen/toesv2.pdf.gz (gzipped pdf, 395K) ftp://ftp.idsia.ch/pub/juergen/toesv2.pdf (pdf, 539K) http://www.idsia.ch/~juergen/onlinepub.html (various formats) PS: I am also seeking two new postdocs, please see the announcement in http://www.idsia.ch/~juergen/postdocs2001.html From patrickw at cs.monash.edu.au Wed Dec 27 22:48:28 2000 From: patrickw at cs.monash.edu.au (Patrick Wilken) Date: Thu, 28 Dec 2000 13:48:28 +1000 Subject: CFP: ASSC5 - The Contents of Consciousness Message-ID: ASSOCIATION FOR THE SCIENTIFIC STUDY OF CONSCIOUSNESS 5TH ANNUAL MEETING CALL FOR PAPERS & WORKSHOPS THE CONTENTS OF CONSCIOUSNESS Perception, Attention, and Phenomenology May 27-30, 2001 Duke University Durham, North Carolina, USA Consciousness has rich and diverse contents, from sensory experiences such as vision, audition, and bodily sensations such as pain, to non-sensory aspects such as volition, emotion, memory, and thought. All of these conscious states can be seen as part of the contents of consciousness. Furthermore, most conscious states can be seen as having representational contents of their own, in the sense that they are about something: objects and states of affairs in the world, or states of our own body. The contents of these states are all presented to us, in William James's powerful metaphor, as part of a "stream of consciousness". The contents of consciousness raise many important questions: Just how rich is the content present in conscious experience? Do the contents of attention exhaust the contents of consciousness, or is there consciousness outside attention? What is the neural basis of the representation of conscious content? How does consciousness of our own body differ from consciousness of the external world? What methods are available to monitor the contents of consciousness in an experimental context? What is the relationship between consciousness and representation? All of these questions have been actively discussed in recent years by neuroscientists, psychologists, philosophers, and other researchers. The fifth conference of the Association for the Scientific Study of Consciousness will bring together researchers from numerous disciplines to discuss the contents of consciousness through an intensive series of workshops, plenary lectures, symposia, paper presentations and poster contributions extending over four days from May 27 through May 30, 2001. The meeting will take place in Durham, North Carolina, on the campus of Duke University. Topics that will be addressed include (among many others): * The relationship between attention and consciousness * The neural basis of attention and consciousness * The neural mechanisms of conscious representation * Current directions in inattentional and change blindness * The relationship between conscious and unconscious contents * Bodily awareness and pain perception * The relationship between consciousness, qualia, and representation * First-person and third-person methods for monitoring conscious contents A partial list of plenary speakers (to be expanded) includes: Larry Weiskrantz (OXFORD, Experimental Psychology) Earl Miller (MIT, Brain and Cognitive Sciences) Greg McCarthy (DUKE, Brain Imaging and Analysis Center) Ralph Adolphs (IOWA, Neurology) Jeremy Wolfe (HARVARD, Center for Ophthalmic Research) Ron Rensink (UBC, Psychology and Computer Science) Owen Flanagan (DUKE, Philosophy) William Lycan (UNC, Philosophy) For latest updates, please check our website: http://www.duke.edu/philosophy/assc5.html The web site will be continually evolving, so please visit often for updated information about the conference. -------------------------- CALL FOR PAPER SUBMISSIONS -------------------------- Although the main theme of ASSC5 is "The Contents of Consciousness" and plenary sessions will deal largely with this theme, speakers in concurrent sessions are invited to talk on any topic relevant to the scientific study of consciousness. Submissions that include physiological, psychological, philosophical, and computational perspectives are welcome. Submissions for both posters and talks will be accepted. Any person may present only one submission, but may be co-author on several. The first author should be the presenting author. Oral presentations will be limited to 20 minutes, to be followed by a 10-minute discussion period. Plenary lectures, symposia, concurrent sessions, and poster sessions will all be held on the Duke University campus. --------------------------- CALL FOR WORKSHOP PROPOSALS --------------------------- This is also a call for workshops. One of the aims of this meeting is to allow researchers to gain a background in areas that they may know little about. Towards that end a number of workshops are planned. Some participants in the conference would be very interested in learning about technical matters such as fMRI or other important brain imaging techniques. Others might enjoy a seminar on a philosophical topic. As with papers, the focus of all workshops should naturally fit within the overall theme of the conference. A non-exclusive list of possible topics might include: -- Brain imaging techniques (e.g. fMRI, EEG, MEG, ERP) -- Blindsight, neglect, or other neuropsychological syndromes -- Computational and other theoretical models of conscious processes -- Conscious and unconscious processing -- Neural basis of attention and consciousness -- Current models of the visual system -- Consciousness and metacognition -- Criteria for the ascription of consciousness -- Philosophical issues concerning consciousness and representation -- Phenomenological methods for investigating consciousness Workshops will be held in parallel sessions on the morning and afternoon of May 27th. Each workshop is intended to last approximately three hours. The sizes of workshops will vary between a minimum of 10 to a maximum of around 25 people. Workshops that do not achieve the minimum enrollment of 10 people will not be offered. Workshop presenters will receive a $500 honorarium. ----------------------------------------- SUBMISSION OF PAPERS & WORKSHOP PROPOSALS ----------------------------------------- WORKSHOP PROPOSALS MUST BE RECEIVED BY JANUARY 31, 2001. Send Workshop presentation abstracts to: metzinger at uni-mainz.de PAPER SUBMISSIONS MUST BE RECEIVED BY FEBRUARY 15th, 2001. Send Oral (paper) or Poster presentation abstracts to: assc5 at duke.edu All submissions must include the following information in the order listed below and MUST BE SUBMITTED ELECTRONICALLY. Please note that there are two different addresses for paper and workshop proposal submissions: *** Note: Please reserve these addresses exclusively for submission of abstracts. Questions concerning the conference can be sent to: fb3 at duke.edu --------------------- SUBMISSION GUIDELINES --------------------- 1. Conference ID (i.e., ASSC5), SURNAME of first author and descriptor (WORKSHOP or PAPER/POSTER) in the "subject" field of the email header. e.g.: ASSC5, Smith, WORKSHOP 2. Name (first line), affiliation (second line), and ASSC membership status of each co-author indicated with asterisk (asterisk = member). e.g.: Smith, A.B.* and Jones, C.D. University of Oxford, U.K. 3. An abstract of up to 200 words for paper and poster submissions or of up to 500 words for workshop proposals. 4. Complete contact information for the author with whom the scientific program committee will interact with about the submission: - Name - Institutional affiliation - Postal address - Email address - Telephone and fax numbers In addition paper and poster proposals should include the following information: 5. One or two keywords describing the domain of your contribution 6. An indication of whether an ORAL or POSTER presentation is requested. 7. An indication of your willingness to present in the other format if your proposal cannot be included in the program as per your stated preference. 8. If you do not receive confirmation of receipt of your submission in 10 days, send an e-mail inquiry to: fb3 at duke.edu. ------------ REGISTRATION ------------ Deadline for early registration: April 1, 2001. Registration fees: Early Late Non-members: $ 175 $ 225 ASSC members: $ 140 $ 190 Students/Postdocs: $ 75 $ 125 Student ASSC members: $ 40 $ 90 Note: All fees should be paid in U.S. dollars. Payment with credit cards will be possible. To register, please follow the instructions available from the conference website as they become available: http://www.duke.edu/philosophy/assc5.html ------------------- FURTHER INFORMATION ------------------- All meetings and poster presentations will be held at the Duke University campus. Accommodations will be available both at Durham hotels at discounted rates and at air-conditioned single/double Duke dormitories. Please check the website for information about accommodation options, as well as for further information about the paper and poster submissions; registration and submission forms; information about travel to Durham, North Carolina; and information about the scientific Program of the meeting. Tune in frequently -- the site will be constantly updated to reflect the latest information. To inquire about any aspect of the conference, please write to the local organizer at: fb3 at duke.edu To find out more about the Association for the Scientific Study of Consciousness, and to apply for membership, please consult: http://assc.caltech.edu The ASSC publishes two scientific journals about which further information is available from the following websites: Consciousness & Cognition: http://www.apnet.com/www/journal/cc.htm PSYCHE: http://psyche.cs.monash.edu.au/ ASSC-5 Conference Committee: Guven Guzeldere (Duke University, co-chair) Ron Mangun (Duke University, co-chair) David Chalmers (University of Arizona) Philip Merikle (University of Waterloo) Thomas Metzinger (Johannes Gutenberg-Universitat Mainz) From Marc.VanHulle at med.kuleuven.ac.be Thu Dec 28 07:46:30 2000 From: Marc.VanHulle at med.kuleuven.ac.be (Marc Van Hulle) Date: Thu, 28 Dec 2000 13:46:30 +0100 Subject: postdoc in biomedical signal-processing and neuroimaging Message-ID: <3A4B3626.C95895A1@neuro.kuleuven.ac.be> ------------------------------------------------------------------- Postdoctoral position biomedical signal-processing and neuroimaging ------------------------------------------------------------------- Deadline for application: 30 January 2001 The Computational Neuroscience Group of the Laboratory of Neuro- and Psychophysiology, Medical School of the Catholic University of Leuven, Belgium (http:\\simone.neuro.kuleuven.ac.be), invites applications for a post-doctoral position in the area of biomedical signal-processing and neuroimaging (functional Magnetic Resonance Imaging). Desired profile: The highly qualified applicant should possess a Ph.D. degree in the field of signal-processing, image-processing, statistics, or neural networks. He/she should be familiar with Independent Components Analysis (ICA), and have a profound knowledge of both uni-variate statistics and multi-variate statistics. Programming skills are an asset (C, Matlab, ...), as is a familiarity with UNIX and PC platforms. We offer: 1) A challenging research environment. The applicant will have access to data from state-of-the-art Magnetic Resonance scanners and advanced statistical tools such as SPM (Statistical Parameter Mapping) for examining brain activity in both human and monkey. 2) An attractive income. The applicant will receive 2000 USD or 2375 Euro per month, including a full social security coverage. This is comparable to the salary of an associate Professor at the University. Housing will be taken care of by the host institute. 3) Free return airline ticket, economy class (maximum 1250 USD or 1500 Euro) and a reimbursement of all costs incurred for shipping luggage to Belgium (maximum 850 USD or 1000 Euro). Send before the deadline of 15 January 2001 your CV (including the names and contact information of three references), bibliography and how to contact you by mail/fax/email/phone to: Prof. Dr. Marc M. Van Hulle K.U.Leuven Laboratorium voor Neuro- en Psychofysiologie Faculteit Geneeskunde Campus Gasthuisberg Herestraat 49 B-3000 Leuven Belgium Phone: + 32 16 345961 Fax: + 32 16 345993 E-mail: marc at neuro.kuleuven.ac.be URL: http://simone.neuro.kuleuven.ac.be