From ken at phy.ucsf.edu Fri Sep 1 01:51:27 2000 From: ken at phy.ucsf.edu (Ken Miller) Date: Thu, 31 Aug 2000 22:51:27 -0700 (PDT) Subject: Paper Available: Spike-Timing-Dependent Synaptic Plasticity Message-ID: <14767.17375.399269.617735@coltrane.ucsf.edu> The following paper is available as ftp://ftp.keck.ucsf.edu/pub/ken/STDP.ps (postscript) ftp://ftp.keck.ucsf.edu/pub/ken/STDP.ps.gz (compressed postscript) or from my home page http://www.keck.ucsf.edu/~ken (click on 'publications') "Competitive Hebbian Learning Through Spike-Timing Dependent Synaptic Plasticity", by Sen Song, Kenneth D. Miller and L. F. Abbott. This is a preprint (final draft) of an article that has appeared as Nature Neuroscience 3:919-926 (2000). ABSTRACT: Hebbian models of development and learning require both activity-dependent synaptic plasticity and a mechanism that induces competition between different synapses. Recent experiments have characterized a form of long-term synaptic plasticity that depends on the relative timing of pre- and postsynaptic action potentials, which we call spike-timing dependent plasticity (STDP). In modeling studies, we find that this form of synaptic modification can automatically balance synaptic strengths to make postsynaptic firing irregular but more sensitive to presynaptic spike timing. It has been argued that neurons in vivo operate in such a balanced regime. Synapses subject to STDP compete for control of the timing of postsynaptic action potentials. Inputs that fire the postsynaptic neuron with short latency or that act in correlated groups are able to compete most successfully and develop strong synapses, while the synapses of longer latency or less effective inputs are weakened. Ken Kenneth D. Miller telephone: (415) 476-8217 Associate Professor fax: (415) 476-4929 Dept. of Physiology, UCSF internet: ken at phy.ucsf.edu 513 Parnassus www: http://www.keck.ucsf.edu/~ken San Francisco, CA 94143-0444 From abrowne at lgu.ac.uk Mon Sep 4 10:10:35 2000 From: abrowne at lgu.ac.uk (Tony Browne) Date: Mon, 4 Sep 2000 15:10:35 +0100 (GMT Daylight Time) Subject: SI on Symbol Processing Message-ID: Special issue of the journal 'Expert Systems: The International Journal of Knowledge Engineering and Neural Networks' on Symbol Processing in Connectionist Systems. Volume 17, No. 1. 2000. ISSN: 0266-4720. Contents: Editorial: Antony Browne. A connectionist production system which can perform both modus ponens and modus tollens simultaneously. Minoru Asogawa. Connectionist symbolic rule encoding using a generalized phase-locking mechanism. Nam Seog Park. Analogy retrieval and processing with distributed vector representations. Tony A. Plate. Fractal encoding of context-free grammars in connectionist networks. Whitney Tabor. http://www.sp.uconn.edu/~ps300vc/papers.html Order from: Marketing Manager, Blackwell Publishers, 108 Cowley Road, Oxford OX4 1JF, UK. ======================================================= Dr. Antony Browne School of Computing, Information Systems & Mathematics London Guildhall University 100 Minories London EC3 1JY, UK Tel: (+44) 0207 320 3106 Fax: (+44) 0207 320 1717 ======================================================= From A.van.Ooyen at nih.knaw.nl Tue Sep 5 10:06:45 2000 From: A.van.Ooyen at nih.knaw.nl (Arjen van Ooyen) Date: Tue, 05 Sep 2000 16:06:45 +0200 Subject: New Paper Message-ID: <39B4FDF4.7581671C@nih.knaw.nl> New Paper: Development of Nerve Connections under the Control of Neurotrophic Factors: Parallels with Consumer-Resource Systems in Population Biology. Arjen van Ooyen & David J. Willshaw, J. Theor. Biol. (2000) 206: 195-210. Download in gzipped PostScript format or PDF format from: http://www.anc.ed.ac.uk/~arjen/competition.html or request reprint: A.van.Ooyen at nih.knaw.nl Abstract -------- We show that a recently formulated model of axonal competition can be rewritten as a general consumer-resource system. This allows neurobiological phenomena to be interpreted in population biological terms and, conversely, results from population biology (where competition is better understood) to be applied to neurobiology. Using findings from population biology, we study two extensions of our axonal competition model. In the first extension, the spatial dimension of the target is explicitly taken into account. We show that distance between axons on their target mitigates competition and permits the coexistence of axons. The model can account for the fact that, in many types of neurons, a positive correlation exists between the size of the dendritic tree and the number of innervating axons surviving into adulthood. In the second extension, axons are allowed to respond to more than one neurotrophic factor. We show that this permits competitive exclusion within one type of axons, while at the same time there is coexistence with a different type of axons innervating the same target. The model offers an explanation for the innervation pattern found on cerebellar Purkinje cells, where climbing fibres compete with each other until only a single one remains, which coexists with parallel fibre input to the same Purkinje cell. -- Arjen van Ooyen, Netherlands Institute for Brain Research, Meibergdreef 33, 1105 AZ Amsterdam, The Netherlands. email: A.van.Ooyen at nih.knaw.nl website: http://www.anc.ed.ac.uk/~arjen phone: +31.20.5665483 fax: +31.20.6961006 From Jean-Pierre.Nadal at lps.ens.fr Tue Sep 5 08:04:38 2000 From: Jean-Pierre.Nadal at lps.ens.fr (Jean-Pierre Nadal) Date: Tue, 5 Sep 2000 14:04:38 +0200 (CEST) Subject: Call for papers DYNN2000 Message-ID: Call for papers --------------- DYNN'2000 INTERNATIONAL WORKSHOP ON "DYNAMICAL NEURAL NETWORKS AND APPLICATIONS" Bielefeld, November 20-24, 2000 http://www.cert.fr/anglais/deri/dauce/DYNN2000 contact: samuelid at supaero.fr OBJECTIVE ---------- Dynamics is a major feature of neural modeling. The study of neural networks viewed as dynamical systems evolving under environmental pressure is an attractive perspective to overcome the limitations of classical artificial neural networks especially in the fields of vision and control. Different disciplines are involved, such as dynamical systems theory, statistical physics, neurobiology, information theory and adaptive control. The DYNN workshop is a place where neurobiologists, theoreticians and engineers can exchange ideas and transfer knowledge. The first international workshop DYNN'96 took place in ONERA in Toulouse, France, and was the occasion to compare theoretical studies and models of visual cortex with more general perceptual devices. The second workshop VI'DYNN'98 in Stockholm focused on Pulse Coupled Neural Networks and was dedicated to more applied tasks of image processing and computervision. The oncoming edition DYNN'2000 keeps all these themes and will introduce new concepts from the physics of "Self-organized Criticality" which describes the spatio-temporal self-organization of coupled automata. DYNN'2000 will take place at the ZIF in Bielefeld University from 11/20/2000 to 11/24/2000 in the frame of the Forschungsgruppe "The Sciences of Complexity: From Mathematics to Technology to a Sustainable World" (http://www.uni-bielefeld.de/ZIF/complexity/complexity.html). Interested researchers are invited to participate to the workshop and to present their contribution. TOPICS ------ Submissions of papers related, but not limited, to the technical areas and subareas listed below are invited. 1.Neural Networks Dynamics and Self Organization. 2.Mean Field Theory for Large Stochastic Networks. 3.Information Properties of Dynamical Neural Networks. 4.Spiking Neurons and Temporal Coding. 5.Applications of Dynamical Neural Networks for Planning and Control 6.Applications of Dynamical Neural Networks to computer vision. ORGANIZATION OF THE WORKSHOP ---------------------------- The workshop is organized during five days and will reserve plenty of time for discussion and interaction among attendants. Special attention will be provided to the formation of young researchers and doctorate students. To fulfill this objective, there will be one day reserved to tutorials and then three types of presentations: * Invited conferences (one hour) will give a large review of the subject and will introduce to ongoing research. They will be designed to allow all the participants coming from different fields to follow all the sessions. * Regular presentations (40 minutes including questions) will be dedicated to present relatively mature work and will be given mostly by invited lecturers. * Short presentations (20 minutes) are specially designed to allow young researchers to present the main ideas of their research project and favor discussion and exchange. Normally short presentations will be associated with posters that allow further interaction between participants. PROGRAM COMMITTEE ------------------ Manuel SAMUELIDES, Chairman - ONERA/ENSAE, Toulouse, France. Manuel.Samuelides at supaero.fr Philippe BLANCHARD - Bielefeld, Germany. blancblanchard at Physik.Uni-Bielefeld.DE Bruno CESSAC - INLN, Nice, France. cessac at inln.cnrs.fr Jacques DEMONGEOT - IUF/CNRS Grenoble, France. Celine.Fontant at imag.fr Philippe GAUSSIER - Cergy-Pontoise, France. gaussier at ensea.fr John JOHNSON - US Army, Germany. science at hq.c5.army.mil Jean-Pierre NADAL - ENS/CNRS, Paris, France. nadal at lps.ens.fr Simon THORPE - CERCO/CNRS, Toulouse, France. thorpe at cerco.ups-tlse.fr John TAYLOR - King's college, London, UK. john.g.taylor at kcl.ac.uk CALENDAR -------- Expression of interest : from now on Extended abstract submission deadline: September 29, 2000 Notification to the authors : October 14, 2000 Early registration : Until october 31, 2000 Date of the workshop : November 20. to 24., 2000 SUBMISSION ---------- The overall submission mode is electronic. Visit our website: http://www.cert.fr/anglais/deri/dauce/DYNN2000 Fill the expression of interest form to be informed about the workshop. The abstracts will be refereed and the accepted papers will be available on the WEB. We are currently investigating the possibility of publishing selected papers in the form of a collective book. Send extended abstract, with respect to format recommandations , 2 pages max, in electronic form (see recommandations on the web site) before September 29th, 2000 to perrinet at cert.fr along with a submission form. -- Manuel SAMUELIDES Professeur a l'ENSAE Ingenieur de recherche a l'ONERA ----------------------------------------------------------------- Answer please to the following email address: samuelid at supaero.fr DYNN2000 website: http://www.cert.fr/anglais/deri/dauce/DYNN2000 ----------------------------------------------------------------- From bert at mbfys.kun.nl Wed Sep 6 05:06:04 2000 From: bert at mbfys.kun.nl (bert@mbfys.kun.nl) Date: Wed, 6 Sep 2000 11:06:04 +0200 Subject: jobs available at SNN Message-ID: <200009060906.LAA03759@anthemius.mbfys.kun.nl> Post doc and research programmer positions available at SNN, University of Nijmegen, the Netherlands. Background: The group consists of 10 researchers and PhD students and conducts theoretical and applied research on neural networks and Bayesian methods. The group is part of the Laboratory of Biophysics which is involved in experimental brain science. Recent research of the group has focused on theoretical description of learning processes using the theory of stochastic processes and the design of efficient learning rules for Boltzmann machines and other graphical models using techniques from statistical mechanics; the extraction of rules from data and the integration of knowledge and data for modeling; the design of robust methods for confidence estimation with neural networks. Applied research is conducted on computer assisted medical diagnosis, music modeling, genetics and time-series prediction tasks. Since 1997, SNN Nijmegen has founded a company which sells commercial services and products in the field of neural networks, AI and statistics. For more information see http://www.smart-research.nl and http://www.mbfys.kun.nl/SNN Job specifications: POST-DOCTORAL FELLOW The tasks of the post-doc will be to conduct independent research in one of the above areas. In addition, it is expected that the post-doc will initiate novel research and will assist in the supervision of PhD students. The postdoc should have a PhD in physics, mathematics or computer science and a strong theoretical background in neural networks. The post-doc salary will be between Dfl. 5589 and Dfl. 7694 per month, depending on experience. The position is available for 2 years with possible extension to 4 years. RESEARCH PROGRAMMER SNN conducts many applied research projects in collaboration with Dutch and foreign industries. Some of these receive public funding, others are funded directly by industry. The aim of these projects is to apply modern neural network or AI methods to concrete industrial problems, rather than the development of novel methodology. Often, the output of the project requires the implementation of the solution in software. Our BayesBuilder and Promedas software are examples of such activities (http://www.mbfys.kun.nl/snn/Research/{promedas,bayesbuilder}. For these activities we seek a research programmer. The research programmer should be familiar with neural networks and/or Bayesian statistics and have a good programming background (C,C++,Java). The research programmer salary will be between Dfl. 4151 and Dfl. 6581 per month, depending on experience. The position is available for 2 years with possible extension to 4 years. Applications: Interested candidates should send a letter with a CV and list of publications before october 1 2000 to dr. H.J. Kappen, Stichting Neurale Netwerken, University of Nijmegen, Geert Grooteplein 21, 6525 EZ Nijmegen. For information contact dr. H.J. Kappen, +31 24 3614241. From mharm at cnbc.cmu.edu Wed Sep 6 10:21:00 2000 From: mharm at cnbc.cmu.edu (Michael Harm) Date: Wed, 6 Sep 2000 10:21:00 -0400 (EDT) Subject: paper available: Are there orthographic impairments in phonological dyslexia? Message-ID: Hi. This is to announce a paper that has been accepted for publication in Cognitive Neuropsychology that may be of interest to some people on this list. Are There Orthographic Impairments in Phonological Dyslexia? Michael W. Harm, CMU Mark S. Seidenberg, USC Abstract: Two hypotheses have been advanced concerning the basis of acquired phonological dyslexia. According to the dual-route model, the pattern derives from impaired grapheme-phoneme conversion. According to the phonological impairment hypothesis, it derived from impaired representation and use of phonology. Effects of graphemic complexity and visual similarity observed in studies by Howard and Best (1996) orthographic effects on phoneme counting (Berndt et al. 1996) and data from patient LB (Derouesne and Beauvois 1985) have been taken as evidence for an orthographic impairment in phonological dyslexia and therefore against the impaired phonology hypothesis (Coltheart 1996). We present a computational simulation, results of two behavioral studies and a critical analysis of the MJ and LB data which suggest that the ``orthographic'' deficits in such patients arise from phonological impairments that interact with orthographic properties of stimuli. A preprint is available at http://www.cnbc.cmu.edu/~mharm/papers/cn2000/cn2000.html Standard copyright notice: The documents distributed here have been provided as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder. (blah blah blah.) Cheers, Mike Harm mharm at cnbc.cmu.edu Center for the Neural Basis of Cognition Carnegie Mellon University http://www.cnbc.cmu.edu/~mharm/ ----------------------------------------- At midnight, all the agents, And the superhuman crew, Come out and round up everyone, That knows more than they do. Bob Dylan, "Desolation Row" From cindy at cns.bu.edu Thu Sep 7 13:04:36 2000 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Thu, 7 Sep 2000 13:04:36 -0400 Subject: Neural Networks 13(6) Message-ID: <200009071704.NAA09759@retina.bu.edu> NEURAL NETWORKS 13(6) Contents - Volume 13, Number 6 - 2000 ------------------------------------------------------------------ NEURAL NETWORKS LETTERS: Neural networks with a continuous squashing function in the output are universal approximators J.L. Castro, C.J. Mantas, and J.M. Benitez Implications of physical symmetries in adaptive image classifiers T. Sams and J.L. Hansen CONTRIBUTED ARTICLES: ***** Neuroscience and Neuropsychology ***** Visual cortical mechanisms of perceptual grouping: Interacting layers, networks, columns, and maps W.D. Ross, S. Grossberg, and E. Mingolla ***** Mathematical and Computational Analysis ***** Blind source separation in the presence of weak sources J.-P. Nadal, E. Korutcheva, and F. Aires Blind signal processing by the adaptive activation function neurons S. Fiori Results concerning the absolute stability of delayed neural networks M. Joy Dynamic topology representing networks J. Si, S. Lin, and M.-A. Vuong Consistency of posterior distributions for neural networks H.K.H. Lee III On the exact solution of the parity-N problem using ordered neural networks E. Lavretsky Approximation of continuous and discontinuous mappings by a growing neural RBF-based algorithm A. Esposito, M. Marinaro, D. Oricchio, and S. Scarpetta ***** Engineering and Design ***** Stable behavior in a recurrent neural network for a finite state machine K. Arai and R. Nakano ***** Technology and Applications ***** A neural network for 500 word vocabulary word spotting using non-uniform units H.-J. Yu ***** Letter to the Editor ***** Ionic current and metabolism for brain scanners (A three state model of modular activation) J.F. Gomez ------------------------------------------------------------------ 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 mike at deathstar.psych.ualberta.ca Thu Sep 7 10:44:41 2000 From: mike at deathstar.psych.ualberta.ca (Michael R.W. Dawson) Date: Thu, 7 Sep 2000 08:44:41 -0600 (MDT) Subject: Positions at U. of Alberta Message-ID: DEPARTMENT OF PSYCHOLOGY, UNIVERSITY OF ALBERTA Four Positions in Brain, Behaviour, and Cognitive Science The Department of Psychology, Faculty of Science at the University of Alberta is seeking to expand its development in Behavioural and Cognitive Neurosciences, which is one of the specializations in the Department's general area of Brain, Behaviour, and Cognitive Science. An open-rank position in Behavioural and Cognitive Neurosciences will be open to competition. The appointment is effective July 1, 2001. Candidates should have a demonstrated excellence in the study of the neural basis of behaviour or cognitive processes as applied to perception, neural plasticity, learning, memory, language, development and aging, attention, motor control, or emotion. The expectation is that the successful candidate will have some postdoctoral experience and will be able to secure NSERC, MRC, or equivalent funding. The Department of Psychology, Faculty of Science at the University of Alberta is seeking to expand its development in Comparative Cognition, which is one of the specializations in the Department's general area of Brain, Behaviour, and Cognitive Science. A tenure-track position in Comparative Cognition at the level of assistant professor will be open to competition. The appointment will be effective July 1, 2001. Candidates should have a strong research record in animal learning or comparative cognition and teaching interests that include both introductory and advanced courses in learning and comparative cognition. Comparative cognition is broadly defined to include studies of processes such as perception, learning, memory and navigation in vertebrates or invertebrates. We particularly encourage applications from candidates with expertise or interest in neural mechanisms underlying learning and cognition, connectionist modeling, or behaviour genetics. The expectation is that the successful candidate will have some postdoctoral experience and will be able to secure NSERC, MRC, or equivalent funding. The Department of Psychology, Faculty of Science at the University of Alberta is seeking to expand its development in the area of Real-World Cognition, which is one of the specializations in the Department’s general area of Brain, Behaviour, and Cognitive Science. A tenure-track position in real-world cognition at the assistant professor level will be open to competition and will be effective July 1, 2001. We invite applications from individuals in any area of real-world cognition, but we are especially interested in a person whose main interest is in human judgment and decision making/risk assessment. Researchers with interest in human factors in human-computer interaction/knowledge engineering, cognitive aspects of survey methodology, autobiographical memory, or applied discourse processing would also be considered for this position. The expectation is that the successful candidate will secure NSERC, MRC, SSHRC, or equivalent funding. The Department of Psychology, Faculty of Science at the University of Alberta is seeking to expand its development in Synthetic Psychology, which is one of the specializations in the Department's general area of Brain, Behaviour, and Cognitive Science. A tenure-track position in Synthetic Psychology at the assistant professor level will be open to competition. The appointment will be effective July 1, 2001. Candidates should have a strong interest in psychologically relevant and/or biologically inspired computer simulation methods with demonstrated excellence and ongoing research programs. Examples of such research would include computational neuroscience, artificial neural networks, evolutionary computation, nonlinear models and/or selectionistism to study any of the following or related areas: perception, learning, language, neural plasticity, development and aging, attention, motor control, emotion, or memory. Researchers with general interests in situated and/or embodied cognition would also be considered for this position. The expectation is that the successful candidate will secure NSERC, MRC, or equivalent funding. Hiring decisions will be made on the basis of demonstrated research capability, teaching ability, and the potential for interactions with colleagues. In particular an ability to interact with the other specializations in Brain, Behaviour, and Cognitive Science in our department would be an asset. Further information on this position can be obtained from http://www.psych.ualberta.ca/hiring. Applicants should send a curriculum vitae, a statement of current and future research plans, a description of teaching interests, recent publications, and arrange to have at least three letters of reference forwarded to: Dr Douglas S Grant, Chair, Department of Psychology, P220 Biological Sciences Building, University of Alberta, Edmonton, Alberta, Canada, T6G 2E9. Applications for the competition should be received by November 1, 2000. The records arising from this competition will be managed in accordance with provisions of the Alberta Freedom of Information and Protection of Privacy Act (FOIPP). In accordance with Canadian Immigration requirements, this advertisement is directed to Canadian citizens and permanent residents. If a suitable Canadian citizen or permanent resident cannot be found, other individuals will be considered. The University of Alberta is committed to the principle of equity of employment. As an employer we welcome diversity in the workplace and encourage applications from all qualified women and men, including Aboriginal peoples, persons with disabilities and members of visible minorities. From derprize at cnbc.cmu.edu Thu Sep 7 15:26:14 2000 From: derprize at cnbc.cmu.edu (David E Rumelhart Prize) Date: Thu, 07 Sep 2000 15:26:14 -0400 Subject: THE RUMELHART PRIZE Announcement and Call for Nominations Message-ID: <39B7EBD6.1C5A8D4A@cnbc.cmu.edu> ANNOUNCEMENT AND CALL FOR NOMINATIONS THE DAVID E. RUMELHART PRIZE FOR CONTRIBUTIONS TO THE FORMAL ANALYSIS OF HUMAN COGNITION The David E. Rumelhart Prize will be awarded biennially to an individual or collaborative team making a significant contemporary contribution to the formal analysis of human cognition. Mathematical modeling of human cognitive processes, formal analysis of language and other products of human cognitive activity, and computational analyses of human cognition using symbolic or non-symbolic frameworks all fall within the scope of the award. The Prize itself will consist of a certificate, a citation of the awardee's contribution, and a monetary award of $100,000. Nomination, Selection and Award Presentation Nominations for the David E. Rumelhart Prize should be sent to the Chair of the Prize Selection Committee by December 1 of each even numbered year, beginning in the year 2000. Nominations should include six sets of the following materials: (1) A three-page statement focusing on the work motivating the nomination, (2) a complete curriculum vitae and (3) copies of up to five of the nominee's relevant publications. Note that the nominee may be an individual or a team, and in the case of a team, vitae for all members should be provided. The awardee will be announced at the meeting of the Cognitive Science Society in the year following the deadline and will receive the Prize and deliver the Prize Lecture at the meeting in the year after that. Thus, the first prize recipient will be announced at the Meeting of the Cognitive Science Society in 2001, and the first Prize Lecture will be given at the meeting of the Society in 2002. Funding of the Prize The David E, Rumelhart Prize will be funded by the Robert J. Glushko and Pamela Samuelson Foundation, based in San Francisco. Robert J. Glushko is an entrepreneur in Silicon Valley who received a Ph. D. in Cognitive Psychology in 1979 under Rumelhart's supervision. Prize Administration The Rumelhart Prize will be Administered by the Chair of the Prize Selection Committee in consultation with the Glushko-Samuelson Foundation and the Distinguished Advisory Board. Screening of nominees and selection of the prize winner will be performed by the Prize Selection Committee. Scientific members (including the Chair) of the Prize Selection Committee will serve for up to two four-year terms, and members of this committee will be selected by the Glushko-Samuelson Foundation in consultation with the Distinguished Advisory Board. A representative of the Foundation will also serve on the Prize Selection Committee. David E. Rumelhart: A Scientific Biography David E. Rumelhart has made many contributions to the formal analysis of human cognition, working primarily within the frameworks of mathematical psychology, symbolic artificial intelligence, and parallel distributed processing. He also admired formal linguistic approaches to cognition and explored the possibility of formulating a formal grammar to capture the structure of stories. Rumelhart obtained his undergraduate education at the University of South Dakota, receiving a B.A. in psychology and mathematics in 1963. He studied mathematical psychology at Stanford University, receiving his Ph. D. in 1967. From 1967 to 1987 he served on the faculty of the Department of Psychology at the University of California, San Diego. In 1987 he moved to Stanford University, serving as Professor there until 1998. He has become disabled by Pick's disease, a progressive neurodegenerative illness, and now lives with his brother in Ann Arbor, Michigan. Rumelhart developed models of a wide range of aspects of human cognition, ranging from motor control to story understanding to visual letter recognition to metaphor and analogy. He collaborated with Don Norman and the LNR Research Group to produce "Explorations in Cognition" in 1975 and with Jay McClelland and the PDP Research Group to produce "Parallel Distributed Processing: Explorations in the Microstructure of Cognition" in 1986. He mastered many formal approaches to human cognition, developing his own list processing language and formulating the powerful back-propagation learning algorithm for training networks of neuron-like processing units. Rumelhart was elected to the National Academy of Sciences in 1991 and received many prizes, including a MacArthur Fellowship, the Warren Medal of the Society of Experimental Psychologists, and the APA Distinguished Scientific Contribution Award. Rumelhart articulated a clear view of what cognitive science, the discipline, is or ought to be. He felt that for cognitive science to be a science, it would have to have formal theories --- and he often pointed to linguistic theories, as well as to mathematical and computational models, as examples of what he had in mind. Distinguished Advisory Board William K. Estes Indiana University Bloomington, Indiana Barbara H. Partee University of Massachusetts Amherst, Massachusetts Herbert A. Simon Carnegie Mellon University Pittsburgh, Pennsylvania Chair, Prize Selection Committee James L. McClelland Carnegie Mellon University and Center for the Neural Basis of Cognition Pittsburgh, Pennsylvania Inquiries and Nominations should be sent to David E. Rumelhart Prize Administration Center for the Neural Basis of Cognition 115 Mellon Institute 4400 Fifth Avenue Pittsburgh, PA 15213 412-268-4000 derprize at cnbc.cmu.edu Visit the prize web site at www.cnbc.cmu.edu/derprize From abrowne at lgu.ac.uk Fri Sep 8 06:58:17 2000 From: abrowne at lgu.ac.uk (Tony Browne) Date: Fri, 8 Sep 2000 11:58:17 +0100 (GMT Daylight Time) Subject: Postdoc in UK Message-ID: A postdoctoral research associate post is available for a project using neural networks for Biological and Chemical Data analysis. The research associate will be based in the Centre for Molecular Design at Portsmouth University, UK, for a 2.5 year period. Starting salary will be in the range of seventeen to eighteen thousand UK pounds (with annual increments). This post requires a graduate with a PhD in Computer Science, Cognitive Science, Mathematics or a related subject, or a graduate with a PhD in Life Sciences with a thorough understanding of Bioinformatics and strong mathematical and programming skills. The successful candidate should posses knowledge in the following areas: Experience of developing neural networks in high-level programming languages. Strong Mathematical and Statistical Skills. An awareness of current developments in Bioinformatics/Cheminformatics. CV's (in text format) should be e-mailed to martyn.ford at port.ac.uk, or forwarded to Professor Martyn Ford, University of Portsmouth, Centre for Molecular Design, School of Biological Sciences, King Henry Building, King Henry 1 Street, Portsmouth PO1 2DY, UK. Tel: (+44) 0239 843 020. ======================================================= Dr. Antony Browne School of Computing, Information Systems & Mathematics London Guildhall University 100 Minories London EC3 1JY, UK Tel: (+44) 0207 320 3106 Fax: (+44) 0207 320 1717 ======================================================= From kempter at phy.ucsf.edu Fri Sep 8 12:49:42 2000 From: kempter at phy.ucsf.edu (Richard Kempter) Date: Fri, 8 Sep 2000 09:49:42 -0700 Subject: Preprint available: Intrinsic Stabilization of Output Rates by Spike-Based Hebbian Learning Message-ID: <20000908094942.A26311@popper.ucsf.edu> Dear connectionists, to all of you who have been interested in the nice paper on Spike-Time Dependent Plasticity by Song, Miller, and Abbott, that Ken Miller announced on this mailing list a couple of days ago, we would like to give a pointer to our preprint on a related topic. Intrinsic Stabilization of Output Rates by Spike-Based Hebbian Learning (Kempter, Gerstner, van Hemmen) http://keck.ucsf.edu/~kempter/Publications/index.html Abstract: We study analytically a model of synaptic plasticity where synaptic changes are triggered by presynaptic spikes, postsynaptic spikes, and the time-differences between pre- and postsynaptic spikes. We show that plasticity can lead to an intrinsic stabilization of the mean firing rate of the postsynaptic neuron. Subtractive normalization of the synaptic weights (summed over all presynaptic inputs converging on a postsynaptic neuron) follows if, in addition, the mean input rates and the mean input correlations are identical at all synapses. If the integral over the learning window is positive, firing rate stabilization requires a non-Hebbian component, while such a component is not necessary, if the integral over the learning window is negative. A negative integral corresponds to `anti-Hebbian' learning in a model with slowly varying firing rates. For spike-based learning, a strict distinction between Hebbian and `anti-Hebbian' rules is questionable, since learning is driven by correlations on the time scale of the learning window. The correlations between presynaptic and postsynaptic firing are evaluated for a piecewise linear Poisson model and for a noisy spiking neuron model with refractoriness. While a negative integral over the learning window leads to intrinsic rate stabilization, the positive part of the learning window picks up spatial and temporal correlations in the input. Richard Kempter and Wulfram Gerstner From terry at salk.edu Fri Sep 8 20:52:52 2000 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 8 Sep 2000 17:52:52 -0700 (PDT) Subject: NEURAL COMPUTATION 12:9 Message-ID: <200009090052.e890qq330478@dax.salk.edu> Neural Computation - Contents - Volume 12, Number 9 - September 1, 2000 ARTICLE DEA: An Architecture for Goal Planning and Classification Francois Fleuret and Eric Brunet NOTE On A Fast, Compact Approximation of the Exponential Function Gavin C. Cawley LETTERS Bounds On Error Expectation for Support Vector Machines V. Vapnik and O. Chapelle A Computational Model of Lateralization and Asymmetries in Cortical Maps Svetlana Levitan and James A. Reggia Rate Limitations of Unitary Event Analysis A. Roy, P. N. Steinmetz, and E. Niebur Estimating Functions of Independent Component Analysis for Temporally Correlated Signals Shun-ichi Amari SMEM Algorithm for Mixture Models Naonori Ueda, Ryohei Nakano, Zoubin Ghahramani, and Geoffrey E. Hinton Stable Encoding of Finite-State Machines in Discrete-Time Recurrent Neural Nets with Sigmoid Units Rafael C. Carrasco, Mikel L. Forcada, M. Angeles Valdes-Munoz, and Ramon P. Neco Approximate Maximum Entropy Joint Feature Inference Consistent with Arbitrary Lower Order Probability Constraints: Application to Statistical Classification David J. Miller and Lian Yan Lambda-opt Neural Approaches to Quadratic Assignment Problem Shin Ishii and Hirotaka Niitsuma ----- 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 vera at cs.cas.cz Wed Sep 13 16:28:40 2000 From: vera at cs.cas.cz (Vera Kurkova) Date: Wed, 13 Sep 00 16:28:40 CET Subject: soft deadline of ICANNGA 2001 Message-ID: <59321.vera@uivt1.uivt.cas.cz> Not wanting to omit fuzzy logic, we have softened our deadline. Submission of papers to: 5th INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS AND GENETIC ALGORITHMS *** ICANNNGA 2001 *** is postponed to 1st October, 20000 For details on submission please see http://www.cs.cas.cz/icannga See you in Prague, April 21-24, 2001 Vera Kurkova, Chair of the Program Committee of ICANNGA 2001 From becker at curie.psychology.mcmaster.ca Wed Sep 13 14:44:40 2000 From: becker at curie.psychology.mcmaster.ca (Sue Becker) Date: Wed, 13 Sep 2000 14:44:40 -0400 (EDT) Subject: POSTDOC AND POSTGRAD POSITIONS IN NEURO-SIGNAL PROCESSING Message-ID: POST-DOCTORAL and POST-GRADUATE POSITIONS in NEURO-SIGNAL PROCESSING Funding for two post-doctoral positions and at least two PhD students is available to develop and test intelligent hearing aid technology. A group of researchers at McMaster University recently received funding from NSERC, Canada for this exciting project which is being conducted in collaboration with Gennum Corporation, one of the world's largest hearing aid manufacturers. The research team, headed by Prof. Simon Haykin in Electrical Engeering, also includes Professors Sue Becker, Ron Racine, John Platt and Laurel Trainor in the Psychology Department. The team's expertise spans neural modelling, signal processing, neurophysiology, neural plasticity, and auditory processing. Preference will be given to applicants with expertise in neurobiological modelling of the auditory system or adaptive filter design or a related field. Excellent computer programming skills are essential. Students joining the team could obtain a graduate degree in either Electrical Engineering or Psychology, and would enroll in September, 2000 or as soon as possible thereafter. Postdocs could start immediately. Please send applications, with two references, to: Prof. Simon Haykin Communications Research Laboratory McMaster Univeristy Hamilton, Ontario, Canada L8S 4K1 haykin at mcmaster.ca From harnad at coglit.ecs.soton.ac.uk Wed Sep 13 06:59:16 2000 From: harnad at coglit.ecs.soton.ac.uk (Stevan Harnad) Date: Wed, 13 Sep 2000 11:59:16 +0100 (BST) Subject: THE WORK OF ROGER SHEPARD: 7 special BBS Calls for Commentators Message-ID: Below are the abstracts of 7 forthcoming target articles to co-appear in a BBS Special Issue on: THE WORK OF ROGER SHEPARD Commentators may comment on one, several, or all 7 target articles. (1) Shepard: Perceptual-Cognitive Universals as Reflections of the World (reprinted from Psychonomic Bulletin & Review, 1994, 1, 2-28) http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.shepard.html (2) Barlow: The Exploitation of Regularities in the Environment by the Brain http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.barlow.html (3) Hecht: Regularities of the Physical World and the Absence of their Internalization http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.hecht.html (4) Kubovy: Internalization: A metaphor we can live without http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.kubovy.pdf (5) Schwartz: Evolutionary Internalized Regularities http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.schwartz.html (6) Tenenbaum & Griffiths: Generalization, Similarity, and Bayesian Inference http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.tenenbaum.html (7) Todorovic: Is kinematic geometry an internalized regularity? http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.todorovic.html These 7 articles have been accepted for joint publication in a special issue on the work of ROGER SHEPARD in Behavioral and Brain Sciences (BBS), an international, interdisciplinary journal providing Open Peer Commentary on important and controversial current research in the biobehavioral and cognitive sciences. To be considered as a commentator for this article, to recommend other appropriate commentators, or for information about how to become a BBS Associate, please reply by EMAIL by September 8th to the address below: bbs at soton.ac.uk Commentators must either be current BBS Associates or they must be nominated by a current BBS Associate (of which there are currently 10,000). Non-Associates should send a CV and/or the name of a current BBS Associate familiar with their work. To help us put together a balanced list of commentators, in your reply please indicate the aspects of the topic on which you would bring your areas of expertise to bear if you were selected as a commentator. Electronic drafts of the full texts of all 7 articles are available for inspection from the Web. Commentators may comment on one, several, or all 7 target articles. Commentary length is 1000 words for a commentary on one target article, to a maximum of 4000 words for a commentary on all 7 (an extra 500 words are allowed for each additional target article). Please indicate which article(s) you propose to comment upon. ____________________________________________________________ 1. SHEPARD, ROGER (2001) PERCEPTUAL-COGNITIVE UNIVERSALS AS REFLECTIONS OF THE WORLD Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.shepard.html Roger N. Shepard Stanford University Stanford, California roger at psych.stanford.edu ABSTRACT: The universality, invariance, and elegance of principles governing the universe may be reflected in principles of the minds that have evolved in that universe--provided that the mental principles are formulated with respect to the abstract spaces appropriate for the representation of biologically significant objects and their properties. (1) Positions and motions of objects conserve their shapes in the geometrically fullest and simplest way when represented as points and connecting geodesic paths in the six-dimensional manifold jointly determined by the Euclidean group of three-dimensional space and the symmetry group of each object. (2) Colors of objects attain constancy when represented as points in a three-dimensional vector space in which each variation in natural illumination is cancelled by application of its inverse from the three-dimensional linear group of terrestrial transformations of the invariant solar source. (3) Kinds of objects support optimal generalization and categorization when represented, in an evolutionarily shaped space of possible objects, as connected regions with associated weights determined by Bayesian revision of maximum-entropy priors. ____________________________________________________________ 2. BARLOW, HORACE (2001) THE EXPLOITATION OF REGULARITIES IN THE ENVIRONMENT BY THE BRAIN Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.barlow.html Horace Barlow Physiological Laboratory Cambridge CB2 3EG England hbb10 at cam.ac.uk KEYWORDS: Chasles' rule, evolution, geometry, perception, redundancy, statistics, twisting. ABSTRACT: Statistical regularities of the environment are important for learning, memory, intelligence, inductive inference, and in fact for any area of cognitive science where an information-processing brain promotes survival by exploiting them. This has been recognised by many of those interested in cognitive function, starting with Helmholtz, Mach and Pearson, and continuing through Craik, Tolman, Attneave, and Brunswik. In the current era many of us have begun to show how neural mechanisms exploit the regular statistical properties of natural images. Shepard proposed that the apparent trajectory of an object when seen successively at two positions results from internalising the rules of kinematic geometry, and although kinematic geometry is not statistical in nature, this is clearly a related idea. Here it is argued that Shepard's term, "internalisation", is insufficient because it is also necessary to derive an advantage from the process. Having mechanisms selectively sensitive to the spatio-temporal patterns of excitation commonly experienced when viewing moving objects would facilitate the detection, interpolation, and extrapolation of such motions, and might explain the twisting motions that are experienced. Although Shepard's explanation in terms of Chasles' rule seems doubtful, his theory and experiments illustrate that local twisting motions are needed for the analysis of moving objects and provoke thoughts about how they might be detected. ____________________________________________________________ 3. HECHT, HEIKO (2001) REGULARITIES OF THE PHYSICAL WORLD AND THE ABSENCE OF THEIR INTERNALIZATION Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.hecht.html Heiko Hecht Man-Vehicle Lab Massachusetts Institute of Technology Mass Ave., Bldg. 37-219, Cambridge, MA 02139 hecht at mit.edu KEYWORDS: Internalization, Evolution, Event Perception ABSTRACT: The notion of internalization put forth by Roger Shepard continues to be appealing and challenging. He suggests that we have internalized, during our evolutionary development, environmental regularities or constraints. Internalization solves one of the hardest problems of perceptual psychology: the underspecification problem. That is the problem of how well-defined perceptual experience is generated from the often ambiguous and incomplete sensory stimulation. Yet, the notion of internalization creates new problems that may outweigh the solution of the underspecification problem. To show this, I first examine the concept of internalization and find it necessary to break it down into several distinct interpretations. These range from well-resolved dynamic regularities to ill-resolved statistical regularities. As a function of the interpretation the researcher selects, an empirical test of the internalization hypothesis may be straight forward or it may become virtually impossible. I then attempt to cover the range of interpretations by drawing on examples from different domains of visual event perception. Unfortunately, the experimental tests regarding most candidate regularities, such as gravitational acceleration, fail to support the concept of internalization. This suggests that narrow interpretations of the concept should be given up in favor of more abstract interpretations. However, the latter are are not easily amenable to empirical testing. There is nonetheless a way to test by contrasting internalization with the opposite concept: externalization of body dynamics. I summarize evidence for such a projection of body constraints onto external objects. Based on the combined evidence of well-resolved and ill-resolved regularities, the value of the notion of internalization has to be reassessed. ____________________________________________________________ 4. KUBOVY, MICHAEL (2001) INTERNALIZATION: A METAPHOR WE CAN LIVE WITHOUT Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.kubovy.pdf Michael Kubovy The University of Virginia KEYWORDS: computational approach, cognitive constructivism, constraints, ecological approach, environmental regularities, evolution, homomorphism, illusory motion, internality, internalization, inverse projec-tion problem, kinematic geometry, mental rotation, metaphors of mind, perception of motion, perceptual universals. ABSTRACT: Shepard has supposed that the mind is stocked with innate knowledge of the world and that this knowledge figures prominently in the way we see the world. According to him, this in-ternal knowledge is the legacy of a process of internalization; a process of natural selection over the evolutionary history of the species. Shepard has developed his proposal most fully in his analysis of the relation between kinematic geometry and the shape of the motion path in apparent motion displays. We argue that Shepard has made a case for applying the principles of kinematic geometry to the perception of motion, but that he has not made the case for in-jecting these principles into the mind of the percipient. We offer a more modest interpretation of his important findings: that kinematic geometry may be a model of apparent motion. Inas-much as our recommended interpretation does not lodge geometry in the mind of the percipient the motivation for positing internalization, a process that moves kinematic geometry into the mind, is obviated. In our conclusion we suggest that cognitive psychologists, in their embrace of internal mental universals and internalization may have been seduced by the siren call of metaphor. ____________________________________________________________ 5. SCHWARTZ, ROBERT (2001) EVOLUTIONARY INTERNALIZED REGULARITIES Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.schwartz.html Robert Schwartz Department of Philosophy University of Wisconsin - Milwaukee Milwaukee, WI 53201 U.S.A. schwartz at uwm.edu KEYWORDS: apparent motion, circadian rhythms, constraints, ecoclogical validity, evolution, internalized regularities, kinematic principle. ABSTRACT: Roger Shepard's proposals and supporting experiments concerning evolutionary internalized regularities have been very influential in the study of vision and in other areas of psychology and cognitive science. This paper examines issues concerning the need, nature, explanatory role, and justification for postulating such internalized constraints. In particular, I seek further clarification from Shepard on how best to understand his claim that principles of kinematic geometry underlie phenomena of motion perception. My primary focus is on the ecological validity of Shepard's kinematic constraint in the context of ordinary motion perception. First, I explore the analogy Shepard draws between internalized circadian rhythms and the supposed internalization of kinematic geometry. Next, questions are raised about how to interpret and justify applying results from his own and others experimental studies of apparent motion to more everyday cases of motion perception in richer environments. Finally, some difficulties with Shepard's account of the evolutionary development of his kinematic constraint are considered. ____________________________________________________________ 6. TENENBAUM, JOSHUA B. & GRIFFITHS, THOMAS L. (2001) GENERALIZATION, SIMILARITY, AND BAYESIAN INFERENCE Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.tenenbaum.html Joshua B. Tenenbaum & Thomas L. Griffiths Department of Psychology Jordan Hall, Building 420 Stanford University Stanford, CA 94305-2130 jbt at psych.stanford.edu KEYWORDS: Additive clustering, Bayesian inference, categorization, concept learning, contrast model, features, generalization, psychological space, similarity. ABSTRACT: Shepard has argued that a universal law should govern generalization across different domains of perception and cognition, as well as across organisms from different species or even different planets. Starting with some basic assumptions about natural kinds, he derived an exponential decay function as the form of the universal generalization gradient, which accords strikingly well with a wide range of empirical data. However, his original formulation applied only to the ideal case of generalization from a single encountered stimulus to a single novel stimulus, and for stimuli that can be represented as points in a continuous metric psychological space. Here we recast Shepard's theory in a more general Bayesian framework and show how this naturally extends his approach to the more realistic situation of generalizing from multiple consequential stimuli with arbitrary representational structure. Our framework also subsumes a version of Tversky's set-theoretic models of similarity, which is conventionally thought of as the primary alternative to Shepard's continuous metric space model of similarity and generalization. This unification allows us not only to draw deep parallels between the set-theoretic and spatial approaches, but also to significantly advance the explanatory power of set-theoretic models. ____________________________________________________________ 7. TODOROVIC, DEJAN (2001) IS KINEMATIC GEOMETRY AN INTERNALIZED REGULARITY? Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.todorovic.html Dejan Todorovic Department of Psychology, University of Belgrade, Serbia, Yugoslavia dejan at arvotek.net dtodorov at dekart.f.bg.ac.yu KEYWORDS: internalization of regularities, kinematic geometry, simplicity ABSTRACT: A general framework for the explanation of perceptual phenomena as internalizations of external regularities was developed by R.N. Shepard. A particular example of this framework is his account of perceived curvilinear apparent motions. This paper contains a brief summary of the relevant psychophysical data, some basic kinematical considerations and examples, and several criticisms of Shepard's account. The criticisms concern the feasibility of internalization of critical motion types, the roles of simplicity and uniqueness, the contrast between classical physics and kinematic geometry, the import of perceived path curvilinearity, and the relation of perceptual and scientific knowledge. ____________________________________________________________ ____________________________________________________________ To help you decide whether you would be an appropriate commentator for these articles, electronic drafts are retrievable from the World Wide Web from the US or UK BBS Archive. Please do not prepare a commentary yet. Just let us know, after having inspected it, what relevant expertise you feel you would bring to bear on what aspect of which article(s). We will then let you know whether it was posible to include your name on the final formal list of invitees. The URLs you can use to get to the BBS Archive: http://www.cogsci.soton.ac.uk/bbs/Archive/ ____________________________________________________________ *** FIVE SUPPLEMENTARY ANNOUNCEMENTS *** ------------------------------------------------------------------ (1) There have been some very important developments in the area of Web archiving of scientific papers very recently. Please see: Science: http://www.cogsci.soton.ac.uk/~harnad/science.html Nature: http://www.cogsci.soton.ac.uk/~harnad/nature.html Am. Sci.: http://www.cogsci.soton.ac.uk/~harnad/amlet.html --------------------------------------------------------------------- (2) All authors in the biobehavioral and cognitive sciences are strongly encouraged to archive all their papers (on their Home-Servers as well as) on CogPrints: http://cogprints.soton.ac.uk/ It is extremely simple to do so and will make all of our papers available to all of us everywhere at no cost to anyone. See: http://vole.lanl.gov/ups/ups.htm http://xxx.lanl.gov/cgi-bin/show_monthly_submissions --------------------------------------------------------------------- (3) BBS has a new policy of accepting submissions electronically. Authors can specify whether they would like their submissions archived publicly during refereeing in the BBS under-refereeing Archive, or in a referees-only, non-public archive. Upon acceptance, preprints of final drafts are moved to the public BBS Archive: http://www.cogsci.soton.ac.uk/bbs/Archive/ -------------------------------------------------------------------- (4) BBS has expanded its annual page quota and is now appearing bimonthly, so the service of Open Peer Commentary can now be be offered to more target articles. The BBS refereeing procedure is also going to be considerably faster with the new electronic submission and processing procedures. Authors are invited to submit papers to: Email: bbs at cogsci.soton.ac.uk Web: http://cogprints.soton.ac.uk http://bbs.cogsci.soton.ac.uk/ INSTRUCTIONS FOR AUTHORS: http://www.cogsci.soton.ac.uk/bbs/instructions.for.authors.html --------------------------------------------------------------------- (5) Call for Book Nominations for BBS Multiple Book Review In the past, Behavioral and Brain Sciences (BBS) journal had only been able to do 1-2 BBS multiple book treatments per year, because of our limited annual page quota. BBS's new expanded page quota will make it possible for us to increase the number of books we treat per year, so this is an excellent time for BBS Associates and biobehavioral/cognitive scientists in general to nominate books you would like to see accorded BBS multiple book review. (Authors may self-nominate, but books can only be selected on the basis of multiple nominations.) It would be very helpful if you indicated in what way a BBS Multiple Book Review of the book(s) you nominate would be useful to the field (and of course a rich list of potential reviewers would be the best evidence of its potential impact!). From cindy at cns.bu.edu Thu Sep 14 16:04:20 2000 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Thu, 14 Sep 2000 16:04:20 -0400 Subject: Neural Networks: 2001 Special Issue Message-ID: <200009142004.QAA27939@retina.bu.edu> CALL FOR PAPERS A 2001 Special Issue of Neural Networks SPIKING NEURONS IN NEUROSCIENCE AND TECHNOLOGY Most neurons of the brain communicate using trains of brief voltage spikes that are capable of carrying complex temporal and rate codes without degradation over large spatial distances. The rates, patterns or oscillations of single spike trains as well as correlations and synchrony across different spike trains, have been studied by many investigators in both normal and clinically abnormal brain tissues. The Special Issue will incorporate invited and contributed articles that examine the importance of spiking in information processing, learning and memory. The Special Issue will cover biophysical and biochemical models of spike generation, neurophysiological and anatomical models that explore how spiking neurons influence behavior through their collective action in neural circuits and networks, as well as learning algorithms that are based on spikes. The computational power of spiking neurons for reliable communication can also be incorporated into various technologies. The Special Issue will therefore also include articles that describe software and hardware applications that are based on this mode of neuronal communication to explore its potential for solving outstanding open problems in technology. CO-EDITORS: Professor Stephen Grossberg, Boston University Professor Wolfgang Maass, Technische Universitat Graz Professor Henry Markram, Weizmann Institute for Science SUBMISSION: Deadline for submission: September 30, 2000 Notification of acceptance: December 31, 2000 Format: no longer than 10,000 words; APA format ADDRESS FOR SUBMISSION: Stephen Grossberg, Editor Neural Networks, Room 203 Department of Cognitive and Neural Systems Boston University 677 Beacon Street Boston, Massachusetts 02215 USA From paolo at eealab.unian.it Fri Sep 15 13:42:22 2000 From: paolo at eealab.unian.it (Paolo Campolucci) Date: Fri, 15 Sep 2000 19:42:22 +0200 (CEST) Subject: 2 new papers on circuit theory, digital signal processing and recurrent neural networks Message-ID: Dear Colleagues, We would like to announce the availability of two new papers of potential interest to people working on circuit theory, digital signal processing and recurrent neural networks at http://nnsp.eealab.unian.it/Campolucci_P Sincerely, Paolo "A Signal-Flow-Graph Approach to On-line Gradient Calculation" By Paolo Campolucci, Aurelio Uncini, Francesco Piazza Neural Computation, vol. 12, nr. 8, August 2000 ABSTRACT A large class of non-linear dynamic adaptive systems such as dynamic recurrent neural networks can be very effectively represented by Signal-Flow-Graphs (SFGs). By this method, complex systems are described as a general connection of many simple components, each of them implementing a simple one-input one-output transformation, as in an electrical circuit. Even if graph representations are popular in the neural network community, they are often used for qualitative description rather than for rigorous representation and computational purposes. In this paper, a method for both on-line and batch backward gradient computation of a system output or cost function with respect to system parameters is derived by the Signal-Flow-Graph representation theory and its known properties. The system can be any causal, in general non-linear and time-variant, dynamic system represented by a SFG, in particular any feedforward, time delay or recurrent neural network. In this work, we use discrete time notation, but the same theory holds for the continuous time case. The gradient is obtained in a straightforward way by the analysis of two SFGs, the original one and its adjoint (obtained from the first by simple transformations) without the complex chain rule expansions of derivatives usually employed. This method can be used for sensitivity analysis and for learning both off-line and on-line. On-line learning is particularly important since it is required by many real applications such as Digital Signal Processing, system identification and control, channel equalization and predistortion. ****************************************************************** "Intrinsic Stability Control Method for Recursive Filters and Neural Networks" By Paolo Campolucci and Francesco Piazza IEEE Transactions on Circuits and Systems, part II: Analog and digital signal processing, vol. 47, nr. 8, August 2000 ABSTRACT Linear recursive filters can be adapted on-line but with instability problems. Stability control techniques exist but they are either computationally expensive or non-robust. For the non-linear case, e.g. locally recurrent neural networks, the stability of Infinite Impulse Response (IIR) synapses is often a condition to be satisfied. This paper considers the known reparametrization-for-stability method for the on-line adaptation of IIR adaptive filters. A new technique is also presented, based on the further adaptation of the squashing function, which allows to improve the convergence performance. The proposed method can be applied to various filter realizations (direct forms, cascade or parallel of second order sections, lattice form) as well as to locally recurrent neural networks, such as the IIR Multi-Layer Perceptron (IIR-MLP), with improved performance with respect to other techniques and to the case of no stability control. In the paper the case of normalized lattice filters is particularly considered; an analysis of the stabilization effects is also presented both analytically and experimentally. ================================= Paolo Campolucci, PhD Dipartimento di Elettronica ed Automatica Universita' di Ancona, Italy e-mail: paolo at eealab.unian.it or campoluc at tiscalinet.it http://nnsp.eealab.unian.it/Campolucci_P ================================= From rsun at cecs.missouri.edu Sun Sep 17 20:55:01 2000 From: rsun at cecs.missouri.edu (Ron Sun) Date: Sun, 17 Sep 2000 19:55:01 -0500 Subject: Ph.D program at UMC Message-ID: <200009180055.TAA25373@pc113.cecs.missouri.edu> The Ph.D program in CECS at University of Missouri-Columbia is accepting applications. Graduate assistantships and other forms of financial support for graduate students are available. Prospective graduate students interested in Artificial Intelligence, Cognitive Science, Connectionist Models (Neural Networks), Multi-Agent Systems, and other related areas are especially encouraged to apply. Students with earned Master's degrees are preferred. The department identifies graduate education and research as its primary missions. The department is conducting quality research in a number of areas: artificial intelligence, cognitive sceince, machine learning, multi-agent systems, neural networks and connectionist models, computer graphics and scientific visualization, computer vision, digital libraries, fuzzy logic, multimedia systems, parallel and distributed computing, and Web computing. To download application forms, use http://www.missouri.edu/~gradschl or http://web.missouri.edu/~regwww/admission/intl_admission/Application_Form/Application_index.html (for international students) ----------------------------------------------------------------- The CECS Department awards degrees at the Bachelor's, Master's and Ph.D's levels. The program is accredited by ABET. The CECS Department has a variety of computing equipment and laboratories available for instruction and research. These facilities are currently being enhanced, in conjunction with computing laboratories maintained by the college and by the campus. The computing facilities offer students a wealth of opportunity to access and utilize a wide range of equipment best suited for their research needs. All of the equipment is connected to departmental, college, campus, and global networks which provides ready access to the exploding world of information and computational resources. A wealth of library resources are available through the extensive collections of books and journals housed in the Engineering and Mathematical Sciences libraries as well as collections in the Main Library and Health Sciences Libraries at MU. The University of Missouri is a Research I university enrolling some 22,000 students. The University offers programs in many areas, ranging from sciences and engineering to psychology, neuroscience, education, biology, medicine, law, agriculture, and journalism. For more information, send e-mail to: gradsec at cecs.missouri.edu See the Web pages below: =========================================================================== Prof. Ron Sun http://www.cecs.missouri.edu/~rsun CECS Department University of Missouri-Columbia fax: (573) 882 8318 201 Engineering Building West Columbia, MO 65211-2060 email: rsun at cecs.missouri.edu http://www.cecs.missouri.edu/~rsun http://www.cecs.missouri.edu/~rsun/journal.html =========================================================================== From istvan at louisiana.edu Mon Sep 18 15:28:50 2000 From: istvan at louisiana.edu (Istvan Berkeley) Date: Mon, 18 Sep 2000 14:28:50 -0500 Subject: Cognitive Science Position Message-ID: <39C66CF2.79EC619A@louisiana.edu> FACULTY POSITION IN THE INSTITUTE OF COGNITIVE SCIENCE. The Institute of Cognitive Science of the University of Louisiana at Lafayette invites applications for a tenure-track faculty appointment for the Fall of 2001. The appointment will be made at the associate professor or senior assistant professor level. The Institute of Cognitive Science is a graduate unit offering a Ph.D. program in cognitive science. Focus areas of the program are in cognitive processes, comparative cognition, cognitive development, computational models of mind, cognitive neuroscience, and language processing. Applicants should hold a Ph.D. in cognitive science, psychology, or a related discipline, and must exhibit evidence of a productive research program. Please send a curriculum vitae, selected reprints, and at least three letters of reference to Subrata Dasgupta, Institute of Cognitive Science, University of Louisiana at Lafayette, P.O. Drawer 43772, Lafayette, LA 70504-3772. Formal review of applications will commence December 1, 2000, but applications will be accepted until the position is filled. The University of Louisiana at Lafayette is an equal opportunity/affirmative action employee. -- Istvan S. N. Berkeley, Ph.D. Philosophy & Cognitive Science E-mail: istvan at usl.edu The University of Louisiana at Lafayette [Formerly, The University of Southwestern Louisiana] P.O. Box 43770 Tel: +1 318 482-6807 Lafayette, LA 70504-3770 Fax: +1 318 482-6195 USA http://www.ucs.usl.edu/~isb9112 From kap-listman at wkap.nl Tue Sep 19 20:02:41 2000 From: kap-listman at wkap.nl (kap-listman@wkap.nl) Date: Wed, 20 Sep 2000 02:02:41 +0200 (MEST) Subject: New Issue: Neural Processing Letters. Vol. 12, Issue 1 Message-ID: <200009200002.CAA11251@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+1+2000 Vol. 12, Issue 1, August 2000. TITLE: Analysis of the Functional Block Involved in the Design of Radial Basis Function Networks AUTHOR(S): I. Rojas, H. Pomares, J. Gonzales, J. L. Bernier, E. Ros, F. J. Pelayo, A. Prieto KEYWORD(S): RBF neural networks, neural networks design, statistical analysis of RBF, RBF structures. PAGE(S): 1-17 TITLE: Control of a Robotic Manipulator Using Artificial Neural Networks with On-line Adaptation AUTHOR(S): Roselito A. Teixeira, Antonio de P. Braga, Benjamim R. de Menezes KEYWORD(S): Adaptive Learning Rate, ANN application, on-line training, PUMA 560, robotic control. PAGE(S): 19-31 TITLE: Simultaneous Identification of Face and Orientation AUTHOR(S): Pei Ling Lai, Colin Fyfe KEYWORD(S): factor analysis, face identification. PAGE(S): 33-40 TITLE: Out-of-Vocabulary Rejection based on Selective Attention Model AUTHOR(S): Ki-Young Park, Soo-Young Lee KEYWORD(S): error backpropagation, noisy speech, out-of-vocabulary rejection, robust speech recognition, selective attention. PAGE(S): 41-48 TITLE: Coherent Response in a Chaotic Neural Network AUTHOR(S): Haruhiko Nishimura, Naofumi Katada, Kazuyuki Aihara KEYWORD(S): chaos, coherence, noise, nonlinear, recurrent neural network, refractoriness, stochastic resonance. PAGE(S): 49-58 TITLE: Clustered Recursive Branching Network AUTHOR(S): Khalid A. Al-Mashouq KEYWORD(S): recursive branching network, structured perceptrons, data clustering. PAGE(S): 59-69 TITLE: Learning with Permutably Homogeneous Multiple-Valued Multiple-Threshold Perceptrons AUTHOR(S): Alioune Ngom, Corina Reischer, Dan A. Simovici, Ivan Stojmenovic KEYWORD(S): learning, multiple-valued multiple-threshold functions, multilinear separability, partial order set, perceptrons. PAGE(S): 71-90 TITLE: On-line Algorithm for Blind Signal Extraction of Arbitrarily Distributed, but Temporally Correlated Sources Using Second Order Statistics AUTHOR(S): Andrzej Cichocki, Ruck Thawonmas KEYWORD(S): adaptive learning algorithms, blind signal processing, neural networks. PAGE(S): 91-98 -------------------------------------------------------------- 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 Patricia_Squadrito at Brown.edu Tue Sep 19 09:07:03 2000 From: Patricia_Squadrito at Brown.edu (Patricia Squadrito) Date: Tue, 19 Sep 2000 09:07:03 -0400 Subject: postdoctoral positions at Brown University Message-ID: BROWN UNIVERSITY. Post-doctoral positions available for cognitive or computational scientist. As part of an NSF award to Brown University through the IGERT program, the Departments of Cognitive and Linguistic Sciences, Computer Science, and Applied Mathematics are hiring research associates. The associates should be scholars who have displayed interest and ability in conducting collaborative interdisciplinary research involving a combination of computational and empirical approaches to one of the content areas of the program: cognition, language, or vision. As well as participating in collaborative research, responsibilities will include helping to coordinate cross-departmental events as well as some graduate teaching. Applicants must hold a PhD in Psychology, Linguistics, Cognitive Science, Computer Science, Mathematics, Applied Mathematics, or a related discipline, or show evidence that the PhD will be completed before the start of the position. Applicants should send a vita, a short research statement, three letters of reference, and other supporting material (e.g., representative publications if available), to IGERT Post-doc Search, Department of Cognitive and Linguistic Sciences, Brown University, Box 1978, Providence, RI 02912. Special consideration will be given to those applicants whose research is relevant to at least two of the participating departments. The positions are open immediately for one year, renewable upon satisfactory completion of duties. Salaries will be between $35,000 and $45,000 per year. All materials must be received by Feb. 1, 2001, for full consideration. Like all NSF-funded programs, this opportunity is available only to American citizens and permanent residents. Brown University is an Equal Opportunity/Affirmative Action Employer. From axon at cortex.rutgers.edu Tue Sep 19 09:06:40 2000 From: axon at cortex.rutgers.edu (Ralph Siegel) Date: Tue, 19 Sep 2000 09:06:40 -0400 Subject: Postdoctoral position - parietal cortex Message-ID: Postdoctoral Trainee. Analysis of visual structure-from-motion in primates. Representation of optic flow and attention in the inferior parietal lobes (area DP and 7a) are being examined in the awake behaving monkey. These studies utilize ***intrinsic optical recording***, single unit recording, in the behaving monkey. Recent graduates who are changing fields from either cellular or computational neuroscience to behavioral and physiological studies are particularly encouraged to apply. Computer expertise useful, but not necessary. Superb experimental and computational facilities in a multi-disciplinary research center. NY-NJ Metro area. Salary NIH scales plus supplement. Ralph Mitchell Siegel, Ph.D. Associate Professor axon at cortex.rutgers.edu voice: 973-353-1080 x3261 fax: 973-353-1272 Center for Molecular and Behavioral Neuroscience Rutgers, The State University 197 University Avenue Newark, NJ 07102 Graduate program information: http://www.bns.rutgers.edu/ Additional information and reprints: http://www.cmbn.rutgers.edu/~rmsiegel From terry at salk.edu Tue Sep 19 20:05:29 2000 From: terry at salk.edu (Terry Sejnowski) Date: Tue, 19 Sep 2000 17:05:29 -0700 (PDT) Subject: NEURAL COMPUTATION 12:10 Message-ID: <200009200005.e8K05Tv75812@purkinje.salk.edu> Neural Computation - Contents - Volume 12, Number 10 - October 1, 2000 Article Spike-Driven Synaptic Plasticity: Theory, Simulation, VLSI Implementation Stefano Fusi, Mario Annunziato, Davide Badoni, Andrea Salamon, and Daniel J. Amit Notes Modeling Alternation to Synchrony with Inhibitory Coupling: A VLSI Approach Gennady S. Cymbalyuk, Girish N. Patel, Ronald. L. Calabrese, Stephen P. DeWeerth, and Avis H. Cohen Representation of Concept Lattices by Bidirectional Associative Memories Radim Belohlavek Letters A Silicon Implementation of the Fly's Optomotor Control System Reid R. Harrison and Christof Koch Efficient Event-Driven Simulation of Large Networks of Spiking Neurons and Dynamical Synapses Maurizio Mattia and Paolo Del Giudice Clustering Irregular Shapes using High-Order Neurons H. Lipson and H. T. Siegelmann Learning Chaotic Attractors by Neural Networks Rembrandt Bakker, Jaap C. Schouten, C. Lee Giles, Floris Takens and Cor M. van den Bleek Generalized Discriminant Analysis Using a Kernel Approach G. Baudat and F. Anouar Generalization and Selection of Examples in Feed Forward Neural Networks Leonardo Franco and Sergio A. Cannas Stationary and Integrated Autoregressive Neural Network Processes Adrian Trapletti, Friedrich Leisch, and Kurt Hornik Learning To Forget: Continual Prediction with LSTM Felix A. Gers, Jurgen Schmidhuber, and Fred Cummins ----- 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 C.Campbell at bristol.ac.uk Wed Sep 20 05:57:09 2000 From: C.Campbell at bristol.ac.uk (Colin Campbell, Engineering Mathematics) Date: Wed, 20 Sep 2000 10:57:09 +0100 (GMT Daylight Time) Subject: Lectureship available Message-ID: Lectureship in Mathematics, University of Bristol. Applications are invited for a permanent Lectureship in Mathematics in the Department of Engineering Mathematics, University of Bristol, United Kingdom. Candidates should preferably have research interests overlapping with current interests in the department which include computational intelligence (support vector machines, neural computing, machine vision, logic programming, reasoning with uncertainty, etc). Candidates should have an excellent track record in research since the opening is in competition with the Nonlinear Dynamics Group in the department which typically gains a strong international field of applicants. Since the department is in a Faculty of Engineering our lecturing is strongly oriented towards applied mathematics. The department runs its own degree programmes in addition to providing mathematical or theoretical computer science courses for degree programmes elsewhere in the Faculty. The department achieved a score of 5 in the last Research Assessment Exercise (1996) and 23/24 for the HEFCE TQA assessment of its courses. For further details see: http://lara.enm.bris.ac.uk/cig or contact Dr. Colin Campbell (C.Campbell at bris.ac.uk). The closing date for applications is *** 15th October 2000 ***. -------------------------------------------- Dr. Colin Campbell, Dept. of Engineering Mathematics, Bristol University, Bristol BS8 1TR, United Kingdom http://lara.enm.bris.ac.uk/cig/ Tel +44 (0) 117 928 9858 C.Campbell at bristol.ac.uk From oby at cs.tu-berlin.de Wed Sep 20 15:12:01 2000 From: oby at cs.tu-berlin.de (Klaus Obermayer) Date: Wed, 20 Sep 2000 21:12:01 +0200 (MET DST) Subject: preprint available Message-ID: <200009201912.VAA14446@pollux.cs.tu-berlin.de> Dear Connectionists, attached please find abstract and preprint location of one manuscript on the analysis of Ca-imaging data from the olfactory system (antennal lobe) of the honeybee. Comments are welcome! Cheers Klaus ----------------------------------------------------------------------------- Prof. Dr. Klaus Obermayer phone: 49-30-314-73442 FR2-1, NI, Informatik 49-30-314-73120 Technische Universitaet Berlin fax: 49-30-314-73121 Franklinstrasse 28/29 e-mail: oby at cs.tu-berlin.de 10587 Berlin, Germany http://ni.cs.tu-berlin.de/ ============================================================================= Analysis of calcium imaging signals from the honeybee brain by nonlinear models M. Stetter^1,3, H. Greve^1, C. Galizia^2, and K. Obermayer^1 ^1 Fachbereich Informatik, Technische Universitaet Berlin ^2 Institut fuer Neurobiology, Freie Universitaet Berlin ^3 Zentrale Forschung, Siemens AG, Muenchen Recent Ca$^{2+}$-imaging studies on the antennal lobe of the honeybee {\it (Apis mellifera)} have shown that olfactory stimuli evoke complex spatiotemporal changes of the intracellular Ca$^{2+}$ concentration, in which stimulus-dependent subsets of glomeruli are highlighted. In this work we use nonlinear models for the quantitative identification of the spatial and temporal properties of the Ca$^{2+}$-dependent fluorescence signal. This technique describes time-series of the Ca$^{2+}$ signal as a superposition of biophysically motivated model functions for photobleaching and Ca$^{2+}$-dynamics, provides optimal estimates of their amplitudes (signal strengths) and time-constants together with error measures. Using this method, we can reliably identify two different stimulus-dependent signal components. Their delays and rise times, $delta_{c1} = (0.4 \pm 0.3)$~s, $\tau_{c1} = (3.8 \pm 1.2)$~s for the fast component and $\delta_{c2} = (2.4 \pm 0.6)$~s, $\tau_{c2} = (10.3 \pm 3.2)$~s for the slow component, are constant over space and across different odors and animals. In chronical experiments, the amplitude of the fast (slow) component often decreases (increases) with time. The pattern of the Ca$^{2+}$-dynamics in space and time can be reliably described as a superposition of only two spatiotemporally separable patterns based on the fast and slow components. However, the distributions of both components over space turn out to differ from each other, and more work has to be done in order to specify their relationship with neuronal activity. in: NeuroImage, in press available at: http://ni.cs.tu-berlin.de/publications/ From danr at cs.uiuc.edu Wed Sep 20 15:28:52 2000 From: danr at cs.uiuc.edu (Dan Roth) Date: Wed, 20 Sep 2000 14:28:52 -0500 Subject: Postdoctoral Position , Beckman Institute, UIUC Message-ID: <39C90FF4.23D2794E@cs.uiuc.edu> Postdoctoral Position Beckman Institute University of Illinois, Urbana-Champaign The Beckman Institute for Advanced Science and Technology is seeking a postdoctoral fellow for a new project funded by the National Science Foundation's ITR program entitled: "Multimodal Human Computer Interaction: Toward a Proactive Computer." This project involves a multi-disciplinary team of researchers from Electrical Engineering, Computer Science, Psychology and Education including Thomas Huang (ECE), David Brown (Ed), David Kriegman (CS), Steve Levinson (ECE), George McConkie (Psych), and Dan Roth (CS). The ideal candidate will have a broad vision of the future of human computer interaction and the technical skills to realize this with expertise in at least one of the following areas: computer vision, image processing, speech understanding, natural language, learning, decision systems, multimedia, or HCI. The candidate should have a Ph.D. in Computer Science, Electrical Engineering or a related field, should enjoy working with a team of researchers on large and challenging problems, should have experience in developing large software systems, and should communicate well in spoken and written English. This specific project is based on the belief that, to be more accessible to the general population, computers must be more proactive in their interactions with people. In human interaction, someone who waits for each command before making any communication attempt would be regarded as uncooperative and unhelpful. In order for a computer to be more proactive and, thus, to bear its part of the burden of initiation in interactions, it must have (1) much more real-time information about its user, and (2) algorithms that select actions based on this information rather than simply on user commands. The computer needs information about the user's current and past emotional, motivational and cognitive state as well as the state of the task at hand. Proposed research includes: (1) further development of methods to sense user postures, movements, expressions and speech; (2) Learning from multi-modal input; (3) analysis and fusion of this information to identify and track user states; (4) task state tracking; (5) creating a corpus of emotion- and action-labeled videotapes for use with computer learning; (6) further development of affective communication; (7) development of the basis for human-centered state-based action decisions; and (8) evaluation of computer proaction on human behavior and response. The testbed is an environment for hands-on education in science and engineering, using the Lego Mindstorms construction and robotics environment, with children of middle school age. An emphasis will be on developing proactive computing methods for encouraging interest and conceptual development of minority children and females, who often show lower achievement in science. Although the work will be conducted within an educational environment, the methods developed and studied will be broadly applicable, and this project should serve as an exemplar of the type of work that is needed in other computer-aided situations. Please send a CV and the names of three references to: Prof. Dan Roth Dept. of Computer Science University of Illinois, Urbana-Champaign 1304 Springfield Ave. Urbana, IL 61801 danr at cs.uiuc.edu From wsenn at cns.unibe.ch Thu Sep 21 05:52:21 2000 From: wsenn at cns.unibe.ch (Walter Senn) Date: Thu, 21 Sep 2000 11:52:21 +0200 (CEST) Subject: Preprint on spike-timing dependent synaptic plasticity Message-ID: The following preprint, `An algorithm for modifying neurotransmitter release probability based on pre- and post-synaptic spike timing', accepted at Neural Computation, can be downloaded from http://www.cns.unibe.ch/~wsenn/#pub. The paper reproduces data of Markram et al. (Science, 1997, including unpublished ones). It also investigates the connection to the BCM-rule and to correlation rules based on (Poisson) firing rates. Walter Senn, Henry Markram, Misha Tsodyks Abstract: The precise times of occurrence of individual pre- and post-synaptic action potentials is known to play a key role in the modification of the synaptic efficacy. Based on stimulation protocols of two synaptically connected neurons, we infer an algorithm which reproduces the experimental data by modifying the probability of vesicle discharge as a function of the relative timing of spikes in the pre- and post-synaptic neurons. The primary feature of this algorithm is an asymmetry with respect to the direction of synaptic modification depending on whether the presynaptic spikes precede or follow the postsynaptic spike. Specifically, if the presynaptic spike occurs up to 50ms before the postsynaptic spike, the probability of vesicle discharge is up-regulated while the probability of vesicle discharge is down-regulated if the presynaptic spike occurs up to 50ms after the postsynaptic spike. In the case where neurons fire irregularly with Poisson spike trains at constant mean firing rates, the probability of vesicle discharge converges towards a characteristic value which is determined by the pre- and post-synaptic firing rates. On the other hand, if the mean rates of the Poisson spike trains slowly change with time our algorithm predicts modifications in the probability of release which generalize Hebbian and BCM rules. We conclude that the proposed spike-based synaptic learning algorithm provides a general framework for regulating neurotransmitter release probability. From hopfield at Princeton.EDU Thu Sep 21 20:25:58 2000 From: hopfield at Princeton.EDU (John J. Hopfield) Date: Thu, 21 Sep 2000 20:25:58 -0400 Subject: Neural Computation Competition Message-ID: <39CAA716.3AEB5E3F@princeton.edu> ANNOUNCING A NEURAL COMPUTATION COMPETITION ------------------------------------------- by John Hopfield (hopfield at princeton.edu) and Carlos Brody (carlos at cns.nyu.edu) Web Site (with preprint): http://neuron.princeton.edu/~moment How do we identify spoken words? How do we recognize textures with our fingers? How do we integrate information over time to perceive structure-from-motion? All of the above are examples of the capacity of nervous systems to integrate information over time and recognize spatiotemporal patterns. How this is actually done in the brain remains, of course, a relative mystery. Here we wish to introduce a novel neural network, built on novel neurocomputational principles, which recognizes spatiotemporal patterns. We exemplify this with robust recognition of a monosyllabic utterance. Unusually, we have chosen to present this novel network in the form of a competition. We have treated the network as if it were a real biological organism, and we present only the results of the "experiments" that one would normally carry out with such a creature. (We have playfully dubbed the network "mus silicium, the sonoran desert sand mouse.") The experimental results presented are, we believe, sufficient to deduce the novel principles on which the network operates. For people wishing to carry out further experiments, we have constructed an interactive web site. Sound stimuli may be uploaded to this web site, and the resulting spike train responses of the mus silicium's neurons may be downloaded from the site. THE CHALLENGE, THEN, AND THE GOAL OF THE COMPETITION, IS TO DISCOVER, BASED ON THE "EXPERIMENTAL" RESULTS, HOW THE NETWORK OPERATES. In this the competition exactly mimics wet neurobiology. The rules of the competition are detailed further below and on the web site; on Dec. 14th, we will anounce the results of the competition and reveal the principles of the network's operation. However, although we have formalized the competition, and we provide specific rules and prizes, we do wish to emphasize that the greatest benefits of the exercise are to be found simply by *trying to DEDUCE, based on the extant "experimental" results, how the network operates*. The prizes and formal competition are there merely for extra fun, they contain no scientific information in themselves. The interactive web site/homepage for this network and associated competition, containing full information on the network, a preprint, and the competition rules, is: http://neuron.princeton.edu/~moment. To be considered, competition entries must be received by carlos at cns.nyu.edu or hopfield at princeton.edu PRIOR to Friday 1st December 2000. ---------- MOTIVATION ---------- We wish to note that there are two quite distinct aspects to what we are doing: (1) We are presenting novel computational principles which we believe will be of great interest to the computational neuroscience and connectionist community. Because of the method of presentation, we cannot demonstrate these principles to you directly. At this point, we can only give you our word that, in our own estimation, they are simple, powerful, biologically plausible, and novel. (2) In computational neuroscience modeling one typically "guesstimates", on the basis of experience, which aspects of the data are relevant and which are irrelevant. One then builds a model consistent with the chosen relevant aspects. This process is an example of what we will term "RATIONAL" reasoning. The rational view as applied to neuroscience allows data properties to be caused by unknown factors such as unobserved cell types, novel channels, etc. This approach should be distinguished from DEDUCTIVE reasoning, for which once basic properties are sufficiently known, new conclusions can be logically deduced from even apparently minor aspects of inconsistency or the unexpected. Deduction is enormously different from even the most rational "guesstimation." Given the quantity of diverse data now available in neuroscience, the question we are posing with our network and which we underscore through the competition is: to what extent is a deductive approach becoming useful in neurobiology? ---------------- THE COMPETITIONS ---------------- Further details of the competition rules can be found through the main site, http://neuron.princeton.edu/~moment. There are two "mus silicium" competitions. You can enter one or both, as you wish. The goal of CONTEST A is to write a 750 word essay, with or without equations, describing how you convincingly reasoned deductively from the experimental results presented in the preprint (augmented if desired with further experiments you may have carried out or seen on the web site) to understand the principles by which the "mus silicium" network operates. The cash prize for the best essay is $500, for the runner-up $200. The goal of CONTEST B is to generate an artificial neural network, of approximately the same size, complexity, and biological plausibility as "mus silicium", which recognizes the spoken word "one". The actual "mus silicium" network can be thought of as merely one possible entry meting the specifications of this contest. The cash prize for the best recognizer network is $500, for the runner-up $200. On the website, we detail what we mean by a network of "approximately same size, complexity", etc. as "mus silicium." For Contest B, we provide on the web site a front end that turns sound files into spatiotemporal patterns of timed events. Thus, Contest B is essentially about generating a network that recognizes spatiotemporal patterns (which underscores the generality of the problem being addressed), while using a limited number of simple, biologically plausible spiking neurons. (Needless to say, we think that, if entered, "mus silicium" would win Contest B-- but maybe we are wrong!) For both contests, entries must be submitted by email to either hopfield at princeton.edu or carlos at cns.nyu.edu before Dec. 1st, 2000. Multiple author submissions are welcome. A group of N authors can submit N entries. From hoethker at ira.uka.de Fri Sep 22 03:22:05 2000 From: hoethker at ira.uka.de (Karin Hoethker) Date: Fri, 22 Sep 2000 09:22:05 +0200 Subject: Job offer in Karlsruhe: modeling melodic structure Message-ID: <39CB089D.89E36C7C@ira.uka.de> ------------------------------------------------------------------------ JOB OFFER "Modelling melodic structure with learning-based methods" ------------------------------------------------------------------------ PROJECT "Modelling melodic structure with learning-based methods" The goal of the project is the development of learning-based methods for detecting style-typical properties of melodies. These methods will be used for analysis and recognition of melodic styles (style-critical analysis) and for the generation of new melodies in a learned style (style imitation). We will use learning-based methods, because adaptive models do not rely on hard-wired assumptions about relevant relationships between melodic features and are therefore substantially style-independent. Furthermore, they allow to control the complexity of a model and thereby to optimize its generalization capability. The resulting methods will be applied to retrieve melodies in a given style from a database and to generate new melodies within an evolutionary framework. For evaluation, folk tunes of different origins and 'classical' melodies will be considered. Two researchers and two students will work on the project. There will be close contact with the institute's Neural Network Group which covers a broad range of methodological issues as well as applications of learning-based methods. A fully-equipped music laboratory is available. The project is funded by the Klaus Tschira Foundation, has a total duration of two years and will prospectively start in January 2001. POSITION A research position is available for the duration of 1-2 years. We are looking for a computer scientist/mathematician with experience in musical informatics or a musicologist with strong background in computer science, preferably at post-doctoral level. Experience in the area of neural networks/machine learning and C/C++ programming skills are desirable. Appointment will be full-time. The salary will be based on BAT IIa, which is the usual salary for scientific employees in German universities. Due to the project scheduling, the earliest possible date of entry is January 2001, the latest is January 2002. The place of employment is Karlsruhe, Germany. APPLICATION Please send your application including * a curriculum vitae, * a statement about your professional interests and goals, and * three relevant publications to Institut f"ur Logik, Komplexit"at und Deduktionssysteme Prof. Dr. W. Menzel Information Structures in Music Universit"at Karlsruhe Am Fasanengarten 5 D-76128 Karlsruhe Germany Alternatively, you can submit your application electronically to musik at ira.uka.de. The deadline for applications is 15.11.2000. The University of Karlsruhe intends to increase the percentage of women in research positions and therefore encourages women to apply. ADDITIONAL INFORMATION "Information structures in music" group http://i11www.ira.uka.de/~musik Klaus Tschira Foundation http://www.kts.villa-bosch.de/ University of Karlsruhe http://www.uni-karlsruhe.de/ City of Karlsruhe http://www.karlsruhe.de/ Please send further inquiries to Karin H"othker (hoethker at ira.uka.de). From: esann To: "Connectionists at cs.cmu.edu" References: From bogus@does.not.exist.com Fri Sep 22 11:26:15 2000 From: bogus@does.not.exist.com () Date: Fri, 22 Sep 2000 17:26:15 +0200 Subject: CFP: ESANN'2001 European Symposium on Artificial Neural Networks Message-ID: ---------------------------------------------------- | | | ESANN'2001 | | | | 9th European Symposium | | on Artificial Neural Networks | | | | Bruges (Belgium) - April 25-26-27, 2001 | | | | First announcement and call for papers | ---------------------------------------------------- Technically co-sponsored by the IEEE Neural Networks Council (TBC), the IEEE Region 8, the IEEE Benelux Section, and the International Neural Networks Society. The call for papers for the ESANN'2001 conference is now available on the Web: http://www.dice.ucl.ac.be/esann For those of you who maintain WWW pages including lists of related ANN sites: we would appreciate if you could add the above URL to your list; thank you very much! We try as much as possible to avoid multiple sendings of this call for papers; however please apologize if you receive this e-mail twice, despite our precautions. You will find below a short version of this call for papers, without the instructions to authors (available on the Web). If you have difficulties to connect to the Web please send an e-mail to esann at dice.ucl.ac.be and we will send you a full version of the call for papers. ESANN'2001 is organised in collaboration with the UCL (Universite catholique de Louvain, Louvain-la-Neuve) and the KULeuven (Katholiek Universiteit Leuven). Scope and topics ---------------- Since its first edition in 1993, the European Symposium on Artificial Neural Networks has become the reference for researchers on fundamentals and theoretical aspects of artificial neural networks. Each year, around 100 specialists attend ESANN, in order to present their latest results and comprehensive surveys, and to discuss the future developments in this field. The ESANN'2001 conference will focus on fundamental aspects of ANNs: theory, models, learning algorithms, mathematical aspects, approximation of functions, classification, control, time-series prediction, statistics, signal processing, vision, self-organization, vector quantization, evolutive learning, psychological computations, biological plausibility, etc. Papers on links and comparisons between ANNs and other domains of research (such as statistics, data analysis, signal processing, biology, psychology, evolutive learning, bio-inspired systems, etc.) are encouraged. Papers will be presented orally (no parallel sessions) and in poster sessions; all posters will be complemented by a short oral presentation during a plenary session. It is important to mention that it is the topics of the paper which will decide if it better fits into an oral or a poster session, not its quality. The selection of posters will be identical to oral presentations, and both will be printed in the same way in the proceedings. Nevertheless, authors have the choice to indicate on the author submission form that they only accept to present their paper orally. The following is a non-exhaustive list of topics covered during the ESANN conferences: * theory * models and architectures * mathematics * learning algorithms * vector quantization * self-organization * RBF networks * Bayesian classification * recurrent networks * support-vector machines * approximation of functions * time series forecasting * adaptive control * statistical data analysis * independent component analysis * signal processing * cellular neural networks * fuzzy neural networks * natural and artificial vision * hybrid networks * identification of non-linear dynamic systems * biologically plausible artificial networks * bio-inspired systems * adaptive behavior * evolutive learning Special sessions ---------------- Special sessions will be organized by renowned scientists in their respective fields. Papers submitted to these sessions are reviewed according to the same rules as any other submission. Authors who submit papers to one of these sessions are invited to mention it on the author submission form; nevertheless, submissions to the special sessions must follow the same format, instructions and deadlines as any other submission, and must be sent to the same address. * Neural networks applications in finance M. Cottrell, Univ. Paris I (France), E. de Bodt (Univ. Lille II (France) & UCL Louvain-la-Neuve (Belgium) * Artificial neural networks and early vision processing C. Fyfe, D. Charles, Univ. of Paisley (Scotland) * Artificial neural networks for web computing M. Maggini, Univ. di Siena (Italy) * Dedicated hardware implementations: perspectives on systems and applications D. Anguita, M. Valle, Univ. of Genoa (Italy) * Novel neural transfer functions W. Duch, Nicholas Copernicus Univ. (Poland) * Neural networks and evolutionary/genetic algorithms - hybrid approaches T. Villmann, Univ. Leipzig (Germany) Location -------- The conference will be held in Bruges (also called "Venice of the North"), one of the most beautiful medieval towns in Europe. Bruges can be reached by train from Brussels in less than one hour (frequent trains). The town of Bruges is world-wide known, and famous for its architectural style, its canals, and its pleasant atmosphere. The conference will be organised in a hotel located near the centre (walking distance) of the town. There is no obligation for the participants to stay in this hotel. Hotels of all level of comfort and price are available in Bruges; there is a possibility to book a room in the hotel of the conference at a preferential rate through the conference secretariat. A list of other smaller hotels is also available. The conference will be held at the Novotel hotel, Katelijnestraat 65B, 8000 Brugge, Belgium. Call for contributions ---------------------- Prospective authors are invited to submit * six copies of their manuscript (including at least two originals or very good copies without glued material, which will be used for the proceedings) * one signed copy of the author submission form * a floppy disk or a CD (PC format preferred) containing their contribution in (generic) PostScript format before December 8, 2000. Sorry, electronic or fax submissions are not accepted. The working language of the conference (including proceedings) is English. The instructions to authors, together with the author submission form, are available on the ESANN Web server: http://www.dice.ucl.ac.be/esann Authors must indicate their choice for oral or poster presentation on the author submission form. They must also sign a written agreement that they will register to the conference and present the paper in case of acceptation of their submission. Authors of accepted papers will have to register before February 28, 2001. They will benefit from the advance registration fee. Submissions must be sent to: Michel Verleysen UCL - DICE 3, place du Levant B-1348 Louvain-la-Neuve Belgium esann at dice.ucl.ac.be All submissions will be acknowledged by fax or email before December 22, 2000. Deadlines --------- Submission of papers December 8, 2000 Notification of acceptance February 5, 2001 Symposium April 25-27, 2001 Registration fees ----------------- registration before registration after March 16, 2001 March 16, 2001 Universities BEF 16500 BEF 17500 Industries BEF 20500 BEF 21500 The registration fee includes the attendance to all sessions, the ESANN'2001 dinner, a copy of the proceedings, daily lunches (25-27 April 2001), and the coffee breaks. Conference secretariat ---------------------- Michel Verleysen D facto conference services phone: + 32 2 420 37 57 27 rue du Laekenveld Fax: + 32 2 420 02 55 B - 1080 Brussels (Belgium) E-mail: esann at dice.ucl.ac.be http://www.dice.ucl.ac.be/esann Steering and local committee (to be confirmed) ---------------------------- Francois Blayo Prefigure (F) Marie Cottrell Univ. Paris I (F) Jeanny Herault INPG Grenoble (F) Henri Leich Fac. Polytech. Mons (B) Bernard Manderick Vrije Univ. Brussel (B) Eric Noldus Univ. Gent (B) Jean-Pierre Peters FUNDP Namur (B) Joos Vandewalle KUL Leuven (B) Michel Verleysen UCL Louvain-la-Neuve (B) Scientific committee (to be confirmed) -------------------- Edoardo Amaldi Politecnico di Milano (I) Herve Bourlard IDIAP Martigny (CH) Joan Cabestany Univ. Polit. de Catalunya (E) Colin Campbell Bristol Univ. (UK) Stephane Canu Inst. Nat. Sciences App. (F) Holk Cruse Universitat Bielefeld (D) Eric de Bodt Univ. Lille II & UCL Louv.-la-N. (B) Dante Del Corso Politecnico di Torino (I) Wlodek Duch Nicholas Copernicus Univ. (PL) Marc Duranton Philips / LEP (F) Richard Duro Univ. Coruna (E) Jean-Claude Fort Universite Nancy I (F) Bernd Fritzke Dresden Univ. of Technology (D) Colin Fyfe Univ. Paisley (UK) Stan Gielen Univ. of Nijmegen (NL) Marco Gori Univ. Siena (I) Bernard Gosselin Fac. Polytech. Mons (B) Manuel Grana UPV San Sebastian (E) Anne Guerin-Dugue INPG Grenoble (F) Martin Hasler EPFL Lausanne (CH) Laurent Herault CEA-LETI Grenoble (F) Gonzalo Joya Univ. Malaga (E) Christian Jutten INPG Grenoble (F) Juha Karhunen Helsinky Univ. of Technology (FIN) Vera Kurkova Acad. of Science of the Czech Rep. (CZ) Jouko Lampinen Helsinki Univ. of Tech. (FIN) Petr Lansky Acad. of Science of the Czech Rep. (CZ) Mia Loccufier Univ. Gent (B) Erzsebet Merenyi Rice Univ. (USA) Jean Arcady Meyer Univ. Pierre et Marie Curie - Paris 6 (F) Jose Mira UNED (E) Jean-Pierre Nadal Ecole Normale Superieure Paris (F) Gilles Pages Univ. Pierre et Marie Curie - Paris 6 (F) Thomas Parisini Politecnico di Milano (I) Helene Paugam-Moisy Univ. Lumiere Lyon 2 (F) Alberto Prieto Universitad de Granada (E) Leonardo Reyneri Politecnico di Torino (I) Tamas Roska Hungarian Academy of Science (H) Jean-Pierre Rospars INRA Versailles (F) Jose Santos Reyes Univ. Coruna (E) John Stonham Brunel University (UK) Johan Suykens KUL Leuven (B) John Taylor King's College London (UK) Claude Touzet IUSPIM Marseilles (F) Marc Van Hulle KUL Leuven (B) Thomas Villmann Univ. Leipzig (D) Christian Wellekens Eurecom Sophia-Antipolis (F) From R.J.Howlett at bton.ac.uk Fri Sep 22 12:25:58 2000 From: R.J.Howlett at bton.ac.uk (R.J.Howlett@bton.ac.uk) Date: Fri, 22 Sep 2000 17:25:58 +0100 Subject: Research vacancy Message-ID: <08C89600D966D4119C7800105AF0CB6B4B00CC@moulsecoomb.bton.ac.uk> -- Intelligent Signal Processing Labs, University of Brighton, Sussex, UK.-- --------- Research Vacancy on scale approx #17000-#24000 --------- An opportunity to develop software skills as a member of an established research group in leading-edge area of technology. You will work on a project to develop new intelligent data analysis techniques that can be used for monitoring and control in a range of applications. There may be an opportunity to extend the work to applying intelligent techniques to data obtained ("mined") automatically from the internet. The work will involve existing software tools (neural networks) and developing them to enhance their capabilities, and also the development of new neural network algorithms. A good first degree in an appropriate subject is required; a PhD in an appropriate field would be an advantage. You should have good programming and software development ability, and good laboratory, practical and measurement skills. Some knowledge of neural networks or other intelligent techniques would be an advantage. The post is available immediately, fixed-term until the 31 December 2001 in accordance with the period of funding. However, one of the duties of the applicant will be to attempt to secure further funding to extend the period of employment. We are unlikely to be able to consider candidates who are not currently available in the UK for interview. To apply send a CV by email to:- R.J.Howlett at bton.ac.uk Please quote ref: SE4010 From kap-listman at wkap.nl Fri Sep 22 20:02:31 2000 From: kap-listman at wkap.nl (kap-listman@wkap.nl) Date: Sat, 23 Sep 2000 02:02:31 +0200 (MEST) Subject: New Issue: Neural Processing Letters. Vol. 12, Issue 2 Message-ID: <200009230002.CAA07209@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+2+2000 Vol. 12, Issue 2, October 2000. TITLE: Obtaining Fault Tolerant Multilayer Perceptrons Using an Explicit Regularization AUTHOR(S): Jose L. Bernier, J. Ortega, I. Rojas, E. Ros, A. Prieto KEYWORD(S): backpropagation, regularization, multilayer perceptron, fault tolerance, mean square sensitivity. PAGE(S): 107-113 TITLE: Evolving Multilayer Perceptrons AUTHOR(S): P. A. Castillo, J. Carpio, J. J. Merelo, A. Prieto, V. Rivas, G. Romero KEYWORD(S): evolutionary algorithms, generalization, learning, neural networks, optimization. PAGE(S): 115-128 TITLE: Associative Memories in Infinite Dimensional Spaces AUTHOR(S): Enrique Carlos Segura, Roberto P. J. Perazzo KEYWORD(S): associative memory, dynamical systems, Glauber dynamics, Hopfield model, infinite dimensional state space, stability. PAGE(S): 129-144 TITLE: Embedding Connectionist Autonomous Agents in Time: The `Road Sign Problem' AUTHOR(S): R. M. Rylatt, C. A. Czarnecki KEYWORD(S): autonomous agents, recurrent neural networks. PAGE(S): 145-158 TITLE: Globally Convergent Modification of the Quickprop Method AUTHOR(S): Michael N. Vrahatis, George D. Magoulas, Vassilis P. Plagianakos KEYWORD(S): Quickprop algorithm, Broyden-s method, secant methods, convergence analysis, backpropagation neural networks. PAGE(S): 159-170 TITLE: Parallel Implementation of Self-Organizing Map on the Partial Tree Shape Neurocomputer AUTHOR(S): Pasi Kolinummi, Pasi Pulkkinen, Timo Hamalainen, Jukka Saarinen KEYWORD(S): computer architecture, neurocomputer, parallel hardware implementation, parallel mapping, self-organizing map. PAGE(S): 171-182 TITLE: Improving the Mean-Field Approximation in Belief Networks Using Bahadur-s Reparameterisation of the Multivariate Binary Distribution AUTHOR(S): K. Humphreys, D. M. Titterington KEYWORD(S): Bahadur, belief network, EM algorithm, Mean-Field, variational approximation. PAGE(S): 183-197 -------------------------------------------------------------- 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 steve at cns.bu.edu Sun Sep 24 19:09:38 2000 From: steve at cns.bu.edu (Stephen Grossberg) Date: Sun, 24 Sep 2000 19:09:38 -0400 Subject: a neural model of smooth pursuit control and motion perception by MST Message-ID: The following article is available at http://www.cns.bu.edu/Profiles/Grossberg in HTML, PDF, and Gzipped postscript: Pack, C., Grossberg, S. and Mingolla, E. (2000). A neural model of smooth pursuit control and motion perception by cortical area MST. Journal of Cognitive Neuroscience, in press. Preliminary version available as Technical Report CAS/CNS-TR-99-023, Boston: Boston University. ABSTRACT: Smooth pursuit eye movements are eye rotations that are used to maintain fixation on a moving target. Such rotations complicate the interpretation of the retinal image, because they nullify the retinal motion of the target, while generating retinal motion of stationary objects in the background. This poses a problem for the oculomotor system, which must track the stabilized target image, while suppressing the optokinetic reflex, which would move the eye in the direction of the retinal background motion, which is opposite to the direction in which the target is moving. Similarly, the perceptual system must estimate the actual direction and speed of moving objects in spite of the confounding effects of the eye rotation. This paper proposes a neural model to account for the ability of primates to accomplish these tasks. The model simulates the neurophysiological properties of cell types found in the superior temporal sulcus of the macaque monkey, specifically the medial superior temporal (MST) region. These cells process signals related to target motion, background motion, and receive an efference copy of eye velocity during pursuit movements. The model focuses on the interactions between cells in the ventral and dorsal subdivisions of MST, which are hypothesized to process target velocity and background motion, respectively. The model explains how these signals can be combined to explain behavioral data about pursuit maintenance and perceptual data from human studies, including the Aubert-Fleischl phenomenon and the Filehne Illusion, thereby clarifying the functional significance of neurophysiological data about these MST cell properties. It is suggested that the connectivity used in the model may represent a general strategy used by the brain in analyzing the visual world. Keywords: smooth pursuit, eye movements, visual cortex, MST, motion, optokinetic nystagmus, target tracking, perception From glanzman at helix.nih.gov Mon Sep 25 09:01:54 2000 From: glanzman at helix.nih.gov (Dennis Glanzman) Date: Mon, 25 Sep 2000 09:01:54 -0400 Subject: Positions Available at the NIMH Message-ID: <4.3.2.7.2.20000925090125.00b205f0@helix.nih.gov> We are currently recruiting outstanding scientists to fill the following four positions at the National Institute of Mental Health in Bethesda, MD. Interdisciplinary Scientist (GS-180/401/601/602-13/14) Eligibility: U.S. citizenship is required. This position is open to all qualified applicants. Salary Range: $60,890.00 - $93,537.00 For further information: http://www.nimh.nih.gov/orm/pmb/nimh000112.htm The incumbent of this position has primary responsibility for the Basic Neuroscience Centers Program, and works closely with other program staff of the Division of Neuroscience and Basic Behavioral Science to assure that the appropriate substantive expertise is brought to bear on all aspects of this program. In this role, the incumbent is responsible for the programmatic evaluation of research grant applications based on the scientific value and pertinence to the interest of this program's objectives which have been approved by a review committee and the National Advisory Mental Health Council. The incumbent makes recommendations for the funding of approved grants for which the incumbent is responsible; regularly consults with other staff members of the Office and Division to advise on program content as it pertains to the program area; attends scientific meetings and conferences to ensure that program objectives and developments are related to the needs of the field, and to present and explain the activities and objectives of the program as well as to present material and chair sessions. The incumbent organizes meetings (workshops, symposia, conference, etc.) on relevant topics; maintains knowledge of the rules, regulations, guidelines, ethics, and public policy concerning the use of humans and animals in research. The incumbent also provides adequate exchange of information with other Offices, Branches, Divisions, and Institutes, various other Federal agencies, professional groups, and scientific and private organizations; cooperates with these groups and agencies regarding research problems and serves as a working member analyzing and evaluating these research endeavors within the scope of the program. Interdisciplinary Scientist (GS-180/401/601/602-13/14) Eligibility: U.S. citizenship is required. This position is open to all qualified applicants. Salary Range: $60,890.00 - $93,537.00 For further information: http://www.nimh.nih.gov/orm/pmb/nimh000110.htm The incumbent of this position provides scientific guidance and direction for a major research program -- the Integrative Neuroscience of Schizophrenia, Mood and Other Brain Disorders Program. This Program constitutes a major segment of the Branch and is designed to support research probing matters fundamental to knowledge of integrative, cognitive, and behavioral neuroscience as they relate to brain disorders and complex mental disorders. The position requires broad competence in basic neuroscience as the incumbent will provide scientific guidance and direction for this program. The incumbent performs duties in three major areas: project management and administration; program leadership and development; and personal scientific activities. For example, the incumbent is expected to analyze current research activities and program needs and identify areas under development that relate to integrative, cognitive, and behavioral neuroscience research as related to brain disorders relevant to mental health. He/she monitors new developments in the field and identifies research opportunities in areas not yet explored; provides technical advice to grantees and contractors on programmatic, scientific, and/or technical issues, including the design, development and implementation of projects and related activities; and organizes and/or represents the Institute at scientific meetings, symposia, and conferences on related topics. Interdisciplinary Scientist (GS-180/401/601/602-13/14) Eligibility: U.S. citizenship is required. This position is open to all qualified applicants. Salary Range: $60,890.00 - $93,537.00 For further information: http://www.nimh.nih.gov/orm/pmb/nimh000111.htm The position to be filled is Chief of the Cognitive Neuroscience Program in the Behavioral and Integrative Neuroscience Research Branch (BINRB). This branch plans, supports, and conducts programs of research, research training, and resource development in the neurobiological basis of behavioral processes, focusing on cognition, learning and memory, and psychopharmacology, as well as computational, theoretical, and related studies. The Cognitive Neuroscience Program represents a major segment of the Branch and is designed to develop and support basic neurobehavioral studies focusing on cognitive research to provide fundamental knowledge to understand, evaluate and treat emotion and mental disorders. The position requires broad competence in basic neuroscience as the incumbent will provide scientific guidance and direction for this program. The incumbent performs duties in three major areas: project management and administration; program leadership and development; and personal scientific activities. For example, the incumbent is expected to analyze current research activities and program needs and identify areas under development that relate to integrative, cognitive, and behavioral neuroscience research as related to brain disorders relevant to mental health. He/she monitors new developments in the field and identifies research opportunities in areas not yet explored; provides technical advice to grantees and contractors on programmatic, scientific, and/or technicalissues, including the design, development and implementation of projects and related activities; and organizes and/or represents the Institute at scientific meetings, symposia, and conferences on related topics. Assoc. Div. Dir Program Analysis & Management (GS-180/401/601/602-14/15) Eligibility: U.S. citizenship is required. This position is open to all qualified applicants. Salary Range $71,954.00 - $110,028.00 http://www.nimh.nih.gov/orm/pmb/nimh000113.htm This position is located in the Division of Neuroscience and Basic Behavioral Science (DNBBS), National Institute of Mental Health (NIMH). This Division oversees NIMH funding of extramural research programs in the areas of basic and clinical neuroscience, genetics, therapeutics development, basic behavioral science, and research training in these areas. Oversight functions include the analysis and evaluation of the current state of these fields, the national research portfolio, and developing research opportunities in the etiology, treatment, and prevention of brain and behavioral disorders. As Associate Division Director, the incumbent assists the Director in the day-to-day scientific and administrative management of the Division's research grant and contract portfolio. He/she is responsible for the continuous review and evaluation of the Division's research grant and contract supported activities designed to further understand the etiology, treatment, and prevention of brain and behavioral disorders relevant to mental health. Activities include: translating emerging needs into programs and goals for the NIMH; monitoring program growth and recommending new program emphasis or direction, adjustments to existing programs, or complete shifts in existing programs in order to maximize the impact of the overall mental health extramural research program; leading or arranging collaborative research efforts with professional scientific groups to bring the effective interaction of ideas and methods and synthesizing the results into cohesive studies. The incumbent serves as the Division's authority for research grants and contracts administration and management policy matters. As such, he/she assesses ongoing or proposed programs for Agency and Departmental grant and contract policy compliance; reviews all new or proposed grants and contracts policy issuances; develops policy positions and represents the Division in the development of Institute and Agency policy on extramural research. The incumbent assists in the formulation and presentation of budget requests and justifications for the Division's programs to the NIMH, NIH and Congress. Develops information and guidance for research, consultant and advisory groups, and members of Congress, Office of Management and Budget, and scientific and lay organizations. Maintains liaison with similar activities carried out in the NIMH, NIH, HHS, other governmental agencies and professional and scientific organizations to avoid duplication of effort and to exchange relevant information. Represents the Institute on committees and working groups, at professional and staff meetings, and regular and ad hoc meetings. From cindy at cns.bu.edu Wed Sep 27 10:56:38 2000 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Wed, 27 Sep 2000 10:56:38 -0400 Subject: 5th ICCNS: Call for Papers Message-ID: <200009271456.KAA27700@retina.bu.edu> ***** CALL FOR PAPERS ***** FIFTH INTERNATIONAL CONFERENCE ON COGNITIVE AND NEURAL SYSTEMS Tutorials: May 30, 2001 Meeting: May 31 - June 2, 2001 Boston University 677 Beacon Street Boston, Massachusetts 02215 http://www.cns.bu.edu/meetings/ Sponsored by Boston University's Center for Adaptive Systems and Department of Cognitive and Neural Systems with financial support from the National Science Foundation and the Office of Naval Research This interdisciplinary conference has drawn about 300 people from around the world each time that it has been offered. Last year's conference was attended by scientists from 28 countries. The conference is structured to facilitate intense communication between its participants, both in the formal sessions and during its other activities. As during previous years, the conference will focus on solutions to the fundamental questions: How Does the Brain Control Behavior? How Can Technology Emulate Biological Intelligence? The conference will include invited tutorials and lectures, and contributed lectures and posters by experts on the biology and technology of how the brain and other intelligent systems adapt to a changing world. The conference is aimed at researchers and students of computational neuroscience, connectionist cognitive science, artificial neural networks, neuromorphic engineering, and artificial intelligence. A single oral or poster session enables all presented work to be highly visible. Abstract submissions encourage submissions of the latest results. Costs are kept at a minimum without compromising the quality of meeting handouts and social events. CALL FOR ABSTRACTS Session Topics: * vision * spatial mapping and navigation * object recognition * neural circuit models * image understanding * neural system models * audition * mathematics of neural systems * speech and language * robotics * unsupervised learning * hybrid systems (fuzzy, evolutionary, digital) * supervised learning * neuromorphic VLSI * reinforcement and emotion * industrial applications * sensory-motor control * 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 Abstract 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 giacinto at diee.unica.it Wed Sep 27 05:06:14 2000 From: giacinto at diee.unica.it (Giorgio Giacinto) Date: Wed, 27 Sep 2000 11:06:14 +0200 Subject: PAA - Special Issue Call "Fusion of Multiple Classifiers" Message-ID: ***************************************** Pattern Analysis and Applications Journal Special Issue Call Fusion of Multiple Classifiers ***************************************** Guest Editors: J. Kittler and F. Roli Deadline: 15 October 2000 Classifier fusion has recently become an important tool for enhancing the performance of pattern recognition systems. A myriad of techniques have been developed for combining classifiers at the decision or soft decision output level. These techniques have been conceived by researchers in many diverse communities including Machine Learning, Pattern Recognition, Neural Networks, Statistics, and Artificial Intelligence. The aim of this special issue is to provide a focal point for recent advances in this methodological area of pattern recognition across different paradigms and disciplines. Submitted papers should report new theories underpinning classifier combination, novel methodologies, applications where classifier fusion significantly enhanced the recognition system performance, or extensive comparative studies of different combination rules. Topics appropriate for this special issue include, but are not limited to: * Decision level fusion * Strategies for multiple classifier fusion * Bagging and boosting * Neural network ensembles * Multiple classifier design * Fusion of one-class classifiers * Fusion of measurement and contextual information * Innovative applications Send four copies of your manuscript (marked "MCS SPECIAL ISSUE") by October 15, 2000 to the following address: Sameer Singh, Editor-in-Chief, Pattern Analysis and Applications, Department of Computer Science, University of Exeter, Exeter EX4 4PT, UK For instructions to authors, please see: http://www.dcs.ex.ac.uk/paa/authors.htm ------------------------------------------------------------- Dr. Giorgio Giacinto, Ph.D. Department of Electrical and Electronic Engineering University of Cagliari, Italy e-mail: giorgio.giacinto at computer.org From jab at ai.mit.edu Wed Sep 27 16:27:42 2000 From: jab at ai.mit.edu (Justin Boyan) Date: Wed, 27 Sep 2000 16:27:42 -0400 Subject: survey/proceedings on Statistical ML for Large-Scale Optimization Message-ID: <14802.22590.437810.357646@ai.mit.edu> Colleagues, At last year's IJCAI, Wray Buntine and I organized an IJCAI workshop on the subject of applying statistical machine learning methods in large-scale optimization domains. With Arun Jagota's help, we have now collected extended abstracts of all the presented work, and several additional contributions, into a survey paper which we believe contains the seeds of many exciting research directions. Here's where you can find it: http://www.icsi.berkeley.edu/~jagota/NCS/ (click on "VOLUME 3") I've attached the table of contents below. We have also set up an email list, learning-optimization at egroups.com, for discussion of related topics. If you'd like to join this list, please visit egroups.com or use the sign-up form at http://ic.arc.nasa.gov/people/jboyan/ijcai99/ Cheers, Justin Statistical Machine Learning for Large-Scale Optimization Editors: Justin Boyan, Wray Buntine, and Arun Jagota Contents: Introduction (J. Boyan) A Review of Iterative Global Optimization (K. Boese) Estimating the Number of Local Minima in Complex Search Spaces (R. Caruana and M. Mullins) Experimentally Determining Regions of Related Solutions for Graph Bisection Problems (T. Carson and R. Impagliazzo) Optimization of Parallel Search Using Machine Learning and Uncertainty Reasoning (D. Cook, P. Gmytrasiewicz, and C. Tseng) Adaptive Heuristic Methods for Maximum Clique (A. Jagota and L. Sanchis) Probabilistic Modeling for Combinatorial Optimization (S. Baluja and S. Davies) Adaptive approaches to Clustering for Discrete Optimization (W. Buntine, L. Su and R. Newton) Building a Basic Block Instruction Scheduler with Reinforcement Learning and Rollouts (A. McGovern, E. Moss and A. Barto) STAGE Learning for Local Search (J. Boyan and A. Moore) Enhancing Discrete Optimization with Reinforcement Learning: Case Studies Using DARP (R. Moll, T. Perkins and A. Barto) Stochastic Optimization with Learning for Standard Cell Placement (L. Su, W. Buntine, R. Newton and B. Peters) Collective Intelligence for Optimization (D. Wolpert and K. Tumer) Efficient Value Function Approximation Using Regression Trees (X. Wang and T. Dietterich) Numerical Methods for Very High-Dimension Vector Spaces (T. Dean, K. Kim, and S. Hazlehurst) -- Justin A. Boyan [Visiting Scientist from NASA Ames Research Center] MIT Artificial Intelligence Lab jab at ai.mit.edu 545 Technology Square NE43-753 http://ic.arc.nasa.gov/people/jboyan Cambridge, MA 02139 (617)-253-8005 voice, (617)-253-7781 fax From giacinto at diee.unica.it Wed Sep 27 05:01:16 2000 From: giacinto at diee.unica.it (Giorgio Giacinto) Date: Wed, 27 Sep 2000 11:01:16 +0200 Subject: 2nd Internation Workshop on Multiple Cassifier Systems Message-ID: ************************************************************ Preliminary Call for Papers MCS 2001 SECOND INTERNATIONAL WORKSHOP ON MULTIPLE CLASSIFIER SYSTEMS Robinson College, Cambridge, UK, July 2-4 2001 Updated information: http://www.diee.unica.it/mcs E-mail: mcs2001 at eim.surrey.ac.uk ************************************************************* WORKSHOP OBJECTIVES MCS 2001 is the second workshop of a series aimed to create a common international forum for researchers of the diverse communities working in the field of multiple classifier systems. Information on the first edition of MCS workshop can be found on www.diee.unica.it/mcs. Contributions from all the research communities working in the field are welcome in order to compare the different approaches and to define the common research priorities. Special attention is also devoted to assess the applications of multiple classifier systems and the potential market perspectives. The papers will be published in the workshop proceedings, and extended versions of selected papers will be considered for publication in a special issue of an international journal. WORKSHOP CHAIRS Josef Kittler (Univ. of Surrey, United Kingdom) Fabio Roli (Univ. of Cagliari, Italy) ORGANIZED BY Center for Vision, Speech and Signal Proc. of the University of Surrey and Dept. of Electrical and Electronic Eng. of the University of Cagliari CO-SPONSORED BY International Association for Pattern Recognition PAPER SUBMISSION Three hard copies of the full paper should be mailed to: MCS 2001 Prof. Josef Kittler Center for Vision, Speech and Signal Proc. University of Surrey, Guildford, Surrey GU2 5XH, UK In addition, participants should submit an electronic version of the manuscript (PostScript or PDF format) to mcs2001 at eim.surrey.ac.uk. The papers should not exceed 15 A4 pages (12pt, double-spaced). A cover sheet with the authors names and affiliations is also requested, with the complete address of the corresponding author, and an abstract (200 words). Two members of the Scientific Committee will referee the papers. WORKSHOP TOPICS Papers describing original work in the following and related research topics are welcome: * Foundations of multiple classifier systems * Methods for classifier fusion * Design of multiple classifier systems * Neural network ensembles * Bagging and boosting * Mixtures of experts * New and related approaches (algebraic and discrete mathematical methods, intelligent agents, etc.) * Applications SCIENTIFIC COMMITTEE J. A. Benediktsson (Iceland) H. Bunke (Switzerland) L. P. Cordella (Italy) B. V. Dasarathy (USA) R. P.W. Duin (The Netherlands) C. Furlanello (Italy) J. Ghosh (USA) T. K. Ho (USA) S. Impedovo (Italy) N. Intrator (Israel) A.K. Jain (USA) M. Kamel (Canada) L.I. Kuncheva (UK) D. Landgrebe (USA) D-S. Lee (USA) D. Partridge (UK) C. Scagliola (Italy) A.J.C. Sharkey (UK) S. N. Srihari (USA) C.Y. Suen (Canada) K. Tumer (USA) G. Vernazza (Italy) IMPORTANT DATES February 1, 2001 : Paper Submission March 15, 2001 : Notification of Acceptance April 10, 2001 : Camera-ready Manuscript April 10, 2001 : Registration WORKSHOP VENUE The workshop will be held at Robinson College, Cambridge, UK. WORKSHOP PROCEEDINGS The papers will be published in the workshop proceedings, and extended versions of selected papers will be considered for publication in a special issue of an international journal. ------------------------------------------------------------- Dr. Giorgio Giacinto, Ph.D. Department of Electrical and Electronic Engineering University of Cagliari, Italy e-mail: giorgio.giacinto at computer.org From Patricia_Squadrito at Brown.edu Tue Sep 19 09:07:03 2000 From: Patricia_Squadrito at Brown.edu (Patricia Squadrito) Date: Tue, 19 Sep 2000 09:07:03 -0400 Subject: postdoctoral positions at Brown University Message-ID: BROWN UNIVERSITY. Post-doctoral positions available for cognitive or computational scientist. As part of an NSF award to Brown University through the IGERT program, the Departments of Cognitive and Linguistic Sciences, Computer Science, and Applied Mathematics are hiring research associates. The associates should be scholars who have displayed interest and ability in conducting collaborative interdisciplinary research involving a combination of computational and empirical approaches to one of the content areas of the program: cognition, language, or vision. As well as participating in collaborative research, responsibilities will include helping to coordinate cross-departmental events as well as some graduate teaching. Applicants must hold a PhD in Psychology, Linguistics, Cognitive Science, Computer Science, Mathematics, Applied Mathematics, or a related discipline, or show evidence that the PhD will be completed before the start of the position. Applicants should send a vita, a short research statement, three letters of reference, and other supporting material (e.g., representative publications if available), to IGERT Post-doc Search, Department of Cognitive and Linguistic Sciences, Brown University, Box 1978, Providence, RI 02912. Special consideration will be given to those applicants whose research is relevant to at least two of the participating departments. The positions are open immediately for one year, renewable upon satisfactory completion of duties. Salaries will be between $35,000 and $45,000 per year. All materials must be received by Feb. 1, 2001, for full consideration. Like all NSF-funded programs, this opportunity is available only to American citizens and permanent residents. Brown University is an Equal Opportunity/Affirmative Action Employer. From kap-listman at wkap.nl Tue Sep 19 20:02:41 2000 From: kap-listman at wkap.nl (kap-listman@wkap.nl) Date: Wed, 20 Sep 2000 02:02:41 +0200 (MEST) Subject: New Issue: Neural Processing Letters. Vol. 12, Issue 1 Message-ID: <200009200002.CAA11251@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+1+2000 Vol. 12, Issue 1, August 2000. TITLE: Analysis of the Functional Block Involved in the Design of Radial Basis Function Networks AUTHOR(S): I. Rojas, H. Pomares, J. Gonzales, J. L. Bernier, E. Ros, F. J. Pelayo, A. Prieto KEYWORD(S): RBF neural networks, neural networks design, statistical analysis of RBF, RBF structures. PAGE(S): 1-17 TITLE: Control of a Robotic Manipulator Using Artificial Neural Networks with On-line Adaptation AUTHOR(S): Roselito A. Teixeira, Antonio de P. Braga, Benjamim R. de Menezes KEYWORD(S): Adaptive Learning Rate, ANN application, on-line training, PUMA 560, robotic control. PAGE(S): 19-31 TITLE: Simultaneous Identification of Face and Orientation AUTHOR(S): Pei Ling Lai, Colin Fyfe KEYWORD(S): factor analysis, face identification. PAGE(S): 33-40 TITLE: Out-of-Vocabulary Rejection based on Selective Attention Model AUTHOR(S): Ki-Young Park, Soo-Young Lee KEYWORD(S): error backpropagation, noisy speech, out-of-vocabulary rejection, robust speech recognition, selective attention. PAGE(S): 41-48 TITLE: Coherent Response in a Chaotic Neural Network AUTHOR(S): Haruhiko Nishimura, Naofumi Katada, Kazuyuki Aihara KEYWORD(S): chaos, coherence, noise, nonlinear, recurrent neural network, refractoriness, stochastic resonance. PAGE(S): 49-58 TITLE: Clustered Recursive Branching Network AUTHOR(S): Khalid A. Al-Mashouq KEYWORD(S): recursive branching network, structured perceptrons, data clustering. PAGE(S): 59-69 TITLE: Learning with Permutably Homogeneous Multiple-Valued Multiple-Threshold Perceptrons AUTHOR(S): Alioune Ngom, Corina Reischer, Dan A. Simovici, Ivan Stojmenovic KEYWORD(S): learning, multiple-valued multiple-threshold functions, multilinear separability, partial order set, perceptrons. PAGE(S): 71-90 TITLE: On-line Algorithm for Blind Signal Extraction of Arbitrarily Distributed, but Temporally Correlated Sources Using Second Order Statistics AUTHOR(S): Andrzej Cichocki, Ruck Thawonmas KEYWORD(S): adaptive learning algorithms, blind signal processing, neural networks. PAGE(S): 91-98 -------------------------------------------------------------- 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 axon at cortex.rutgers.edu Tue Sep 19 09:06:40 2000 From: axon at cortex.rutgers.edu (Ralph Siegel) Date: Tue, 19 Sep 2000 09:06:40 -0400 Subject: Postdoctoral position - parietal cortex Message-ID: Postdoctoral Trainee. Analysis of visual structure-from-motion in primates. Representation of optic flow and attention in the inferior parietal lobes (area DP and 7a) are being examined in the awake behaving monkey. These studies utilize ***intrinsic optical recording***, single unit recording, in the behaving monkey. Recent graduates who are changing fields from either cellular or computational neuroscience to behavioral and physiological studies are particularly encouraged to apply. Computer expertise useful, but not necessary. Superb experimental and computational facilities in a multi-disciplinary research center. NY-NJ Metro area. Salary NIH scales plus supplement. Ralph Mitchell Siegel, Ph.D. Associate Professor axon at cortex.rutgers.edu voice: 973-353-1080 x3261 fax: 973-353-1272 Center for Molecular and Behavioral Neuroscience Rutgers, The State University 197 University Avenue Newark, NJ 07102 Graduate program information: http://www.bns.rutgers.edu/ Additional information and reprints: http://www.cmbn.rutgers.edu/~rmsiegel From ken at phy.ucsf.edu Fri Sep 1 01:51:27 2000 From: ken at phy.ucsf.edu (Ken Miller) Date: Thu, 31 Aug 2000 22:51:27 -0700 (PDT) Subject: Paper Available: Spike-Timing-Dependent Synaptic Plasticity Message-ID: <14767.17375.399269.617735@coltrane.ucsf.edu> The following paper is available as ftp://ftp.keck.ucsf.edu/pub/ken/STDP.ps (postscript) ftp://ftp.keck.ucsf.edu/pub/ken/STDP.ps.gz (compressed postscript) or from my home page http://www.keck.ucsf.edu/~ken (click on 'publications') "Competitive Hebbian Learning Through Spike-Timing Dependent Synaptic Plasticity", by Sen Song, Kenneth D. Miller and L. F. Abbott. This is a preprint (final draft) of an article that has appeared as Nature Neuroscience 3:919-926 (2000). ABSTRACT: Hebbian models of development and learning require both activity-dependent synaptic plasticity and a mechanism that induces competition between different synapses. Recent experiments have characterized a form of long-term synaptic plasticity that depends on the relative timing of pre- and postsynaptic action potentials, which we call spike-timing dependent plasticity (STDP). In modeling studies, we find that this form of synaptic modification can automatically balance synaptic strengths to make postsynaptic firing irregular but more sensitive to presynaptic spike timing. It has been argued that neurons in vivo operate in such a balanced regime. Synapses subject to STDP compete for control of the timing of postsynaptic action potentials. Inputs that fire the postsynaptic neuron with short latency or that act in correlated groups are able to compete most successfully and develop strong synapses, while the synapses of longer latency or less effective inputs are weakened. Ken Kenneth D. Miller telephone: (415) 476-8217 Associate Professor fax: (415) 476-4929 Dept. of Physiology, UCSF internet: ken at phy.ucsf.edu 513 Parnassus www: http://www.keck.ucsf.edu/~ken San Francisco, CA 94143-0444 From abrowne at lgu.ac.uk Mon Sep 4 10:10:35 2000 From: abrowne at lgu.ac.uk (Tony Browne) Date: Mon, 4 Sep 2000 15:10:35 +0100 (GMT Daylight Time) Subject: SI on Symbol Processing Message-ID: Special issue of the journal 'Expert Systems: The International Journal of Knowledge Engineering and Neural Networks' on Symbol Processing in Connectionist Systems. Volume 17, No. 1. 2000. ISSN: 0266-4720. Contents: Editorial: Antony Browne. A connectionist production system which can perform both modus ponens and modus tollens simultaneously. Minoru Asogawa. Connectionist symbolic rule encoding using a generalized phase-locking mechanism. Nam Seog Park. Analogy retrieval and processing with distributed vector representations. Tony A. Plate. Fractal encoding of context-free grammars in connectionist networks. Whitney Tabor. http://www.sp.uconn.edu/~ps300vc/papers.html Order from: Marketing Manager, Blackwell Publishers, 108 Cowley Road, Oxford OX4 1JF, UK. ======================================================= Dr. Antony Browne School of Computing, Information Systems & Mathematics London Guildhall University 100 Minories London EC3 1JY, UK Tel: (+44) 0207 320 3106 Fax: (+44) 0207 320 1717 ======================================================= From A.van.Ooyen at nih.knaw.nl Tue Sep 5 10:06:45 2000 From: A.van.Ooyen at nih.knaw.nl (Arjen van Ooyen) Date: Tue, 05 Sep 2000 16:06:45 +0200 Subject: New Paper Message-ID: <39B4FDF4.7581671C@nih.knaw.nl> New Paper: Development of Nerve Connections under the Control of Neurotrophic Factors: Parallels with Consumer-Resource Systems in Population Biology. Arjen van Ooyen & David J. Willshaw, J. Theor. Biol. (2000) 206: 195-210. Download in gzipped PostScript format or PDF format from: http://www.anc.ed.ac.uk/~arjen/competition.html or request reprint: A.van.Ooyen at nih.knaw.nl Abstract -------- We show that a recently formulated model of axonal competition can be rewritten as a general consumer-resource system. This allows neurobiological phenomena to be interpreted in population biological terms and, conversely, results from population biology (where competition is better understood) to be applied to neurobiology. Using findings from population biology, we study two extensions of our axonal competition model. In the first extension, the spatial dimension of the target is explicitly taken into account. We show that distance between axons on their target mitigates competition and permits the coexistence of axons. The model can account for the fact that, in many types of neurons, a positive correlation exists between the size of the dendritic tree and the number of innervating axons surviving into adulthood. In the second extension, axons are allowed to respond to more than one neurotrophic factor. We show that this permits competitive exclusion within one type of axons, while at the same time there is coexistence with a different type of axons innervating the same target. The model offers an explanation for the innervation pattern found on cerebellar Purkinje cells, where climbing fibres compete with each other until only a single one remains, which coexists with parallel fibre input to the same Purkinje cell. -- Arjen van Ooyen, Netherlands Institute for Brain Research, Meibergdreef 33, 1105 AZ Amsterdam, The Netherlands. email: A.van.Ooyen at nih.knaw.nl website: http://www.anc.ed.ac.uk/~arjen phone: +31.20.5665483 fax: +31.20.6961006 From Jean-Pierre.Nadal at lps.ens.fr Tue Sep 5 08:04:38 2000 From: Jean-Pierre.Nadal at lps.ens.fr (Jean-Pierre Nadal) Date: Tue, 5 Sep 2000 14:04:38 +0200 (CEST) Subject: Call for papers DYNN2000 Message-ID: Call for papers --------------- DYNN'2000 INTERNATIONAL WORKSHOP ON "DYNAMICAL NEURAL NETWORKS AND APPLICATIONS" Bielefeld, November 20-24, 2000 http://www.cert.fr/anglais/deri/dauce/DYNN2000 contact: samuelid at supaero.fr OBJECTIVE ---------- Dynamics is a major feature of neural modeling. The study of neural networks viewed as dynamical systems evolving under environmental pressure is an attractive perspective to overcome the limitations of classical artificial neural networks especially in the fields of vision and control. Different disciplines are involved, such as dynamical systems theory, statistical physics, neurobiology, information theory and adaptive control. The DYNN workshop is a place where neurobiologists, theoreticians and engineers can exchange ideas and transfer knowledge. The first international workshop DYNN'96 took place in ONERA in Toulouse, France, and was the occasion to compare theoretical studies and models of visual cortex with more general perceptual devices. The second workshop VI'DYNN'98 in Stockholm focused on Pulse Coupled Neural Networks and was dedicated to more applied tasks of image processing and computervision. The oncoming edition DYNN'2000 keeps all these themes and will introduce new concepts from the physics of "Self-organized Criticality" which describes the spatio-temporal self-organization of coupled automata. DYNN'2000 will take place at the ZIF in Bielefeld University from 11/20/2000 to 11/24/2000 in the frame of the Forschungsgruppe "The Sciences of Complexity: From Mathematics to Technology to a Sustainable World" (http://www.uni-bielefeld.de/ZIF/complexity/complexity.html). Interested researchers are invited to participate to the workshop and to present their contribution. TOPICS ------ Submissions of papers related, but not limited, to the technical areas and subareas listed below are invited. 1.Neural Networks Dynamics and Self Organization. 2.Mean Field Theory for Large Stochastic Networks. 3.Information Properties of Dynamical Neural Networks. 4.Spiking Neurons and Temporal Coding. 5.Applications of Dynamical Neural Networks for Planning and Control 6.Applications of Dynamical Neural Networks to computer vision. ORGANIZATION OF THE WORKSHOP ---------------------------- The workshop is organized during five days and will reserve plenty of time for discussion and interaction among attendants. Special attention will be provided to the formation of young researchers and doctorate students. To fulfill this objective, there will be one day reserved to tutorials and then three types of presentations: * Invited conferences (one hour) will give a large review of the subject and will introduce to ongoing research. They will be designed to allow all the participants coming from different fields to follow all the sessions. * Regular presentations (40 minutes including questions) will be dedicated to present relatively mature work and will be given mostly by invited lecturers. * Short presentations (20 minutes) are specially designed to allow young researchers to present the main ideas of their research project and favor discussion and exchange. Normally short presentations will be associated with posters that allow further interaction between participants. PROGRAM COMMITTEE ------------------ Manuel SAMUELIDES, Chairman - ONERA/ENSAE, Toulouse, France. Manuel.Samuelides at supaero.fr Philippe BLANCHARD - Bielefeld, Germany. blancblanchard at Physik.Uni-Bielefeld.DE Bruno CESSAC - INLN, Nice, France. cessac at inln.cnrs.fr Jacques DEMONGEOT - IUF/CNRS Grenoble, France. Celine.Fontant at imag.fr Philippe GAUSSIER - Cergy-Pontoise, France. gaussier at ensea.fr John JOHNSON - US Army, Germany. science at hq.c5.army.mil Jean-Pierre NADAL - ENS/CNRS, Paris, France. nadal at lps.ens.fr Simon THORPE - CERCO/CNRS, Toulouse, France. thorpe at cerco.ups-tlse.fr John TAYLOR - King's college, London, UK. john.g.taylor at kcl.ac.uk CALENDAR -------- Expression of interest : from now on Extended abstract submission deadline: September 29, 2000 Notification to the authors : October 14, 2000 Early registration : Until october 31, 2000 Date of the workshop : November 20. to 24., 2000 SUBMISSION ---------- The overall submission mode is electronic. Visit our website: http://www.cert.fr/anglais/deri/dauce/DYNN2000 Fill the expression of interest form to be informed about the workshop. The abstracts will be refereed and the accepted papers will be available on the WEB. We are currently investigating the possibility of publishing selected papers in the form of a collective book. Send extended abstract, with respect to format recommandations , 2 pages max, in electronic form (see recommandations on the web site) before September 29th, 2000 to perrinet at cert.fr along with a submission form. -- Manuel SAMUELIDES Professeur a l'ENSAE Ingenieur de recherche a l'ONERA ----------------------------------------------------------------- Answer please to the following email address: samuelid at supaero.fr DYNN2000 website: http://www.cert.fr/anglais/deri/dauce/DYNN2000 ----------------------------------------------------------------- From bert at mbfys.kun.nl Wed Sep 6 05:06:04 2000 From: bert at mbfys.kun.nl (bert@mbfys.kun.nl) Date: Wed, 6 Sep 2000 11:06:04 +0200 Subject: jobs available at SNN Message-ID: <200009060906.LAA03759@anthemius.mbfys.kun.nl> Post doc and research programmer positions available at SNN, University of Nijmegen, the Netherlands. Background: The group consists of 10 researchers and PhD students and conducts theoretical and applied research on neural networks and Bayesian methods. The group is part of the Laboratory of Biophysics which is involved in experimental brain science. Recent research of the group has focused on theoretical description of learning processes using the theory of stochastic processes and the design of efficient learning rules for Boltzmann machines and other graphical models using techniques from statistical mechanics; the extraction of rules from data and the integration of knowledge and data for modeling; the design of robust methods for confidence estimation with neural networks. Applied research is conducted on computer assisted medical diagnosis, music modeling, genetics and time-series prediction tasks. Since 1997, SNN Nijmegen has founded a company which sells commercial services and products in the field of neural networks, AI and statistics. For more information see http://www.smart-research.nl and http://www.mbfys.kun.nl/SNN Job specifications: POST-DOCTORAL FELLOW The tasks of the post-doc will be to conduct independent research in one of the above areas. In addition, it is expected that the post-doc will initiate novel research and will assist in the supervision of PhD students. The postdoc should have a PhD in physics, mathematics or computer science and a strong theoretical background in neural networks. The post-doc salary will be between Dfl. 5589 and Dfl. 7694 per month, depending on experience. The position is available for 2 years with possible extension to 4 years. RESEARCH PROGRAMMER SNN conducts many applied research projects in collaboration with Dutch and foreign industries. Some of these receive public funding, others are funded directly by industry. The aim of these projects is to apply modern neural network or AI methods to concrete industrial problems, rather than the development of novel methodology. Often, the output of the project requires the implementation of the solution in software. Our BayesBuilder and Promedas software are examples of such activities (http://www.mbfys.kun.nl/snn/Research/{promedas,bayesbuilder}. For these activities we seek a research programmer. The research programmer should be familiar with neural networks and/or Bayesian statistics and have a good programming background (C,C++,Java). The research programmer salary will be between Dfl. 4151 and Dfl. 6581 per month, depending on experience. The position is available for 2 years with possible extension to 4 years. Applications: Interested candidates should send a letter with a CV and list of publications before october 1 2000 to dr. H.J. Kappen, Stichting Neurale Netwerken, University of Nijmegen, Geert Grooteplein 21, 6525 EZ Nijmegen. For information contact dr. H.J. Kappen, +31 24 3614241. From mharm at cnbc.cmu.edu Wed Sep 6 10:21:00 2000 From: mharm at cnbc.cmu.edu (Michael Harm) Date: Wed, 6 Sep 2000 10:21:00 -0400 (EDT) Subject: paper available: Are there orthographic impairments in phonological dyslexia? Message-ID: Hi. This is to announce a paper that has been accepted for publication in Cognitive Neuropsychology that may be of interest to some people on this list. Are There Orthographic Impairments in Phonological Dyslexia? Michael W. Harm, CMU Mark S. Seidenberg, USC Abstract: Two hypotheses have been advanced concerning the basis of acquired phonological dyslexia. According to the dual-route model, the pattern derives from impaired grapheme-phoneme conversion. According to the phonological impairment hypothesis, it derived from impaired representation and use of phonology. Effects of graphemic complexity and visual similarity observed in studies by Howard and Best (1996) orthographic effects on phoneme counting (Berndt et al. 1996) and data from patient LB (Derouesne and Beauvois 1985) have been taken as evidence for an orthographic impairment in phonological dyslexia and therefore against the impaired phonology hypothesis (Coltheart 1996). We present a computational simulation, results of two behavioral studies and a critical analysis of the MJ and LB data which suggest that the ``orthographic'' deficits in such patients arise from phonological impairments that interact with orthographic properties of stimuli. A preprint is available at http://www.cnbc.cmu.edu/~mharm/papers/cn2000/cn2000.html Standard copyright notice: The documents distributed here have been provided as a means to ensure timely dissemination of scholarly and technical work on a noncommercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder. (blah blah blah.) Cheers, Mike Harm mharm at cnbc.cmu.edu Center for the Neural Basis of Cognition Carnegie Mellon University http://www.cnbc.cmu.edu/~mharm/ ----------------------------------------- At midnight, all the agents, And the superhuman crew, Come out and round up everyone, That knows more than they do. Bob Dylan, "Desolation Row" From cindy at cns.bu.edu Thu Sep 7 13:04:36 2000 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Thu, 7 Sep 2000 13:04:36 -0400 Subject: Neural Networks 13(6) Message-ID: <200009071704.NAA09759@retina.bu.edu> NEURAL NETWORKS 13(6) Contents - Volume 13, Number 6 - 2000 ------------------------------------------------------------------ NEURAL NETWORKS LETTERS: Neural networks with a continuous squashing function in the output are universal approximators J.L. Castro, C.J. Mantas, and J.M. Benitez Implications of physical symmetries in adaptive image classifiers T. Sams and J.L. Hansen CONTRIBUTED ARTICLES: ***** Neuroscience and Neuropsychology ***** Visual cortical mechanisms of perceptual grouping: Interacting layers, networks, columns, and maps W.D. Ross, S. Grossberg, and E. Mingolla ***** Mathematical and Computational Analysis ***** Blind source separation in the presence of weak sources J.-P. Nadal, E. Korutcheva, and F. Aires Blind signal processing by the adaptive activation function neurons S. Fiori Results concerning the absolute stability of delayed neural networks M. Joy Dynamic topology representing networks J. Si, S. Lin, and M.-A. Vuong Consistency of posterior distributions for neural networks H.K.H. Lee III On the exact solution of the parity-N problem using ordered neural networks E. Lavretsky Approximation of continuous and discontinuous mappings by a growing neural RBF-based algorithm A. Esposito, M. Marinaro, D. Oricchio, and S. Scarpetta ***** Engineering and Design ***** Stable behavior in a recurrent neural network for a finite state machine K. Arai and R. Nakano ***** Technology and Applications ***** A neural network for 500 word vocabulary word spotting using non-uniform units H.-J. Yu ***** Letter to the Editor ***** Ionic current and metabolism for brain scanners (A three state model of modular activation) J.F. Gomez ------------------------------------------------------------------ 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 mike at deathstar.psych.ualberta.ca Thu Sep 7 10:44:41 2000 From: mike at deathstar.psych.ualberta.ca (Michael R.W. Dawson) Date: Thu, 7 Sep 2000 08:44:41 -0600 (MDT) Subject: Positions at U. of Alberta Message-ID: DEPARTMENT OF PSYCHOLOGY, UNIVERSITY OF ALBERTA Four Positions in Brain, Behaviour, and Cognitive Science The Department of Psychology, Faculty of Science at the University of Alberta is seeking to expand its development in Behavioural and Cognitive Neurosciences, which is one of the specializations in the Department's general area of Brain, Behaviour, and Cognitive Science. An open-rank position in Behavioural and Cognitive Neurosciences will be open to competition. The appointment is effective July 1, 2001. Candidates should have a demonstrated excellence in the study of the neural basis of behaviour or cognitive processes as applied to perception, neural plasticity, learning, memory, language, development and aging, attention, motor control, or emotion. The expectation is that the successful candidate will have some postdoctoral experience and will be able to secure NSERC, MRC, or equivalent funding. The Department of Psychology, Faculty of Science at the University of Alberta is seeking to expand its development in Comparative Cognition, which is one of the specializations in the Department's general area of Brain, Behaviour, and Cognitive Science. A tenure-track position in Comparative Cognition at the level of assistant professor will be open to competition. The appointment will be effective July 1, 2001. Candidates should have a strong research record in animal learning or comparative cognition and teaching interests that include both introductory and advanced courses in learning and comparative cognition. Comparative cognition is broadly defined to include studies of processes such as perception, learning, memory and navigation in vertebrates or invertebrates. We particularly encourage applications from candidates with expertise or interest in neural mechanisms underlying learning and cognition, connectionist modeling, or behaviour genetics. The expectation is that the successful candidate will have some postdoctoral experience and will be able to secure NSERC, MRC, or equivalent funding. The Department of Psychology, Faculty of Science at the University of Alberta is seeking to expand its development in the area of Real-World Cognition, which is one of the specializations in the Department’s general area of Brain, Behaviour, and Cognitive Science. A tenure-track position in real-world cognition at the assistant professor level will be open to competition and will be effective July 1, 2001. We invite applications from individuals in any area of real-world cognition, but we are especially interested in a person whose main interest is in human judgment and decision making/risk assessment. Researchers with interest in human factors in human-computer interaction/knowledge engineering, cognitive aspects of survey methodology, autobiographical memory, or applied discourse processing would also be considered for this position. The expectation is that the successful candidate will secure NSERC, MRC, SSHRC, or equivalent funding. The Department of Psychology, Faculty of Science at the University of Alberta is seeking to expand its development in Synthetic Psychology, which is one of the specializations in the Department's general area of Brain, Behaviour, and Cognitive Science. A tenure-track position in Synthetic Psychology at the assistant professor level will be open to competition. The appointment will be effective July 1, 2001. Candidates should have a strong interest in psychologically relevant and/or biologically inspired computer simulation methods with demonstrated excellence and ongoing research programs. Examples of such research would include computational neuroscience, artificial neural networks, evolutionary computation, nonlinear models and/or selectionistism to study any of the following or related areas: perception, learning, language, neural plasticity, development and aging, attention, motor control, emotion, or memory. Researchers with general interests in situated and/or embodied cognition would also be considered for this position. The expectation is that the successful candidate will secure NSERC, MRC, or equivalent funding. Hiring decisions will be made on the basis of demonstrated research capability, teaching ability, and the potential for interactions with colleagues. In particular an ability to interact with the other specializations in Brain, Behaviour, and Cognitive Science in our department would be an asset. Further information on this position can be obtained from http://www.psych.ualberta.ca/hiring. Applicants should send a curriculum vitae, a statement of current and future research plans, a description of teaching interests, recent publications, and arrange to have at least three letters of reference forwarded to: Dr Douglas S Grant, Chair, Department of Psychology, P220 Biological Sciences Building, University of Alberta, Edmonton, Alberta, Canada, T6G 2E9. Applications for the competition should be received by November 1, 2000. The records arising from this competition will be managed in accordance with provisions of the Alberta Freedom of Information and Protection of Privacy Act (FOIPP). In accordance with Canadian Immigration requirements, this advertisement is directed to Canadian citizens and permanent residents. If a suitable Canadian citizen or permanent resident cannot be found, other individuals will be considered. The University of Alberta is committed to the principle of equity of employment. As an employer we welcome diversity in the workplace and encourage applications from all qualified women and men, including Aboriginal peoples, persons with disabilities and members of visible minorities. From derprize at cnbc.cmu.edu Thu Sep 7 15:26:14 2000 From: derprize at cnbc.cmu.edu (David E Rumelhart Prize) Date: Thu, 07 Sep 2000 15:26:14 -0400 Subject: THE RUMELHART PRIZE Announcement and Call for Nominations Message-ID: <39B7EBD6.1C5A8D4A@cnbc.cmu.edu> ANNOUNCEMENT AND CALL FOR NOMINATIONS THE DAVID E. RUMELHART PRIZE FOR CONTRIBUTIONS TO THE FORMAL ANALYSIS OF HUMAN COGNITION The David E. Rumelhart Prize will be awarded biennially to an individual or collaborative team making a significant contemporary contribution to the formal analysis of human cognition. Mathematical modeling of human cognitive processes, formal analysis of language and other products of human cognitive activity, and computational analyses of human cognition using symbolic or non-symbolic frameworks all fall within the scope of the award. The Prize itself will consist of a certificate, a citation of the awardee's contribution, and a monetary award of $100,000. Nomination, Selection and Award Presentation Nominations for the David E. Rumelhart Prize should be sent to the Chair of the Prize Selection Committee by December 1 of each even numbered year, beginning in the year 2000. Nominations should include six sets of the following materials: (1) A three-page statement focusing on the work motivating the nomination, (2) a complete curriculum vitae and (3) copies of up to five of the nominee's relevant publications. Note that the nominee may be an individual or a team, and in the case of a team, vitae for all members should be provided. The awardee will be announced at the meeting of the Cognitive Science Society in the year following the deadline and will receive the Prize and deliver the Prize Lecture at the meeting in the year after that. Thus, the first prize recipient will be announced at the Meeting of the Cognitive Science Society in 2001, and the first Prize Lecture will be given at the meeting of the Society in 2002. Funding of the Prize The David E, Rumelhart Prize will be funded by the Robert J. Glushko and Pamela Samuelson Foundation, based in San Francisco. Robert J. Glushko is an entrepreneur in Silicon Valley who received a Ph. D. in Cognitive Psychology in 1979 under Rumelhart's supervision. Prize Administration The Rumelhart Prize will be Administered by the Chair of the Prize Selection Committee in consultation with the Glushko-Samuelson Foundation and the Distinguished Advisory Board. Screening of nominees and selection of the prize winner will be performed by the Prize Selection Committee. Scientific members (including the Chair) of the Prize Selection Committee will serve for up to two four-year terms, and members of this committee will be selected by the Glushko-Samuelson Foundation in consultation with the Distinguished Advisory Board. A representative of the Foundation will also serve on the Prize Selection Committee. David E. Rumelhart: A Scientific Biography David E. Rumelhart has made many contributions to the formal analysis of human cognition, working primarily within the frameworks of mathematical psychology, symbolic artificial intelligence, and parallel distributed processing. He also admired formal linguistic approaches to cognition and explored the possibility of formulating a formal grammar to capture the structure of stories. Rumelhart obtained his undergraduate education at the University of South Dakota, receiving a B.A. in psychology and mathematics in 1963. He studied mathematical psychology at Stanford University, receiving his Ph. D. in 1967. From 1967 to 1987 he served on the faculty of the Department of Psychology at the University of California, San Diego. In 1987 he moved to Stanford University, serving as Professor there until 1998. He has become disabled by Pick's disease, a progressive neurodegenerative illness, and now lives with his brother in Ann Arbor, Michigan. Rumelhart developed models of a wide range of aspects of human cognition, ranging from motor control to story understanding to visual letter recognition to metaphor and analogy. He collaborated with Don Norman and the LNR Research Group to produce "Explorations in Cognition" in 1975 and with Jay McClelland and the PDP Research Group to produce "Parallel Distributed Processing: Explorations in the Microstructure of Cognition" in 1986. He mastered many formal approaches to human cognition, developing his own list processing language and formulating the powerful back-propagation learning algorithm for training networks of neuron-like processing units. Rumelhart was elected to the National Academy of Sciences in 1991 and received many prizes, including a MacArthur Fellowship, the Warren Medal of the Society of Experimental Psychologists, and the APA Distinguished Scientific Contribution Award. Rumelhart articulated a clear view of what cognitive science, the discipline, is or ought to be. He felt that for cognitive science to be a science, it would have to have formal theories --- and he often pointed to linguistic theories, as well as to mathematical and computational models, as examples of what he had in mind. Distinguished Advisory Board William K. Estes Indiana University Bloomington, Indiana Barbara H. Partee University of Massachusetts Amherst, Massachusetts Herbert A. Simon Carnegie Mellon University Pittsburgh, Pennsylvania Chair, Prize Selection Committee James L. McClelland Carnegie Mellon University and Center for the Neural Basis of Cognition Pittsburgh, Pennsylvania Inquiries and Nominations should be sent to David E. Rumelhart Prize Administration Center for the Neural Basis of Cognition 115 Mellon Institute 4400 Fifth Avenue Pittsburgh, PA 15213 412-268-4000 derprize at cnbc.cmu.edu Visit the prize web site at www.cnbc.cmu.edu/derprize From abrowne at lgu.ac.uk Fri Sep 8 06:58:17 2000 From: abrowne at lgu.ac.uk (Tony Browne) Date: Fri, 8 Sep 2000 11:58:17 +0100 (GMT Daylight Time) Subject: Postdoc in UK Message-ID: A postdoctoral research associate post is available for a project using neural networks for Biological and Chemical Data analysis. The research associate will be based in the Centre for Molecular Design at Portsmouth University, UK, for a 2.5 year period. Starting salary will be in the range of seventeen to eighteen thousand UK pounds (with annual increments). This post requires a graduate with a PhD in Computer Science, Cognitive Science, Mathematics or a related subject, or a graduate with a PhD in Life Sciences with a thorough understanding of Bioinformatics and strong mathematical and programming skills. The successful candidate should posses knowledge in the following areas: Experience of developing neural networks in high-level programming languages. Strong Mathematical and Statistical Skills. An awareness of current developments in Bioinformatics/Cheminformatics. CV's (in text format) should be e-mailed to martyn.ford at port.ac.uk, or forwarded to Professor Martyn Ford, University of Portsmouth, Centre for Molecular Design, School of Biological Sciences, King Henry Building, King Henry 1 Street, Portsmouth PO1 2DY, UK. Tel: (+44) 0239 843 020. ======================================================= Dr. Antony Browne School of Computing, Information Systems & Mathematics London Guildhall University 100 Minories London EC3 1JY, UK Tel: (+44) 0207 320 3106 Fax: (+44) 0207 320 1717 ======================================================= From kempter at phy.ucsf.edu Fri Sep 8 12:49:42 2000 From: kempter at phy.ucsf.edu (Richard Kempter) Date: Fri, 8 Sep 2000 09:49:42 -0700 Subject: Preprint available: Intrinsic Stabilization of Output Rates by Spike-Based Hebbian Learning Message-ID: <20000908094942.A26311@popper.ucsf.edu> Dear connectionists, to all of you who have been interested in the nice paper on Spike-Time Dependent Plasticity by Song, Miller, and Abbott, that Ken Miller announced on this mailing list a couple of days ago, we would like to give a pointer to our preprint on a related topic. Intrinsic Stabilization of Output Rates by Spike-Based Hebbian Learning (Kempter, Gerstner, van Hemmen) http://keck.ucsf.edu/~kempter/Publications/index.html Abstract: We study analytically a model of synaptic plasticity where synaptic changes are triggered by presynaptic spikes, postsynaptic spikes, and the time-differences between pre- and postsynaptic spikes. We show that plasticity can lead to an intrinsic stabilization of the mean firing rate of the postsynaptic neuron. Subtractive normalization of the synaptic weights (summed over all presynaptic inputs converging on a postsynaptic neuron) follows if, in addition, the mean input rates and the mean input correlations are identical at all synapses. If the integral over the learning window is positive, firing rate stabilization requires a non-Hebbian component, while such a component is not necessary, if the integral over the learning window is negative. A negative integral corresponds to `anti-Hebbian' learning in a model with slowly varying firing rates. For spike-based learning, a strict distinction between Hebbian and `anti-Hebbian' rules is questionable, since learning is driven by correlations on the time scale of the learning window. The correlations between presynaptic and postsynaptic firing are evaluated for a piecewise linear Poisson model and for a noisy spiking neuron model with refractoriness. While a negative integral over the learning window leads to intrinsic rate stabilization, the positive part of the learning window picks up spatial and temporal correlations in the input. Richard Kempter and Wulfram Gerstner From terry at salk.edu Fri Sep 8 20:52:52 2000 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 8 Sep 2000 17:52:52 -0700 (PDT) Subject: NEURAL COMPUTATION 12:9 Message-ID: <200009090052.e890qq330478@dax.salk.edu> Neural Computation - Contents - Volume 12, Number 9 - September 1, 2000 ARTICLE DEA: An Architecture for Goal Planning and Classification Francois Fleuret and Eric Brunet NOTE On A Fast, Compact Approximation of the Exponential Function Gavin C. Cawley LETTERS Bounds On Error Expectation for Support Vector Machines V. Vapnik and O. Chapelle A Computational Model of Lateralization and Asymmetries in Cortical Maps Svetlana Levitan and James A. Reggia Rate Limitations of Unitary Event Analysis A. Roy, P. N. Steinmetz, and E. Niebur Estimating Functions of Independent Component Analysis for Temporally Correlated Signals Shun-ichi Amari SMEM Algorithm for Mixture Models Naonori Ueda, Ryohei Nakano, Zoubin Ghahramani, and Geoffrey E. Hinton Stable Encoding of Finite-State Machines in Discrete-Time Recurrent Neural Nets with Sigmoid Units Rafael C. Carrasco, Mikel L. Forcada, M. Angeles Valdes-Munoz, and Ramon P. Neco Approximate Maximum Entropy Joint Feature Inference Consistent with Arbitrary Lower Order Probability Constraints: Application to Statistical Classification David J. Miller and Lian Yan Lambda-opt Neural Approaches to Quadratic Assignment Problem Shin Ishii and Hirotaka Niitsuma ----- 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 vera at cs.cas.cz Wed Sep 13 16:28:40 2000 From: vera at cs.cas.cz (Vera Kurkova) Date: Wed, 13 Sep 00 16:28:40 CET Subject: soft deadline of ICANNGA 2001 Message-ID: <59321.vera@uivt1.uivt.cas.cz> Not wanting to omit fuzzy logic, we have softened our deadline. Submission of papers to: 5th INTERNATIONAL CONFERENCE ON ARTIFICIAL NEURAL NETWORKS AND GENETIC ALGORITHMS *** ICANNNGA 2001 *** is postponed to 1st October, 20000 For details on submission please see http://www.cs.cas.cz/icannga See you in Prague, April 21-24, 2001 Vera Kurkova, Chair of the Program Committee of ICANNGA 2001 From becker at curie.psychology.mcmaster.ca Wed Sep 13 14:44:40 2000 From: becker at curie.psychology.mcmaster.ca (Sue Becker) Date: Wed, 13 Sep 2000 14:44:40 -0400 (EDT) Subject: POSTDOC AND POSTGRAD POSITIONS IN NEURO-SIGNAL PROCESSING Message-ID: POST-DOCTORAL and POST-GRADUATE POSITIONS in NEURO-SIGNAL PROCESSING Funding for two post-doctoral positions and at least two PhD students is available to develop and test intelligent hearing aid technology. A group of researchers at McMaster University recently received funding from NSERC, Canada for this exciting project which is being conducted in collaboration with Gennum Corporation, one of the world's largest hearing aid manufacturers. The research team, headed by Prof. Simon Haykin in Electrical Engeering, also includes Professors Sue Becker, Ron Racine, John Platt and Laurel Trainor in the Psychology Department. The team's expertise spans neural modelling, signal processing, neurophysiology, neural plasticity, and auditory processing. Preference will be given to applicants with expertise in neurobiological modelling of the auditory system or adaptive filter design or a related field. Excellent computer programming skills are essential. Students joining the team could obtain a graduate degree in either Electrical Engineering or Psychology, and would enroll in September, 2000 or as soon as possible thereafter. Postdocs could start immediately. Please send applications, with two references, to: Prof. Simon Haykin Communications Research Laboratory McMaster Univeristy Hamilton, Ontario, Canada L8S 4K1 haykin at mcmaster.ca From harnad at coglit.ecs.soton.ac.uk Wed Sep 13 06:59:16 2000 From: harnad at coglit.ecs.soton.ac.uk (Stevan Harnad) Date: Wed, 13 Sep 2000 11:59:16 +0100 (BST) Subject: THE WORK OF ROGER SHEPARD: 7 special BBS Calls for Commentators Message-ID: Below are the abstracts of 7 forthcoming target articles to co-appear in a BBS Special Issue on: THE WORK OF ROGER SHEPARD Commentators may comment on one, several, or all 7 target articles. (1) Shepard: Perceptual-Cognitive Universals as Reflections of the World (reprinted from Psychonomic Bulletin & Review, 1994, 1, 2-28) http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.shepard.html (2) Barlow: The Exploitation of Regularities in the Environment by the Brain http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.barlow.html (3) Hecht: Regularities of the Physical World and the Absence of their Internalization http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.hecht.html (4) Kubovy: Internalization: A metaphor we can live without http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.kubovy.pdf (5) Schwartz: Evolutionary Internalized Regularities http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.schwartz.html (6) Tenenbaum & Griffiths: Generalization, Similarity, and Bayesian Inference http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.tenenbaum.html (7) Todorovic: Is kinematic geometry an internalized regularity? http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.todorovic.html These 7 articles have been accepted for joint publication in a special issue on the work of ROGER SHEPARD in Behavioral and Brain Sciences (BBS), an international, interdisciplinary journal providing Open Peer Commentary on important and controversial current research in the biobehavioral and cognitive sciences. To be considered as a commentator for this article, to recommend other appropriate commentators, or for information about how to become a BBS Associate, please reply by EMAIL by September 8th to the address below: bbs at soton.ac.uk Commentators must either be current BBS Associates or they must be nominated by a current BBS Associate (of which there are currently 10,000). Non-Associates should send a CV and/or the name of a current BBS Associate familiar with their work. To help us put together a balanced list of commentators, in your reply please indicate the aspects of the topic on which you would bring your areas of expertise to bear if you were selected as a commentator. Electronic drafts of the full texts of all 7 articles are available for inspection from the Web. Commentators may comment on one, several, or all 7 target articles. Commentary length is 1000 words for a commentary on one target article, to a maximum of 4000 words for a commentary on all 7 (an extra 500 words are allowed for each additional target article). Please indicate which article(s) you propose to comment upon. ____________________________________________________________ 1. SHEPARD, ROGER (2001) PERCEPTUAL-COGNITIVE UNIVERSALS AS REFLECTIONS OF THE WORLD Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.shepard.html Roger N. Shepard Stanford University Stanford, California roger at psych.stanford.edu ABSTRACT: The universality, invariance, and elegance of principles governing the universe may be reflected in principles of the minds that have evolved in that universe--provided that the mental principles are formulated with respect to the abstract spaces appropriate for the representation of biologically significant objects and their properties. (1) Positions and motions of objects conserve their shapes in the geometrically fullest and simplest way when represented as points and connecting geodesic paths in the six-dimensional manifold jointly determined by the Euclidean group of three-dimensional space and the symmetry group of each object. (2) Colors of objects attain constancy when represented as points in a three-dimensional vector space in which each variation in natural illumination is cancelled by application of its inverse from the three-dimensional linear group of terrestrial transformations of the invariant solar source. (3) Kinds of objects support optimal generalization and categorization when represented, in an evolutionarily shaped space of possible objects, as connected regions with associated weights determined by Bayesian revision of maximum-entropy priors. ____________________________________________________________ 2. BARLOW, HORACE (2001) THE EXPLOITATION OF REGULARITIES IN THE ENVIRONMENT BY THE BRAIN Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.barlow.html Horace Barlow Physiological Laboratory Cambridge CB2 3EG England hbb10 at cam.ac.uk KEYWORDS: Chasles' rule, evolution, geometry, perception, redundancy, statistics, twisting. ABSTRACT: Statistical regularities of the environment are important for learning, memory, intelligence, inductive inference, and in fact for any area of cognitive science where an information-processing brain promotes survival by exploiting them. This has been recognised by many of those interested in cognitive function, starting with Helmholtz, Mach and Pearson, and continuing through Craik, Tolman, Attneave, and Brunswik. In the current era many of us have begun to show how neural mechanisms exploit the regular statistical properties of natural images. Shepard proposed that the apparent trajectory of an object when seen successively at two positions results from internalising the rules of kinematic geometry, and although kinematic geometry is not statistical in nature, this is clearly a related idea. Here it is argued that Shepard's term, "internalisation", is insufficient because it is also necessary to derive an advantage from the process. Having mechanisms selectively sensitive to the spatio-temporal patterns of excitation commonly experienced when viewing moving objects would facilitate the detection, interpolation, and extrapolation of such motions, and might explain the twisting motions that are experienced. Although Shepard's explanation in terms of Chasles' rule seems doubtful, his theory and experiments illustrate that local twisting motions are needed for the analysis of moving objects and provoke thoughts about how they might be detected. ____________________________________________________________ 3. HECHT, HEIKO (2001) REGULARITIES OF THE PHYSICAL WORLD AND THE ABSENCE OF THEIR INTERNALIZATION Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.hecht.html Heiko Hecht Man-Vehicle Lab Massachusetts Institute of Technology Mass Ave., Bldg. 37-219, Cambridge, MA 02139 hecht at mit.edu KEYWORDS: Internalization, Evolution, Event Perception ABSTRACT: The notion of internalization put forth by Roger Shepard continues to be appealing and challenging. He suggests that we have internalized, during our evolutionary development, environmental regularities or constraints. Internalization solves one of the hardest problems of perceptual psychology: the underspecification problem. That is the problem of how well-defined perceptual experience is generated from the often ambiguous and incomplete sensory stimulation. Yet, the notion of internalization creates new problems that may outweigh the solution of the underspecification problem. To show this, I first examine the concept of internalization and find it necessary to break it down into several distinct interpretations. These range from well-resolved dynamic regularities to ill-resolved statistical regularities. As a function of the interpretation the researcher selects, an empirical test of the internalization hypothesis may be straight forward or it may become virtually impossible. I then attempt to cover the range of interpretations by drawing on examples from different domains of visual event perception. Unfortunately, the experimental tests regarding most candidate regularities, such as gravitational acceleration, fail to support the concept of internalization. This suggests that narrow interpretations of the concept should be given up in favor of more abstract interpretations. However, the latter are are not easily amenable to empirical testing. There is nonetheless a way to test by contrasting internalization with the opposite concept: externalization of body dynamics. I summarize evidence for such a projection of body constraints onto external objects. Based on the combined evidence of well-resolved and ill-resolved regularities, the value of the notion of internalization has to be reassessed. ____________________________________________________________ 4. KUBOVY, MICHAEL (2001) INTERNALIZATION: A METAPHOR WE CAN LIVE WITHOUT Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.kubovy.pdf Michael Kubovy The University of Virginia KEYWORDS: computational approach, cognitive constructivism, constraints, ecological approach, environmental regularities, evolution, homomorphism, illusory motion, internality, internalization, inverse projec-tion problem, kinematic geometry, mental rotation, metaphors of mind, perception of motion, perceptual universals. ABSTRACT: Shepard has supposed that the mind is stocked with innate knowledge of the world and that this knowledge figures prominently in the way we see the world. According to him, this in-ternal knowledge is the legacy of a process of internalization; a process of natural selection over the evolutionary history of the species. Shepard has developed his proposal most fully in his analysis of the relation between kinematic geometry and the shape of the motion path in apparent motion displays. We argue that Shepard has made a case for applying the principles of kinematic geometry to the perception of motion, but that he has not made the case for in-jecting these principles into the mind of the percipient. We offer a more modest interpretation of his important findings: that kinematic geometry may be a model of apparent motion. Inas-much as our recommended interpretation does not lodge geometry in the mind of the percipient the motivation for positing internalization, a process that moves kinematic geometry into the mind, is obviated. In our conclusion we suggest that cognitive psychologists, in their embrace of internal mental universals and internalization may have been seduced by the siren call of metaphor. ____________________________________________________________ 5. SCHWARTZ, ROBERT (2001) EVOLUTIONARY INTERNALIZED REGULARITIES Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.schwartz.html Robert Schwartz Department of Philosophy University of Wisconsin - Milwaukee Milwaukee, WI 53201 U.S.A. schwartz at uwm.edu KEYWORDS: apparent motion, circadian rhythms, constraints, ecoclogical validity, evolution, internalized regularities, kinematic principle. ABSTRACT: Roger Shepard's proposals and supporting experiments concerning evolutionary internalized regularities have been very influential in the study of vision and in other areas of psychology and cognitive science. This paper examines issues concerning the need, nature, explanatory role, and justification for postulating such internalized constraints. In particular, I seek further clarification from Shepard on how best to understand his claim that principles of kinematic geometry underlie phenomena of motion perception. My primary focus is on the ecological validity of Shepard's kinematic constraint in the context of ordinary motion perception. First, I explore the analogy Shepard draws between internalized circadian rhythms and the supposed internalization of kinematic geometry. Next, questions are raised about how to interpret and justify applying results from his own and others experimental studies of apparent motion to more everyday cases of motion perception in richer environments. Finally, some difficulties with Shepard's account of the evolutionary development of his kinematic constraint are considered. ____________________________________________________________ 6. TENENBAUM, JOSHUA B. & GRIFFITHS, THOMAS L. (2001) GENERALIZATION, SIMILARITY, AND BAYESIAN INFERENCE Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.tenenbaum.html Joshua B. Tenenbaum & Thomas L. Griffiths Department of Psychology Jordan Hall, Building 420 Stanford University Stanford, CA 94305-2130 jbt at psych.stanford.edu KEYWORDS: Additive clustering, Bayesian inference, categorization, concept learning, contrast model, features, generalization, psychological space, similarity. ABSTRACT: Shepard has argued that a universal law should govern generalization across different domains of perception and cognition, as well as across organisms from different species or even different planets. Starting with some basic assumptions about natural kinds, he derived an exponential decay function as the form of the universal generalization gradient, which accords strikingly well with a wide range of empirical data. However, his original formulation applied only to the ideal case of generalization from a single encountered stimulus to a single novel stimulus, and for stimuli that can be represented as points in a continuous metric psychological space. Here we recast Shepard's theory in a more general Bayesian framework and show how this naturally extends his approach to the more realistic situation of generalizing from multiple consequential stimuli with arbitrary representational structure. Our framework also subsumes a version of Tversky's set-theoretic models of similarity, which is conventionally thought of as the primary alternative to Shepard's continuous metric space model of similarity and generalization. This unification allows us not only to draw deep parallels between the set-theoretic and spatial approaches, but also to significantly advance the explanatory power of set-theoretic models. ____________________________________________________________ 7. TODOROVIC, DEJAN (2001) IS KINEMATIC GEOMETRY AN INTERNALIZED REGULARITY? Behavioral and Brain Sciences 24 (2): XXX-XXX. URL: http://www.cogsci.soton.ac.uk/bbs/Archive/bbs.todorovic.html Dejan Todorovic Department of Psychology, University of Belgrade, Serbia, Yugoslavia dejan at arvotek.net dtodorov at dekart.f.bg.ac.yu KEYWORDS: internalization of regularities, kinematic geometry, simplicity ABSTRACT: A general framework for the explanation of perceptual phenomena as internalizations of external regularities was developed by R.N. Shepard. A particular example of this framework is his account of perceived curvilinear apparent motions. This paper contains a brief summary of the relevant psychophysical data, some basic kinematical considerations and examples, and several criticisms of Shepard's account. The criticisms concern the feasibility of internalization of critical motion types, the roles of simplicity and uniqueness, the contrast between classical physics and kinematic geometry, the import of perceived path curvilinearity, and the relation of perceptual and scientific knowledge. ____________________________________________________________ ____________________________________________________________ To help you decide whether you would be an appropriate commentator for these articles, electronic drafts are retrievable from the World Wide Web from the US or UK BBS Archive. Please do not prepare a commentary yet. Just let us know, after having inspected it, what relevant expertise you feel you would bring to bear on what aspect of which article(s). We will then let you know whether it was posible to include your name on the final formal list of invitees. The URLs you can use to get to the BBS Archive: http://www.cogsci.soton.ac.uk/bbs/Archive/ ____________________________________________________________ *** FIVE SUPPLEMENTARY ANNOUNCEMENTS *** ------------------------------------------------------------------ (1) There have been some very important developments in the area of Web archiving of scientific papers very recently. Please see: Science: http://www.cogsci.soton.ac.uk/~harnad/science.html Nature: http://www.cogsci.soton.ac.uk/~harnad/nature.html Am. Sci.: http://www.cogsci.soton.ac.uk/~harnad/amlet.html --------------------------------------------------------------------- (2) All authors in the biobehavioral and cognitive sciences are strongly encouraged to archive all their papers (on their Home-Servers as well as) on CogPrints: http://cogprints.soton.ac.uk/ It is extremely simple to do so and will make all of our papers available to all of us everywhere at no cost to anyone. See: http://vole.lanl.gov/ups/ups.htm http://xxx.lanl.gov/cgi-bin/show_monthly_submissions --------------------------------------------------------------------- (3) BBS has a new policy of accepting submissions electronically. Authors can specify whether they would like their submissions archived publicly during refereeing in the BBS under-refereeing Archive, or in a referees-only, non-public archive. Upon acceptance, preprints of final drafts are moved to the public BBS Archive: http://www.cogsci.soton.ac.uk/bbs/Archive/ -------------------------------------------------------------------- (4) BBS has expanded its annual page quota and is now appearing bimonthly, so the service of Open Peer Commentary can now be be offered to more target articles. The BBS refereeing procedure is also going to be considerably faster with the new electronic submission and processing procedures. Authors are invited to submit papers to: Email: bbs at cogsci.soton.ac.uk Web: http://cogprints.soton.ac.uk http://bbs.cogsci.soton.ac.uk/ INSTRUCTIONS FOR AUTHORS: http://www.cogsci.soton.ac.uk/bbs/instructions.for.authors.html --------------------------------------------------------------------- (5) Call for Book Nominations for BBS Multiple Book Review In the past, Behavioral and Brain Sciences (BBS) journal had only been able to do 1-2 BBS multiple book treatments per year, because of our limited annual page quota. BBS's new expanded page quota will make it possible for us to increase the number of books we treat per year, so this is an excellent time for BBS Associates and biobehavioral/cognitive scientists in general to nominate books you would like to see accorded BBS multiple book review. (Authors may self-nominate, but books can only be selected on the basis of multiple nominations.) It would be very helpful if you indicated in what way a BBS Multiple Book Review of the book(s) you nominate would be useful to the field (and of course a rich list of potential reviewers would be the best evidence of its potential impact!). From cindy at cns.bu.edu Thu Sep 14 16:04:20 2000 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Thu, 14 Sep 2000 16:04:20 -0400 Subject: Neural Networks: 2001 Special Issue Message-ID: <200009142004.QAA27939@retina.bu.edu> CALL FOR PAPERS A 2001 Special Issue of Neural Networks SPIKING NEURONS IN NEUROSCIENCE AND TECHNOLOGY Most neurons of the brain communicate using trains of brief voltage spikes that are capable of carrying complex temporal and rate codes without degradation over large spatial distances. The rates, patterns or oscillations of single spike trains as well as correlations and synchrony across different spike trains, have been studied by many investigators in both normal and clinically abnormal brain tissues. The Special Issue will incorporate invited and contributed articles that examine the importance of spiking in information processing, learning and memory. The Special Issue will cover biophysical and biochemical models of spike generation, neurophysiological and anatomical models that explore how spiking neurons influence behavior through their collective action in neural circuits and networks, as well as learning algorithms that are based on spikes. The computational power of spiking neurons for reliable communication can also be incorporated into various technologies. The Special Issue will therefore also include articles that describe software and hardware applications that are based on this mode of neuronal communication to explore its potential for solving outstanding open problems in technology. CO-EDITORS: Professor Stephen Grossberg, Boston University Professor Wolfgang Maass, Technische Universitat Graz Professor Henry Markram, Weizmann Institute for Science SUBMISSION: Deadline for submission: September 30, 2000 Notification of acceptance: December 31, 2000 Format: no longer than 10,000 words; APA format ADDRESS FOR SUBMISSION: Stephen Grossberg, Editor Neural Networks, Room 203 Department of Cognitive and Neural Systems Boston University 677 Beacon Street Boston, Massachusetts 02215 USA From paolo at eealab.unian.it Fri Sep 15 13:42:22 2000 From: paolo at eealab.unian.it (Paolo Campolucci) Date: Fri, 15 Sep 2000 19:42:22 +0200 (CEST) Subject: 2 new papers on circuit theory, digital signal processing and recurrent neural networks Message-ID: Dear Colleagues, We would like to announce the availability of two new papers of potential interest to people working on circuit theory, digital signal processing and recurrent neural networks at http://nnsp.eealab.unian.it/Campolucci_P Sincerely, Paolo "A Signal-Flow-Graph Approach to On-line Gradient Calculation" By Paolo Campolucci, Aurelio Uncini, Francesco Piazza Neural Computation, vol. 12, nr. 8, August 2000 ABSTRACT A large class of non-linear dynamic adaptive systems such as dynamic recurrent neural networks can be very effectively represented by Signal-Flow-Graphs (SFGs). By this method, complex systems are described as a general connection of many simple components, each of them implementing a simple one-input one-output transformation, as in an electrical circuit. Even if graph representations are popular in the neural network community, they are often used for qualitative description rather than for rigorous representation and computational purposes. In this paper, a method for both on-line and batch backward gradient computation of a system output or cost function with respect to system parameters is derived by the Signal-Flow-Graph representation theory and its known properties. The system can be any causal, in general non-linear and time-variant, dynamic system represented by a SFG, in particular any feedforward, time delay or recurrent neural network. In this work, we use discrete time notation, but the same theory holds for the continuous time case. The gradient is obtained in a straightforward way by the analysis of two SFGs, the original one and its adjoint (obtained from the first by simple transformations) without the complex chain rule expansions of derivatives usually employed. This method can be used for sensitivity analysis and for learning both off-line and on-line. On-line learning is particularly important since it is required by many real applications such as Digital Signal Processing, system identification and control, channel equalization and predistortion. ****************************************************************** "Intrinsic Stability Control Method for Recursive Filters and Neural Networks" By Paolo Campolucci and Francesco Piazza IEEE Transactions on Circuits and Systems, part II: Analog and digital signal processing, vol. 47, nr. 8, August 2000 ABSTRACT Linear recursive filters can be adapted on-line but with instability problems. Stability control techniques exist but they are either computationally expensive or non-robust. For the non-linear case, e.g. locally recurrent neural networks, the stability of Infinite Impulse Response (IIR) synapses is often a condition to be satisfied. This paper considers the known reparametrization-for-stability method for the on-line adaptation of IIR adaptive filters. A new technique is also presented, based on the further adaptation of the squashing function, which allows to improve the convergence performance. The proposed method can be applied to various filter realizations (direct forms, cascade or parallel of second order sections, lattice form) as well as to locally recurrent neural networks, such as the IIR Multi-Layer Perceptron (IIR-MLP), with improved performance with respect to other techniques and to the case of no stability control. In the paper the case of normalized lattice filters is particularly considered; an analysis of the stabilization effects is also presented both analytically and experimentally. ================================= Paolo Campolucci, PhD Dipartimento di Elettronica ed Automatica Universita' di Ancona, Italy e-mail: paolo at eealab.unian.it or campoluc at tiscalinet.it http://nnsp.eealab.unian.it/Campolucci_P ================================= From rsun at cecs.missouri.edu Sun Sep 17 20:55:01 2000 From: rsun at cecs.missouri.edu (Ron Sun) Date: Sun, 17 Sep 2000 19:55:01 -0500 Subject: Ph.D program at UMC Message-ID: <200009180055.TAA25373@pc113.cecs.missouri.edu> The Ph.D program in CECS at University of Missouri-Columbia is accepting applications. Graduate assistantships and other forms of financial support for graduate students are available. Prospective graduate students interested in Artificial Intelligence, Cognitive Science, Connectionist Models (Neural Networks), Multi-Agent Systems, and other related areas are especially encouraged to apply. Students with earned Master's degrees are preferred. The department identifies graduate education and research as its primary missions. The department is conducting quality research in a number of areas: artificial intelligence, cognitive sceince, machine learning, multi-agent systems, neural networks and connectionist models, computer graphics and scientific visualization, computer vision, digital libraries, fuzzy logic, multimedia systems, parallel and distributed computing, and Web computing. To download application forms, use http://www.missouri.edu/~gradschl or http://web.missouri.edu/~regwww/admission/intl_admission/Application_Form/Application_index.html (for international students) ----------------------------------------------------------------- The CECS Department awards degrees at the Bachelor's, Master's and Ph.D's levels. The program is accredited by ABET. The CECS Department has a variety of computing equipment and laboratories available for instruction and research. These facilities are currently being enhanced, in conjunction with computing laboratories maintained by the college and by the campus. The computing facilities offer students a wealth of opportunity to access and utilize a wide range of equipment best suited for their research needs. All of the equipment is connected to departmental, college, campus, and global networks which provides ready access to the exploding world of information and computational resources. A wealth of library resources are available through the extensive collections of books and journals housed in the Engineering and Mathematical Sciences libraries as well as collections in the Main Library and Health Sciences Libraries at MU. The University of Missouri is a Research I university enrolling some 22,000 students. The University offers programs in many areas, ranging from sciences and engineering to psychology, neuroscience, education, biology, medicine, law, agriculture, and journalism. For more information, send e-mail to: gradsec at cecs.missouri.edu See the Web pages below: =========================================================================== Prof. Ron Sun http://www.cecs.missouri.edu/~rsun CECS Department University of Missouri-Columbia fax: (573) 882 8318 201 Engineering Building West Columbia, MO 65211-2060 email: rsun at cecs.missouri.edu http://www.cecs.missouri.edu/~rsun http://www.cecs.missouri.edu/~rsun/journal.html =========================================================================== From istvan at louisiana.edu Mon Sep 18 15:28:50 2000 From: istvan at louisiana.edu (Istvan Berkeley) Date: Mon, 18 Sep 2000 14:28:50 -0500 Subject: Cognitive Science Position Message-ID: <39C66CF2.79EC619A@louisiana.edu> FACULTY POSITION IN THE INSTITUTE OF COGNITIVE SCIENCE. The Institute of Cognitive Science of the University of Louisiana at Lafayette invites applications for a tenure-track faculty appointment for the Fall of 2001. The appointment will be made at the associate professor or senior assistant professor level. The Institute of Cognitive Science is a graduate unit offering a Ph.D. program in cognitive science. Focus areas of the program are in cognitive processes, comparative cognition, cognitive development, computational models of mind, cognitive neuroscience, and language processing. Applicants should hold a Ph.D. in cognitive science, psychology, or a related discipline, and must exhibit evidence of a productive research program. Please send a curriculum vitae, selected reprints, and at least three letters of reference to Subrata Dasgupta, Institute of Cognitive Science, University of Louisiana at Lafayette, P.O. Drawer 43772, Lafayette, LA 70504-3772. Formal review of applications will commence December 1, 2000, but applications will be accepted until the position is filled. The University of Louisiana at Lafayette is an equal opportunity/affirmative action employee. -- Istvan S. N. Berkeley, Ph.D. Philosophy & Cognitive Science E-mail: istvan at usl.edu The University of Louisiana at Lafayette [Formerly, The University of Southwestern Louisiana] P.O. Box 43770 Tel: +1 318 482-6807 Lafayette, LA 70504-3770 Fax: +1 318 482-6195 USA http://www.ucs.usl.edu/~isb9112 From kap-listman at wkap.nl Tue Sep 19 20:02:41 2000 From: kap-listman at wkap.nl (kap-listman@wkap.nl) Date: Wed, 20 Sep 2000 02:02:41 +0200 (MEST) Subject: New Issue: Neural Processing Letters. Vol. 12, Issue 1 Message-ID: <200009200002.CAA11251@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+1+2000 Vol. 12, Issue 1, August 2000. TITLE: Analysis of the Functional Block Involved in the Design of Radial Basis Function Networks AUTHOR(S): I. Rojas, H. Pomares, J. Gonzales, J. L. Bernier, E. Ros, F. J. Pelayo, A. Prieto KEYWORD(S): RBF neural networks, neural networks design, statistical analysis of RBF, RBF structures. PAGE(S): 1-17 TITLE: Control of a Robotic Manipulator Using Artificial Neural Networks with On-line Adaptation AUTHOR(S): Roselito A. Teixeira, Antonio de P. Braga, Benjamim R. de Menezes KEYWORD(S): Adaptive Learning Rate, ANN application, on-line training, PUMA 560, robotic control. PAGE(S): 19-31 TITLE: Simultaneous Identification of Face and Orientation AUTHOR(S): Pei Ling Lai, Colin Fyfe KEYWORD(S): factor analysis, face identification. PAGE(S): 33-40 TITLE: Out-of-Vocabulary Rejection based on Selective Attention Model AUTHOR(S): Ki-Young Park, Soo-Young Lee KEYWORD(S): error backpropagation, noisy speech, out-of-vocabulary rejection, robust speech recognition, selective attention. PAGE(S): 41-48 TITLE: Coherent Response in a Chaotic Neural Network AUTHOR(S): Haruhiko Nishimura, Naofumi Katada, Kazuyuki Aihara KEYWORD(S): chaos, coherence, noise, nonlinear, recurrent neural network, refractoriness, stochastic resonance. PAGE(S): 49-58 TITLE: Clustered Recursive Branching Network AUTHOR(S): Khalid A. Al-Mashouq KEYWORD(S): recursive branching network, structured perceptrons, data clustering. PAGE(S): 59-69 TITLE: Learning with Permutably Homogeneous Multiple-Valued Multiple-Threshold Perceptrons AUTHOR(S): Alioune Ngom, Corina Reischer, Dan A. Simovici, Ivan Stojmenovic KEYWORD(S): learning, multiple-valued multiple-threshold functions, multilinear separability, partial order set, perceptrons. PAGE(S): 71-90 TITLE: On-line Algorithm for Blind Signal Extraction of Arbitrarily Distributed, but Temporally Correlated Sources Using Second Order Statistics AUTHOR(S): Andrzej Cichocki, Ruck Thawonmas KEYWORD(S): adaptive learning algorithms, blind signal processing, neural networks. PAGE(S): 91-98 -------------------------------------------------------------- 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 Patricia_Squadrito at Brown.edu Tue Sep 19 09:07:03 2000 From: Patricia_Squadrito at Brown.edu (Patricia Squadrito) Date: Tue, 19 Sep 2000 09:07:03 -0400 Subject: postdoctoral positions at Brown University Message-ID: BROWN UNIVERSITY. Post-doctoral positions available for cognitive or computational scientist. As part of an NSF award to Brown University through the IGERT program, the Departments of Cognitive and Linguistic Sciences, Computer Science, and Applied Mathematics are hiring research associates. The associates should be scholars who have displayed interest and ability in conducting collaborative interdisciplinary research involving a combination of computational and empirical approaches to one of the content areas of the program: cognition, language, or vision. As well as participating in collaborative research, responsibilities will include helping to coordinate cross-departmental events as well as some graduate teaching. Applicants must hold a PhD in Psychology, Linguistics, Cognitive Science, Computer Science, Mathematics, Applied Mathematics, or a related discipline, or show evidence that the PhD will be completed before the start of the position. Applicants should send a vita, a short research statement, three letters of reference, and other supporting material (e.g., representative publications if available), to IGERT Post-doc Search, Department of Cognitive and Linguistic Sciences, Brown University, Box 1978, Providence, RI 02912. Special consideration will be given to those applicants whose research is relevant to at least two of the participating departments. The positions are open immediately for one year, renewable upon satisfactory completion of duties. Salaries will be between $35,000 and $45,000 per year. All materials must be received by Feb. 1, 2001, for full consideration. Like all NSF-funded programs, this opportunity is available only to American citizens and permanent residents. Brown University is an Equal Opportunity/Affirmative Action Employer. From axon at cortex.rutgers.edu Tue Sep 19 09:06:40 2000 From: axon at cortex.rutgers.edu (Ralph Siegel) Date: Tue, 19 Sep 2000 09:06:40 -0400 Subject: Postdoctoral position - parietal cortex Message-ID: Postdoctoral Trainee. Analysis of visual structure-from-motion in primates. Representation of optic flow and attention in the inferior parietal lobes (area DP and 7a) are being examined in the awake behaving monkey. These studies utilize ***intrinsic optical recording***, single unit recording, in the behaving monkey. Recent graduates who are changing fields from either cellular or computational neuroscience to behavioral and physiological studies are particularly encouraged to apply. Computer expertise useful, but not necessary. Superb experimental and computational facilities in a multi-disciplinary research center. NY-NJ Metro area. Salary NIH scales plus supplement. Ralph Mitchell Siegel, Ph.D. Associate Professor axon at cortex.rutgers.edu voice: 973-353-1080 x3261 fax: 973-353-1272 Center for Molecular and Behavioral Neuroscience Rutgers, The State University 197 University Avenue Newark, NJ 07102 Graduate program information: http://www.bns.rutgers.edu/ Additional information and reprints: http://www.cmbn.rutgers.edu/~rmsiegel From terry at salk.edu Tue Sep 19 20:05:29 2000 From: terry at salk.edu (Terry Sejnowski) Date: Tue, 19 Sep 2000 17:05:29 -0700 (PDT) Subject: NEURAL COMPUTATION 12:10 Message-ID: <200009200005.e8K05Tv75812@purkinje.salk.edu> Neural Computation - Contents - Volume 12, Number 10 - October 1, 2000 Article Spike-Driven Synaptic Plasticity: Theory, Simulation, VLSI Implementation Stefano Fusi, Mario Annunziato, Davide Badoni, Andrea Salamon, and Daniel J. Amit Notes Modeling Alternation to Synchrony with Inhibitory Coupling: A VLSI Approach Gennady S. Cymbalyuk, Girish N. Patel, Ronald. L. Calabrese, Stephen P. DeWeerth, and Avis H. Cohen Representation of Concept Lattices by Bidirectional Associative Memories Radim Belohlavek Letters A Silicon Implementation of the Fly's Optomotor Control System Reid R. Harrison and Christof Koch Efficient Event-Driven Simulation of Large Networks of Spiking Neurons and Dynamical Synapses Maurizio Mattia and Paolo Del Giudice Clustering Irregular Shapes using High-Order Neurons H. Lipson and H. T. Siegelmann Learning Chaotic Attractors by Neural Networks Rembrandt Bakker, Jaap C. Schouten, C. Lee Giles, Floris Takens and Cor M. van den Bleek Generalized Discriminant Analysis Using a Kernel Approach G. Baudat and F. Anouar Generalization and Selection of Examples in Feed Forward Neural Networks Leonardo Franco and Sergio A. Cannas Stationary and Integrated Autoregressive Neural Network Processes Adrian Trapletti, Friedrich Leisch, and Kurt Hornik Learning To Forget: Continual Prediction with LSTM Felix A. Gers, Jurgen Schmidhuber, and Fred Cummins ----- 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 C.Campbell at bristol.ac.uk Wed Sep 20 05:57:09 2000 From: C.Campbell at bristol.ac.uk (Colin Campbell, Engineering Mathematics) Date: Wed, 20 Sep 2000 10:57:09 +0100 (GMT Daylight Time) Subject: Lectureship available Message-ID: Lectureship in Mathematics, University of Bristol. Applications are invited for a permanent Lectureship in Mathematics in the Department of Engineering Mathematics, University of Bristol, United Kingdom. Candidates should preferably have research interests overlapping with current interests in the department which include computational intelligence (support vector machines, neural computing, machine vision, logic programming, reasoning with uncertainty, etc). Candidates should have an excellent track record in research since the opening is in competition with the Nonlinear Dynamics Group in the department which typically gains a strong international field of applicants. Since the department is in a Faculty of Engineering our lecturing is strongly oriented towards applied mathematics. The department runs its own degree programmes in addition to providing mathematical or theoretical computer science courses for degree programmes elsewhere in the Faculty. The department achieved a score of 5 in the last Research Assessment Exercise (1996) and 23/24 for the HEFCE TQA assessment of its courses. For further details see: http://lara.enm.bris.ac.uk/cig or contact Dr. Colin Campbell (C.Campbell at bris.ac.uk). The closing date for applications is *** 15th October 2000 ***. -------------------------------------------- Dr. Colin Campbell, Dept. of Engineering Mathematics, Bristol University, Bristol BS8 1TR, United Kingdom http://lara.enm.bris.ac.uk/cig/ Tel +44 (0) 117 928 9858 C.Campbell at bristol.ac.uk From oby at cs.tu-berlin.de Wed Sep 20 15:12:01 2000 From: oby at cs.tu-berlin.de (Klaus Obermayer) Date: Wed, 20 Sep 2000 21:12:01 +0200 (MET DST) Subject: preprint available Message-ID: <200009201912.VAA14446@pollux.cs.tu-berlin.de> Dear Connectionists, attached please find abstract and preprint location of one manuscript on the analysis of Ca-imaging data from the olfactory system (antennal lobe) of the honeybee. Comments are welcome! Cheers Klaus ----------------------------------------------------------------------------- Prof. Dr. Klaus Obermayer phone: 49-30-314-73442 FR2-1, NI, Informatik 49-30-314-73120 Technische Universitaet Berlin fax: 49-30-314-73121 Franklinstrasse 28/29 e-mail: oby at cs.tu-berlin.de 10587 Berlin, Germany http://ni.cs.tu-berlin.de/ ============================================================================= Analysis of calcium imaging signals from the honeybee brain by nonlinear models M. Stetter^1,3, H. Greve^1, C. Galizia^2, and K. Obermayer^1 ^1 Fachbereich Informatik, Technische Universitaet Berlin ^2 Institut fuer Neurobiology, Freie Universitaet Berlin ^3 Zentrale Forschung, Siemens AG, Muenchen Recent Ca$^{2+}$-imaging studies on the antennal lobe of the honeybee {\it (Apis mellifera)} have shown that olfactory stimuli evoke complex spatiotemporal changes of the intracellular Ca$^{2+}$ concentration, in which stimulus-dependent subsets of glomeruli are highlighted. In this work we use nonlinear models for the quantitative identification of the spatial and temporal properties of the Ca$^{2+}$-dependent fluorescence signal. This technique describes time-series of the Ca$^{2+}$ signal as a superposition of biophysically motivated model functions for photobleaching and Ca$^{2+}$-dynamics, provides optimal estimates of their amplitudes (signal strengths) and time-constants together with error measures. Using this method, we can reliably identify two different stimulus-dependent signal components. Their delays and rise times, $delta_{c1} = (0.4 \pm 0.3)$~s, $\tau_{c1} = (3.8 \pm 1.2)$~s for the fast component and $\delta_{c2} = (2.4 \pm 0.6)$~s, $\tau_{c2} = (10.3 \pm 3.2)$~s for the slow component, are constant over space and across different odors and animals. In chronical experiments, the amplitude of the fast (slow) component often decreases (increases) with time. The pattern of the Ca$^{2+}$-dynamics in space and time can be reliably described as a superposition of only two spatiotemporally separable patterns based on the fast and slow components. However, the distributions of both components over space turn out to differ from each other, and more work has to be done in order to specify their relationship with neuronal activity. in: NeuroImage, in press available at: http://ni.cs.tu-berlin.de/publications/ From danr at cs.uiuc.edu Wed Sep 20 15:28:52 2000 From: danr at cs.uiuc.edu (Dan Roth) Date: Wed, 20 Sep 2000 14:28:52 -0500 Subject: Postdoctoral Position , Beckman Institute, UIUC Message-ID: <39C90FF4.23D2794E@cs.uiuc.edu> Postdoctoral Position Beckman Institute University of Illinois, Urbana-Champaign The Beckman Institute for Advanced Science and Technology is seeking a postdoctoral fellow for a new project funded by the National Science Foundation's ITR program entitled: "Multimodal Human Computer Interaction: Toward a Proactive Computer." This project involves a multi-disciplinary team of researchers from Electrical Engineering, Computer Science, Psychology and Education including Thomas Huang (ECE), David Brown (Ed), David Kriegman (CS), Steve Levinson (ECE), George McConkie (Psych), and Dan Roth (CS). The ideal candidate will have a broad vision of the future of human computer interaction and the technical skills to realize this with expertise in at least one of the following areas: computer vision, image processing, speech understanding, natural language, learning, decision systems, multimedia, or HCI. The candidate should have a Ph.D. in Computer Science, Electrical Engineering or a related field, should enjoy working with a team of researchers on large and challenging problems, should have experience in developing large software systems, and should communicate well in spoken and written English. This specific project is based on the belief that, to be more accessible to the general population, computers must be more proactive in their interactions with people. In human interaction, someone who waits for each command before making any communication attempt would be regarded as uncooperative and unhelpful. In order for a computer to be more proactive and, thus, to bear its part of the burden of initiation in interactions, it must have (1) much more real-time information about its user, and (2) algorithms that select actions based on this information rather than simply on user commands. The computer needs information about the user's current and past emotional, motivational and cognitive state as well as the state of the task at hand. Proposed research includes: (1) further development of methods to sense user postures, movements, expressions and speech; (2) Learning from multi-modal input; (3) analysis and fusion of this information to identify and track user states; (4) task state tracking; (5) creating a corpus of emotion- and action-labeled videotapes for use with computer learning; (6) further development of affective communication; (7) development of the basis for human-centered state-based action decisions; and (8) evaluation of computer proaction on human behavior and response. The testbed is an environment for hands-on education in science and engineering, using the Lego Mindstorms construction and robotics environment, with children of middle school age. An emphasis will be on developing proactive computing methods for encouraging interest and conceptual development of minority children and females, who often show lower achievement in science. Although the work will be conducted within an educational environment, the methods developed and studied will be broadly applicable, and this project should serve as an exemplar of the type of work that is needed in other computer-aided situations. Please send a CV and the names of three references to: Prof. Dan Roth Dept. of Computer Science University of Illinois, Urbana-Champaign 1304 Springfield Ave. Urbana, IL 61801 danr at cs.uiuc.edu From wsenn at cns.unibe.ch Thu Sep 21 05:52:21 2000 From: wsenn at cns.unibe.ch (Walter Senn) Date: Thu, 21 Sep 2000 11:52:21 +0200 (CEST) Subject: Preprint on spike-timing dependent synaptic plasticity Message-ID: The following preprint, `An algorithm for modifying neurotransmitter release probability based on pre- and post-synaptic spike timing', accepted at Neural Computation, can be downloaded from http://www.cns.unibe.ch/~wsenn/#pub. The paper reproduces data of Markram et al. (Science, 1997, including unpublished ones). It also investigates the connection to the BCM-rule and to correlation rules based on (Poisson) firing rates. Walter Senn, Henry Markram, Misha Tsodyks Abstract: The precise times of occurrence of individual pre- and post-synaptic action potentials is known to play a key role in the modification of the synaptic efficacy. Based on stimulation protocols of two synaptically connected neurons, we infer an algorithm which reproduces the experimental data by modifying the probability of vesicle discharge as a function of the relative timing of spikes in the pre- and post-synaptic neurons. The primary feature of this algorithm is an asymmetry with respect to the direction of synaptic modification depending on whether the presynaptic spikes precede or follow the postsynaptic spike. Specifically, if the presynaptic spike occurs up to 50ms before the postsynaptic spike, the probability of vesicle discharge is up-regulated while the probability of vesicle discharge is down-regulated if the presynaptic spike occurs up to 50ms after the postsynaptic spike. In the case where neurons fire irregularly with Poisson spike trains at constant mean firing rates, the probability of vesicle discharge converges towards a characteristic value which is determined by the pre- and post-synaptic firing rates. On the other hand, if the mean rates of the Poisson spike trains slowly change with time our algorithm predicts modifications in the probability of release which generalize Hebbian and BCM rules. We conclude that the proposed spike-based synaptic learning algorithm provides a general framework for regulating neurotransmitter release probability. From hopfield at Princeton.EDU Thu Sep 21 20:25:58 2000 From: hopfield at Princeton.EDU (John J. Hopfield) Date: Thu, 21 Sep 2000 20:25:58 -0400 Subject: Neural Computation Competition Message-ID: <39CAA716.3AEB5E3F@princeton.edu> ANNOUNCING A NEURAL COMPUTATION COMPETITION ------------------------------------------- by John Hopfield (hopfield at princeton.edu) and Carlos Brody (carlos at cns.nyu.edu) Web Site (with preprint): http://neuron.princeton.edu/~moment How do we identify spoken words? How do we recognize textures with our fingers? How do we integrate information over time to perceive structure-from-motion? All of the above are examples of the capacity of nervous systems to integrate information over time and recognize spatiotemporal patterns. How this is actually done in the brain remains, of course, a relative mystery. Here we wish to introduce a novel neural network, built on novel neurocomputational principles, which recognizes spatiotemporal patterns. We exemplify this with robust recognition of a monosyllabic utterance. Unusually, we have chosen to present this novel network in the form of a competition. We have treated the network as if it were a real biological organism, and we present only the results of the "experiments" that one would normally carry out with such a creature. (We have playfully dubbed the network "mus silicium, the sonoran desert sand mouse.") The experimental results presented are, we believe, sufficient to deduce the novel principles on which the network operates. For people wishing to carry out further experiments, we have constructed an interactive web site. Sound stimuli may be uploaded to this web site, and the resulting spike train responses of the mus silicium's neurons may be downloaded from the site. THE CHALLENGE, THEN, AND THE GOAL OF THE COMPETITION, IS TO DISCOVER, BASED ON THE "EXPERIMENTAL" RESULTS, HOW THE NETWORK OPERATES. In this the competition exactly mimics wet neurobiology. The rules of the competition are detailed further below and on the web site; on Dec. 14th, we will anounce the results of the competition and reveal the principles of the network's operation. However, although we have formalized the competition, and we provide specific rules and prizes, we do wish to emphasize that the greatest benefits of the exercise are to be found simply by *trying to DEDUCE, based on the extant "experimental" results, how the network operates*. The prizes and formal competition are there merely for extra fun, they contain no scientific information in themselves. The interactive web site/homepage for this network and associated competition, containing full information on the network, a preprint, and the competition rules, is: http://neuron.princeton.edu/~moment. To be considered, competition entries must be received by carlos at cns.nyu.edu or hopfield at princeton.edu PRIOR to Friday 1st December 2000. ---------- MOTIVATION ---------- We wish to note that there are two quite distinct aspects to what we are doing: (1) We are presenting novel computational principles which we believe will be of great interest to the computational neuroscience and connectionist community. Because of the method of presentation, we cannot demonstrate these principles to you directly. At this point, we can only give you our word that, in our own estimation, they are simple, powerful, biologically plausible, and novel. (2) In computational neuroscience modeling one typically "guesstimates", on the basis of experience, which aspects of the data are relevant and which are irrelevant. One then builds a model consistent with the chosen relevant aspects. This process is an example of what we will term "RATIONAL" reasoning. The rational view as applied to neuroscience allows data properties to be caused by unknown factors such as unobserved cell types, novel channels, etc. This approach should be distinguished from DEDUCTIVE reasoning, for which once basic properties are sufficiently known, new conclusions can be logically deduced from even apparently minor aspects of inconsistency or the unexpected. Deduction is enormously different from even the most rational "guesstimation." Given the quantity of diverse data now available in neuroscience, the question we are posing with our network and which we underscore through the competition is: to what extent is a deductive approach becoming useful in neurobiology? ---------------- THE COMPETITIONS ---------------- Further details of the competition rules can be found through the main site, http://neuron.princeton.edu/~moment. There are two "mus silicium" competitions. You can enter one or both, as you wish. The goal of CONTEST A is to write a 750 word essay, with or without equations, describing how you convincingly reasoned deductively from the experimental results presented in the preprint (augmented if desired with further experiments you may have carried out or seen on the web site) to understand the principles by which the "mus silicium" network operates. The cash prize for the best essay is $500, for the runner-up $200. The goal of CONTEST B is to generate an artificial neural network, of approximately the same size, complexity, and biological plausibility as "mus silicium", which recognizes the spoken word "one". The actual "mus silicium" network can be thought of as merely one possible entry meting the specifications of this contest. The cash prize for the best recognizer network is $500, for the runner-up $200. On the website, we detail what we mean by a network of "approximately same size, complexity", etc. as "mus silicium." For Contest B, we provide on the web site a front end that turns sound files into spatiotemporal patterns of timed events. Thus, Contest B is essentially about generating a network that recognizes spatiotemporal patterns (which underscores the generality of the problem being addressed), while using a limited number of simple, biologically plausible spiking neurons. (Needless to say, we think that, if entered, "mus silicium" would win Contest B-- but maybe we are wrong!) For both contests, entries must be submitted by email to either hopfield at princeton.edu or carlos at cns.nyu.edu before Dec. 1st, 2000. Multiple author submissions are welcome. A group of N authors can submit N entries. From hoethker at ira.uka.de Fri Sep 22 03:22:05 2000 From: hoethker at ira.uka.de (Karin Hoethker) Date: Fri, 22 Sep 2000 09:22:05 +0200 Subject: Job offer in Karlsruhe: modeling melodic structure Message-ID: <39CB089D.89E36C7C@ira.uka.de> ------------------------------------------------------------------------ JOB OFFER "Modelling melodic structure with learning-based methods" ------------------------------------------------------------------------ PROJECT "Modelling melodic structure with learning-based methods" The goal of the project is the development of learning-based methods for detecting style-typical properties of melodies. These methods will be used for analysis and recognition of melodic styles (style-critical analysis) and for the generation of new melodies in a learned style (style imitation). We will use learning-based methods, because adaptive models do not rely on hard-wired assumptions about relevant relationships between melodic features and are therefore substantially style-independent. Furthermore, they allow to control the complexity of a model and thereby to optimize its generalization capability. The resulting methods will be applied to retrieve melodies in a given style from a database and to generate new melodies within an evolutionary framework. For evaluation, folk tunes of different origins and 'classical' melodies will be considered. Two researchers and two students will work on the project. There will be close contact with the institute's Neural Network Group which covers a broad range of methodological issues as well as applications of learning-based methods. A fully-equipped music laboratory is available. The project is funded by the Klaus Tschira Foundation, has a total duration of two years and will prospectively start in January 2001. POSITION A research position is available for the duration of 1-2 years. We are looking for a computer scientist/mathematician with experience in musical informatics or a musicologist with strong background in computer science, preferably at post-doctoral level. Experience in the area of neural networks/machine learning and C/C++ programming skills are desirable. Appointment will be full-time. The salary will be based on BAT IIa, which is the usual salary for scientific employees in German universities. Due to the project scheduling, the earliest possible date of entry is January 2001, the latest is January 2002. The place of employment is Karlsruhe, Germany. APPLICATION Please send your application including * a curriculum vitae, * a statement about your professional interests and goals, and * three relevant publications to Institut f"ur Logik, Komplexit"at und Deduktionssysteme Prof. Dr. W. Menzel Information Structures in Music Universit"at Karlsruhe Am Fasanengarten 5 D-76128 Karlsruhe Germany Alternatively, you can submit your application electronically to musik at ira.uka.de. The deadline for applications is 15.11.2000. The University of Karlsruhe intends to increase the percentage of women in research positions and therefore encourages women to apply. ADDITIONAL INFORMATION "Information structures in music" group http://i11www.ira.uka.de/~musik Klaus Tschira Foundation http://www.kts.villa-bosch.de/ University of Karlsruhe http://www.uni-karlsruhe.de/ City of Karlsruhe http://www.karlsruhe.de/ Please send further inquiries to Karin H"othker (hoethker at ira.uka.de). From: esann To: "Connectionists at cs.cmu.edu" References: From bogus@does.not.exist.com Fri Sep 22 11:26:15 2000 From: bogus@does.not.exist.com () Date: Fri, 22 Sep 2000 17:26:15 +0200 Subject: CFP: ESANN'2001 European Symposium on Artificial Neural Networks Message-ID: ---------------------------------------------------- | | | ESANN'2001 | | | | 9th European Symposium | | on Artificial Neural Networks | | | | Bruges (Belgium) - April 25-26-27, 2001 | | | | First announcement and call for papers | ---------------------------------------------------- Technically co-sponsored by the IEEE Neural Networks Council (TBC), the IEEE Region 8, the IEEE Benelux Section, and the International Neural Networks Society. The call for papers for the ESANN'2001 conference is now available on the Web: http://www.dice.ucl.ac.be/esann For those of you who maintain WWW pages including lists of related ANN sites: we would appreciate if you could add the above URL to your list; thank you very much! We try as much as possible to avoid multiple sendings of this call for papers; however please apologize if you receive this e-mail twice, despite our precautions. You will find below a short version of this call for papers, without the instructions to authors (available on the Web). If you have difficulties to connect to the Web please send an e-mail to esann at dice.ucl.ac.be and we will send you a full version of the call for papers. ESANN'2001 is organised in collaboration with the UCL (Universite catholique de Louvain, Louvain-la-Neuve) and the KULeuven (Katholiek Universiteit Leuven). Scope and topics ---------------- Since its first edition in 1993, the European Symposium on Artificial Neural Networks has become the reference for researchers on fundamentals and theoretical aspects of artificial neural networks. Each year, around 100 specialists attend ESANN, in order to present their latest results and comprehensive surveys, and to discuss the future developments in this field. The ESANN'2001 conference will focus on fundamental aspects of ANNs: theory, models, learning algorithms, mathematical aspects, approximation of functions, classification, control, time-series prediction, statistics, signal processing, vision, self-organization, vector quantization, evolutive learning, psychological computations, biological plausibility, etc. Papers on links and comparisons between ANNs and other domains of research (such as statistics, data analysis, signal processing, biology, psychology, evolutive learning, bio-inspired systems, etc.) are encouraged. Papers will be presented orally (no parallel sessions) and in poster sessions; all posters will be complemented by a short oral presentation during a plenary session. It is important to mention that it is the topics of the paper which will decide if it better fits into an oral or a poster session, not its quality. The selection of posters will be identical to oral presentations, and both will be printed in the same way in the proceedings. Nevertheless, authors have the choice to indicate on the author submission form that they only accept to present their paper orally. The following is a non-exhaustive list of topics covered during the ESANN conferences: * theory * models and architectures * mathematics * learning algorithms * vector quantization * self-organization * RBF networks * Bayesian classification * recurrent networks * support-vector machines * approximation of functions * time series forecasting * adaptive control * statistical data analysis * independent component analysis * signal processing * cellular neural networks * fuzzy neural networks * natural and artificial vision * hybrid networks * identification of non-linear dynamic systems * biologically plausible artificial networks * bio-inspired systems * adaptive behavior * evolutive learning Special sessions ---------------- Special sessions will be organized by renowned scientists in their respective fields. Papers submitted to these sessions are reviewed according to the same rules as any other submission. Authors who submit papers to one of these sessions are invited to mention it on the author submission form; nevertheless, submissions to the special sessions must follow the same format, instructions and deadlines as any other submission, and must be sent to the same address. * Neural networks applications in finance M. Cottrell, Univ. Paris I (France), E. de Bodt (Univ. Lille II (France) & UCL Louvain-la-Neuve (Belgium) * Artificial neural networks and early vision processing C. Fyfe, D. Charles, Univ. of Paisley (Scotland) * Artificial neural networks for web computing M. Maggini, Univ. di Siena (Italy) * Dedicated hardware implementations: perspectives on systems and applications D. Anguita, M. Valle, Univ. of Genoa (Italy) * Novel neural transfer functions W. Duch, Nicholas Copernicus Univ. (Poland) * Neural networks and evolutionary/genetic algorithms - hybrid approaches T. Villmann, Univ. Leipzig (Germany) Location -------- The conference will be held in Bruges (also called "Venice of the North"), one of the most beautiful medieval towns in Europe. Bruges can be reached by train from Brussels in less than one hour (frequent trains). The town of Bruges is world-wide known, and famous for its architectural style, its canals, and its pleasant atmosphere. The conference will be organised in a hotel located near the centre (walking distance) of the town. There is no obligation for the participants to stay in this hotel. Hotels of all level of comfort and price are available in Bruges; there is a possibility to book a room in the hotel of the conference at a preferential rate through the conference secretariat. A list of other smaller hotels is also available. The conference will be held at the Novotel hotel, Katelijnestraat 65B, 8000 Brugge, Belgium. Call for contributions ---------------------- Prospective authors are invited to submit * six copies of their manuscript (including at least two originals or very good copies without glued material, which will be used for the proceedings) * one signed copy of the author submission form * a floppy disk or a CD (PC format preferred) containing their contribution in (generic) PostScript format before December 8, 2000. Sorry, electronic or fax submissions are not accepted. The working language of the conference (including proceedings) is English. The instructions to authors, together with the author submission form, are available on the ESANN Web server: http://www.dice.ucl.ac.be/esann Authors must indicate their choice for oral or poster presentation on the author submission form. They must also sign a written agreement that they will register to the conference and present the paper in case of acceptation of their submission. Authors of accepted papers will have to register before February 28, 2001. They will benefit from the advance registration fee. Submissions must be sent to: Michel Verleysen UCL - DICE 3, place du Levant B-1348 Louvain-la-Neuve Belgium esann at dice.ucl.ac.be All submissions will be acknowledged by fax or email before December 22, 2000. Deadlines --------- Submission of papers December 8, 2000 Notification of acceptance February 5, 2001 Symposium April 25-27, 2001 Registration fees ----------------- registration before registration after March 16, 2001 March 16, 2001 Universities BEF 16500 BEF 17500 Industries BEF 20500 BEF 21500 The registration fee includes the attendance to all sessions, the ESANN'2001 dinner, a copy of the proceedings, daily lunches (25-27 April 2001), and the coffee breaks. Conference secretariat ---------------------- Michel Verleysen D facto conference services phone: + 32 2 420 37 57 27 rue du Laekenveld Fax: + 32 2 420 02 55 B - 1080 Brussels (Belgium) E-mail: esann at dice.ucl.ac.be http://www.dice.ucl.ac.be/esann Steering and local committee (to be confirmed) ---------------------------- Francois Blayo Prefigure (F) Marie Cottrell Univ. Paris I (F) Jeanny Herault INPG Grenoble (F) Henri Leich Fac. Polytech. Mons (B) Bernard Manderick Vrije Univ. Brussel (B) Eric Noldus Univ. Gent (B) Jean-Pierre Peters FUNDP Namur (B) Joos Vandewalle KUL Leuven (B) Michel Verleysen UCL Louvain-la-Neuve (B) Scientific committee (to be confirmed) -------------------- Edoardo Amaldi Politecnico di Milano (I) Herve Bourlard IDIAP Martigny (CH) Joan Cabestany Univ. Polit. de Catalunya (E) Colin Campbell Bristol Univ. (UK) Stephane Canu Inst. Nat. Sciences App. (F) Holk Cruse Universitat Bielefeld (D) Eric de Bodt Univ. Lille II & UCL Louv.-la-N. (B) Dante Del Corso Politecnico di Torino (I) Wlodek Duch Nicholas Copernicus Univ. (PL) Marc Duranton Philips / LEP (F) Richard Duro Univ. Coruna (E) Jean-Claude Fort Universite Nancy I (F) Bernd Fritzke Dresden Univ. of Technology (D) Colin Fyfe Univ. Paisley (UK) Stan Gielen Univ. of Nijmegen (NL) Marco Gori Univ. Siena (I) Bernard Gosselin Fac. Polytech. Mons (B) Manuel Grana UPV San Sebastian (E) Anne Guerin-Dugue INPG Grenoble (F) Martin Hasler EPFL Lausanne (CH) Laurent Herault CEA-LETI Grenoble (F) Gonzalo Joya Univ. Malaga (E) Christian Jutten INPG Grenoble (F) Juha Karhunen Helsinky Univ. of Technology (FIN) Vera Kurkova Acad. of Science of the Czech Rep. (CZ) Jouko Lampinen Helsinki Univ. of Tech. (FIN) Petr Lansky Acad. of Science of the Czech Rep. (CZ) Mia Loccufier Univ. Gent (B) Erzsebet Merenyi Rice Univ. (USA) Jean Arcady Meyer Univ. Pierre et Marie Curie - Paris 6 (F) Jose Mira UNED (E) Jean-Pierre Nadal Ecole Normale Superieure Paris (F) Gilles Pages Univ. Pierre et Marie Curie - Paris 6 (F) Thomas Parisini Politecnico di Milano (I) Helene Paugam-Moisy Univ. Lumiere Lyon 2 (F) Alberto Prieto Universitad de Granada (E) Leonardo Reyneri Politecnico di Torino (I) Tamas Roska Hungarian Academy of Science (H) Jean-Pierre Rospars INRA Versailles (F) Jose Santos Reyes Univ. Coruna (E) John Stonham Brunel University (UK) Johan Suykens KUL Leuven (B) John Taylor King's College London (UK) Claude Touzet IUSPIM Marseilles (F) Marc Van Hulle KUL Leuven (B) Thomas Villmann Univ. Leipzig (D) Christian Wellekens Eurecom Sophia-Antipolis (F) From R.J.Howlett at bton.ac.uk Fri Sep 22 12:25:58 2000 From: R.J.Howlett at bton.ac.uk (R.J.Howlett@bton.ac.uk) Date: Fri, 22 Sep 2000 17:25:58 +0100 Subject: Research vacancy Message-ID: <08C89600D966D4119C7800105AF0CB6B4B00CC@moulsecoomb.bton.ac.uk> -- Intelligent Signal Processing Labs, University of Brighton, Sussex, UK.-- --------- Research Vacancy on scale approx #17000-#24000 --------- An opportunity to develop software skills as a member of an established research group in leading-edge area of technology. You will work on a project to develop new intelligent data analysis techniques that can be used for monitoring and control in a range of applications. There may be an opportunity to extend the work to applying intelligent techniques to data obtained ("mined") automatically from the internet. The work will involve existing software tools (neural networks) and developing them to enhance their capabilities, and also the development of new neural network algorithms. A good first degree in an appropriate subject is required; a PhD in an appropriate field would be an advantage. You should have good programming and software development ability, and good laboratory, practical and measurement skills. Some knowledge of neural networks or other intelligent techniques would be an advantage. The post is available immediately, fixed-term until the 31 December 2001 in accordance with the period of funding. However, one of the duties of the applicant will be to attempt to secure further funding to extend the period of employment. We are unlikely to be able to consider candidates who are not currently available in the UK for interview. To apply send a CV by email to:- R.J.Howlett at bton.ac.uk Please quote ref: SE4010 From kap-listman at wkap.nl Fri Sep 22 20:02:31 2000 From: kap-listman at wkap.nl (kap-listman@wkap.nl) Date: Sat, 23 Sep 2000 02:02:31 +0200 (MEST) Subject: New Issue: Neural Processing Letters. Vol. 12, Issue 2 Message-ID: <200009230002.CAA07209@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+2+2000 Vol. 12, Issue 2, October 2000. TITLE: Obtaining Fault Tolerant Multilayer Perceptrons Using an Explicit Regularization AUTHOR(S): Jose L. Bernier, J. Ortega, I. Rojas, E. Ros, A. Prieto KEYWORD(S): backpropagation, regularization, multilayer perceptron, fault tolerance, mean square sensitivity. PAGE(S): 107-113 TITLE: Evolving Multilayer Perceptrons AUTHOR(S): P. A. Castillo, J. Carpio, J. J. Merelo, A. Prieto, V. Rivas, G. Romero KEYWORD(S): evolutionary algorithms, generalization, learning, neural networks, optimization. PAGE(S): 115-128 TITLE: Associative Memories in Infinite Dimensional Spaces AUTHOR(S): Enrique Carlos Segura, Roberto P. J. Perazzo KEYWORD(S): associative memory, dynamical systems, Glauber dynamics, Hopfield model, infinite dimensional state space, stability. PAGE(S): 129-144 TITLE: Embedding Connectionist Autonomous Agents in Time: The `Road Sign Problem' AUTHOR(S): R. M. Rylatt, C. A. Czarnecki KEYWORD(S): autonomous agents, recurrent neural networks. PAGE(S): 145-158 TITLE: Globally Convergent Modification of the Quickprop Method AUTHOR(S): Michael N. Vrahatis, George D. Magoulas, Vassilis P. Plagianakos KEYWORD(S): Quickprop algorithm, Broyden-s method, secant methods, convergence analysis, backpropagation neural networks. PAGE(S): 159-170 TITLE: Parallel Implementation of Self-Organizing Map on the Partial Tree Shape Neurocomputer AUTHOR(S): Pasi Kolinummi, Pasi Pulkkinen, Timo Hamalainen, Jukka Saarinen KEYWORD(S): computer architecture, neurocomputer, parallel hardware implementation, parallel mapping, self-organizing map. PAGE(S): 171-182 TITLE: Improving the Mean-Field Approximation in Belief Networks Using Bahadur-s Reparameterisation of the Multivariate Binary Distribution AUTHOR(S): K. Humphreys, D. M. Titterington KEYWORD(S): Bahadur, belief network, EM algorithm, Mean-Field, variational approximation. PAGE(S): 183-197 -------------------------------------------------------------- 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 steve at cns.bu.edu Sun Sep 24 19:09:38 2000 From: steve at cns.bu.edu (Stephen Grossberg) Date: Sun, 24 Sep 2000 19:09:38 -0400 Subject: a neural model of smooth pursuit control and motion perception by MST Message-ID: The following article is available at http://www.cns.bu.edu/Profiles/Grossberg in HTML, PDF, and Gzipped postscript: Pack, C., Grossberg, S. and Mingolla, E. (2000). A neural model of smooth pursuit control and motion perception by cortical area MST. Journal of Cognitive Neuroscience, in press. Preliminary version available as Technical Report CAS/CNS-TR-99-023, Boston: Boston University. ABSTRACT: Smooth pursuit eye movements are eye rotations that are used to maintain fixation on a moving target. Such rotations complicate the interpretation of the retinal image, because they nullify the retinal motion of the target, while generating retinal motion of stationary objects in the background. This poses a problem for the oculomotor system, which must track the stabilized target image, while suppressing the optokinetic reflex, which would move the eye in the direction of the retinal background motion, which is opposite to the direction in which the target is moving. Similarly, the perceptual system must estimate the actual direction and speed of moving objects in spite of the confounding effects of the eye rotation. This paper proposes a neural model to account for the ability of primates to accomplish these tasks. The model simulates the neurophysiological properties of cell types found in the superior temporal sulcus of the macaque monkey, specifically the medial superior temporal (MST) region. These cells process signals related to target motion, background motion, and receive an efference copy of eye velocity during pursuit movements. The model focuses on the interactions between cells in the ventral and dorsal subdivisions of MST, which are hypothesized to process target velocity and background motion, respectively. The model explains how these signals can be combined to explain behavioral data about pursuit maintenance and perceptual data from human studies, including the Aubert-Fleischl phenomenon and the Filehne Illusion, thereby clarifying the functional significance of neurophysiological data about these MST cell properties. It is suggested that the connectivity used in the model may represent a general strategy used by the brain in analyzing the visual world. Keywords: smooth pursuit, eye movements, visual cortex, MST, motion, optokinetic nystagmus, target tracking, perception From glanzman at helix.nih.gov Mon Sep 25 09:01:54 2000 From: glanzman at helix.nih.gov (Dennis Glanzman) Date: Mon, 25 Sep 2000 09:01:54 -0400 Subject: Positions Available at the NIMH Message-ID: <4.3.2.7.2.20000925090125.00b205f0@helix.nih.gov> We are currently recruiting outstanding scientists to fill the following four positions at the National Institute of Mental Health in Bethesda, MD. Interdisciplinary Scientist (GS-180/401/601/602-13/14) Eligibility: U.S. citizenship is required. This position is open to all qualified applicants. Salary Range: $60,890.00 - $93,537.00 For further information: http://www.nimh.nih.gov/orm/pmb/nimh000112.htm The incumbent of this position has primary responsibility for the Basic Neuroscience Centers Program, and works closely with other program staff of the Division of Neuroscience and Basic Behavioral Science to assure that the appropriate substantive expertise is brought to bear on all aspects of this program. In this role, the incumbent is responsible for the programmatic evaluation of research grant applications based on the scientific value and pertinence to the interest of this program's objectives which have been approved by a review committee and the National Advisory Mental Health Council. The incumbent makes recommendations for the funding of approved grants for which the incumbent is responsible; regularly consults with other staff members of the Office and Division to advise on program content as it pertains to the program area; attends scientific meetings and conferences to ensure that program objectives and developments are related to the needs of the field, and to present and explain the activities and objectives of the program as well as to present material and chair sessions. The incumbent organizes meetings (workshops, symposia, conference, etc.) on relevant topics; maintains knowledge of the rules, regulations, guidelines, ethics, and public policy concerning the use of humans and animals in research. The incumbent also provides adequate exchange of information with other Offices, Branches, Divisions, and Institutes, various other Federal agencies, professional groups, and scientific and private organizations; cooperates with these groups and agencies regarding research problems and serves as a working member analyzing and evaluating these research endeavors within the scope of the program. Interdisciplinary Scientist (GS-180/401/601/602-13/14) Eligibility: U.S. citizenship is required. This position is open to all qualified applicants. Salary Range: $60,890.00 - $93,537.00 For further information: http://www.nimh.nih.gov/orm/pmb/nimh000110.htm The incumbent of this position provides scientific guidance and direction for a major research program -- the Integrative Neuroscience of Schizophrenia, Mood and Other Brain Disorders Program. This Program constitutes a major segment of the Branch and is designed to support research probing matters fundamental to knowledge of integrative, cognitive, and behavioral neuroscience as they relate to brain disorders and complex mental disorders. The position requires broad competence in basic neuroscience as the incumbent will provide scientific guidance and direction for this program. The incumbent performs duties in three major areas: project management and administration; program leadership and development; and personal scientific activities. For example, the incumbent is expected to analyze current research activities and program needs and identify areas under development that relate to integrative, cognitive, and behavioral neuroscience research as related to brain disorders relevant to mental health. He/she monitors new developments in the field and identifies research opportunities in areas not yet explored; provides technical advice to grantees and contractors on programmatic, scientific, and/or technical issues, including the design, development and implementation of projects and related activities; and organizes and/or represents the Institute at scientific meetings, symposia, and conferences on related topics. Interdisciplinary Scientist (GS-180/401/601/602-13/14) Eligibility: U.S. citizenship is required. This position is open to all qualified applicants. Salary Range: $60,890.00 - $93,537.00 For further information: http://www.nimh.nih.gov/orm/pmb/nimh000111.htm The position to be filled is Chief of the Cognitive Neuroscience Program in the Behavioral and Integrative Neuroscience Research Branch (BINRB). This branch plans, supports, and conducts programs of research, research training, and resource development in the neurobiological basis of behavioral processes, focusing on cognition, learning and memory, and psychopharmacology, as well as computational, theoretical, and related studies. The Cognitive Neuroscience Program represents a major segment of the Branch and is designed to develop and support basic neurobehavioral studies focusing on cognitive research to provide fundamental knowledge to understand, evaluate and treat emotion and mental disorders. The position requires broad competence in basic neuroscience as the incumbent will provide scientific guidance and direction for this program. The incumbent performs duties in three major areas: project management and administration; program leadership and development; and personal scientific activities. For example, the incumbent is expected to analyze current research activities and program needs and identify areas under development that relate to integrative, cognitive, and behavioral neuroscience research as related to brain disorders relevant to mental health. He/she monitors new developments in the field and identifies research opportunities in areas not yet explored; provides technical advice to grantees and contractors on programmatic, scientific, and/or technicalissues, including the design, development and implementation of projects and related activities; and organizes and/or represents the Institute at scientific meetings, symposia, and conferences on related topics. Assoc. Div. Dir Program Analysis & Management (GS-180/401/601/602-14/15) Eligibility: U.S. citizenship is required. This position is open to all qualified applicants. Salary Range $71,954.00 - $110,028.00 http://www.nimh.nih.gov/orm/pmb/nimh000113.htm This position is located in the Division of Neuroscience and Basic Behavioral Science (DNBBS), National Institute of Mental Health (NIMH). This Division oversees NIMH funding of extramural research programs in the areas of basic and clinical neuroscience, genetics, therapeutics development, basic behavioral science, and research training in these areas. Oversight functions include the analysis and evaluation of the current state of these fields, the national research portfolio, and developing research opportunities in the etiology, treatment, and prevention of brain and behavioral disorders. As Associate Division Director, the incumbent assists the Director in the day-to-day scientific and administrative management of the Division's research grant and contract portfolio. He/she is responsible for the continuous review and evaluation of the Division's research grant and contract supported activities designed to further understand the etiology, treatment, and prevention of brain and behavioral disorders relevant to mental health. Activities include: translating emerging needs into programs and goals for the NIMH; monitoring program growth and recommending new program emphasis or direction, adjustments to existing programs, or complete shifts in existing programs in order to maximize the impact of the overall mental health extramural research program; leading or arranging collaborative research efforts with professional scientific groups to bring the effective interaction of ideas and methods and synthesizing the results into cohesive studies. The incumbent serves as the Division's authority for research grants and contracts administration and management policy matters. As such, he/she assesses ongoing or proposed programs for Agency and Departmental grant and contract policy compliance; reviews all new or proposed grants and contracts policy issuances; develops policy positions and represents the Division in the development of Institute and Agency policy on extramural research. The incumbent assists in the formulation and presentation of budget requests and justifications for the Division's programs to the NIMH, NIH and Congress. Develops information and guidance for research, consultant and advisory groups, and members of Congress, Office of Management and Budget, and scientific and lay organizations. Maintains liaison with similar activities carried out in the NIMH, NIH, HHS, other governmental agencies and professional and scientific organizations to avoid duplication of effort and to exchange relevant information. Represents the Institute on committees and working groups, at professional and staff meetings, and regular and ad hoc meetings. From cindy at cns.bu.edu Wed Sep 27 10:56:38 2000 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Wed, 27 Sep 2000 10:56:38 -0400 Subject: 5th ICCNS: Call for Papers Message-ID: <200009271456.KAA27700@retina.bu.edu> ***** CALL FOR PAPERS ***** FIFTH INTERNATIONAL CONFERENCE ON COGNITIVE AND NEURAL SYSTEMS Tutorials: May 30, 2001 Meeting: May 31 - June 2, 2001 Boston University 677 Beacon Street Boston, Massachusetts 02215 http://www.cns.bu.edu/meetings/ Sponsored by Boston University's Center for Adaptive Systems and Department of Cognitive and Neural Systems with financial support from the National Science Foundation and the Office of Naval Research This interdisciplinary conference has drawn about 300 people from around the world each time that it has been offered. Last year's conference was attended by scientists from 28 countries. The conference is structured to facilitate intense communication between its participants, both in the formal sessions and during its other activities. As during previous years, the conference will focus on solutions to the fundamental questions: How Does the Brain Control Behavior? How Can Technology Emulate Biological Intelligence? The conference will include invited tutorials and lectures, and contributed lectures and posters by experts on the biology and technology of how the brain and other intelligent systems adapt to a changing world. The conference is aimed at researchers and students of computational neuroscience, connectionist cognitive science, artificial neural networks, neuromorphic engineering, and artificial intelligence. A single oral or poster session enables all presented work to be highly visible. Abstract submissions encourage submissions of the latest results. Costs are kept at a minimum without compromising the quality of meeting handouts and social events. CALL FOR ABSTRACTS Session Topics: * vision * spatial mapping and navigation * object recognition * neural circuit models * image understanding * neural system models * audition * mathematics of neural systems * speech and language * robotics * unsupervised learning * hybrid systems (fuzzy, evolutionary, digital) * supervised learning * neuromorphic VLSI * reinforcement and emotion * industrial applications * sensory-motor control * 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 Abstract 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 giacinto at diee.unica.it Wed Sep 27 05:06:14 2000 From: giacinto at diee.unica.it (Giorgio Giacinto) Date: Wed, 27 Sep 2000 11:06:14 +0200 Subject: PAA - Special Issue Call "Fusion of Multiple Classifiers" Message-ID: ***************************************** Pattern Analysis and Applications Journal Special Issue Call Fusion of Multiple Classifiers ***************************************** Guest Editors: J. Kittler and F. Roli Deadline: 15 October 2000 Classifier fusion has recently become an important tool for enhancing the performance of pattern recognition systems. A myriad of techniques have been developed for combining classifiers at the decision or soft decision output level. These techniques have been conceived by researchers in many diverse communities including Machine Learning, Pattern Recognition, Neural Networks, Statistics, and Artificial Intelligence. The aim of this special issue is to provide a focal point for recent advances in this methodological area of pattern recognition across different paradigms and disciplines. Submitted papers should report new theories underpinning classifier combination, novel methodologies, applications where classifier fusion significantly enhanced the recognition system performance, or extensive comparative studies of different combination rules. Topics appropriate for this special issue include, but are not limited to: * Decision level fusion * Strategies for multiple classifier fusion * Bagging and boosting * Neural network ensembles * Multiple classifier design * Fusion of one-class classifiers * Fusion of measurement and contextual information * Innovative applications Send four copies of your manuscript (marked "MCS SPECIAL ISSUE") by October 15, 2000 to the following address: Sameer Singh, Editor-in-Chief, Pattern Analysis and Applications, Department of Computer Science, University of Exeter, Exeter EX4 4PT, UK For instructions to authors, please see: http://www.dcs.ex.ac.uk/paa/authors.htm ------------------------------------------------------------- Dr. Giorgio Giacinto, Ph.D. Department of Electrical and Electronic Engineering University of Cagliari, Italy e-mail: giorgio.giacinto at computer.org From jab at ai.mit.edu Wed Sep 27 16:27:42 2000 From: jab at ai.mit.edu (Justin Boyan) Date: Wed, 27 Sep 2000 16:27:42 -0400 Subject: survey/proceedings on Statistical ML for Large-Scale Optimization Message-ID: <14802.22590.437810.357646@ai.mit.edu> Colleagues, At last year's IJCAI, Wray Buntine and I organized an IJCAI workshop on the subject of applying statistical machine learning methods in large-scale optimization domains. With Arun Jagota's help, we have now collected extended abstracts of all the presented work, and several additional contributions, into a survey paper which we believe contains the seeds of many exciting research directions. Here's where you can find it: http://www.icsi.berkeley.edu/~jagota/NCS/ (click on "VOLUME 3") I've attached the table of contents below. We have also set up an email list, learning-optimization at egroups.com, for discussion of related topics. If you'd like to join this list, please visit egroups.com or use the sign-up form at http://ic.arc.nasa.gov/people/jboyan/ijcai99/ Cheers, Justin Statistical Machine Learning for Large-Scale Optimization Editors: Justin Boyan, Wray Buntine, and Arun Jagota Contents: Introduction (J. Boyan) A Review of Iterative Global Optimization (K. Boese) Estimating the Number of Local Minima in Complex Search Spaces (R. Caruana and M. Mullins) Experimentally Determining Regions of Related Solutions for Graph Bisection Problems (T. Carson and R. Impagliazzo) Optimization of Parallel Search Using Machine Learning and Uncertainty Reasoning (D. Cook, P. Gmytrasiewicz, and C. Tseng) Adaptive Heuristic Methods for Maximum Clique (A. Jagota and L. Sanchis) Probabilistic Modeling for Combinatorial Optimization (S. Baluja and S. Davies) Adaptive approaches to Clustering for Discrete Optimization (W. Buntine, L. Su and R. Newton) Building a Basic Block Instruction Scheduler with Reinforcement Learning and Rollouts (A. McGovern, E. Moss and A. Barto) STAGE Learning for Local Search (J. Boyan and A. Moore) Enhancing Discrete Optimization with Reinforcement Learning: Case Studies Using DARP (R. Moll, T. Perkins and A. Barto) Stochastic Optimization with Learning for Standard Cell Placement (L. Su, W. Buntine, R. Newton and B. Peters) Collective Intelligence for Optimization (D. Wolpert and K. Tumer) Efficient Value Function Approximation Using Regression Trees (X. Wang and T. Dietterich) Numerical Methods for Very High-Dimension Vector Spaces (T. Dean, K. Kim, and S. Hazlehurst) -- Justin A. Boyan [Visiting Scientist from NASA Ames Research Center] MIT Artificial Intelligence Lab jab at ai.mit.edu 545 Technology Square NE43-753 http://ic.arc.nasa.gov/people/jboyan Cambridge, MA 02139 (617)-253-8005 voice, (617)-253-7781 fax From giacinto at diee.unica.it Wed Sep 27 05:01:16 2000 From: giacinto at diee.unica.it (Giorgio Giacinto) Date: Wed, 27 Sep 2000 11:01:16 +0200 Subject: 2nd Internation Workshop on Multiple Cassifier Systems Message-ID: ************************************************************ Preliminary Call for Papers MCS 2001 SECOND INTERNATIONAL WORKSHOP ON MULTIPLE CLASSIFIER SYSTEMS Robinson College, Cambridge, UK, July 2-4 2001 Updated information: http://www.diee.unica.it/mcs E-mail: mcs2001 at eim.surrey.ac.uk ************************************************************* WORKSHOP OBJECTIVES MCS 2001 is the second workshop of a series aimed to create a common international forum for researchers of the diverse communities working in the field of multiple classifier systems. Information on the first edition of MCS workshop can be found on www.diee.unica.it/mcs. Contributions from all the research communities working in the field are welcome in order to compare the different approaches and to define the common research priorities. Special attention is also devoted to assess the applications of multiple classifier systems and the potential market perspectives. The papers will be published in the workshop proceedings, and extended versions of selected papers will be considered for publication in a special issue of an international journal. WORKSHOP CHAIRS Josef Kittler (Univ. of Surrey, United Kingdom) Fabio Roli (Univ. of Cagliari, Italy) ORGANIZED BY Center for Vision, Speech and Signal Proc. of the University of Surrey and Dept. of Electrical and Electronic Eng. of the University of Cagliari CO-SPONSORED BY International Association for Pattern Recognition PAPER SUBMISSION Three hard copies of the full paper should be mailed to: MCS 2001 Prof. Josef Kittler Center for Vision, Speech and Signal Proc. University of Surrey, Guildford, Surrey GU2 5XH, UK In addition, participants should submit an electronic version of the manuscript (PostScript or PDF format) to mcs2001 at eim.surrey.ac.uk. The papers should not exceed 15 A4 pages (12pt, double-spaced). A cover sheet with the authors names and affiliations is also requested, with the complete address of the corresponding author, and an abstract (200 words). Two members of the Scientific Committee will referee the papers. WORKSHOP TOPICS Papers describing original work in the following and related research topics are welcome: * Foundations of multiple classifier systems * Methods for classifier fusion * Design of multiple classifier systems * Neural network ensembles * Bagging and boosting * Mixtures of experts * New and related approaches (algebraic and discrete mathematical methods, intelligent agents, etc.) * Applications SCIENTIFIC COMMITTEE J. A. Benediktsson (Iceland) H. Bunke (Switzerland) L. P. Cordella (Italy) B. V. Dasarathy (USA) R. P.W. Duin (The Netherlands) C. Furlanello (Italy) J. Ghosh (USA) T. K. Ho (USA) S. Impedovo (Italy) N. Intrator (Israel) A.K. Jain (USA) M. Kamel (Canada) L.I. Kuncheva (UK) D. Landgrebe (USA) D-S. Lee (USA) D. Partridge (UK) C. Scagliola (Italy) A.J.C. Sharkey (UK) S. N. Srihari (USA) C.Y. Suen (Canada) K. Tumer (USA) G. Vernazza (Italy) IMPORTANT DATES February 1, 2001 : Paper Submission March 15, 2001 : Notification of Acceptance April 10, 2001 : Camera-ready Manuscript April 10, 2001 : Registration WORKSHOP VENUE The workshop will be held at Robinson College, Cambridge, UK. WORKSHOP PROCEEDINGS The papers will be published in the workshop proceedings, and extended versions of selected papers will be considered for publication in a special issue of an international journal. ------------------------------------------------------------- Dr. Giorgio Giacinto, Ph.D. Department of Electrical and Electronic Engineering University of Cagliari, Italy e-mail: giorgio.giacinto at computer.org From Patricia_Squadrito at Brown.edu Tue Sep 19 09:07:03 2000 From: Patricia_Squadrito at Brown.edu (Patricia Squadrito) Date: Tue, 19 Sep 2000 09:07:03 -0400 Subject: postdoctoral positions at Brown University Message-ID: BROWN UNIVERSITY. Post-doctoral positions available for cognitive or computational scientist. As part of an NSF award to Brown University through the IGERT program, the Departments of Cognitive and Linguistic Sciences, Computer Science, and Applied Mathematics are hiring research associates. The associates should be scholars who have displayed interest and ability in conducting collaborative interdisciplinary research involving a combination of computational and empirical approaches to one of the content areas of the program: cognition, language, or vision. As well as participating in collaborative research, responsibilities will include helping to coordinate cross-departmental events as well as some graduate teaching. Applicants must hold a PhD in Psychology, Linguistics, Cognitive Science, Computer Science, Mathematics, Applied Mathematics, or a related discipline, or show evidence that the PhD will be completed before the start of the position. Applicants should send a vita, a short research statement, three letters of reference, and other supporting material (e.g., representative publications if available), to IGERT Post-doc Search, Department of Cognitive and Linguistic Sciences, Brown University, Box 1978, Providence, RI 02912. Special consideration will be given to those applicants whose research is relevant to at least two of the participating departments. The positions are open immediately for one year, renewable upon satisfactory completion of duties. Salaries will be between $35,000 and $45,000 per year. All materials must be received by Feb. 1, 2001, for full consideration. Like all NSF-funded programs, this opportunity is available only to American citizens and permanent residents. Brown University is an Equal Opportunity/Affirmative Action Employer. From kap-listman at wkap.nl Tue Sep 19 20:02:41 2000 From: kap-listman at wkap.nl (kap-listman@wkap.nl) Date: Wed, 20 Sep 2000 02:02:41 +0200 (MEST) Subject: New Issue: Neural Processing Letters. Vol. 12, Issue 1 Message-ID: <200009200002.CAA11251@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+1+2000 Vol. 12, Issue 1, August 2000. TITLE: Analysis of the Functional Block Involved in the Design of Radial Basis Function Networks AUTHOR(S): I. Rojas, H. Pomares, J. Gonzales, J. L. Bernier, E. Ros, F. J. Pelayo, A. Prieto KEYWORD(S): RBF neural networks, neural networks design, statistical analysis of RBF, RBF structures. PAGE(S): 1-17 TITLE: Control of a Robotic Manipulator Using Artificial Neural Networks with On-line Adaptation AUTHOR(S): Roselito A. Teixeira, Antonio de P. Braga, Benjamim R. de Menezes KEYWORD(S): Adaptive Learning Rate, ANN application, on-line training, PUMA 560, robotic control. PAGE(S): 19-31 TITLE: Simultaneous Identification of Face and Orientation AUTHOR(S): Pei Ling Lai, Colin Fyfe KEYWORD(S): factor analysis, face identification. PAGE(S): 33-40 TITLE: Out-of-Vocabulary Rejection based on Selective Attention Model AUTHOR(S): Ki-Young Park, Soo-Young Lee KEYWORD(S): error backpropagation, noisy speech, out-of-vocabulary rejection, robust speech recognition, selective attention. PAGE(S): 41-48 TITLE: Coherent Response in a Chaotic Neural Network AUTHOR(S): Haruhiko Nishimura, Naofumi Katada, Kazuyuki Aihara KEYWORD(S): chaos, coherence, noise, nonlinear, recurrent neural network, refractoriness, stochastic resonance. PAGE(S): 49-58 TITLE: Clustered Recursive Branching Network AUTHOR(S): Khalid A. Al-Mashouq KEYWORD(S): recursive branching network, structured perceptrons, data clustering. PAGE(S): 59-69 TITLE: Learning with Permutably Homogeneous Multiple-Valued Multiple-Threshold Perceptrons AUTHOR(S): Alioune Ngom, Corina Reischer, Dan A. Simovici, Ivan Stojmenovic KEYWORD(S): learning, multiple-valued multiple-threshold functions, multilinear separability, partial order set, perceptrons. PAGE(S): 71-90 TITLE: On-line Algorithm for Blind Signal Extraction of Arbitrarily Distributed, but Temporally Correlated Sources Using Second Order Statistics AUTHOR(S): Andrzej Cichocki, Ruck Thawonmas KEYWORD(S): adaptive learning algorithms, blind signal processing, neural networks. PAGE(S): 91-98 -------------------------------------------------------------- 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 axon at cortex.rutgers.edu Tue Sep 19 09:06:40 2000 From: axon at cortex.rutgers.edu (Ralph Siegel) Date: Tue, 19 Sep 2000 09:06:40 -0400 Subject: Postdoctoral position - parietal cortex Message-ID: Postdoctoral Trainee. Analysis of visual structure-from-motion in primates. Representation of optic flow and attention in the inferior parietal lobes (area DP and 7a) are being examined in the awake behaving monkey. These studies utilize ***intrinsic optical recording***, single unit recording, in the behaving monkey. Recent graduates who are changing fields from either cellular or computational neuroscience to behavioral and physiological studies are particularly encouraged to apply. Computer expertise useful, but not necessary. Superb experimental and computational facilities in a multi-disciplinary research center. NY-NJ Metro area. Salary NIH scales plus supplement. Ralph Mitchell Siegel, Ph.D. Associate Professor axon at cortex.rutgers.edu voice: 973-353-1080 x3261 fax: 973-353-1272 Center for Molecular and Behavioral Neuroscience Rutgers, The State University 197 University Avenue Newark, NJ 07102 Graduate program information: http://www.bns.rutgers.edu/ Additional information and reprints: http://www.cmbn.rutgers.edu/~rmsiegel