From oby at cs.tu-berlin.de Thu Nov 1 07:41:17 2001 From: oby at cs.tu-berlin.de (Klaus Obermayer) Date: Thu, 1 Nov 2001 13:41:17 +0100 (MET) Subject: tenured faculty position Message-ID: <200111011241.fA1CfH725557@fiesta.cs.tu-berlin.de> Dear Connectionists, below please find an announcement for an open faculty position (tenured) in the area of artificial intelligence in our department (EE and CS) at the Technical Universoity of Berlin, which could be of interest. Cheers Klaus =========================================================================== FACULTY POSITION IN ARTIFICIAL INTELLIGENCE Faculty IV, Technical University of Berlin, Berlin, Germany The Department for Electrical Engineering and Computer Science solicits application for a tenured faculty position (salary level C3) in the area of artificial intelligence. Potential areas of research include (but are not restricted to) machine learning, automatic deduction and problem solving, planning and decision making, knowledge representation, scene analysis, and speech processing. The candidate should be open to interdisciplinary research projects which combine computer science and engineering with the cognitive sciences. The successful candidate is expected to join the department's undergraduate teaching programs, as well as the graduate education in the area of Artificial Intelligence. The successful candidate is expected to teach courses in German after two years. Requirements: Ph.D. degree and Habilitation or equivalent achievements (cf. 100 BerlHG); research experience in the field of artificial intelligence; a strong publication record and teaching experience. Experience in the acquisition of research grants is desirable. Please send applications to: Chair of the Department of Electrical Engineering Computer Science Technical University of Berlin FR 5-1, Franklinstrasse 28/29 10587 Berlin, Germany email: fbv13 at cs.tu-berlin.de All applications received before November 30th, 2001, will be given full consideration. The Technical University of Berlin wants to increase the percentage of women on its faculty and strongly encourages applications from qualified individuals. Women will be preferred given equal qualifications. Handicapped persons will be preferred given equal qualifications. ========================================================================== 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/ From whitneytabor at yahoo.com Fri Nov 2 17:04:45 2001 From: whitneytabor at yahoo.com (Whitney Tabor) Date: Fri, 2 Nov 2001 14:04:45 -0800 (PST) Subject: PhD Studentships available at UConn Psychology Message-ID: <20011102220445.16650.qmail@web10201.mail.yahoo.com> ******************************************************************* GRADUATE TRAINING IN LANGUAGE AND COGNITION AT THE UNIVERSITY OF CONNECTICUT ******************************************************************* Opportunities abound at the University of Connecticut (UConn) for qualified students to pursue graduate studies in Language and Cognition leading to the Ph.D. in Experimental Psychology. At least 4 PhD studentships will begin in Fall, 2002. Speech perception and production, the reading process and the development of reading skills, sentence processing, and ecological studies of perception and action have long been areas of research strength at UConn within Psychology and related departments. A unique synthesis is now occurring between the ecological work, which has focused on dynamical models of human movement, and the language work, which uses closely related connectionist models to study language as action. An important element in the mix is Haskins Laboratories, an independent research lab located nearby in New Haven, which, for over 65 years, has sustained an environment of intellectual cross-pollination and has made many breakthroughs in research on speech and reading. See the Language and Cognition Program Web Page for more details: http://www.sp.uconn.edu/~ps300vc/LangandCog/langandcog.html For admission guidelines and to download application forms, see: http://www.sp.uconn.edu/~wwwpsyc/ and http://www.sp.uconn.edu/~wwwpsyc/GradAd.html To obtain a printed brochure and a set of application materials, write, telephone, fax, or email: Gina Belz, Department of Psychology, University of Connecticut, 406 Babbidge Road, Unit 1030, Storrs, CT 06269-1030 Important deadline: January 15: Graduate Applications due. Phone: (860) 486-3528 FAX: (860) 486-2760 E-Mail: futuregr at psych.psy.uconn.edu ******************************************************************* Description of the Program in Language and Cognition: The Program in Language and Cognition focuses on those aspects of language that make it a uniquely versatile vehicle for communication and thought. There is thus a strong focus on the dynamical aspects of language, including experimental studies of language processing, learning, and change at the phoneme, word, and sentence level, modeling of language processes using artificial neural (connectionist) networks and symbolic computational models, and mathematical analysis using dynamical systems theory and statistics. There is particular interest in an ecological approach, which emphasizes continual interaction between speaker/hearers and their environments. There is much interest in the biological basis of language, both in pursuit of innate endowment questions and in studies of neural mechanisms using state-of-the-art neuroimaging tools. The group has long conducted basic research on the reading process; some members of the group are also engaged in the translation of research findings to the classroom. The Program has close ties to the Center for the Study of Perception and Action (CESPA---http://ione.psy.uconn.edu/~cespaweb/), the Developmental and Behavioral Neuroscience Divisions in the Dept. of Psychology (http://www.sp.uconn.edu/~wwwpsyc/), the Linguistics Department (http://vm.uconn.edu/~wwwling/), and the Cognitive Science Focus (http://cogsci.uconn.edu/) at the University of Connecticut. In addition, Haskins Laboratories (http://www.haskins.yale.edu), located nearby in New Haven, provides a stimulating environment for research and training. The program prepares students for careers in research and teaching. A student's research activity begins immediately on entry to the program. In addition, three courses are typically taken each semester. A student's schedule also includes attendance at colloquia and informal weekly group meetings for discussion of problems in theory and research. Course work for the Ph.D. degree can often be completed in two-and-a-half to three years. Another year or two is needed to complete the dissertation. Applicants should have an excellent academic record. Research experience is helpful but not necessary. Applicants may have an undergraduate major in psychology, linguistics, computer science, mathematics, cognitive science, or other related fields of study. ***** CAROL FOWLER (http://www.sp.uconn.edu/~wwwpsyc/Faculty/Fowler/Fowler.html), Professor of Psychology. Dr. Fowler works on speech perception and production within the developing direct-realist framework. In addition, she has begun collaborative research on cross-person coordination and cooperation in language use. This is part of an effort to develop an ecological theory of language-that is, an understanding of how language is used in ordinary contexts in which speech occurs. Dr. Fowler is the Director of Haskins Laboratories. LEONARD KATZ (http://www.sp.uconn.edu/~wwwpsyc/Faculty/Katz/Katz.html), Professor of Psychology. Dr. Katz studies reading, focusing on the process of printed word recognition. Cross-language experiments are often used to reveal in which ways word recognition is shaped by a language's particular characteristics and in which ways it is more general. Languages studied include English, Hebrew, Russian, Serbo-Croatian and Turkish. In addition, functional Magnetic Resonance Imaging studies (carried out in conjunction with Haskins Laboratories and Yale Medical School) explore the brain mechanisms that support the word recognition process. Finally, behavioral experiments in English are used to study the effects on word recognition of the reader's lexicon (i.e., neighborhood factors) and reader strategies. JAY RUECKL (http://www.sp.uconn.edu/~wwwpsyc/Faculty/Rueckl/Rueckl.html), Associate Professor of Psychology. A primary goal of Dr. Rueckl's research is to use connectionist networks to forge a link between theories of implicit memory and models of word identification. His research focuses on the interaction of phonological, morphological, and semantic factors in the influence of implicit memory on work identification in reading, the role of perceptual detail (e.g. the characteristics of a speaker's voice) in visual and spoken word identification. In addition, together with his colleagues at Haskins Laboratories, Dr. Rueckl has recently begun to apply artificial neural network models to the investigation of the cognitive neuropsychology of reading. DONALD SHANKWEILER (http://www.sp.uconn.edu/~wwwpsyc/Faculty/Shankweiler/Shankweiler.html), Professor of Psychology. The broad aim of Dr. Shankweiler's research is to understand how the language apparatus, which is biologically specialized for speech, becomes adapted to reading and writing. In studies carried out in the 1970's, he and Dr. I. Y. Liberman discovered that there is an important association between children's abilities to analyze speech into its components (phonemes, syllables, and morphemes) and their progress in reading. Recent research has pursued the implications of this association for the operation of short-term verbal memory; for children who lack phonologically analytic skills, short-term memory function is also impaired. Dr. Shankweiler, with Stephen Crain and their students, have developed a model of the role of short-term memory in language comprehension. WHITNEY TABOR (http://www.sp.uconn.edu/~ps300vc/tabor.html), Assistant Professor of Psychology. Dr. Tabor's research focuses on the coexistence of structure and flexibility in complex systems. He uses artificial neural networks and dynamical systems theory to develop models of human language processing, learning, and change. He has worked on the role of semantic information in sentence processing, evidence for ungrammatical influences in sentence processing, attractor models of syntactic category structure, the learning of complex phrase structure grammars, and the evolution of grammatical categories over historical time. * * * * * AFFILIATED FACULTY CLAUDIA CARELLO, Professor of Psychology, Director of CESPA: Ecological study of human movement, printed word recognition in English, Korean, Serbo-Croatian. ROGER CHAFFIN, Professor of Psychology (Hartford): Semantic memory, memory for skilled performance. ELENA LEVY, Associate Professor of Psychology (Stamford): Language and gesture, language development. DIANE LILLO-MARTIN, Professor of Linguistics and Psychology: The structure of American Sign Language, its acquisition and processing, and the processes deaf people use to read. GEORGIJE LUKATELA, Visiting Professor: The phonological basis of printed word recognition. LETITIA NAIGLES, Associate Professor of Psychology: Language acquisition, word learning. KENNETH PUGH, Associate Professor, Yale University and Haskins Laboratories: Brain imaging studies of reading. WILLIAM SNYDER, Assistant Professor of Linguistics: Cross-linguistic studies of language acquisition; sentence processing. MICHAEL TURVEY, Professor of Psychology: Ecological study of human movement, the phonological basis of printed word recognition. ******************************************************************* UNIVERSITY OF CONNECTICUT LANGUAGE AND COGNITION PROGRAM GRADUATE TRAINING ANNOUNCEMENT For more information, write to: Claudia Carello Department of Psychology University of Connecticut 406 Babbidge Road, Unit 1020 Storrs, CT 06269-1020 Phone: (860) 486-3529 E-mail: CESPA1 at uconnvm.uconn.edu ******************************************************************* ===== Whitney Tabor (860) 486-4910 (office) Department of Psychology (860) 486-2760 (fax) University of Connecticut (860) 486-6080 (lab) Storrs, CT 06269-1020 tabor at uconnvm.uconn.edu USA WAB Room 124 (office) http://www.sp.uconn.edu/~wwwpsyc/Faculty/Tabor/Tabor.html __________________________________________________ Do You Yahoo!? Find a job, post your resume. http://careers.yahoo.com From erik at bbf.uia.ac.be Mon Nov 5 11:43:50 2001 From: erik at bbf.uia.ac.be (Erik De Schutter) Date: Mon, 5 Nov 2001 17:43:50 +0100 Subject: CNS*2002 announcement and new paper submission procedure Message-ID: Eleventh Annual Computational Neuroscience Meeting CNS*2002 July 21 - July 25, 2002 Chicago, Illinois USA http://www.neuroinf.org/CNS.shtml CNS*2002 will be held in Chicago from Sunday, July 21, 2002 to Thursday, July 25 in the Congress Plaza Hotel & Convention Center. This is a historic hotel located on Lake Michigan in downtown Chicago. General sessions will be Sunday-Wednesday, Thursday will be a full day of workshops. The conference dinner will be Wednesday night, followed by the rock-n-roll jam session. INVITED SPEAKERS: Ad Aertsen (Albert-Ludwigs-University, Germany) Leah Keshet (University British Columbia, Canada) Alex Thomson (University College London, UK) PAPER SUBMISSIONS Papers will be submitted through a preprint server run by Elsevier and linked from the CNS site. Authors will have the option at the time of submission of making their preprint publicly available (which qualifies it for inclusion in the Proceedings, if accepted), or keeping it private (no inclusion in the Proceedings). Submissions will be reviewed in the usual way (independent of their public/private status), and the small number of papers not accepted will be removed from the preprint site. Papers that are accepted will be published in both the journal Neurocomputing and in a separate Proceedings volume. Only papers submitted before the January deadline will be accepted, but authors will be able to edit and improve their submissions continuously till the Proceedings are finalized. We will encourage the community to access this server before the actual meeting and to engage in discussions about papers. In this way, discussions and feedback both before and during the meeting can lead to improved quality of the published paper. It will be possible to use the paper on the preprint server directly as Proceedings submission in October. To facilitate the transition to this new submission procedure we will accept in 2002 both submission old style (= abstract + summary) and as real papers (proper length for the Proceedings). Submission deadline: January 25, 2002. ORGANIZING COMMITTEE: Program chair: Erik De Schutter (University of Antwerp, Belgium) Local organizer: Philip Ulinski (University of Chicago, USA) Workshop organizer: Maneesh Sahani (Gatsby Computational Neuroscience Unit, UK) Government Liaison: Dennis Glanzman (NIMH/NIH, USA) Program Committee: Upinder Bhalla (National Centre for Biological Sciences, India) Avrama Blackwell (George Mason University, USA) Victoria Booth (New Jersey Institute of Technology, USA) Alain Destexhe (CNRS Gif-sur-Yvette, France) John Hertz (Nordita, Denmark) David Horn (University of Tel Aviv, Israel) Barry Richmond (NIMH, USA) Steven Schiff (George Mason University, USA) Todd Troyer (University of Maryland, USA) From bbs at bbsonline.org Mon Nov 5 15:17:15 2001 From: bbs at bbsonline.org (Stevan Harnad - Behavioral & Brain Sciences (Editor)) Date: Mon, 05 Nov 2001 15:17:15 -0500 Subject: Pylyshyn: Mental Imagery: BBS Call for Commentators Message-ID: Below is the abstract of a forthcoming BBS target article Mental Imagery: In search of a theory by Zenon W. Pylyshyn http://www.bbsonline.org/Preprints/Pylyshyn/Referees/ This article has been accepted for publication 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. Commentators must be BBS Associates or nominated by a BBS Associate. To be considered as a commentator for this article, to suggest other appropriate commentators, or for information about how to become a BBS Associate, please reply by EMAIL within three (3) weeks to: calls at bbsonline.org The Calls are sent to 10,000 BBS Associates, so there is no expectation (indeed, it would be calamitous) that each recipient should comment on every occasion! Hence there is no need to reply except if you wish to comment, or to nominate someone to comment. If you are not a BBS Associate, please approach a current BBS Associate (there are currently over 10,000 worldwide) who is familiar with your work to nominate you. All past BBS authors, referees and commentators are eligible to become BBS Associates. A full electronic list of current BBS Associates is available at this location to help you select a name: http://www.bbsonline.org/Instructions/assoclist.html If no current BBS Associate knows your work, please send us your Curriculum Vitae and BBS will circulate it to appropriate Associates to ask whether they would be prepared to nominate you. (In the meantime, your name, address and email address will be entered into our database as an unaffiliated investigator.) To help us put together a balanced list of commentators, please give some indication of the aspects of the topic on which you would bring your areas of expertise to bear if you were selected as a commentator. To help you decide whether you would be an appropriate commentator for this article, an electronic draft is retrievable from the online BBSPrints Archive, at the URL that follows the abstract below. _____________________________________________________________ Mental Imagery: In search of a theory Zenon W. Pylyshyn Rutgers Center for Cognitive Science New Brunswick, New Jersey ABSTRACT: It is generally accepted that there is something special about reasoning that uses mental images. The question of how it is special, however, has never been satisfactorily spelled out, despite over thirty years of research in the post-behaviorist tradition. This article considers some of the general motivation for the assumption that entertaining mental images involves inspecting a picture-like object. It sets out a distinction between phenomena attributable to the nature of mind, to what is called the cognitive architecture, and ones that are attributable to tacit knowledge used to simulate what would happen in a visual situation. With this distinction in mind the paper then considers in detail the widely held assumption that in some important sense images are spatially displayed or are depictive, and that examining images uses the same mechanisms that are deployed in visual perception. I argue that the assumption of the spatial or depictive nature of images is only explanatory if taken literally, as a claim about how images are physically instantiated in the brain, and that the literal view fails for a number of empirical reasons e.g., because of the cognitive penetrability of the phenomena cited in its favor. Similarly, while it is arguably the case that imagery and vision involve some of the same mechanisms, this tells us very little about the nature of mental imagery and does not support claims about the pictorial nature of mental images. Finally I consider whether recent neuroscience evidence clarifies the debate over the nature of mental images. I claim that when such questions as whether images are depictive or spatial are formulated more clearly, the evidence does not provide support for the picture-theory over a symbol structure theory of mental imagery. Even if all the empirical claims turned out to be true, the view that many people take them to support, that mental images are literally spatial, remain incompatible with what is known about how images function in thought. We are then left with the provisional counterintuitive conclusion that the available evidence does not support rejection of what I call the "null hypothesis"; viz., that reasoning with mental images involves the same form of representation and the same processes as that of reasoning in general, except that the content or subject matter of thoughts experienced as images includes information about how things would look. http://www.bbsonline.org/Preprints/Pylyshyn/Referees/ ___________________________________________________________ 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 the article. We will then let you know whether it was possible to include your name on the final formal list of invitees. _______________________________________________________________________ *** SUPPLEMENTARY ANNOUNCEMENTS *** (1) The authors of scientific articles are not paid money for their refereed research papers; they give them away. What they want is to reach all interested researchers worldwide, so as to maximize the potential research impact of their findings. Subscription/Site-License/Pay-Per-View costs are accordingly access-barriers, and hence impact-barriers for this give-away research literature. There is now a way to free the entire refereed journal literature, for everyone, everywhere, immediately, by mounting interoperable university eprint archives, and self-archiving all refereed research papers in them. Please see: http://www.eprints.org http://www.openarchives.org/ http://www.dlib.org/dlib/december99/12harnad.html --------------------------------------------------------------------- (2) All authors in the biobehavioral and cognitive sciences are strongly encouraged to self-archive all their papers in their own institution's Eprint Archives or in CogPrints, the Eprint Archive for the biobehavioral and cognitive sciences: http://cogprints.soton.ac.uk/ It is extremely simple to self-archive and will make all of our papers available to all of us everywhere, at no cost to anyone, forever. Authors of BBS papers wishing to archive their already published BBS Target Articles should submit it to BBSPrints Archive. Information about the archiving of BBS' entire backcatalogue will be sent to you in the near future. Meantime please see: http://www.bbsonline.org/help/ and http://www.bbsonline.org/Instructions/ --------------------------------------------------------------------- (3) Call for Book Nominations for BBS Multiple Book Review In the past, Behavioral and Brain Sciences (BBS) 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!). *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* Please note: Your email address has been added to our user database for Calls for Commentators, the reason you received this email. If you do not wish to receive further Calls, please feel free to change your mailshot status through your User Login link on the BBSPrints homepage, useing your username and password above: http://www.bbsonline.org/ For information about the mailshot, please see the help file at: http://www.bbsonline.org/help/node5.html#mailshot *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* From rsun at cecs.missouri.edu Mon Nov 5 15:29:55 2001 From: rsun at cecs.missouri.edu (rsun@cecs.missouri.edu) Date: Mon, 5 Nov 2001 14:29:55 -0600 Subject: Cognitive Systems Research 2 (3), 2001 Message-ID: <200111052029.fA5KTtr09929@ari1.cecs.missouri.edu> The new issue of Cognitive Systems Research: --------------------------------------------------------- Table of Contents for Cognitive Systems Research Volume 2, Issue 3, 2001 William Frawley and Raoul N. Smith A processing theory of alexithymia [Abstract] [Full text] (PDF 191.9 Kb) 189-206 Jacqueline P. Leighton and Michael R.W. Dawson A parallel distributed processing model of Wason's selection task 207-231 [Abstract] [Full text] (PDF 320.9 Kb) Reza Farivar Review of The Mind within the Net: Models of Learning, Thinking, and Acting - Manfred Spitzer; MIT Press, Cambridge, MA, xi+359 pp; ISBN 0-262-19406-6 (PB+HC) 235-240 [Abstract] [Full text] (PDF 57.9 Kb) Jelle van Dijk and Gert-Jan Bleeker Review of A Universe of Consciousness. How Matter becomes Imagination - G.M. Edelman & G. Tononi; Basic Books, New York, 2000; 266 pp; ISBN 0465013767 241-244 [Abstract] [Full text] (PDF 48.4 Kb) * Full text files can be viewed and printed using the Adobe Acrobat Reader. Download the papers from the Web site: http://www.cecs.missouri.edu/~rsun/journal.html http://www.elsevier.nl/locate/cogsys http://www.elsevier.com/locate/cogsys Copyright 2001, Elsevier Science, All rights reserved. =========================================================================== Prof. Ron Sun http://www.cecs.missouri.edu/~rsun CECS Department phone: (573) 884-7662 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 http://www.elsevier.com/locate/cogsys =========================================================================== From winfried.ilg at tuebingen.mpg.de Mon Nov 5 07:12:51 2001 From: winfried.ilg at tuebingen.mpg.de (Winfried Ilg) Date: Mon, 05 Nov 2001 13:12:51 +0100 Subject: job announcement Message-ID: PhD / POSTDOC POSITIONS FOR THEORETICAL NEUROSCIENCE ==================================================== The Laboratory for Action Representation and Learning at the Department of Cognitive Neurology and the Max-Planck Institute for Biological Cybernetics in Tuebingen (Germany) offers a Postdoc or PhD position for a neuroscientist or computer scientist with interest in neural modeling. Aim of the project is the development and evaluation of models for the neural mechanisms of the recognition and planning of complex movements. Dependent on her / his interest, the successful candidate will also have the opportunity to take part in psychophysical, electrophysiological and FMRI experiments for testing neural theories of motion recognition and learning of movements by imitation. Tuebingen offers an excellent environment for experimental and theoretical neuroscience. In addition, PhD students can acquire a PhD degree in "Neuroscience" in an interdiciplinary graduate program. The experimental side of the project will be realized in close collaboration with experimentalists at the Max-Planck-Institute, the Department for Brain and Cogniutive Science, M.I.T., and Harvard Medical School (USA). The ideal candidate should have a reasonable computational background, and at least some basic training in neuroscience. Payment is, dependent on prior experience, according to BAT II for 3 years (extendable). Starting date should be as soon as possible. The position is funded by the German Volkswagen Foundation. For further information please contact: Dr. Martin Giese Laboratory for Action Representation and Learning Max-Planck-Institut for Biological Cybernetics Spemannstr. 34 D-72076 Tuebingen GERMANY Email: martin.giese at tuebingen.mpg.de Applicants are asked to submit their CV, a bibliography, and the names of two references. Applications and references should be sent by email to the same address. -------------------------------------------------------- Dr. Martin Giese Laboratory for Action Representation and Learning Max-Planck-Institut for Biological Cybernetics Spemannstr. 34 D-72076 Tuebingen GERMANY Email: martin.giese at tuebingen.mpg.de -------------------------------------------------------- From jose at psychology.rutgers.edu Mon Nov 5 07:02:09 2001 From: jose at psychology.rutgers.edu (stephen jose hanson) Date: Mon, 05 Nov 2001 07:02:09 -0500 Subject: FACULTY POSITION--PSYCHOLOGY DEPARTMENT --RUTGERS-Newark Message-ID: <3BE67FC1.BD7C76AC@psychology.rutgers.edu> RUTGERS UNIVERSITY-Newark Campus. The Department of Psychology anticipates making one tenure track , Assistant Professor level appointment in area of COGNITIVE SCIENCE. In particular we are seeking individuals in one any of the THREE following areas: LEARNING (Cognitive Modeling), COMPUTATIONAL NEUROSCIENCE or SOCIAL-COGNITION (interests in neuroimaging in any of these areas would also be a plus, since the Department in conjunction with UMDNJ has recently acquired a 3T Neuroimaging Center (see http://www.psych.rutgers.edu/fmri). Candidates must be effective teachers at the graduate and undergraduate levels. Review of applications begin JANUARY 30th, 2002, pending final budgetary approval from the administration. Rutgers University is an equal opportunity/affirmative action employer. Qualified women and minority candidates are encouraged to apply. Please send a CV, a statement of current and future research interests, and three letters of recommendation to COGNITIVE SCIENCE SEARCH COMMITTEE, Department of Psychology, Rutgers University, Newark, NJ 07102. Email enquires can be made to cogsci at psychology.rutgers.edu. Also see, http://www.psych.rutgers.edu. From tom at mbfys.kun.nl Wed Nov 7 05:12:03 2001 From: tom at mbfys.kun.nl (Tom Heskes) Date: Wed, 07 Nov 2001 11:12:03 +0100 Subject: opening at SNN Nijmegen Message-ID: <3BE908F3.81F40CFD@mbfys.kun.nl> Postdoc or PhD position at SNN Nijmegen ======================================= SNN at the University of Nijmegen, The Netherlands, offers a Postdoc or PhD position for a computer scientist, statistician or physicist with interest in machine learning, (dynamical) Bayesian networks and affiliated techniques. The candidate will be assigned to work on the STW project "Sales forecasting through aggregation". Within this project, our aim is to develop Bayesian methodology to handle and learn from a large amount of similar time series. This project is a collaboration with Eindhoven Technical University. From a postdoc, we expect a PhD in physics, mathematics or computer science and a solid background in machine learning and statistics. Excellent candidates interested in a PhD position can apply as well. SNN Nijmegen offers a stimulating research environment, with 10 researchers and PhD students working on theoretical and practical aspects of neural and Bayesian networks, machine learning, and computational neuroscience. We are part of the Department of Biophysics which is involved in experimental brain research. Work of our group has been commercialized successfully through the company SMART Research BV. More information on our research interests can be found at http://www.snn.kun.nl/nijmegen. The postdoc salary will be between Dfl. 5847 and Dfl. 7995 per month, depending on experience. The position is available for 2 years with possible extension to 4 years. The PhD position will be for 4 years with salary from Dfl. 3268 per month in the first year to Dfl. 4666 in the fourth. Interested candidates are asked to submit their CV and a list of publications by regular or e-mail to Tom Heskes SNN, University of Nijmegen Geert Grooteplein 21 6525 EZ Nijmegen The Netherlands tom at mbfys.kun.nl For further information, feel free to contact me at tom at mbfys.kun.nl or +31 24 3615039. From coenen at csl.sony.fr Wed Nov 7 23:55:07 2001 From: coenen at csl.sony.fr (Olivier Coenen) Date: Wed, 07 Nov 2001 20:55:07 -0800 Subject: Post-doctoral and Ph.D.student positions Message-ID: <3BEA102B.2A76EB48@csl.sony.fr> Post-doctoral and Ph.D. Student Positions available IN THEORETICAL AND COMPUTATIONAL NEUROSCIENCE Sony Computer Science Laboratory - Paris A post-doctoral research associate position and a Ph.D. student position are available immediately for theoretical and computational studies of sensorimotor integration and control. Highly motivated and creative individuals are sought for a period of 1 1/2 year (Post-doctoral) and up to 3 years (Ph.D. student) to join our research efforts. The interested candidates will be building mathematical and computational models of neural processing, with a particular emphasis on representation and learning in the cerebellum. Research interests include unsupervised learning, information theory and probabilistic approaches to representation and learning in networks of (spiking) neurons, reinforcement learning and robotic learning and control. The candidates will have the opportunity to work across disciplines and levels of investigation, from analytical models and detailed compartmental models of neurons to the creation of a unique computing platform. The models will be informed and constrained by neurobiological and psychological data. Current collaborations will give the candidates the possibility to interact closely with theoreticians, experimental neurophysiologists, and computer and hardware scientists at universities in Paris and abroad. The Sony Computer Science Laboratory is a fundamental research center located in the Quartier Latin, in the center of Paris. It is next door to the renown Ecole Normale Superieure and only a few steps away from a large number of universities in Paris (Sorbonne, Jussieu, College de France, etc.). The laboratory has interests in cognition, music, language, and robotics. Candidates should have a solid analytical background and a keen interest in neuroscience. Experience in machine learning algorithms and in computational models is desirable. Excellent computer programming skills (Matlab, C or C++) are essential. Applicants should send in plain text or pdf format a curriculum vitae (CV) with a list of publications (PhD applicants should include details of course work and grades), a statement of research interests, and names, addresses, emails and phone numbers of at least three referees to coenen at csl.sony.fr (email preferred) or to: Olivier J.-M. D. Coenen, Ph.D. Sony Computer Science Laboratory - Paris 6, rue Amyot 75005, Paris France Phone: +33 1 44 08 05 04 Fax: +33 1 45 87 87 50 http://www.csl.sony.fr (Interested candidates may also get in touch at the Society for Neuroscience meeting in San Diego). From dimi at ci.tuwien.ac.at Wed Nov 7 10:05:42 2001 From: dimi at ci.tuwien.ac.at (Evgenia Dimitriadou) Date: Wed, 7 Nov 2001 16:05:42 +0100 (CET) Subject: CI BibTeX Collection -- Update Message-ID: The following volumes have been added to the collection of BibTeX files maintained by the Vienna Center for Computational Intelligence: IEEE Transactions on Evolutionary Computation, Volumes 5/1-5/5 IEEE Transactions on Fuzzy Systems, Volumes 9/1-9/4 IEEE Transactions on Neural Networks, Volumes 12/1-12/5 Machine Learning, Volumes 43/3-46/3 Neural Computation, Volumes 13/2-13/11 Neural Networks, Volumes 14/4-14/9 Neural Processing Letters, Volumes 13/2-14/2 Most files have been converted automatically from various source formats, please report any bugs you find. The complete collection can be downloaded from http://www.ci.tuwien.ac.at/docs/ci/bibtex_collection.html ftp://ftp.ci.tuwien.ac.at/pub/texmf/bibtex/ Best, Vivi ************************************************************************ * Evgenia Dimitriadou * ************************************************************************ * Institut fuer Statistik * Tel: (+43 1) 58801 10773 * * Technische Universitaet Wien * Fax: (+43 1) 58801 10798 * * Wiedner Hauptstr. 8-10/1071 * Evgenia.Dimitriadou at ci.tuwien.ac.at * * A-1040 Wien, Austria * http://www.ci.tuwien.ac.at/~dimi* ************************************************************************ From d.mareschal at bbk.ac.uk Thu Nov 8 04:44:58 2001 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Thu, 8 Nov 2001 10:44:58 +0100 Subject: Faculty position Message-ID: Readers of this list may be interested in the following job opening at Birkbeck College. We are looking for a Lecturer in Cognitive Neuropsychology of Language. However, candidates with related research interests will also be considered providing they can fulfill the teaching and administrative responsibilities and contribute to one of the areas of research strength within the School. Details of the position can be obtained from the following web page: http://www.psyc.bbk.ac.uk/announce/index.html In addition, informal enquires may be made to: Dr Simon Green, Head of School of Psychology: email s.green at bbk.ac.uk Or Professor Mark Johnson, School of Psychology: email mark.johnson at psychology.bbk.ac.uk Further information is also on the School's web site: http://www.psyc.bbk.ac.uk ================================================= Dr. Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 (0)20 7631-6582/6323 reception: 6207 fax +44 (0)20 7631-6312 http://www.psyc.bbk.ac.uk/staff/dm.html ================================================= From crocker at CoLi.Uni-SB.DE Fri Nov 9 09:24:29 2001 From: crocker at CoLi.Uni-SB.DE (Matthew Crocker) Date: Fri, 9 Nov 2001 15:24:29 +0100 Subject: PhD Studentships: Saarbruecken-Edinburgh Message-ID: <7C6EF97C-D51D-11D5-A06B-0003930AC5B0@coli.uni-sb.de> Saarland University is pleased to announce the availability of three doctoral scholarships within the recently established European Post-Graduate College "Language Technology and Cognitive Systems" Saarbruecken - Edinburgh starting in April 1st, 2002. Each scholarship will be funded for two years (extendable to three years). Doctoral degrees may be obtained in computational linguistics, phonetics, and informatics (computer science), from Saarland University. The European Post-Graduate College has been established in cooperation between Saarland University and the University of Edinburgh (Division of Informatics) - two leading institutions in the fields of Computational Linguistics, Artificial Intelligence and Cognitive Science who are collaborating in offering a joint post-graduate education programme. The cooperation includes * a six to twelve months research stay in Edinburgh * joint supervision of dissertations by lecturers from Saarbruecken and Edinburgh * an intensive research exchange programme between Saarbruecken and Edinburgh (including, for example, an annual two-week forum attended by college members and lecturers from both centres) The college focuses on the computational and cognitive foundations of human language processing, particularly emphasising the following research areas: * inference and reasoning * knowledge representation, lexicon, and ontology * data-intensive language models (including corpus-based and statistical language modelling) * dialogue and language generation (computational and cognitive models) * language understanding Lecturers in Saarbruecken are M. Pinkal, H. Uszkoreit (computational linguistics), W. Barry (phonetics), M. Crocker (psycholinguistics), M. Kohlhase, J. Siekmann, G. Smolka, W. Wahlster (informatics/AI). In Edinburgh, lecturers include M. Fourman, E. Klein, A. Lascarides, C. Mellish, J. Moore, J. Oberlander, M. Osborne, M. Pickering, M. Steedman, P. Taylor, B. Webber, and C. Williams. The scholarship provides up to DM 2,870 per month. Additional compensation includes family allowance (where applicable), travel funding, and an additional monthly allowance of approximately DM 1,410 for the stay in Edinburgh. Applicants should hold a strong university degree in one of the relevant areas, preferably at the Masters level (equivalent to German Diplom) and should not be more than 28 years of age. Female scientists and international students are particularly encouraged to apply. Applications should include: 1. a curriculum vitae (including a list of publications, where possible) 2. a sample of written work (e.g. research paper, or dissertation, preferably in English) 3. copies of high school and university degree certificates 4. two references (to be sent directly to the college speaker) 5. an informal cover letter specifying interests, previous knowledge and activities in any of the relevant research areas. The letter should indicate the area in which the dissertation is to be conducted (computational linguistics, phonetics, or informatics/AI): where possible, it should include a brief outline of research interests to be pursued within the scholarship. Applications should be sent (hardcopy format strongly preferred) to the speaker of the college (see address below). Closing date for applications is Dec 14th, 2001. Prof. Dr. Matthew Crocker (Speaker) Department of Computational Linguistics Saarland University P.O. Box 15 11 50 D-66041 Saarbruecken Tel: +49 (0)681 302-6560 E-mail: egk-admin at coli.uni-sb.de Fax: +49 (0)681 302-6561 Internet: http://www.coli.uni-sb.de/egk From doya at atr.co.jp Sat Nov 10 01:35:15 2001 From: doya at atr.co.jp (Kenji Doya) Date: Sat, 10 Nov 2001 15:35:15 +0900 Subject: Research positions: computational neuroscience and robotics Message-ID: <20011110063517.16167@mwd.biglobe.ne.jp> ---- Kenji Doya ATR Human Information Science Laboratories; CREST, JST 2-2-2 Hikaridai, Seika, Soraku, Kyoto 619-0288, Japan Phone:+81-774-95-1251; Fax:+81-774-95-1259 http://www.atr.co.jp/his/~doya Post-doctoral Research Positions Computational Neuroscience and Robotics Metalearning and Neuromodulation "Creating the Brain", CREST, JST http://www.atr.co.jp/his/nip/crest/ Post-doctoral positions are available immediately for the following research subjects: 1) Metalearning Models of Neuromodulators: The goal of the research is to build a theory of the functions and the dynamics of neuromodulators, such as dopamine, serotonin, and norepinephrine. The candidate should build computational models based on the theory of metalearning, which can be tested through collaborations with experimental laboratories. 2) Cyber Rodent Project: We are building a multi-agent experimental platform for the studies of learning, metalearning, communication, and evolution. The candidate will develop learning and control algorithms for foraging, nesting, and gene exchanges by small mobile robots. Candidates should have a strong background in theoretical and/or experimental sciences, including neurobiology, psychology, computer science, robotics, physics and mathematics. Competitive salaries and benefits are provided by JST (Japan Science and Technology Corporation). The laboratory is located at ATR International in Kyoto, where people from diverse origins and backgrounds get together for basic research on human cognition and telecommunication. Applicants should send a CV, a statement of research interests, and recent reprints and/or preprints by December 15th, 2001 to Kenji Doya ATR Human Information Science Laboratories 2-2-2 Hikaridai, Seika, Soraku Kyoto 619-0288, Japan For more information, please contact nip-info at his.atr.co.jp or visit our web pages at http://www.atr.co.jp/his/nip/crest/ ---- Kenji Doya ATR Human Information Science Laboratories; CREST, JST 2-2-2 Hikaridai, Seika, Soraku, Kyoto 619-0288, Japan Phone:+81-774-95-1251; Fax:+81-774-95-1259 http://www.atr.co.jp/his/~doya From Patrick.DeMaziere at antwerpen.be Mon Nov 12 09:43:57 2001 From: Patrick.DeMaziere at antwerpen.be (Patrick De Maziere) Date: Mon, 12 Nov 2001 15:43:57 +0100 Subject: Postdoctoral position Message-ID: <3BEFE02D.5C91E795@neuro.kuleuven.ac.be> MR RESEARCH CENTRE Department of Radiology University Hospital, Katholieke Universiteit Leuven Leuven (Belgium) Postdoctoral position The Magnetic Resonance (MR) Research Centre of the Department of Radiology and the Faculty of Medicine of the Katholieke Universiteit Leuven, Belgium has a vacant position for a physicist or (bio)engineer (preferably postdoc) on a European Project (Fifth Framework) on Functional Magnetic Resonance (fMRI) in the human and in the monkey. The research is a collaboration with the Laboratory of Neurophysiology of the Faculty of Medicine (G.A. Orban, Coordinator) of the K.U.Leuven, INRIA (Sophia-Antipolis, Fran ce) and the Technical University of Denmark (Lyngby). Functional MR imaging is a recent technique for the non-invasive visualisation of neuronal activity in the human and in animals. The MR Research Centre has specialized the last five years in both basic neuroscience and in clinical applications of fMRI. The task of the candidate is the development of new fMRI acquisition techniques and methods, to optimize the spatial and temporal resolution, as well as the S/N, using new data processing algorithms, developed by the partners of the project. A background and some experience in Magnetic Resonance (Imaging) is a prerequisite. The applicant will be offered a salary in accordance with official baremas, commensurate with his training and experience. The project ends september 2003. For more information, please contact Prof. Paul Van Hecke NMR, Radiology University Hospital Gasthuisberg B-3000 Leuven Belgium Tel: +32 16 34 37 80 e-mail: paul.vanhecke at med.kuleuven.ac.be From: esann To: "Connectionists at cs.cmu.edu" References: From bogus@does.not.exist.com Tue Nov 13 06:15:39 2001 From: bogus@does.not.exist.com () Date: Tue, 13 Nov 2001 12:15:39 +0100 Subject: ESANN proceedings available on-line Message-ID: ---------------------------------------------------- | | | ESANN proceedings available on-line | | | | European Symposium | | on Artificial Neural Networks | | | ---------------------------------------------------- Dear colleagues, We are pleased to announce that all proceedings of the past ESANN conferences (European Symposium on Artificial Neural Networks) are now available on-line (full papers) on the Web site of the conference (http://www.dice.ucl.ac.be/esann/); click on "Proceedings" in the left menu and then on the link in the "Electronic proceedings" section. This is a 100% free service to the scientific community intended to ensure the widest possible dissemination to the publications. Papers are available on the site in PDF format. Some abstracts are still missing, and some papers had to be scanned (instead of being converted from the original electronic files). We would appreciate if authors of papers could help us to complete this site. Notes to authors: ----------------- 1) We converted in PDF format all files provided by the authors; nevertheless most papers from the first ESANN conferences had to be scanned. If, as author, you still have an electronic version of a paper available on the site as scanned version, please send it by e-mail (esann at dice.ucl.ac.be) and we will replace the scanned document by your electronic version (Postscript or PDF format). 2) If, as author, you have an abstract which is not yet available on the site, please send it by e-mail (esann at dice.ucl.ac.be). In both cases, we would appreciate if you could include in the "Subject" field of your e-mail the number of your paper; this number may be found right above the title of your paper, in each of the ESANN proceedings lists. 3) You are free to download, copy and distribute any paper contained in these pages, provided that you keep the reference of the paper that has been added as header to each page. If you maintain your own Web site with an electronic version of your ESANN paper(s), please only use the version available on the ESANN site; having the reference added as header will help the researchers who download your papers to cite them in their own publications. Thank you in advance for your help! Sincerely yours, The ESANN organizing committee. ======================================================== ESANN - European Symposium on Artificial Neural Networks http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews,... Michel Verleysen Univ. Cath. de Louvain - Microelectronics Laboratory 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at dice.ucl.ac.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at dice.ucl.ac.be ======================================================== From phkywong at ust.hk Tue Nov 13 06:28:49 2001 From: phkywong at ust.hk (K. Y. Michael Wong) Date: Tue, 13 Nov 2001 19:28:49 +0800 (HKT) Subject: Postdoc Position Announcement Message-ID: Postdoc Position Announcement There is an opening for a one-year postdoctoral research associateship in my research group on the application of many-body physics in information processing. The work involves the use of many-body techniques in the dynamics and statics of information processing, such as learning, parameter estimation, error-correcting codes and data-mining. Potential candidates should have strong mathematical and computational skills. Background in statistical physics, many-body physics, or statistics will be useful. The salary ranges from HKD18,000 to HKD20,000 per month. If you are interested in the position, please send a full CV and publication list, together with the names of three referees, either by postage, e-mail or fax. The correspondence is: Dr. K. Y. M. Wong, Department of Physics, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong. E-mail: phkywong at ust.hk Fax: +852-2358 1652 Phone: +852-2358 7480 From cindy at cns.bu.edu Tue Nov 13 10:24:27 2001 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Tue, 13 Nov 2001 10:24:27 -0500 Subject: Neural Networks 14(10) Message-ID: <200111131524.KAA28587@retina.bu.edu> NEURAL NETWORKS 14(10) Contents - Volume 14, Number 10 - 2001 ------------------------------------------------------------------ CONTRIBUTED ARTICLES: ***** Psychology and Cognitive Science ***** Connectionist inference models Antony Browne and Ron Sun ***** Neuroscience and Neuropsychology ***** Analysis of the frequency response of the saccadic circuit: Numerical simulations Mark E. Jackson, Oleg Litvak, and James W. Gnadt ***** Mathematical and Computational Analysis ***** Unified stabilization approach to principal and minor components extraction algorithms Tianping Chen and Shun-ichi Amari Improvement of generalization ability for identifying dynamic systems by using universal learning networks Kotaro Hirasawa, Sung-ho Kim, Jinglu Hu, Junichi Murata, Min Han, and Chunzhi Jin Self-organization in the one-dimensional SOM with a decreasing neighborhood John A. Flanagan Upper bound of the expected training error of neural network regression for a Gaussian noise sequence Katsuyuki Hagiwara, Taichi Hayasaka, Naohiro Toda, Shiro Usui, and Kazuhiro Kuno The POP learning algorithms: Reducing work in identifying fuzzy rules C. Quek and R.W. Zhou ***** Engineering & Design ***** Oriented principal component analysis for large margin classifiers Sergio Bermejo and Joan Cabestany ***** Letters to the Editor ***** A remark on "On stability of nonlinear continuous-time neural networks with delays" Yuming Chen On using the Poincare polynomial for calculating the V-C dimension of neural networks Michael Schmitt Response: On using the Poincare polynomial for calculating the V-C dimension of neural networks Martha A. Carter and Mark E. Oxley ***** Erratum ***** Evaluating the Vapnik-Chervonenkis dimension of artificial neural networks using the Poincare polynomial (Neural Networks, 1999, 12, 403-408) Martha A. Carter and Mark E. Oxley ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 (regular) SEK 660 (regular) Y 13,000 (regular) Neural Networks (plus 2,000 enrollment fee) $20 (student) SEK 460 (student) Y 11,000 (student) (plus 2,000 enrollment fee) ----------------------------------------------------------------------------- membership without $30 SEK 200 not available to Neural Networks non-students (subscribe through another society) Y 5,000 (student) (plus 2,000 enrollment fee) ----------------------------------------------------------------------------- Name: _____________________________________ Title: _____________________________________ Address: _____________________________________ _____________________________________ _____________________________________ Phone: _____________________________________ Fax: _____________________________________ Email: _____________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number ____________________________ expiration date ________________________ INNS Membership 19 Mantua Road Mount Royal NJ 08061 USA 856 423 0162 (phone) 856 423 3420 (fax) innshq at talley.com http://www.inns.org ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership c/o Professor Takashi Nagano Faculty of Engineering Hosei University 3-7-2, Kajinocho, Koganei-shi Tokyo 184-8584 Japan 81 42 387 6350 (phone and fax) jnns at k.hosei.ac.jp http://jnns.inf.eng.tamagawa.ac.jp/home-j.html ----------------------------------------------------------------- From bernabe at imse.cnm.es Thu Nov 15 06:58:20 2001 From: bernabe at imse.cnm.es (Bernabe Linares B.) Date: Thu, 15 Nov 2001 12:58:20 +0100 (MET) Subject: Call for Papers on NN Hardware Message-ID: <200111151158.MAA03377@cnm30.imse.cnm.es> CALL FOR PAPERS: IEEE TRANS. ON NEURAL NETWORKS Special Issue on NEURAL NETWORKS HARDWARE IMPLEMENTATIONS This is to announce a forthcomming Special issue on NN hardware implementations in the IEEE Trans. on Neural Networks. Paper submission deadline is September 15th, 2002. Issue will be published September 2003. The details of the "Call for Papers" are available at: http://www.imse.cnm.es/~bernabe/CFPNN.html or in PDF format: http://www.imse.cnm.es/~bernabe/CFPNN.pdf Please announce and distribute to potential authors. ------------------------------------------------------------------------- Bernabe Linares-Barranco, PhD Tenured Scientist (Cientifico Titular) CSIC Instituto Microelectronica Sevilla (IMSE) Phone: 34-95-505-6670/66 National Microelectronics Center, CNM-CSIC Fax: 34-95-505-6686 Ed. CICA, Av. Reina Mercedes s/n E-mail: bernabe at imse.cnm.es 41012 Sevilla, SPAIN URL: http://www.imse.cnm.es/~bernabe ------------------------------------------------------------------------- From abrowne at lgu.ac.uk Thu Nov 15 06:15:23 2001 From: abrowne at lgu.ac.uk (Tony Browne) Date: Thu, 15 Nov 2001 11:15:23 +0000 (GMT Standard Time) Subject: Extrapolation preprint Message-ID: Apologies if you receive this posting more than once. A preprint is available for download, of the paper 'Representation and Extrapolation in Multi-Layer Perceptrons' by Antony Browne (to appear in `Neural Computation'). 20 Pages, 27 References. Abstract: To give an adequate explanation of cognition and perform certain practical tasks connectionist systems must be able to extrapolate. This work has explored the relationship between input representation and extrapolation, using simulations of multi-layer perceptrons trained to model the identity function. It has been discovered that representation has a marked effect on extrapolation. Keywords: Extrapolation, distributed representation, localist representation, identity task, circular convolution. Download Instructions: Go to http://www.lgu.ac.uk/~abrowne/abrowne.htm and scroll down to the section 'Downloadable Technical Reports and Preprints'. Click on the file to download (in zipped Postscript or PDF format). Comments Welcome If you have problems downloading, please e-mail me. Tony Browne ======================================================= Dr. Antony Browne Reader in Intelligent Systems School of Computing, Information Systems & Mathematics London Guildhall University 100 Minories, London EC3 1JY, UK E-mail: abrowne at lgu.ac.uk http://www.lgu.ac.uk/~abrowne/abrowne.htm Tel: (+44) 0207 320 1708 or 1700 Fax: (+44) 0207 320 1717 ======================================================= From angelo at soc.plym.ac.uk Fri Nov 16 09:39:11 2001 From: angelo at soc.plym.ac.uk (Angelo Cangelosi) Date: Fri, 16 Nov 2001 14:39:11 +0000 Subject: Book announcement: Simulating the Evolution of Language Message-ID: <3.0.6.32.20011116143911.0115e348@hebe.soc.plym.ac.uk> New book announcement: Cangelosi A. & Parisi D. (Eds.) (2001). Simulating the Evolution of Language. London: Springer. http://www.tech.plym.ac.uk/soc/staff/angelo/book2001-TOC.html SUMMARY This volume provides a comprehensive survey of the computational models and methodologies used for studying the origin and evolution of language and communication. With contributions from the most influential figures in the field, Simulating the Evolution of Language presents and summarises current computational approaches to language evolution and highlights new lines of development. Among the main discussion points are: Analysis of emerging linguistic behaviours and structures Demonstration of the strict interaction and interdependence between language and other non-linguistic abilities Direct comparisons between simulation studies and empirical research Essential reading for researchers and students in the areas of evolutionary and adaptive systems, language evolution, modelling and linguistics, it will also be of particular interest to computer scientists working on multi-agent systems, robotics and internet agents. TABLE OF CONTENT PART I INTRODUCTION Chapter 1: Computer Simulation: A New Scientific Approach to the Study of Language Evolution Angelo Cangelosi & Domenico Parisi Chapter 2: An Introduction to Methods for Simulating the Evolution of Language Huck Turner PART II EVOLUTION OF SIGNALING SYSTEMS Chapter 3: Adaptive Factors in the Evolution of Signaling Systems Jason Noble, Ezequiel Di Paolo, Seth Bullock Chapter 4: Evolving Sound Systems Bart De Boer Chapter 5: The Evolution of Dialect Diversity Daniel Livingstone PART III EVOLUTION OF SYNTAX Chapter 6: The Emergence of Linguistic Structure: An Overview of the Iterated Learning Model Simon Kirby & Jim Hurford Chapter 7: Population Dynamics of Grammar Acquisition Natalia L. Komarova & Martin A. Nowak Chapter 8: The role of sequential learning in language evolution: Computational and experimental studies Morten Christiansen, Michelle R. Ellefson, Christopher M. Conway & Rick A.C. Dale PART IV GROUNDING OF LANGUAGE Chapter 9: Symbol Grounding and the Symbolic Theft Hypothesis Angelo Cangelosi, Alberto Greco & Stevan Harnad Chapter 10: Grounding Symbols through Evolutionary Language Games Luc Steels PART V BEHAVIORAL AND NEURAL FACTORS Chapter 11: Grounding the Mirror System Hypothesis for the Evolution of the Language-ready Brain Michael Arbib Chapter 12: A Unified Simulation Scenario for Language Development, Evolution, and Historical Change Domenico Parisi & Angelo Cangelosi PART VI BEHAVIORAL AND NEURAL FACTORS Chapter 13: Auto-Organisation and Emergence of Shared Language Structure Edwin Hutchins & Brian Hazlehurst Chapter 14: The constructive approach to the dynamical view of language Takashi Hashimoto ( PART VII CONCLUSION Chapter 15: Some Facts about Primate (including Human) Communication and Social Learning Michael Tomasello -------------------- Angelo Cangelosi, PhD ----------------------- Senior Lecturer, Centre for Neural and Adaptive Systems School of Computing, University of Plymouth 9 Kirkby Place Plymouth PL4 8AA (UK) E-mail: a.cangelosi at plymouth.ac.uk http://www.tech.plym.ac.uk/soc/staff/angelo (tel) +44 1752 232559 (fax) +44 1752 232540 From jfeldman at ICSI.Berkeley.EDU Fri Nov 16 19:20:11 2001 From: jfeldman at ICSI.Berkeley.EDU (Jerome Feldman) Date: Fri, 16 Nov 2001 16:20:11 -0800 Subject: Asst. Prof. positions at UC Berkeley Message-ID: <3BF5AD3B.B5A54DF4@icsi.berkeley.edu> THE UNIVERSITY OF CALIFORNIA AT BERKELEY invites applications for tenure-track positions in ELECTRICAL ENGINEERING AND COMPUTER SCIENCES at the ASSISTANT PROFESSOR level beginning in Fall Semester 2002. One of the positions may involve a joint appointment with the Helen Wills Neuroscience Institute at UC, Berkeley. Several faculty searches have been approved. We are also considering the possibility of joint searches with other UC Berkeley departments. The joint position with Neuroscience would be in the area of Computational Neuroscience, broadly defined. Applicants should have received (or be about to receive) a doctoral degree in Computer Science, Electrical Engineering, or Computer Engineering or a related field. All areas of research in Computer Science and Electrical Engineering will be considered. For the shared position with Neuroscience, the degree may be in Neuroscience or related fields with a strong emphasis in Computational Neuroscience. A principal requirement is demonstrated excellence in research. In addition, potential for excellence in teaching and leadership are important requirements. Successful applicants will be expected to set up a quality research program and to teach both graduate and undergraduate courses in their general area of specialty. Interested persons should send a resume, a select subset of publications, a one- to two-page statement of their future research plans and interests, and the names of three references to the appropriate address below. We will not consider applications received after April 1, 2002. However, review of completed applications will begin January 10, 2002. The applicant should request their references to forward letters of reference directly to the same address to arrive before February 1, 2002. These letters will NOT be requested directly by the department. Electrical Engineering applications should be sent to: EE Faculty Search Committee Chair c/o Jean Richter Department of Electrical Engineering and Computer Sciences 231 Cory Hall # 1770 University of California, Berkeley Berkeley, California 94720-1770 Computer Science and Computational Neuroscience applications should be sent to: CS Faculty Search Committee Chair c/o Debra Zaller Department of Electrical Engineering and Computer Sciences 381 Soda Hall # 1776 University of California, Berkeley Berkeley, California 94720-1776 -- Jerome Feldman ICSI & EECS UC Berkeley "O wad some Pow'r the giftie gie us 1947 Center St. To see oursels as other see us!" Berkeley CA 94704 Robert Burns - To a Louse From aonishi at bsp.brain.riken.go.jp Sun Nov 18 21:39:30 2001 From: aonishi at bsp.brain.riken.go.jp (Toru Aonishi) Date: Mon, 19 Nov 2001 11:39:30 +0900 Subject: Papers on coupled oscillators Message-ID: <20011119113930H.aonishi@bsp.brain.riken.go.jp> Dear Connectionists, I am pleased to announce the availability of my recent paper and of one potentially related paper. Recent paper: ------------- Multibranch entrainment and slow evolution among branches in coupled oscillators T. Aonishi and M. Okada, Physical Review Letters (in press) Available at http://arXiv.org/abs/cond-mat/0104526 Abstract: In globally coupled oscillators, it is believed that strong higher harmonics of coupling functions are essential for {\it multibranch entrainment} (MBE), in which there exist many stable states, whose number scales as $\sim$ $O(\exp N)$ (where $N$ is the system size). The existence of MBE implies the non-ergodicity of the system. Then, because this apparent breaking of ergodicity is caused by {\it microscopic} energy barriers, this seems to be in conflict with a basic principle of statistical physics. In this paper, using macroscopic dynamical theories, we demonstrate that there is no such ergodicity breaking, and such a system slowly evolves among branch states, jumping over microscopic energy barriers due to the influence of thermal noise. This phenomenon can be regarded as an example of slow dynamics driven by a perturbation along a neutrally stable manifold consisting of an infinite number of branch states. Related paper: -------------- Statistical mechanics of an oscillator associative memory with scattered natural frequencies T. Aonishi, K. Kurata and M. Okada, Physical Review Letters, 82[13], pp. 2800--2803 (1999) Available at http://prl.aps.org/ http://arXiv.org/abs/cond-mat/9808090 Abstract: Analytic treatment of a non-equilibrium random system with large degrees of freedoms is one of most important problems of physics. However, little research has been done on this problem as far as we know. In this paper, we propose a new mean field theory that can treat a general class of a non-equilibrium random system. We apply the present theory to an analysis for an associative memory with oscillatory elements, which is a well-known typical random system with large degrees of freedoms. Regards, Toru Aonishi (Ph.D) Laboratory for Advanced Brain Signal Processing Brain Science Institute The Institute of Physical and Chemical Research (RIKEN) Hirosawa, 2-1, Wako-shi, Saitama, 351-0198, Japan E-mail: aonishi at brain.riken.go.jp URL: http://www.bsp.brain.riken.go.jp/~aonishi/ From steve at cns.bu.edu Mon Nov 19 09:17:56 2001 From: steve at cns.bu.edu (Stephen Grossberg) Date: Mon, 19 Nov 2001 09:17:56 -0500 Subject: Postdoc in vision and recognition at Boston University Message-ID: POSTDOCTORAL FELLOW DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS BOSTON UNIVERSITY A postdoctoral fellow is sought to join the Boston University Department of Cognitive and Neural Systems, with funding from an AFOSR grant: "A unified brain architecture for perception and cognition with applications to information processing technology." The fellowship is available immediately for a minimum term of two years. The postdoc would collaborate with Professors Gail Carpenter and Stephen Grossberg on basic research and technology transfer efforts. Candidates should have substantial training in developing neural network models of biomimetic vision/image processing and/or adaptive pattern recognition. The CNS Department offers excellent opportunities for broadening knowledge of neural modeling and applications, as summarized at http://www.cns.bu.edu . Boston University is an Equal Opportunity/Affirmative Action Employer. Please send a curriculum vitae, 3 letters of recommendation, and illustrative research articles to: Postdoctoral Search, Room 203, Department of Cognitive and Neural Systems, Boston University, 677 Beacon Street, Boston, MA 02215. From Wulfram.Gerstner at dimail.epfl.ch Tue Nov 20 03:54:49 2001 From: Wulfram.Gerstner at dimail.epfl.ch (Wulfram Gerstner) Date: Tue, 20 Nov 2001 09:54:49 +0100 Subject: PostDoc positions in Switzerland Message-ID: <3BFA1A59.AEEA6C43@di.epfl.ch> PostDoc positions in Computational Neuroscience in Lausanne The Laboratory of Computational Neuroscience at the Swiss Federal Institute of Technology in Lausanne (Switzerland) invites applications for 3 PostDoc positions in Computational Neuroscience. Members of the lab are interested in models of brain function and brain dynamics, especially models of spiking neurons/spike-time dependent learning rules, models of hippocampus/spatial navigation, and models of conditioning/reinforcement learning. For further details see: http://diwww.epfl.ch/mantra/ Candidates should have a strong analytical background and a keen interest in neuroscience. Competitive salaries are available. The Laboratory of Computational Neuroscience will be part of the new Brain and Mind Institutes on Campus and provides a unique opportunity to interact with world-class experimentalists. The city of Lausanne, situated on the shores of the Lake of Geneva, and surrounded by beautiful mountains, offers an exceptionally high qualitfy of life. Applicants should send in plain text format (i) a CV, (ii) a 1-page statement of research interests, (iii) names and addresses of three referees to brigitte.ramuz at epfl.ch (subject: PostDoc application) Closing date for applications: December 15 Starting dates of appointment: Between April and September 2002 -- Wulfram Gerstner Swiss Federal Institute of Technology Lausanne Professor Laboratory of Computational Neuroscience, DI-LCN 1015 Lausanne EPFL Tel. +41-21-693 6713 wulfram.gerstner at epfl.ch Fax. +41-21-693 5263 http://diwww.epfl.ch/mantra From K.Branney at elsevier.nl Tue Nov 20 08:18:10 2001 From: K.Branney at elsevier.nl (Branney, Kate (ELS)) Date: Tue, 20 Nov 2001 14:18:10 +0100 Subject: Cognitive Systems Research Message-ID: <46414F09B351C64BAA875CE0B37BE071A09884@elsamsvexch02.elsevier.nl> Apologies for multiple postings Special Offer for 2002 subscriptions to Cognitive Systems Research Cognitive Systems Research...the new journal devoted to the study of cognitive science To celebrate the launch of the new online journal, Cognitive Systems Research, Elsevier Science is pleased to offer institutions subscribing in 2002 extra archival material from 2000 and 2001. With each new subscription, institutions will receive FREE copies of the print copy of volumes 1 and 2, as well as Volume 3 at the end of 2002. A year's institutional subscription for 2002 costs just USD 308 or EUR 275, including THREE years' of archival material. Cognitive Systems Research seeks to foster and promote the discussion of novel approaches in studying cognitive and intelligent systems. It encourages cross-fertilization of disciplines. This is achieved by soliciting and publishing high-quality contributions in all of the areas of study in cognitive science, including artificial intelligence, linguistics, psychology, psychiatry, philosophy, system and control theory, anthropology, sociology, biological sciences, and neuroscience. The scope of the journal includes the study of a variety of different cognitive systems, at different levels, ranging from social/cultural cognition, to individual cognitive agents, to components of cognitive systems. Of particular interest are theoretical, experimental, computational, and integrative studies of cognitive systems at different levels of detail, and from different perspectives Call for Papers - Cognitive Systems Research covers all topics in the study of cognitive processes, in both natural and artificial systems. The journal seeks top-quality contributions and encourages, in particular, articles that transcend traditional disciplinary boundaries (in terms of implications or in terms of approaches). Please submit your papers via www.elsevier.com/locate/cogsys For subscription details, to view the abstracts, and for FREE access to the full PDFs until the end of 2001, please visit: www.elsevier.com/locate/cogsys Kate Branney Elsevier Science From malchiodi at dsi.unimi.it Tue Nov 20 10:07:50 2001 From: malchiodi at dsi.unimi.it (Dario Malchiodi) Date: Tue, 20 Nov 2001 16:07:50 +0100 Subject: Course at the International School on Neural Nets "E.R.Caianiello" - 2nd Announcement Message-ID: <3BFA71C6.692854D3@dsi.unimi.it> Many apologizes for cross posting The following meeting may be of interest to researchers interested in artificial intelligence, biology, neural networks and psychology FROM SYNAPSES TO RULES: DISCOVERING SYMBOLIC RULES FROM NEURAL PROCESSED DATA A course of INTERNATIONAL SCHOOL ON NEURAL NETS "E. R. CAIANIELLO" ETTORE MAJORANA CENTRE FOR SCIENTIFIC CULTURE ERICE-SICILY: 25 FEBRUARY - 7 MARCH 2002 Application deadline: December 15, 2001 The school aims at fixing a theoretical and applicatry framework for extracting formal rules from data. To this end the modern approaches will be expounded that collapse the two typical goals of the conventional AI and connectionism - respectively, deducing within an axiomatic shell formal rules about a phenomenon and inferring the actual behavior of it from examples - into a challenging inferential framework where we learn from data and understand what we have learnt. The target reads as a translation of the subsymbolic structure of the data - stored in the synapses of a neural network - into formal properties described by rules. To capture this trip from synapses to rules and then render it manageable for affording real world learning tasks, the Course will deal in depth with the following aspects: i. theoretical foundations of learning algorithms and soft computing, ii. intimate relationships between symbolic and subsymbolic reasoning methods, iii. integration of the related hosting architectures in both physiological and artificial brain. TOPICS Inferential bases for learning Theoretical foundations for soft computing Integration of symbolic-subsymbolic reasoning methods Physics and metaphysics of learning Toward applications LECTURERS * B. Apolloni, University of Milan, I * D. Malchiodi, University of Milan, I * D. Mundici, University of Milan, I * M. Gori, University of Siena, I * F. Kurfess, California Polytechnic State Univ., San Luis Obispo, CA, USA * A. Roy, Arizona State University, Tempe, AZ, USA * R. Sun, University of Missouri-Columbia, MO, USA * L. Agnati, Karolinska Institutet, Stockholm, S * G. Basti, Pontificia Universit? Lateranense, Rome, I * G. Biella, C.N.R. LITA, Milan, I * J. G. Taylor, King's College, London, UK * A. Esposito, Istituto Italiano Alti Studi Scientifici, Vietri, I * A. Moise, Boise State University, ID, USA DIRECTORS OF THE COURSE B. APOLLONI, A. MOISE DIRECTORS OF THE SCHOOL M. J. JORDAN, M. MARINARO DIRECTOR OF THE CENTRE A. ZICHICHI APPLICATIONS Interested candidates should send a letter to: * Professor Bruno Apolloni - Dipartimento di Scienze dell'Informazione Universit? degli Studi di Milano Via Comelico 39/41 20135 Milano, Italy Tel: ++39.02.5835.6284, Fax: ++39.02.5835.6228 e-mail: apolloni at dsi.unimi.it specifying: i) date and place of birth and present activity; ii) nationality. Thanks to the generosity of the sponsoring Institutions, partial support can be granted to some deserving students who need financial aid. Requests to this effect must be specified and justified in the letter of application. Notification of acceptance will be sent within the end of January 2002. For APPLICATION, CONTRIBUTING PAPERS, GRANTS, FEES, and further information please visit http://laren.usr.dsi.unimi.it/ericeSchool.html. For information about the Ettore Majorana Centre please visit http://www.ccsem.infn.it. From glanzman at helix.nih.gov Tue Nov 20 12:48:18 2001 From: glanzman at helix.nih.gov (Dennis Glanzman) Date: Tue, 20 Nov 2001 12:48:18 -0500 Subject: Joint NSF/NIH Initiative to Support Collaborative Research in Computational Neuroscience (CRCNS) Message-ID: <4.3.2.7.2.20011120124754.00b1fe30@helix.nih.gov> I would like to bring the following program announcement to your attention. The complete announcement may be accessed in HTML, PDF or ASCII format via the National Science Foundation's website at http://www.nsf.gov/cgi-bin/getpub?nsf02018 Please excuse duplicate mailings if you receive this notice more than once. Excerpts from the program announcement follow: JOINT NSF/NIH INITIATIVE TO SUPPORT COLLABORATIVE RESEARCH IN COMPUTATIONAL NEUROSCIENCE (CRCNS) The most exciting and difficult challenge facing neuroscientists is to understand the functions of complex neurobiological systems. Computational neuroscience provides a theoretical foundation and set of technological approaches that may enhance our understanding of nervous system function by providing analytical and modeling tools that describe, traverse and integrate different levels of organization, spanning vast temporal and spatial scales. Computational approaches are needed in the study of neuroscience as the requirement for comprehensive analysis and interpretation of complex data sets becomes increasingly important. Collaborations among computer scientists, cognitive scientists, engineers, theoreticians and neuorobiologists are imperative to advance our understanding of the nervous system. Participating Directorates of the National Science Foundation (NSF) and the Institutes of the National Institutes of Health (NIH) plan to support interdisciplinary research in computational neuroscience. Both agencies recognize the need for research that focuses on integrating computational models and methods with neuroscience. This solicitation is designed to encourage new and existing collaborations at this interface. ASSURANCE OF COLLABORATIVE RESEARCH EFFORT ACROSS SCIENTIFIC DISCIPLINES The driving principle behind this program solicitation is the recognition that projects crossing traditional academic interdisciplinary boundaries often bring about increased productivity and creativity when collaborative efforts include participation by scientists and engineers bringing their experience and training from widely varying backgrounds. Such interdisciplinary collaborations are required and should be demonstrated in the grant proposal, for example, by naming a co-investigator with academic credentials and appointment in an area different from that of the principal investigator, or by other means. A typical research collaboration might include a computer scientist and a neurobiologist. This interdisciplinary approach can also be demonstrated by a single investigator with appropriate multidisciplinary expertise. Proposals should describe interdisciplinary work to be done. Applications that are not clearly collaborative and/or interdisciplinary in nature will be returned without review. AWARD INFORMATION It is estimated that approximately $7.0 Million ($3.0 Million from NSF and $4.0 Million from NIH) will be available for this competition. Award sizes are expected to range from $100,000 to $500,000 per year with durations of 3-5 years. Estimated program budget, number of awards and average award size/duration are subject to the availability of funds. PROPOSAL PREPARATION AND SUBMISSION INSTRUCTIONS Letters of Intent: Must be submitted via email at crcns at nsf.gov by December 14, 2001. Letters of intent should be sent from the prospective PI by email to crcns at nsf.gov, and should contain the PI and the co-PI's names, a list of possible participating institutions, a possible title, and not more than 500 words to describe the work enough to permit intelligent choice of reviewers. Letters of intent will not be evaluated or used to decide on funding. They are requested to assist NSF and NIH in planning the review process. The submission of letters of intent enables NSF to begin choosing panelists before the proposal submission deadline. Full Proposal: Must be submitted by February 4, 2002. Proposals submitted in response to this program announcement/solicitation should be prepared and submitted in accordance with the general guidelines contained in the NSF Grant Proposal Guide (GPG). The complete text of the GPG is available electronically on the NSF Web Site at: http://= www.nsf.gov/cgi-bin/getpub?gpg. Paper copies of the GPG may be obtained from the NSF Publications Clearinghouse, telephone (301) 947-2722 or by e-mail from pubs at nsf.gov. -- Dennis L. Glanzman, Ph.D. Program Chief for Theoretical and Computational Neuroscience National Institute of Mental Health 6001 Executive Boulevard, MSC 9637 Bethesda, MD 20892-9637 Phone: 301.443.1576 Fax: 301.443.4822 From bengio at idiap.ch Wed Nov 21 02:05:32 2001 From: bengio at idiap.ch (Samy Bengio) Date: Wed, 21 Nov 2001 08:05:32 +0100 (CET) Subject: call for paper: NNSP'02, september 4-6, 2002 Message-ID: 2002 IEEE Workshop Neural Networks for Signal Processing September 4-6, 2002 Martigny, Valais, Switzerland http://eivind.imm.dtu.dk/nnsp2002 Sponsored by the IEEE Signal Processing Society In cooperation with the IEEE Neural Networks Council Call for Papers Thanks to the sponsorship of IEEE Signal Processing Society and IEEE Neural Network Council, the twelfth of a series of IEEE workshops on Neural Networks for Signal Processing will be held in Martigny (http://www.martigny.ch), Switzerland, at the ``Centre du Parc'' (http://www.hotelduparc.ch). The workshop will feature keynote addresses, technical presentations and panel discussions. Papers are solicited for, but not limited to, the following areas: Algorithms and Architectures: Artificial neural networks, kernel methods, committee models, independent component analysis, adaptive and/or nonlinear signal processing, (hidden) Markov models, Bayesian modeling, parameter estimation, generalization, optimization, design algorithms. Applications: Speech processing, image processing (computer vision, OCR), multimodal interactions, multi-channel processing, intelligent multimedia and web processing, robotics, sonar and radar, bio-medical engineering, bio-informatics, financial analysis, time series prediction, blind source separation, data fusion, data mining, adaptive filtering, communications, sensors, system identification, and other signal processing and pattern recognition applications. Implementations: Parallel and distributed implementation, hardware design, and other general implementation technologies. Further Information NNSP'2002 webpage: http://eivind.imm.dtu.dk/nnsp2002 Paper Submission Procedure Prospective authors are invited to submit a full paper of up to ten pages using the electronic submission procedure described at the workshop homepage. Accepted papers will be published in a hard-bound volume by IEEE and distributed at the workshop. Schedule Submission of full paper: April 15, 2002 Notification of acceptance: May 1, 2002 Camera-ready paper and author registration: June 1, 2002 Advance registration, before: July 15, 2002 Preliminary Programme September 4, AM: Pleanry talk by Mahesan Niranjan, Sheffield University "From Kalman to Particle Filtering for solving Signal Processing Problems with Neural Networks" Regular session, including oral and poster presentations September 4, PM: Special session on "Machine Learning and statistical approaches for Bio-Informatic Applications", Plenary talk by Anders Krogh, University of Denmark "Hidden Markov models of proteins and DNA", followed by special session, including oral and poster presentations September 5, AM: Plenary Talk: Yoshua Bengio, University of Montreal "Faking unlabeled data for geometric regularization" Regular session, including oral and poster presentations September 5, PM: Special session on "Multimodal/multi-channel processing" Plenary talk by Josef Kittler, University of Surrey "Fusion of multiple experts in multimodal biometric personal identity verification systems" September 6, AM: Plenary talk by Zoubin Ghahramani, Gatzby Institute, UK "Occam's Razor and Infinite Models" Regular oral and poster sessions. Invited Speakers Yoshua Bengio, University of Montreal Title of the talk: Faking unlabeled data for geometric regularization Zoubin Ghahramani, Gatzby Institute, Title of the talk: Occam's Razor and Infinite Models Josef Kittler, University of Surrey Invited for a Special Session on Multimodal and multi-channel applications Title of the talk: Fusion of multiple experts in multimodal biometric personal identity verification systems Anders Krogh, University of Denmark Invited for a Special Session on Bio-Informatics Title of the talk: Hidden Markov models of proteins and DNA Mahesan Niranjan, Sheffield University Title of the talk: From Kalman to Particle Filtering for solving Signal Processing Problems with Neural Networks General Chairs Herv BOURLARD IDIAP and EPF, Lausanne Tlay ADALI University of Maryland Baltimore County Program Chairs Samy BENGIO IDIAP Jan LARSEN Technical University of Denmark Technical Committee Chair Jose PRINCIPE University of Florida at Gainsville Finance Chair Jean-Philippe THIRAN EPF, Lausanne Proceedings Chairs Jean-Cdric CHAPPELIER EPF, Lausanne Scott C. DOUGLAS Southern Methodist University Publicity Chair Marc VAN HULLE Katholieke Universiteit, Leuven American Liaison Jose PRINCIPE University of Florida at Gainsville Asia Liaison Shigeru KATAGIRI NTT Communication Science Laboratories Program Committee Amir Assadi Andrew Back Samy Bengio Yoshua Bengio M. Carreira-Perpinan Jean-Cdric Chappelier Andrzej Cichocki Jesus Cid-Sueiro Bob Dony Scott Douglas Craig Fancourt Ling Guan Tzyy-Ping Jung Shigeru Katagiri Jens Kohlmorgen Shoji Makino Danilo Mandic Elias Manolakos Takashi Matsumoto David Miller Li Min Christophe Molina Mahesan Niranjan Kostas Plataniotis Tommy Poggio Jose Principe Phillip Regalia Steve Renals Joo-Marcos Romano Jonas Sjberg Robert Snapp Kemal Snmez Sren Riis Jean-Philippe Thiran Naonori Ueda Marc Van Hulle Fernando Von Zuben Christian Wellekens Lizhong Wu Lian Yan ----- Samy Bengio Research Director. Machine Learning Group Leader. IDIAP, CP 592, rue du Simplon 4, 1920 Martigny, Switzerland. tel: +41 27 721 77 39, fax: +41 27 721 77 12. mailto:bengio at idiap.ch, http://www.idiap.ch/~bengio From thrun at stanford.edu Wed Nov 21 12:25:51 2001 From: thrun at stanford.edu (Sebastian Thrun) Date: Wed, 21 Nov 2001 09:25:51 -0800 Subject: JMLR and the Web, by Boston Globe Message-ID: <200111211725.fALHPp009324@saga16.Stanford.EDU> This article in Boston Globe should be of interest to many in the Connectionists community. It provides a writer's perspective on the recent creation of the Journal of Machine Learning Research (JMLR), and the motivation behind the mass resignation of Machine Learning's editorial board. JMLR sets an example of what I believe will ultimately happen to many journals. The Web reaches many more people than current publishing mechanisms. As JAIR has proven, using the Web doesn't negatively affect the quality of a journal. By moving from paper to the Web, I hope we ultimately change the way we publish research results. It will be much easier to annotate papers by animations, software, and on-line discussions. It will be possible to link to follow-up research, publish revisions if necessary, and link to related scientific findings that came along after an original paper was published. And, of course, the whole world can access all of this, not just a selected few. Best wishes, sebastian thrun ------------------------------------------------------------------- SPREADING THE GOSPEL OF FREE SCIENCE Author: By Nicholas Thompson, GLOBE CORRESPONDENT Date: 11/20/2001 Page: C1 Section: Health Science Leslie Kaelbling hardly looks like a threat to the scientific establishment. The perky MIT professor rides to work on a bicycle that neatly folds into a briefcase-sized rectangle and spends her days trying to make machines that can learn. As associate director of MIT's Artificial Intelligence Laboratory, she is surrounded by quirky creations, from tiny fish-like robots made partly from frog tissue to robots that look like humans and, one day, may think like them, too. But Kaelbling leads another revolution in her spare time. As editor of the upstart Journal of Machine Learning Research, Kaelbling offers some of the latest debates and developments in artificial intelligence to anyone with access to the Internet - free. By contrast, the scholarly journals that largely set the world's science agenda sometimes charge more than $1,000 a year for a subscription. Kaelbling would be just another quixotic idealist with her unpaid staff - the journal "doesn't even have a bank account right now," she acknowledges - except for one thing. Thirty-nine board members of the leading artificial intelligence journal in her field, Machine Learning, announced their resignations last month to join her crusade. Kaelbling and her supporters argue that putting all top current research online could well inspire crucial insights from people who wouldn't otherwise have access; a statistician in Mongolia may spur the next breakthrough, after all. "The only thing we care about in the world is that people read our work," Kaelbling said. The rivalry between Kaelbling's journal and Machine Learning - which costs $1,050 a year for institutions and $120 for individuals - is part of a much broader debate about how much scientific information should be free. For instance, the federal government's Human Genome Project and private Celera Genomics have locked horns repeatedly over Celera's plan to withhold some key information from the human genetic blueprint that could be sold to pharmaceutical companies looking for potential new drugs. More closely parallel to Kaelbling's work, the National Institutes of Health have created a database called PubMed Central intended to allow anyone in the world to freely search and retrieve the full text of any published scientific article, with archives extending back for decades. Several months ago, a coalition of about 30,000 scientists, led partly by former NIH director and Nobel laureate Harold Varmus, pledged to boycott any journals that didn't meet PubMed Central's standards for freely distributing data. The coalition backed off a little in early September, but the conflict still looms. The free, Internet-based Journal of Machine Learning Research challenges an elaborate system of disseminating scientific information that touches everything from what appears on the nightly news to which researchers become stars. A few well-known journals such as Science, Nature, and the New England Journal of Medicine considerably influence scientific discussion and have a near hammerlock on determining what science appears in the mainstream press. A slew of others - including Machine Learning - shape their respective subject areas, helping determine who gets tenure, where grants go, and how their fields move forward. Kaelbling and others note that the scientific community differs in several ways from journalism, where support for free online access to magazines and newspapers has withered. For one, most scientific authors don't get paid for publishing, even in the journals with costly subscription prices. Instead, they receive their funding from universities, corporations, or government grants, and publish mainly for prestige and to advance their fields. Kaelbling earns her salary from the Massachusetts Institute of Technology and part of her job description requires her to offer public service to the community, such as editing the Journal of Machine Learning Research. Secondly, progress in any scientific field relies to a huge extent on the amount of available information. More available information equals more and better science. Some of Kaelbling's colleagues, for example, want to design robots that actually think like humans: Rodney Brooks, the director of Kaelbling's laboratory, helped inspire Steven Spielberg's vision for the movie "A.I." That enormously complicated task would be helped with input from as many different scientists as possible. Putting everything online seems like the obvious thing to do, Kaelbling argued. Still, numerous scientists and publishers fear that moving away from printed, subscription-based journals could derail standards and practices that have worked well for years. Others fear that such a change could shutter prestigious and important journals. In the machine-learning community, swords have already crossed. In their letter resigning from Machine Learning, the rebellious members, who represented about two-thirds of the board, wrote: "Journals should principally serve the needs of the intellectual community, in particular by providing the immediate and universal access to journal articles that modern technology supports, and doing so at a cost that excludes no one." In the past, scholars in the field researched and wrote their articles, submitted them to Machine Learning, and then waited up to a year to see them in print. Probably most aggravating to the authors, Machine Learning's owners, Netherlands-based Kluwer Academic Publishers, retained complete copyright control. Authors couldn't even publish their articles on personal Web pages - a fairly restrictive policy for the industry that the company changed after the mass resignation. With the Journal of Machine Learning Research, authors just e-mail their pieces to Kaelbling, who then forwards them to assorted editors. These volunteers, generally prestigious researchers in whatever particular sub-field the article covers, then decide whether to accept or reject the articles. If accepted, the articles appear online immediately and the authors retain full copyrights. "Mostly, it's just a bunch of work," said Kaelbling, before noting that she still spends vastly more time with her MIT students and Erik the Red, a robot resembling R2D2 that she is trying to teach to see and navigate through hallways. Despite Kaelbling's optimism, though, other scientists argue that there are holes in her boat. Robert Holte, the editor of Machine Learning, supports the new journal and suggests that both his journal and Kaelbling's can exist harmoniously. But, he added, "What [the Journal of Machine Learning Research] doesn't have right now is a history. You can have the most famous people on your editorial board that you like. But until a journal has a well-established track record proving its ability to attract a large number of high quality, highly-cited papers, it cannot claim to be the community's flagship journal." Tenure committees, for example, know that being published in Machine Learning means you've accomplished something significant. Until it earns a reputation, Kaelbling's journal could just be two crackpots in a barn with a cable modem. In addition, advocates of print journals argue that online journals may not hold to the same quality standards, becoming, in a sense, the scientific equivalents of the Drudge Report. "Paper journals have a strict limit on the number of papers they can publish. With an online journal, there's always a temptation to accept rather than reject," said Cornell professor Shai Ben-David, one member of the editorial board of Machine Learning who chose not to resign. Kaelbling acknowledged that her journal hasn't earned prestige yet, but she insists that it will maintain strict standards. "It's the same people doing the same work," she said, noting that the editorial board of the Journal of Machine Learning Research is made up of many people who used to work for Machine Learning. Kaelbling is one of the most highly respected scientists in her field and, before resigning last year, she herself reviewed papers for her print rival. Kaelbling faces another potential problem in that no major for-profit publisher supports and promotes her journal. Kluwer Academic Publishing, the world's second largest scientific publisher with 731 journals under its umbrella, stated that it supports Machine Learning by providing services that include promotion, copy-editing, distribution and representation of the journal at conferences. Still, the nonprofit MIT Press does offer Kaelbling's journal its support, publishing and promoting quarterly bound editions of the articles that have appeared on the journal's Web site. "I don't think they are any less effective than Kluwer," Kaelbling said. MIT Press does publish and promote quarterly bound editions of the articles that have appeared on Kaelbling's Web site, but has garnered fewer than 100 subscriptions so far. That doesn't phase Kaelbling, either. "Everyone's going to have to do this," she said. Even some scientists closely attached to old print publications agree. According to Thomas Dietterich, a former editor of Machine Learning, and one of the recent defectors to the new journal: "I am emotionally attached to Machine Learning. I have every issue from the start to now. But things change. In the computer business, we are used to technology turning things upside down." From xwu at emba.uvm.edu Fri Nov 23 11:41:10 2001 From: xwu at emba.uvm.edu (Xindong Wu) Date: Fri, 23 Nov 2001 11:41:10 -0500 (EST) Subject: Knowledge and Information Systems: 3(4), November 2001 Message-ID: <200111231641.LAA08409@kais.emba.uvm.edu> Knowledge and Information Systems: An International Journal ----------------------------------------------------------- ISSN: 0219-1377 (printed version) ISSN: 0219-3116 (electronic version) by Springer-Verlag Home Page: http://www.cs.uvm.edu/~xwu/kais.html =============================================== Volume 3, Number 4 (November 2001) ---------------------------------- link.springer.de/link/service/journals/10115/tocs/t1003004.htm or link.springer-ny.com/link/service/journals/10115/tocs/t1003004.htm Mehmet Sayal, Peter Scheuermann: Distributed Web Log Mining Using Maximal Large Itemsets Knowledge and Information Systems 3 (2001) 4, 389-404 URL: link.springer.de/link/service/journals/10115/bibs/1003004/10030389.htm David B. Skillicorn, Yu Wang: Parallel and Sequential Algorithms for Data Mining Using Inductive Logic Knowledge and Information Systems 3 (2001) 4, 405-421 URL: link.springer.de/link/service/journals/10115/bibs/1003004/10030405.htm Hillol Kargupta, Weiyun Huang, Krishnamoorthy Sivakumar, Erik Johnson: Distributed Clustering Using Collective Principal Component Analysis Knowledge and Information Systems 3 (2001) 4, 422-448 URL: link.springer.de/link/service/journals/10115/bibs/1003004/10030422.htm Andreas L. Prodromidis, Salvatore J. Stolfo: Cost Complexity-Based Pruning of Ensemble Classifiers Knowledge and Information Systems 3 (2001) 4, 449-469 URL: link.springer.de/link/service/journals/10115/bibs/1003004/10030449.htm Julio Ortega, Moshe Koppel, Shlomo Argamon: Arbitrating Among Competing Classifiers Using Learned Referees Knowledge and Information Systems 3 (2001) 4, 470-490 URL: link.springer.de/link/service/journals/10115/bibs/1003004/10030470.htm Stephen D. Bay: Multivariate Discretization for Set Mining Knowledge and Information Systems 3 (2001) 4, 491-512 URL: link.springer.de/link/service/journals/10115/bibs/1003004/10030491.htm ---------------------------------------------------- Online publication: November 21, 2001 (c) Springer-Verlag London Limited 2001 From tohru-nitta at aist.go.jp Sat Nov 24 02:51:03 2001 From: tohru-nitta at aist.go.jp (Tohru Nitta) Date: Sat, 24 Nov 2001 16:51:03 +0900 Subject: CFP ICONIP'2002-Singapore Special Session: Complex-valued Neural Networks Message-ID: <4.2.0.58.J.20011105192237.009bb540@mail.aist.go.jp> Dear Connectionists, The Special Session "Complex-valued Neural Networks" is going to be organized in the International Conference on Neural Information Processing (ICONIP2002) to be held in Singapore, November 18-22, 2002 (http://www.ntu.edu.sg/home/nef/). In these years the complex-valued neural networks, which are the extensions of the real-valued neural networks to complex numbers, expand the application fields in image processing, computer vision, optoelectronic imaging, and communication and so on.The potentially wide applicability yields new aspects of theories required for novel or more effective functions and mechanisms. This special session will cover original and pioneering contributions, theory as well as applications on complex-valued neural networks, and aim at an inspiring discussion on the recent progress and the future development. Papers should be submitted according to the guidelines provided by the ICONIP2002 home page (http://www.ntu.edu.sg/home/nef/) except the address for paper submission. Papers should be sent directly to the special session organizer via e-mail or airmail by April 30, 2002: Tohru Nitta, Mathematical Neuroinformatics Group, Neuroscience Research Institute, National Institute of Advanced Industrial Science and Technology, AIST Tsukuba Central 2, 1-1-1 Umezono, Tsukuba-shi, Ibaraki, 305-8568 Japan. FAX: +81-298-61-5841, E-mail: tohru-nitta at aist.go.jp Please do not send your papers to ICONIP2002 Secretariat. If you have any questions, please make contact with the special session organizer. I am looking forward to receiving your submission. Yours sincerely, -- Tohru Nitta (Dr.) Mathematical Neuroinformatics Group, Neuroscience Research Institute, National Institute of Advanced Industrial Science and Technology, AIST Tsukuba Central 2, 1-1-1 Umezono, Tsukuba-shi, Ibaraki, 305-8568 Japan. FAX: +81-298-61-5841, E-mail: tohru-nitta at aist.go.jp From terry at salk.edu Sun Nov 25 22:14:56 2001 From: terry at salk.edu (Terry Sejnowski) Date: Sun, 25 Nov 2001 19:14:56 -0800 (PST) Subject: ICA 2001 Deadline Message-ID: <200111260314.fAQ3EuL07538@purkinje.salk.edu> Special hotel rate available until Nov 29, 2001. ICA2001 http://ica2001.org Third International Conference on Independent Component Analysis and Signal Separation San Diego, California December 9-13, 2001 Program and Registration: http://ica2001.ucsd.edu/ Independent Component Analysis (ICA) is an emerging area of signal processing and data analysis based on the blind source separation of unknown mixtures of unknown source signals. Research advances on ICA have been made in machine learning, neural networks, statistical signal processing and Bayesian modeling. Numerous applications of ICA have been found in adaptive speech filtering, speech signal coding, biomedical signal processing, image compression, text modeling and financial data analysis. Chair Terrence Sejnowski terry at inc.ucsd.edu Program Te-Won Lee tewon at inc.ucsd.edu Publicity Scott Makeig scott at inc.ucsd.edu Treasurer John Staight jstaight at ucsd.edu Publication Tzyy-Ping Jung jung at inc.ucsd.edu Comm. Javier Movellan javier at inc.ucsd.edu International Advisory Committee: C. Jutten, INPG, France E. Oja, Helsinki University of Technology, Finland A. Bell, The Salk Institute, USA S. I. Amari, RIKEN, Japan Invited Speakers: Michael Arbib (USC) Robert Hecht-Nielsen (HNC & UCSD) Geoffry Hinton (Toronto) Michael Jordan (UC Berkeley) Christof Koch (Caltech) Gilles Laurent (Caltech) V.S. Ramachandran (UCSD) Mohan Trivedi (UCSD) ----- From scheler at ICSI.Berkeley.EDU Sat Nov 24 19:22:00 2001 From: scheler at ICSI.Berkeley.EDU (scheler@ICSI.Berkeley.EDU) Date: Sat, 24 Nov 2001 16:22:00 -0800 (PST) Subject: Parallel Paper Submission Message-ID: <200111250022.QAA23127@raclette.ICSI.Berkeley.EDU> We would like to suggest the adoption of a general policy in the Neural Network Community of unlimited parallel paper submission. It is the task of editors and reviewers then to accept or reject papers, and the liberty of authors to select the journal where they want to publish. Gabriele Dorothea Scheler Johann Martin Philipp Schumann From Wulfram.Gerstner at dimail.epfl.ch Mon Nov 26 04:37:03 2001 From: Wulfram.Gerstner at dimail.epfl.ch (Wulfram Gerstner) Date: Mon, 26 Nov 2001 10:37:03 +0100 Subject: Faculty Positions in Switzerland Message-ID: <3C020D3F.6631B8CB@di.epfl.ch> Faculty Positions in Computational and Experimental Neurosciences The Swiss Federal Institute of Technology in Lausanne will establish a `Brain and Mind Institute' with several openings for faculty positions in Computational and Experimental Neurosciences. For details see http://admwww.epfl.ch/pres/neurosciences.html For inquiries contact: life.sciences at epfl.ch Applications, including curriculum vitae, publication list, brief statement of research interests (three pages or less) and names and addresses (including e-mail) of at least seven references should be sent to : The office of the President EPFL CH-1015 Lausanne Switzerland From tgd at cs.orst.edu Mon Nov 26 11:17:10 2001 From: tgd at cs.orst.edu (Thomas G. Dietterich) Date: Mon, 26 Nov 2001 08:17:10 -0800 Subject: Parallel Paper Submission In-Reply-To: <200111250022.QAA23127@raclette.ICSI.Berkeley.EDU> (scheler@ICSI.Berkeley.EDU) References: <200111250022.QAA23127@raclette.ICSI.Berkeley.EDU> Message-ID: <4518-Mon26Nov2001081710-0800-tgd@cs.orst.edu> One of the most precious resources in the research community is our time. Unlimited parallel submission requires more time spent reviewing papers. This would probably have the effect of reducing the quality of the reviewing and reducing the willingness of referees to agree to donate their time. We need to strike a compromise between the one extreme of allowing authors to "shotgun" their papers to multiple conferences and the other extreme of allowing authors only a single chance to publish a paper. One possible compromise is the current arrangement whereby authors are permitted to submit to multiple conferences/journals but that these submissions must be sequential. This has the added advantage that the paper can be improved with each submission in light of the reviews obtained from the previous submission. -- Thomas G. Dietterich Voice: 541-737-5559 Department of Computer Science FAX: 541-737-3014 Dearborn Hall 102 URL: http://www.cs.orst.edu/~tgd Oregon State University Corvallis, OR 97331-3102 From wahba at stat.wisc.edu Mon Nov 26 13:26:25 2001 From: wahba at stat.wisc.edu (Grace Wahba) Date: Mon, 26 Nov 2001 12:26:25 -0600 (CST) Subject: Parallel Paper Submission Message-ID: <200111261826.MAA15415@hera.stat.wisc.edu> There is a downside to the idea below: If everyone submitted their paper to five journals in the hopes of maximizing its acceptance by at least one, this will mean multiplying the amount of refereeing work to be done by up to a factor of 5. Furthermore if an author gets an early acceptance from their second favorite journal and decides to wait to see if their first favorite journal will take it, then the second favorite journal has their publication schedule messed up. Editors and reviewers do not have unlimited free resources to deal with this ... S & S - suggest you bounce this idea off a few editors, as well as people who are maxxed out on refereeing, and see what kind of flack bounces back. ................................... From nnsp02 at neuro.kuleuven.ac.be Mon Nov 26 04:50:27 2001 From: nnsp02 at neuro.kuleuven.ac.be (Neural Networks for Signal Processing 2002) Date: Mon, 26 Nov 2001 10:50:27 +0100 Subject: NNSP'2002: IEEE Workshop, Neural Networks for Signal Processing, Call for Papers Message-ID: <3C021063.933639FD@neuro.kuleuven.ac.be> 2002 IEEE Workshop Neural Networks for Signal Processing September 4-6, 2002 Martigny, Valais, Switzerland http://eivind.imm.dtu.dk/nnsp2002 Sponsored by the IEEE Signal Processing Society In cooperation with the IEEE Neural Networks Council Call for Papers Thanks to the sponsorship of IEEE Signal Processing Society and IEEE Neural Network Council, the twelfth of a series of IEEE workshops on Neural Networks for Signal Processing will be held in Martigny (http://www.martigny.ch ), Switzerland, at the ``Centre du Parc'' (http://www.hotelduparc.ch ). The workshop will feature keynote addresses, technical presentations and panel discussions. Papers are solicited for, but not limited to, the following areas: Algorithms and Architectures: Artificial neural networks, kernel methods, committee models, independent component analysis, adaptive and/or nonlinear signal processing, (hidden) Markov models, Bayesian modeling, parameter estimation, generalization, optimization, design algorithms. Applications: Speech processing, image processing (computer vision, OCR), multimodal interactions, multi-channel processing, intelligent multimedia and web processing, robotics, sonar and radar, bio-medical engineering, bio-informatics, financial analysis, time series prediction, blind source separation, data fusion, data mining, adaptive filtering, communications, sensors, system identification, and other signal processing and pattern recognition applications. Implementations: Parallel and distributed implementation, hardware design, and other general implementation technologies. Further Information NNSP'2002 webpage: http://eivind.imm.dtu.dk/nnsp2002 Paper Submission Procedure Prospective authors are invited to submit a full paper of up to ten pages using the electronic submission procedure described at the workshop homepage. Accepted papers will be published in a hard-bound volume by IEEE and distributed at the workshop. Schedule Submission of full paper: April 15, 2002 Notification of acceptance: May 1, 2002 Camera-ready paper and author registration: June 1, 2002 Advance registration, before: July 15, 2002 Preliminary Programme September 4, AM: Plenary talk by Mahesan Niranjan, Sheffield University "From Kalman to Particle Filtering for solving Signal Processing Problems with Neural Networks" Regular session, including oral and poster presentations September 4, PM: Special session on "Machine Learning and statistical approaches for Bio-Informatic Applications", Plenary talk by Anders Krogh, University of Denmark "Hidden Markov models of proteins and DNA", followed by special session, including oral and poster presentations September 5, AM: Plenary Talk: Yoshua Bengio, University of Montreal "Faking unlabeled data for geometric regularization" Regular session, including oral and poster presentations September 5, PM: Special session on "Multimodal/multi-channel processing" Plenary talk by Josef Kittler, University of Surrey "Fusion of multiple experts in multimodal biometric personal identity verification systems" September 6, AM: Plenary talk by Zoubin Ghahramani, Gatsby Institute, UK "Occam's Razor and Infinite Models" Regular oral and poster sessions. Invited Speakers Yoshua Bengio, University of Montreal Title of the talk: Faking unlabeled data for geometric regularization Zoubin Ghahramani, Gatzby Institute, Title of the talk: Occam's Razor and Infinite Models Josef Kittler, University of Surrey Invited for a Special Session on Multimodal and multi-channel applications Title of the talk: Fusion of multiple experts in multimodal biometric personal identity verification systems Anders Krogh, University of Denmark Invited for a Special Session on Bio-Informatics Title of the talk: Hidden Markov models of proteins and DNA Mahesan Niranjan, Sheffield University Title of the talk: From Kalman to Particle Filtering for solving Signal Processing Problems with Neural Networks General Chairs Herve BOURLARD IDIAP and EPF, Lausanne Tulay ADALI University of Maryland Baltimore County Program Chairs Samy BENGIO IDIAP Jan LARSEN Technical University of Denmark Technical Committee Chair Jose PRINCIPE University of Florida at Gainsville Finance Chair Jean-Philippe THIRAN EPF, Lausanne Proceedings Chairs Jean-Cdric CHAPPELIER EPF, Lausanne Scott C. DOUGLAS Southern Methodist University Publicity Chair Marc VAN HULLE Katholieke Universiteit, Leuven American Liaison Jose PRINCIPE University of Florida at Gainsville Asia Liaison Shigeru KATAGIRI NTT Communication Science Laboratories Program Committee Amir Assadi Andrew Back Samy Bengio Yoshua Bengio M. Carreira-Perpinan Jean-Cdric Chappelier Andrzej Cichocki Jesus Cid-Sueiro Bob Dony Scott Douglas Craig Fancourt Ling Guan Tzyy-Ping Jung Shigeru Katagiri Jens Kohlmorgen Shoji Makino Danilo Mandic Elias Manolakos Takashi Matsumoto David Miller Li Min Christophe Molina Mahesan Niranjan Kostas Plataniotis Tommy Poggio Jose Principe Phillip Regalia Steve Renals Joo-Marcos Romano Jonas Sjberg Robert Snapp Kemal Snmez Sren Riis Jean-Philippe Thiran Naonori Ueda Marc Van Hulle Fernando Von Zuben Christian Wellekens Lizhong Wu Lian Yan From jlm at cnbc.cmu.edu Mon Nov 26 17:04:07 2001 From: jlm at cnbc.cmu.edu (Jay McClelland) Date: Mon, 26 Nov 2001 17:04:07 -0500 (EST) Subject: Parallel Paper Submission In-Reply-To: <4518-Mon26Nov2001081710-0800-tgd@cs.orst.edu> Message-ID: I wholeheartedly agree with Tom. Parallel submission would create a huge waste of reviewer time, and would lead to many bad feelings if a paper is accepted to two outlets. Obviously the problem with the sequential approach is that review turnaround can be slow. This is an issue that we all can and should work on. -- Jay McClelland From mlyons at atr.co.jp Mon Nov 26 21:50:11 2001 From: mlyons at atr.co.jp (Michael J. Lyons) Date: Tue, 27 Nov 2001 11:50:11 +0900 Subject: Parallel Paper Submission: Separate Refereeing and Editorial processes In-Reply-To: <200111261826.MAA15415@hera.stat.wisc.edu> Message-ID: On Mon, 26 Nov 2001, Grace Wahba wrote: > There is a downside to the idea below: If everyone submitted their > paper to five journals in the hopes of maximizing its > acceptance by at least one, this will mean multiplying the amount of > refereeing work to be done by up to a factor of 5. Furthermore > if an author gets an early acceptance from their > second favorite journal and decides to wait to see if > their first favorite journal will take it, then the > second favorite journal has their publication schedule > messed up. Editors and reviewers do not have unlimited free > resources to deal with this ... S & S - suggest you bounce this > idea off a few editors, as well as people who are maxxed out > on refereeing, and see what kind of flack bounces back. It's already not unusual to be asked to review a paper that has been rejected by one journal a second time for another journal. Perhaps a way around this is a complete revision of the publishing model. For example, the reviewing and editorial processes could be separated such that a paper is only reviewed by 2 or 3 referees by a system independent of the editorial process. Maybe referee selection can be partially automated using something like the Citeseer system. Then journal Editors could bid competitively on the pool of reviewed papers. This is just a suggestion, there could be many other possible models of the peer-review publishing process. Is there anything sacred (or optimal) about the system that is currently in place? Cheers, - Michael Lyons -- Michael J. Lyons, PhD Senior Researcher ATR Media Information Science Kyoto, Japan http://www.mic.atr.co.jp/~mlyons From seiffert at ipe.et.Uni-Magdeburg.DE Tue Nov 27 07:38:18 2001 From: seiffert at ipe.et.Uni-Magdeburg.DE (Udo Seiffert) Date: Tue, 27 Nov 2001 13:38:18 +0100 Subject: New Book on Self-Organizing Neural Networks Message-ID: <3C03893A.2DEB52E4@iesk.et.uni-magdeburg.de> Dear Colleagues, I am happy to announce the new Springer book Self-Organizing Neural Networks - Recent Advances and Applications. This compilation contains new theoretical work as well as up-to-date applications contributed by some of the world leaders of current SOM research. It is a compact and vivid collection of almost all aspects of current research on Self-Organizing Maps, ranging from theoretical work, several technical and non-technical applications, numerical and implementation details on sequential and parallel hardware to self-organisation with spiking neurons. An overture, given by Teuvo Kohonen, builds a bridge from the development of the fundamentals to the many extensions, modifications and applications which have made this neural network architecture so successful. Please find more information at Springer's web site http://www.springer.de/cgi-bin/search_book.pl?isbn=3D3-7908-1417-2 or Amazon.com http://www.amazon.com/exec/obidos/ASIN/3790814172/qid%3D/002-1230852-1153629 Kind regards, Udo Seiffert -- ____________________________________________________ Dr. Udo Seiffert University of Magdeburg IESK Email : seiffert at iesk.et.uni-magdeburg.de WWW : http://iesk.et.uni-magdeburg.de/~seiffert ____________________________________________________ From espaa at exeter.ac.uk Tue Nov 27 08:36:37 2001 From: espaa at exeter.ac.uk (Oliver Jenkin) Date: Tue, 27 Nov 2001 13:36:37 +0000 (GMT Standard Time) Subject: PAA Journal contents Message-ID: Pattern Analysis and Applications An International Journal by Springer-Verlag Website: http://www.dcs.ex.ac.uk/paa CONTENTS LIST YEAR 2001 Table of Contents Vol. 4 Issue 1 F. Mokhtarian, S. Abbasi: Affine Curvature Scale Space with Affine Length Parametrisation Pattern Analysis & Applications 4 (2001) 1, 1-8 Hyunwoon Kim, Ki Sang Hong: Robust Image Mosaicing of Soccer Videos using Self-Calibration and Line Tracking Pattern Analysis & Applications 4 (2001) 1, 9-19 Hiroki Hayashi, Mineichi Kudo, Jun Toyama, Masaru Shimbo: Fast Labelling of Natural Scenes Using Enhanced Knowledge Pattern Analysis & Applications 4 (2001) 1, 20-27 J. Bedenas, M. Boder, F. Pla: Segmenting Traffic Scenes from Grey Level and Motion Information Pattern Analysis & Applications 4 (2001) 1, 28-38 A. Kaarna, J. Parkkinen: Transform Based Lossy Compression of Multispectral Images Pattern Analysis & Applications 4 (2001) 1, 39-50 A. Hennig, N. Sherkat: Cursive Script Recognition using Wildcards and Multiple Experts Pattern Analysis & Applications 4 (2001) 1, 51-60 Yue-Fei Guo, Ting-Ting Shu, Jing-Yu Yang, Shi-Jin Li: Feature Extraction Method Based on the Generalised Fisher Discriminant Criterion and Facial Recognition Pattern Analysis & Applications 4 (2001) 1, 61-66 Table of Contents Vol. 4 Issue 2/3 (SPECIAL ISSUE ON IMAGE INDEXATION) Jean-Michel Jolion: Editorial Pattern Analysis & Applications 4 (2001) 2/3, 81-82 S. Berretti, A. Del Bimbo, E. Vicario: Modelling Spatial Relationships between Colour Clusters Pattern Analysis & Applications 4 (2001) 2/3, 83-92 N. Tsapatsoulis, Y. Avrithis, S. Kollias: Facial Image Indexing in Multimedia Databases Pattern Analysis & Applications 4 (2001) 2/3, 93-107 Laurent Amsaleg, Patrick Gros: Content-based Retrieval Using Local Descriptors: Problems and Issues from a Database Perspective Pattern Analysis & Applications 4 (2001) 2/3, 108-124 Joo-Hwee Lim: Building Visual Vocabulary for Image Indexation and Query Formulation Pattern Analysis & Applications 4 (2001) 2/3, 125-139 Jorma Laaksonen, Markus Koskela, Sami Laakso, Erkki Oja: Self-Organising Maps as a Relevance Feedback Technique in Content-Based Image Retrieval Pattern Analysis & Applications 4 (2001) 2/3, 140-152 J. Fournier, M. Cord, S. Philipp-Foliguet: RETIN: A Content-Based Image Indexing and Retrieval System Pattern Analysis & Applications 4 (2001) 2/3, 153-173 ByoungChul Ko, Jing Peng, Hyeran Byun: Region-based Image Retrieval Using Probabilistic Feature Relevance Learning Pattern Analysis & Applications 4 (2001) 2/3, 174-184 Patricia Ladret, Anne Guérin-Dugué: Categorisation and Retrieval of Scene Photographs from JPEG Compressed Database Pattern Analysis & Applications 4 (2001) 2/3, 185-199 E. Louupias, S. Bres: Key Points-based Indexing for Pre-attentive Similarities: The KIWI System Pattern Analysis & Applications 4 (2001) 2/3, 200-214 Linhui Jia, Leslie Kitchen: Object-Based Image Content Characterisation for Semantic-Level Image Similarity Calculation Pattern Analysis & Applications 4 (2001) 2/3, 215-226 Table of Contents Vol. 4 Issue 4 A. Raudys, J. A. Long: MLP Based Linear Fea ure Extraction for Nonlinearly Separable Data Pattern Analysis & Applications 4 (2001) 4, 227-234 Baoming Hong, Songmei Tang: An Integrated Face Rec gniti n System Based n Multiscale L cal Discriminatory Features Pattern Analysis & Applications 4 (2001) 4, 235-243 Dayou Wang, James M. Keller, C. Andrew Carson: Pulsed-Field Gel Elec rophoresis Pa ern Recogni ion of Bac erial DNA: A Systemic Approach Pattern Analysis & Applications 4 (2001) 4, 244-255 Max Mignotte, Jean Meunier, Jean-Claude Tardif: Endocardial Boundary E timation and Tracking in Echocardiographic Images using Deformable Template and Markov Random Fields Pattern Analysis & Applications 4 (2001) 4, 256-271 X. Yuan, D. Goldman, A. Moghaddamzadeh, N. Bourbakis: Segmentation of Colour Images with Highlights and Shadows sing Fuzzy-like Reasoning Pattern Analysis & Applications 4 (2001) 4, 272-282 Peter Tinù, Christian Schittenkopf, Georg Dorffner: Volatility Trading ia Temporal Pattern Recognition in Quantised Financial Time Series Pattern Analysis & Applications 4 (2001) 4, 283-299 __________________________________________ Oliver Jenkin Pattern Analysis and Applications Journal Department of Computer Science University of Exeter Exeter EX4 4PT, UK Tel: +44-1392-264061 Fax: +44-1392-264067 E-mail: espaa at ex.ac.uk Web: http://www.dcs.ex.ac.uk/paa ____________________________________________ From macgyver_99 at hotmail.com Tue Nov 27 08:35:48 2001 From: macgyver_99 at hotmail.com (M. Imad Khan) Date: Tue, 27 Nov 2001 18:35:48 +0500 Subject: Parallel Paper Submission References: Message-ID: What about publishing everything on the web and leave ALL kinds of paper publications. There could be a section where "unpublished" papers are published and the readers can cast votes as to "publish" them in the published section. This way soemthing that is useful but not "published" can be taken care of, while the normal people can act as reviewers and make the status of "unpublished" change to "published" through their vote. Imad ----- Original Message ----- From pau at ac.upc.es Tue Nov 27 09:10:17 2001 From: pau at ac.upc.es (Pau Bofill) Date: Tue, 27 Nov 2001 15:10:17 +0100 Subject: Parallel Paper Submission References: Message-ID: <004101c1774d$3db761e0$44235393@ac.upc.es> What about a pool of papers where anyone can submit? Editors/reviewers would then select their preferred papers from the pool... (This is an embryonary approach, to be further improved. Don't take it full value, please, but let's ponder the idea). Pau Bofill ----- Original Message ----- From peter.andras at ncl.ac.uk Tue Nov 27 09:35:06 2001 From: peter.andras at ncl.ac.uk (Peter Andras) Date: Tue, 27 Nov 2001 14:35:06 -0000 Subject: Parallel Paper Submission In-Reply-To: <4518-Mon26Nov2001081710-0800-tgd@cs.orst.edu> Message-ID: I think that a better way of handling the publication problem would be to have a publication clearing centre to which many publications would be affiliated. Papers would be send to the clearing centre, and authors would specify the preference list of journals where they wish to publish. The clearing centre would manage the refereeing process, and referees would suggest the place of publication, besides providing comments and recommendations. If the suggested place of publication matches the author's wishes, the paper would be published in that journal, otherwise the author could be consulted whether he accepts the suggested place of publication. The publications and referees would have ranks, depending on their measured scientific impact (impact factor for journals, recent cumulative impact factor and recent citation index for referees). Depending on the ranks of the target journals the referees with appropriate ranks would be assigned to evaluate the submissions. In this way the editorial boards of the journals would be primarily responsible for defining the scientific orientation and limits of the journal, and would release their role in the refereeing process as an editorial body (the members would still provide individual refereeing service to the publication clearing centre). Having enough many journals and referees associated to a publication clearing centre, this would provide an efficient way to publish scientific results much faster than it is currently possible (in average; obviously the established, well-known researchers publish relatively fast even today, but those who are not-well-known, at the begining of their scientific carrier may have to wait long time, until their papers appear in print). Having shorter time delays between first submission and publication, in average, would be very beneficial for the faster advancement of science. I see that the creation of a such clearing centre needs efforts and organization, but I don't see impossible the creation of a publication clearing centre in the near future. Best wishes, Peter Andras ----------------------- Dr Peter Andras Lecturer Neural Systems Group Department of Psychology University of Newcastle upon Tyne Newcastle upon Tyne NE1 7RU UK tel. +44-191-2225790 fax. +44-191-2225622 http://www.staff.ncl.ac.uk/peter.andras/ From jjost at mis.mpg.de Tue Nov 27 11:26:40 2001 From: jjost at mis.mpg.de (Juergen Jost) Date: Tue, 27 Nov 2001 17:26:40 +0100 (MET) Subject: open position Message-ID: Dear connectionists, at the Max Planck Institute for Mathematics in the Sciences in Leipzig (Germany), we have an open position for a postdoc in the field of Mathematical Modelling of Cognitive Systems. Applicants should be able to build upon a solid education in mathematics or physics in order to develop and analyze formal models, for example neural networks, that lead to new insights about information processing and cognitive structures. The work will take place in an open interdisciplinary group at a research institute with a strong background in mathematics and with many and diverse international contacts. Collaborations with researchers at the University of Leipzig or other institutions are possible. The position is offered for two years, with the possibility of an extension in case of mutual interest. The beginning date is flexible. Payment and benefits are determined by the regulations for the German Public Service. Handicapped applicants will be given preference in case of equal qualification. The Max Planck Society as the employer aims at increasing the number of female scientists in fields where underrepresented. Therefore, women are particularly encouraged to apply. Please send your application to the address below. Juergen Jost P.S: We also regularly accept applications for our PhD program. XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX Juergen Jost Max-Planck-Institut fuer Mathematik in den Naturwissenschaften Inselstrasse 22 - 26 D-04103 Leipzig Germany Tel.: +49-341-9959-550 +49-341-9959-552 (secretary) Fax: +49-341-9959-555 email: jost at mis.mpg.de XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX From rinkus at mediaone.net Tue Nov 27 11:37:06 2001 From: rinkus at mediaone.net (rinkus) Date: Tue, 27 Nov 2001 11:37:06 -0500 Subject: Parallel Paper Submission: Separate Refereeing and Editorial processes In-Reply-To: Message-ID: <004001c17761$c0941db0$17bcfea9@DBJH8M01> If people are genuinely interested in improving the scientific review process you might want to consider making it unacceptable for the graduate students of reviewers to do the actual reviewing. Graduate students are just that...students...and lack the knowledge and wisdom to provide a fair review of novel ideas. In many instances a particular student may have particular knowledge and insight relevant to a particular submission but the proper model here is for the advertised reviewer (i.e., whose name appears on the editorial board of the publication) to consult with the student about the submission (and this should probably be in an indirect fashion so as to protect the author's identity and ideas) and then write the review from scratch himself. The scientific review process is undoubtedly worse off to the extent this kind of accountability is not ensured. We end up seeing far too much rehashing of old ideas and not enough new ideas. Rod Rinkus From swindale at interchange.ubc.ca Tue Nov 27 13:28:57 2001 From: swindale at interchange.ubc.ca (Nicholas Swindale) Date: Tue, 27 Nov 2001 10:28:57 -0800 Subject: Parallel Paper Submission Message-ID: <4.3.2.20011127101510.00c77460@pop.interchange.ubc.ca> What about the following idea - allow unlimited parallel submission but shift the burden of obtaining referee reports to the authors. So the authors find 2 or 3 referees likely to be known to journal editors and likely to be impartial, submit the paper directly to the referees, and then when the paper is adequately revised submit it to the journal(s) of their choice and get the referees to send in their reports at the same time. This could be done sequentially or in parallel. This would a) save journal offices a lot of trouble, b) cut down on multiple refereeing and time-consuming resubmissions, c) get rid of anonymous reviewing and d) speed up publication. Nick Swindale __________________ Associate Professor, Dept of Ophthalmology, University of British Columbia, 2550 Willow St., Vancouver BC Canada V5Z 3N9 tel. 604 875 5379 fax. 604 875 4663 e-mail: swindale at interchange.ubc.ca From lazzaro at CS.Berkeley.EDU Tue Nov 27 14:54:26 2001 From: lazzaro at CS.Berkeley.EDU (John Lazzaro) Date: Tue, 27 Nov 2001 11:54:26 -0800 Subject: Parallel Paper Submission [...] Message-ID: <200111271954.LAA25156@snap.CS.Berkeley.EDU> > Michael Lyons writes > > Perhaps a way around this is a complete revision of the publishing model. We might also look to Hollywood -- the New York Times movie reviewer does not exercise prior restraint to prevent "bad" movies from being made or released. Instead, financial issues -- funding the movie, and distributor buy-in -- dictates whether a movie gets made and released. The role of the newspaper reviewer is to judge movies after release -- and the public is trained to read the opinion of respected reviewers, as part of the decision-making process of which movie to see on a Friday night. Ideas of this sort are under active investigation in the Digital Library community; this abstract gives the flavor of a project here at Berkeley: http://buffy.eecs.berkeley.edu/Seminars/2001/Nov/011105.wilensky.html --jl ------------------------------------------------------------------------- John Lazzaro -- Research Specialist -- CS Division -- EECS -- UC Berkeley lazzaro [at] cs [dot] berkeley [dot] edu www.cs.berkeley.edu/~lazzaro ------------------------------------------------------------------------- From dr+ at cs.cmu.edu Tue Nov 27 20:16:12 2001 From: dr+ at cs.cmu.edu (Douglas Rohde) Date: Tue, 27 Nov 2001 20:16:12 -0500 Subject: Parallel Paper Submission References: Message-ID: <3C043ADC.4090704@cs.cmu.edu> I considered the idea of a submission pool, from which editors would select papers they wished to publish, but decided against suggesting it myself because I think it would seriously compromise the effectiveness of the review process. I think most of us would agree that the review process, however painful for both the author and the reviewer, is nevertheless very useful for identifying flaws in work that should not be published and, perhaps more importantly, for improving good papers. If you submitted a paper to the pool and journal A wanted to accept it with major (and presumably justified) revisions and journal B wanted to accept it with minor ones, would you spend the time to do the revisions, or would you just go ahead and publish it in journal B as is? In order to attract potentially good papers, the journal editors will have incentive to suggest the fewest changes. As a result, the quality of the published papers will diminish. And if you were asked to write a review for a paper from the pool, how much effort would you put in if you knew the author may not even pay attention to your review and could just ignore it and publish elsewhere? In regards to Nicholas Swindale's suggestion, I can't imagine that the "get your own reviewers" model could possibly work. Would we be paying the reviewers as well? How many reviews can we solicit before choosing the ones we want to send in? Finally, I think the quality of the stuff coming out of Hollywood speaks to the viability of the movie reviewer model. Although I do think it would be interesting to have a journal purely devoted to review of and commentary on already published work in a particular field. Doug Rohde Carnegie Mellon University From rsun at cecs.missouri.edu Tue Nov 27 23:36:02 2001 From: rsun at cecs.missouri.edu (rsun@cecs.missouri.edu) Date: Tue, 27 Nov 2001 22:36:02 -0600 Subject: Parallel Paper Submission Message-ID: <200111280436.fAS4a2a24303@ari1.cecs.missouri.edu> >From: "M. Imad Khan" >To: Jay McClelland , connectionists at cs.cmu.edu > >What about publishing everything on the web and leave ALL kinds of paper >publications. There could be a section where "unpublished" papers are >published and the readers can cast votes as to "publish" them in the >published section. This way soemthing that is useful but not "published" can >be taken care of, while the normal people can act as reviewers and make the >status of "unpublished" change to "published" through their vote. > The opinions of experts should weigh a lot more than those of others --- that's the only way to maintain quality and quality is absolutely critical to scientific work. How do we emphasize experts' opinions if we do away with peer reviews? Even with peer reviews, we are constantly having difficulty in determining who the experts are (whenever we go outside of (relatively) clearly delineated narrow areas). --Ron =========================================================================== Prof. Ron Sun http://www.cecs.missouri.edu/~rsun CECS Department phone: (573) 884-7662 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 http://www.elsevier.com/locate/cogsys =========================================================================== From adriaan at tijsseling.com Wed Nov 28 00:42:15 2001 From: adriaan at tijsseling.com (Adriaan Tijsseling) Date: Wed, 28 Nov 2001 14:42:15 +0900 Subject: Parallel Paper Submission In-Reply-To: Message-ID: > I wholeheartedly agree with Tom. Parallel submission would create > a huge waste of reviewer time, and would lead to many bad feelings > if a paper is accepted to two outlets. Obviously the problem with > the sequential approach is that review turnaround can be slow. This > is an issue that we all can and should work on. An additional problem is that the reviewing process itself is not particularly efficient. How many times does it not occur that reviewers' reports do not agree? Or that one reviewer suggests a modification, which another reviewer actually requests to be removed? An ideal, but certainly attainable option is to have one single online repository for papers, in the same vein as citeseer or cogprints. Researchers can then retrieve the papers they are interested in, read them, and return a score based on relevance, originality, and the like. Perhaps they can submit a more detailed commentary anonymously, visible to the author(s) only. In this age, one should optimally try to benefit from modern internet technologies. Let the academic public decide which articles they deem relevant and useful. This way articles are much faster distributed (the current 1, 2, 3 year delay between writing and publishing is really becoming ridiculous nowadays). Adriaan Tijsseling From terry at salk.edu Wed Nov 28 06:15:46 2001 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 28 Nov 2001 03:15:46 -0800 (PST) Subject: Computational Neurobiology Graduate Training at UCSD Message-ID: <200111281115.fASBFks13378@purkinje.salk.edu> DEADLINE: JANUARY 4, 2002 COMPUTATIONAL NEUROBIOLOGY GRADUATE PROGRAM Department of Biology - University of California, San Diego http://www.biology.ucsd.edu/grad/other_compneuro.html The goal of the Computational Neurobiology Graduate Program at UCSD is to train researchers who are equally at home measuring large-scale brain activity, analyzing the data with advanced computational techniques, and developing new models for brain development and function. Financial support for students enrolled in this training program is available through an NSF Integrative Graduate Education and Research Training (IGERT) award. Candidates from a wide range of backgrounds are invited to apply, including Biology, Psychology, Computer Science, Physics and Mathematics. The three major themes in the training program are: 1. Neurobiology of Neural Systems: Anatomy, physiology and behavior of systems of neurons. Using modern neuroanatomical, behavioral, neuropharmacological and electrophysiological techniques. Lectures, wet laboratories and computer simulations, as well as research rotations. Major new imaging and recording techniques also will be taught, including two-photon laser scanning microscopy and functional magnetic resonance imaging (fMRI). 2. Algorithms and Realizations for the Analysis of Neuronal Data: New algorithms and techniques for analyzing data obtained from physiological recording, with an emphasis on recordings from large populations of neurons with imaging and multielectrode recording techniques. New methods for the study of co-ordinated activity, such as multi-taper spectral analysis and Independent Component Analysis (ICA). 3. Neuroinformatics, Dynamics and Control of Systems of Neurons: Theoretical aspects of single cell function and emergent properties as many neurons interact among themselves and react to sensory inputs. A synthesis of approaches from mathematics and physical sciences as well as biology will be used to explore the collective properties and nonlinear dynamics of neuronal systems, as well as issues of sensory coding and motor control. Participating Faculty include: * Henry Abarbanel (Physics): Nonlinear and oscillatory dynamics; modeling central pattern generators in the lobster stomatogastric ganglion. Director, Institute for Nonlinear Systems at UCSD. * Thomas Albright (Salk Institute): Motion processing in primate visual cortex; linking single neurons to perception; fMRI in awake, behaving monkeys. Director, Sloan Center for Theoretical Neurobiology. * Darwin Berg (Biology): Regulation synaptic components, assembly and localization, function and long-term stability. Former Chairman of Biology. * Garrison Cottrell (Computer Science and Engineering): Dynamical neural network models and learning algorithms. * Mark Ellisman (Neurosciences, School of Medicine): High resolution electron and light microscopy; anatomical reconstructions. Director, National Center for Microscopy and Imaging Research. * Robert Hecht-Nielsen (Electrical and Computer Engineering): Neural computation and the functional organization of the cerebral cortex. Founder of Hecht-Nielsen Corporation. * Harvey Karten (Neurosciences, School of Medicine): Anatomical, physiological and computational studies of the retina and optic tectum of birds and squirrels. * David Kleinfeld (Physics):Active sensation in rats; properties of neuronal assemblies; optical imaging of large-scale activity. Co-director, Analysis of Neural Data Workshop (MBL). * William Kristan (Biology): Computational Neuroethology; functional and developmental studies of the leech nervous system, including studies of the bending reflex and locomotion. Director, Neurosciences Graduate Program at UCSD. * Herbert Levine (Physics): Nonlinear dynamics and pattern formation in physical and biological systems, including cardiac dynamics and the growth and form of bacterial colonies. * Javier Movellan (Institue for Neural Computation): Sensory fusion and learning algorithms for continuous stochastic systems. * Mikhael Rabinovich (Institute for Nonlinear Science): Dynamical systems analysis of the stomatogastric ganglion of the lobster and the antenna lobe of insects. * Terrence Sejnowski hSalk Institute/Biology): Computational neurobiology; physiological studies of neuronal reliability and synaptic mechanisms. Director, Institute for Neural Computation. * Martin Sereno (Cognitive Science): Neural bases of visual cognition and language using anatomical, electrophysiological, computational, and non-invasive brain imaging techniques. * Nicholas Spitzer (Biology): Regulation of ionic channels and neurotransmitters in neurons; effects of electrical activity in developing neurons on neural function. Chair of the Neurobiology Section in Biology. * Charles Stevens (Salk Institute): Synaptic physiology; physiological studies and biophysical models of synaptic plasticity in hippocampal neurons. * Roger Tsien (Chemistry): Second messenger systems in neurons; development of new optical and MRI probes of neuron function, including calcium indicators and caged neurotransmitters. * Mark Whitehead (Neurosurgery, School of Medicine): Peripheral and central taste systems; anatomical and functional studies of regions in the caudal brainstem important for feeding behavior. * Ruth Williams (Mathematics): Probabilistic analysis of stochastic systems and continuous learning algorithms. Requests for application materials should be sent to the University of California, San Diego, Division of Biology 0348, Graduate Admissions Office, 9500 Gilman Drive, La Jolla, CA, 92093-0348 or to [gradprog at biomail.ucsd.edu]. The deadline for completed application materials, including letters of recommendation, is January 4, 2002. More information about applying to the UCSD Biology Graduate Program is available at http://www.biology.ucsd.edu/grad/admissions/index.html From sunny at sunnybains.com Wed Nov 28 07:17:18 2001 From: sunny at sunnybains.com (Sunny Bains) Date: Wed, 28 Nov 2001 12:17:18 +0000 Subject: Parallel Paper Submission References: Message-ID: <3C04D5CE.30503@sunnybains.com> This may be an entirely off-the-wall comment, but there is a possible solution that be able to be imported from (believe it or not) the vagaries of English property law. It used to be that each potential buyer (the journals) of a house (the paper) would have their own separate survey (review) done for the mortgaging companies. More recently, someone came up with the idea (this is still experimental) of having the buyer have their house surveyed themselves (the surveying profession is independent), and then give this report to any potential buyers. So, you could have a panel of reviewers who review for many journals in the same field. If the author puts a list of all the journals he/she is interested in, in order, then the reviewer can make the appropriate comments... (I have a very narrow experience of paper publishing, so apologies if this is a naive solution... I just thought it might be worth suggesting). Best, Sunny Bains Imperial College of Science and Technology Jay McClelland wrote: > > I wholeheartedly agree with Tom. Parallel submission would create > a huge waste of reviewer time, and would lead to many bad feelings > if a paper is accepted to two outlets. Obviously the problem with > the sequential approach is that review turnaround can be slow. This > is an issue that we all can and should work on. > > -- Jay McClelland > > > From koza at stanford.edu Wed Nov 28 11:25:30 2001 From: koza at stanford.edu (John Koza) Date: Wed, 28 Nov 2001 08:25:30 -0800 Subject: Parallel Paper Submission Message-ID: <019801c17829$4b96f0a0$050010ac@mendel> Hello Connectionists: There is a very simple way to solve the real problems that the proponents of parallel paper submission are trying to address. It does not involve any new complicated machinery (e.g., clearinghouses) and its does not involve (after initial implementation) any more work for already-busy editors and reviewers. A couple of years ago, there was one journal in the field of genetic and evolutionary computation. Like most journals in the computer science field, it had a lengthy review process. Papers languished for months on the editors desk before being sent out for reviewers. Reviewers were typically allowed 6 - 9 months or more to write their reviews. The editors then took many additional months before reaching a decision. Submitting authors were frustrated with having their work "tied up" waiting for a (possibly adverse) decision on whether their paper would be published. This is, of course, particularly significant for new academics who need publications in order to earn tenure. It was almost true that the author had forgotten that he had written the paper by the time it was published. When the IEEE starting considering creation of a new journal in the field of genetic and evolutionary computation, I talked to the editor-designate and convinced him to follow the practice of the biological and medical sciences. The nearly universal practice in the biological and medical sciences is exclusive submission combined with quick review. For example, Science demands that an author submit the paper exclusively to them; however, in exchange, Science promises the author a cursory yes-no decision (based on topic suitability and general appearance) in a couple of weeks and a final decision (after detailed review by peer reviewers) in about 6 weeks. I subscribe personally to over a dozen journals in the biological and medical sciences. They all follow this approach (as do other journals that I read in the library). I would say the overall average time that I see is about 70 - 90 days. In fact, many of them loudly advertise (in ads for their own journal and as part of the author submission instructions) their average review time. I've even seen competitive ads from the journal themselves pointing out their average time versus the average time for "brand X". There is nothing inconsistent about a rapid overall schedule and quality of reviewing or editing. The fact is that it doesn't take the reviewers or the editors any more time or effort to maintain a "biological sciences" kind of schedule than a schedule where reviewers are given 6 - 9 months and editors habitually take another 6 - 9 months to reach a decision. It is simply of a matter of when people spent their time. Having reviewed hundreds of papers, I can say that I read the paper and write the review on only one of two moment --- independent of whether I've been 30, 60, 90, or 180 days to do the rwview. If the paper really grabs my attention, I do it the day or so after I receive it and then just sendmy review in. If not, I do it on the day or so just before the review is due. Later, when the Genetic Programming and Evolvable Machines journal was being created, I also convinced the publisher and editor-designate to follow the same kind of schedule. That was much easier because the IEEE journal had already established and maintained its quick schedule. Over time, the original journal in the field of genetic and evolutionary computation has, because of competitive pressure, moved toward this same kind of schedule. (There is, of course, a one-time transitional effort required to get onto a faster schedule). The fact is, in a rapidly changing field, unnecessarily long publication schedules are a significant disservice to the field. They impede advances in the field because new ideas get out more slowly. They hamper the careers of individual authors. The simple way to move from the current "lose-lose" situation to a "win-win" situation a rapid schedule. Of course, once one journal in a field adopts this kind of common sense schedule, Darwinian natural selection takes over and produces significant competitive pressure on the others. John R. Koza Consulting Professor Biomedical Informatics Department of Medicine Medical School Office Building (MC 5479) Stanford University Stanford, California 94305-5479 Consulting Professor Department of Electrical Engineering School of Engineering Stanford University Phone: 650-941-0336 Fax: 650-941-9430 E-Mail: koza at stanford.edu WWW Home Page: http://www.smi.stanford.edu/people/koza For information about field of genetic programming in general: http://www.genetic-programming.org For information about Genetic Programming Inc.: http://www.genetic-programming.com For information about GECCO-2002 (GP-2002) conference in New York City on July 9 - 13, 2002 (Tuesday - Saturday) and the International Society on Genetic and Evolutionary Computation visit: http://www.isgec.org/ For information about the annual Euro-GP-2002 conference on April 3 - 5, 2002 in Ireland, visit http://evonet.dcs.napier.ac.uk/eurogp2002 From jkolen at altair.coginst.uwf.edu Wed Nov 28 12:56:57 2001 From: jkolen at altair.coginst.uwf.edu (John F. Kolen) Date: Wed, 28 Nov 2001 11:56:57 -0600 Subject: Parallel Paper Submission In-Reply-To: <4.3.2.20011127101510.00c77460@pop.interchange.ubc.ca>; from swindale@interchange.ubc.ca on Tue, Nov 27, 2001 at 10:28:57AM -0800 References: <4.3.2.20011127101510.00c77460@pop.interchange.ubc.ca> Message-ID: <20011128115657.F1472@altair.coginst.uwf.edu> Parallel submission offers the author the illusion of saving time and energy by increasing the probability of acceptance with minimal revisions. In my experience as an AE, very few papers are accepted as-is on the first attempt. Flat out rejects were just as rare. Revise and resubmit was the most frequent. Upon resubmission, papers were accepted either as-is or with minor-corrections. Now consider what happens with parallel submission. Essentially, more people look at your paper. Most quality reviews will identify the same deficiencies in the reviewed paper. So rather than have two or three people pointing out your mistakes, you've got five or six...and a couple of journals telling you to revise and resubmit. And it's still a two-step process. Most, if not all, of the suggestions on this thread have made the same assumption. That is, all that matters for acceptance is quality of the paper. This is not the case, especially in a field as diverse as ours. For any two journals, the review critera are different. Journals have target audiences that have certain expectations. Some audiences expect excruciatingly thorough background sections, while others are happy with the formulas and a minimal amount of window dressing. Thus, multiple submissions should entail additional work for each submission to tailor it to the target audience. This assumes, of course, that the author cares about such matters and does not perceive the publication as merely 'a line on the vita'. Finally, if you think that the reviews are unfair, discuss it with the editor. If you think the turnaround time is too long, get involved in the review process and write quality reviews with a quick turnaround. There always seems to be more papers than reviewers. -- John F. Kolen voice: 850.202.4420 Research Scientist fax: 850.202.4440 Institute for Human and Machine Cognition University of West Florida From anand at speech.sri.com Wed Nov 28 12:48:08 2001 From: anand at speech.sri.com (Anand Venkataraman) Date: Wed, 28 Nov 2001 09:48:08 -0800 (PST) Subject: Parallel Paper Submission Message-ID: <200111281748.JAA09061@chalumeau> > What about publishing everything on the web and leave ALL kinds of paper > publications. There could be a section where "unpublished" papers are > published and the readers can cast votes as to "publish" them in the > published section. This way soemthing that is useful but not "published" can > be taken care of, while the normal people can act as reviewers and make the > status of "unpublished" change to "published" through their vote. The problem with this is that it is not very clear who gets to vote. Proper and conscientious reviewing of papers by well qualified individuals is not only of service to the community, but also to the authors. It ensures that their papers do not see ink prematurely and become a source of embarrassment later on in their careers. A similar forum as you suggest is already available through the repository at www.arXiv.org where people are invited (and frequently do) post papers and reports that they may not intend to publish. Many publications also cite these arXived papers as though they were actually in print. & From hinton at cs.toronto.edu Wed Nov 28 12:51:45 2001 From: hinton at cs.toronto.edu (Geoffrey Hinton) Date: Wed, 28 Nov 2001 12:51:45 -0500 Subject: how to decide what to read Message-ID: <01Nov28.125155edt.453148-19376@jane.cs.toronto.edu> In the old days, there had to be a way to decide what to print because printing and circulation were bottlenecks. But now that we have the web, the problem is clearly how to decide what to read. It is very valuable to have the opinions of people you respect in helping you make this choice. For the last five years, I have been expecting someone to produce software that facilitates the following: On people's homepages, there is some convention for indicating a set of recommended papers which are specified by their URL's. When I read a paper I think is really neat, I add its URL to my recommended list using the fancy software (which also allows me to make comments and ratings available). I also keep a file of the homepages of people who I trust (and how much I trust them) and the fancy software alerts me to new papers that several of them like. Its hard to manipulate the system because people own their own hompages and if they bow to pressure to recommend second-rate stuff written by their adviser, other people will stop relying on them. Obviously, there are many ways to elaborate and improve this basic idea and many potential problems that need to be ironed out. But I think it would be extremely useful to have. Somebody please write this software. Geoff Hinton From ivo at idsia.ch Wed Nov 28 04:56:29 2001 From: ivo at idsia.ch (Ivo Kwee) Date: Wed, 28 Nov 2001 10:56:29 +0100 Subject: referee idea References: <3BFCC2C7.6040406@idsia.ch> <3681911.1006414391@[130.62.67.97]> Message-ID: <3C04B4CD.6090409@idsia.ch> Hi, I saw the postings on connectionists about referees. As a matter of fact, I bounced a related idea of open review for JMLR to Leslie just a week ago. I think it is relevant and might be in fact feasible [hope L. doesn't mind me quoting her...]. About L's comment on "sifting": additionally we can keep a personal list of what are the latest reviewed papers of some (important) person, personal "recommendations" (see Amazon), reviewers ranking, global download statistics, online versioning etc. The good thing about "the Amazon way" is that you can also read the reviewers comment themselves, which is mostly not available in most journals but is quite useful (as an exception I think the J. of Am. Statistics does include reviewers comments). Ivo Kwee IDSIA Ivo Kwee wrote: > Leslie, > > Why not make JMRL even more radical? Get away with an Editorial Board > at all? Do a referee system like Amazon.com, publish papers > immediately and let *everyone* act as referee immediately, but also > give points to referees themselves (start the current Board members as > "veterans"). This gives also fair credit to student/researchers that > referee papers on behalf of someone. > > What do you think? > > Ivo > Leslie Pack Kaelbling wrote: > It's an interesting idea. Might be fun to try in parallel with the > usual system (you can start a new journal that works this way!). > > I guess I'm ultimately an elitist. I think that a minority of the > community have better insight, understanding, and taste than the rest, > and that they should decide what gets published. > > Published is probably the wrong word here. In some sense, because of > things like eprint archives, everybody can publish their own work, > which is great and important. So I see the role of journals as really > giving an imprimatur. Some group of people thinks these (few) papers > are good. > > As more and more information becomes available, we'll even pay for > people to sift it for us, and find the good parts. Of course, "good" > to me is "bad" to someone else, and so that other community should > find some other editor to sift out the stuff they like. > > The reason I subscribe to some magazines is that my taste is aligned > with that of the editors. Even if a huge superset of that material > were available online, I'd pay for the (paper or electronic) magazine, > because I don't have time to do the sifting for myself. > > - L > From jbower at bbb.caltech.edu Wed Nov 28 22:11:26 2001 From: jbower at bbb.caltech.edu (James M. Bower) Date: Wed, 28 Nov 2001 19:11:26 -0800 Subject: Fwd: Re: Parallel Paper Submission Message-ID: > > >The opinions of experts should weigh a lot more than those of others --- >that's the only way to maintain quality and quality is absolutely critical >to scientific work. The deep and serious problem, in my view, is that the review of papers has become more and more political and more and more conservative, as viewed over my now 20 years publishing in the scientific literature. All one has to do is look at the real process of publishing in journals like Science and Nature to see that. Even established investigators regularly complain about a review process that seems to be driven more by who you know than what you know and that regularly rejects papers based on what is in the discussion section, rather than what is in the methods and results. Personally, I increasingly find that graduate students and postdocs are better judges of what is scientifically interesting than are many established faculty tied up in these political loops. I realize there is an inherent contradiction here, because at least in biology, many of the senior faculty I know (including one I am very familiar with) rely heavily on their graduate students and post docs to ghost reviews. So perhaps the problem has to do with the fact that the ghost reviewing students are trying to write the kind of reviews they would imagine their mentors would write. :-) Whatever, in my view there is no question that something is broken, and something needs to be done to fix it. The robustness of the discussions on this mail group speaks to that. I also think that, in the long run, the review that matters is the one that will be provided by the graduate student 100 years from now who no longer understands the politics and will therefore be considering published work on its merits and with the benefit of some hindsight. I would prefer to be able to speak to that student without the political filter currently being applied to way too many of our papers. I am happy to take the risk that I will be judged a fool. Rather that than not be allowed to take risks at all. Jim Bower -- *************************************** James M. Bower Ph.D. Research Imaging Center University of Texas Health Science Center - San Antonio and Cajal Neuroscience Research Center University of Texas - San Antonio (626) 791-9615 (626) 791-9797 FAX (626) 484-3918 (cell worldwide) Temporary address for correspondence: 110 Taos Rd. Altadena, CA. 91001 WWW addresses for: laboratory (temp) http://www.bbb.caltech.edu/bowerlab GENESIS (temp) http://www.bbb.caltech.edu/GENESIS From eytan at dpt-info.u-strasbg.fr Wed Nov 28 23:49:35 2001 From: eytan at dpt-info.u-strasbg.fr (Michel Eytan) Date: Thu, 29 Nov 2001 05:49:35 +0100 Subject: Parallel Paper Submission Message-ID: Thus hath held forth Adriaan Tijsseling at 28-11-2001 re Re: Parallel Paper Submission: [snip] > An ideal, but certainly attainable option is to have one single online > repository for papers, in the same vein as citeseer or cogprints. > Researchers can then retrieve the papers they are interested in, read them, > and return a score based on relevance, originality, and the like. Perhaps > they can submit a more detailed commentary anonymously, visible to the > author(s) only. We all know that there is a very serious pb about this: MONEY! The editors will *never* agree to put on the Web for free items that they sell -- and not cheap at that :-((( > In this age, one should optimally try to benefit from modern internet > technologies. Let the academic public decide which articles they deem HOW? The refrereeing process is intended to do precisely that, with the concourse of experts in the field... > relevant and useful. This way articles are much faster distributed (the > current 1, 2, 3 year delay between writing and publishing is really becoming > ridiculous nowadays). > > > Adriaan Tijsseling -- Michel Eytan eytan at dpt-info.u-strasbg.fr I say what I mean and mean what I say From jkolen at altair.coginst.uwf.edu Thu Nov 29 02:29:27 2001 From: jkolen at altair.coginst.uwf.edu (John F. Kolen) Date: Thu, 29 Nov 2001 01:29:27 -0600 Subject: Parallel Paper Submission In-Reply-To: ; from adriaan@tijsseling.com on Wed, Nov 28, 2001 at 02:42:15PM +0900 References: Message-ID: <20011129012927.M1472@altair.coginst.uwf.edu> On Wed, Nov 28, 2001 at 02:42:15PM +0900, Adriaan Tijsseling wrote: > An additional problem is that the reviewing process itself is not > particularly efficient. How many times does it not occur that reviewers' > reports do not agree? Or that one reviewer suggests a modification, which > another reviewer actually requests to be removed? > I think you're talking about consistency here, not efficiency. The editor, not the reviewers, is the final judge in such situations. > An ideal, but certainly attainable option is to have one single online > repository for papers, in the same vein as citeseer or cogprints. > Researchers can then retrieve the papers they are interested in, read them, > and return a score based on relevance, originality, and the like. Perhaps > they can submit a more detailed commentary anonymously, visible to the > author(s) only. > > In this age, one should optimally try to benefit from modern internet > technologies. Let the academic public decide which articles they deem > relevant and useful. This way articles are much faster distributed (the > current 1, 2, 3 year delay between writing and publishing is really becoming > ridiculous nowadays). The big time sinks are collecting reviews and then getting the paper to press. The former is a necessary evil, the magic stamp of approval. The latter, however, could be dispensed with by personally providing access to electronic versions that index engines, such as CiteSeer, can latch onto. And don't we already decide which articles are relevant and useful? Does it really matter if the information comes from a peer-reviewed journal or self-published technical report? Neuroprose was full of such documents. The real issue, IMHO, has nothing to do with disseminating information. Want everyone to have your paper? Just post it, don't bother submitting it to a journal. The true problem is the apparent value of a published article to those committies and administrators outside our field. -- John F. Kolen voice: 850.202.4420 Research Scientist fax: 850.202.4440 Institute for Human and Machine Cognition University of West Florida From giles at research.nj.nec.com Thu Nov 29 13:48:39 2001 From: giles at research.nj.nec.com (Lee Giles) Date: Thu, 29 Nov 2001 13:48:39 -0500 (EST) Subject: Parallel Paper Submission In-Reply-To: <019801c17829$4b96f0a0$050010ac@mendel> Message-ID: Readers of this thread might find this paper "Online or Invisible? "recently published in Nature of interest. http://www.neci.nec.com/~lawrence/papers/online-nature01/ Steve Lawrence presents evidence that online papers are 5 times more likely to be cited than those not online. Lee Giles -- C. Lee Giles, David Reese Professor, School of Information Sciences and Technology Professor, Computer Science and Engineering The Pennsylvania State University 001 Thomas Bldg, University Park, PA, 16802, USA giles at ist.psu.edu - 814 865 7884 http://ist.psu.edu/giles From stiber at u.washington.edu Thu Nov 29 22:12:20 2001 From: stiber at u.washington.edu (Prof. Michael Stiber) Date: Thu, 29 Nov 2001 19:12:20 -0800 Subject: reviewing In-Reply-To: <01Nov28.125155edt.453148-19376@jane.cs.toronto.edu> References: <01Nov28.125155edt.453148-19376@jane.cs.toronto.edu> Message-ID: <15366.63764.111258.27729@kasei.bothell.washington.edu> Geoffrey Hinton writes: > > In the old days, there had to be a way to decide what to print because > printing and circulation were bottlenecks. But now that we have the > web, the problem is clearly how to decide what to read. It is very This is the basis of one of the recurring themes of arguments over "modernizing" the publication review process. Suggestions usually revolve around letting something like market forces decide which papers are really most significant. This is based on the assumption that the only motivation for the current review system is filtering, and that we can all save ourselves some time by using technology to speed the filtering process (perhaps by distributing it among a large number of independently-operating processors, each doing a much smaller amount of work than current reviewers do :^)). For many (most?) people publishing, however, peer review serves another purpose: it provides an ongoing, relatively objective performance review. This is done incrementally, so the review is already distributed along time and among a number of people. When someone is asked to review a package of information about a colleague for promotion or tenure, for example, it is perfectly reasonable to rely on past reviews --- publication record --- to give a broad overview of _one aspect_ of performance. Lacking that, I suppose a conscientious reviewer would be faced with the enormous task of carefully reading a good fraction of the candidate's work. The same would be true, if less extensive, for annual performance reviews. In effect, all that time "saved" in streamlining the paper review process would just pop up elsewhere. Mike Stiber -- Prof. Michael Stiber stiber at u.washington.edu Computing and Software Systems http://faculty.washington.edu/stiber University of Washington, Bothell tel: +1-425-352-5280 Box 358534, 18115 Campus Way NE fax: +1-425-352-5216 Bothell, WA 98011-8246 USA From t.c.pearce at leicester.ac.uk Thu Nov 29 11:10:27 2001 From: t.c.pearce at leicester.ac.uk (Tim Pearce) Date: Thu, 29 Nov 2001 16:10:27 -0000 Subject: 3 PhD/3 Postdoc Positions Message-ID: Qualified applicants are being sought for 6 positions (3 postdoctoral and 3 postgraduate PhD. Researchers) at 3 institutions across Europe in the areas of computational neuroscience, neuromorphic engineering, and experimental neuroscience. All six positions are funded for 4 years duration under the EU Framework V IST, Future and Emerging Technologies initiative, starting from January 2002. The project concerns the development of an unmanned aerial vehicle (UAV) artefact to perform stereotypical moth-like chemotaxis behaviour in uncertain environments. We propose to develop biologically-inspired sensor, information processing and control systems for a c (hemosensing) UAV. The cUAV will identify and track volatile compounds of different chemical composition in outdooor environments. Its olfactory and sensory-motor systems are to be inspired by the moth. This development continues our research in artificial and biological olfaction, sensory processing and analysis, neuronal models of learning, real-time behavioural control, and robotics. Fleets of cUAVs will ultimately be deployed to sense, identify, and map the airborne chemical composition of large scale environments. Further details on the project and the research teams can be found at http://www.le.ac.uk/eg/tcp1/amoth/ The project includes significant funding and opportunities for travel within Europe to visit the laboratories of the participating consortia and outside Europe to attend international scientific meetings. University of Leicester, UK. A computational neuroscience postdoctoral researcher is required to develop a biologically constrained model of the insect antennal lobe operating in real-time and driven by broadly-tuned integrated chemosensors. Expertise in modelling of spiking neuronal populations, information theoretical analysis, and/or modelling of synaptic plasticity is desirable. A postgraduate researcher (who will be expected to register for a PhD) in the area of neuromorphic engineering is required to support this modelling activity as well as deal with the implementation of the model using FPGA/DSP technology and its integration with real-world chemical sensors. Strong mathematical, analytical and programming skills are required for both positions. Informal enquiries regarding these positions and the project in general should be addressed to the project co-ordinator, Dr. T.C. Pearce, Department of Engineering, University of Leicester, Leicester LE1 7RH, United Kingdom, +44 116 223 1290, t.c.pearce at le.ac.uk ETH/Univ Zurich, Switzerland. A computational neuroscience postdoctoral researcher is required to implement a model of sequence-based learning based upon the protocerebellum of the moth. A PhD researcher is also required for neuromorphic hardware implmentation. Both researchers will be involved in the construction of the UAV. Hence, interest and demonstrated skills in both computational neuroscience and the construction and control of robots is required. Informal enquiries regarding these positions and the project in general should be addressed to the project co-ordinator, Dr. P.F.M.J. Verschure, Institute of Neuroinformatics Winterthurerstrasse 190, 8057, Zurich, Switzerland. ++41 1 6353070, pfmjv at ini.phys.ethz.ch Sveriges Lantbruksuniversitet, Sweden. At the researcher level we will hire a postdoctoral scientist specializing in neurophysiology and neuromorphology of the insect central olfactory system. The main task will be to elucidate neural interactions within the antennal lobe allowing the amplification in sensitivity observed in earlier investigations A postgraduate researcher (who will be expected to register for a PhD) will work on similar issues but will also perform behavioural experiments investigating moth orientation to host odours and run linked gas chromatographic - electrophysiological experiments to pinpoint active semiochemicals. Both positions require skills in neurobiological techniques. Both positions will be formal positions, including full Swedish social benefits. Informal enquiries regarding these positions and the project in general should be addressed to the local co-ordinator, Professor Bill S. Hansson, Division of Chemical Ecology, Department of Crop Science, Swedish University of Agricultural Sciences, P.O. Box 44, SE-23053 Alnarp, Sweden, +46 40415300, bill.hansson at vv.slu.se Applicants should send a CV, cover letter stating for which position they are applying, the names of at least three referees, to the named academic associated with each position. Deadline for receipt of applications is 20th December, 2001. Regards, Tim. -- T.C. Pearce, PhD URL: http://www.leicester.ac.uk/eg/tcp1/ Lecturer in Bioengineering E-mail: t.c.pearce at leicester.ac.uk Department of Engineering Tel: +44 (0)116 223 1290 University of Leicester Fax: +44 (0)116 252 2619 Leicester LE1 7RH Bioengineering, Transducers and United Kingdom Signal Processing Group From gaijin at yha.att.ne.jp Thu Nov 29 10:07:45 2001 From: gaijin at yha.att.ne.jp (Sam Joseph) Date: Fri, 30 Nov 2001 00:07:45 +0900 Subject: how to decide what to read References: <01Nov28.125155edt.453148-19376@jane.cs.toronto.edu> Message-ID: <3C064F41.4A22FB2E@yha.att.ne.jp> This is exactly the sort of thing that the NeuroGrid project is trying to achieve. http://www.neurogrid.net/ I won't claim that we have the perfect solution just yet, but we're working towards a system where you can easily publish meta-data about whatever documents you care to. Over time the system learns who you go to for which information, automatically adjusting future recommendations on this basis. e.g. I often read and download pages related to "Fly Fishing"that were marked up by John, so my NeuroGrid node learns to go to John first when I search for things related to "Fly Fishing". NeuroGrid is completely open source, the code is all in SourceForge, which means that it 1. is still under development 2 will take some time before it is a turn key solution I believe that integrating trust and learning into this sort of distributed system is essential and that ultimately we will all benefit from the approach, whether NeuroGrid is the actual system we end up using or not. CHEERS> SAM Geoffrey Hinton wrote: > In the old days, there had to be a way to decide what to print because > printing and circulation were bottlenecks. But now that we have the > web, the problem is clearly how to decide what to read. It is very > valuable to have the opinions of people you respect in helping you > make this choice. For the last five years, I have been expecting > someone to produce software that facilitates the following: > > On people's homepages, there is some convention for indicating a set > of recommended papers which are specified by their URL's. When I read > a paper I think is really neat, I add its URL to my recommended list > using the fancy software (which also allows me to make comments and > ratings available). > > I also keep a file of the homepages of people who I trust (and how > much I trust them) and the fancy software alerts me to new papers that > several of them like. > > Its hard to manipulate the system because people own their own > hompages and if they bow to pressure to recommend second-rate stuff > written by their adviser, other people will stop relying on them. > > Obviously, there are many ways to elaborate and improve this basic > idea and many potential problems that need to be ironed out. > But I think it would be extremely useful to have. > Somebody please write this software. > > Geoff Hinton From james at tardis.ed.ac.uk Thu Nov 29 09:23:02 2001 From: james at tardis.ed.ac.uk (James Hammerton) Date: Thu, 29 Nov 2001 14:23:02 +0000 Subject: Parallel Paper Submission In-Reply-To: Your message of "Tue, 27 Nov 2001 22:36:02 CST." <200111280436.fAS4a2a24303@ari1.cecs.missouri.edu> Message-ID: <20011129142303.555687B5D@omega.tardis.ed.ac.uk> Hi, I've followed this discussion with some interest. It seems to me the main problem people are trying to address is the amount of time taken in the reviewing process. In my opinion, the way things work now is fine, the long times taken by the review process aside. Speeding up the review process isn't so difficult though if things are handled electronically. I'm one of the editors for a special issue of the JMLR, and we managed to get the reviewing process done and notifications sent out inside 3 months. The deadline for papers was 2nd September, we gave a 5th November deadline for reviews to be sent back to us and we planned notifications for the 16th November, but we slipped back a week on that timetable due to some late reviews. The JMLR normally gives reviewers 6 weeks to return their reviews and gets a relatively quick turnover as a result. I don't see why more journals can't operate like this -- even if the final publication is in print rather than on the web. I don't think the idea put forward for authors choosing their own reviewers is a good one -- there's a conflict of interests there. It seems to me that the ideas for pools of reviewers to whom papers get submitted is interesting but may be too complicated in practice. I'm not sure there is any pressing need to change from the current model, as opposed to finding ways to speed it up (e.g. by handling things electronically and using tight review schedules). James Hammerton From andre at icmc.sc.usp.br Thu Nov 29 05:30:25 2001 From: andre at icmc.sc.usp.br (andre) Date: Thu, 29 Nov 2001 08:30:25 -0200 Subject: IJCIA Journal - 2001 Contents References: <3B1697EF.294D0DC2@cpdee.ufmg.br> Message-ID: <3C060E41.A58C9D96@icmc.sc.usp.br> >>> CONTENTS LIST YEAR 2001 <<<< International Journal of Computational Intelligence and Applications by Imperial College Press and World Scientific http://www.wspc.com.sg/profiles/anncat/anncat/journals/compsci/ijcia.html Table of Contents Vol. 1 Issue 1 K. Horio and T. Yamakawa: Feedback Self-Organizing Map and its Applications to Spatio-Temporal Pattern Classification Extent: 1-18 W. Pedrycz and A. Gacek: Learning of Fuzzy Automata Extent: 19-33 J. M. Corchado, B. Lees and J. Aiken: Hybrid Instance-Based System for Predicting Ocean Temperatures Extent: 35-52 Y. Bennani and F. Bossaert Modular Connectionist Modelling and Classification Approaches for Local Diagnosis in Telecommunication Traffic Management Extent: 53-70 S. Oman and P. Cunningham Using Case Retrieval to Seed Genetic Algorithms Extent: 71-82 W. Xiangdong and W. Shoujue The Application of Feedforward Neural Networks in VLSI Fabrication Process Optimization Extent: 83-90 G. W. Grewal and T. C. Wilson An Enhanced Genetic Algorithm for Solving the High-Level Synthesis Problems of Scheduling, Allocation, and Binding Extent: 91-110 Calendar of Events Extent: 111-114 Book Review Extent: 115-119 Table of Contents Vol. 1 Issue 2 V. Stephan, K. Debes, H.-M. Gross, F. Wintrich and H. Wintrich A New Control Scheme for Combustion Processes Using Reinforcement Learning Based on Neural Networks Extent: 121-136 H. K. Lee and S. I. Yoo A Neural Network-Based Image Retrieval Using Nonlinear Combination of Heterogeneous Features Extent: 137-149 X. Z. Gao and S. J. Ovaska Fuzzy Power Command Enhancement in Mobile Communications Systems Extent: 151-163 G. G. Yen and Q. Fu Automatic Frog Calls Monitoring System: A Machine Learning Approach Extent: 165-186 S. S. Quek, C. P. Lim and K. K. Peh Prediction of Drug Dissolution Profiles Using Artificial Neural Networks Extent: 187-202 J. Sil and A. Konar A Hybrid Approach to Knowledge Acquisition Using Neural Petri Nets and DS Theory Extent: 203-223 Calender of Events Extent: 225-233 Book Review Extent: 235-238 Table of Contents Vol. 1 Issue 3 L. N. de Castro and F. J. Von Zuben: Immune and Neural Network Models: Theoretical and Empirical Comparisons Extent: 239-257 H. Selvaraj, P. Sapiecha and T. Luba Functional Decomposition and Its Applications in Machine Learning and Neural Networks Extent: 259-271 P. A. Boxer Learning Naive Physics by Visual Observation: Using Qualitative Spatial Representations and Probabilistic Reasoning Extent: 273-285 P. Wira and J.-P. Urban Predicting Unknown Motion for Model Independent Visual Servoing Extent: 287-302 Z.-Q. Liu and Y. Zhang Compensation Competitive Learning Extent: 303-322 Calendar of Events Extent: 323-329 Book Reviews Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence G. Weiss Extent: 331-334 Pattern Classification R. O. Duda, P. E. Hart and D. G. Stork Extent: 335-339 Table of Contents Vol. 1 Issue 4 Z-H. Zhou J-X. Wu, W. Tang and Z-Q. Chen: Combining regression estimators: GA-based selective neural network ensemble Extent: 341-356 H. W-K. Chia and C-L. Tan: Neural logic network learning using genetic programming Extent: 357-368 K. Mcgarry, S. Wermter and J. Macintyre: The extraction of knowledge from local function networks Extent: 369-382 B.W. Wah and M. Qian: Violation-guided neural-network learning for constrained formulations in time-series predictions Extent: 383-398 D.S. Yeung, S. Qiu, E.C.C. Tsang and X. Wang: A general updating rule for discrete Hopfield-type neural network with time-delay and the corresponding search algorithm Extent: 399-412 F. Linaker and H. Jacobsson: Learning delayed response tasks through unsupervised event extraction Extent: 413-426 S. Behnke: Learning iterative image reconstruction in the neural abstraction pyramid Extent: 427-438 R.S.T. Lee and J.K. Liu: NORN predictor - stock prediction using a neural oscillatory-based recurrent network Extent: 439-452 From jbednar at cs.utexas.edu Thu Nov 29 02:59:19 2001 From: jbednar at cs.utexas.edu (James A. Bednar) Date: Thu, 29 Nov 2001 01:59:19 -0600 Subject: self-organization software, papers, web demos Message-ID: <200111290759.BAA09014@pale.csres.utexas.edu> Version 3.0 of the LISSOM software package for self-organization of hierarchical laterally connected maps is now available from the UTCS Neural Networks Research Group website, http://www.cs.utexas.edu/users/nn. The software has been developed in the LISSOM project of modeling the mammalian visual system, and is intended to serve as a starting point for computational studies of the development and function of perceptual maps in general. Abstracts of two recent papers from the LISSOM project are also included below. The first paper shows how LISSOM simulations can be scaled up to model large cortical areas, obtaining quantitatively equivalent maps at each size. The second paper uses these techniques and the LISSOM software to demonstrate how innate face preferences and later adult face processing may both result from general-purpose learning and self-organization. Other papers and demos of the LISSOM software are available at http://www.cs.utexas.edu/users/nn/pages/research/visualcortex.html. - Jim, Amol, and Risto Software: ----------------------------------------------------------------------- LISSOM V3.0: HIERARCHICAL LATERALLY CONNECTED SELF-ORGANIZING MAPS http://www.cs.utexas.edu/users/nn/pages/software/abstracts.html#lissom James A. Bednar The LISSOM V3.0 package contains the C++ source code and examples for training and testing RF-LISSOM and HLISSOM. These self-organizing models support detailed simulations of the development and function of the mammalian visual system. The simulator is designed to have full functionality even when run in batch mode or remote mode, using a simple but powerful command file format and online command prompt. Because of the focus on batch/remote use, it does not have a GUI, but it does create a wide variety of images for analysis and testing. Sample command files are provided for running orientation, ocular-dominance, and face perception simulations using a variety of network and machine sizes. Extensive documentation is also included, all of which is also available via online help where appropriate. Version 3.0 supports an arbitrary number of maps of various types, which can be arranged into a hierarchy representing the visual system. Currently supported map types include input regions (e.g. a Retina), convolving regions (e.g. ON/OFF cell layers), and RF-LISSOM regions (with modifiable afferent and lateral connections.) Environmental input is controlled by a simple but flexible language that allows arbitrary patterns and natural images to be rendered, scaled, rotated, combined, etc. This language makes it possible to use LISSOM for many of your own projects without having to write any new simulator code. The simulator can also serve as a good starting point for writing a batch-mode neural-network or related simulator. In particular, it includes independent and general-purpose routines for image creation from matrices, PPM format image input and output, gnuplot image creation, polymorphic datatypes, 2D input drawing, streams of inputs from different distributions, convolution kernel specification, and cortical map measurement, as well as many general-purpose support algorithms and datatypes. Papers: ----------------------------------------------------------------------- SCALING SELF-ORGANIZING MAPS TO MODEL LARGE CORTICAL NETWORKS Amol Kelkar, James A. Bednar and Risto Miikkulainen Department of Computer Sciences, The University of Texas at Austin Technical Report AI-00-285, August 2001. (Expanded version of CNS*01 paper; 16 pages) http://www.cs.utexas.edu/users/nn/pages/publications/abstracts.html#kelkar.utcstr01 Self-organizing computational models with specific intracortical connections can explain many functional features of visual cortex, such as topographic orientation and ocular dominance maps. However, due to their computational requirements, it is difficult to use such detailed models to study large-scale phenomena like object segmentation and binding, object recognition, tilt illusions, optic flow, and fovea--periphery interaction. This paper introduces two techniques that make large simulations practical. First, a set of general linear scaling equations for the RF-LISSOM self-organizing model is derived and shown to result in quantitatively equivalent maps over a wide range of simulation sizes. Second, the equations are combined into a new growing map method called GLISSOM, which dramatically reduces the memory and computational requirements of large self-organizing networks. With GLISSOM it should be possible to simulate all of human V1 at the single-column level using existing supercomputers, making detailed computational study of large-scale phenomena possible. ----------------------------------------------------------------------- LEARNING INNATE FACE PREFERENCES James A. Bednar and Risto Miikkulainen Department of Computer Sciences, The University of Texas at Austin Technical Report AI-01-291, November 2001. (Expanded version of AAAI-00 paper; 28 pages) http://www.cs.utexas.edu/users/nn/pages/publications/abstracts.html#bednar.utcstr01 Whether humans have a specific, innate perceptual ability to process faces remains controversial. Studies have found face-selective brain regions in adults and have shown that even newborns preferentially attend to face-like stimuli. On this basis researchers have proposed that there are genetically hard-wired brain regions that specifically process faces. However, other studies suggest that the face-processing hardware is general purpose and highly plastic, even at birth. We propose a solution to this apparent paradox: innate face preferences may be learned by a general-purpose self-organizing system from internally generated input patterns, such as those found in PGO waves during REM sleep. Simulating this process with the HLISSOM model, we demonstrate that such an architecture constitutes an efficient way to specify, develop, and maintain functionally appropriate perceptual organization. This preorganization can account for newborn face preferences, providing a computational explanation for how genetic influences interact with experience to construct a complex system. From neted at anc.ed.ac.uk Thu Nov 29 10:20:47 2001 From: neted at anc.ed.ac.uk (Network Editor) Date: Thu, 29 Nov 2001 15:20:47 +0000 Subject: NETWORK: Computation in Neural Systems Message-ID: <15366.21071.74022.793376@gargle.gargle.HOWL> Please see below the contents for the current issue of NETWORK: Computation in Neural Systems. NETWORK is always striving to reduce the time taken in processing submitted papers. Here are some figures for the past year: - For accepted papers, our median receipt-to-final decision time was 157 days. - For rejected papers, our median receipt-to-final decision time was 137 days. - Note that for accepted papers, the median receipt-to-FIRST decision time was 94 days. The difference of 63 days was in most part due to authors carrying out revisions required prior to publication. NETWORK is available electronically (http://www.iop.org/journals/ne). For non-subscribers the current issue is freely accessible (http://www.iop.org/free2001). --------------------------------------------------------------------------- Professor David Willshaw Editor-in-Chief NETWORK: Computation in Neural Systems Institute for Adaptive & Neural Computation Division of Informatics University of Edinburgh 5 Forrest Hill Edinburgh EH1 2QL UK Tel: +44-(0)131-650 4404 Fax: +44-(0)131-650 4406 Email: neted at anc.ed.ac.uk ============================================================================= NETWORK: Computation in Neural Systems, volume 12, issue 4 Pages: 409-516 PAPERS 409 Effect of lateral connections on the accuracy of the population code for a network of spiking neurons M Spiridon and W Gerstner 423 Speed of feedforward and recurrent processing in multilayer networks of integrate-and-fire neurons S Panzeri, E T Rolls, F Battaglia and R Lavis 441 Neural coding and decoding: communication channels and quantization A G Dimitrov and J P Miller 473 Pattern recognition in a compartmental model of a CA1 pyramidal neuron B P Graham 493 A hybrid learning network for shift, orientation, and scaling invariant pattern recognition R Wang BOOK REVIEW 513 Mechanisms of Cortical Development D J Price and D J Willshaw (reviewed by P Kind) 515 AUTHOR INDEX (with titles), Volume 12 From: esann To: "Connectionists at cs.cmu.edu" References: From bogus@does.not.exist.com Thu Nov 29 09:09:42 2001 From: bogus@does.not.exist.com () Date: Thu, 29 Nov 2001 15:09:42 +0100 Subject: ESANN'2002 : extended deadline Message-ID: ---------------------------------------------------- | | | ESANN'2002 | | | | 10th European Symposium | | on Artificial Neural Networks | | | | Bruges (Belgium) - April 24-25-26, 2002 | | | | Extended deadline | ---------------------------------------------------- Due to numerous requests, we are pleased to announce that the deadline for submitting papers to the ESANN'2002 conference has been extended. New deadline: December 10, 2001. The ESANN'2002 covers most of the topics related to the neural network field (see http://www.dice.ucl.ac.be/esann for details). Six special sessions will also be organized: 1. Perspectives on Learning with Recurrent Networks (B. Hammer, J.J. Steil) 2. Representation of high-dimensional data (A. Gurin-Dugu, J. Hrault) 3. Neural Network Techniques in Fault Detection and Isolation (S. Simani) 4. Hardware and Parallel Computer Implementations of Neural Networks (U. Seiffert) 5. Exploratory Data Analysis in Medicine and Bioinformatics (A. Wismller, T. Villmann) 6. Neural Networks and Cognitive Science (H. Paugam-Moisy, D. Puzenat) Instructions concerning the submission of papers are detailed on the web site of the conference. ======================================================== ESANN - European Symposium on Artificial Neural Networks http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews,... Michel Verleysen Univ. Cath. de Louvain - Microelectronics Laboratory 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at dice.ucl.ac.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at dice.ucl.ac.be ======================================================== From terry at salk.edu Thu Nov 29 18:40:38 2001 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 29 Nov 2001 15:40:38 -0800 (PST) Subject: NEURAL COMPUTATION 13:12 Message-ID: <200111292340.fATNecF17024@purkinje.salk.edu> Neural Computation - Contents - Volume 13, Number 12 - December 1, 2001 ARTICLE Synchronization of the Neural Response to Noisy Periodic Synaptic Input A. N. Burkitt and G.M. Clark NOTE Specification of Training Sets and the Number of Hidden Neurons for Multilayer Perceptrons L. S. Camargo and T. Yoneyama LETTERS Spotting Neural Spike Patterns Using an Adversary Background Model Itay Gat and Naftali Tishby Intrinsic Stabilization of Output Rates by Spike-Based Hebbian Learning Richard Kempter, Wulfram Gerstner, and J. Leo van Hemmen Information Transfer Between Rhythmically Coupled Networks: Reading the Hippocampal Phase Code Ole Jensen Gaussian Process Approach to Spiking Neurons for Inhomogeneous Poisson Inputs Ken-ichi Amemori and Shin Ishii Dual Information Representation with Stable Firing Rates and Chaotic Spatiotemporal Spike Patterns in a Neural Network Model Osamu Araki and Kazuyuki Aihara Neurons with Two Sites of Synaptic Integration Learn Invariant Representations Konrad P. Kording and Peter Konig Linear Constraints in Weight Representation for Generalized Learning of Multilayer Networks Masaki Ishii and Itsuo Kumazawa Feedforward Neural Network Construction Using Cross Validation Rudy Setiono ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2002 - VOLUME 14 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $88 $94.16 $136 Institution $506 $451.42 $554 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From adriaan at tijsseling.com Fri Nov 30 06:38:47 2001 From: adriaan at tijsseling.com (Adriaan Tijsseling) Date: Fri, 30 Nov 2001 20:38:47 +0900 Subject: Parallel Paper Submission In-Reply-To: Message-ID: > http://www.neci.nec.com/~lawrence/papers/online-nature01/ > > Steve Lawrence presents evidence that online papers are 5 times > more likely to be cited than those not online. Amen to that! Which was basically my point as well when I suggested a central repository for papers. Some assumed I was talking about journals making paper submission an online thing. But in fact, why are we still going for paper? Research would speed up much more if work could be published online in a searchable and widely accessible database. Would that cost money? None at all. All that is needed is a fast server and a reliable host. Researchers who have read a paper in that database can submit a review or score, provided they are subscribed (for free of course) to that kind of service. Over time, any paper would be accumulating reviews and scores, much to the benefit of the author. After all, it would not be restricted to one or two or three reviewers, but to anyone interested in the paper. Of course, as someone pointed out to me, this may mean some papers might never be reviewed (But then, one could actively request a review). These are just loose ideas, but I really feel the time is there to make away with tedious reviewing, editing, and publishing and instead use what is already there: internet. Adriaan Tijsseling From goldfarb at unb.ca Fri Nov 30 12:57:58 2001 From: goldfarb at unb.ca (Lev Goldfarb) Date: Fri, 30 Nov 2001 13:57:58 -0400 (AST) Subject: A paper: "What is a structural measurement process?" Message-ID: (Our apologies in case you, as a subscriber to several lists, receive several copies of this message) Dear colleagues, The following paper, whose abstract is attached below, proposes a far-reaching (biologically inspired) generalization of the classical concept of measurement process, based on the ETS model for structural representation proposed by us earlier, and attempts to explain it on a simple "shape example". The paper also attempts to clarify the radical differences between the two kinds of "measurement" processes. Thus, we address a very broad scientific context within which it might be useful to treat the proposed ETS model. http://www.cs.unb.ca/profs/goldfarb/smp.ps or http://www.cs.unb.ca/profs/goldfarb/smp.pdf Best regards, Lev http://www.cs.unb.ca/profs/goldfarb.htm ********************************************************************** WHAT IS A STRUCTURAL MEASUREMENT PROCESS? Lev Goldfarb and Oleg Golubitsky ABSTRACT. Numbers have emerged historically as by far the most popular form of representation. All our basic scientific paradigms are built on the foundation of these, numeric, or quantitative, concepts. Measurement, as conventionally understood, is the corresponding process for (numeric) representation of objects or events, i.e., it is a procedure or device that realizes the mapping from the set of objects to the set of numbers. Any (including a future) measurement device is constructed based on the underlying mathematical structure that is thought appropriate for the purpose. It has gradually become clear to us that the classical numeric mathematical structures, and hence the corresponding (including all present) measurement devices, impose on "real" events/objects a very rigid form of representation, which cannot be modified dynamically in order to capture their combinative, or compositional, structure. To remove this fundamental limitation, a new mathematical structure--evolving transformation system (ETS)--was proposed earlier. This mathematical structure specifies a radically new form of object representation that, in particular, allows one to capture (inductively) the compositional, or combinative, structure of objects or events. Thus, since the new structure also captures the concept of number, it offers one the possibility of capturing simultaneously both the qualitative (compositional) and the quantitative structure of events. In a broader scientific context, we briefly discuss the concept of a fundamentally new, biologically inspired, "measurement process", the inductive measurement process, based on the ETS model. In simple terms, all existing measurement processes "produce" numbers as their outputs, while we are proposing a measurement process whose outputs capture the representation of the corresponding class of objects, which includes the class projenitor (a non-numeric entity) plus the class transformation system (the structural class operations). Such processes capture the structure of events/objects in an inductive manner, through a direct interaction with the environment. From stiber at u.washington.edu Fri Nov 30 17:18:33 2001 From: stiber at u.washington.edu (Prof. Michael Stiber) Date: Fri, 30 Nov 2001 14:18:33 -0800 Subject: Parallel Paper Submission In-Reply-To: References: Message-ID: <15368.1465.955083.919049@kasei.bothell.washington.edu> Adriaan Tijsseling writes: > > Researchers who have read a paper in that database can submit a review or > score, provided they are subscribed (for free of course) to that kind of > service. Over time, any paper would be accumulating reviews and scores, much > to the benefit of the author. After all, it would not be restricted to one > or two or three reviewers, but to anyone interested in the paper. Of course, > as someone pointed out to me, this may mean some papers might never be > reviewed (But then, one could actively request a review). > > These are just loose ideas, but I really feel the time is there to make away > with tedious reviewing, editing, and publishing and instead use what is > already there: internet. Actually, the scoring system you mention is also already there: ISI Web of Science (the electronic version of the Science Citation Index). In this case, scores are the number of times that a paper has been cited, with links to the citing works (which in effect review the paper by using its results). Unfortunately, it isn't public domain. Mike Stiber -- Prof. Michael Stiber stiber at u.washington.edu Computing and Software Systems http://faculty.washington.edu/stiber University of Washington, Bothell tel: +1-425-352-5280 Box 358534, 18115 Campus Way NE fax: +1-425-352-5216 Bothell, WA 98011-8246 USA From hans.liljenstrom at sdi.slu.se Fri Nov 30 16:50:45 2001 From: hans.liljenstrom at sdi.slu.se (Hans Liljenstrom) Date: Fri, 30 Nov 2001 22:50:45 +0100 Subject: PhD position Message-ID: <017201c179e9$13403380$6895143e@oden> A PhD position is open at the Dept. of Biometry and Informatics, SLU, Uppsala Ref number 4440/01-4711 Title: Mathematical modeling, analysis and computer simulation of brain dynamics, with special focus on EEG signals. Project area: The project is part of a collaboration with the psychiatric clinic at a nearby hospital. The clinic has modern equipment for continuous measure and treatment, and data for hundreds of patients is produced. The project objective is to relate EEG response to the effect of treatments, and in support for the analysis, computer models and simulations of neural networks are needed. The project also includes development of non-linear models and analytical tools for stochastic and chaotic time series. Many new and interesting problems can be addressed with a combination of stochastic and deterministic modelling. Development of computational techniques is also required to deal with the gigantic amount of data available. The theoretical results from the project are expected to provide new insight in how EEG signals from the brain should be interpreted and used for prediction of clinical treatment effects. At the Department of Biometry and Informatics, a broad and cross-disciplinary research is carried out, including theoretical biology and biophysics, applied mathematics, mathematical statistics/biometry, as well as environmental and geo-informatics. In addition, there is an extensive educational program within these areas. Suitable background: MSc in engineering, physics, computer science, or similar programs, or a mathematical education with focus on biology, biomedicine or similar. Financing: A stipend covering one year of studies, whereafter a full graduate position is created. Both forms include, in addition to the research work, also possibilities of 20% institutional work (such as teaching). For more information contact project leader Prof. Hans Liljenstrm, tel. +46-(0)18-67 17 28 or email hans.liljenstrom at bi.slu.se. Information regarding salary and other administrative issues is given by Birgitta Callmer at the personnel division of SLU, tel. +46-(0)18-67 10 76. Welcome with your application, including a personal CV and a description of your interests and expectations, and why you would be a suitable graduate student at our department. Your application should be marked with reference number 4440/01-4711 and should be sent to Registrator, SLU, Box 7070, SE-750 07 Uppsala, Sweden, by 10 December 2001. ================================================================ Hans Liljenstrm, Prof. Dept. of Biometry and Informatics Swedish University of Agricultural Sciences P. O. Box 7013, SE-750 07 Uppsala, Sweden Phone: +46 (0)18-671728, +46 (0)73-654 7977 Fax: +46 (0)18 673502, email: Hans.Liljenstrom at bi.slu.se Home page: www.bi.slu.se/~hanslil ================================================================ From hinton at cs.toronto.edu Wed Nov 28 12:51:45 2001 From: hinton at cs.toronto.edu (Geoffrey Hinton) Date: Wed, 28 Nov 2001 12:51:45 -0500 Subject: how to decide what to read Message-ID: In the old days, there had to be a way to decide what to print because printing and circulation were bottlenecks. But now that we have the web, the problem is clearly how to decide what to read. It is very valuable to have the opinions of people you respect in helping you make this choice. For the last five years, I have been expecting someone to produce software that facilitates the following: On people's homepages, there is some convention for indicating a set of recommended papers which are specified by their URL's. When I read a paper I think is really neat, I add its URL to my recommended list using the fancy software (which also allows me to make comments and ratings available). I also keep a file of the homepages of people who I trust (and how much I trust them) and the fancy software alerts me to new papers that several of them like. Its hard to manipulate the system because people own their own hompages and if they bow to pressure to recommend second-rate stuff written by their adviser, other people will stop relying on them. Obviously, there are many ways to elaborate and improve this basic idea and many potential problems that need to be ironed out. But I think it would be extremely useful to have. Somebody please write this software. Geoff Hinton From oby at cs.tu-berlin.de Thu Nov 1 07:41:17 2001 From: oby at cs.tu-berlin.de (Klaus Obermayer) Date: Thu, 1 Nov 2001 13:41:17 +0100 (MET) Subject: tenured faculty position Message-ID: <200111011241.fA1CfH725557@fiesta.cs.tu-berlin.de> Dear Connectionists, below please find an announcement for an open faculty position (tenured) in the area of artificial intelligence in our department (EE and CS) at the Technical Universoity of Berlin, which could be of interest. Cheers Klaus =========================================================================== FACULTY POSITION IN ARTIFICIAL INTELLIGENCE Faculty IV, Technical University of Berlin, Berlin, Germany The Department for Electrical Engineering and Computer Science solicits application for a tenured faculty position (salary level C3) in the area of artificial intelligence. Potential areas of research include (but are not restricted to) machine learning, automatic deduction and problem solving, planning and decision making, knowledge representation, scene analysis, and speech processing. The candidate should be open to interdisciplinary research projects which combine computer science and engineering with the cognitive sciences. The successful candidate is expected to join the department's undergraduate teaching programs, as well as the graduate education in the area of Artificial Intelligence. The successful candidate is expected to teach courses in German after two years. Requirements: Ph.D. degree and Habilitation or equivalent achievements (cf. 100 BerlHG); research experience in the field of artificial intelligence; a strong publication record and teaching experience. Experience in the acquisition of research grants is desirable. Please send applications to: Chair of the Department of Electrical Engineering Computer Science Technical University of Berlin FR 5-1, Franklinstrasse 28/29 10587 Berlin, Germany email: fbv13 at cs.tu-berlin.de All applications received before November 30th, 2001, will be given full consideration. The Technical University of Berlin wants to increase the percentage of women on its faculty and strongly encourages applications from qualified individuals. Women will be preferred given equal qualifications. Handicapped persons will be preferred given equal qualifications. ========================================================================== 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/ From whitneytabor at yahoo.com Fri Nov 2 17:04:45 2001 From: whitneytabor at yahoo.com (Whitney Tabor) Date: Fri, 2 Nov 2001 14:04:45 -0800 (PST) Subject: PhD Studentships available at UConn Psychology Message-ID: <20011102220445.16650.qmail@web10201.mail.yahoo.com> ******************************************************************* GRADUATE TRAINING IN LANGUAGE AND COGNITION AT THE UNIVERSITY OF CONNECTICUT ******************************************************************* Opportunities abound at the University of Connecticut (UConn) for qualified students to pursue graduate studies in Language and Cognition leading to the Ph.D. in Experimental Psychology. At least 4 PhD studentships will begin in Fall, 2002. Speech perception and production, the reading process and the development of reading skills, sentence processing, and ecological studies of perception and action have long been areas of research strength at UConn within Psychology and related departments. A unique synthesis is now occurring between the ecological work, which has focused on dynamical models of human movement, and the language work, which uses closely related connectionist models to study language as action. An important element in the mix is Haskins Laboratories, an independent research lab located nearby in New Haven, which, for over 65 years, has sustained an environment of intellectual cross-pollination and has made many breakthroughs in research on speech and reading. See the Language and Cognition Program Web Page for more details: http://www.sp.uconn.edu/~ps300vc/LangandCog/langandcog.html For admission guidelines and to download application forms, see: http://www.sp.uconn.edu/~wwwpsyc/ and http://www.sp.uconn.edu/~wwwpsyc/GradAd.html To obtain a printed brochure and a set of application materials, write, telephone, fax, or email: Gina Belz, Department of Psychology, University of Connecticut, 406 Babbidge Road, Unit 1030, Storrs, CT 06269-1030 Important deadline: January 15: Graduate Applications due. Phone: (860) 486-3528 FAX: (860) 486-2760 E-Mail: futuregr at psych.psy.uconn.edu ******************************************************************* Description of the Program in Language and Cognition: The Program in Language and Cognition focuses on those aspects of language that make it a uniquely versatile vehicle for communication and thought. There is thus a strong focus on the dynamical aspects of language, including experimental studies of language processing, learning, and change at the phoneme, word, and sentence level, modeling of language processes using artificial neural (connectionist) networks and symbolic computational models, and mathematical analysis using dynamical systems theory and statistics. There is particular interest in an ecological approach, which emphasizes continual interaction between speaker/hearers and their environments. There is much interest in the biological basis of language, both in pursuit of innate endowment questions and in studies of neural mechanisms using state-of-the-art neuroimaging tools. The group has long conducted basic research on the reading process; some members of the group are also engaged in the translation of research findings to the classroom. The Program has close ties to the Center for the Study of Perception and Action (CESPA---http://ione.psy.uconn.edu/~cespaweb/), the Developmental and Behavioral Neuroscience Divisions in the Dept. of Psychology (http://www.sp.uconn.edu/~wwwpsyc/), the Linguistics Department (http://vm.uconn.edu/~wwwling/), and the Cognitive Science Focus (http://cogsci.uconn.edu/) at the University of Connecticut. In addition, Haskins Laboratories (http://www.haskins.yale.edu), located nearby in New Haven, provides a stimulating environment for research and training. The program prepares students for careers in research and teaching. A student's research activity begins immediately on entry to the program. In addition, three courses are typically taken each semester. A student's schedule also includes attendance at colloquia and informal weekly group meetings for discussion of problems in theory and research. Course work for the Ph.D. degree can often be completed in two-and-a-half to three years. Another year or two is needed to complete the dissertation. Applicants should have an excellent academic record. Research experience is helpful but not necessary. Applicants may have an undergraduate major in psychology, linguistics, computer science, mathematics, cognitive science, or other related fields of study. ***** CAROL FOWLER (http://www.sp.uconn.edu/~wwwpsyc/Faculty/Fowler/Fowler.html), Professor of Psychology. Dr. Fowler works on speech perception and production within the developing direct-realist framework. In addition, she has begun collaborative research on cross-person coordination and cooperation in language use. This is part of an effort to develop an ecological theory of language-that is, an understanding of how language is used in ordinary contexts in which speech occurs. Dr. Fowler is the Director of Haskins Laboratories. LEONARD KATZ (http://www.sp.uconn.edu/~wwwpsyc/Faculty/Katz/Katz.html), Professor of Psychology. Dr. Katz studies reading, focusing on the process of printed word recognition. Cross-language experiments are often used to reveal in which ways word recognition is shaped by a language's particular characteristics and in which ways it is more general. Languages studied include English, Hebrew, Russian, Serbo-Croatian and Turkish. In addition, functional Magnetic Resonance Imaging studies (carried out in conjunction with Haskins Laboratories and Yale Medical School) explore the brain mechanisms that support the word recognition process. Finally, behavioral experiments in English are used to study the effects on word recognition of the reader's lexicon (i.e., neighborhood factors) and reader strategies. JAY RUECKL (http://www.sp.uconn.edu/~wwwpsyc/Faculty/Rueckl/Rueckl.html), Associate Professor of Psychology. A primary goal of Dr. Rueckl's research is to use connectionist networks to forge a link between theories of implicit memory and models of word identification. His research focuses on the interaction of phonological, morphological, and semantic factors in the influence of implicit memory on work identification in reading, the role of perceptual detail (e.g. the characteristics of a speaker's voice) in visual and spoken word identification. In addition, together with his colleagues at Haskins Laboratories, Dr. Rueckl has recently begun to apply artificial neural network models to the investigation of the cognitive neuropsychology of reading. DONALD SHANKWEILER (http://www.sp.uconn.edu/~wwwpsyc/Faculty/Shankweiler/Shankweiler.html), Professor of Psychology. The broad aim of Dr. Shankweiler's research is to understand how the language apparatus, which is biologically specialized for speech, becomes adapted to reading and writing. In studies carried out in the 1970's, he and Dr. I. Y. Liberman discovered that there is an important association between children's abilities to analyze speech into its components (phonemes, syllables, and morphemes) and their progress in reading. Recent research has pursued the implications of this association for the operation of short-term verbal memory; for children who lack phonologically analytic skills, short-term memory function is also impaired. Dr. Shankweiler, with Stephen Crain and their students, have developed a model of the role of short-term memory in language comprehension. WHITNEY TABOR (http://www.sp.uconn.edu/~ps300vc/tabor.html), Assistant Professor of Psychology. Dr. Tabor's research focuses on the coexistence of structure and flexibility in complex systems. He uses artificial neural networks and dynamical systems theory to develop models of human language processing, learning, and change. He has worked on the role of semantic information in sentence processing, evidence for ungrammatical influences in sentence processing, attractor models of syntactic category structure, the learning of complex phrase structure grammars, and the evolution of grammatical categories over historical time. * * * * * AFFILIATED FACULTY CLAUDIA CARELLO, Professor of Psychology, Director of CESPA: Ecological study of human movement, printed word recognition in English, Korean, Serbo-Croatian. ROGER CHAFFIN, Professor of Psychology (Hartford): Semantic memory, memory for skilled performance. ELENA LEVY, Associate Professor of Psychology (Stamford): Language and gesture, language development. DIANE LILLO-MARTIN, Professor of Linguistics and Psychology: The structure of American Sign Language, its acquisition and processing, and the processes deaf people use to read. GEORGIJE LUKATELA, Visiting Professor: The phonological basis of printed word recognition. LETITIA NAIGLES, Associate Professor of Psychology: Language acquisition, word learning. KENNETH PUGH, Associate Professor, Yale University and Haskins Laboratories: Brain imaging studies of reading. WILLIAM SNYDER, Assistant Professor of Linguistics: Cross-linguistic studies of language acquisition; sentence processing. MICHAEL TURVEY, Professor of Psychology: Ecological study of human movement, the phonological basis of printed word recognition. ******************************************************************* UNIVERSITY OF CONNECTICUT LANGUAGE AND COGNITION PROGRAM GRADUATE TRAINING ANNOUNCEMENT For more information, write to: Claudia Carello Department of Psychology University of Connecticut 406 Babbidge Road, Unit 1020 Storrs, CT 06269-1020 Phone: (860) 486-3529 E-mail: CESPA1 at uconnvm.uconn.edu ******************************************************************* ===== Whitney Tabor (860) 486-4910 (office) Department of Psychology (860) 486-2760 (fax) University of Connecticut (860) 486-6080 (lab) Storrs, CT 06269-1020 tabor at uconnvm.uconn.edu USA WAB Room 124 (office) http://www.sp.uconn.edu/~wwwpsyc/Faculty/Tabor/Tabor.html __________________________________________________ Do You Yahoo!? Find a job, post your resume. http://careers.yahoo.com From erik at bbf.uia.ac.be Mon Nov 5 11:43:50 2001 From: erik at bbf.uia.ac.be (Erik De Schutter) Date: Mon, 5 Nov 2001 17:43:50 +0100 Subject: CNS*2002 announcement and new paper submission procedure Message-ID: Eleventh Annual Computational Neuroscience Meeting CNS*2002 July 21 - July 25, 2002 Chicago, Illinois USA http://www.neuroinf.org/CNS.shtml CNS*2002 will be held in Chicago from Sunday, July 21, 2002 to Thursday, July 25 in the Congress Plaza Hotel & Convention Center. This is a historic hotel located on Lake Michigan in downtown Chicago. General sessions will be Sunday-Wednesday, Thursday will be a full day of workshops. The conference dinner will be Wednesday night, followed by the rock-n-roll jam session. INVITED SPEAKERS: Ad Aertsen (Albert-Ludwigs-University, Germany) Leah Keshet (University British Columbia, Canada) Alex Thomson (University College London, UK) PAPER SUBMISSIONS Papers will be submitted through a preprint server run by Elsevier and linked from the CNS site. Authors will have the option at the time of submission of making their preprint publicly available (which qualifies it for inclusion in the Proceedings, if accepted), or keeping it private (no inclusion in the Proceedings). Submissions will be reviewed in the usual way (independent of their public/private status), and the small number of papers not accepted will be removed from the preprint site. Papers that are accepted will be published in both the journal Neurocomputing and in a separate Proceedings volume. Only papers submitted before the January deadline will be accepted, but authors will be able to edit and improve their submissions continuously till the Proceedings are finalized. We will encourage the community to access this server before the actual meeting and to engage in discussions about papers. In this way, discussions and feedback both before and during the meeting can lead to improved quality of the published paper. It will be possible to use the paper on the preprint server directly as Proceedings submission in October. To facilitate the transition to this new submission procedure we will accept in 2002 both submission old style (= abstract + summary) and as real papers (proper length for the Proceedings). Submission deadline: January 25, 2002. ORGANIZING COMMITTEE: Program chair: Erik De Schutter (University of Antwerp, Belgium) Local organizer: Philip Ulinski (University of Chicago, USA) Workshop organizer: Maneesh Sahani (Gatsby Computational Neuroscience Unit, UK) Government Liaison: Dennis Glanzman (NIMH/NIH, USA) Program Committee: Upinder Bhalla (National Centre for Biological Sciences, India) Avrama Blackwell (George Mason University, USA) Victoria Booth (New Jersey Institute of Technology, USA) Alain Destexhe (CNRS Gif-sur-Yvette, France) John Hertz (Nordita, Denmark) David Horn (University of Tel Aviv, Israel) Barry Richmond (NIMH, USA) Steven Schiff (George Mason University, USA) Todd Troyer (University of Maryland, USA) From bbs at bbsonline.org Mon Nov 5 15:17:15 2001 From: bbs at bbsonline.org (Stevan Harnad - Behavioral & Brain Sciences (Editor)) Date: Mon, 05 Nov 2001 15:17:15 -0500 Subject: Pylyshyn: Mental Imagery: BBS Call for Commentators Message-ID: Below is the abstract of a forthcoming BBS target article Mental Imagery: In search of a theory by Zenon W. Pylyshyn http://www.bbsonline.org/Preprints/Pylyshyn/Referees/ This article has been accepted for publication 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. Commentators must be BBS Associates or nominated by a BBS Associate. To be considered as a commentator for this article, to suggest other appropriate commentators, or for information about how to become a BBS Associate, please reply by EMAIL within three (3) weeks to: calls at bbsonline.org The Calls are sent to 10,000 BBS Associates, so there is no expectation (indeed, it would be calamitous) that each recipient should comment on every occasion! Hence there is no need to reply except if you wish to comment, or to nominate someone to comment. If you are not a BBS Associate, please approach a current BBS Associate (there are currently over 10,000 worldwide) who is familiar with your work to nominate you. All past BBS authors, referees and commentators are eligible to become BBS Associates. A full electronic list of current BBS Associates is available at this location to help you select a name: http://www.bbsonline.org/Instructions/assoclist.html If no current BBS Associate knows your work, please send us your Curriculum Vitae and BBS will circulate it to appropriate Associates to ask whether they would be prepared to nominate you. (In the meantime, your name, address and email address will be entered into our database as an unaffiliated investigator.) To help us put together a balanced list of commentators, please give some indication of the aspects of the topic on which you would bring your areas of expertise to bear if you were selected as a commentator. To help you decide whether you would be an appropriate commentator for this article, an electronic draft is retrievable from the online BBSPrints Archive, at the URL that follows the abstract below. _____________________________________________________________ Mental Imagery: In search of a theory Zenon W. Pylyshyn Rutgers Center for Cognitive Science New Brunswick, New Jersey ABSTRACT: It is generally accepted that there is something special about reasoning that uses mental images. The question of how it is special, however, has never been satisfactorily spelled out, despite over thirty years of research in the post-behaviorist tradition. This article considers some of the general motivation for the assumption that entertaining mental images involves inspecting a picture-like object. It sets out a distinction between phenomena attributable to the nature of mind, to what is called the cognitive architecture, and ones that are attributable to tacit knowledge used to simulate what would happen in a visual situation. With this distinction in mind the paper then considers in detail the widely held assumption that in some important sense images are spatially displayed or are depictive, and that examining images uses the same mechanisms that are deployed in visual perception. I argue that the assumption of the spatial or depictive nature of images is only explanatory if taken literally, as a claim about how images are physically instantiated in the brain, and that the literal view fails for a number of empirical reasons e.g., because of the cognitive penetrability of the phenomena cited in its favor. Similarly, while it is arguably the case that imagery and vision involve some of the same mechanisms, this tells us very little about the nature of mental imagery and does not support claims about the pictorial nature of mental images. Finally I consider whether recent neuroscience evidence clarifies the debate over the nature of mental images. I claim that when such questions as whether images are depictive or spatial are formulated more clearly, the evidence does not provide support for the picture-theory over a symbol structure theory of mental imagery. Even if all the empirical claims turned out to be true, the view that many people take them to support, that mental images are literally spatial, remain incompatible with what is known about how images function in thought. We are then left with the provisional counterintuitive conclusion that the available evidence does not support rejection of what I call the "null hypothesis"; viz., that reasoning with mental images involves the same form of representation and the same processes as that of reasoning in general, except that the content or subject matter of thoughts experienced as images includes information about how things would look. http://www.bbsonline.org/Preprints/Pylyshyn/Referees/ ___________________________________________________________ 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 the article. We will then let you know whether it was possible to include your name on the final formal list of invitees. _______________________________________________________________________ *** SUPPLEMENTARY ANNOUNCEMENTS *** (1) The authors of scientific articles are not paid money for their refereed research papers; they give them away. What they want is to reach all interested researchers worldwide, so as to maximize the potential research impact of their findings. Subscription/Site-License/Pay-Per-View costs are accordingly access-barriers, and hence impact-barriers for this give-away research literature. There is now a way to free the entire refereed journal literature, for everyone, everywhere, immediately, by mounting interoperable university eprint archives, and self-archiving all refereed research papers in them. Please see: http://www.eprints.org http://www.openarchives.org/ http://www.dlib.org/dlib/december99/12harnad.html --------------------------------------------------------------------- (2) All authors in the biobehavioral and cognitive sciences are strongly encouraged to self-archive all their papers in their own institution's Eprint Archives or in CogPrints, the Eprint Archive for the biobehavioral and cognitive sciences: http://cogprints.soton.ac.uk/ It is extremely simple to self-archive and will make all of our papers available to all of us everywhere, at no cost to anyone, forever. Authors of BBS papers wishing to archive their already published BBS Target Articles should submit it to BBSPrints Archive. Information about the archiving of BBS' entire backcatalogue will be sent to you in the near future. Meantime please see: http://www.bbsonline.org/help/ and http://www.bbsonline.org/Instructions/ --------------------------------------------------------------------- (3) Call for Book Nominations for BBS Multiple Book Review In the past, Behavioral and Brain Sciences (BBS) 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!). *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* Please note: Your email address has been added to our user database for Calls for Commentators, the reason you received this email. If you do not wish to receive further Calls, please feel free to change your mailshot status through your User Login link on the BBSPrints homepage, useing your username and password above: http://www.bbsonline.org/ For information about the mailshot, please see the help file at: http://www.bbsonline.org/help/node5.html#mailshot *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* From rsun at cecs.missouri.edu Mon Nov 5 15:29:55 2001 From: rsun at cecs.missouri.edu (rsun@cecs.missouri.edu) Date: Mon, 5 Nov 2001 14:29:55 -0600 Subject: Cognitive Systems Research 2 (3), 2001 Message-ID: <200111052029.fA5KTtr09929@ari1.cecs.missouri.edu> The new issue of Cognitive Systems Research: --------------------------------------------------------- Table of Contents for Cognitive Systems Research Volume 2, Issue 3, 2001 William Frawley and Raoul N. Smith A processing theory of alexithymia [Abstract] [Full text] (PDF 191.9 Kb) 189-206 Jacqueline P. Leighton and Michael R.W. Dawson A parallel distributed processing model of Wason's selection task 207-231 [Abstract] [Full text] (PDF 320.9 Kb) Reza Farivar Review of The Mind within the Net: Models of Learning, Thinking, and Acting - Manfred Spitzer; MIT Press, Cambridge, MA, xi+359 pp; ISBN 0-262-19406-6 (PB+HC) 235-240 [Abstract] [Full text] (PDF 57.9 Kb) Jelle van Dijk and Gert-Jan Bleeker Review of A Universe of Consciousness. How Matter becomes Imagination - G.M. Edelman & G. Tononi; Basic Books, New York, 2000; 266 pp; ISBN 0465013767 241-244 [Abstract] [Full text] (PDF 48.4 Kb) * Full text files can be viewed and printed using the Adobe Acrobat Reader. Download the papers from the Web site: http://www.cecs.missouri.edu/~rsun/journal.html http://www.elsevier.nl/locate/cogsys http://www.elsevier.com/locate/cogsys Copyright 2001, Elsevier Science, All rights reserved. =========================================================================== Prof. Ron Sun http://www.cecs.missouri.edu/~rsun CECS Department phone: (573) 884-7662 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 http://www.elsevier.com/locate/cogsys =========================================================================== From winfried.ilg at tuebingen.mpg.de Mon Nov 5 07:12:51 2001 From: winfried.ilg at tuebingen.mpg.de (Winfried Ilg) Date: Mon, 05 Nov 2001 13:12:51 +0100 Subject: job announcement Message-ID: PhD / POSTDOC POSITIONS FOR THEORETICAL NEUROSCIENCE ==================================================== The Laboratory for Action Representation and Learning at the Department of Cognitive Neurology and the Max-Planck Institute for Biological Cybernetics in Tuebingen (Germany) offers a Postdoc or PhD position for a neuroscientist or computer scientist with interest in neural modeling. Aim of the project is the development and evaluation of models for the neural mechanisms of the recognition and planning of complex movements. Dependent on her / his interest, the successful candidate will also have the opportunity to take part in psychophysical, electrophysiological and FMRI experiments for testing neural theories of motion recognition and learning of movements by imitation. Tuebingen offers an excellent environment for experimental and theoretical neuroscience. In addition, PhD students can acquire a PhD degree in "Neuroscience" in an interdiciplinary graduate program. The experimental side of the project will be realized in close collaboration with experimentalists at the Max-Planck-Institute, the Department for Brain and Cogniutive Science, M.I.T., and Harvard Medical School (USA). The ideal candidate should have a reasonable computational background, and at least some basic training in neuroscience. Payment is, dependent on prior experience, according to BAT II for 3 years (extendable). Starting date should be as soon as possible. The position is funded by the German Volkswagen Foundation. For further information please contact: Dr. Martin Giese Laboratory for Action Representation and Learning Max-Planck-Institut for Biological Cybernetics Spemannstr. 34 D-72076 Tuebingen GERMANY Email: martin.giese at tuebingen.mpg.de Applicants are asked to submit their CV, a bibliography, and the names of two references. Applications and references should be sent by email to the same address. -------------------------------------------------------- Dr. Martin Giese Laboratory for Action Representation and Learning Max-Planck-Institut for Biological Cybernetics Spemannstr. 34 D-72076 Tuebingen GERMANY Email: martin.giese at tuebingen.mpg.de -------------------------------------------------------- From jose at psychology.rutgers.edu Mon Nov 5 07:02:09 2001 From: jose at psychology.rutgers.edu (stephen jose hanson) Date: Mon, 05 Nov 2001 07:02:09 -0500 Subject: FACULTY POSITION--PSYCHOLOGY DEPARTMENT --RUTGERS-Newark Message-ID: <3BE67FC1.BD7C76AC@psychology.rutgers.edu> RUTGERS UNIVERSITY-Newark Campus. The Department of Psychology anticipates making one tenure track , Assistant Professor level appointment in area of COGNITIVE SCIENCE. In particular we are seeking individuals in one any of the THREE following areas: LEARNING (Cognitive Modeling), COMPUTATIONAL NEUROSCIENCE or SOCIAL-COGNITION (interests in neuroimaging in any of these areas would also be a plus, since the Department in conjunction with UMDNJ has recently acquired a 3T Neuroimaging Center (see http://www.psych.rutgers.edu/fmri). Candidates must be effective teachers at the graduate and undergraduate levels. Review of applications begin JANUARY 30th, 2002, pending final budgetary approval from the administration. Rutgers University is an equal opportunity/affirmative action employer. Qualified women and minority candidates are encouraged to apply. Please send a CV, a statement of current and future research interests, and three letters of recommendation to COGNITIVE SCIENCE SEARCH COMMITTEE, Department of Psychology, Rutgers University, Newark, NJ 07102. Email enquires can be made to cogsci at psychology.rutgers.edu. Also see, http://www.psych.rutgers.edu. From tom at mbfys.kun.nl Wed Nov 7 05:12:03 2001 From: tom at mbfys.kun.nl (Tom Heskes) Date: Wed, 07 Nov 2001 11:12:03 +0100 Subject: opening at SNN Nijmegen Message-ID: <3BE908F3.81F40CFD@mbfys.kun.nl> Postdoc or PhD position at SNN Nijmegen ======================================= SNN at the University of Nijmegen, The Netherlands, offers a Postdoc or PhD position for a computer scientist, statistician or physicist with interest in machine learning, (dynamical) Bayesian networks and affiliated techniques. The candidate will be assigned to work on the STW project "Sales forecasting through aggregation". Within this project, our aim is to develop Bayesian methodology to handle and learn from a large amount of similar time series. This project is a collaboration with Eindhoven Technical University. From a postdoc, we expect a PhD in physics, mathematics or computer science and a solid background in machine learning and statistics. Excellent candidates interested in a PhD position can apply as well. SNN Nijmegen offers a stimulating research environment, with 10 researchers and PhD students working on theoretical and practical aspects of neural and Bayesian networks, machine learning, and computational neuroscience. We are part of the Department of Biophysics which is involved in experimental brain research. Work of our group has been commercialized successfully through the company SMART Research BV. More information on our research interests can be found at http://www.snn.kun.nl/nijmegen. The postdoc salary will be between Dfl. 5847 and Dfl. 7995 per month, depending on experience. The position is available for 2 years with possible extension to 4 years. The PhD position will be for 4 years with salary from Dfl. 3268 per month in the first year to Dfl. 4666 in the fourth. Interested candidates are asked to submit their CV and a list of publications by regular or e-mail to Tom Heskes SNN, University of Nijmegen Geert Grooteplein 21 6525 EZ Nijmegen The Netherlands tom at mbfys.kun.nl For further information, feel free to contact me at tom at mbfys.kun.nl or +31 24 3615039. From coenen at csl.sony.fr Wed Nov 7 23:55:07 2001 From: coenen at csl.sony.fr (Olivier Coenen) Date: Wed, 07 Nov 2001 20:55:07 -0800 Subject: Post-doctoral and Ph.D.student positions Message-ID: <3BEA102B.2A76EB48@csl.sony.fr> Post-doctoral and Ph.D. Student Positions available IN THEORETICAL AND COMPUTATIONAL NEUROSCIENCE Sony Computer Science Laboratory - Paris A post-doctoral research associate position and a Ph.D. student position are available immediately for theoretical and computational studies of sensorimotor integration and control. Highly motivated and creative individuals are sought for a period of 1 1/2 year (Post-doctoral) and up to 3 years (Ph.D. student) to join our research efforts. The interested candidates will be building mathematical and computational models of neural processing, with a particular emphasis on representation and learning in the cerebellum. Research interests include unsupervised learning, information theory and probabilistic approaches to representation and learning in networks of (spiking) neurons, reinforcement learning and robotic learning and control. The candidates will have the opportunity to work across disciplines and levels of investigation, from analytical models and detailed compartmental models of neurons to the creation of a unique computing platform. The models will be informed and constrained by neurobiological and psychological data. Current collaborations will give the candidates the possibility to interact closely with theoreticians, experimental neurophysiologists, and computer and hardware scientists at universities in Paris and abroad. The Sony Computer Science Laboratory is a fundamental research center located in the Quartier Latin, in the center of Paris. It is next door to the renown Ecole Normale Superieure and only a few steps away from a large number of universities in Paris (Sorbonne, Jussieu, College de France, etc.). The laboratory has interests in cognition, music, language, and robotics. Candidates should have a solid analytical background and a keen interest in neuroscience. Experience in machine learning algorithms and in computational models is desirable. Excellent computer programming skills (Matlab, C or C++) are essential. Applicants should send in plain text or pdf format a curriculum vitae (CV) with a list of publications (PhD applicants should include details of course work and grades), a statement of research interests, and names, addresses, emails and phone numbers of at least three referees to coenen at csl.sony.fr (email preferred) or to: Olivier J.-M. D. Coenen, Ph.D. Sony Computer Science Laboratory - Paris 6, rue Amyot 75005, Paris France Phone: +33 1 44 08 05 04 Fax: +33 1 45 87 87 50 http://www.csl.sony.fr (Interested candidates may also get in touch at the Society for Neuroscience meeting in San Diego). From dimi at ci.tuwien.ac.at Wed Nov 7 10:05:42 2001 From: dimi at ci.tuwien.ac.at (Evgenia Dimitriadou) Date: Wed, 7 Nov 2001 16:05:42 +0100 (CET) Subject: CI BibTeX Collection -- Update Message-ID: The following volumes have been added to the collection of BibTeX files maintained by the Vienna Center for Computational Intelligence: IEEE Transactions on Evolutionary Computation, Volumes 5/1-5/5 IEEE Transactions on Fuzzy Systems, Volumes 9/1-9/4 IEEE Transactions on Neural Networks, Volumes 12/1-12/5 Machine Learning, Volumes 43/3-46/3 Neural Computation, Volumes 13/2-13/11 Neural Networks, Volumes 14/4-14/9 Neural Processing Letters, Volumes 13/2-14/2 Most files have been converted automatically from various source formats, please report any bugs you find. The complete collection can be downloaded from http://www.ci.tuwien.ac.at/docs/ci/bibtex_collection.html ftp://ftp.ci.tuwien.ac.at/pub/texmf/bibtex/ Best, Vivi ************************************************************************ * Evgenia Dimitriadou * ************************************************************************ * Institut fuer Statistik * Tel: (+43 1) 58801 10773 * * Technische Universitaet Wien * Fax: (+43 1) 58801 10798 * * Wiedner Hauptstr. 8-10/1071 * Evgenia.Dimitriadou at ci.tuwien.ac.at * * A-1040 Wien, Austria * http://www.ci.tuwien.ac.at/~dimi* ************************************************************************ From d.mareschal at bbk.ac.uk Thu Nov 8 04:44:58 2001 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Thu, 8 Nov 2001 10:44:58 +0100 Subject: Faculty position Message-ID: Readers of this list may be interested in the following job opening at Birkbeck College. We are looking for a Lecturer in Cognitive Neuropsychology of Language. However, candidates with related research interests will also be considered providing they can fulfill the teaching and administrative responsibilities and contribute to one of the areas of research strength within the School. Details of the position can be obtained from the following web page: http://www.psyc.bbk.ac.uk/announce/index.html In addition, informal enquires may be made to: Dr Simon Green, Head of School of Psychology: email s.green at bbk.ac.uk Or Professor Mark Johnson, School of Psychology: email mark.johnson at psychology.bbk.ac.uk Further information is also on the School's web site: http://www.psyc.bbk.ac.uk ================================================= Dr. Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 (0)20 7631-6582/6323 reception: 6207 fax +44 (0)20 7631-6312 http://www.psyc.bbk.ac.uk/staff/dm.html ================================================= From crocker at CoLi.Uni-SB.DE Fri Nov 9 09:24:29 2001 From: crocker at CoLi.Uni-SB.DE (Matthew Crocker) Date: Fri, 9 Nov 2001 15:24:29 +0100 Subject: PhD Studentships: Saarbruecken-Edinburgh Message-ID: <7C6EF97C-D51D-11D5-A06B-0003930AC5B0@coli.uni-sb.de> Saarland University is pleased to announce the availability of three doctoral scholarships within the recently established European Post-Graduate College "Language Technology and Cognitive Systems" Saarbruecken - Edinburgh starting in April 1st, 2002. Each scholarship will be funded for two years (extendable to three years). Doctoral degrees may be obtained in computational linguistics, phonetics, and informatics (computer science), from Saarland University. The European Post-Graduate College has been established in cooperation between Saarland University and the University of Edinburgh (Division of Informatics) - two leading institutions in the fields of Computational Linguistics, Artificial Intelligence and Cognitive Science who are collaborating in offering a joint post-graduate education programme. The cooperation includes * a six to twelve months research stay in Edinburgh * joint supervision of dissertations by lecturers from Saarbruecken and Edinburgh * an intensive research exchange programme between Saarbruecken and Edinburgh (including, for example, an annual two-week forum attended by college members and lecturers from both centres) The college focuses on the computational and cognitive foundations of human language processing, particularly emphasising the following research areas: * inference and reasoning * knowledge representation, lexicon, and ontology * data-intensive language models (including corpus-based and statistical language modelling) * dialogue and language generation (computational and cognitive models) * language understanding Lecturers in Saarbruecken are M. Pinkal, H. Uszkoreit (computational linguistics), W. Barry (phonetics), M. Crocker (psycholinguistics), M. Kohlhase, J. Siekmann, G. Smolka, W. Wahlster (informatics/AI). In Edinburgh, lecturers include M. Fourman, E. Klein, A. Lascarides, C. Mellish, J. Moore, J. Oberlander, M. Osborne, M. Pickering, M. Steedman, P. Taylor, B. Webber, and C. Williams. The scholarship provides up to DM 2,870 per month. Additional compensation includes family allowance (where applicable), travel funding, and an additional monthly allowance of approximately DM 1,410 for the stay in Edinburgh. Applicants should hold a strong university degree in one of the relevant areas, preferably at the Masters level (equivalent to German Diplom) and should not be more than 28 years of age. Female scientists and international students are particularly encouraged to apply. Applications should include: 1. a curriculum vitae (including a list of publications, where possible) 2. a sample of written work (e.g. research paper, or dissertation, preferably in English) 3. copies of high school and university degree certificates 4. two references (to be sent directly to the college speaker) 5. an informal cover letter specifying interests, previous knowledge and activities in any of the relevant research areas. The letter should indicate the area in which the dissertation is to be conducted (computational linguistics, phonetics, or informatics/AI): where possible, it should include a brief outline of research interests to be pursued within the scholarship. Applications should be sent (hardcopy format strongly preferred) to the speaker of the college (see address below). Closing date for applications is Dec 14th, 2001. Prof. Dr. Matthew Crocker (Speaker) Department of Computational Linguistics Saarland University P.O. Box 15 11 50 D-66041 Saarbruecken Tel: +49 (0)681 302-6560 E-mail: egk-admin at coli.uni-sb.de Fax: +49 (0)681 302-6561 Internet: http://www.coli.uni-sb.de/egk From doya at atr.co.jp Sat Nov 10 01:35:15 2001 From: doya at atr.co.jp (Kenji Doya) Date: Sat, 10 Nov 2001 15:35:15 +0900 Subject: Research positions: computational neuroscience and robotics Message-ID: <20011110063517.16167@mwd.biglobe.ne.jp> ---- Kenji Doya ATR Human Information Science Laboratories; CREST, JST 2-2-2 Hikaridai, Seika, Soraku, Kyoto 619-0288, Japan Phone:+81-774-95-1251; Fax:+81-774-95-1259 http://www.atr.co.jp/his/~doya Post-doctoral Research Positions Computational Neuroscience and Robotics Metalearning and Neuromodulation "Creating the Brain", CREST, JST http://www.atr.co.jp/his/nip/crest/ Post-doctoral positions are available immediately for the following research subjects: 1) Metalearning Models of Neuromodulators: The goal of the research is to build a theory of the functions and the dynamics of neuromodulators, such as dopamine, serotonin, and norepinephrine. The candidate should build computational models based on the theory of metalearning, which can be tested through collaborations with experimental laboratories. 2) Cyber Rodent Project: We are building a multi-agent experimental platform for the studies of learning, metalearning, communication, and evolution. The candidate will develop learning and control algorithms for foraging, nesting, and gene exchanges by small mobile robots. Candidates should have a strong background in theoretical and/or experimental sciences, including neurobiology, psychology, computer science, robotics, physics and mathematics. Competitive salaries and benefits are provided by JST (Japan Science and Technology Corporation). The laboratory is located at ATR International in Kyoto, where people from diverse origins and backgrounds get together for basic research on human cognition and telecommunication. Applicants should send a CV, a statement of research interests, and recent reprints and/or preprints by December 15th, 2001 to Kenji Doya ATR Human Information Science Laboratories 2-2-2 Hikaridai, Seika, Soraku Kyoto 619-0288, Japan For more information, please contact nip-info at his.atr.co.jp or visit our web pages at http://www.atr.co.jp/his/nip/crest/ ---- Kenji Doya ATR Human Information Science Laboratories; CREST, JST 2-2-2 Hikaridai, Seika, Soraku, Kyoto 619-0288, Japan Phone:+81-774-95-1251; Fax:+81-774-95-1259 http://www.atr.co.jp/his/~doya From Patrick.DeMaziere at antwerpen.be Mon Nov 12 09:43:57 2001 From: Patrick.DeMaziere at antwerpen.be (Patrick De Maziere) Date: Mon, 12 Nov 2001 15:43:57 +0100 Subject: Postdoctoral position Message-ID: <3BEFE02D.5C91E795@neuro.kuleuven.ac.be> MR RESEARCH CENTRE Department of Radiology University Hospital, Katholieke Universiteit Leuven Leuven (Belgium) Postdoctoral position The Magnetic Resonance (MR) Research Centre of the Department of Radiology and the Faculty of Medicine of the Katholieke Universiteit Leuven, Belgium has a vacant position for a physicist or (bio)engineer (preferably postdoc) on a European Project (Fifth Framework) on Functional Magnetic Resonance (fMRI) in the human and in the monkey. The research is a collaboration with the Laboratory of Neurophysiology of the Faculty of Medicine (G.A. Orban, Coordinator) of the K.U.Leuven, INRIA (Sophia-Antipolis, Fran ce) and the Technical University of Denmark (Lyngby). Functional MR imaging is a recent technique for the non-invasive visualisation of neuronal activity in the human and in animals. The MR Research Centre has specialized the last five years in both basic neuroscience and in clinical applications of fMRI. The task of the candidate is the development of new fMRI acquisition techniques and methods, to optimize the spatial and temporal resolution, as well as the S/N, using new data processing algorithms, developed by the partners of the project. A background and some experience in Magnetic Resonance (Imaging) is a prerequisite. The applicant will be offered a salary in accordance with official baremas, commensurate with his training and experience. The project ends september 2003. For more information, please contact Prof. Paul Van Hecke NMR, Radiology University Hospital Gasthuisberg B-3000 Leuven Belgium Tel: +32 16 34 37 80 e-mail: paul.vanhecke at med.kuleuven.ac.be From: esann To: "Connectionists at cs.cmu.edu" References: From bogus@does.not.exist.com Tue Nov 13 06:15:39 2001 From: bogus@does.not.exist.com () Date: Tue, 13 Nov 2001 12:15:39 +0100 Subject: ESANN proceedings available on-line Message-ID: ---------------------------------------------------- | | | ESANN proceedings available on-line | | | | European Symposium | | on Artificial Neural Networks | | | ---------------------------------------------------- Dear colleagues, We are pleased to announce that all proceedings of the past ESANN conferences (European Symposium on Artificial Neural Networks) are now available on-line (full papers) on the Web site of the conference (http://www.dice.ucl.ac.be/esann/); click on "Proceedings" in the left menu and then on the link in the "Electronic proceedings" section. This is a 100% free service to the scientific community intended to ensure the widest possible dissemination to the publications. Papers are available on the site in PDF format. Some abstracts are still missing, and some papers had to be scanned (instead of being converted from the original electronic files). We would appreciate if authors of papers could help us to complete this site. Notes to authors: ----------------- 1) We converted in PDF format all files provided by the authors; nevertheless most papers from the first ESANN conferences had to be scanned. If, as author, you still have an electronic version of a paper available on the site as scanned version, please send it by e-mail (esann at dice.ucl.ac.be) and we will replace the scanned document by your electronic version (Postscript or PDF format). 2) If, as author, you have an abstract which is not yet available on the site, please send it by e-mail (esann at dice.ucl.ac.be). In both cases, we would appreciate if you could include in the "Subject" field of your e-mail the number of your paper; this number may be found right above the title of your paper, in each of the ESANN proceedings lists. 3) You are free to download, copy and distribute any paper contained in these pages, provided that you keep the reference of the paper that has been added as header to each page. If you maintain your own Web site with an electronic version of your ESANN paper(s), please only use the version available on the ESANN site; having the reference added as header will help the researchers who download your papers to cite them in their own publications. Thank you in advance for your help! Sincerely yours, The ESANN organizing committee. ======================================================== ESANN - European Symposium on Artificial Neural Networks http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews,... Michel Verleysen Univ. Cath. de Louvain - Microelectronics Laboratory 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at dice.ucl.ac.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at dice.ucl.ac.be ======================================================== From phkywong at ust.hk Tue Nov 13 06:28:49 2001 From: phkywong at ust.hk (K. Y. Michael Wong) Date: Tue, 13 Nov 2001 19:28:49 +0800 (HKT) Subject: Postdoc Position Announcement Message-ID: Postdoc Position Announcement There is an opening for a one-year postdoctoral research associateship in my research group on the application of many-body physics in information processing. The work involves the use of many-body techniques in the dynamics and statics of information processing, such as learning, parameter estimation, error-correcting codes and data-mining. Potential candidates should have strong mathematical and computational skills. Background in statistical physics, many-body physics, or statistics will be useful. The salary ranges from HKD18,000 to HKD20,000 per month. If you are interested in the position, please send a full CV and publication list, together with the names of three referees, either by postage, e-mail or fax. The correspondence is: Dr. K. Y. M. Wong, Department of Physics, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong. E-mail: phkywong at ust.hk Fax: +852-2358 1652 Phone: +852-2358 7480 From cindy at cns.bu.edu Tue Nov 13 10:24:27 2001 From: cindy at cns.bu.edu (Cynthia Bradford) Date: Tue, 13 Nov 2001 10:24:27 -0500 Subject: Neural Networks 14(10) Message-ID: <200111131524.KAA28587@retina.bu.edu> NEURAL NETWORKS 14(10) Contents - Volume 14, Number 10 - 2001 ------------------------------------------------------------------ CONTRIBUTED ARTICLES: ***** Psychology and Cognitive Science ***** Connectionist inference models Antony Browne and Ron Sun ***** Neuroscience and Neuropsychology ***** Analysis of the frequency response of the saccadic circuit: Numerical simulations Mark E. Jackson, Oleg Litvak, and James W. Gnadt ***** Mathematical and Computational Analysis ***** Unified stabilization approach to principal and minor components extraction algorithms Tianping Chen and Shun-ichi Amari Improvement of generalization ability for identifying dynamic systems by using universal learning networks Kotaro Hirasawa, Sung-ho Kim, Jinglu Hu, Junichi Murata, Min Han, and Chunzhi Jin Self-organization in the one-dimensional SOM with a decreasing neighborhood John A. Flanagan Upper bound of the expected training error of neural network regression for a Gaussian noise sequence Katsuyuki Hagiwara, Taichi Hayasaka, Naohiro Toda, Shiro Usui, and Kazuhiro Kuno The POP learning algorithms: Reducing work in identifying fuzzy rules C. Quek and R.W. Zhou ***** Engineering & Design ***** Oriented principal component analysis for large margin classifiers Sergio Bermejo and Joan Cabestany ***** Letters to the Editor ***** A remark on "On stability of nonlinear continuous-time neural networks with delays" Yuming Chen On using the Poincare polynomial for calculating the V-C dimension of neural networks Michael Schmitt Response: On using the Poincare polynomial for calculating the V-C dimension of neural networks Martha A. Carter and Mark E. Oxley ***** Erratum ***** Evaluating the Vapnik-Chervonenkis dimension of artificial neural networks using the Poincare polynomial (Neural Networks, 1999, 12, 403-408) Martha A. Carter and Mark E. Oxley ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 (regular) SEK 660 (regular) Y 13,000 (regular) Neural Networks (plus 2,000 enrollment fee) $20 (student) SEK 460 (student) Y 11,000 (student) (plus 2,000 enrollment fee) ----------------------------------------------------------------------------- membership without $30 SEK 200 not available to Neural Networks non-students (subscribe through another society) Y 5,000 (student) (plus 2,000 enrollment fee) ----------------------------------------------------------------------------- Name: _____________________________________ Title: _____________________________________ Address: _____________________________________ _____________________________________ _____________________________________ Phone: _____________________________________ Fax: _____________________________________ Email: _____________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number ____________________________ expiration date ________________________ INNS Membership 19 Mantua Road Mount Royal NJ 08061 USA 856 423 0162 (phone) 856 423 3420 (fax) innshq at talley.com http://www.inns.org ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership c/o Professor Takashi Nagano Faculty of Engineering Hosei University 3-7-2, Kajinocho, Koganei-shi Tokyo 184-8584 Japan 81 42 387 6350 (phone and fax) jnns at k.hosei.ac.jp http://jnns.inf.eng.tamagawa.ac.jp/home-j.html ----------------------------------------------------------------- From bernabe at imse.cnm.es Thu Nov 15 06:58:20 2001 From: bernabe at imse.cnm.es (Bernabe Linares B.) Date: Thu, 15 Nov 2001 12:58:20 +0100 (MET) Subject: Call for Papers on NN Hardware Message-ID: <200111151158.MAA03377@cnm30.imse.cnm.es> CALL FOR PAPERS: IEEE TRANS. ON NEURAL NETWORKS Special Issue on NEURAL NETWORKS HARDWARE IMPLEMENTATIONS This is to announce a forthcomming Special issue on NN hardware implementations in the IEEE Trans. on Neural Networks. Paper submission deadline is September 15th, 2002. Issue will be published September 2003. The details of the "Call for Papers" are available at: http://www.imse.cnm.es/~bernabe/CFPNN.html or in PDF format: http://www.imse.cnm.es/~bernabe/CFPNN.pdf Please announce and distribute to potential authors. ------------------------------------------------------------------------- Bernabe Linares-Barranco, PhD Tenured Scientist (Cientifico Titular) CSIC Instituto Microelectronica Sevilla (IMSE) Phone: 34-95-505-6670/66 National Microelectronics Center, CNM-CSIC Fax: 34-95-505-6686 Ed. CICA, Av. Reina Mercedes s/n E-mail: bernabe at imse.cnm.es 41012 Sevilla, SPAIN URL: http://www.imse.cnm.es/~bernabe ------------------------------------------------------------------------- From abrowne at lgu.ac.uk Thu Nov 15 06:15:23 2001 From: abrowne at lgu.ac.uk (Tony Browne) Date: Thu, 15 Nov 2001 11:15:23 +0000 (GMT Standard Time) Subject: Extrapolation preprint Message-ID: Apologies if you receive this posting more than once. A preprint is available for download, of the paper 'Representation and Extrapolation in Multi-Layer Perceptrons' by Antony Browne (to appear in `Neural Computation'). 20 Pages, 27 References. Abstract: To give an adequate explanation of cognition and perform certain practical tasks connectionist systems must be able to extrapolate. This work has explored the relationship between input representation and extrapolation, using simulations of multi-layer perceptrons trained to model the identity function. It has been discovered that representation has a marked effect on extrapolation. Keywords: Extrapolation, distributed representation, localist representation, identity task, circular convolution. Download Instructions: Go to http://www.lgu.ac.uk/~abrowne/abrowne.htm and scroll down to the section 'Downloadable Technical Reports and Preprints'. Click on the file to download (in zipped Postscript or PDF format). Comments Welcome If you have problems downloading, please e-mail me. Tony Browne ======================================================= Dr. Antony Browne Reader in Intelligent Systems School of Computing, Information Systems & Mathematics London Guildhall University 100 Minories, London EC3 1JY, UK E-mail: abrowne at lgu.ac.uk http://www.lgu.ac.uk/~abrowne/abrowne.htm Tel: (+44) 0207 320 1708 or 1700 Fax: (+44) 0207 320 1717 ======================================================= From angelo at soc.plym.ac.uk Fri Nov 16 09:39:11 2001 From: angelo at soc.plym.ac.uk (Angelo Cangelosi) Date: Fri, 16 Nov 2001 14:39:11 +0000 Subject: Book announcement: Simulating the Evolution of Language Message-ID: <3.0.6.32.20011116143911.0115e348@hebe.soc.plym.ac.uk> New book announcement: Cangelosi A. & Parisi D. (Eds.) (2001). Simulating the Evolution of Language. London: Springer. http://www.tech.plym.ac.uk/soc/staff/angelo/book2001-TOC.html SUMMARY This volume provides a comprehensive survey of the computational models and methodologies used for studying the origin and evolution of language and communication. With contributions from the most influential figures in the field, Simulating the Evolution of Language presents and summarises current computational approaches to language evolution and highlights new lines of development. Among the main discussion points are: Analysis of emerging linguistic behaviours and structures Demonstration of the strict interaction and interdependence between language and other non-linguistic abilities Direct comparisons between simulation studies and empirical research Essential reading for researchers and students in the areas of evolutionary and adaptive systems, language evolution, modelling and linguistics, it will also be of particular interest to computer scientists working on multi-agent systems, robotics and internet agents. TABLE OF CONTENT PART I INTRODUCTION Chapter 1: Computer Simulation: A New Scientific Approach to the Study of Language Evolution Angelo Cangelosi & Domenico Parisi Chapter 2: An Introduction to Methods for Simulating the Evolution of Language Huck Turner PART II EVOLUTION OF SIGNALING SYSTEMS Chapter 3: Adaptive Factors in the Evolution of Signaling Systems Jason Noble, Ezequiel Di Paolo, Seth Bullock Chapter 4: Evolving Sound Systems Bart De Boer Chapter 5: The Evolution of Dialect Diversity Daniel Livingstone PART III EVOLUTION OF SYNTAX Chapter 6: The Emergence of Linguistic Structure: An Overview of the Iterated Learning Model Simon Kirby & Jim Hurford Chapter 7: Population Dynamics of Grammar Acquisition Natalia L. Komarova & Martin A. Nowak Chapter 8: The role of sequential learning in language evolution: Computational and experimental studies Morten Christiansen, Michelle R. Ellefson, Christopher M. Conway & Rick A.C. Dale PART IV GROUNDING OF LANGUAGE Chapter 9: Symbol Grounding and the Symbolic Theft Hypothesis Angelo Cangelosi, Alberto Greco & Stevan Harnad Chapter 10: Grounding Symbols through Evolutionary Language Games Luc Steels PART V BEHAVIORAL AND NEURAL FACTORS Chapter 11: Grounding the Mirror System Hypothesis for the Evolution of the Language-ready Brain Michael Arbib Chapter 12: A Unified Simulation Scenario for Language Development, Evolution, and Historical Change Domenico Parisi & Angelo Cangelosi PART VI BEHAVIORAL AND NEURAL FACTORS Chapter 13: Auto-Organisation and Emergence of Shared Language Structure Edwin Hutchins & Brian Hazlehurst Chapter 14: The constructive approach to the dynamical view of language Takashi Hashimoto ( PART VII CONCLUSION Chapter 15: Some Facts about Primate (including Human) Communication and Social Learning Michael Tomasello -------------------- Angelo Cangelosi, PhD ----------------------- Senior Lecturer, Centre for Neural and Adaptive Systems School of Computing, University of Plymouth 9 Kirkby Place Plymouth PL4 8AA (UK) E-mail: a.cangelosi at plymouth.ac.uk http://www.tech.plym.ac.uk/soc/staff/angelo (tel) +44 1752 232559 (fax) +44 1752 232540 From jfeldman at ICSI.Berkeley.EDU Fri Nov 16 19:20:11 2001 From: jfeldman at ICSI.Berkeley.EDU (Jerome Feldman) Date: Fri, 16 Nov 2001 16:20:11 -0800 Subject: Asst. Prof. positions at UC Berkeley Message-ID: <3BF5AD3B.B5A54DF4@icsi.berkeley.edu> THE UNIVERSITY OF CALIFORNIA AT BERKELEY invites applications for tenure-track positions in ELECTRICAL ENGINEERING AND COMPUTER SCIENCES at the ASSISTANT PROFESSOR level beginning in Fall Semester 2002. One of the positions may involve a joint appointment with the Helen Wills Neuroscience Institute at UC, Berkeley. Several faculty searches have been approved. We are also considering the possibility of joint searches with other UC Berkeley departments. The joint position with Neuroscience would be in the area of Computational Neuroscience, broadly defined. Applicants should have received (or be about to receive) a doctoral degree in Computer Science, Electrical Engineering, or Computer Engineering or a related field. All areas of research in Computer Science and Electrical Engineering will be considered. For the shared position with Neuroscience, the degree may be in Neuroscience or related fields with a strong emphasis in Computational Neuroscience. A principal requirement is demonstrated excellence in research. In addition, potential for excellence in teaching and leadership are important requirements. Successful applicants will be expected to set up a quality research program and to teach both graduate and undergraduate courses in their general area of specialty. Interested persons should send a resume, a select subset of publications, a one- to two-page statement of their future research plans and interests, and the names of three references to the appropriate address below. We will not consider applications received after April 1, 2002. However, review of completed applications will begin January 10, 2002. The applicant should request their references to forward letters of reference directly to the same address to arrive before February 1, 2002. These letters will NOT be requested directly by the department. Electrical Engineering applications should be sent to: EE Faculty Search Committee Chair c/o Jean Richter Department of Electrical Engineering and Computer Sciences 231 Cory Hall # 1770 University of California, Berkeley Berkeley, California 94720-1770 Computer Science and Computational Neuroscience applications should be sent to: CS Faculty Search Committee Chair c/o Debra Zaller Department of Electrical Engineering and Computer Sciences 381 Soda Hall # 1776 University of California, Berkeley Berkeley, California 94720-1776 -- Jerome Feldman ICSI & EECS UC Berkeley "O wad some Pow'r the giftie gie us 1947 Center St. To see oursels as other see us!" Berkeley CA 94704 Robert Burns - To a Louse From aonishi at bsp.brain.riken.go.jp Sun Nov 18 21:39:30 2001 From: aonishi at bsp.brain.riken.go.jp (Toru Aonishi) Date: Mon, 19 Nov 2001 11:39:30 +0900 Subject: Papers on coupled oscillators Message-ID: <20011119113930H.aonishi@bsp.brain.riken.go.jp> Dear Connectionists, I am pleased to announce the availability of my recent paper and of one potentially related paper. Recent paper: ------------- Multibranch entrainment and slow evolution among branches in coupled oscillators T. Aonishi and M. Okada, Physical Review Letters (in press) Available at http://arXiv.org/abs/cond-mat/0104526 Abstract: In globally coupled oscillators, it is believed that strong higher harmonics of coupling functions are essential for {\it multibranch entrainment} (MBE), in which there exist many stable states, whose number scales as $\sim$ $O(\exp N)$ (where $N$ is the system size). The existence of MBE implies the non-ergodicity of the system. Then, because this apparent breaking of ergodicity is caused by {\it microscopic} energy barriers, this seems to be in conflict with a basic principle of statistical physics. In this paper, using macroscopic dynamical theories, we demonstrate that there is no such ergodicity breaking, and such a system slowly evolves among branch states, jumping over microscopic energy barriers due to the influence of thermal noise. This phenomenon can be regarded as an example of slow dynamics driven by a perturbation along a neutrally stable manifold consisting of an infinite number of branch states. Related paper: -------------- Statistical mechanics of an oscillator associative memory with scattered natural frequencies T. Aonishi, K. Kurata and M. Okada, Physical Review Letters, 82[13], pp. 2800--2803 (1999) Available at http://prl.aps.org/ http://arXiv.org/abs/cond-mat/9808090 Abstract: Analytic treatment of a non-equilibrium random system with large degrees of freedoms is one of most important problems of physics. However, little research has been done on this problem as far as we know. In this paper, we propose a new mean field theory that can treat a general class of a non-equilibrium random system. We apply the present theory to an analysis for an associative memory with oscillatory elements, which is a well-known typical random system with large degrees of freedoms. Regards, Toru Aonishi (Ph.D) Laboratory for Advanced Brain Signal Processing Brain Science Institute The Institute of Physical and Chemical Research (RIKEN) Hirosawa, 2-1, Wako-shi, Saitama, 351-0198, Japan E-mail: aonishi at brain.riken.go.jp URL: http://www.bsp.brain.riken.go.jp/~aonishi/ From steve at cns.bu.edu Mon Nov 19 09:17:56 2001 From: steve at cns.bu.edu (Stephen Grossberg) Date: Mon, 19 Nov 2001 09:17:56 -0500 Subject: Postdoc in vision and recognition at Boston University Message-ID: POSTDOCTORAL FELLOW DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS BOSTON UNIVERSITY A postdoctoral fellow is sought to join the Boston University Department of Cognitive and Neural Systems, with funding from an AFOSR grant: "A unified brain architecture for perception and cognition with applications to information processing technology." The fellowship is available immediately for a minimum term of two years. The postdoc would collaborate with Professors Gail Carpenter and Stephen Grossberg on basic research and technology transfer efforts. Candidates should have substantial training in developing neural network models of biomimetic vision/image processing and/or adaptive pattern recognition. The CNS Department offers excellent opportunities for broadening knowledge of neural modeling and applications, as summarized at http://www.cns.bu.edu . Boston University is an Equal Opportunity/Affirmative Action Employer. Please send a curriculum vitae, 3 letters of recommendation, and illustrative research articles to: Postdoctoral Search, Room 203, Department of Cognitive and Neural Systems, Boston University, 677 Beacon Street, Boston, MA 02215. From Wulfram.Gerstner at dimail.epfl.ch Tue Nov 20 03:54:49 2001 From: Wulfram.Gerstner at dimail.epfl.ch (Wulfram Gerstner) Date: Tue, 20 Nov 2001 09:54:49 +0100 Subject: PostDoc positions in Switzerland Message-ID: <3BFA1A59.AEEA6C43@di.epfl.ch> PostDoc positions in Computational Neuroscience in Lausanne The Laboratory of Computational Neuroscience at the Swiss Federal Institute of Technology in Lausanne (Switzerland) invites applications for 3 PostDoc positions in Computational Neuroscience. Members of the lab are interested in models of brain function and brain dynamics, especially models of spiking neurons/spike-time dependent learning rules, models of hippocampus/spatial navigation, and models of conditioning/reinforcement learning. For further details see: http://diwww.epfl.ch/mantra/ Candidates should have a strong analytical background and a keen interest in neuroscience. Competitive salaries are available. The Laboratory of Computational Neuroscience will be part of the new Brain and Mind Institutes on Campus and provides a unique opportunity to interact with world-class experimentalists. The city of Lausanne, situated on the shores of the Lake of Geneva, and surrounded by beautiful mountains, offers an exceptionally high qualitfy of life. Applicants should send in plain text format (i) a CV, (ii) a 1-page statement of research interests, (iii) names and addresses of three referees to brigitte.ramuz at epfl.ch (subject: PostDoc application) Closing date for applications: December 15 Starting dates of appointment: Between April and September 2002 -- Wulfram Gerstner Swiss Federal Institute of Technology Lausanne Professor Laboratory of Computational Neuroscience, DI-LCN 1015 Lausanne EPFL Tel. +41-21-693 6713 wulfram.gerstner at epfl.ch Fax. +41-21-693 5263 http://diwww.epfl.ch/mantra From K.Branney at elsevier.nl Tue Nov 20 08:18:10 2001 From: K.Branney at elsevier.nl (Branney, Kate (ELS)) Date: Tue, 20 Nov 2001 14:18:10 +0100 Subject: Cognitive Systems Research Message-ID: <46414F09B351C64BAA875CE0B37BE071A09884@elsamsvexch02.elsevier.nl> Apologies for multiple postings Special Offer for 2002 subscriptions to Cognitive Systems Research Cognitive Systems Research...the new journal devoted to the study of cognitive science To celebrate the launch of the new online journal, Cognitive Systems Research, Elsevier Science is pleased to offer institutions subscribing in 2002 extra archival material from 2000 and 2001. With each new subscription, institutions will receive FREE copies of the print copy of volumes 1 and 2, as well as Volume 3 at the end of 2002. A year's institutional subscription for 2002 costs just USD 308 or EUR 275, including THREE years' of archival material. Cognitive Systems Research seeks to foster and promote the discussion of novel approaches in studying cognitive and intelligent systems. It encourages cross-fertilization of disciplines. This is achieved by soliciting and publishing high-quality contributions in all of the areas of study in cognitive science, including artificial intelligence, linguistics, psychology, psychiatry, philosophy, system and control theory, anthropology, sociology, biological sciences, and neuroscience. The scope of the journal includes the study of a variety of different cognitive systems, at different levels, ranging from social/cultural cognition, to individual cognitive agents, to components of cognitive systems. Of particular interest are theoretical, experimental, computational, and integrative studies of cognitive systems at different levels of detail, and from different perspectives Call for Papers - Cognitive Systems Research covers all topics in the study of cognitive processes, in both natural and artificial systems. The journal seeks top-quality contributions and encourages, in particular, articles that transcend traditional disciplinary boundaries (in terms of implications or in terms of approaches). Please submit your papers via www.elsevier.com/locate/cogsys For subscription details, to view the abstracts, and for FREE access to the full PDFs until the end of 2001, please visit: www.elsevier.com/locate/cogsys Kate Branney Elsevier Science From malchiodi at dsi.unimi.it Tue Nov 20 10:07:50 2001 From: malchiodi at dsi.unimi.it (Dario Malchiodi) Date: Tue, 20 Nov 2001 16:07:50 +0100 Subject: Course at the International School on Neural Nets "E.R.Caianiello" - 2nd Announcement Message-ID: <3BFA71C6.692854D3@dsi.unimi.it> Many apologizes for cross posting The following meeting may be of interest to researchers interested in artificial intelligence, biology, neural networks and psychology FROM SYNAPSES TO RULES: DISCOVERING SYMBOLIC RULES FROM NEURAL PROCESSED DATA A course of INTERNATIONAL SCHOOL ON NEURAL NETS "E. R. CAIANIELLO" ETTORE MAJORANA CENTRE FOR SCIENTIFIC CULTURE ERICE-SICILY: 25 FEBRUARY - 7 MARCH 2002 Application deadline: December 15, 2001 The school aims at fixing a theoretical and applicatry framework for extracting formal rules from data. To this end the modern approaches will be expounded that collapse the two typical goals of the conventional AI and connectionism - respectively, deducing within an axiomatic shell formal rules about a phenomenon and inferring the actual behavior of it from examples - into a challenging inferential framework where we learn from data and understand what we have learnt. The target reads as a translation of the subsymbolic structure of the data - stored in the synapses of a neural network - into formal properties described by rules. To capture this trip from synapses to rules and then render it manageable for affording real world learning tasks, the Course will deal in depth with the following aspects: i. theoretical foundations of learning algorithms and soft computing, ii. intimate relationships between symbolic and subsymbolic reasoning methods, iii. integration of the related hosting architectures in both physiological and artificial brain. TOPICS Inferential bases for learning Theoretical foundations for soft computing Integration of symbolic-subsymbolic reasoning methods Physics and metaphysics of learning Toward applications LECTURERS * B. Apolloni, University of Milan, I * D. Malchiodi, University of Milan, I * D. Mundici, University of Milan, I * M. Gori, University of Siena, I * F. Kurfess, California Polytechnic State Univ., San Luis Obispo, CA, USA * A. Roy, Arizona State University, Tempe, AZ, USA * R. Sun, University of Missouri-Columbia, MO, USA * L. Agnati, Karolinska Institutet, Stockholm, S * G. Basti, Pontificia Universit? Lateranense, Rome, I * G. Biella, C.N.R. LITA, Milan, I * J. G. Taylor, King's College, London, UK * A. Esposito, Istituto Italiano Alti Studi Scientifici, Vietri, I * A. Moise, Boise State University, ID, USA DIRECTORS OF THE COURSE B. APOLLONI, A. MOISE DIRECTORS OF THE SCHOOL M. J. JORDAN, M. MARINARO DIRECTOR OF THE CENTRE A. ZICHICHI APPLICATIONS Interested candidates should send a letter to: * Professor Bruno Apolloni - Dipartimento di Scienze dell'Informazione Universit? degli Studi di Milano Via Comelico 39/41 20135 Milano, Italy Tel: ++39.02.5835.6284, Fax: ++39.02.5835.6228 e-mail: apolloni at dsi.unimi.it specifying: i) date and place of birth and present activity; ii) nationality. Thanks to the generosity of the sponsoring Institutions, partial support can be granted to some deserving students who need financial aid. Requests to this effect must be specified and justified in the letter of application. Notification of acceptance will be sent within the end of January 2002. For APPLICATION, CONTRIBUTING PAPERS, GRANTS, FEES, and further information please visit http://laren.usr.dsi.unimi.it/ericeSchool.html. For information about the Ettore Majorana Centre please visit http://www.ccsem.infn.it. From glanzman at helix.nih.gov Tue Nov 20 12:48:18 2001 From: glanzman at helix.nih.gov (Dennis Glanzman) Date: Tue, 20 Nov 2001 12:48:18 -0500 Subject: Joint NSF/NIH Initiative to Support Collaborative Research in Computational Neuroscience (CRCNS) Message-ID: <4.3.2.7.2.20011120124754.00b1fe30@helix.nih.gov> I would like to bring the following program announcement to your attention. The complete announcement may be accessed in HTML, PDF or ASCII format via the National Science Foundation's website at http://www.nsf.gov/cgi-bin/getpub?nsf02018 Please excuse duplicate mailings if you receive this notice more than once. Excerpts from the program announcement follow: JOINT NSF/NIH INITIATIVE TO SUPPORT COLLABORATIVE RESEARCH IN COMPUTATIONAL NEUROSCIENCE (CRCNS) The most exciting and difficult challenge facing neuroscientists is to understand the functions of complex neurobiological systems. Computational neuroscience provides a theoretical foundation and set of technological approaches that may enhance our understanding of nervous system function by providing analytical and modeling tools that describe, traverse and integrate different levels of organization, spanning vast temporal and spatial scales. Computational approaches are needed in the study of neuroscience as the requirement for comprehensive analysis and interpretation of complex data sets becomes increasingly important. Collaborations among computer scientists, cognitive scientists, engineers, theoreticians and neuorobiologists are imperative to advance our understanding of the nervous system. Participating Directorates of the National Science Foundation (NSF) and the Institutes of the National Institutes of Health (NIH) plan to support interdisciplinary research in computational neuroscience. Both agencies recognize the need for research that focuses on integrating computational models and methods with neuroscience. This solicitation is designed to encourage new and existing collaborations at this interface. ASSURANCE OF COLLABORATIVE RESEARCH EFFORT ACROSS SCIENTIFIC DISCIPLINES The driving principle behind this program solicitation is the recognition that projects crossing traditional academic interdisciplinary boundaries often bring about increased productivity and creativity when collaborative efforts include participation by scientists and engineers bringing their experience and training from widely varying backgrounds. Such interdisciplinary collaborations are required and should be demonstrated in the grant proposal, for example, by naming a co-investigator with academic credentials and appointment in an area different from that of the principal investigator, or by other means. A typical research collaboration might include a computer scientist and a neurobiologist. This interdisciplinary approach can also be demonstrated by a single investigator with appropriate multidisciplinary expertise. Proposals should describe interdisciplinary work to be done. Applications that are not clearly collaborative and/or interdisciplinary in nature will be returned without review. AWARD INFORMATION It is estimated that approximately $7.0 Million ($3.0 Million from NSF and $4.0 Million from NIH) will be available for this competition. Award sizes are expected to range from $100,000 to $500,000 per year with durations of 3-5 years. Estimated program budget, number of awards and average award size/duration are subject to the availability of funds. PROPOSAL PREPARATION AND SUBMISSION INSTRUCTIONS Letters of Intent: Must be submitted via email at crcns at nsf.gov by December 14, 2001. Letters of intent should be sent from the prospective PI by email to crcns at nsf.gov, and should contain the PI and the co-PI's names, a list of possible participating institutions, a possible title, and not more than 500 words to describe the work enough to permit intelligent choice of reviewers. Letters of intent will not be evaluated or used to decide on funding. They are requested to assist NSF and NIH in planning the review process. The submission of letters of intent enables NSF to begin choosing panelists before the proposal submission deadline. Full Proposal: Must be submitted by February 4, 2002. Proposals submitted in response to this program announcement/solicitation should be prepared and submitted in accordance with the general guidelines contained in the NSF Grant Proposal Guide (GPG). The complete text of the GPG is available electronically on the NSF Web Site at: http://= www.nsf.gov/cgi-bin/getpub?gpg. Paper copies of the GPG may be obtained from the NSF Publications Clearinghouse, telephone (301) 947-2722 or by e-mail from pubs at nsf.gov. -- Dennis L. Glanzman, Ph.D. Program Chief for Theoretical and Computational Neuroscience National Institute of Mental Health 6001 Executive Boulevard, MSC 9637 Bethesda, MD 20892-9637 Phone: 301.443.1576 Fax: 301.443.4822 From bengio at idiap.ch Wed Nov 21 02:05:32 2001 From: bengio at idiap.ch (Samy Bengio) Date: Wed, 21 Nov 2001 08:05:32 +0100 (CET) Subject: call for paper: NNSP'02, september 4-6, 2002 Message-ID: 2002 IEEE Workshop Neural Networks for Signal Processing September 4-6, 2002 Martigny, Valais, Switzerland http://eivind.imm.dtu.dk/nnsp2002 Sponsored by the IEEE Signal Processing Society In cooperation with the IEEE Neural Networks Council Call for Papers Thanks to the sponsorship of IEEE Signal Processing Society and IEEE Neural Network Council, the twelfth of a series of IEEE workshops on Neural Networks for Signal Processing will be held in Martigny (http://www.martigny.ch), Switzerland, at the ``Centre du Parc'' (http://www.hotelduparc.ch). The workshop will feature keynote addresses, technical presentations and panel discussions. Papers are solicited for, but not limited to, the following areas: Algorithms and Architectures: Artificial neural networks, kernel methods, committee models, independent component analysis, adaptive and/or nonlinear signal processing, (hidden) Markov models, Bayesian modeling, parameter estimation, generalization, optimization, design algorithms. Applications: Speech processing, image processing (computer vision, OCR), multimodal interactions, multi-channel processing, intelligent multimedia and web processing, robotics, sonar and radar, bio-medical engineering, bio-informatics, financial analysis, time series prediction, blind source separation, data fusion, data mining, adaptive filtering, communications, sensors, system identification, and other signal processing and pattern recognition applications. Implementations: Parallel and distributed implementation, hardware design, and other general implementation technologies. Further Information NNSP'2002 webpage: http://eivind.imm.dtu.dk/nnsp2002 Paper Submission Procedure Prospective authors are invited to submit a full paper of up to ten pages using the electronic submission procedure described at the workshop homepage. Accepted papers will be published in a hard-bound volume by IEEE and distributed at the workshop. Schedule Submission of full paper: April 15, 2002 Notification of acceptance: May 1, 2002 Camera-ready paper and author registration: June 1, 2002 Advance registration, before: July 15, 2002 Preliminary Programme September 4, AM: Pleanry talk by Mahesan Niranjan, Sheffield University "From Kalman to Particle Filtering for solving Signal Processing Problems with Neural Networks" Regular session, including oral and poster presentations September 4, PM: Special session on "Machine Learning and statistical approaches for Bio-Informatic Applications", Plenary talk by Anders Krogh, University of Denmark "Hidden Markov models of proteins and DNA", followed by special session, including oral and poster presentations September 5, AM: Plenary Talk: Yoshua Bengio, University of Montreal "Faking unlabeled data for geometric regularization" Regular session, including oral and poster presentations September 5, PM: Special session on "Multimodal/multi-channel processing" Plenary talk by Josef Kittler, University of Surrey "Fusion of multiple experts in multimodal biometric personal identity verification systems" September 6, AM: Plenary talk by Zoubin Ghahramani, Gatzby Institute, UK "Occam's Razor and Infinite Models" Regular oral and poster sessions. Invited Speakers Yoshua Bengio, University of Montreal Title of the talk: Faking unlabeled data for geometric regularization Zoubin Ghahramani, Gatzby Institute, Title of the talk: Occam's Razor and Infinite Models Josef Kittler, University of Surrey Invited for a Special Session on Multimodal and multi-channel applications Title of the talk: Fusion of multiple experts in multimodal biometric personal identity verification systems Anders Krogh, University of Denmark Invited for a Special Session on Bio-Informatics Title of the talk: Hidden Markov models of proteins and DNA Mahesan Niranjan, Sheffield University Title of the talk: From Kalman to Particle Filtering for solving Signal Processing Problems with Neural Networks General Chairs Herv BOURLARD IDIAP and EPF, Lausanne Tlay ADALI University of Maryland Baltimore County Program Chairs Samy BENGIO IDIAP Jan LARSEN Technical University of Denmark Technical Committee Chair Jose PRINCIPE University of Florida at Gainsville Finance Chair Jean-Philippe THIRAN EPF, Lausanne Proceedings Chairs Jean-Cdric CHAPPELIER EPF, Lausanne Scott C. DOUGLAS Southern Methodist University Publicity Chair Marc VAN HULLE Katholieke Universiteit, Leuven American Liaison Jose PRINCIPE University of Florida at Gainsville Asia Liaison Shigeru KATAGIRI NTT Communication Science Laboratories Program Committee Amir Assadi Andrew Back Samy Bengio Yoshua Bengio M. Carreira-Perpinan Jean-Cdric Chappelier Andrzej Cichocki Jesus Cid-Sueiro Bob Dony Scott Douglas Craig Fancourt Ling Guan Tzyy-Ping Jung Shigeru Katagiri Jens Kohlmorgen Shoji Makino Danilo Mandic Elias Manolakos Takashi Matsumoto David Miller Li Min Christophe Molina Mahesan Niranjan Kostas Plataniotis Tommy Poggio Jose Principe Phillip Regalia Steve Renals Joo-Marcos Romano Jonas Sjberg Robert Snapp Kemal Snmez Sren Riis Jean-Philippe Thiran Naonori Ueda Marc Van Hulle Fernando Von Zuben Christian Wellekens Lizhong Wu Lian Yan ----- Samy Bengio Research Director. Machine Learning Group Leader. IDIAP, CP 592, rue du Simplon 4, 1920 Martigny, Switzerland. tel: +41 27 721 77 39, fax: +41 27 721 77 12. mailto:bengio at idiap.ch, http://www.idiap.ch/~bengio From thrun at stanford.edu Wed Nov 21 12:25:51 2001 From: thrun at stanford.edu (Sebastian Thrun) Date: Wed, 21 Nov 2001 09:25:51 -0800 Subject: JMLR and the Web, by Boston Globe Message-ID: <200111211725.fALHPp009324@saga16.Stanford.EDU> This article in Boston Globe should be of interest to many in the Connectionists community. It provides a writer's perspective on the recent creation of the Journal of Machine Learning Research (JMLR), and the motivation behind the mass resignation of Machine Learning's editorial board. JMLR sets an example of what I believe will ultimately happen to many journals. The Web reaches many more people than current publishing mechanisms. As JAIR has proven, using the Web doesn't negatively affect the quality of a journal. By moving from paper to the Web, I hope we ultimately change the way we publish research results. It will be much easier to annotate papers by animations, software, and on-line discussions. It will be possible to link to follow-up research, publish revisions if necessary, and link to related scientific findings that came along after an original paper was published. And, of course, the whole world can access all of this, not just a selected few. Best wishes, sebastian thrun ------------------------------------------------------------------- SPREADING THE GOSPEL OF FREE SCIENCE Author: By Nicholas Thompson, GLOBE CORRESPONDENT Date: 11/20/2001 Page: C1 Section: Health Science Leslie Kaelbling hardly looks like a threat to the scientific establishment. The perky MIT professor rides to work on a bicycle that neatly folds into a briefcase-sized rectangle and spends her days trying to make machines that can learn. As associate director of MIT's Artificial Intelligence Laboratory, she is surrounded by quirky creations, from tiny fish-like robots made partly from frog tissue to robots that look like humans and, one day, may think like them, too. But Kaelbling leads another revolution in her spare time. As editor of the upstart Journal of Machine Learning Research, Kaelbling offers some of the latest debates and developments in artificial intelligence to anyone with access to the Internet - free. By contrast, the scholarly journals that largely set the world's science agenda sometimes charge more than $1,000 a year for a subscription. Kaelbling would be just another quixotic idealist with her unpaid staff - the journal "doesn't even have a bank account right now," she acknowledges - except for one thing. Thirty-nine board members of the leading artificial intelligence journal in her field, Machine Learning, announced their resignations last month to join her crusade. Kaelbling and her supporters argue that putting all top current research online could well inspire crucial insights from people who wouldn't otherwise have access; a statistician in Mongolia may spur the next breakthrough, after all. "The only thing we care about in the world is that people read our work," Kaelbling said. The rivalry between Kaelbling's journal and Machine Learning - which costs $1,050 a year for institutions and $120 for individuals - is part of a much broader debate about how much scientific information should be free. For instance, the federal government's Human Genome Project and private Celera Genomics have locked horns repeatedly over Celera's plan to withhold some key information from the human genetic blueprint that could be sold to pharmaceutical companies looking for potential new drugs. More closely parallel to Kaelbling's work, the National Institutes of Health have created a database called PubMed Central intended to allow anyone in the world to freely search and retrieve the full text of any published scientific article, with archives extending back for decades. Several months ago, a coalition of about 30,000 scientists, led partly by former NIH director and Nobel laureate Harold Varmus, pledged to boycott any journals that didn't meet PubMed Central's standards for freely distributing data. The coalition backed off a little in early September, but the conflict still looms. The free, Internet-based Journal of Machine Learning Research challenges an elaborate system of disseminating scientific information that touches everything from what appears on the nightly news to which researchers become stars. A few well-known journals such as Science, Nature, and the New England Journal of Medicine considerably influence scientific discussion and have a near hammerlock on determining what science appears in the mainstream press. A slew of others - including Machine Learning - shape their respective subject areas, helping determine who gets tenure, where grants go, and how their fields move forward. Kaelbling and others note that the scientific community differs in several ways from journalism, where support for free online access to magazines and newspapers has withered. For one, most scientific authors don't get paid for publishing, even in the journals with costly subscription prices. Instead, they receive their funding from universities, corporations, or government grants, and publish mainly for prestige and to advance their fields. Kaelbling earns her salary from the Massachusetts Institute of Technology and part of her job description requires her to offer public service to the community, such as editing the Journal of Machine Learning Research. Secondly, progress in any scientific field relies to a huge extent on the amount of available information. More available information equals more and better science. Some of Kaelbling's colleagues, for example, want to design robots that actually think like humans: Rodney Brooks, the director of Kaelbling's laboratory, helped inspire Steven Spielberg's vision for the movie "A.I." That enormously complicated task would be helped with input from as many different scientists as possible. Putting everything online seems like the obvious thing to do, Kaelbling argued. Still, numerous scientists and publishers fear that moving away from printed, subscription-based journals could derail standards and practices that have worked well for years. Others fear that such a change could shutter prestigious and important journals. In the machine-learning community, swords have already crossed. In their letter resigning from Machine Learning, the rebellious members, who represented about two-thirds of the board, wrote: "Journals should principally serve the needs of the intellectual community, in particular by providing the immediate and universal access to journal articles that modern technology supports, and doing so at a cost that excludes no one." In the past, scholars in the field researched and wrote their articles, submitted them to Machine Learning, and then waited up to a year to see them in print. Probably most aggravating to the authors, Machine Learning's owners, Netherlands-based Kluwer Academic Publishers, retained complete copyright control. Authors couldn't even publish their articles on personal Web pages - a fairly restrictive policy for the industry that the company changed after the mass resignation. With the Journal of Machine Learning Research, authors just e-mail their pieces to Kaelbling, who then forwards them to assorted editors. These volunteers, generally prestigious researchers in whatever particular sub-field the article covers, then decide whether to accept or reject the articles. If accepted, the articles appear online immediately and the authors retain full copyrights. "Mostly, it's just a bunch of work," said Kaelbling, before noting that she still spends vastly more time with her MIT students and Erik the Red, a robot resembling R2D2 that she is trying to teach to see and navigate through hallways. Despite Kaelbling's optimism, though, other scientists argue that there are holes in her boat. Robert Holte, the editor of Machine Learning, supports the new journal and suggests that both his journal and Kaelbling's can exist harmoniously. But, he added, "What [the Journal of Machine Learning Research] doesn't have right now is a history. You can have the most famous people on your editorial board that you like. But until a journal has a well-established track record proving its ability to attract a large number of high quality, highly-cited papers, it cannot claim to be the community's flagship journal." Tenure committees, for example, know that being published in Machine Learning means you've accomplished something significant. Until it earns a reputation, Kaelbling's journal could just be two crackpots in a barn with a cable modem. In addition, advocates of print journals argue that online journals may not hold to the same quality standards, becoming, in a sense, the scientific equivalents of the Drudge Report. "Paper journals have a strict limit on the number of papers they can publish. With an online journal, there's always a temptation to accept rather than reject," said Cornell professor Shai Ben-David, one member of the editorial board of Machine Learning who chose not to resign. Kaelbling acknowledged that her journal hasn't earned prestige yet, but she insists that it will maintain strict standards. "It's the same people doing the same work," she said, noting that the editorial board of the Journal of Machine Learning Research is made up of many people who used to work for Machine Learning. Kaelbling is one of the most highly respected scientists in her field and, before resigning last year, she herself reviewed papers for her print rival. Kaelbling faces another potential problem in that no major for-profit publisher supports and promotes her journal. Kluwer Academic Publishing, the world's second largest scientific publisher with 731 journals under its umbrella, stated that it supports Machine Learning by providing services that include promotion, copy-editing, distribution and representation of the journal at conferences. Still, the nonprofit MIT Press does offer Kaelbling's journal its support, publishing and promoting quarterly bound editions of the articles that have appeared on the journal's Web site. "I don't think they are any less effective than Kluwer," Kaelbling said. MIT Press does publish and promote quarterly bound editions of the articles that have appeared on Kaelbling's Web site, but has garnered fewer than 100 subscriptions so far. That doesn't phase Kaelbling, either. "Everyone's going to have to do this," she said. Even some scientists closely attached to old print publications agree. According to Thomas Dietterich, a former editor of Machine Learning, and one of the recent defectors to the new journal: "I am emotionally attached to Machine Learning. I have every issue from the start to now. But things change. In the computer business, we are used to technology turning things upside down." From xwu at emba.uvm.edu Fri Nov 23 11:41:10 2001 From: xwu at emba.uvm.edu (Xindong Wu) Date: Fri, 23 Nov 2001 11:41:10 -0500 (EST) Subject: Knowledge and Information Systems: 3(4), November 2001 Message-ID: <200111231641.LAA08409@kais.emba.uvm.edu> Knowledge and Information Systems: An International Journal ----------------------------------------------------------- ISSN: 0219-1377 (printed version) ISSN: 0219-3116 (electronic version) by Springer-Verlag Home Page: http://www.cs.uvm.edu/~xwu/kais.html =============================================== Volume 3, Number 4 (November 2001) ---------------------------------- link.springer.de/link/service/journals/10115/tocs/t1003004.htm or link.springer-ny.com/link/service/journals/10115/tocs/t1003004.htm Mehmet Sayal, Peter Scheuermann: Distributed Web Log Mining Using Maximal Large Itemsets Knowledge and Information Systems 3 (2001) 4, 389-404 URL: link.springer.de/link/service/journals/10115/bibs/1003004/10030389.htm David B. Skillicorn, Yu Wang: Parallel and Sequential Algorithms for Data Mining Using Inductive Logic Knowledge and Information Systems 3 (2001) 4, 405-421 URL: link.springer.de/link/service/journals/10115/bibs/1003004/10030405.htm Hillol Kargupta, Weiyun Huang, Krishnamoorthy Sivakumar, Erik Johnson: Distributed Clustering Using Collective Principal Component Analysis Knowledge and Information Systems 3 (2001) 4, 422-448 URL: link.springer.de/link/service/journals/10115/bibs/1003004/10030422.htm Andreas L. Prodromidis, Salvatore J. Stolfo: Cost Complexity-Based Pruning of Ensemble Classifiers Knowledge and Information Systems 3 (2001) 4, 449-469 URL: link.springer.de/link/service/journals/10115/bibs/1003004/10030449.htm Julio Ortega, Moshe Koppel, Shlomo Argamon: Arbitrating Among Competing Classifiers Using Learned Referees Knowledge and Information Systems 3 (2001) 4, 470-490 URL: link.springer.de/link/service/journals/10115/bibs/1003004/10030470.htm Stephen D. Bay: Multivariate Discretization for Set Mining Knowledge and Information Systems 3 (2001) 4, 491-512 URL: link.springer.de/link/service/journals/10115/bibs/1003004/10030491.htm ---------------------------------------------------- Online publication: November 21, 2001 (c) Springer-Verlag London Limited 2001 From tohru-nitta at aist.go.jp Sat Nov 24 02:51:03 2001 From: tohru-nitta at aist.go.jp (Tohru Nitta) Date: Sat, 24 Nov 2001 16:51:03 +0900 Subject: CFP ICONIP'2002-Singapore Special Session: Complex-valued Neural Networks Message-ID: <4.2.0.58.J.20011105192237.009bb540@mail.aist.go.jp> Dear Connectionists, The Special Session "Complex-valued Neural Networks" is going to be organized in the International Conference on Neural Information Processing (ICONIP2002) to be held in Singapore, November 18-22, 2002 (http://www.ntu.edu.sg/home/nef/). In these years the complex-valued neural networks, which are the extensions of the real-valued neural networks to complex numbers, expand the application fields in image processing, computer vision, optoelectronic imaging, and communication and so on.The potentially wide applicability yields new aspects of theories required for novel or more effective functions and mechanisms. This special session will cover original and pioneering contributions, theory as well as applications on complex-valued neural networks, and aim at an inspiring discussion on the recent progress and the future development. Papers should be submitted according to the guidelines provided by the ICONIP2002 home page (http://www.ntu.edu.sg/home/nef/) except the address for paper submission. Papers should be sent directly to the special session organizer via e-mail or airmail by April 30, 2002: Tohru Nitta, Mathematical Neuroinformatics Group, Neuroscience Research Institute, National Institute of Advanced Industrial Science and Technology, AIST Tsukuba Central 2, 1-1-1 Umezono, Tsukuba-shi, Ibaraki, 305-8568 Japan. FAX: +81-298-61-5841, E-mail: tohru-nitta at aist.go.jp Please do not send your papers to ICONIP2002 Secretariat. If you have any questions, please make contact with the special session organizer. I am looking forward to receiving your submission. Yours sincerely, -- Tohru Nitta (Dr.) Mathematical Neuroinformatics Group, Neuroscience Research Institute, National Institute of Advanced Industrial Science and Technology, AIST Tsukuba Central 2, 1-1-1 Umezono, Tsukuba-shi, Ibaraki, 305-8568 Japan. FAX: +81-298-61-5841, E-mail: tohru-nitta at aist.go.jp From terry at salk.edu Sun Nov 25 22:14:56 2001 From: terry at salk.edu (Terry Sejnowski) Date: Sun, 25 Nov 2001 19:14:56 -0800 (PST) Subject: ICA 2001 Deadline Message-ID: <200111260314.fAQ3EuL07538@purkinje.salk.edu> Special hotel rate available until Nov 29, 2001. ICA2001 http://ica2001.org Third International Conference on Independent Component Analysis and Signal Separation San Diego, California December 9-13, 2001 Program and Registration: http://ica2001.ucsd.edu/ Independent Component Analysis (ICA) is an emerging area of signal processing and data analysis based on the blind source separation of unknown mixtures of unknown source signals. Research advances on ICA have been made in machine learning, neural networks, statistical signal processing and Bayesian modeling. Numerous applications of ICA have been found in adaptive speech filtering, speech signal coding, biomedical signal processing, image compression, text modeling and financial data analysis. Chair Terrence Sejnowski terry at inc.ucsd.edu Program Te-Won Lee tewon at inc.ucsd.edu Publicity Scott Makeig scott at inc.ucsd.edu Treasurer John Staight jstaight at ucsd.edu Publication Tzyy-Ping Jung jung at inc.ucsd.edu Comm. Javier Movellan javier at inc.ucsd.edu International Advisory Committee: C. Jutten, INPG, France E. Oja, Helsinki University of Technology, Finland A. Bell, The Salk Institute, USA S. I. Amari, RIKEN, Japan Invited Speakers: Michael Arbib (USC) Robert Hecht-Nielsen (HNC & UCSD) Geoffry Hinton (Toronto) Michael Jordan (UC Berkeley) Christof Koch (Caltech) Gilles Laurent (Caltech) V.S. Ramachandran (UCSD) Mohan Trivedi (UCSD) ----- From scheler at ICSI.Berkeley.EDU Sat Nov 24 19:22:00 2001 From: scheler at ICSI.Berkeley.EDU (scheler@ICSI.Berkeley.EDU) Date: Sat, 24 Nov 2001 16:22:00 -0800 (PST) Subject: Parallel Paper Submission Message-ID: <200111250022.QAA23127@raclette.ICSI.Berkeley.EDU> We would like to suggest the adoption of a general policy in the Neural Network Community of unlimited parallel paper submission. It is the task of editors and reviewers then to accept or reject papers, and the liberty of authors to select the journal where they want to publish. Gabriele Dorothea Scheler Johann Martin Philipp Schumann From Wulfram.Gerstner at dimail.epfl.ch Mon Nov 26 04:37:03 2001 From: Wulfram.Gerstner at dimail.epfl.ch (Wulfram Gerstner) Date: Mon, 26 Nov 2001 10:37:03 +0100 Subject: Faculty Positions in Switzerland Message-ID: <3C020D3F.6631B8CB@di.epfl.ch> Faculty Positions in Computational and Experimental Neurosciences The Swiss Federal Institute of Technology in Lausanne will establish a `Brain and Mind Institute' with several openings for faculty positions in Computational and Experimental Neurosciences. For details see http://admwww.epfl.ch/pres/neurosciences.html For inquiries contact: life.sciences at epfl.ch Applications, including curriculum vitae, publication list, brief statement of research interests (three pages or less) and names and addresses (including e-mail) of at least seven references should be sent to : The office of the President EPFL CH-1015 Lausanne Switzerland From tgd at cs.orst.edu Mon Nov 26 11:17:10 2001 From: tgd at cs.orst.edu (Thomas G. Dietterich) Date: Mon, 26 Nov 2001 08:17:10 -0800 Subject: Parallel Paper Submission In-Reply-To: <200111250022.QAA23127@raclette.ICSI.Berkeley.EDU> (scheler@ICSI.Berkeley.EDU) References: <200111250022.QAA23127@raclette.ICSI.Berkeley.EDU> Message-ID: <4518-Mon26Nov2001081710-0800-tgd@cs.orst.edu> One of the most precious resources in the research community is our time. Unlimited parallel submission requires more time spent reviewing papers. This would probably have the effect of reducing the quality of the reviewing and reducing the willingness of referees to agree to donate their time. We need to strike a compromise between the one extreme of allowing authors to "shotgun" their papers to multiple conferences and the other extreme of allowing authors only a single chance to publish a paper. One possible compromise is the current arrangement whereby authors are permitted to submit to multiple conferences/journals but that these submissions must be sequential. This has the added advantage that the paper can be improved with each submission in light of the reviews obtained from the previous submission. -- Thomas G. Dietterich Voice: 541-737-5559 Department of Computer Science FAX: 541-737-3014 Dearborn Hall 102 URL: http://www.cs.orst.edu/~tgd Oregon State University Corvallis, OR 97331-3102 From wahba at stat.wisc.edu Mon Nov 26 13:26:25 2001 From: wahba at stat.wisc.edu (Grace Wahba) Date: Mon, 26 Nov 2001 12:26:25 -0600 (CST) Subject: Parallel Paper Submission Message-ID: <200111261826.MAA15415@hera.stat.wisc.edu> There is a downside to the idea below: If everyone submitted their paper to five journals in the hopes of maximizing its acceptance by at least one, this will mean multiplying the amount of refereeing work to be done by up to a factor of 5. Furthermore if an author gets an early acceptance from their second favorite journal and decides to wait to see if their first favorite journal will take it, then the second favorite journal has their publication schedule messed up. Editors and reviewers do not have unlimited free resources to deal with this ... S & S - suggest you bounce this idea off a few editors, as well as people who are maxxed out on refereeing, and see what kind of flack bounces back. ................................... From nnsp02 at neuro.kuleuven.ac.be Mon Nov 26 04:50:27 2001 From: nnsp02 at neuro.kuleuven.ac.be (Neural Networks for Signal Processing 2002) Date: Mon, 26 Nov 2001 10:50:27 +0100 Subject: NNSP'2002: IEEE Workshop, Neural Networks for Signal Processing, Call for Papers Message-ID: <3C021063.933639FD@neuro.kuleuven.ac.be> 2002 IEEE Workshop Neural Networks for Signal Processing September 4-6, 2002 Martigny, Valais, Switzerland http://eivind.imm.dtu.dk/nnsp2002 Sponsored by the IEEE Signal Processing Society In cooperation with the IEEE Neural Networks Council Call for Papers Thanks to the sponsorship of IEEE Signal Processing Society and IEEE Neural Network Council, the twelfth of a series of IEEE workshops on Neural Networks for Signal Processing will be held in Martigny (http://www.martigny.ch ), Switzerland, at the ``Centre du Parc'' (http://www.hotelduparc.ch ). The workshop will feature keynote addresses, technical presentations and panel discussions. Papers are solicited for, but not limited to, the following areas: Algorithms and Architectures: Artificial neural networks, kernel methods, committee models, independent component analysis, adaptive and/or nonlinear signal processing, (hidden) Markov models, Bayesian modeling, parameter estimation, generalization, optimization, design algorithms. Applications: Speech processing, image processing (computer vision, OCR), multimodal interactions, multi-channel processing, intelligent multimedia and web processing, robotics, sonar and radar, bio-medical engineering, bio-informatics, financial analysis, time series prediction, blind source separation, data fusion, data mining, adaptive filtering, communications, sensors, system identification, and other signal processing and pattern recognition applications. Implementations: Parallel and distributed implementation, hardware design, and other general implementation technologies. Further Information NNSP'2002 webpage: http://eivind.imm.dtu.dk/nnsp2002 Paper Submission Procedure Prospective authors are invited to submit a full paper of up to ten pages using the electronic submission procedure described at the workshop homepage. Accepted papers will be published in a hard-bound volume by IEEE and distributed at the workshop. Schedule Submission of full paper: April 15, 2002 Notification of acceptance: May 1, 2002 Camera-ready paper and author registration: June 1, 2002 Advance registration, before: July 15, 2002 Preliminary Programme September 4, AM: Plenary talk by Mahesan Niranjan, Sheffield University "From Kalman to Particle Filtering for solving Signal Processing Problems with Neural Networks" Regular session, including oral and poster presentations September 4, PM: Special session on "Machine Learning and statistical approaches for Bio-Informatic Applications", Plenary talk by Anders Krogh, University of Denmark "Hidden Markov models of proteins and DNA", followed by special session, including oral and poster presentations September 5, AM: Plenary Talk: Yoshua Bengio, University of Montreal "Faking unlabeled data for geometric regularization" Regular session, including oral and poster presentations September 5, PM: Special session on "Multimodal/multi-channel processing" Plenary talk by Josef Kittler, University of Surrey "Fusion of multiple experts in multimodal biometric personal identity verification systems" September 6, AM: Plenary talk by Zoubin Ghahramani, Gatsby Institute, UK "Occam's Razor and Infinite Models" Regular oral and poster sessions. Invited Speakers Yoshua Bengio, University of Montreal Title of the talk: Faking unlabeled data for geometric regularization Zoubin Ghahramani, Gatzby Institute, Title of the talk: Occam's Razor and Infinite Models Josef Kittler, University of Surrey Invited for a Special Session on Multimodal and multi-channel applications Title of the talk: Fusion of multiple experts in multimodal biometric personal identity verification systems Anders Krogh, University of Denmark Invited for a Special Session on Bio-Informatics Title of the talk: Hidden Markov models of proteins and DNA Mahesan Niranjan, Sheffield University Title of the talk: From Kalman to Particle Filtering for solving Signal Processing Problems with Neural Networks General Chairs Herve BOURLARD IDIAP and EPF, Lausanne Tulay ADALI University of Maryland Baltimore County Program Chairs Samy BENGIO IDIAP Jan LARSEN Technical University of Denmark Technical Committee Chair Jose PRINCIPE University of Florida at Gainsville Finance Chair Jean-Philippe THIRAN EPF, Lausanne Proceedings Chairs Jean-Cdric CHAPPELIER EPF, Lausanne Scott C. DOUGLAS Southern Methodist University Publicity Chair Marc VAN HULLE Katholieke Universiteit, Leuven American Liaison Jose PRINCIPE University of Florida at Gainsville Asia Liaison Shigeru KATAGIRI NTT Communication Science Laboratories Program Committee Amir Assadi Andrew Back Samy Bengio Yoshua Bengio M. Carreira-Perpinan Jean-Cdric Chappelier Andrzej Cichocki Jesus Cid-Sueiro Bob Dony Scott Douglas Craig Fancourt Ling Guan Tzyy-Ping Jung Shigeru Katagiri Jens Kohlmorgen Shoji Makino Danilo Mandic Elias Manolakos Takashi Matsumoto David Miller Li Min Christophe Molina Mahesan Niranjan Kostas Plataniotis Tommy Poggio Jose Principe Phillip Regalia Steve Renals Joo-Marcos Romano Jonas Sjberg Robert Snapp Kemal Snmez Sren Riis Jean-Philippe Thiran Naonori Ueda Marc Van Hulle Fernando Von Zuben Christian Wellekens Lizhong Wu Lian Yan From jlm at cnbc.cmu.edu Mon Nov 26 17:04:07 2001 From: jlm at cnbc.cmu.edu (Jay McClelland) Date: Mon, 26 Nov 2001 17:04:07 -0500 (EST) Subject: Parallel Paper Submission In-Reply-To: <4518-Mon26Nov2001081710-0800-tgd@cs.orst.edu> Message-ID: I wholeheartedly agree with Tom. Parallel submission would create a huge waste of reviewer time, and would lead to many bad feelings if a paper is accepted to two outlets. Obviously the problem with the sequential approach is that review turnaround can be slow. This is an issue that we all can and should work on. -- Jay McClelland From mlyons at atr.co.jp Mon Nov 26 21:50:11 2001 From: mlyons at atr.co.jp (Michael J. Lyons) Date: Tue, 27 Nov 2001 11:50:11 +0900 Subject: Parallel Paper Submission: Separate Refereeing and Editorial processes In-Reply-To: <200111261826.MAA15415@hera.stat.wisc.edu> Message-ID: On Mon, 26 Nov 2001, Grace Wahba wrote: > There is a downside to the idea below: If everyone submitted their > paper to five journals in the hopes of maximizing its > acceptance by at least one, this will mean multiplying the amount of > refereeing work to be done by up to a factor of 5. Furthermore > if an author gets an early acceptance from their > second favorite journal and decides to wait to see if > their first favorite journal will take it, then the > second favorite journal has their publication schedule > messed up. Editors and reviewers do not have unlimited free > resources to deal with this ... S & S - suggest you bounce this > idea off a few editors, as well as people who are maxxed out > on refereeing, and see what kind of flack bounces back. It's already not unusual to be asked to review a paper that has been rejected by one journal a second time for another journal. Perhaps a way around this is a complete revision of the publishing model. For example, the reviewing and editorial processes could be separated such that a paper is only reviewed by 2 or 3 referees by a system independent of the editorial process. Maybe referee selection can be partially automated using something like the Citeseer system. Then journal Editors could bid competitively on the pool of reviewed papers. This is just a suggestion, there could be many other possible models of the peer-review publishing process. Is there anything sacred (or optimal) about the system that is currently in place? Cheers, - Michael Lyons -- Michael J. Lyons, PhD Senior Researcher ATR Media Information Science Kyoto, Japan http://www.mic.atr.co.jp/~mlyons From seiffert at ipe.et.Uni-Magdeburg.DE Tue Nov 27 07:38:18 2001 From: seiffert at ipe.et.Uni-Magdeburg.DE (Udo Seiffert) Date: Tue, 27 Nov 2001 13:38:18 +0100 Subject: New Book on Self-Organizing Neural Networks Message-ID: <3C03893A.2DEB52E4@iesk.et.uni-magdeburg.de> Dear Colleagues, I am happy to announce the new Springer book Self-Organizing Neural Networks - Recent Advances and Applications. This compilation contains new theoretical work as well as up-to-date applications contributed by some of the world leaders of current SOM research. It is a compact and vivid collection of almost all aspects of current research on Self-Organizing Maps, ranging from theoretical work, several technical and non-technical applications, numerical and implementation details on sequential and parallel hardware to self-organisation with spiking neurons. An overture, given by Teuvo Kohonen, builds a bridge from the development of the fundamentals to the many extensions, modifications and applications which have made this neural network architecture so successful. Please find more information at Springer's web site http://www.springer.de/cgi-bin/search_book.pl?isbn=3D3-7908-1417-2 or Amazon.com http://www.amazon.com/exec/obidos/ASIN/3790814172/qid%3D/002-1230852-1153629 Kind regards, Udo Seiffert -- ____________________________________________________ Dr. Udo Seiffert University of Magdeburg IESK Email : seiffert at iesk.et.uni-magdeburg.de WWW : http://iesk.et.uni-magdeburg.de/~seiffert ____________________________________________________ From espaa at exeter.ac.uk Tue Nov 27 08:36:37 2001 From: espaa at exeter.ac.uk (Oliver Jenkin) Date: Tue, 27 Nov 2001 13:36:37 +0000 (GMT Standard Time) Subject: PAA Journal contents Message-ID: Pattern Analysis and Applications An International Journal by Springer-Verlag Website: http://www.dcs.ex.ac.uk/paa CONTENTS LIST YEAR 2001 Table of Contents Vol. 4 Issue 1 F. Mokhtarian, S. Abbasi: Affine Curvature Scale Space with Affine Length Parametrisation Pattern Analysis & Applications 4 (2001) 1, 1-8 Hyunwoon Kim, Ki Sang Hong: Robust Image Mosaicing of Soccer Videos using Self-Calibration and Line Tracking Pattern Analysis & Applications 4 (2001) 1, 9-19 Hiroki Hayashi, Mineichi Kudo, Jun Toyama, Masaru Shimbo: Fast Labelling of Natural Scenes Using Enhanced Knowledge Pattern Analysis & Applications 4 (2001) 1, 20-27 J. Bedenas, M. Boder, F. Pla: Segmenting Traffic Scenes from Grey Level and Motion Information Pattern Analysis & Applications 4 (2001) 1, 28-38 A. Kaarna, J. Parkkinen: Transform Based Lossy Compression of Multispectral Images Pattern Analysis & Applications 4 (2001) 1, 39-50 A. Hennig, N. Sherkat: Cursive Script Recognition using Wildcards and Multiple Experts Pattern Analysis & Applications 4 (2001) 1, 51-60 Yue-Fei Guo, Ting-Ting Shu, Jing-Yu Yang, Shi-Jin Li: Feature Extraction Method Based on the Generalised Fisher Discriminant Criterion and Facial Recognition Pattern Analysis & Applications 4 (2001) 1, 61-66 Table of Contents Vol. 4 Issue 2/3 (SPECIAL ISSUE ON IMAGE INDEXATION) Jean-Michel Jolion: Editorial Pattern Analysis & Applications 4 (2001) 2/3, 81-82 S. Berretti, A. Del Bimbo, E. Vicario: Modelling Spatial Relationships between Colour Clusters Pattern Analysis & Applications 4 (2001) 2/3, 83-92 N. Tsapatsoulis, Y. Avrithis, S. Kollias: Facial Image Indexing in Multimedia Databases Pattern Analysis & Applications 4 (2001) 2/3, 93-107 Laurent Amsaleg, Patrick Gros: Content-based Retrieval Using Local Descriptors: Problems and Issues from a Database Perspective Pattern Analysis & Applications 4 (2001) 2/3, 108-124 Joo-Hwee Lim: Building Visual Vocabulary for Image Indexation and Query Formulation Pattern Analysis & Applications 4 (2001) 2/3, 125-139 Jorma Laaksonen, Markus Koskela, Sami Laakso, Erkki Oja: Self-Organising Maps as a Relevance Feedback Technique in Content-Based Image Retrieval Pattern Analysis & Applications 4 (2001) 2/3, 140-152 J. Fournier, M. Cord, S. Philipp-Foliguet: RETIN: A Content-Based Image Indexing and Retrieval System Pattern Analysis & Applications 4 (2001) 2/3, 153-173 ByoungChul Ko, Jing Peng, Hyeran Byun: Region-based Image Retrieval Using Probabilistic Feature Relevance Learning Pattern Analysis & Applications 4 (2001) 2/3, 174-184 Patricia Ladret, Anne Guérin-Dugué: Categorisation and Retrieval of Scene Photographs from JPEG Compressed Database Pattern Analysis & Applications 4 (2001) 2/3, 185-199 E. Louupias, S. Bres: Key Points-based Indexing for Pre-attentive Similarities: The KIWI System Pattern Analysis & Applications 4 (2001) 2/3, 200-214 Linhui Jia, Leslie Kitchen: Object-Based Image Content Characterisation for Semantic-Level Image Similarity Calculation Pattern Analysis & Applications 4 (2001) 2/3, 215-226 Table of Contents Vol. 4 Issue 4 A. Raudys, J. A. Long: MLP Based Linear Fea ure Extraction for Nonlinearly Separable Data Pattern Analysis & Applications 4 (2001) 4, 227-234 Baoming Hong, Songmei Tang: An Integrated Face Rec gniti n System Based n Multiscale L cal Discriminatory Features Pattern Analysis & Applications 4 (2001) 4, 235-243 Dayou Wang, James M. Keller, C. Andrew Carson: Pulsed-Field Gel Elec rophoresis Pa ern Recogni ion of Bac erial DNA: A Systemic Approach Pattern Analysis & Applications 4 (2001) 4, 244-255 Max Mignotte, Jean Meunier, Jean-Claude Tardif: Endocardial Boundary E timation and Tracking in Echocardiographic Images using Deformable Template and Markov Random Fields Pattern Analysis & Applications 4 (2001) 4, 256-271 X. Yuan, D. Goldman, A. Moghaddamzadeh, N. Bourbakis: Segmentation of Colour Images with Highlights and Shadows sing Fuzzy-like Reasoning Pattern Analysis & Applications 4 (2001) 4, 272-282 Peter Tinù, Christian Schittenkopf, Georg Dorffner: Volatility Trading ia Temporal Pattern Recognition in Quantised Financial Time Series Pattern Analysis & Applications 4 (2001) 4, 283-299 __________________________________________ Oliver Jenkin Pattern Analysis and Applications Journal Department of Computer Science University of Exeter Exeter EX4 4PT, UK Tel: +44-1392-264061 Fax: +44-1392-264067 E-mail: espaa at ex.ac.uk Web: http://www.dcs.ex.ac.uk/paa ____________________________________________ From macgyver_99 at hotmail.com Tue Nov 27 08:35:48 2001 From: macgyver_99 at hotmail.com (M. Imad Khan) Date: Tue, 27 Nov 2001 18:35:48 +0500 Subject: Parallel Paper Submission References: Message-ID: What about publishing everything on the web and leave ALL kinds of paper publications. There could be a section where "unpublished" papers are published and the readers can cast votes as to "publish" them in the published section. This way soemthing that is useful but not "published" can be taken care of, while the normal people can act as reviewers and make the status of "unpublished" change to "published" through their vote. Imad ----- Original Message ----- From pau at ac.upc.es Tue Nov 27 09:10:17 2001 From: pau at ac.upc.es (Pau Bofill) Date: Tue, 27 Nov 2001 15:10:17 +0100 Subject: Parallel Paper Submission References: Message-ID: <004101c1774d$3db761e0$44235393@ac.upc.es> What about a pool of papers where anyone can submit? Editors/reviewers would then select their preferred papers from the pool... (This is an embryonary approach, to be further improved. Don't take it full value, please, but let's ponder the idea). Pau Bofill ----- Original Message ----- From peter.andras at ncl.ac.uk Tue Nov 27 09:35:06 2001 From: peter.andras at ncl.ac.uk (Peter Andras) Date: Tue, 27 Nov 2001 14:35:06 -0000 Subject: Parallel Paper Submission In-Reply-To: <4518-Mon26Nov2001081710-0800-tgd@cs.orst.edu> Message-ID: I think that a better way of handling the publication problem would be to have a publication clearing centre to which many publications would be affiliated. Papers would be send to the clearing centre, and authors would specify the preference list of journals where they wish to publish. The clearing centre would manage the refereeing process, and referees would suggest the place of publication, besides providing comments and recommendations. If the suggested place of publication matches the author's wishes, the paper would be published in that journal, otherwise the author could be consulted whether he accepts the suggested place of publication. The publications and referees would have ranks, depending on their measured scientific impact (impact factor for journals, recent cumulative impact factor and recent citation index for referees). Depending on the ranks of the target journals the referees with appropriate ranks would be assigned to evaluate the submissions. In this way the editorial boards of the journals would be primarily responsible for defining the scientific orientation and limits of the journal, and would release their role in the refereeing process as an editorial body (the members would still provide individual refereeing service to the publication clearing centre). Having enough many journals and referees associated to a publication clearing centre, this would provide an efficient way to publish scientific results much faster than it is currently possible (in average; obviously the established, well-known researchers publish relatively fast even today, but those who are not-well-known, at the begining of their scientific carrier may have to wait long time, until their papers appear in print). Having shorter time delays between first submission and publication, in average, would be very beneficial for the faster advancement of science. I see that the creation of a such clearing centre needs efforts and organization, but I don't see impossible the creation of a publication clearing centre in the near future. Best wishes, Peter Andras ----------------------- Dr Peter Andras Lecturer Neural Systems Group Department of Psychology University of Newcastle upon Tyne Newcastle upon Tyne NE1 7RU UK tel. +44-191-2225790 fax. +44-191-2225622 http://www.staff.ncl.ac.uk/peter.andras/ From jjost at mis.mpg.de Tue Nov 27 11:26:40 2001 From: jjost at mis.mpg.de (Juergen Jost) Date: Tue, 27 Nov 2001 17:26:40 +0100 (MET) Subject: open position Message-ID: Dear connectionists, at the Max Planck Institute for Mathematics in the Sciences in Leipzig (Germany), we have an open position for a postdoc in the field of Mathematical Modelling of Cognitive Systems. Applicants should be able to build upon a solid education in mathematics or physics in order to develop and analyze formal models, for example neural networks, that lead to new insights about information processing and cognitive structures. The work will take place in an open interdisciplinary group at a research institute with a strong background in mathematics and with many and diverse international contacts. Collaborations with researchers at the University of Leipzig or other institutions are possible. The position is offered for two years, with the possibility of an extension in case of mutual interest. The beginning date is flexible. Payment and benefits are determined by the regulations for the German Public Service. Handicapped applicants will be given preference in case of equal qualification. The Max Planck Society as the employer aims at increasing the number of female scientists in fields where underrepresented. Therefore, women are particularly encouraged to apply. Please send your application to the address below. Juergen Jost P.S: We also regularly accept applications for our PhD program. XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX Juergen Jost Max-Planck-Institut fuer Mathematik in den Naturwissenschaften Inselstrasse 22 - 26 D-04103 Leipzig Germany Tel.: +49-341-9959-550 +49-341-9959-552 (secretary) Fax: +49-341-9959-555 email: jost at mis.mpg.de XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX From rinkus at mediaone.net Tue Nov 27 11:37:06 2001 From: rinkus at mediaone.net (rinkus) Date: Tue, 27 Nov 2001 11:37:06 -0500 Subject: Parallel Paper Submission: Separate Refereeing and Editorial processes In-Reply-To: Message-ID: <004001c17761$c0941db0$17bcfea9@DBJH8M01> If people are genuinely interested in improving the scientific review process you might want to consider making it unacceptable for the graduate students of reviewers to do the actual reviewing. Graduate students are just that...students...and lack the knowledge and wisdom to provide a fair review of novel ideas. In many instances a particular student may have particular knowledge and insight relevant to a particular submission but the proper model here is for the advertised reviewer (i.e., whose name appears on the editorial board of the publication) to consult with the student about the submission (and this should probably be in an indirect fashion so as to protect the author's identity and ideas) and then write the review from scratch himself. The scientific review process is undoubtedly worse off to the extent this kind of accountability is not ensured. We end up seeing far too much rehashing of old ideas and not enough new ideas. Rod Rinkus From swindale at interchange.ubc.ca Tue Nov 27 13:28:57 2001 From: swindale at interchange.ubc.ca (Nicholas Swindale) Date: Tue, 27 Nov 2001 10:28:57 -0800 Subject: Parallel Paper Submission Message-ID: <4.3.2.20011127101510.00c77460@pop.interchange.ubc.ca> What about the following idea - allow unlimited parallel submission but shift the burden of obtaining referee reports to the authors. So the authors find 2 or 3 referees likely to be known to journal editors and likely to be impartial, submit the paper directly to the referees, and then when the paper is adequately revised submit it to the journal(s) of their choice and get the referees to send in their reports at the same time. This could be done sequentially or in parallel. This would a) save journal offices a lot of trouble, b) cut down on multiple refereeing and time-consuming resubmissions, c) get rid of anonymous reviewing and d) speed up publication. Nick Swindale __________________ Associate Professor, Dept of Ophthalmology, University of British Columbia, 2550 Willow St., Vancouver BC Canada V5Z 3N9 tel. 604 875 5379 fax. 604 875 4663 e-mail: swindale at interchange.ubc.ca From lazzaro at CS.Berkeley.EDU Tue Nov 27 14:54:26 2001 From: lazzaro at CS.Berkeley.EDU (John Lazzaro) Date: Tue, 27 Nov 2001 11:54:26 -0800 Subject: Parallel Paper Submission [...] Message-ID: <200111271954.LAA25156@snap.CS.Berkeley.EDU> > Michael Lyons writes > > Perhaps a way around this is a complete revision of the publishing model. We might also look to Hollywood -- the New York Times movie reviewer does not exercise prior restraint to prevent "bad" movies from being made or released. Instead, financial issues -- funding the movie, and distributor buy-in -- dictates whether a movie gets made and released. The role of the newspaper reviewer is to judge movies after release -- and the public is trained to read the opinion of respected reviewers, as part of the decision-making process of which movie to see on a Friday night. Ideas of this sort are under active investigation in the Digital Library community; this abstract gives the flavor of a project here at Berkeley: http://buffy.eecs.berkeley.edu/Seminars/2001/Nov/011105.wilensky.html --jl ------------------------------------------------------------------------- John Lazzaro -- Research Specialist -- CS Division -- EECS -- UC Berkeley lazzaro [at] cs [dot] berkeley [dot] edu www.cs.berkeley.edu/~lazzaro ------------------------------------------------------------------------- From dr+ at cs.cmu.edu Tue Nov 27 20:16:12 2001 From: dr+ at cs.cmu.edu (Douglas Rohde) Date: Tue, 27 Nov 2001 20:16:12 -0500 Subject: Parallel Paper Submission References: Message-ID: <3C043ADC.4090704@cs.cmu.edu> I considered the idea of a submission pool, from which editors would select papers they wished to publish, but decided against suggesting it myself because I think it would seriously compromise the effectiveness of the review process. I think most of us would agree that the review process, however painful for both the author and the reviewer, is nevertheless very useful for identifying flaws in work that should not be published and, perhaps more importantly, for improving good papers. If you submitted a paper to the pool and journal A wanted to accept it with major (and presumably justified) revisions and journal B wanted to accept it with minor ones, would you spend the time to do the revisions, or would you just go ahead and publish it in journal B as is? In order to attract potentially good papers, the journal editors will have incentive to suggest the fewest changes. As a result, the quality of the published papers will diminish. And if you were asked to write a review for a paper from the pool, how much effort would you put in if you knew the author may not even pay attention to your review and could just ignore it and publish elsewhere? In regards to Nicholas Swindale's suggestion, I can't imagine that the "get your own reviewers" model could possibly work. Would we be paying the reviewers as well? How many reviews can we solicit before choosing the ones we want to send in? Finally, I think the quality of the stuff coming out of Hollywood speaks to the viability of the movie reviewer model. Although I do think it would be interesting to have a journal purely devoted to review of and commentary on already published work in a particular field. Doug Rohde Carnegie Mellon University From rsun at cecs.missouri.edu Tue Nov 27 23:36:02 2001 From: rsun at cecs.missouri.edu (rsun@cecs.missouri.edu) Date: Tue, 27 Nov 2001 22:36:02 -0600 Subject: Parallel Paper Submission Message-ID: <200111280436.fAS4a2a24303@ari1.cecs.missouri.edu> >From: "M. Imad Khan" >To: Jay McClelland , connectionists at cs.cmu.edu > >What about publishing everything on the web and leave ALL kinds of paper >publications. There could be a section where "unpublished" papers are >published and the readers can cast votes as to "publish" them in the >published section. This way soemthing that is useful but not "published" can >be taken care of, while the normal people can act as reviewers and make the >status of "unpublished" change to "published" through their vote. > The opinions of experts should weigh a lot more than those of others --- that's the only way to maintain quality and quality is absolutely critical to scientific work. How do we emphasize experts' opinions if we do away with peer reviews? Even with peer reviews, we are constantly having difficulty in determining who the experts are (whenever we go outside of (relatively) clearly delineated narrow areas). --Ron =========================================================================== Prof. Ron Sun http://www.cecs.missouri.edu/~rsun CECS Department phone: (573) 884-7662 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 http://www.elsevier.com/locate/cogsys =========================================================================== From adriaan at tijsseling.com Wed Nov 28 00:42:15 2001 From: adriaan at tijsseling.com (Adriaan Tijsseling) Date: Wed, 28 Nov 2001 14:42:15 +0900 Subject: Parallel Paper Submission In-Reply-To: Message-ID: > I wholeheartedly agree with Tom. Parallel submission would create > a huge waste of reviewer time, and would lead to many bad feelings > if a paper is accepted to two outlets. Obviously the problem with > the sequential approach is that review turnaround can be slow. This > is an issue that we all can and should work on. An additional problem is that the reviewing process itself is not particularly efficient. How many times does it not occur that reviewers' reports do not agree? Or that one reviewer suggests a modification, which another reviewer actually requests to be removed? An ideal, but certainly attainable option is to have one single online repository for papers, in the same vein as citeseer or cogprints. Researchers can then retrieve the papers they are interested in, read them, and return a score based on relevance, originality, and the like. Perhaps they can submit a more detailed commentary anonymously, visible to the author(s) only. In this age, one should optimally try to benefit from modern internet technologies. Let the academic public decide which articles they deem relevant and useful. This way articles are much faster distributed (the current 1, 2, 3 year delay between writing and publishing is really becoming ridiculous nowadays). Adriaan Tijsseling From terry at salk.edu Wed Nov 28 06:15:46 2001 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 28 Nov 2001 03:15:46 -0800 (PST) Subject: Computational Neurobiology Graduate Training at UCSD Message-ID: <200111281115.fASBFks13378@purkinje.salk.edu> DEADLINE: JANUARY 4, 2002 COMPUTATIONAL NEUROBIOLOGY GRADUATE PROGRAM Department of Biology - University of California, San Diego http://www.biology.ucsd.edu/grad/other_compneuro.html The goal of the Computational Neurobiology Graduate Program at UCSD is to train researchers who are equally at home measuring large-scale brain activity, analyzing the data with advanced computational techniques, and developing new models for brain development and function. Financial support for students enrolled in this training program is available through an NSF Integrative Graduate Education and Research Training (IGERT) award. Candidates from a wide range of backgrounds are invited to apply, including Biology, Psychology, Computer Science, Physics and Mathematics. The three major themes in the training program are: 1. Neurobiology of Neural Systems: Anatomy, physiology and behavior of systems of neurons. Using modern neuroanatomical, behavioral, neuropharmacological and electrophysiological techniques. Lectures, wet laboratories and computer simulations, as well as research rotations. Major new imaging and recording techniques also will be taught, including two-photon laser scanning microscopy and functional magnetic resonance imaging (fMRI). 2. Algorithms and Realizations for the Analysis of Neuronal Data: New algorithms and techniques for analyzing data obtained from physiological recording, with an emphasis on recordings from large populations of neurons with imaging and multielectrode recording techniques. New methods for the study of co-ordinated activity, such as multi-taper spectral analysis and Independent Component Analysis (ICA). 3. Neuroinformatics, Dynamics and Control of Systems of Neurons: Theoretical aspects of single cell function and emergent properties as many neurons interact among themselves and react to sensory inputs. A synthesis of approaches from mathematics and physical sciences as well as biology will be used to explore the collective properties and nonlinear dynamics of neuronal systems, as well as issues of sensory coding and motor control. Participating Faculty include: * Henry Abarbanel (Physics): Nonlinear and oscillatory dynamics; modeling central pattern generators in the lobster stomatogastric ganglion. Director, Institute for Nonlinear Systems at UCSD. * Thomas Albright (Salk Institute): Motion processing in primate visual cortex; linking single neurons to perception; fMRI in awake, behaving monkeys. Director, Sloan Center for Theoretical Neurobiology. * Darwin Berg (Biology): Regulation synaptic components, assembly and localization, function and long-term stability. Former Chairman of Biology. * Garrison Cottrell (Computer Science and Engineering): Dynamical neural network models and learning algorithms. * Mark Ellisman (Neurosciences, School of Medicine): High resolution electron and light microscopy; anatomical reconstructions. Director, National Center for Microscopy and Imaging Research. * Robert Hecht-Nielsen (Electrical and Computer Engineering): Neural computation and the functional organization of the cerebral cortex. Founder of Hecht-Nielsen Corporation. * Harvey Karten (Neurosciences, School of Medicine): Anatomical, physiological and computational studies of the retina and optic tectum of birds and squirrels. * David Kleinfeld (Physics):Active sensation in rats; properties of neuronal assemblies; optical imaging of large-scale activity. Co-director, Analysis of Neural Data Workshop (MBL). * William Kristan (Biology): Computational Neuroethology; functional and developmental studies of the leech nervous system, including studies of the bending reflex and locomotion. Director, Neurosciences Graduate Program at UCSD. * Herbert Levine (Physics): Nonlinear dynamics and pattern formation in physical and biological systems, including cardiac dynamics and the growth and form of bacterial colonies. * Javier Movellan (Institue for Neural Computation): Sensory fusion and learning algorithms for continuous stochastic systems. * Mikhael Rabinovich (Institute for Nonlinear Science): Dynamical systems analysis of the stomatogastric ganglion of the lobster and the antenna lobe of insects. * Terrence Sejnowski hSalk Institute/Biology): Computational neurobiology; physiological studies of neuronal reliability and synaptic mechanisms. Director, Institute for Neural Computation. * Martin Sereno (Cognitive Science): Neural bases of visual cognition and language using anatomical, electrophysiological, computational, and non-invasive brain imaging techniques. * Nicholas Spitzer (Biology): Regulation of ionic channels and neurotransmitters in neurons; effects of electrical activity in developing neurons on neural function. Chair of the Neurobiology Section in Biology. * Charles Stevens (Salk Institute): Synaptic physiology; physiological studies and biophysical models of synaptic plasticity in hippocampal neurons. * Roger Tsien (Chemistry): Second messenger systems in neurons; development of new optical and MRI probes of neuron function, including calcium indicators and caged neurotransmitters. * Mark Whitehead (Neurosurgery, School of Medicine): Peripheral and central taste systems; anatomical and functional studies of regions in the caudal brainstem important for feeding behavior. * Ruth Williams (Mathematics): Probabilistic analysis of stochastic systems and continuous learning algorithms. Requests for application materials should be sent to the University of California, San Diego, Division of Biology 0348, Graduate Admissions Office, 9500 Gilman Drive, La Jolla, CA, 92093-0348 or to [gradprog at biomail.ucsd.edu]. The deadline for completed application materials, including letters of recommendation, is January 4, 2002. More information about applying to the UCSD Biology Graduate Program is available at http://www.biology.ucsd.edu/grad/admissions/index.html From sunny at sunnybains.com Wed Nov 28 07:17:18 2001 From: sunny at sunnybains.com (Sunny Bains) Date: Wed, 28 Nov 2001 12:17:18 +0000 Subject: Parallel Paper Submission References: Message-ID: <3C04D5CE.30503@sunnybains.com> This may be an entirely off-the-wall comment, but there is a possible solution that be able to be imported from (believe it or not) the vagaries of English property law. It used to be that each potential buyer (the journals) of a house (the paper) would have their own separate survey (review) done for the mortgaging companies. More recently, someone came up with the idea (this is still experimental) of having the buyer have their house surveyed themselves (the surveying profession is independent), and then give this report to any potential buyers. So, you could have a panel of reviewers who review for many journals in the same field. If the author puts a list of all the journals he/she is interested in, in order, then the reviewer can make the appropriate comments... (I have a very narrow experience of paper publishing, so apologies if this is a naive solution... I just thought it might be worth suggesting). Best, Sunny Bains Imperial College of Science and Technology Jay McClelland wrote: > > I wholeheartedly agree with Tom. Parallel submission would create > a huge waste of reviewer time, and would lead to many bad feelings > if a paper is accepted to two outlets. Obviously the problem with > the sequential approach is that review turnaround can be slow. This > is an issue that we all can and should work on. > > -- Jay McClelland > > > From koza at stanford.edu Wed Nov 28 11:25:30 2001 From: koza at stanford.edu (John Koza) Date: Wed, 28 Nov 2001 08:25:30 -0800 Subject: Parallel Paper Submission Message-ID: <019801c17829$4b96f0a0$050010ac@mendel> Hello Connectionists: There is a very simple way to solve the real problems that the proponents of parallel paper submission are trying to address. It does not involve any new complicated machinery (e.g., clearinghouses) and its does not involve (after initial implementation) any more work for already-busy editors and reviewers. A couple of years ago, there was one journal in the field of genetic and evolutionary computation. Like most journals in the computer science field, it had a lengthy review process. Papers languished for months on the editors desk before being sent out for reviewers. Reviewers were typically allowed 6 - 9 months or more to write their reviews. The editors then took many additional months before reaching a decision. Submitting authors were frustrated with having their work "tied up" waiting for a (possibly adverse) decision on whether their paper would be published. This is, of course, particularly significant for new academics who need publications in order to earn tenure. It was almost true that the author had forgotten that he had written the paper by the time it was published. When the IEEE starting considering creation of a new journal in the field of genetic and evolutionary computation, I talked to the editor-designate and convinced him to follow the practice of the biological and medical sciences. The nearly universal practice in the biological and medical sciences is exclusive submission combined with quick review. For example, Science demands that an author submit the paper exclusively to them; however, in exchange, Science promises the author a cursory yes-no decision (based on topic suitability and general appearance) in a couple of weeks and a final decision (after detailed review by peer reviewers) in about 6 weeks. I subscribe personally to over a dozen journals in the biological and medical sciences. They all follow this approach (as do other journals that I read in the library). I would say the overall average time that I see is about 70 - 90 days. In fact, many of them loudly advertise (in ads for their own journal and as part of the author submission instructions) their average review time. I've even seen competitive ads from the journal themselves pointing out their average time versus the average time for "brand X". There is nothing inconsistent about a rapid overall schedule and quality of reviewing or editing. The fact is that it doesn't take the reviewers or the editors any more time or effort to maintain a "biological sciences" kind of schedule than a schedule where reviewers are given 6 - 9 months and editors habitually take another 6 - 9 months to reach a decision. It is simply of a matter of when people spent their time. Having reviewed hundreds of papers, I can say that I read the paper and write the review on only one of two moment --- independent of whether I've been 30, 60, 90, or 180 days to do the rwview. If the paper really grabs my attention, I do it the day or so after I receive it and then just sendmy review in. If not, I do it on the day or so just before the review is due. Later, when the Genetic Programming and Evolvable Machines journal was being created, I also convinced the publisher and editor-designate to follow the same kind of schedule. That was much easier because the IEEE journal had already established and maintained its quick schedule. Over time, the original journal in the field of genetic and evolutionary computation has, because of competitive pressure, moved toward this same kind of schedule. (There is, of course, a one-time transitional effort required to get onto a faster schedule). The fact is, in a rapidly changing field, unnecessarily long publication schedules are a significant disservice to the field. They impede advances in the field because new ideas get out more slowly. They hamper the careers of individual authors. The simple way to move from the current "lose-lose" situation to a "win-win" situation a rapid schedule. Of course, once one journal in a field adopts this kind of common sense schedule, Darwinian natural selection takes over and produces significant competitive pressure on the others. John R. Koza Consulting Professor Biomedical Informatics Department of Medicine Medical School Office Building (MC 5479) Stanford University Stanford, California 94305-5479 Consulting Professor Department of Electrical Engineering School of Engineering Stanford University Phone: 650-941-0336 Fax: 650-941-9430 E-Mail: koza at stanford.edu WWW Home Page: http://www.smi.stanford.edu/people/koza For information about field of genetic programming in general: http://www.genetic-programming.org For information about Genetic Programming Inc.: http://www.genetic-programming.com For information about GECCO-2002 (GP-2002) conference in New York City on July 9 - 13, 2002 (Tuesday - Saturday) and the International Society on Genetic and Evolutionary Computation visit: http://www.isgec.org/ For information about the annual Euro-GP-2002 conference on April 3 - 5, 2002 in Ireland, visit http://evonet.dcs.napier.ac.uk/eurogp2002 From jkolen at altair.coginst.uwf.edu Wed Nov 28 12:56:57 2001 From: jkolen at altair.coginst.uwf.edu (John F. Kolen) Date: Wed, 28 Nov 2001 11:56:57 -0600 Subject: Parallel Paper Submission In-Reply-To: <4.3.2.20011127101510.00c77460@pop.interchange.ubc.ca>; from swindale@interchange.ubc.ca on Tue, Nov 27, 2001 at 10:28:57AM -0800 References: <4.3.2.20011127101510.00c77460@pop.interchange.ubc.ca> Message-ID: <20011128115657.F1472@altair.coginst.uwf.edu> Parallel submission offers the author the illusion of saving time and energy by increasing the probability of acceptance with minimal revisions. In my experience as an AE, very few papers are accepted as-is on the first attempt. Flat out rejects were just as rare. Revise and resubmit was the most frequent. Upon resubmission, papers were accepted either as-is or with minor-corrections. Now consider what happens with parallel submission. Essentially, more people look at your paper. Most quality reviews will identify the same deficiencies in the reviewed paper. So rather than have two or three people pointing out your mistakes, you've got five or six...and a couple of journals telling you to revise and resubmit. And it's still a two-step process. Most, if not all, of the suggestions on this thread have made the same assumption. That is, all that matters for acceptance is quality of the paper. This is not the case, especially in a field as diverse as ours. For any two journals, the review critera are different. Journals have target audiences that have certain expectations. Some audiences expect excruciatingly thorough background sections, while others are happy with the formulas and a minimal amount of window dressing. Thus, multiple submissions should entail additional work for each submission to tailor it to the target audience. This assumes, of course, that the author cares about such matters and does not perceive the publication as merely 'a line on the vita'. Finally, if you think that the reviews are unfair, discuss it with the editor. If you think the turnaround time is too long, get involved in the review process and write quality reviews with a quick turnaround. There always seems to be more papers than reviewers. -- John F. Kolen voice: 850.202.4420 Research Scientist fax: 850.202.4440 Institute for Human and Machine Cognition University of West Florida From anand at speech.sri.com Wed Nov 28 12:48:08 2001 From: anand at speech.sri.com (Anand Venkataraman) Date: Wed, 28 Nov 2001 09:48:08 -0800 (PST) Subject: Parallel Paper Submission Message-ID: <200111281748.JAA09061@chalumeau> > What about publishing everything on the web and leave ALL kinds of paper > publications. There could be a section where "unpublished" papers are > published and the readers can cast votes as to "publish" them in the > published section. This way soemthing that is useful but not "published" can > be taken care of, while the normal people can act as reviewers and make the > status of "unpublished" change to "published" through their vote. The problem with this is that it is not very clear who gets to vote. Proper and conscientious reviewing of papers by well qualified individuals is not only of service to the community, but also to the authors. It ensures that their papers do not see ink prematurely and become a source of embarrassment later on in their careers. A similar forum as you suggest is already available through the repository at www.arXiv.org where people are invited (and frequently do) post papers and reports that they may not intend to publish. Many publications also cite these arXived papers as though they were actually in print. & From hinton at cs.toronto.edu Wed Nov 28 12:51:45 2001 From: hinton at cs.toronto.edu (Geoffrey Hinton) Date: Wed, 28 Nov 2001 12:51:45 -0500 Subject: how to decide what to read Message-ID: <01Nov28.125155edt.453148-19376@jane.cs.toronto.edu> In the old days, there had to be a way to decide what to print because printing and circulation were bottlenecks. But now that we have the web, the problem is clearly how to decide what to read. It is very valuable to have the opinions of people you respect in helping you make this choice. For the last five years, I have been expecting someone to produce software that facilitates the following: On people's homepages, there is some convention for indicating a set of recommended papers which are specified by their URL's. When I read a paper I think is really neat, I add its URL to my recommended list using the fancy software (which also allows me to make comments and ratings available). I also keep a file of the homepages of people who I trust (and how much I trust them) and the fancy software alerts me to new papers that several of them like. Its hard to manipulate the system because people own their own hompages and if they bow to pressure to recommend second-rate stuff written by their adviser, other people will stop relying on them. Obviously, there are many ways to elaborate and improve this basic idea and many potential problems that need to be ironed out. But I think it would be extremely useful to have. Somebody please write this software. Geoff Hinton From ivo at idsia.ch Wed Nov 28 04:56:29 2001 From: ivo at idsia.ch (Ivo Kwee) Date: Wed, 28 Nov 2001 10:56:29 +0100 Subject: referee idea References: <3BFCC2C7.6040406@idsia.ch> <3681911.1006414391@[130.62.67.97]> Message-ID: <3C04B4CD.6090409@idsia.ch> Hi, I saw the postings on connectionists about referees. As a matter of fact, I bounced a related idea of open review for JMLR to Leslie just a week ago. I think it is relevant and might be in fact feasible [hope L. doesn't mind me quoting her...]. About L's comment on "sifting": additionally we can keep a personal list of what are the latest reviewed papers of some (important) person, personal "recommendations" (see Amazon), reviewers ranking, global download statistics, online versioning etc. The good thing about "the Amazon way" is that you can also read the reviewers comment themselves, which is mostly not available in most journals but is quite useful (as an exception I think the J. of Am. Statistics does include reviewers comments). Ivo Kwee IDSIA Ivo Kwee wrote: > Leslie, > > Why not make JMRL even more radical? Get away with an Editorial Board > at all? Do a referee system like Amazon.com, publish papers > immediately and let *everyone* act as referee immediately, but also > give points to referees themselves (start the current Board members as > "veterans"). This gives also fair credit to student/researchers that > referee papers on behalf of someone. > > What do you think? > > Ivo > Leslie Pack Kaelbling wrote: > It's an interesting idea. Might be fun to try in parallel with the > usual system (you can start a new journal that works this way!). > > I guess I'm ultimately an elitist. I think that a minority of the > community have better insight, understanding, and taste than the rest, > and that they should decide what gets published. > > Published is probably the wrong word here. In some sense, because of > things like eprint archives, everybody can publish their own work, > which is great and important. So I see the role of journals as really > giving an imprimatur. Some group of people thinks these (few) papers > are good. > > As more and more information becomes available, we'll even pay for > people to sift it for us, and find the good parts. Of course, "good" > to me is "bad" to someone else, and so that other community should > find some other editor to sift out the stuff they like. > > The reason I subscribe to some magazines is that my taste is aligned > with that of the editors. Even if a huge superset of that material > were available online, I'd pay for the (paper or electronic) magazine, > because I don't have time to do the sifting for myself. > > - L > From jbower at bbb.caltech.edu Wed Nov 28 22:11:26 2001 From: jbower at bbb.caltech.edu (James M. Bower) Date: Wed, 28 Nov 2001 19:11:26 -0800 Subject: Fwd: Re: Parallel Paper Submission Message-ID: > > >The opinions of experts should weigh a lot more than those of others --- >that's the only way to maintain quality and quality is absolutely critical >to scientific work. The deep and serious problem, in my view, is that the review of papers has become more and more political and more and more conservative, as viewed over my now 20 years publishing in the scientific literature. All one has to do is look at the real process of publishing in journals like Science and Nature to see that. Even established investigators regularly complain about a review process that seems to be driven more by who you know than what you know and that regularly rejects papers based on what is in the discussion section, rather than what is in the methods and results. Personally, I increasingly find that graduate students and postdocs are better judges of what is scientifically interesting than are many established faculty tied up in these political loops. I realize there is an inherent contradiction here, because at least in biology, many of the senior faculty I know (including one I am very familiar with) rely heavily on their graduate students and post docs to ghost reviews. So perhaps the problem has to do with the fact that the ghost reviewing students are trying to write the kind of reviews they would imagine their mentors would write. :-) Whatever, in my view there is no question that something is broken, and something needs to be done to fix it. The robustness of the discussions on this mail group speaks to that. I also think that, in the long run, the review that matters is the one that will be provided by the graduate student 100 years from now who no longer understands the politics and will therefore be considering published work on its merits and with the benefit of some hindsight. I would prefer to be able to speak to that student without the political filter currently being applied to way too many of our papers. I am happy to take the risk that I will be judged a fool. Rather that than not be allowed to take risks at all. Jim Bower -- *************************************** James M. Bower Ph.D. Research Imaging Center University of Texas Health Science Center - San Antonio and Cajal Neuroscience Research Center University of Texas - San Antonio (626) 791-9615 (626) 791-9797 FAX (626) 484-3918 (cell worldwide) Temporary address for correspondence: 110 Taos Rd. Altadena, CA. 91001 WWW addresses for: laboratory (temp) http://www.bbb.caltech.edu/bowerlab GENESIS (temp) http://www.bbb.caltech.edu/GENESIS From eytan at dpt-info.u-strasbg.fr Wed Nov 28 23:49:35 2001 From: eytan at dpt-info.u-strasbg.fr (Michel Eytan) Date: Thu, 29 Nov 2001 05:49:35 +0100 Subject: Parallel Paper Submission Message-ID: Thus hath held forth Adriaan Tijsseling at 28-11-2001 re Re: Parallel Paper Submission: [snip] > An ideal, but certainly attainable option is to have one single online > repository for papers, in the same vein as citeseer or cogprints. > Researchers can then retrieve the papers they are interested in, read them, > and return a score based on relevance, originality, and the like. Perhaps > they can submit a more detailed commentary anonymously, visible to the > author(s) only. We all know that there is a very serious pb about this: MONEY! The editors will *never* agree to put on the Web for free items that they sell -- and not cheap at that :-((( > In this age, one should optimally try to benefit from modern internet > technologies. Let the academic public decide which articles they deem HOW? The refrereeing process is intended to do precisely that, with the concourse of experts in the field... > relevant and useful. This way articles are much faster distributed (the > current 1, 2, 3 year delay between writing and publishing is really becoming > ridiculous nowadays). > > > Adriaan Tijsseling -- Michel Eytan eytan at dpt-info.u-strasbg.fr I say what I mean and mean what I say From jkolen at altair.coginst.uwf.edu Thu Nov 29 02:29:27 2001 From: jkolen at altair.coginst.uwf.edu (John F. Kolen) Date: Thu, 29 Nov 2001 01:29:27 -0600 Subject: Parallel Paper Submission In-Reply-To: ; from adriaan@tijsseling.com on Wed, Nov 28, 2001 at 02:42:15PM +0900 References: Message-ID: <20011129012927.M1472@altair.coginst.uwf.edu> On Wed, Nov 28, 2001 at 02:42:15PM +0900, Adriaan Tijsseling wrote: > An additional problem is that the reviewing process itself is not > particularly efficient. How many times does it not occur that reviewers' > reports do not agree? Or that one reviewer suggests a modification, which > another reviewer actually requests to be removed? > I think you're talking about consistency here, not efficiency. The editor, not the reviewers, is the final judge in such situations. > An ideal, but certainly attainable option is to have one single online > repository for papers, in the same vein as citeseer or cogprints. > Researchers can then retrieve the papers they are interested in, read them, > and return a score based on relevance, originality, and the like. Perhaps > they can submit a more detailed commentary anonymously, visible to the > author(s) only. > > In this age, one should optimally try to benefit from modern internet > technologies. Let the academic public decide which articles they deem > relevant and useful. This way articles are much faster distributed (the > current 1, 2, 3 year delay between writing and publishing is really becoming > ridiculous nowadays). The big time sinks are collecting reviews and then getting the paper to press. The former is a necessary evil, the magic stamp of approval. The latter, however, could be dispensed with by personally providing access to electronic versions that index engines, such as CiteSeer, can latch onto. And don't we already decide which articles are relevant and useful? Does it really matter if the information comes from a peer-reviewed journal or self-published technical report? Neuroprose was full of such documents. The real issue, IMHO, has nothing to do with disseminating information. Want everyone to have your paper? Just post it, don't bother submitting it to a journal. The true problem is the apparent value of a published article to those committies and administrators outside our field. -- John F. Kolen voice: 850.202.4420 Research Scientist fax: 850.202.4440 Institute for Human and Machine Cognition University of West Florida From giles at research.nj.nec.com Thu Nov 29 13:48:39 2001 From: giles at research.nj.nec.com (Lee Giles) Date: Thu, 29 Nov 2001 13:48:39 -0500 (EST) Subject: Parallel Paper Submission In-Reply-To: <019801c17829$4b96f0a0$050010ac@mendel> Message-ID: Readers of this thread might find this paper "Online or Invisible? "recently published in Nature of interest. http://www.neci.nec.com/~lawrence/papers/online-nature01/ Steve Lawrence presents evidence that online papers are 5 times more likely to be cited than those not online. Lee Giles -- C. Lee Giles, David Reese Professor, School of Information Sciences and Technology Professor, Computer Science and Engineering The Pennsylvania State University 001 Thomas Bldg, University Park, PA, 16802, USA giles at ist.psu.edu - 814 865 7884 http://ist.psu.edu/giles From stiber at u.washington.edu Thu Nov 29 22:12:20 2001 From: stiber at u.washington.edu (Prof. Michael Stiber) Date: Thu, 29 Nov 2001 19:12:20 -0800 Subject: reviewing In-Reply-To: <01Nov28.125155edt.453148-19376@jane.cs.toronto.edu> References: <01Nov28.125155edt.453148-19376@jane.cs.toronto.edu> Message-ID: <15366.63764.111258.27729@kasei.bothell.washington.edu> Geoffrey Hinton writes: > > In the old days, there had to be a way to decide what to print because > printing and circulation were bottlenecks. But now that we have the > web, the problem is clearly how to decide what to read. It is very This is the basis of one of the recurring themes of arguments over "modernizing" the publication review process. Suggestions usually revolve around letting something like market forces decide which papers are really most significant. This is based on the assumption that the only motivation for the current review system is filtering, and that we can all save ourselves some time by using technology to speed the filtering process (perhaps by distributing it among a large number of independently-operating processors, each doing a much smaller amount of work than current reviewers do :^)). For many (most?) people publishing, however, peer review serves another purpose: it provides an ongoing, relatively objective performance review. This is done incrementally, so the review is already distributed along time and among a number of people. When someone is asked to review a package of information about a colleague for promotion or tenure, for example, it is perfectly reasonable to rely on past reviews --- publication record --- to give a broad overview of _one aspect_ of performance. Lacking that, I suppose a conscientious reviewer would be faced with the enormous task of carefully reading a good fraction of the candidate's work. The same would be true, if less extensive, for annual performance reviews. In effect, all that time "saved" in streamlining the paper review process would just pop up elsewhere. Mike Stiber -- Prof. Michael Stiber stiber at u.washington.edu Computing and Software Systems http://faculty.washington.edu/stiber University of Washington, Bothell tel: +1-425-352-5280 Box 358534, 18115 Campus Way NE fax: +1-425-352-5216 Bothell, WA 98011-8246 USA From t.c.pearce at leicester.ac.uk Thu Nov 29 11:10:27 2001 From: t.c.pearce at leicester.ac.uk (Tim Pearce) Date: Thu, 29 Nov 2001 16:10:27 -0000 Subject: 3 PhD/3 Postdoc Positions Message-ID: Qualified applicants are being sought for 6 positions (3 postdoctoral and 3 postgraduate PhD. Researchers) at 3 institutions across Europe in the areas of computational neuroscience, neuromorphic engineering, and experimental neuroscience. All six positions are funded for 4 years duration under the EU Framework V IST, Future and Emerging Technologies initiative, starting from January 2002. The project concerns the development of an unmanned aerial vehicle (UAV) artefact to perform stereotypical moth-like chemotaxis behaviour in uncertain environments. We propose to develop biologically-inspired sensor, information processing and control systems for a c (hemosensing) UAV. The cUAV will identify and track volatile compounds of different chemical composition in outdooor environments. Its olfactory and sensory-motor systems are to be inspired by the moth. This development continues our research in artificial and biological olfaction, sensory processing and analysis, neuronal models of learning, real-time behavioural control, and robotics. Fleets of cUAVs will ultimately be deployed to sense, identify, and map the airborne chemical composition of large scale environments. Further details on the project and the research teams can be found at http://www.le.ac.uk/eg/tcp1/amoth/ The project includes significant funding and opportunities for travel within Europe to visit the laboratories of the participating consortia and outside Europe to attend international scientific meetings. University of Leicester, UK. A computational neuroscience postdoctoral researcher is required to develop a biologically constrained model of the insect antennal lobe operating in real-time and driven by broadly-tuned integrated chemosensors. Expertise in modelling of spiking neuronal populations, information theoretical analysis, and/or modelling of synaptic plasticity is desirable. A postgraduate researcher (who will be expected to register for a PhD) in the area of neuromorphic engineering is required to support this modelling activity as well as deal with the implementation of the model using FPGA/DSP technology and its integration with real-world chemical sensors. Strong mathematical, analytical and programming skills are required for both positions. Informal enquiries regarding these positions and the project in general should be addressed to the project co-ordinator, Dr. T.C. Pearce, Department of Engineering, University of Leicester, Leicester LE1 7RH, United Kingdom, +44 116 223 1290, t.c.pearce at le.ac.uk ETH/Univ Zurich, Switzerland. A computational neuroscience postdoctoral researcher is required to implement a model of sequence-based learning based upon the protocerebellum of the moth. A PhD researcher is also required for neuromorphic hardware implmentation. Both researchers will be involved in the construction of the UAV. Hence, interest and demonstrated skills in both computational neuroscience and the construction and control of robots is required. Informal enquiries regarding these positions and the project in general should be addressed to the project co-ordinator, Dr. P.F.M.J. Verschure, Institute of Neuroinformatics Winterthurerstrasse 190, 8057, Zurich, Switzerland. ++41 1 6353070, pfmjv at ini.phys.ethz.ch Sveriges Lantbruksuniversitet, Sweden. At the researcher level we will hire a postdoctoral scientist specializing in neurophysiology and neuromorphology of the insect central olfactory system. The main task will be to elucidate neural interactions within the antennal lobe allowing the amplification in sensitivity observed in earlier investigations A postgraduate researcher (who will be expected to register for a PhD) will work on similar issues but will also perform behavioural experiments investigating moth orientation to host odours and run linked gas chromatographic - electrophysiological experiments to pinpoint active semiochemicals. Both positions require skills in neurobiological techniques. Both positions will be formal positions, including full Swedish social benefits. Informal enquiries regarding these positions and the project in general should be addressed to the local co-ordinator, Professor Bill S. Hansson, Division of Chemical Ecology, Department of Crop Science, Swedish University of Agricultural Sciences, P.O. Box 44, SE-23053 Alnarp, Sweden, +46 40415300, bill.hansson at vv.slu.se Applicants should send a CV, cover letter stating for which position they are applying, the names of at least three referees, to the named academic associated with each position. Deadline for receipt of applications is 20th December, 2001. Regards, Tim. -- T.C. Pearce, PhD URL: http://www.leicester.ac.uk/eg/tcp1/ Lecturer in Bioengineering E-mail: t.c.pearce at leicester.ac.uk Department of Engineering Tel: +44 (0)116 223 1290 University of Leicester Fax: +44 (0)116 252 2619 Leicester LE1 7RH Bioengineering, Transducers and United Kingdom Signal Processing Group From gaijin at yha.att.ne.jp Thu Nov 29 10:07:45 2001 From: gaijin at yha.att.ne.jp (Sam Joseph) Date: Fri, 30 Nov 2001 00:07:45 +0900 Subject: how to decide what to read References: <01Nov28.125155edt.453148-19376@jane.cs.toronto.edu> Message-ID: <3C064F41.4A22FB2E@yha.att.ne.jp> This is exactly the sort of thing that the NeuroGrid project is trying to achieve. http://www.neurogrid.net/ I won't claim that we have the perfect solution just yet, but we're working towards a system where you can easily publish meta-data about whatever documents you care to. Over time the system learns who you go to for which information, automatically adjusting future recommendations on this basis. e.g. I often read and download pages related to "Fly Fishing"that were marked up by John, so my NeuroGrid node learns to go to John first when I search for things related to "Fly Fishing". NeuroGrid is completely open source, the code is all in SourceForge, which means that it 1. is still under development 2 will take some time before it is a turn key solution I believe that integrating trust and learning into this sort of distributed system is essential and that ultimately we will all benefit from the approach, whether NeuroGrid is the actual system we end up using or not. CHEERS> SAM Geoffrey Hinton wrote: > In the old days, there had to be a way to decide what to print because > printing and circulation were bottlenecks. But now that we have the > web, the problem is clearly how to decide what to read. It is very > valuable to have the opinions of people you respect in helping you > make this choice. For the last five years, I have been expecting > someone to produce software that facilitates the following: > > On people's homepages, there is some convention for indicating a set > of recommended papers which are specified by their URL's. When I read > a paper I think is really neat, I add its URL to my recommended list > using the fancy software (which also allows me to make comments and > ratings available). > > I also keep a file of the homepages of people who I trust (and how > much I trust them) and the fancy software alerts me to new papers that > several of them like. > > Its hard to manipulate the system because people own their own > hompages and if they bow to pressure to recommend second-rate stuff > written by their adviser, other people will stop relying on them. > > Obviously, there are many ways to elaborate and improve this basic > idea and many potential problems that need to be ironed out. > But I think it would be extremely useful to have. > Somebody please write this software. > > Geoff Hinton From james at tardis.ed.ac.uk Thu Nov 29 09:23:02 2001 From: james at tardis.ed.ac.uk (James Hammerton) Date: Thu, 29 Nov 2001 14:23:02 +0000 Subject: Parallel Paper Submission In-Reply-To: Your message of "Tue, 27 Nov 2001 22:36:02 CST." <200111280436.fAS4a2a24303@ari1.cecs.missouri.edu> Message-ID: <20011129142303.555687B5D@omega.tardis.ed.ac.uk> Hi, I've followed this discussion with some interest. It seems to me the main problem people are trying to address is the amount of time taken in the reviewing process. In my opinion, the way things work now is fine, the long times taken by the review process aside. Speeding up the review process isn't so difficult though if things are handled electronically. I'm one of the editors for a special issue of the JMLR, and we managed to get the reviewing process done and notifications sent out inside 3 months. The deadline for papers was 2nd September, we gave a 5th November deadline for reviews to be sent back to us and we planned notifications for the 16th November, but we slipped back a week on that timetable due to some late reviews. The JMLR normally gives reviewers 6 weeks to return their reviews and gets a relatively quick turnover as a result. I don't see why more journals can't operate like this -- even if the final publication is in print rather than on the web. I don't think the idea put forward for authors choosing their own reviewers is a good one -- there's a conflict of interests there. It seems to me that the ideas for pools of reviewers to whom papers get submitted is interesting but may be too complicated in practice. I'm not sure there is any pressing need to change from the current model, as opposed to finding ways to speed it up (e.g. by handling things electronically and using tight review schedules). James Hammerton From andre at icmc.sc.usp.br Thu Nov 29 05:30:25 2001 From: andre at icmc.sc.usp.br (andre) Date: Thu, 29 Nov 2001 08:30:25 -0200 Subject: IJCIA Journal - 2001 Contents References: <3B1697EF.294D0DC2@cpdee.ufmg.br> Message-ID: <3C060E41.A58C9D96@icmc.sc.usp.br> >>> CONTENTS LIST YEAR 2001 <<<< International Journal of Computational Intelligence and Applications by Imperial College Press and World Scientific http://www.wspc.com.sg/profiles/anncat/anncat/journals/compsci/ijcia.html Table of Contents Vol. 1 Issue 1 K. Horio and T. Yamakawa: Feedback Self-Organizing Map and its Applications to Spatio-Temporal Pattern Classification Extent: 1-18 W. Pedrycz and A. Gacek: Learning of Fuzzy Automata Extent: 19-33 J. M. Corchado, B. Lees and J. Aiken: Hybrid Instance-Based System for Predicting Ocean Temperatures Extent: 35-52 Y. Bennani and F. Bossaert Modular Connectionist Modelling and Classification Approaches for Local Diagnosis in Telecommunication Traffic Management Extent: 53-70 S. Oman and P. Cunningham Using Case Retrieval to Seed Genetic Algorithms Extent: 71-82 W. Xiangdong and W. Shoujue The Application of Feedforward Neural Networks in VLSI Fabrication Process Optimization Extent: 83-90 G. W. Grewal and T. C. Wilson An Enhanced Genetic Algorithm for Solving the High-Level Synthesis Problems of Scheduling, Allocation, and Binding Extent: 91-110 Calendar of Events Extent: 111-114 Book Review Extent: 115-119 Table of Contents Vol. 1 Issue 2 V. Stephan, K. Debes, H.-M. Gross, F. Wintrich and H. Wintrich A New Control Scheme for Combustion Processes Using Reinforcement Learning Based on Neural Networks Extent: 121-136 H. K. Lee and S. I. Yoo A Neural Network-Based Image Retrieval Using Nonlinear Combination of Heterogeneous Features Extent: 137-149 X. Z. Gao and S. J. Ovaska Fuzzy Power Command Enhancement in Mobile Communications Systems Extent: 151-163 G. G. Yen and Q. Fu Automatic Frog Calls Monitoring System: A Machine Learning Approach Extent: 165-186 S. S. Quek, C. P. Lim and K. K. Peh Prediction of Drug Dissolution Profiles Using Artificial Neural Networks Extent: 187-202 J. Sil and A. Konar A Hybrid Approach to Knowledge Acquisition Using Neural Petri Nets and DS Theory Extent: 203-223 Calender of Events Extent: 225-233 Book Review Extent: 235-238 Table of Contents Vol. 1 Issue 3 L. N. de Castro and F. J. Von Zuben: Immune and Neural Network Models: Theoretical and Empirical Comparisons Extent: 239-257 H. Selvaraj, P. Sapiecha and T. Luba Functional Decomposition and Its Applications in Machine Learning and Neural Networks Extent: 259-271 P. A. Boxer Learning Naive Physics by Visual Observation: Using Qualitative Spatial Representations and Probabilistic Reasoning Extent: 273-285 P. Wira and J.-P. Urban Predicting Unknown Motion for Model Independent Visual Servoing Extent: 287-302 Z.-Q. Liu and Y. Zhang Compensation Competitive Learning Extent: 303-322 Calendar of Events Extent: 323-329 Book Reviews Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence G. Weiss Extent: 331-334 Pattern Classification R. O. Duda, P. E. Hart and D. G. Stork Extent: 335-339 Table of Contents Vol. 1 Issue 4 Z-H. Zhou J-X. Wu, W. Tang and Z-Q. Chen: Combining regression estimators: GA-based selective neural network ensemble Extent: 341-356 H. W-K. Chia and C-L. Tan: Neural logic network learning using genetic programming Extent: 357-368 K. Mcgarry, S. Wermter and J. Macintyre: The extraction of knowledge from local function networks Extent: 369-382 B.W. Wah and M. Qian: Violation-guided neural-network learning for constrained formulations in time-series predictions Extent: 383-398 D.S. Yeung, S. Qiu, E.C.C. Tsang and X. Wang: A general updating rule for discrete Hopfield-type neural network with time-delay and the corresponding search algorithm Extent: 399-412 F. Linaker and H. Jacobsson: Learning delayed response tasks through unsupervised event extraction Extent: 413-426 S. Behnke: Learning iterative image reconstruction in the neural abstraction pyramid Extent: 427-438 R.S.T. Lee and J.K. Liu: NORN predictor - stock prediction using a neural oscillatory-based recurrent network Extent: 439-452 From jbednar at cs.utexas.edu Thu Nov 29 02:59:19 2001 From: jbednar at cs.utexas.edu (James A. Bednar) Date: Thu, 29 Nov 2001 01:59:19 -0600 Subject: self-organization software, papers, web demos Message-ID: <200111290759.BAA09014@pale.csres.utexas.edu> Version 3.0 of the LISSOM software package for self-organization of hierarchical laterally connected maps is now available from the UTCS Neural Networks Research Group website, http://www.cs.utexas.edu/users/nn. The software has been developed in the LISSOM project of modeling the mammalian visual system, and is intended to serve as a starting point for computational studies of the development and function of perceptual maps in general. Abstracts of two recent papers from the LISSOM project are also included below. The first paper shows how LISSOM simulations can be scaled up to model large cortical areas, obtaining quantitatively equivalent maps at each size. The second paper uses these techniques and the LISSOM software to demonstrate how innate face preferences and later adult face processing may both result from general-purpose learning and self-organization. Other papers and demos of the LISSOM software are available at http://www.cs.utexas.edu/users/nn/pages/research/visualcortex.html. - Jim, Amol, and Risto Software: ----------------------------------------------------------------------- LISSOM V3.0: HIERARCHICAL LATERALLY CONNECTED SELF-ORGANIZING MAPS http://www.cs.utexas.edu/users/nn/pages/software/abstracts.html#lissom James A. Bednar The LISSOM V3.0 package contains the C++ source code and examples for training and testing RF-LISSOM and HLISSOM. These self-organizing models support detailed simulations of the development and function of the mammalian visual system. The simulator is designed to have full functionality even when run in batch mode or remote mode, using a simple but powerful command file format and online command prompt. Because of the focus on batch/remote use, it does not have a GUI, but it does create a wide variety of images for analysis and testing. Sample command files are provided for running orientation, ocular-dominance, and face perception simulations using a variety of network and machine sizes. Extensive documentation is also included, all of which is also available via online help where appropriate. Version 3.0 supports an arbitrary number of maps of various types, which can be arranged into a hierarchy representing the visual system. Currently supported map types include input regions (e.g. a Retina), convolving regions (e.g. ON/OFF cell layers), and RF-LISSOM regions (with modifiable afferent and lateral connections.) Environmental input is controlled by a simple but flexible language that allows arbitrary patterns and natural images to be rendered, scaled, rotated, combined, etc. This language makes it possible to use LISSOM for many of your own projects without having to write any new simulator code. The simulator can also serve as a good starting point for writing a batch-mode neural-network or related simulator. In particular, it includes independent and general-purpose routines for image creation from matrices, PPM format image input and output, gnuplot image creation, polymorphic datatypes, 2D input drawing, streams of inputs from different distributions, convolution kernel specification, and cortical map measurement, as well as many general-purpose support algorithms and datatypes. Papers: ----------------------------------------------------------------------- SCALING SELF-ORGANIZING MAPS TO MODEL LARGE CORTICAL NETWORKS Amol Kelkar, James A. Bednar and Risto Miikkulainen Department of Computer Sciences, The University of Texas at Austin Technical Report AI-00-285, August 2001. (Expanded version of CNS*01 paper; 16 pages) http://www.cs.utexas.edu/users/nn/pages/publications/abstracts.html#kelkar.utcstr01 Self-organizing computational models with specific intracortical connections can explain many functional features of visual cortex, such as topographic orientation and ocular dominance maps. However, due to their computational requirements, it is difficult to use such detailed models to study large-scale phenomena like object segmentation and binding, object recognition, tilt illusions, optic flow, and fovea--periphery interaction. This paper introduces two techniques that make large simulations practical. First, a set of general linear scaling equations for the RF-LISSOM self-organizing model is derived and shown to result in quantitatively equivalent maps over a wide range of simulation sizes. Second, the equations are combined into a new growing map method called GLISSOM, which dramatically reduces the memory and computational requirements of large self-organizing networks. With GLISSOM it should be possible to simulate all of human V1 at the single-column level using existing supercomputers, making detailed computational study of large-scale phenomena possible. ----------------------------------------------------------------------- LEARNING INNATE FACE PREFERENCES James A. Bednar and Risto Miikkulainen Department of Computer Sciences, The University of Texas at Austin Technical Report AI-01-291, November 2001. (Expanded version of AAAI-00 paper; 28 pages) http://www.cs.utexas.edu/users/nn/pages/publications/abstracts.html#bednar.utcstr01 Whether humans have a specific, innate perceptual ability to process faces remains controversial. Studies have found face-selective brain regions in adults and have shown that even newborns preferentially attend to face-like stimuli. On this basis researchers have proposed that there are genetically hard-wired brain regions that specifically process faces. However, other studies suggest that the face-processing hardware is general purpose and highly plastic, even at birth. We propose a solution to this apparent paradox: innate face preferences may be learned by a general-purpose self-organizing system from internally generated input patterns, such as those found in PGO waves during REM sleep. Simulating this process with the HLISSOM model, we demonstrate that such an architecture constitutes an efficient way to specify, develop, and maintain functionally appropriate perceptual organization. This preorganization can account for newborn face preferences, providing a computational explanation for how genetic influences interact with experience to construct a complex system. From neted at anc.ed.ac.uk Thu Nov 29 10:20:47 2001 From: neted at anc.ed.ac.uk (Network Editor) Date: Thu, 29 Nov 2001 15:20:47 +0000 Subject: NETWORK: Computation in Neural Systems Message-ID: <15366.21071.74022.793376@gargle.gargle.HOWL> Please see below the contents for the current issue of NETWORK: Computation in Neural Systems. NETWORK is always striving to reduce the time taken in processing submitted papers. Here are some figures for the past year: - For accepted papers, our median receipt-to-final decision time was 157 days. - For rejected papers, our median receipt-to-final decision time was 137 days. - Note that for accepted papers, the median receipt-to-FIRST decision time was 94 days. The difference of 63 days was in most part due to authors carrying out revisions required prior to publication. NETWORK is available electronically (http://www.iop.org/journals/ne). For non-subscribers the current issue is freely accessible (http://www.iop.org/free2001). --------------------------------------------------------------------------- Professor David Willshaw Editor-in-Chief NETWORK: Computation in Neural Systems Institute for Adaptive & Neural Computation Division of Informatics University of Edinburgh 5 Forrest Hill Edinburgh EH1 2QL UK Tel: +44-(0)131-650 4404 Fax: +44-(0)131-650 4406 Email: neted at anc.ed.ac.uk ============================================================================= NETWORK: Computation in Neural Systems, volume 12, issue 4 Pages: 409-516 PAPERS 409 Effect of lateral connections on the accuracy of the population code for a network of spiking neurons M Spiridon and W Gerstner 423 Speed of feedforward and recurrent processing in multilayer networks of integrate-and-fire neurons S Panzeri, E T Rolls, F Battaglia and R Lavis 441 Neural coding and decoding: communication channels and quantization A G Dimitrov and J P Miller 473 Pattern recognition in a compartmental model of a CA1 pyramidal neuron B P Graham 493 A hybrid learning network for shift, orientation, and scaling invariant pattern recognition R Wang BOOK REVIEW 513 Mechanisms of Cortical Development D J Price and D J Willshaw (reviewed by P Kind) 515 AUTHOR INDEX (with titles), Volume 12 From: esann To: "Connectionists at cs.cmu.edu" References: From bogus@does.not.exist.com Thu Nov 29 09:09:42 2001 From: bogus@does.not.exist.com () Date: Thu, 29 Nov 2001 15:09:42 +0100 Subject: ESANN'2002 : extended deadline Message-ID: ---------------------------------------------------- | | | ESANN'2002 | | | | 10th European Symposium | | on Artificial Neural Networks | | | | Bruges (Belgium) - April 24-25-26, 2002 | | | | Extended deadline | ---------------------------------------------------- Due to numerous requests, we are pleased to announce that the deadline for submitting papers to the ESANN'2002 conference has been extended. New deadline: December 10, 2001. The ESANN'2002 covers most of the topics related to the neural network field (see http://www.dice.ucl.ac.be/esann for details). Six special sessions will also be organized: 1. Perspectives on Learning with Recurrent Networks (B. Hammer, J.J. Steil) 2. Representation of high-dimensional data (A. Gurin-Dugu, J. Hrault) 3. Neural Network Techniques in Fault Detection and Isolation (S. Simani) 4. Hardware and Parallel Computer Implementations of Neural Networks (U. Seiffert) 5. Exploratory Data Analysis in Medicine and Bioinformatics (A. Wismller, T. Villmann) 6. Neural Networks and Cognitive Science (H. Paugam-Moisy, D. Puzenat) Instructions concerning the submission of papers are detailed on the web site of the conference. ======================================================== ESANN - European Symposium on Artificial Neural Networks http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews,... Michel Verleysen Univ. Cath. de Louvain - Microelectronics Laboratory 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at dice.ucl.ac.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at dice.ucl.ac.be ======================================================== From terry at salk.edu Thu Nov 29 18:40:38 2001 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 29 Nov 2001 15:40:38 -0800 (PST) Subject: NEURAL COMPUTATION 13:12 Message-ID: <200111292340.fATNecF17024@purkinje.salk.edu> Neural Computation - Contents - Volume 13, Number 12 - December 1, 2001 ARTICLE Synchronization of the Neural Response to Noisy Periodic Synaptic Input A. N. Burkitt and G.M. Clark NOTE Specification of Training Sets and the Number of Hidden Neurons for Multilayer Perceptrons L. S. Camargo and T. Yoneyama LETTERS Spotting Neural Spike Patterns Using an Adversary Background Model Itay Gat and Naftali Tishby Intrinsic Stabilization of Output Rates by Spike-Based Hebbian Learning Richard Kempter, Wulfram Gerstner, and J. Leo van Hemmen Information Transfer Between Rhythmically Coupled Networks: Reading the Hippocampal Phase Code Ole Jensen Gaussian Process Approach to Spiking Neurons for Inhomogeneous Poisson Inputs Ken-ichi Amemori and Shin Ishii Dual Information Representation with Stable Firing Rates and Chaotic Spatiotemporal Spike Patterns in a Neural Network Model Osamu Araki and Kazuyuki Aihara Neurons with Two Sites of Synaptic Integration Learn Invariant Representations Konrad P. Kording and Peter Konig Linear Constraints in Weight Representation for Generalized Learning of Multilayer Networks Masaki Ishii and Itsuo Kumazawa Feedforward Neural Network Construction Using Cross Validation Rudy Setiono ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2002 - VOLUME 14 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $88 $94.16 $136 Institution $506 $451.42 $554 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From adriaan at tijsseling.com Fri Nov 30 06:38:47 2001 From: adriaan at tijsseling.com (Adriaan Tijsseling) Date: Fri, 30 Nov 2001 20:38:47 +0900 Subject: Parallel Paper Submission In-Reply-To: Message-ID: > http://www.neci.nec.com/~lawrence/papers/online-nature01/ > > Steve Lawrence presents evidence that online papers are 5 times > more likely to be cited than those not online. Amen to that! Which was basically my point as well when I suggested a central repository for papers. Some assumed I was talking about journals making paper submission an online thing. But in fact, why are we still going for paper? Research would speed up much more if work could be published online in a searchable and widely accessible database. Would that cost money? None at all. All that is needed is a fast server and a reliable host. Researchers who have read a paper in that database can submit a review or score, provided they are subscribed (for free of course) to that kind of service. Over time, any paper would be accumulating reviews and scores, much to the benefit of the author. After all, it would not be restricted to one or two or three reviewers, but to anyone interested in the paper. Of course, as someone pointed out to me, this may mean some papers might never be reviewed (But then, one could actively request a review). These are just loose ideas, but I really feel the time is there to make away with tedious reviewing, editing, and publishing and instead use what is already there: internet. Adriaan Tijsseling From goldfarb at unb.ca Fri Nov 30 12:57:58 2001 From: goldfarb at unb.ca (Lev Goldfarb) Date: Fri, 30 Nov 2001 13:57:58 -0400 (AST) Subject: A paper: "What is a structural measurement process?" Message-ID: (Our apologies in case you, as a subscriber to several lists, receive several copies of this message) Dear colleagues, The following paper, whose abstract is attached below, proposes a far-reaching (biologically inspired) generalization of the classical concept of measurement process, based on the ETS model for structural representation proposed by us earlier, and attempts to explain it on a simple "shape example". The paper also attempts to clarify the radical differences between the two kinds of "measurement" processes. Thus, we address a very broad scientific context within which it might be useful to treat the proposed ETS model. http://www.cs.unb.ca/profs/goldfarb/smp.ps or http://www.cs.unb.ca/profs/goldfarb/smp.pdf Best regards, Lev http://www.cs.unb.ca/profs/goldfarb.htm ********************************************************************** WHAT IS A STRUCTURAL MEASUREMENT PROCESS? Lev Goldfarb and Oleg Golubitsky ABSTRACT. Numbers have emerged historically as by far the most popular form of representation. All our basic scientific paradigms are built on the foundation of these, numeric, or quantitative, concepts. Measurement, as conventionally understood, is the corresponding process for (numeric) representation of objects or events, i.e., it is a procedure or device that realizes the mapping from the set of objects to the set of numbers. Any (including a future) measurement device is constructed based on the underlying mathematical structure that is thought appropriate for the purpose. It has gradually become clear to us that the classical numeric mathematical structures, and hence the corresponding (including all present) measurement devices, impose on "real" events/objects a very rigid form of representation, which cannot be modified dynamically in order to capture their combinative, or compositional, structure. To remove this fundamental limitation, a new mathematical structure--evolving transformation system (ETS)--was proposed earlier. This mathematical structure specifies a radically new form of object representation that, in particular, allows one to capture (inductively) the compositional, or combinative, structure of objects or events. Thus, since the new structure also captures the concept of number, it offers one the possibility of capturing simultaneously both the qualitative (compositional) and the quantitative structure of events. In a broader scientific context, we briefly discuss the concept of a fundamentally new, biologically inspired, "measurement process", the inductive measurement process, based on the ETS model. In simple terms, all existing measurement processes "produce" numbers as their outputs, while we are proposing a measurement process whose outputs capture the representation of the corresponding class of objects, which includes the class projenitor (a non-numeric entity) plus the class transformation system (the structural class operations). Such processes capture the structure of events/objects in an inductive manner, through a direct interaction with the environment. From stiber at u.washington.edu Fri Nov 30 17:18:33 2001 From: stiber at u.washington.edu (Prof. Michael Stiber) Date: Fri, 30 Nov 2001 14:18:33 -0800 Subject: Parallel Paper Submission In-Reply-To: References: Message-ID: <15368.1465.955083.919049@kasei.bothell.washington.edu> Adriaan Tijsseling writes: > > Researchers who have read a paper in that database can submit a review or > score, provided they are subscribed (for free of course) to that kind of > service. Over time, any paper would be accumulating reviews and scores, much > to the benefit of the author. After all, it would not be restricted to one > or two or three reviewers, but to anyone interested in the paper. Of course, > as someone pointed out to me, this may mean some papers might never be > reviewed (But then, one could actively request a review). > > These are just loose ideas, but I really feel the time is there to make away > with tedious reviewing, editing, and publishing and instead use what is > already there: internet. Actually, the scoring system you mention is also already there: ISI Web of Science (the electronic version of the Science Citation Index). In this case, scores are the number of times that a paper has been cited, with links to the citing works (which in effect review the paper by using its results). Unfortunately, it isn't public domain. Mike Stiber -- Prof. Michael Stiber stiber at u.washington.edu Computing and Software Systems http://faculty.washington.edu/stiber University of Washington, Bothell tel: +1-425-352-5280 Box 358534, 18115 Campus Way NE fax: +1-425-352-5216 Bothell, WA 98011-8246 USA From hans.liljenstrom at sdi.slu.se Fri Nov 30 16:50:45 2001 From: hans.liljenstrom at sdi.slu.se (Hans Liljenstrom) Date: Fri, 30 Nov 2001 22:50:45 +0100 Subject: PhD position Message-ID: <017201c179e9$13403380$6895143e@oden> A PhD position is open at the Dept. of Biometry and Informatics, SLU, Uppsala Ref number 4440/01-4711 Title: Mathematical modeling, analysis and computer simulation of brain dynamics, with special focus on EEG signals. Project area: The project is part of a collaboration with the psychiatric clinic at a nearby hospital. The clinic has modern equipment for continuous measure and treatment, and data for hundreds of patients is produced. The project objective is to relate EEG response to the effect of treatments, and in support for the analysis, computer models and simulations of neural networks are needed. The project also includes development of non-linear models and analytical tools for stochastic and chaotic time series. Many new and interesting problems can be addressed with a combination of stochastic and deterministic modelling. Development of computational techniques is also required to deal with the gigantic amount of data available. The theoretical results from the project are expected to provide new insight in how EEG signals from the brain should be interpreted and used for prediction of clinical treatment effects. At the Department of Biometry and Informatics, a broad and cross-disciplinary research is carried out, including theoretical biology and biophysics, applied mathematics, mathematical statistics/biometry, as well as environmental and geo-informatics. In addition, there is an extensive educational program within these areas. Suitable background: MSc in engineering, physics, computer science, or similar programs, or a mathematical education with focus on biology, biomedicine or similar. Financing: A stipend covering one year of studies, whereafter a full graduate position is created. Both forms include, in addition to the research work, also possibilities of 20% institutional work (such as teaching). For more information contact project leader Prof. Hans Liljenstrm, tel. +46-(0)18-67 17 28 or email hans.liljenstrom at bi.slu.se. Information regarding salary and other administrative issues is given by Birgitta Callmer at the personnel division of SLU, tel. +46-(0)18-67 10 76. Welcome with your application, including a personal CV and a description of your interests and expectations, and why you would be a suitable graduate student at our department. Your application should be marked with reference number 4440/01-4711 and should be sent to Registrator, SLU, Box 7070, SE-750 07 Uppsala, Sweden, by 10 December 2001. ================================================================ Hans Liljenstrm, Prof. Dept. of Biometry and Informatics Swedish University of Agricultural Sciences P. O. Box 7013, SE-750 07 Uppsala, Sweden Phone: +46 (0)18-671728, +46 (0)73-654 7977 Fax: +46 (0)18 673502, email: Hans.Liljenstrom at bi.slu.se Home page: www.bi.slu.se/~hanslil ================================================================ From hinton at cs.toronto.edu Wed Nov 28 12:51:45 2001 From: hinton at cs.toronto.edu (Geoffrey Hinton) Date: Wed, 28 Nov 2001 12:51:45 -0500 Subject: how to decide what to read Message-ID: In the old days, there had to be a way to decide what to print because printing and circulation were bottlenecks. But now that we have the web, the problem is clearly how to decide what to read. It is very valuable to have the opinions of people you respect in helping you make this choice. For the last five years, I have been expecting someone to produce software that facilitates the following: On people's homepages, there is some convention for indicating a set of recommended papers which are specified by their URL's. When I read a paper I think is really neat, I add its URL to my recommended list using the fancy software (which also allows me to make comments and ratings available). I also keep a file of the homepages of people who I trust (and how much I trust them) and the fancy software alerts me to new papers that several of them like. Its hard to manipulate the system because people own their own hompages and if they bow to pressure to recommend second-rate stuff written by their adviser, other people will stop relying on them. Obviously, there are many ways to elaborate and improve this basic idea and many potential problems that need to be ironed out. But I think it would be extremely useful to have. Somebody please write this software. Geoff Hinton