From d6-evans at uwe.ac.uk Thu Sep 2 07:48:32 2004 From: d6-evans at uwe.ac.uk (Dylan Evans) Date: Thu, 2 Sep 2004 12:48:32 +0100 (BST) Subject: Call for papers: AISB'05 symposium on emotion and motivation Message-ID: Agents that want and like: motivational and emotional roots of cognition and action. A symposium of the AISB'05 Convention University of Hertfordshire, Hatfield, UK, 14th - 15th April, 2005 ** Submission Deadline: October 31, 2004 ** http://www.dylan.org.uk/emotivation_aisb05/ SYMPOSIUM DESCRIPTION: --------------------- Motivation and emotion are highly intertwined (e.g., emotions are often very powerful motivational factors; motivation can be seen as a consequence of emotion and viceversa, etc.) and it is not always easy to establish clear boundaries between them. Both types of phenomena are grouped under the broader category of "affect", traditionally distinguished from "cold" cognition. They lie at the heart of autonomy, adaptation, and social interaction in both biological and artificial agents. They also have a powerful and wide-ranging influence on many aspects of cognition and action. However, their roles are often considered to be complementary - as a first approximation, motivation would be concerned with the internal and external factors involved in the establishment of "goals" and the initiation and execution of goal-oriented action, whereas emotion is rather concerned, among other critical factors, with evaluative aspects of the relation between an agent and its environment. This symposium proposes to investigate the roles and mutual interactions of motivation and emotion in influencing different aspects of cognition and action in biological and artificial agents that interact with their physical and social environment. The nature of this topic necessitates a highly multi-disciplinary symposium, and we invite contributions from different relevant disciplines such as psychology, biology, neuroscience, ethology, sociology and philosophy, in addition to AI and robotics. SYMPOSIUM ORGANISERS: -------------------- Lola Canamero Adaptive Systems Research Group School of Computer Science University of Hertfordshire College Lane, Hatfield, Herts AL10 9AB Phone: +44-(0)1707-284308; Fax: +44-(0)1707-284303 URL: http://homepages.feis.herts.ac.uk/~comqlc E-mail: L.Canamero at herts.ac.uk Dylan Evans Faculty of Computing, Engineering and Mathematical Sciences University of the West of England Frenchay Campus Coldharbour Lane, Bristol BS16 1QY Tel: 0117-328-3294 (lab) Tel: 0117-328-2489 (office) Fax: 0117-344-3960 Web: http://www.dylan.org.uk E-mail: d6-evans at uwe.ac.uk SUBMISSION DETAILS: ------------------ Potential participants who would wish to present their work at the symposium (poster, demo, or oral presentation) should submit an extended abstract of no more than 2500 words. Contributions should describe work in progress, completed work, positions, or give insight into the current state or perspectives of research in the topic of the symposium. All submissions must include: title, author(s) name(s), affiliation(s), mailing and electronic addresses, and telephone and fax numbers. The abstracts submission deadline for this symposium is *31st October, 2004*. Extended abstracts of no more than 2500 words should be sent by e-mail (ASCII or URL from which your contribution can be downloaded are preferred; otherwise attached PDF, or UNIX-compatible postscript) to both organisers: L.Canamero at herts.ac.uk AND d6-evans at uwe.ac.uk Since contributions will be evaluated on the basis of extended abstracts, it is very important that authors make very clear why and how their contribution is relevant to the symposium. Abstracts should explain clearly: - The problem you are addressing. - Why this is an interesting problem, and how and why it is relevant to the theme of the symposium. - What has been tried before (in your community, in different communities) and why/how your contribution is better/different/more original. - How it will help others/contribute to/enrich research or applications having to do with the symposium topic. - Some results/proof/hint that it works (how can your work be evaluated?). Authors of accepted submissions will be invited to contribute a paper to the symposium proceedings, edited by the AISB Society. PROGRAMME COMMITTEE: ------------------- Orlando Avila-Garcia - University of Hertfordshire, UK Ruth Aylett - Univesity of Salford, UK Cynthia Breazeal - MIT, USA Joanna Bryson - University of Bath, UK Lola Canamero - University of Hertfordshire, UK Dylan Evans - University of the West of England, UK Philippe Gaussier - University of Cergy-Pontoise, France Steve Grand - Cyberlife Research Ltd., UK Chris Melhuish - University of the West of England, UK Jean-Arcady Meyer - LIP6, France Jacqueline Nadel - CNRS & Hopital La Salpetriere, France Paolo Petta - OFAI & Medical University of Vienna, Austria Tony Prescott - University of Sheffield, UK David Sander - University of Geneva, CH IMPORTANT DATES: --------------- - 31 October 2004: Abstract submissions due - 22 November 2004: Notification to authors - 17 December 2004: camera-ready copies due to symposium chairs - 14 January 2005: early registration deadline - 12-15 April 2005: AISB 2005 convention (symposium dates: 14 & 15 April) For further details about the symposium please visit http://www.dylan.org.uk/emotivation_aisb05 --- Dylan Evans Senior Lecturer in Intelligent Autonomous Systems Faculty of Computing, Engineering and Mathematical Sciences University of the West of England Frenchay Campus Coldharbour Lane Bristol BS16 1QY Tel: 0117-328-3294 (lab) Tel: 0117-328-2489 (office) Fax: 0117-344-3960 Web: http://www.dylan.org.uk Please avoid sending me Word or PowerPoint attachments: see http://www.fsf.org/philosophy/no-word-attachments.html From chaos at first.fhg.de Thu Sep 2 16:03:44 2004 From: chaos at first.fhg.de (Fraunhofer First) Date: Thu, 02 Sep 2004 22:03:44 +0200 Subject: Two positions in machine learning at FIRST.IDA, Berlin Message-ID: <41377CA0.5030608@first.fhg.de> Fraunhofer FIRST.IDA has two open positions in machine learning in Berlin, Germany: Department Description (see also http://ida.first.fraunhofer.de/) The IDA group at Fraunhofer FIRST in Berlin is concerned with theoretical concepts and algorithms for machine learning and their practical application to real world data analysis problems. In particular, we are developing tools for high-dimensional multivariate statistics based on methods originally developed in the field of statistics and, more recently, in the neural networks and machine learning community. Our major objective is to pursue our research all the way from theory to application. To this end, we are contributing to the theoretical development of new data analysis techniques, to their implementation according to software-engineering standards, and, finally, to their industrial or academic application. Scope of Work The positions will be focused on developing and applying methods and software in the areas of machine learning, signal processing, and statistical data analysis. One position is directed towards EEG analysis, the other towards computational chemistry. Required Knowledge and Skills - Expertise in machine learning (in particular: kernel-based methods), signal processing, and statistical data analysis. - Good organizational and communication skills. - Significant experience in software development, preferably in MATLAB. - Ability to interact well in a team in the creation of new designs and approaches. - A strong plus would be experience in EEG analysis or computational chemistry. For further details, please refer to the official job announcement (in german): http://www.jobs.fraunhofer.de/servlet/is/14526/ Please submit your resume by mentioning the job ID "FIRST-113-04-005" to Fraunhofer-Gesellschaft Zentrale-Hauptabteilung Personal z.H. Frau Rabel Kekulestr. 7 12489 Berlin Germany From doya at irp.oist.jp Fri Sep 3 06:54:16 2004 From: doya at irp.oist.jp (Kenji Doya) Date: Fri, 3 Sep 2004 19:54:16 +0900 Subject: Okinawa Computational Neuroscience Course -- Final Call for Applications In-Reply-To: <6758E810-DBFA-11D8-8D2A-000A95C0CA8A@irp.oist.jp> References: <6758E810-DBFA-11D8-8D2A-000A95C0CA8A@irp.oist.jp> Message-ID: <999C8EAE-FD97-11D8-9A96-000D93C06A16@irp.oist.jp> Dear Connectionists, Many people asked us about the attendance fee of Okinawa Computational Neuroscience Course. Fortunately, there will be no attendance fee; the sponsor will provide the airfare to Okinawa and local expenses for accepted students. Please find below the updated list of speakers. Application deadline is September 10th. Best wishes, Kenji Doya ************************************************************************ Call for Applications OKINAWA COMPUTATIONAL NEUROSCIENCE COURSE Bayesian Brain: Probabilistic Approaches to Neural Coding and Learning November 9-19, 2004. Okinawa, Japan. http://www.irp.oist.jp/ocnc Application deadline: September 10th, 2004 The aim of Okinawa Computational Neuroscience Course is to provide opportunities for young researchers with theoretical backgrounds to learn up-to-date neurobiological findings, and those with experimental backgrounds to have hands-on experience in computational modeling. We invite graduate students and postgraduate researchers to participate in the course, to be held from November 9th through 19th at Bankoku Shinryokan, a seaside conference facility that hosted 2000 Okinawa Summit. The sponsor will provide lodging at the adjacent beach resort, The Busena Terrace, and support for travel to Okinawa. The special topic for this year's course is "Bayesian Brain: Probabilistic approaches to neural coding and learning." Lectures by leading theoretical and experimental neuroscientists will be given in the morning and evening, and the afternoon will be open for free discussions and student projects. Each student will give a short presentation of his/her current work at the beginning of the course and present the summary of his/her project work at the end of the course. Those interested in attending the course should send the materials below by the course web page, e-mail, or postal mail to the course secretariat by SEPTEMBER 10TH. We will accept 30 students by considering the matching of each student's background and motivation to the course content, and also by considering the balance of members' research disciplines, geographic origins, and genders. This course is the second of the tutorial courses sponsored by the Cabinet Office of the Japanese government as a precursory activity for Okinawa Institute of Science and Technology. We hope that this course will be a good opportunity for theoretical and experimental neuroscientists to meet together and to explore the attractive nature and culture of Okinawa, the southernmost island prefecture of Japan. ******** Okinawa Computational Neuroscience Course (OCNC 2004) Bayesian Brain: Probabilistic Approaches to Neural Coding and Learning Date: November 9th to 19th, 2004 Place: Bankoku Shinryo-kan (http://www.shinryokan.com) Lodging: The Busena Terrace (http://www.terrace.co.jp) Sponsor: Okinawa Institute of Science and Technology Project, Cabinet Office, Japan Co-sponsors: Japanese Neural Network Society Center of Excellence Program, Tamagawa University Center of Excellence Program, Kyushu Institute of Technology Advisory Board: Sydney Brenner, Salk Institute Masao Ito, RIKEN Brain Science Institute Terrence Sejnowski, Salk Institute Susumu Tonegawa, MIT Torsten Wiesel, Rockfeller University Co-organizers: Kenji Doya, Initial Research Project, OIST Shin Ishii, Nara Institute of Science and Technology Alexandre Pouget, University of Rochester Rajesh Rao, University of Washington CONFIRMED LECTURES (titles with * are tentative) Theoretical Foundations Kevin Murphy (MIT): Bayesian inference and learning* Shun-ichi Amari (RIKEN BSI): Statistical approach to neural learning and population coding Neurobiological Foundations Adrienne Fairhall (Washington U.): Spike coding Alexandre Pouget (U. of Rochester): Population coding Barry Richmond (NIH): Neural coding* Computational Modeling Anthony Bell (Redwood Neurosci. Inst.): Unsupervised machine learning with spike timings Peter Latham (Gatsby Comp. Neuro. Unit): Computing with population codes Wolfgang Maass (T. U. Graz): Liquid state machine* Bruno Olshausen (U. C. Davis): Representing what and where in time-varying images Rajesh Rao (U. of Washington): Bayesian computation in cortical networks* Emanuel Todorov (U. C. San Diego): Optimality principles in sensorimotor control Richard Zemel (U. of Toronto): Coding and decoding uncertainty Experimental Approaches Karl Friston (UCL): Dynamic causal modeling David Knill (U. of Rochester): Bayesian models of sensory cue integration Konrad Koerding (UCL): Bayesian combination of priors and perception Tai-Sing Lee (Carnegie Mellon U.): Hierarchical Bayesian inference in visual cortex Jonathan Pillow (New York U.): Estimationg neuron models from spike trains* Michael Shadlen (U. of Washington): Decision making* APPLICATION Please send the following through the web application page (http://www.irp.oist.jp/ocnc/), e-mail (ocnc at irp.oist.jp), or postal mail to the secretariat below. 1) Name, 2) Date of birth, 3) Gender, 4) Nationality, 5) Affiliation, 6) Postal address, 7) Phone, 8) Fax, 9) E-mail, 10) Web page URL (if any), 11) Educational background, 12) Work experience, 13) List of publications, 14) Research interests (up to 500 words), 15) Motivations for attending the course (up to 500 words), 16) Two letters of recommendation. The items 11) to 14) can be replaced by a CV. Letters of recommendation should be sent directly to the secretariat from the referee by e-mail or postal mail. Please note the names, affiliations, and e-mail addresses of the referees in the application. There will be no attendance fee. The sponsor will provide lodging, meals, and travel support for accepted students. SECRETARIAT Okinawa Computational Neuroscience Course c/o Initial Research Project Okinawa Institute of Science and Technology 12-22 Suzaki, Gushikawa Okinawa 904-2234, Japan Phone: +81-98-921-3795 Fax: +81-98-934-1401 E-mail: ocnc at irp.oist.jp For more information, please visit the web page: http://www.irp.oist.jp/ocnc ************************************************************************ ---- Kenji Doya Initial Research Project, Okinawa Institute of Science and Technology 12-22 Suzaki, Gushikawa, Okinawa 904-2234, Japan Phone:+81-98-921-3843; Fax:+81-98-921-3873 http://www.irp.oist.jp/ From W.Wiegerinck at science.ru.nl Fri Sep 3 08:09:58 2004 From: W.Wiegerinck at science.ru.nl (Wim Wiegerinck) Date: Fri, 03 Sep 2004 14:09:58 +0200 Subject: phd and postdoc postion at SNN Nijmegen Message-ID: <41385F16.7060009@science.ru.nl> PhD student and postdoc position available at SNN Nijmegen. SNN Nijmegen is a research group dedicated to fundamental research in the areas of machine learning and computational neuroscience. Specific topics are Bayesian networks, approximate inference methods, time-series modeling, bio-informatics, expert systems, stochastic control and collaborative decision making. The group consists currently of 8 researchers and three programmers. In our group, we have two positions available that can be filled at either the PhD student level or at the postdoc level. See the job anouncements at http://www.mbfys.kun.nl/snn/nijmegen/index.php3?page=29 The requirement for the PhD student position is a completed university degree in physics, mathematics or computer science. The position is full-time for a period of 4 years. The requirement for the postdoc position is a PhD and publications on one of the above research topics. The postdoc position is full-time for a period of 2.5 years. For more information see www.snn.kun.nl/nijmegen or contact dr. H.J. Kappen (bert at snn.kun.nl, +31(0)24 3614241), or dr. W. Wiegerinck (wimw at snn.kun.nl). Applications should contain a complete CV, a brief description of his or her research interests and a copy of a recent publication or dissertation (optional). Send your application before October 1 2004 either by email to dr. H.J. Kappen (bert at snn.kun.nl) and dr. W. Wiegerinck (wimw at snn.kun.nl) or by ordinary mail to SNN, Radboud University Nijmegen, Geert Grooteplein 21, 6525 EZ Nijmegen, the Netherlands. From r.w.clowes at sussex.ac.uk Sun Sep 5 13:22:53 2004 From: r.w.clowes at sussex.ac.uk (Robert Clowes) Date: Sun, 5 Sep 2004 18:22:53 +0100 Subject: CFP : Next Generation approaches to Machine Consciousness: Imagination, Development, Intersubjectivity, and Embodiment. Message-ID: Next Generation approaches to Machine Consciousness: Imagination, Development, Intersubjectivity, and Embodiment. University of Hertfordshire, Hatfield, UK, 12th - 13th April, 2005 *** Submission Deadline: 31st October 2004 *** 1st Call for Papers for: Submissions are invited for presentation at a two-day symposium as part of the AISB 2005 Convention on Social Intelligence and Interaction in Animals, Robots and Agents (12-15 April, University of Hertfordshire, de Havilland Campus, Hatfield, England). ** Scope ** Machine Consciousness (MC) concerns itself with the study and creation of artefacts which have mental characteristics typically associated with consciousness such as (self-) awareness, emotion, affect, phenomenal states, imagination, etc. Recently, developments in AI and robotics, especially through the prisms of behavioural and epigenetic robotics, have stressed the embodied, interactive and developmental nature of intelligent agents which are now regarded by many as essential to engineering human-level intelligence. Some recent work has suggested that giving robots imaginative or simulation capabilities might be a big step towards achieving MC. Other studies have emphasized 'second person' issues such as intersubjectivity and empathy as a substrate for human consciousness. Alongside this, the infant-caregiver relationship has been recognised as essential to the development of consciousness in its specifically human form. Until now, most have considered these issues as, at best, tangential to the creation of artificial consciousness. This symposium proposes to bring them into greater focus and explore the contribution such work might make to next generation approaches to MC. Submissions are especially invited on the following topics in their relation to MC: * Imagination * Development * Enactive Approaches * Heterophenomenology * Synthetic Phenomenology * Intersubjectivity * Ethics * General aspects (techniques, theories, constraints) See http://www.sussex.ac.uk/cogs/mc-background for more information. Preference will be given to submissions that are: * Relevant: closely related to the themes of the symposium * Implemented: based on working robotic or other implemented systems * Novel: not previously presented elsewhere However, it is not expected that all accepted submissions will meet all three criteria of preference. ** Symposium Dates ** Symposium will be held on the 12 and 13th April 2005 as part of the AISB,05 Convention. ** 1 September 2004: First CFP distributed. ** 31 October 2004: Submissions due by this date. ** 22 November 2004: Notification of accepted papers will be sent out. ** 17 December 2004: camera ready copies due (for inclusion in AISB proceedings) ** 14 January 2005: early registration deadline (NB symposium attendees must register for the full convention) ** 12-15 April 2005: AISB 2005 convention ** Publication ** The Chairs intend to publish the proceedings of the Symposium in a book or journal special issue. ** Symposium Co-Chairs ** Ron Chrisley - Centre for Cognitive Science (COGS), University of Sussex Rob Clowes - Centre for Cognitive Science (COGS), University of Sussex ** Scientific Committee ** Igor Aleksander - Imperial College, UK and COGS Sussex Giovanna Colombetti - York University, Canada Owen Holland - University of Essex, UK Takashi Ikegami - University of Tokyo, Japan Murray Shanahan - Imperial College, UK Steve Torrance - Department of Psychology, University of Middlesex, UK and COGS Sussex Tom Ziemke - School of Humanities and Informatics, University of Sk=F6vde, Sweden ** Submissions ** Extended abstracts of not more than 500 words (plus references) should be submitted in plain text to : Rob Clowes Centre for Research in Cognitive Science. University of Sussex Falmer BN1 9QH United Kingdom +44 (0)1273 638317 Email : robertc at cogs.susx.ac.uk (please note '@' should be inserted for ' at '. This is as an attempt to avoid spam). Organised in association with the AISB (The Society for the Study of Artificial Intelligence and the Simulation of Behaviour) From dsmith06 at maine.rr.com Wed Sep 8 08:01:32 2004 From: dsmith06 at maine.rr.com (David Smith) Date: Wed, 8 Sep 2004 08:01:32 -0400 (EDT) Subject: Book Announcement - Why We Lie: The Evolutionary Roots of Deception and the Unconscious Mind Message-ID: <008601c4959b$9570e590$0200a8c0@dad> Why We Lie: The Evolutionary Roots of Deception and the Unconscious Mind David Livingstone Smith St. Martin's Press 256 pages Size: 5-1/2 x 8-1/4 $24.95 Hardcover Pub Date: 07/2004 ISBN: 0-312-31039-0 Deceit, lying, and falsehoods lie at the very heart of our cultural heritage. Even the founding myth of the Judeo-Christian tradition, the story of Adam and Eve, revolves around a lie. We have been talking, writing and singing about deception ever since Eve told God, "The serpent deceived me, and I ate." Our seemingly insatiable appetite for stories of deception spans the extremes of culture from King Lear to Little Red Riding Hood, retaining a grip on our imaginations despite endless repetition. These tales of deception are so enthralling because they speak to something fundamental in the human condition. The ever-present possibility of deceit is a crucial dimension of all human relationships, even the most central: our relationships with our very own selves. David Livingstone Smith elucidates the essential role that deception and self-deception have played in human--and non-human--evolution and shows that the very structure of our minds has been shaped from our earliest beginnings by the need to deceive. Smith shows us that by examining the stories we tell, the falsehoods we weave, and the unconscious signals we send out, we can learn much about ourselves and how our minds work. "Smith combines philosophy, psychology and biology to argue for the importance of deception to our identity as human beings." -- Scientists' Bookshelf Monthly "Intriguing" - Psychology Today "Smith presents a lively survey of the many forms of deception practiced by plants, insects, and animals. He then turns to Homo sapiens and offers cogent and provocative analysis of the link between increasingly complex societies, the evolution of the brain, and the need for 'social lies' in the interest of civility...With an 'aha!' moment on every page, Smith's inquiry is stimulating and unsettling" -- Booklist "Smith draws on Darwin's theory of natural selection, kin altruism, and the basics of sociobiology....Presenting an intriguing theory with skill and imagination" -- Library Journal "David Livingstone Smith unearths the roots of self-deception." - Seed "A leap beyond mainstream science proposes how the unconscious mind could drive our everyday mastery of the art of deceit, both of others and ourselves. . . . Deliciously tantalizing, with morality as the Grandest Deceit of them all." --Kirkus Reviews "Self-deception is one of the most powerful ideas in psychology, indeed, in human affairs, and David Smith's Why We Lie is an excellent synthesis of this crucial topic. The biology is up-to-date and accurate, the psychological implications are clearly worked out, and the writing is inviting and accessible." --Steven Pinker author of The Blank Slate and The Language Instinct "David Smith has thoroughly documented and analyzed the ubiquitous human characteristics of deception and self-deception, drawing from the fields of evolutionary biology, ethology, social psychology and cognitive science and bringing the Freudian concept of the unconscious into the behavioral science of the 21st century. This is an engaging, erudite and powerful book, comprehensible to the layperson as well as the academic, and requisite reading for anyone with a serious interest in human nature." -- Irwin Silverman, Ph.D., Emeritus Professor of Psychology and Senior Scholar, York University, Toronto, Canada "David Smith has pulled off a beaut. Freud, Darwin, Machiavelli (and, oh yes, Liz Smith) meet around the poker table of life. Why We Lie is a wonderfully blended cluster of arguments to support the painful truth that we are a species whose skills at deceiving others is matched only by our ability to deceive ourselves." --Arthur S. Reber, author of The Penguin Dictionary of Psychology "Why We Lie is written with snap, panache, and the sort of insights that stop you in your tracks. Its subject--deception, trickery, pulling a fast one, conning other humans and conning ourselves--is critical to understanding the evolution of the human mind. Getting a handle on deception is crucial to understanding the self with which you and I live from second to second every minute of our conscious and our dreaming lives." --Howard Bloom, author of Global Brain and The Lucifer Principle connectionists at cs.cmu.edu From y.demiris at imperial.ac.uk Thu Sep 9 05:33:45 2004 From: y.demiris at imperial.ac.uk (Yiannis Demiris) Date: Thu, 9 Sep 2004 10:33:45 +0100 Subject: CFP: Imitation in Animals and Artifacts Message-ID: Dear all, details about the third interdisciplinary symposium on imitation in animals and artifacts that will take place in Hatfield UK in April 2005 can be found at the symposium's URL: http://www.iis.ee.ic.ac.uk/yiannis/imitation2005.html Contributions describing connectionist models of the mechanisms underlying imitation skills, and learning by observation are welcome. The deadline for submissions of papers is the 31st of October 2004. Best wishes, Yiannis --- Dr. Yiannis Demiris Lecturer, Intelligent Systems and Networks Group Department of Electrical and Electronic Engineering, Imperial College London, SW7 2BT, London, UK Tel: +44 (0) 2075946300, Fax: +44 (0) 2075946274 http://www.iis.ee.ic.ac.uk/yiannis From whorstma at uni-bielefeld.de Thu Sep 9 09:27:31 2004 From: whorstma at uni-bielefeld.de (whorstma@uni-bielefeld.de) Date: Thu, 09 Sep 2004 15:27:31 +0200 Subject: "Brains, Minds and Media" -- open access eJournal -- call for participation Message-ID: <3f009e3ef192.3ef1923f009e@uni-bielefeld.de> =========================CALL FOR PARTNERS & SUBMISSIONS ========================="Brains, Minds & Media" eJournal of New Media in Neural and Cognitive Science Education ========================= It is the main aim of this novel open-access eJournal to provide peer-reviewed articles and interactive/visual media for education in the neural and cognitive sciences ranging from the advanced school level to all areas of higher education. We seek to ... ... assure citability, content quality and accessibility of your materials through peer-reviewed publication ... adequately represent knowledge beyond papers and textbooks with visualizations and interactive media ... promote an intelligible and serious understanding of neural and cognitive concepts We encourage combined submission of a mandatory short paper and (optional) elaborated, high-quality media (visualizations, simulations, tutorials and the like), which may be browser-ready, but can also be proprietary. Papers on the use and effect of new media in the neural and cognitive sciences and reviews are also welcome. The E-Journal will be open-access, internationally peer-reviewed and initially free of page charge thanks to funding program "Digital Peer Publishing" of the state government NRW, Germany. Sustainable and maintained infrastructure (hard- and software) and permanent administrative manpower is provided through library services (see 'Partners'). The in-house work is fostered by several researchers at Bielefeld University with experience international editorial boards from the fields of Neurobiology, Biological Cybernetics, Biorobotics and Neuroinformatics. We are now to build the international group of supporters and co-workers and prepare an initial issue. We call for your participation! *****CALL***** Please express your interest with an informal eMail (see ?contact?) if you can contribute as ... * AUTHOR if you have visualizations, simulations and the like, which are well-tried in your scientific talks or lessons and can submit a short paper on background and application. (No processing charge for early submissions, guidelines available) * EDITOR / REVIEWER if you have a clear view on a specific section of the neural and/or cognitive sciences, a dedication for visualizations and simulation and can help to process submissions in reviewing. (Professional workflow software for the editorial is already set up.) * ADVISOR / ADVOCAT if you are experienced member in the scientific community and wish to escort the initiative in strategic development as member of the advisory board or as external consultant. * RECIPIENT if you simply want to be kept informed about the initiative (e.g. Newsletter). CONTACT: The procedure is intentionally informal in the initial phase. Please feel free to send a noncommittal and private eMail to the organizational team with the area(s) of interest indicated. For arranging possible next steps, we will come to you with further information. Corresponding eMail: wolfram.horstmann at uni-bielefeld.de Thank you! Your organizational team, Wolfram Horstmann and Soeren Lorenz FURTHER PARTNERS * Bielefeld University Library * University Library Centre "HBZ" of State Government NRW, Germany * Initiative "Digital Peer Publishing" State Government NRW, Germany (funding) From kdharris at andromeda.rutgers.edu Wed Sep 8 18:11:24 2004 From: kdharris at andromeda.rutgers.edu (Ken Harris) Date: Wed, 8 Sep 2004 18:11:24 -0400 Subject: Assistant Professorship in Neuroscience at Rutgers Newark Message-ID: <000401c495f0$c7835860$7db5e6a5@rutgers.edu> The Center for Molecular and Behavioral Neuroscience at Rutgers-Newark has announced an opening for an Assistant Professor, tenure-track faculty position in Behavioral/Cognitive Neuroscience. The Center is primarily dedicated to research and graduate training. We seek a mature candidate with a clear research agenda focused on fundamental questions that link brain and behavior. The candidate should be ready to run an independent laboratory, train graduate students and postdoctoral fellows, and attract substantial independent external funding. Further details on our facilities, faculty, and training programs can be found at http://www.cmbn.rutgers.edu. Local resources include state-of-the art animal labs, human testing facilities, computer facilities and a 3T Siemens Allegra fMRI (see http://www.rutgers-newark.rutgers.edu/fmri/). There is excellent access to a wide variety of neuropsychological, neurological, and psychiatric patient populations of all ages through ongoing cooperative relationships with our medical school and other clinical facilities in nearby northern New Jersey and New York City. Close connections with the CNS research divisions of the extensive New Jersey pharmaceutical industry provides additional opportunities for collaboration and support. Our campus is located in Northern New Jersey, in downtown Newark, just 13 miles -- and 20 minutes -- from midtown Manhattan. Extensive commuter rail lines make is feasible to live either in New York City or in the suburbs or rural areas of New Jersey. Five minutes from the downtown Newark train station, the campus is part of the five-university University Heights section of town with over 10,000 undergraduate and graduate students. Further information at http://www.newark.rutgers.edu/. The Integrative Neuroscience Ph.D. Program is a multidisciplinary program whose strengths range from molecular neurobiology through cognitive neuroscience. Emphasizing the integrative understanding of the links between brain and behavior, the program includes faculty from both Rutgers University - Newark and our medical school, the University of Medicine and Dentistry of New Jersey (UMDNJ). For more information, see http://www.ins.rutgers.edu. To apply, send CV, three letters of references and statement of research goals to: Dr. Paula Tallal, Co-Director, Center for Molecular & Behavioral Neuroscience, Rutgers University - Newark. 197 University Avenue, Newark, New Jersey 07102. For additional information, feel free to contact Dr. Tallal at tallal at axon.rutgers.edu. ------------------------ Kenneth D. Harris, Ph.D. Assistant Professor Center for Molecular and Behavioral Neuroscience Rutgers, The State University of New Jersey 197 University Avenue Newark NJ 07102, USA phone: 973 353 1080, x3331 fax: 973 353 1272 email: kdharris at andromeda.rutgers.edu web: http://qneuro.rutgers.edu From juergen at idsia.ch Fri Sep 10 05:09:25 2004 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Fri, 10 Sep 2004 11:09:25 +0200 Subject: Jobs for postdocs & PhD students at IDSIA (Switzerland) & TU Munich (Germany) Message-ID: <41416F45.6020304@idsia.ch> We are seeking outstanding postdocs and PhD students for research on learning robots. Details: http://www.idsia.ch/~juergen/jobstrep2004.html http://www.idsia.ch/~juergen/bat2004.html (Interviews possible at ANNIE 2004, Nov 7-10, St Louis) Juergen Schmidhuber http://www.idsia.ch/~juergen/ From nnrev at atr.co.jp Fri Sep 10 04:22:44 2004 From: nnrev at atr.co.jp (Neural Networks Editorial Office) Date: Fri, 10 Sep 2004 17:22:44 +0900 Subject: Neural Networks 17(7) Message-ID: NEURAL NETWORKS 17(7) Contents - Volume 17, Number 7- 2004 ------------------------------------------------------------------ ***** Psychology and Cognitive Science ***** Oscillatory model of attention-guided object selection and novelty detection Roman M. Borisyuk, Yakov B. Kazanovich ***** Neuroscience and Neuropsychology ***** Impact of deviation from precise balance of spike-timing-dependent plasticity Narihisa Matsumoto, Masato Okada ***** Mathematical and Computational Analysis ***** Learning to generate combinatorial action sequences utilizing the initial sensitivity of deterministic dynamical systems Ryu Nishimoto, Jun Tani Reliability of internal prediction/estimation and its application. I. Adaptive action selection reflecting reliability of value function Yutaka Sakaguchi, Mitsuo Takano Binocular disparity encoding cells generated through an Infomax based learning algorithm Kenji Okajima Analysis of perfect mappings of the stimuli through neural temporal sequences Francisco B. Rodri'guez, Ramo'n Huerta, Modeling of growing networks with directional attachment and communities Masahiro Kimura, Kazumi Saito1, Naonori Ueda When is approximation by Gaussian networks necessarily a linear process? H.N. Mhaskar A recurrent neural network with exponential convergence for solving convex quadratic program and related linear piecewise equations Youshen Xia, Gang Feng, Jun Wang Boundedness and stability for nonautonomous cellular neural networks with delay Mehbuba Rehim, Haijun Jiang, Zhidong Teng An analysis of exponential stability of delayed neural networks with time varying delays Sabri Arik CURRENT EVENTS ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 (regular) SEK 660 Y 13,000 Neural Networks (plus Y 2,000 enrollment fee) $20 (student) SEK 460 Y 11,000 (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- membership without $30 SEK 200 not available to Neural Networks non-students (subscribe through another society) Y 5,000 student (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- Name: _____________________________________ Title: _____________________________________ Address: _____________________________________ _____________________________________ _____________________________________ Phone: _____________________________________ Fax: _____________________________________ Email: _____________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number ____________________________ expiration date ________________________ INNS Membership International Neural Network Society 7600 Terrace Avenue, Ste. 203 Middleton WI 53562 608-831-0584, ext. 138 (phone) 608-831-5122 (fax) srees at reesgroupinc.com ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership c/o Professor Shozo Yasui Kyushu Institute of Technology Graduate School of Life Science and Engineering 2-4 Hibikino, Wakamatsu-ku Kitakyushu 808-0196 Japan 81 93 695 6108 (phone and fax) jnns at brain.kyutech.ac.jp http://www.jnns.org/ ---------------------------------------------------------------------------- From r.kempter at biologie.hu-berlin.de Fri Sep 10 06:32:39 2004 From: r.kempter at biologie.hu-berlin.de (Richard Kempter) Date: Fri, 10 Sep 2004 12:32:39 +0200 Subject: Berlin Autumn School LEARNING AND MEMORY, Oct 11-13, 2004 Message-ID: <20040910103239.GA18603@pauling.biologie.hu-berlin.de> Announcement, program, and call for participation: Berlin Autumn School LEARNING AND MEMORY: MOLECULAR MECHANISMS - CELLULAR PROCESSES - MATHEMATICAL MODELS October 11-13, 2004 Berlin, Germany Learning and memory are central ingredients for proper biological function in changing environments. Both processes are of particular importance for neuroscience but they also play a significant role in other biological disciplines. This autumn school focuses on the basic molecular and cellular processes underlying learning and memory in neural systems, with emphasis on synaptic plasticity. Experimental approaches will be discussed in close relation with the corresponding mathematical models, both at an introductory level. The last day of the school will bridge between the physiological and behavioral level and also touch on learning and memory in the immune system. PROGRAM Monday, October 11: 8:30 - 9:00 Arrival 9.00 - 9:15 Opening of the Autumn School 9.15 - 10.45 Dietmar Schmitz (NWFZ, Charite) Cellular processes of learning and memory: Development & current state of concepts and experiments (I) 11.15 - 12.45 Andreas Herz (ITB, HU Berlin) Modelling short-term synaptic plasticity with differential equations and iterated maps (I) 15.15 - 16.45 Dietmar Kuhl (Neurobiology, FU Berlin) Molecular and cellular mechanisms of learning and memory (I) 17.15 - 18.45 Hanspeter Herzel (ITB, Charite) Modelling molecular signal transduction chains and networks 19.00 - Reception and Dinner Tuesday, October 12: 9.15 - 10.45 Dietmar Schmitz (NWFZ, Charite) Cellular processes of learning and memory: Development & current state of concepts and experiments (II) 11.15 - 12.45 Andreas Herz (ITB, HU Berlin) Modelling short-term synaptic plasticity with differential equations and iterated maps (II) 15.15 - 16.45 Dietmar Kuhl (Neurobiology, FU Berlin) Molecular and cellular mechanisms of learning and memory (II) 17.15 - 18.45 Laurenz Wiskott (ITB, HU Berlin) Modelling learning and memory: The systems level Wednesday, October 13: 9.15 - 10.15 Dietmar Schmitz (NWFZ, Charite) Short- and long-term plasticity of the mossy fiber synapse 10.15 - 11.15 Richard Kempter (ITB, HU Berlin) Hippocampal plasticity: Learning behavioral sequences 11.45 - 12.45 Andreas Radbruch (DRFZ, Berlin) Learning and memory in the immune system 15.15 - 16.15 Gerd Kempermann (Max Delbrueck Center, Berlin) Adult neurogenesis 16.15 - 17.15 Livia de Hoz (Neurophysiology, Charite) Memory consolidation 17.45 - 19.15 Andreas Herz (ITB, HU Berlin) The Hebbian memory trace: New insight from bee olfaction LOCATION: Lecture Hall 12, Department of Biology, Humboldt-Universitaet zu Berlin, Invalidenstrasse 43, 10115 Berlin-Mitte. REGISTRATION: E-mail to Richard Kempter before October 4: r.kempter at biologie.hu-berlin.de The registration fee of 30 Euro (students 15 Euro) is to be paid upon arrival and includes the buffet on Monday (Oct 11) evening. For details, please visit: http://itb.biologie.hu-berlin.de/events/memory.html PDF poster of this announcement: http://itb.biologie.hu-berlin.de/~kempter/berlin_autumn_school/learning_and_memory_2004.pdf -- The autumn school on "Learning and Memory" is organized by the DFG Collaborative Research Center ("Sonderforschungsbereich", SFB 618) "Theoretical Biology: Robustness, Modularity, and Evolutionary Design of Living Systems" Humboldt-Universitaet zu Berlin Department of Biology Invalidenstrasse 43 10115 Berlin, Germany http://www.biologie.hu-berlin.de/forschung/SFB_618/ From zoubin at gatsby.ucl.ac.uk Sat Sep 11 11:04:47 2004 From: zoubin at gatsby.ucl.ac.uk (Zoubin Ghahramani) Date: Sat, 11 Sep 2004 16:04:47 +0100 Subject: AISTATS 2005 Submission Deadline Extended (Sep 28) Message-ID: <16707.5135.885494.592287@wald.gatsby.ucl.ac.uk> ---------------------------------------------------------------------- Call for Papers Submission Deadline Extended: Sep 28th AISTATS 2005 Tenth International Workshop on Artificial Intelligence and Statistics January 6-8, 2005, The Savannah Hotel, Barbados http://www.gatsby.ucl.ac.uk/aistats/ Submission Deadline: September 28, 2004 ---------------------------------------------------------------------- This is the tenth workshop on Artificial Intelligence and Statistics, an interdisciplinary gathering of researchers at the intersection of computer science, statistics, and related areas. Since its inception in 1985, the primary goal of this workshop has been to broaden research in both of these fields by promoting the exchange of ideas between them. We encourage the submission of all papers which are in keeping with this objective. Presentations will include invited talks, contributed talks, and posters. Papers for poster sessions will be treated equally with papers for presentation in the publication. Submission Requirements: ------------------------- Electronic submission of papers is required. The papers (up to 8 pages in length) should be submitted through the AI and Statistics Conference Management page. See: http://www.gatsby.ucl.ac.uk/aistats/submit.htm Submissions will be considered if they are received by 11:59 PM September 28, 2004, Pacific Daylight Time. Acceptance notices will be emailed by November 3, 2004. Final papers (up to 8 pages, double column) must be received by November 24, 2004. These papers will be made available on the web, published in the proceedings, and distributed at the workshop in electronic form. Invited Speakers ---------------- Craig Boutelier (University of Toronto) Nir Friedman (Hebrew University) Tommi Jaakkola (MIT) Steffen Lauritzen (University of Oxford) Tom Minka (Microsoft Research) Program Chairs: ---------------- Robert Cowell, Actuarial Science and Statistics, City University, London Zoubin Ghahramani, Gatsby Unit, University College London From special at math.unipd.it Mon Sep 13 09:50:38 2004 From: special at math.unipd.it (Login per Congresso Alessandro Sperduti) Date: Mon, 13 Sep 2004 15:50:38 +0200 (CEST) Subject: reminder: call for papers Message-ID: ************************* R E M I N D E R ************************** C A L L F O R P A P E R S Special Issue of Neural Networks on Neural Networks and Kernel Methods for Structured Domains Co-editors:Barbara Hammer, Craig Saunders, Alessandro Sperduti (http://www.informatik.uni-osnabrueck.de/barbara/specialNN/) >>>>> Deadline for submission October 11, 2004 <<<<< ---------------------------------------------------------------------- In recent years several researchers have started to consider the adaptive processing of structured data. This interest is motivated by two main reasons: i) several very important computational problems in Bioinformatics, Chemistry, document classification and filtering (just to name a few), require the use of some Machine Learning procedure to be properly treated because their complexity does not allow a formal and precise definition of the problem and thus no algorithmic solution to the problem is known; on the other hand experimental data is available and usable by a Machine Learning approach; ii) in many of the above problems, the objects of interest are more naturally represented via varying-size structured representations, such as sequences, strings, trees, directed or undirected graphs. Moreover, it is commonly believed that any computational process representing these objects via flat fixed-size vectorial representations, risks to discard structural information relevant for solving the task at hand. The aim of the special issue is to bring together recent works developed mainly into the fields of Recurrent and Recursive Neural Networks, and Kernel Methods, with the hope to function as a conceptual support for the improvement of current technologies and the growth of new integrated methodologies for learning in structured domains. TOPICS: Recurrent and Recursive Neural Networks, Self-Organizing Maps for Structures, Support Vector Machines and Kernel Methods for Structured Domains, Fisher Kernels, Probabilistic Models for Structured Domains, Applications of the above methods to Structured Domains, other relevant topics. ---------------------------------------------------------------------- I M P O R T A N T D A T E S Deadline for submission October 11, 2004 Notification of acceptance: March 14, 2005 Deadline for final paper: June 6, 2005 ---------------------------------------------------------------------- P A P E R S U B M I S S I O N Format: http://www.informatik.uni-osnabrueck.de/barbara/specialNN/ Papers must be submitted in electronic form (either Postscript or PDF) to the following e-mail address: specialNN.structure at math.unipd.it Hard-paper submissions are accepted only if the authors do not have access to electronic facilities, and should be mailed to the following address: Prof. Alessandro Sperduti Dipartimento di Matematica Pura ed Applicata Via Belzoni 7 35131 Padova ITALY ---------------------------------------------------------------------- From DGB at CDRH.FDA.GOV Sat Sep 11 10:31:28 2004 From: DGB at CDRH.FDA.GOV (Brown, David G.) Date: Sat, 11 Sep 2004 10:31:28 -0400 Subject: Call for Special Session Proposals - IJCNN'05 Message-ID: <60E5EBF1DFB4EC498E0ACAE75A49F8ED0C4509E7@DRM558.CDRH.FDA.GOV> Call for Special Session Proposals International Joint INNS-IEEE Conference on Neural Networks (IJCNN) 2005 Hilton Bonaventure Hotel Montreal, Quebec, Canada July 31- August 4, 2005 (IJCNN 2005) The IJCNN 2005 Organizing Committee invites proposals for special sessions to be held during the conference (http://faculty.uwb.edu/ijcnn05 ), taking place July 31- August 4, 2005, in Montreal. Each special session proposal should be well motivated and should consist of 4 to 6 papers. Each paper must have the title, authors with e-mails/web sites, and as detailed an abstract as possible. The special session organizer(s) contact information should also be included. All special session organizers must obtain firm commitments from their special session presenters and authors to submit papers or extended abstracts in a timely fashion (if the special session is accepted) and, of course, present them at the IJCNN 2005. Each special session organizer will be responsible for the quality of the special session papers and manage the review process accordingly. All accepted papers will be published in the IJCNN 2005 Proceedings. Authors who planned papers for special sessions which were not accepted can submit their papers as regular submissions (the deadline is January 31, 2005). Proposals should be submitted in ELECTRONIC FORM to: Fredric Ham, Program Co-Chair Florida Institute of Technology College of Engineering 150 West University Boulevard Melbourne, Florida 32901-6975, U.S.A. phone +1 (321) 674-7124 E-mail: fmh AT fit.edu Important Deadlines November 1, 2004 Special session proposal deadline December 1, 2004 Acceptance notification January 31, 2005 Extended abstracts/full papers due to be submitted through the regular submission site (marked for appropriate special sessions) IMPORTANT! Submissions of full papers for each special session is highly encouraged, but at the minimum extended abstracts (2 to 3 pages in the conference paper format) are required for each presentation at the special session. David David G. Brown, Ph.D. Publicity Chair, IJCNN'05 Center for Devices and Radiological Health (HFZ-140) 12720 Twinbrook Parkway Rockville, MD 20852 301-443-3314 ext. 133 301-443-9101 (fax) david.brown at fda.hhs.gov From d.mareschal at bbk.ac.uk Mon Sep 13 06:01:30 2004 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Mon, 13 Sep 2004 11:01:30 +0100 Subject: Senior Job Opportunity in London Message-ID: Readers of this list may be interested in the following senior job opportunity. PLEASE DO NOT RESPOND TO ME DIRECTLY cheers, Denis ======================================== Faculty of Science Head of School: Reader/Professor in Psychology The School of Psychology (RAE 5) is seeking an exceptional individual to provide strategic leadership for an already successful School, with particular strengths in developmental and cognitive neuroscience, developmental and cognitive psychology, and psychosocial studies. The person appointed will have an established international research reputation, and have demonstrated effective managerial and leadership abilities in an academic or related environment. Tenure is permanent; the post of Head of School is a rotating one and the successful candidate will be expected to fill it for the first four years of their appointment. The post is tenable from 31 March 2005. Salary will be commensurate with qualifications and experience, and level of appointment. Closing date: 1 December 2004 For application forms and further details please see http://www.bbk.ac.uk or send an A4 sae (quoting Ref: APS109), to the Human Resources Team, Birkbeck, Malet Street, Bloomsbury, London, WC1E 7HX or e-mail humanresources at bbk.ac.uk Birkbeck is an Equal Opportunities Employer. -- ================================================= Dr. Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 (0)20 7631-6582/6226 reception: 6207 fax +44 (0)20 7631-6312 http://www.psyc.bbk.ac.uk/people/academic/mareschal_d/ ================================================= From j.v.stone at sheffield.ac.uk Mon Sep 13 07:31:51 2004 From: j.v.stone at sheffield.ac.uk (Jim Stone) Date: Mon, 13 Sep 2004 12:31:51 +0100 Subject: New book: Independent Component Analysis Message-ID: I would like to announce a new book, Independent Component Analysis: A Tutorial Introduction by James V Stone University of Sheffield. Published September 2004 by MIT Press. Price: (pounds) 22.95. For details, see http://www.shef.ac.uk/~pc1jvs/ Contents Part I Independent Component Analysis and Blind Source Separation Chapter 1 Overview of Independent Component Analysis 1.1: Introduction 1.2: Independent Component Analysis: What Is It? 1.3: How Independent Component Analysis Works 1.4: Independent Component Analysis and Perception 1.5: Principal Component Analysis and Factor Analysis 1.6: Independent Component Analysis: What Is It Good For? Chapter 2 Strategies for Blind Source Separation 2.1: Introduction 2.2: Mixing Signals 2.3: Unmixing Signals 2.4: The Number of Sources and Mixtures 2.5: Comparing Strategies 2.6: Summary Part II The Geometry of Mixtures Chapter 3 Mixing and Unmixing 3.1: Introduction 3.2: Signals, Variables, and Scalars 3.3: The Geometry of Signals 3.4: Summary Chapter 4 Unmixing Using the Inner Product 4.1: Introduction 4.2: Unmixing Coefficients as Weight Vectors 4.3: The Inner Product 4.4: Matrices as Geometric Transformations 4.5: The Mixing Matrix Transforms Source Signal Axes 4.6: Summary Chapter 5 Independence and Probability Density Functions 5.1: Introduction 5.2: Histograms 5.3: Histograms and Probability Density Functions 5.4: The Central Limit Theorem 5.5: Cumulative Density Functions 5.6: Moments: Mean, Variance, Skewness and Kurtosis 5.7: Independence and Correlation 5.8: Uncorrelated Pendulums 5.9: Summary Part III Methods for Blind Source Separation Chapter 6 Projection Pursuit 6.1: Introduction 6.2: Mixtures Are Gaussian 6.3: Gaussian Signals: Good News, Bad News 6.4: Kurtosis as a Measure of Non-Normality 6.5: Weight Vector Angle and Kurtosis 6.6: Using Kurtosis to Recover Multiple Source Signals 6.7: Projection Pursuit and ICA Extract the Same Signals 6.8: When to Stop Extracting Signals 6.9: Summary Chapter 7 Independent Component Analysis 7.1: Introduction 7.2: Independence of Joint and Marginal Distributions 7.3: Infomax: Independence and Entropy 7.4: Maximum Likelihood ICA 7.5: Maximum Likelihood and Infomax Equivalence 7.6: Extracting Source Signals Using Gradient Ascent 7.7: Temporal and Spatial ICA 7.8: Summary Chapter 8 Complexity Pursuit 8.1: Introduction 8.2: Predictability and Complexity 8.3: Measuring Complexity Using Signal Predictability 8.4: Extracting Signals by Maximizing Predictability 8.5: Summary Chapter 9 Gradient Ascent 9.1: Introduction 9.2: Gradient Ascent on a Line 9.3: Gradient Ascent on a Hill 9.4: Second Order Methods 9.5: The Natural Gradient 9.6: Global and Local Maxima 9.7: Summary Chapter 10 Principal Component Analysis and Factor Analysis 10.1: Introduction 10.2: ICA and PCA 10.3: Eigenvectors and Eigenvalues 10.4: PCA Applied to Speech Signal Mixtures 10.5: Factor Analysis 10.6: Summary PartIV Applications Chapter 11 Applications of ICA 11.1: Introduction 11.2: Temporal ICA of Voice Mixtures 11.3: Temporal ICA of Electroencephalograms158 11.4: Spatial ICA of fMRI Data 11.5: Spatial ICA for Color MRI Data 11.6: Complexity Pursuit for Fetal Heart Monitoring 11.7: Complexity Pursuit for Learning Stereo Disparity PartV Appendices Appendix A: A Vector Matrix Tutorial Appendix B: Projection Pursuit Gradient Ascent Appendix C: Projection Pursuit: Stepwise Separation of Sources Appendix D: ICA Gradient Ascent Appendix E: Complexity Pursuit Gradient Ascent Appendix F: Principal Component Analysis for Preprocessing Data Appendix G: Independent Component Analysis Resources Appendix H: Recommended Reading From terry at salk.edu Mon Sep 13 22:51:55 2004 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 13 Sep 2004 19:51:55 -0700 (PDT) Subject: NEURAL COMPUTATION 16:10 In-Reply-To: <200408131737.i7DHbKn81419@kepler.snl.salk.edu> Message-ID: <200409140251.i8E2ptP04124@kepler.snl.salk.edu> Neural Computation - Contents - Volume 16, Number 10 - October 1, 2004 LETTERS Understanding the Cortical Specialization for Horizontal Disparity Jenny C. A. Read and Bruce G. Cumming Different Predictions by the Minimum Variance and Minimum Torque-Change Models on the Skewness of Movement Velocity Profiles Hirokazu Tanaka, Meihua Tai, and Ning Qian Disambiguating Visual Motion Through Contextual Feedback Modulation Pierre Bayerl and Heiko Neumann Exact Solution for the Optimal Neuronal Layout Problem Dmitri B. Chklovskii Decoding a Temporal Population Code Philipp Knuesel, Reto Wyss, Peter Koenig and Paul F.M.J. Verschure Minimal Models of Adapted Neuronal Response to In Vivo-Like Input Currents Giancarlo La Camera, Alexander Rauch, Hans-R. Luescher, Walter Senn and Stefano Fusi Including Long-Range Dependence in Integrate-and-Fire Models of the High Interspike-Interval Variability of Cortical Neurons B. Scott Jackson Learning Eigenfunctions Links Spectral Clustering and Kernel PCA Yoshua Bengio, Olivier Delalleau, Nicolas Le Roux, Jean-Francois Paiement, Pascal Vincent and Marie Ouimet ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2004 - VOLUME 16 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $108 $54 $57.78 Individual $95 $101.65 $143 $85 $90.95 Institution $635 $679.45 $689 $572 $612.04 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From chiba at Cogsci.ucsd.edu Tue Sep 14 13:27:07 2004 From: chiba at Cogsci.ucsd.edu (Andrea Chiba) Date: Tue, 14 Sep 2004 10:27:07 -0700 (PDT) Subject: REGISTER NOW! ICDL 2004 Message-ID: THIRD INTERNATIONAL CONFERENCE ON DEVELOPMENT AND LEARNING (ICDL2004) The Salk Institute October 20-23, 2004 San Diego, California http://icdl.cc The ICDL conference brings together leading researchers in neuroscience, machine learning, robotics, and developmental psychology. The goal is to gain new insights about learning and development in biological and artificial systems that have to operate autonomously in the physical and social world. Below is a summary of talks and conference activities. For more information please visit the conference Web Site at http://icdl.cc Wednesday October 20 Tutorials. Pietro Perona: Invited Talk. Alex Pentland: Social Dynamics: The Voice of Power and Influence. Leslie J. Carver: Neural correlates of social referencing. Teresa Farroni, Mark H. Johnson, Gergely Csibra: The perception of direct gaze in human infants. Christof Teuscher, Jochen Triesch: To Care or Not to Care: Analyzing the Caregiver in a Computational Gaze Following Framework. Masato Ito and Jun Tani: Joint attention between a humanoid robot and users in imitation game. Katharina J. Rohlfing, Jannik Fritsch and Britta Wrede: Learning to manipulate objects: A quantitative evaluation of Motionese. Thursday October 21 Dana Ballard: Invited Talk. Frederic Dandurand, Melissa Bowen, Thomas R. Shultz: Learning by Imitation, Reinforcement and Verbal Rules in Problem Solving Tasks. Patricia Zukow-Goldring and Michael Arbib: Caregivers and the Education of the Mirror System James B. Marshall, Douglas Blank, Lisa Meeden: An Emergent Framework for Self-Motivation in Developmental Robotics. Andrew G. Barto, Satinder Singh, Nuttapong Chentanez: Intrinsically Motivated Learning of Hierarchical Collections of Skills. Hidefumi Funakoshi, Wako Yoshida, Shin Ishii: An imaging study on human action selection using hierarchical rules. E. P. Kasten and P. K. McKinley: MESO: Perceptual Memory to Support Online Learning in Adaptive Software. Kaplan, F. and Oudeyer, P-Y.: Neuromodulation and open-ended development. Jay McCLelland: Invited Talk. Rutvik Desai: A Model of Frame and Verb Compliance in Language Acquisition. Karl Pfleger: On-Line Cumulative Learning of Hierarchical Sparse n-grams. Chen Yu and Dana H. Ballard: A Unified Model of Early Word Learning: Integrating Statistical and Social Cues. Arturo E. Hernandez: On Language and Age of Acquisition. Peter Ford Dominey, Jean-David Boucher: Developmental Stages of Perception and Language Acquisition in a Physically Grounded Robot. Friday October 22 Eric Courchesne: Invited Talk. Matthew K Belmonte Simon Baron-Cohen: Small-world Network Properties and the Emergence of Social Cognition: Evidence from Functional Studies of Autism. B.Wicker, B.Hubert, B.Gepner, C.Deruelle: The emotional brain in autism : cerebral correlates of abnormal explicit processing of emotional information. Bill Greenough: Invited Talk. Pawan Sinha: Project PRAKASH: Development of object perception following long-term Visual deprivation. Lingyun Zhang Garrison W. Cottrell: Four Blobs: "Y" or Face? Andrew Lovett, Brian Scassellati: Using a Robot to Reexamine Looking Time Experiments. David Philipona, J. Kevin O'Regan, and Olivier J.-M. D. Coenen: Color perception in sensorimotor theory, or what do we really perceive? Jonathan Nelson, Gary Cottrell, Javier R. Movellan: Explaining Eye Movements During Learning as an Active Sampling Process. Karen Dobkins: Invited Talk Yuichiro Yoshikawa, Koh Hosoda, and Minoru Asada: Cross-anchoring for binding tactile and visual sensations via unique association through self-perception. Jeffrey L. Krichmar, Douglas A. Nitz, Gerald M. Edelman: Object recognition, Adaptive Behavior and Learning in Brain-Based Devices. Terrence Sejnowski: Invited Talk. Saturday October 23 Development of Hiking Abilities at Torrey Pines Park. Development of Golf Skills at the Torrey Pines Golf Course. Learning to Paraglide at the Torrey Pines International Glideport. Learning How To Surf at La Jolla Shores. Learning Ocean Kayaking at La Jolla Shores. From worgott at cn.stir.ac.uk Wed Sep 15 06:17:25 2004 From: worgott at cn.stir.ac.uk (Florentin Woergoetter) Date: Wed, 15 Sep 2004 11:17:25 +0100 Subject: review article on temporal sequence learning Message-ID: <414816B5.9090506@cn.stir.ac.uk> Dear Connectionists, I would like to announce the availability of a review article which could be of broader interest at: http://www.cn.stir.ac.uk/~faw1/Publications/papers/woe_porr_nc2004.pdf Wrgtter, F. and Porr, B. (2004) Temporal sequence learning, prediction and control - A review of different models and their relation to biological mechanisms. Neural Comp. 17, 1-75. Abstract: In this article we compare methods for temporal sequence learning (TSL) across the disciplines machine-control, classical conditioning, neuronal models for TSL as well as spike-timing dependent plasticity. This review will briefly introduce the most influential models and focus on two questions: 1) To what degree are reward-based (e.g. TD-learning) and correlation based (hebbian) learning related? and 2) How do the different models correspond to possibly underlying biological mechanisms of synaptic plasticity? We will first compare the different models in an open-loop condition, where behavioral feedback does not alter the learning. Here we observe, that reward-based and correlation based learning are indeed very similar. Machine-control is then used to introduce the problem of closed-loop control (e.g. actor-critic architectures). Here the problem of evaluative (rewards) versus non-evaluative (correlations) feedback from the environment will be discussed showing that both learning approaches are fundamentally different in the closed-loop condition. In trying to answer the second question we will compare neuronal versions of the different learning architectures to the anatomy of the involved brain structures (basal-ganglia, thalamus and cortex) and to the molecular biophysics of glutamatergic and dopaminergic synapses. Finally we discuss the different algorithms used to model spike-timing dependent plasticity (STDP) and compare them to reward based learning rules. Certain similarities are found in spite of the strongly different time scales. Here we focus on the biophysics of the different Calcium-release mechanisms known to be involved in STDP. best wishes F. Woergoetter From adr at adrlab.ahc.umn.edu Wed Sep 15 16:13:37 2004 From: adr at adrlab.ahc.umn.edu (A David Redish) Date: Wed, 15 Sep 2004 15:13:37 -0500 Subject: Call for Papers: Special issue on navigation Message-ID: <200409152013.i8FKDbvc019067@adrlab.ahc.umn.edu> Call for Papers A Special Issue on Navigation Guest Editor: K.J. Jeffery Biologists and designers of artificial systems share an interest in understanding how mobile agents can not only move around the world in an adaptive manner, but also learn the locations of salient places so that they can return there later. Those who study animal navigation have provided a wealth of data with which to formulate hypotheses about how animals navigate. Roboticists and computational modellers, in turn, have elucidated some of the underlying principles of spatial representation and navigation. Nevertheless, convincing models of animal navigation remain elusive, as do useful artificial navigation systems. This issue aims to bring to the fore some of the most important questions from both domains. Key research issues and topics in the area include: - The evolution of navigation - Navigation across different scales - How are places represented? - Representing and reaching a goal - The problem of multiple goals - Planning trajectories - Shortcutting and detours - Navigating in featureless environments - Interactions between multiple navigation systems - Is there a geometric module in animals? - Multisensory integration - Spatial learning The main aims of this special issue are to approach the theoretical questions pertaining to navigation from a biological perspective. Contributions are encouraged both from biologists with an interest in the theoretical implications of biological data, and from designers of artificial navigational systems (including computer models and robots). Papers may be straightforwardly computational or more theoretical, and presentation of new experimental data is welcomed. Submission Instructions Manuscripts, either full papers or shorter research notes (up to 4000 words), following the Connection Science guidelines http://www.tandf.co.uk/journals/authors/ccosauth.asp) should be emailed to the guest editor by October 14, 2004. Reviews will be completed by December 1, 2004, and final drafts will be accepted no later than February 28, 2005. Guest Editor K.J. Jeffery Department of Psychology University College London 26 Bedford Way London WC1H OAP UK Tel/Fax: +44 (0) 207 679 5308 E-mail: k.jeffery at ucl.ac.uk Web: http://www.psychol.ucl.ac.uk/people/profiles/jeffery_kate.htm Special Editorial board Simon Benhamou, Behavioural Ecology Group, Centre d'Ecologie Fonctionelle et Evolutive, CNRS, Montpelier, France Michael Hasselmo, Department of Psychology, Center for Memory and Brain and Program in Neuroscience, Boston University, Boston, USA David Redish, Department of Neuroscience, University of Minnesota, Minneapolis, USA Matthew Shapiro, Fishberg Research Center for Neurobiology, Kastor Neurobiology of Aging Laboratories, Mount Sinai School of Medicine, New York, USA. From AEL at zurich.ibm.com Tue Sep 14 04:50:10 2004 From: AEL at zurich.ibm.com (Andre Elisseeff) Date: Tue, 14 Sep 2004 10:50:10 +0200 Subject: 1 PhD/1 Post Doc position - IBM Research Lab - Zurich Message-ID: PhD/Post Doc position - IBM Research Lab - Zurich, Switzerland. Algorithm Design for Sequential Decision Making Systems. The machine learning team of the IBM Research Lab in Zurich is looking for students for one PhD position and one Post-doc position in the area of machine learning, artificial intelligence, statistics, and/or related fields. The candidate would work on designing and developing new approaches for sequential/temporal data with applications to marketing and medical data analysis. She/he will be integrated in a scientific environment where academic publications and real data analysis are the main activities. It is expected that the candidate has a strong understanding of advanced statistical algorithms and is ready to get into the implementation of the techniques that she/he will develop in the group. The IBM Research Lab in Zurich is located in Rueschlikon (15min. away from the center of Zurich). The official language of the lab is English. See www.zurich.ibm.com for more information about the lab and its surroundings. -- Introduction to the research topic: -- With the advent of the information technology era, companies and institutions have recorded a lot of data: hospitals have gathered historical records of patients with the evolution of their disease, web companies are monitoring how visitors move from pages to pages, even video game programmers start to look at how players interact with the game. In all those situations, the data is used to analyze how the patient, the visitor or the gamer will react to some action/decision that the doctor/company or game might make. As the number of records and the complexity of real problems increase, this analytical process tends to be performed more and more by machines. This has led to the invention of sequential decision making techniques which use a database of historical records to build a statistical model of the environment (e.g. patient, visitor or gamer) and to find the optimal set of actions to be taken in the future. Although such techniques have been used in a large domain of applications, no generic solution can be taken off the shelves. Designing sequential decision making algorithms that can take into account application specific constraints is an ongoing research subject and is the main topic of our team. -- Please send your application by email (C.V. including a cover letter) to: Andre Elisseeff (ael at zurich.ibm.com) Abderrahim Labbi (abl at zurich.ibm.com) IBM Research Lab, Zurich Saumerstrasse 4, CH-8803 Rueschlikon -- Closing date for all applications by email or post: Friday 29th October 2004. -- Note: the starting dates of the positions will be defined according to the candidate's possibilities. Andre Elisseeff From maass at igi.tu-graz.ac.at Tue Sep 14 06:17:00 2004 From: maass at igi.tu-graz.ac.at (Wolfgang Maass) Date: Tue, 14 Sep 2004 12:17:00 +0200 Subject: Workshop on Biologically Inspired Computing Message-ID: <4146C51C.4030604@igi.tu-graz.ac.at> ------------------------------------------------------------------------ International Workshop on BIOLOGICALLY INSPIRED COMPUTING November 19 and 20, 2004, at Tohoku University, Sendai, Japan ------------------------------------------------------------------------ This workshop has the goal to improve the collaboration between computer scientists and neuroscientists on problems of common interests, such as the investigation of computing and learning in biological neural systems, and the design of biologically inspired computing machinery with autonomous learning capability. Apart from invited talks and tutorials, there will also be sessions for the presentation of some submitted papers. This meeting will be quite informal. It is hoped that this workshop will develop into series of annual joint-meetings of computer scientists and neuroscientists. Papers presented at this workshop will be made publicly available on a webpage. If there exists sufficient interest we will also publish a book or special issue of a journal with selected papers from this workshop. Invited talks will be presented by Kazuyuki Aihara (The University of Tokyo, Japan http://www.sat.t.u-tokyo.ac.jp/index.html) Jianfeng Feng (Sussex University, UK http://www.cogs.susx.ac.uk/informatics_docs/research/bam/) Shigetoshi Nara (Okayama University, Japan) Rajesh P.N. Rao (University of Washington, USA http://www.cs.washington.edu/homes/rao/) Dan Roth (University of Illinois, USA http://l2r.cs.uiuc.edu/~danr/) Ichiro Tsuda (Hokkaido University, Japan http://www.math.hokudai.ac.jp/~tsuda/) Minoru Tsukada (Tamagawa University, Japan) In addition Wolfgang Maass (http://www.igi.tugraz.at/maass/Welcome.html) will give a tutorial on biologically inspired models of computation. The workshop fee is 20,000 yen which includes admission to the workshop, a copy of the proceedings, a welcome reception on November 18 at Tohoku University, a banquet on November 19 at SENDAI EXCEL HOTEL TOKYU, and two lunches. Please return your registration form attached by November 5, 2004. For more information, contact Email : bic at maruoka.ecei.tohoku.ac.jp URL : http://www.maruoka.ecei.tohoku.ac.jp/bic/ Organizers: Wolfgang Maass (Graz University of Technology, Austria) Akira Maruoka (Tohoku University, Sendai, Japan) ------------------------------------------------------------------------ Paper submissions: Extended abstracts (not exceeding 12 pages) with original new results on the theme of this workshop should be submitted electronically by October 15, to bic at maruoka.ecei.tohoku.ac.jp, including all authors' names, contact author's name, mailing addresses, affiliation and email addresses of all authors. All submissions will be reviewed by referees, and notifications of acceptance will be sent out by October 31. ------------------------------------------------------------------------ Participation in the workshop: There will be a registration fee of 20,000 yen, including admission to the workshop, a copy of proceedings, a welcome reception on November 18 at Tohoku University, a banquet on November 19 at SENDAI EXCEL HOTEL TOKYU, and two lunches. Please return the completed registration form by November 5 to Email: bic at maruoka.ecei.tohoku.ac.jp or Fax : +81-22-263-9413 ------------------------------------------------------------------------- Begin of Registration Form ------------------------------------------------------------------------- International Workshop on BIOLOGICALLY INSPIRED COMPUTING REGISTRATION FORM November 19--20,2004 Aoba Memorial Bldg.,Tohoku University, Sendai, Japan Last Name First Name Middle Name Name as you Want to Appear on Badge Affiliation Mailing Address City State Zip Code Country Phone Fax Email URL Arrival Date Departure Date Payment: We accept payment only by credit card (VISA or MasterCard). Please complete the following information and return to Mail: bic at maruoka.ecei.tohoku.ac.jp or Fax : +81-22-263-9413 Note: Because email is not secure, we recommend you to send your credit card information by Fax. Type of credit card: ____________________________ Credit card number: ____________________________ Expiration date: ____________________________ Print name as shown on credit card: ____________________________ Signature: ____________________________ ------------------------------------------------------------------------- End of Registration Form ------------------------------------------------------------------------- Accommodation: A block of rooms has been reserved for the participants of BIC04. Reservations can be made by simply calling the hotel directly. Please be sure to mention "BIC04" when making reservations by telephone by November 5 to obtain the special rates. SENDAI EXCEL HOTEL TOKYU 2-9-25 Ichiban-cho, Aoba-ku, Sendai-Shi Miyagi, Japan 980-0811 Phone : +81-22-262-2412 Fax : +81-22-262-4109 URL : http://www.tokyuhotels.co.jp Email : sendai at tokyuhotel.co.jp -- Wolfgang Maass Professor of Computer Science Technische Universitaet Graz http://www.igi.tugraz.at/maass/ From esann at dice.ucl.ac.be Wed Sep 15 15:10:15 2004 From: esann at dice.ucl.ac.be (esann) Date: Wed, 15 Sep 2004 21:10:15 +0200 Subject: CFP: ESANN'2005 European Symposium on Artificial Neural Networks Message-ID: <001f01c49b57$a4621d50$43ed6882@dice.ucl.ac.be> ESANN'2005 13th European Symposium on Artificial Neural Networks Bruges (Belgium) - April 27-28-29, 2005 Announcement and call for papers ========================== Technically co-sponsored by the International Neural Networks Society, the European Neural Networks Society, the IEEE Computational Intelligence Society, the IEEE Region 8 (to be confirmed), the IEEE Benelux Section. The call for papers for the ESANN'2005 conference is now available on the Web: http://www.dice.ucl.ac.be/esann For those of you who maintain WWW pages including lists of related ANN sites: we would appreciate if you could add the above URL to your list; thank you very much! We try as much as possible to avoid multiple sendings of this call for papers; however we apologize if you receive this e-mail twice, despite our precautions. You will find below a short version of this call for papers, without the instructions to authors (available on the Web). ESANN'2005 is organized in collaboration with the UCL (Universite catholique de Louvain, Louvain-la-Neuve) and the KULeuven (Katholiek Universiteit Leuven). Scope and topics ---------------- Since its first happening in 1993, the European Symposium on Artificial Neural Networks has become the reference for researchers on fundamentals and theoretical aspects of artificial neural networks. Each year, around 100 specialists attend ESANN, in order to present their latest results and comprehensive surveys, and to discuss the future developments in this field. The ESANN'2005 conference will focus on fundamental aspects of ANNs: theory, models, learning algorithms, mathematical and statistical aspects, in the context of function approximation, classification, data analysis, control, time-series prediction, signal processing, vision, etc. Papers on links and comparisons between ANNs and other domains of research (such as statistics, signal processing, biology, psychology, evolutive learning, bio-inspired systems, etc.) are encouraged. Papers will be presented orally (no parallel sessions) and in poster sessions; all posters will be complemented by a short oral presentation during a plenary session. The topic of the paper decides if it better fits into an oral or a poster session, not its quality. The selection of posters will be identical to oral presentations, and both will be printed in the same way in the proceedings. Nevertheless, authors have the choice to indicate their choice for oral or poster presentation only. The following is a non-exhaustive list of topics covered during the ESANN conferences: - Models and architectures - Learning algorithms - Theory - Mathematics - Statistical data analysis - Classification - Approximation of functions - Time series forecasting - Nonlinear dimension reduction - Multi-layer Perceptrons - RBF networks - Self-organizing maps - Vector quantization - Support Vector Machines - Recurrent networks - Fuzzy neural nets - Hybrid networks - Bayesian neural nets - Cellular neural networks - Signal processing - Independent component analysis - Natural and artificial vision - Adaptive control - Identification of non-linear dynamical systems - Biologically plausible networks - Bio-inspired systems - Cognitive psychology - Evolutiv learning - Adaptive behaviour Special sessions ---------------- Special sessions will be organized by renowned scientists in their respective fields. Papers submitted to these sessions are reviewed according to the same rules as any other submission. Authors who submit papers to one of these sessions are invited to mention it on the author submission form; nevertheless, submissions to the special sessions must follow the same format, instructions and deadlines as any other submission, and must be sent to the same address. The following special sessions will be organized at ESANN'2005: 1. Kernel Machines and Exponential Families S. Canu, Australian Nat. Univ. (Australia) & INSA Rouen (France), A. Smola, Australian Nat. Univ. (Australia) 2. Classification using non-standard metrics B. Hammer, Univ. Osnabr?ck, T. Villmann, Univ. Leipzig (Germany) 3. Evolutionary and neural computation C. Igel, Ruhr-Univ. Bochum, B. Sendhoff, Honda Research Institute Europe GmbH (Germany) 4. Dynamical and Numerical Aspects of Neural Computing M. Atencia, University of M?laga (Spain) 5. Artificial Neural Networks and Prognosis in Medicine Jos? M. Jerez, Univ. Malaga (Spain), Leonardo Franco, Univ. Oxford (UK) Location -------- The conference will be held in Bruges (also called "Venice of the North"), one of the most beautiful medieval towns in Europe. Bruges can be reached by train from Brussels in less than one hour (frequent trains). The town of Bruges is world-wide known, and famous for its architectural style, its canals, and its pleasant atmosphere. The conference will be organized in a hotel located near the centre (walking distance) of the town. There is no obligation for the participants to stay in this hotel. Hotels of all level of comfort and price are available in Bruges; there is a possibility to book a room in the hotel of the conference at a preferential rate through the conference secretariat. A list of other smaller hotels is also available. The conference will be held at the Novotel hotel, Katelijnestraat 65B, 8000 Brugge, Belgium. Proceedings and journal special issue ------------------------------------- The proceedings will include all communications presented to the conference (tutorials, oral and posters), and will be available on-site. Extended versions of selected papers will be published in the Neurocomputing journal (Elsevier). Call for contributions ---------------------- Prospective authors are invited to submit their contributions before 3 December 2004. The electronic submission procedure will be available soon on the ESANN Web pages http://www.dice.ucl.ac.be/esann/. Authors must indicate their choice for oral or poster presentation at the submission. They must commit themselves that they will register to the conference and present the paper in case of acceptation of their submission (one paper per registrant). Authors of accepted papers will have to register before February 25, 2005; they will benefit from the advance registration fee. Deadlines --------- Submission of papers December 3, 2004 Notification of acceptance February 4, 2005 Symposium April 27-29, 2005 Registration fees ----------------- Universities Industries speakers registration 440 ? 540 ? (before 28 February 2005) (one paper per speaker) non-speaker registration (before 22 March 2005) 440 ? 540 ? non-speaker registration (after 22 March 2005) 490 ? 590 ? The registration fee includes the attendance to all sessions, the ESANN'2005 dinner, a copy of the proceedings, daily lunches (27-29 April 2005), and the coffee breaks. Conference secretariat ---------------------- ESANN'2005 d-side conference services phone: + 32 2 730 06 11 24 av. L. Mommaerts Fax: + 32 2 730 06 00 B - 1140 Evere (Belgium) E-mail: esann at dice.ucl.ac.be http://www.dice.ucl.ac.be/esann Steering and local committee (to be confirmed) ---------------------------- Hugues Bersini Univ. Libre Bruxelles (B) Fran?ois Blayo Pr?figure (F) Marie Cottrell Univ. Paris I (F) Jeanny H?rault INPG Grenoble (F) Bernard Manderick Vrije Univ. Brussel (B) Eric Noldus Univ. Gent (B) Jean-Pierre Peters FUNDP Namur (B) Joos Vandewalle KUL Leuven (B) Michel Verleysen UCL Louvain-la-Neuve (B) Scientific committee (to be confirmed) -------------------- Samy Bengio IDIAP Martigny (CH) Pierre Bessi?re CNRS (F) Gianluca Bontempi Univ. Libre Bruxelles (B) Herv? Bourlard IDIAP Martigny (CH) Joan Cabestany Univ. Polit. de Catalunya (E) Colin Campbell Bristol Univ. (UK) St?phane Canu Inst. Nat. Sciences App. (F) Valentina Colla Scuola Sup. Sant'Anna Pisa (I) Holk Cruse Universit?t Bielefeld (D) Eric de Bodt Univ. Lille II (F) & UCL Louvain-la-Neuve (B) Dante Del Corso Politecnico di Torino (I) Georg Dorffner University of Vienna (A) Wlodek Duch Nicholas Copernicus Univ. (PL) Marc Duranton Philips Semiconductors (USA) Richard Duro Univ. Coruna (E) Anibal Figueiras-Vidal Univ. Carlos III Madrid (E) Simone Fiori Univ. Perugia (I) Jean-Claude Fort Universit? Nancy I (F) Colin Fyfe Univ. Paisley (UK) Stan Gielen Univ. of Nijmegen (NL) Mirta Gordon IMAG Grenoble (F) Marco Gori Univ. Siena (I) Bernard Gosselin Fac. Polytech. Mons (B) Manuel Grana UPV San Sebastian (E) Anne Gu?rin-Dugu? INPG Grenoble (F) Barbara Hammer Univ. of Osn?bruck (D) Martin Hasler EPFL Lausanne (CH) Laurent H?rault CEA-LETI Grenoble (F) Gonzalo Joya Univ. Malaga (E) Christian Jutten INPG Grenoble (F) Juha Karhunen Helsinki Univ. of Technology (FIN) Stefanos Kollias National Tech. Univ. Athens (GR) Vera Kurkova Acad. of Science of the Czech Rep. (CZ) Jouko Lampinen Helsinki Univ. of Tech. (FIN) Petr Lansky Acad. of Science of the Czech Rep. (CZ) Beatrice Lazzerini Univ. Pisa (I) Mia Loccufier Univ. Gent (B) Erzsebet Merenyi Rice Univ. (USA) Jos? Mira UNED (E) Jean-Pierre Nadal Ecole Normale Sup?rieure Paris (F) Erkki Oja Helsinki Univ. of Technology (FIN) Arlindo Oliveira INESC-ID (P) Gilles Pag?s Univ. Paris 6 (F) Thomas Parisini Univ. Trieste (I) H?l?ne Paugam-Moisy Universit? Lumi?re Lyon 2 (F) Alberto Prieto Universitad de Granada (E) Didier Puzenat Univ. Antilles-Guyane (F) Leonardo Reyneri Politecnico di Torino (I) Jean-Pierre Rospars INRA Versailles (F) Jose Santos Reyes Univ. Coruna (E) Udo Seiffert IPK Gatersleben (D) Jochen Steil Univ. Bielefeld (D) John Stonham Brunel University (UK) Johan Suykens K. U. Leuven (B) John Taylor King?s College London (UK) Claude Touzet Univ. Provence (F) Marc Van Hulle KUL Leuven (B) Thomas Villmann Univ. Leipzig (D) Axel Wism?ller Ludwig-Maximilians-Univ. M?nchen (D) Michalis Zervakis Technical Univ. Crete (GR) ============================ 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 - Machine Learning Group 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 harnad at ecs.soton.ac.uk Wed Sep 15 08:10:38 2004 From: harnad at ecs.soton.ac.uk (Stevan Harnad) Date: Wed, 15 Sep 2004 13:10:38 +0100 (BST) Subject: Cognition and Technology: Call for papers (fwd) Message-ID: ---------- Forwarded message ---------- From kcox at fasfind.com Wed Sep 15 08:00:18 2004 From: kcox at fasfind.com (Kevin Cox) Date: Wed, 15 Sep 2004 12:00:18 -0000 Subject: No subject Message-ID: As technology advances we are witnessing changes in the nature of cognition. A wide range of issues pertaining to technology and cognition will be covered in a series of special issues of the journal Pragmatics & Cognition. We are inviting contributions to our special issues, as specified below (for full details, please see: http://www.ecs.soton.ac.uk/~id/technology.html ) Pragmatics & Cognition (P&C) will henceforth pay special attention to the growing interest in the relationship between technological advances and cognition =96 a field that is intimately related to the journal's basic concerns. Beginning with volume 13 (2005), Pragmatics & Cognition will contain three issues instead of the current two. Each year, one of P&C's issues will be a thematic Special Issue devoted to "Cognition and Technology" (C&T), containing invited as well as submitted refereed papers. Space will also be reserved in these thematic issues for submitted articles, discussion notes, and book reviews in the field of C&T not specifically related to the theme of the Special Issue. Each Special Issue will be co-edited by a Guest Editor and Itiel Dror, who has been appointed P&C's Associate Editor for C&T. For full details, please see: http://www.ecs.soton.ac.uk/~id/technology.html Special Issues 1. New Technologies and the Pragmatics of Cognition Editors: Marcelo Dascal and Itiel Dror 2. Distributed Cognition Editors: Stevan Harnad and Itiel Dror 3. Robotics and Cognition Editors: Pim Haselager, Maria Eunice Qumlice Gonzales, and Itiel Dror 4. Ageing, Impairment, and Technology Editors: Romola Bucks, Jonathan Cole, and Itiel Dror 5. Technologies for Cognitive Research: Achievements, Problems, and Prospects Editors: Boris Velichkovsky and Itiel Dror 6. Cognitive Development and Education in the Mirror of Technology Editors: TBA and Itiel Dror Contributions are invited to the Special Cognition and Technology Series (for full details, please see: http://www.ecs.soton.ac.uk/~id/technology.html ) From kbp at imm.dtu.dk Tue Sep 21 10:54:25 2004 From: kbp at imm.dtu.dk (Kaare Brandt Petersen) Date: Tue, 21 Sep 2004 16:54:25 +0200 (METDST) Subject: The Matrix Cookbook: A Desktop Reference Message-ID: Dear Colleagues In case you might be interested: A 30 pages collection of identities, approximations and related issues regarding matrices, can be found at the following address http://www.imm.dtu.dk/pubdb/views/edoc_download.php/3274/pdf/imm3274.pdf Best regards, Kaare Brandt Petersen -- Kaare Brandt Petersen * http://2302.dk From dwang at cse.ohio-state.edu Tue Sep 21 15:48:52 2004 From: dwang at cse.ohio-state.edu (DeLiang Wang) Date: Tue, 21 Sep 2004 15:48:52 -0400 Subject: Available: IEEE TNN Special Issue on Temporal Coding In-Reply-To: <3E7236CC.203886BC@cis.ohio-state.edu> References: <3DC03C8C.B2A5BA8E@cis.ohio-state.edu> <3E7236CC.203886BC@cis.ohio-state.edu> Message-ID: <415085A4.8000304@cse.ohio-state.edu> IEEE Transactions on Neural Networks - Volume 15, Number 5, September 2004 (http://ieee-cis.org/pubs/tnn/) SPECIAL ISSUE ON TEMPORAL CODING FOR NEURAL INFORMATION PROCESSING (Online accessible from IEEE Xpore, http://ieeexplore.ieee.org/) Guest Editorial D. Wang, W. J. Freeman, R. Kozma, A. G. Lozowski, and A. A. Minai SPECIAL ISSUE PAPERS Coincidence Detection Correlated Inhibitory and Excitatory Inputs to the Coincidence Detector: Analytical Solution S. Mikula and E. Niebur An Instance of Coincidence Detection Architecture Relying on Temporal Coding D. B?roule A Network of Coincidence Detector Neurons With Periodic and Chaotic Dynamics M. Watanabe and K. Aihara Dynamics Dynamics and the Single Spike M. G. Paulin, L. F. Hoffman, and C. Assad On the Sample Complexity of Learning for Networks of Spiking Neurons With Nonlinear Synaptic Interactions M. Schmitt Dynamic Proximity of Spatio-Temporal Sequences D. Horn, G. Dror, and B. Quenet An Analysis of Globally Connected Active Rotators With Excitatory and Inhibitory Connections Having Different Time Constants Using the Nonlinear Fokker?Planck Equations T. Kanamaru and M. Sekine Grouping Synchronization in a Pulse-Coupled Network of Chaotic Spiking Oscillators H. Nakano and T. Saito Synchronization Rates in Classes of Relaxation Oscillators S. R. Campbell, D. Wang, and C. Jayaprakash Neural Modeling Different Types of Signal Coupling in the Visual Cortex Related to Neural Mechanisms of Associative Processing and Perception R. Eckhorn, A. M. Gail, A. Bruns, A. Gabriel, B. Al-Shaikhli, and M. Saam Dynamical Analysis of Neural Oscillators in an Olfactory Cortex Model D. Xu and J. C. Principe Which Model to Use for Cortical Spiking Neurons? E. M. Izhikevich The Role of Temporal Parameters in a Thalamocortical Model of Analogy Y. Choe Stimulus-Specific Oscillations in a Retinal Model G. T. Kenyon, B. J. Travis, J. Theiler, J. S. George, G. J. Stephens, and D. W. Marshak Theta-Modulated Feedforward Network Generates Rate and Phase Coded Firing in the Entorhino-Hippocampal System M. Lengyel and P. ?rdi Auditory Processing Temporal Codes and Computations for Sensory Representation and Scene Analysis P. A. Cariani A Temporal-Analysis-Based Pitch Estimation System for Noisy Speech With a Comparative Study of Performance of Recent Systems A. Khurshid and S. L. Denham Robust Sound Onset Detection Using Leaky Integrate-and-Fire Neurons With Depressing Synapses L. S. Smith and D. S. Fraser Monaural Speech Segregation Based on Pitch Tracking and Amplitude Modulation G. Hu and D. Wang A Computational Model of Auditory Selective Attention S. N. Wrigley and G. J. Brown Visual Processing Coding Static Natural Images Using Spiking Event Times: Do Neurons Cooperate? L. Perrinet, M. Samuelides, and S. Thorpe Pixel Clustering by Adaptive Pixel Moving and Chaotic Synchronization L. Zhao, A. C. P. L. F. de Carvalho, and Z. Li Pulse-Coupled Neural Networks for Contour and Motion Matchings B. Yu and L. Zhang Temporally Sequenced Intelligent Block-Matching and Motion-Segmentation Using Locally Coupled Networks X. Zhang and A. A. Minai Associative Networks Storage Capacity Diverges With Synaptic Efficiency in an Associative Memory Model With Synaptic Delay and Pruning S. Miyoshi and M. Okada A Transient-Chaotic Autoassociative Network (TCAN) Based on Lee Oscillators R. S. T. Lee Identification and Control of Dynamical Systems Using the Self-Organizing Map G. A. Barreto and A. F. R. Ara?jo Temporal Processing Temporal Processing in Primate Motor Control: Relation Between Cortical and EMG Activity O. F. L. Manette and M. A. Maier Signal Processing With Temporal Sequences in Olfactory Systems A. G. Lozowski, M. Lysetskiy, and J. M. Zurada Temporal BYY Encoding, Markovian State Spaces, and Space Dimension Determination L. Xu Hardware Implementation Synchrony Detection and Amplification by Silicon Neurons With STDP Synapses A. Bofill-i-Petit and A. F. Murray Temporal Coding in a Silicon Network of Integrate-and-Fire Neurons S.-C. Liu and R. Douglas Synchronization of Nonlinear Electronic Oscillators for Neural Computation J. Cosp, J. Madrenas, E. Alarc?n, E. Vidal, and G. Villar From cemgil at science.uva.nl Wed Sep 22 05:31:18 2004 From: cemgil at science.uva.nl (Ali Taylan Cemgil) Date: Wed, 22 Sep 2004 11:31:18 +0200 Subject: PhD thesis on music transcription Message-ID: <005701c4a086$ed95dd20$6a42fea9@TaylanLaptop> Dear Connectionists, My PhD thesis on music transcription is available from http://carol.science.uva.nl/~cemgil/papers.html A. Taylan Cemgil %--------------------- Title: Bayesian Music Transcription Institute: Radboud University Nijmegen, the Netherlands Keywords: Graphical models, Dynamic Bayesian Networks, Switching State Space models, Monte Carlo simulation, Music Transcription, Rhythm Quantization, Tempo Tracking, Polyphonic Pitch Tracking Abstract : Music transcription refers to extraction of a human readable and interpretable description from a recording of a music performance. The final goal is to implement a program that can automatically infer a musical notation that lists the pitch levels of notes and corresponding score positions in any arbitrary acoustical input. However, in this full generality, music transcription stays yet as a hard problem and arguably requires simulation of a human level intelligence. On the other hand, under some realistic assumptions, a practical engineering solution is possible by an interplay of scientific knowledge from cognitive science, musicology, musical acoustics and computational techniques from artificial intelligence, machine learning and digital signal processing. In this context, the aim of this thesis is to integrate this vast amount of prior knowledge in a consistent and transparent computational framework and to demonstrate the feasibility of such an approach in moving us closer to a practical solution to music transcription. In this thesis, we approach music transcription as a statistical inference problem where given a signal, we search for a score that is consistent with the encoded music. In this context, we identify three subproblems: Rhythm Quantization, Tempo Tracking and Polyphonic Pitch Tracking. For each subproblem, we define a probabilistic generative model, that relates the observables (i.e. onsets or audio signal) with the underlying score. Conceptually, the transcription task is then to ``invert'' this generative model by using the Bayes Theorem and to estimate the most likely score. From Harel.Shouval at uth.tmc.edu Wed Sep 22 13:51:44 2004 From: Harel.Shouval at uth.tmc.edu (Harel Shouval) Date: Wed, 22 Sep 2004 12:51:44 -0500 Subject: A New Book: Theory of cortical plasticity Message-ID: <4151BBB0.7000402@uth.tmc.edu> Announcing a new book: Theory of cortical plasticity. Authors: Leon N Cooper, Nathan Intrator, Brian S. Blais, & Harel Z. Shouval This book presents a theory of cortical plasticity and shows how this theory leads to experiments that test both its assumptions and consequences. It elucidates, in a manner that is accessible to students as well as researchers, the role which the BCM theory has played in guiding research and suggesting experiments that have led to our present understanding of the mechanisms underlying cortical plasticity. Most of the connections between theory and experiment that are discussed require complex simulations. A unique feature of the book is the accompanying software package, Plasticity . This is provided complete with source code, and enables the reader to repeat any of the simulations quoted in the book as well as to vary either parameters or assumptions. Plasticity is thus a research and an educational tool. Readers can use it to obtain hands-on knowledge of the structure of BCM and various other learning algorithms. They can check and replicate our results as well as test algorithms and refinements of their own. Now available from World Scientific Publishing see also: Amazon.com , Barnesandnoble.com , Booksamillion.com , Cabobble.com , Quantumbooks.com -- Harel Shouval Department of Neurobiology and Anatomy University of Texas Medical School at Houston 6431 Fannin st. Houston TX 77025 Phone: 713-500-5708 Web: http://nba.uth.tmc.edu/resources/faculty/members/shouval.htm From lynn.hazan at myrealbox.com Wed Sep 22 17:24:37 2004 From: lynn.hazan at myrealbox.com (Lynn Hazan) Date: Wed, 22 Sep 2004 17:24:37 -0400 Subject: NeuroScope Message-ID: <200409221724.37608.lynn.hazan@myrealbox.com> We are pleased to announce the release of NeuroScope, an advanced viewer for electrophysiological and behavioral data with limited editing capabilities. NeuroScope allows comparison of analyzed data with the original recordings. It can display original and processed local field potentials (EEG), action potentials recorded from single neurons on groups of electrodes (e.g., tetrodes or multisite siliconprobes), behavioral events, including 2 dimensional information (e.g., the position of a rat). NeuroScope was written by Lynn Hazan (lynn.hazan at myrealbox.com) in the laboratory of Gyorgy Buzsaki at Rutgers University (http://osiris.rutgers.edu), in collaboration with the laboratory of Kenneth D. Harris (http://qneuro.rutgers.edu) and is released under the GNU General Public Licence (www.gnu.org). NeuroScope offers many features enabling the user to explore neuronal recordings: * Selection and grouping of channels according to post-hoc anatomical or physiological information * Selection and grouping of channels for spike sorting and other treatments * Color-coding of traces or groups * Fast and easy navigation in the data, by steps, specific time or markers * Temporal and amplitude zooms * Superimposition of post-hoc data (e. g., spike rasters, events) on original or filtered traces * Editing of behavioral events * Display of the positions of the animal for the currently selected timeframe * Multiple displays of parallel or sequentially recorded sets * Storage in XML format of recording parameters (groups, colors) for subsequent analyses * Session management (XML format) * Ergonomic user interface for maximum speed. NeuroScope is written in C++ for Linux under the KDE environment. The program, source code, and full documentation are available at http://neuroscope.sourceforge.net. From cns-course at jupiter.chaos.gwdg.de Fri Sep 24 07:13:19 2004 From: cns-course at jupiter.chaos.gwdg.de (CNS Course) Date: Fri, 24 Sep 2004 13:13:19 +0200 (CEST) Subject: Professorship in Computational Neuroscience Message-ID: Professorship (W3) in Computational Neuroscience The Georg-August-Universitaet Goettingen invites, pending the approval of the BMBF, applications for a Professorship in Computational Neuroscience (W3) starting as early as possible. We are looking for an internationally recognized research personality, who will represent the field of Computational Neuroscience in research and teaching. The successful candidate should collaborate with existing research groups in the area of Neuroscience in Goettingen and participate in the coordination of the Center for Theoretical Neuroscience Goettingen, which is currently being established. The candidate's research should complement and expand the scientific spectrum of the Center. Possible areas of research include dynamics and coding in biological neural networks, computer-aided analysis of complex neural systems and/or the development of simulation technology for large biological neural networks. We expect a substantial contribution of the candidate towards establishing the PhD program in Computational Neuroscience within the Goettingen Graduate School of Science. The professorship is assigned to the Institute for Informatics in the Faculty of Mathematics of the Georg-August-Universitaet Goettingen. Initially the position is limited to five years but will be extended to tenure following a positive evaluation. Habilitation or alternatively documented evidence of equivalent scientific qualifications is required. The Universitaet Goettingen seeks to increase the proportion of female faculty members. Thus qualified women are especially encouraged to apply. If equally qualified, candidates with disabilities will be preferentially considered. The deadline for applications is October 27, 2004. Please submit your application in English, together with the usual information (curriculum vitae, publication list, names of three possible referees) and copies of your three most important publications to: Prof. Dr. Theo Geisel Institut fuer Nichtlineare Dynamik Universitaet Goettingen Bunsenstrasse 10 37073 Goettingen, Germany http://www.chaos.gwdg.de From Anthony.Pipe at uwe.ac.uk Thu Sep 23 03:55:00 2004 From: Anthony.Pipe at uwe.ac.uk (Tony Pipe) Date: Thu, 23 Sep 2004 08:55:00 +0100 Subject: CFP: FLAIRS'05 conference, Neural Networks Applications track Message-ID: <000a01c4a142$a03703d0$17800ba4@cems.uwe.ac.uk> CALL FOR PAPERS (submission deadline one month from now) Neural Network Applications Special Track at the 18th International FLAIRS Conference In cooperation with the American Association for Artificial Intelligence Adam's Mark Hotel Clearwater Beach, Florida May 16-18, 2005 For the web version of this call, please visit the conference web page at http://ranger.uta.edu/flairs05/ then select 'Special Tracks' and then 'Neural Networks Applications' -------------------------------------------------------------------------------- Papers are being solicited for a special track on Neural Network Applications at the 17th International FLAIRS Conference (FLAIRS-2004). The special track will be devoted to the applications of Neural Networks with the aim of presenting new and important contributions in this area. These application areas include, but are not limited to, the following: Vision Pattern Recognition Control and Process Monitoring Biomedical Applications Robotics Speech Recognition Text Mining Diagnostic Problems Telecommunications Power Systems Signal Processing Image Processing -------------------------------------------------------------------------------- Submission Guidelines Interested authors must submit completed manuscripts by October 22, 2004. Submissions should be no more than 6 pages (4000 words) in length, including figures, and contain no identifying reference to self or organization. Papers should be formatted according to AAAI Guidelines. Submission instructions can be found at FLAIRS-05 website at http://ranger.uta.edu/flairs05. Notification of acceptance will be mailed around January 7, 2005. Authors of accepted papers will be expected to submit the final camera-ready copies of their full papers by February 4, 2005 for publication in the conference proceedings which will be published by AAAI Press. Authors may be invited to submit a revised copy of their paper to a special issue of the International Journal on Artificial Intelligence Tools (IJAIT). -------------------------------------------------------------------------------- FLAIRS 2005 Invited Speakers Lawrence Hunter, University of Colorado Martha Pollack, University of Michigan Ted Senator, DARPA David Stork, Ricoh and Stanford University -------------------------------------------------------------------------------- Important Dates Paper submissions due: October 22, 2004 Notification letters sent: January 7, 2005 Camera ready copy due: February 4, 2005 -------------------------------------------------------------------------------- Special Track Committee Ingrid Russell (Co-Chair), University of Hartford, USA Tony Pipe (Co-Chair), University of the West of England, UK Brian Carse (Co-Chair), University of the West of England, UK Jim Austin, University of York, UK Vijayakumar Bhagavatula, Carnegie Mellon University, USA Douglas S. Blank, Bryn Mawr College, USA Serge Dolenko, Moscow State University, Russia Okan Ersoy, Purdue University, USA Michael Georgiopoulos, University of Central Florida, USA Mike James, York University, UK John Kolen, University of West Florida, USA Luis Marti, Universidad de La Habana, Cuba Lisa Meeden, Swarthmore College, USA Costas Neocleous, Higher Technical Institute, Cyprus Luis Fernando Nio, National University of Colombia, Colombia Sergio Roa, National University of Colombia, Colombia Roberto Santana, Institute of Cybernetics, Mathematics and Physics (ICIMAF), Cuba Bernhard Sendhoff, Honda Research and Development Europe, Offenbach/Main, Germany Chellu Chandra Sekhar, Indian Institute of Technology, India Wai Sum Tang, Chinese University of Hong Kong, Hong Kong Antony J. Waldock, University of theWest of England, UK Stefan Wermter, University of Sunderland, UK Hujun Yin, University of Manchester Institute of Science and Technology, UK -------------------------------------------------------------------------------- Further Information Questions regarding the special track should be addressed to: Tony Pipe Voice: +44-117-344-2818 Fax: +44-117-344-3800 email: Anthony.Pipe at uwe.ac.uk This email has been independently scanned for viruses and any virus detected has been removed using McAfee anti-virus software From dglanzma at mail.nih.gov Thu Sep 23 12:34:57 2004 From: dglanzma at mail.nih.gov (Glanzman, Dennis (NIH/NIMH)) Date: Thu, 23 Sep 2004 12:34:57 -0400 Subject: CORRECTION -- Dynamical Neuroscience Satellite Symposium: Closing the Loop -- CORRECTION Message-ID: <8F3AB322628548428A992EFB0E80F5D30C565604@nihexchange8.nih.gov> Twelfth Annual Dynamical Neuroscience Satellite Symposium Closing the Loop Thursday, October 21, 2004 8 a.m.-9 p.m. Friday, October 22, 2004 8 a.m.-6 p.m. Preceding the 34th Annual Meeting of the Society for Neuroscience San Diego Convention Center San Diego, California From pli at richmond.edu Fri Sep 24 16:27:53 2004 From: pli at richmond.edu (Ping Li) Date: Fri, 24 Sep 2004 16:27:53 -0400 (EDT) Subject: The APA Style Converter Message-ID: <49916.141.166.212.246.1096057673.squirrel@spidermail.richmond.edu> Dear Colleagues, If you are submitting articles to journals that require the APA Style (such as Neural Networks, for the Reference section), you might be interested in a web interface that we have developed, the APA Style Converter. A description of the Converter is attached below. You can access the Converter from our web server at: http://cogsci.richmond.edu/. We welcome your feedback, comments, and suggestions. Sincerely Ping Li pli at richmond.edu http://www.richmond.edu/~pli/ Abstract: The APA Style Converter is a web-based tool for authors to prepare their papers in APA Style according to the APA Publication Manual (5th ed.). The converter provides a user-friendly interface that allows authors to copy and paste text and upload figures through the web, and it automatically turns all texts, references, and figures to a structured article in APA Style. The output is saved in PDF format, ready for either electronic submission or hardcopy printing. Rationale: While the APA Style has widespread use in the scientific community, there are several factors that hinder authors from accurate use of the style. First, many authors find it difficult to keep track of all the details specified in the Manual. For example, when asked, few researchers are certain about, (a) whether the Footnotes section should come before or after the Author Note, (b) whether the Appendices should come before or after the Tables, or (c) what a Page Header is, how it is different from a Running Head, and how these head and headers should be laid out on the Title Page. Second, some authors who are familiar with earlier versions of the APA Style might not have kept up with the newest changes in the current version such as the abolition of underlines and the citation for internet resources. Third, researchers from countries other than North America and Europe are relatively unfamiliar with the APA Style, either because it is not part of their training or because writing conventions and publication guidelines for their native languages differ from the APA Style. Yet more and more researchers find it necessary to deal with the APA Style: the style is widely used in many disciplines, and the journals to which they submit papers require it. Researchers from other countries are also under increasing pressure to publish in international journals that may require the APA Style. From anguita at dibe.unige.it Mon Sep 27 06:25:38 2004 From: anguita at dibe.unige.it (Davide Anguita) Date: Mon, 27 Sep 2004 12:25:38 +0200 Subject: ANN: cSVM software Message-ID: <024701c4a47c$67816610$b759fb82@dibe.unige.it> Our apologies if you receive multiple copies of this message due to overlaps in mailing lists. ========== cSVM 3.0.0 ========== cSVM 3.0.0 implements the training and model selection of a Support Vector Machine for classification tasks (two-classes). People familiar with our MBP package for training Multi Layer Perceptrons should find cSVM easy to use. This software has been developed in Fortran95 and binaries have been successfully tested on x86-based PCs running Windows XP or Red Hat Linux 8, but should run faultlessly on any x86-based Win32 or Linux system. The package can be downloaded from the web pages of our laboratory: http://www.smartlab.dibe.unige.it under the section "software". cSVM is provided "as-is" and is intended for research purposes only. For any other use, information request or comments, please contact one of the authors. D.Anguita*, A.Boni**, S.Ridella*, F.Rivieccio*, D.Sterpi*. * DIBE - Dept. of Biophysical and Electronic Engineering University of Genoa Via Opera Pia 11A, 16145, Genoa ITALY {anguita, ridella, rivieccio, sterpi} AT dibe DOT unige DOT it ** DIT - Dept. of Information and Communication Technology University of Trento, Via Sommarive 14, 38050, Povo (TN), ITALY boni AT dit DOT unitn DOT it From adr at adrlab.ahc.umn.edu Fri Sep 24 10:54:50 2004 From: adr at adrlab.ahc.umn.edu (David Redish) Date: Fri, 24 Sep 2004 09:54:50 -0500 Subject: postdoctoral position available Message-ID: <200409241454.i8OEsoat001253@adrlab.ahc.umn.edu> ------------------------------------------------------------ POSTDOCTORAL POSITION AVAILABLE in the laboratory of A. David Redish Department of Neuroscience University of Minnesota Starting date: 1 January 2005 A postdoctoral position will be available starting 1 January 2005 in my laboratory in the Department of Neuroscience at the University of Minnesota. Research interests include behavioral neuroscience, with specific interests in spatial cognition in rats. My laboratory does both experimental and computational work and postdocs would be expected to participate in both aspects. Possible research projects include (but are not limited to) computational models of addiction, recording neural ensembles in striatum, and dynamics of the hippocampal place cell and post-subicular head-direction systems. Candidates should have recently completed (or be about to complete) their PhD and should have some experience in either computational or experimental neuroscience. Pay will be commensurate with NIH standards. Those interested should contact me via email at the following address redish at ahc.umn.edu The University of Minnesota is an equal-opportunity employer. ----------------------------------------------------- A. David Redish redish at ahc.umn.edu Assistant Professor http://www.cbc.umn.edu/~redish Department of Neuroscience, University of Minnesota Office: 4-142 MCB Postal Address: 6-145 Jackson Hall / 321 Church St SE / Minneapolis MN 55455 ----------------------------------------------------- From nik.kasabov at aut.ac.nz Wed Sep 29 01:07:03 2004 From: nik.kasabov at aut.ac.nz (Nik Kasabov) Date: Wed, 29 Sep 2004 17:07:03 +1200 Subject: CFP - Special session at IJCNN'05 on Computational Neuro-Genetic Modelling Message-ID: Call for Papers for a Special Session "Computational Neuro-Genetic Modelling" International Joint INNS-IEEE Conference on Neural Networks (IJCNN) 2005 Hilton Bonaventure Hotel, Montreal, Quebec, Canada July 31- August 4, 2005, IJCNN 2005, (http://faculty.uwb.edu/ijcnn05) The aim of the session is to bring together researchers in a new research area called Computational Neuro-Genetic Modelling (CNGM), that is concerned with the study and the development of dynamic neuronal models integrated with gene models. This area brings together knowledge from at least three areas of science: computer and information science, neuroscience, and molecular biology. A computational neuro-genetic model is created to model a brain function or a brain disease, or to be used as a general mathematical model for solving complex scientific and engineering problems. The CNGM goes beyond modelling simple relationship between a single gene and a single neuronal function. It is the interaction between tens, hundreds and possibly thousands of genes in a neuron and their relationship with the functioning of a neuronal ensemble and the brain as a whole. The computational neuro-genetic models constitute a new generation of neural network models that are closer to biological neural networks in their complex interaction of neuronal learning dynamics and gene activities. Topics include: Genes and growth functions; Genes and gene regulatory networks related to the brain; Genes and gene regulatory networks related to the brain development, evolution and plasticity; Genes and gene networks related to learning, memory and perception; Genes and gene networks related to brain diseases, such as, epilepsy, mental retardation, schizophrenia, etc; Functional integration of neural networks and gene networks to model brain functions; Models of spiking neurons and spiking neural networks with gene-defined parameters; Evolving and evolutionary neural networks; Software and hardware computational neurogenetic systems; Brain-like neurogenetic architectures; Applications. Organizers: Prof. Nik Kasabov (nkasabov at aut.ac.nz ) and Dr. Luba Benuskova (lbenusko at aut.ac.nz) Knowledge Engineering and Discovery research Institute, KEDRI www.kedri.info, New Zealand Submissions and deadlines: 25 October 2004: An abstract (1 page) should be sent electronically to the organizers 15 December 2004: A full paper (see the IJCNN'05 instructions for submissions) sent to the organizers. 15 January 2005: Reviews and a notification of acceptance/rejection sent to the authors. 31 January 2005: Final paper submitted to the special session electronically (IJCNN'05 portal) All accepted papers will be published in the IJCNN 2005 Proceedings. Papers not accepted for the special session can be submitted as regular submissions for IJCNN'05 (the deadline is also January 31, 2005). Authors will be invited to submit extended versions of their papers to a special issue of an international journal. Each paper must have the title, authors with e-mails/web sites, and as detailed an abstract as possible. All accepted papers must be presented at the conference. -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- Prof. Nik Kasabov, MSc, PhD FRSNZ, FNZCS, SrMIEEE Founding Director and Chief Scientist - Knowledge Engineering and Discovery Research Institute, KEDRI Chair of Knowledge Engineering, School of Computer and Information Sciences Auckland University of Technology phone: +64 9 917 9506 ; fax: +64 9 917 9501 WWW http://www.kedri.info email: nkasabov at aut.ac.nz (PA Joyce D'Mello: jdmello at aut.ac.nz; +64 9 917 9504) From d6-evans at uwe.ac.uk Thu Sep 2 07:48:32 2004 From: d6-evans at uwe.ac.uk (Dylan Evans) Date: Thu, 2 Sep 2004 12:48:32 +0100 (BST) Subject: Call for papers: AISB'05 symposium on emotion and motivation Message-ID: Agents that want and like: motivational and emotional roots of cognition and action. A symposium of the AISB'05 Convention University of Hertfordshire, Hatfield, UK, 14th - 15th April, 2005 ** Submission Deadline: October 31, 2004 ** http://www.dylan.org.uk/emotivation_aisb05/ SYMPOSIUM DESCRIPTION: --------------------- Motivation and emotion are highly intertwined (e.g., emotions are often very powerful motivational factors; motivation can be seen as a consequence of emotion and viceversa, etc.) and it is not always easy to establish clear boundaries between them. Both types of phenomena are grouped under the broader category of "affect", traditionally distinguished from "cold" cognition. They lie at the heart of autonomy, adaptation, and social interaction in both biological and artificial agents. They also have a powerful and wide-ranging influence on many aspects of cognition and action. However, their roles are often considered to be complementary - as a first approximation, motivation would be concerned with the internal and external factors involved in the establishment of "goals" and the initiation and execution of goal-oriented action, whereas emotion is rather concerned, among other critical factors, with evaluative aspects of the relation between an agent and its environment. This symposium proposes to investigate the roles and mutual interactions of motivation and emotion in influencing different aspects of cognition and action in biological and artificial agents that interact with their physical and social environment. The nature of this topic necessitates a highly multi-disciplinary symposium, and we invite contributions from different relevant disciplines such as psychology, biology, neuroscience, ethology, sociology and philosophy, in addition to AI and robotics. SYMPOSIUM ORGANISERS: -------------------- Lola Canamero Adaptive Systems Research Group School of Computer Science University of Hertfordshire College Lane, Hatfield, Herts AL10 9AB Phone: +44-(0)1707-284308; Fax: +44-(0)1707-284303 URL: http://homepages.feis.herts.ac.uk/~comqlc E-mail: L.Canamero at herts.ac.uk Dylan Evans Faculty of Computing, Engineering and Mathematical Sciences University of the West of England Frenchay Campus Coldharbour Lane, Bristol BS16 1QY Tel: 0117-328-3294 (lab) Tel: 0117-328-2489 (office) Fax: 0117-344-3960 Web: http://www.dylan.org.uk E-mail: d6-evans at uwe.ac.uk SUBMISSION DETAILS: ------------------ Potential participants who would wish to present their work at the symposium (poster, demo, or oral presentation) should submit an extended abstract of no more than 2500 words. Contributions should describe work in progress, completed work, positions, or give insight into the current state or perspectives of research in the topic of the symposium. All submissions must include: title, author(s) name(s), affiliation(s), mailing and electronic addresses, and telephone and fax numbers. The abstracts submission deadline for this symposium is *31st October, 2004*. Extended abstracts of no more than 2500 words should be sent by e-mail (ASCII or URL from which your contribution can be downloaded are preferred; otherwise attached PDF, or UNIX-compatible postscript) to both organisers: L.Canamero at herts.ac.uk AND d6-evans at uwe.ac.uk Since contributions will be evaluated on the basis of extended abstracts, it is very important that authors make very clear why and how their contribution is relevant to the symposium. Abstracts should explain clearly: - The problem you are addressing. - Why this is an interesting problem, and how and why it is relevant to the theme of the symposium. - What has been tried before (in your community, in different communities) and why/how your contribution is better/different/more original. - How it will help others/contribute to/enrich research or applications having to do with the symposium topic. - Some results/proof/hint that it works (how can your work be evaluated?). Authors of accepted submissions will be invited to contribute a paper to the symposium proceedings, edited by the AISB Society. PROGRAMME COMMITTEE: ------------------- Orlando Avila-Garcia - University of Hertfordshire, UK Ruth Aylett - Univesity of Salford, UK Cynthia Breazeal - MIT, USA Joanna Bryson - University of Bath, UK Lola Canamero - University of Hertfordshire, UK Dylan Evans - University of the West of England, UK Philippe Gaussier - University of Cergy-Pontoise, France Steve Grand - Cyberlife Research Ltd., UK Chris Melhuish - University of the West of England, UK Jean-Arcady Meyer - LIP6, France Jacqueline Nadel - CNRS & Hopital La Salpetriere, France Paolo Petta - OFAI & Medical University of Vienna, Austria Tony Prescott - University of Sheffield, UK David Sander - University of Geneva, CH IMPORTANT DATES: --------------- - 31 October 2004: Abstract submissions due - 22 November 2004: Notification to authors - 17 December 2004: camera-ready copies due to symposium chairs - 14 January 2005: early registration deadline - 12-15 April 2005: AISB 2005 convention (symposium dates: 14 & 15 April) For further details about the symposium please visit http://www.dylan.org.uk/emotivation_aisb05 --- Dylan Evans Senior Lecturer in Intelligent Autonomous Systems Faculty of Computing, Engineering and Mathematical Sciences University of the West of England Frenchay Campus Coldharbour Lane Bristol BS16 1QY Tel: 0117-328-3294 (lab) Tel: 0117-328-2489 (office) Fax: 0117-344-3960 Web: http://www.dylan.org.uk Please avoid sending me Word or PowerPoint attachments: see http://www.fsf.org/philosophy/no-word-attachments.html From chaos at first.fhg.de Thu Sep 2 16:03:44 2004 From: chaos at first.fhg.de (Fraunhofer First) Date: Thu, 02 Sep 2004 22:03:44 +0200 Subject: Two positions in machine learning at FIRST.IDA, Berlin Message-ID: <41377CA0.5030608@first.fhg.de> Fraunhofer FIRST.IDA has two open positions in machine learning in Berlin, Germany: Department Description (see also http://ida.first.fraunhofer.de/) The IDA group at Fraunhofer FIRST in Berlin is concerned with theoretical concepts and algorithms for machine learning and their practical application to real world data analysis problems. In particular, we are developing tools for high-dimensional multivariate statistics based on methods originally developed in the field of statistics and, more recently, in the neural networks and machine learning community. Our major objective is to pursue our research all the way from theory to application. To this end, we are contributing to the theoretical development of new data analysis techniques, to their implementation according to software-engineering standards, and, finally, to their industrial or academic application. Scope of Work The positions will be focused on developing and applying methods and software in the areas of machine learning, signal processing, and statistical data analysis. One position is directed towards EEG analysis, the other towards computational chemistry. Required Knowledge and Skills - Expertise in machine learning (in particular: kernel-based methods), signal processing, and statistical data analysis. - Good organizational and communication skills. - Significant experience in software development, preferably in MATLAB. - Ability to interact well in a team in the creation of new designs and approaches. - A strong plus would be experience in EEG analysis or computational chemistry. For further details, please refer to the official job announcement (in german): http://www.jobs.fraunhofer.de/servlet/is/14526/ Please submit your resume by mentioning the job ID "FIRST-113-04-005" to Fraunhofer-Gesellschaft Zentrale-Hauptabteilung Personal z.H. Frau Rabel Kekulestr. 7 12489 Berlin Germany From doya at irp.oist.jp Fri Sep 3 06:54:16 2004 From: doya at irp.oist.jp (Kenji Doya) Date: Fri, 3 Sep 2004 19:54:16 +0900 Subject: Okinawa Computational Neuroscience Course -- Final Call for Applications In-Reply-To: <6758E810-DBFA-11D8-8D2A-000A95C0CA8A@irp.oist.jp> References: <6758E810-DBFA-11D8-8D2A-000A95C0CA8A@irp.oist.jp> Message-ID: <999C8EAE-FD97-11D8-9A96-000D93C06A16@irp.oist.jp> Dear Connectionists, Many people asked us about the attendance fee of Okinawa Computational Neuroscience Course. Fortunately, there will be no attendance fee; the sponsor will provide the airfare to Okinawa and local expenses for accepted students. Please find below the updated list of speakers. Application deadline is September 10th. Best wishes, Kenji Doya ************************************************************************ Call for Applications OKINAWA COMPUTATIONAL NEUROSCIENCE COURSE Bayesian Brain: Probabilistic Approaches to Neural Coding and Learning November 9-19, 2004. Okinawa, Japan. http://www.irp.oist.jp/ocnc Application deadline: September 10th, 2004 The aim of Okinawa Computational Neuroscience Course is to provide opportunities for young researchers with theoretical backgrounds to learn up-to-date neurobiological findings, and those with experimental backgrounds to have hands-on experience in computational modeling. We invite graduate students and postgraduate researchers to participate in the course, to be held from November 9th through 19th at Bankoku Shinryokan, a seaside conference facility that hosted 2000 Okinawa Summit. The sponsor will provide lodging at the adjacent beach resort, The Busena Terrace, and support for travel to Okinawa. The special topic for this year's course is "Bayesian Brain: Probabilistic approaches to neural coding and learning." Lectures by leading theoretical and experimental neuroscientists will be given in the morning and evening, and the afternoon will be open for free discussions and student projects. Each student will give a short presentation of his/her current work at the beginning of the course and present the summary of his/her project work at the end of the course. Those interested in attending the course should send the materials below by the course web page, e-mail, or postal mail to the course secretariat by SEPTEMBER 10TH. We will accept 30 students by considering the matching of each student's background and motivation to the course content, and also by considering the balance of members' research disciplines, geographic origins, and genders. This course is the second of the tutorial courses sponsored by the Cabinet Office of the Japanese government as a precursory activity for Okinawa Institute of Science and Technology. We hope that this course will be a good opportunity for theoretical and experimental neuroscientists to meet together and to explore the attractive nature and culture of Okinawa, the southernmost island prefecture of Japan. ******** Okinawa Computational Neuroscience Course (OCNC 2004) Bayesian Brain: Probabilistic Approaches to Neural Coding and Learning Date: November 9th to 19th, 2004 Place: Bankoku Shinryo-kan (http://www.shinryokan.com) Lodging: The Busena Terrace (http://www.terrace.co.jp) Sponsor: Okinawa Institute of Science and Technology Project, Cabinet Office, Japan Co-sponsors: Japanese Neural Network Society Center of Excellence Program, Tamagawa University Center of Excellence Program, Kyushu Institute of Technology Advisory Board: Sydney Brenner, Salk Institute Masao Ito, RIKEN Brain Science Institute Terrence Sejnowski, Salk Institute Susumu Tonegawa, MIT Torsten Wiesel, Rockfeller University Co-organizers: Kenji Doya, Initial Research Project, OIST Shin Ishii, Nara Institute of Science and Technology Alexandre Pouget, University of Rochester Rajesh Rao, University of Washington CONFIRMED LECTURES (titles with * are tentative) Theoretical Foundations Kevin Murphy (MIT): Bayesian inference and learning* Shun-ichi Amari (RIKEN BSI): Statistical approach to neural learning and population coding Neurobiological Foundations Adrienne Fairhall (Washington U.): Spike coding Alexandre Pouget (U. of Rochester): Population coding Barry Richmond (NIH): Neural coding* Computational Modeling Anthony Bell (Redwood Neurosci. Inst.): Unsupervised machine learning with spike timings Peter Latham (Gatsby Comp. Neuro. Unit): Computing with population codes Wolfgang Maass (T. U. Graz): Liquid state machine* Bruno Olshausen (U. C. Davis): Representing what and where in time-varying images Rajesh Rao (U. of Washington): Bayesian computation in cortical networks* Emanuel Todorov (U. C. San Diego): Optimality principles in sensorimotor control Richard Zemel (U. of Toronto): Coding and decoding uncertainty Experimental Approaches Karl Friston (UCL): Dynamic causal modeling David Knill (U. of Rochester): Bayesian models of sensory cue integration Konrad Koerding (UCL): Bayesian combination of priors and perception Tai-Sing Lee (Carnegie Mellon U.): Hierarchical Bayesian inference in visual cortex Jonathan Pillow (New York U.): Estimationg neuron models from spike trains* Michael Shadlen (U. of Washington): Decision making* APPLICATION Please send the following through the web application page (http://www.irp.oist.jp/ocnc/), e-mail (ocnc at irp.oist.jp), or postal mail to the secretariat below. 1) Name, 2) Date of birth, 3) Gender, 4) Nationality, 5) Affiliation, 6) Postal address, 7) Phone, 8) Fax, 9) E-mail, 10) Web page URL (if any), 11) Educational background, 12) Work experience, 13) List of publications, 14) Research interests (up to 500 words), 15) Motivations for attending the course (up to 500 words), 16) Two letters of recommendation. The items 11) to 14) can be replaced by a CV. Letters of recommendation should be sent directly to the secretariat from the referee by e-mail or postal mail. Please note the names, affiliations, and e-mail addresses of the referees in the application. There will be no attendance fee. The sponsor will provide lodging, meals, and travel support for accepted students. SECRETARIAT Okinawa Computational Neuroscience Course c/o Initial Research Project Okinawa Institute of Science and Technology 12-22 Suzaki, Gushikawa Okinawa 904-2234, Japan Phone: +81-98-921-3795 Fax: +81-98-934-1401 E-mail: ocnc at irp.oist.jp For more information, please visit the web page: http://www.irp.oist.jp/ocnc ************************************************************************ ---- Kenji Doya Initial Research Project, Okinawa Institute of Science and Technology 12-22 Suzaki, Gushikawa, Okinawa 904-2234, Japan Phone:+81-98-921-3843; Fax:+81-98-921-3873 http://www.irp.oist.jp/ From W.Wiegerinck at science.ru.nl Fri Sep 3 08:09:58 2004 From: W.Wiegerinck at science.ru.nl (Wim Wiegerinck) Date: Fri, 03 Sep 2004 14:09:58 +0200 Subject: phd and postdoc postion at SNN Nijmegen Message-ID: <41385F16.7060009@science.ru.nl> PhD student and postdoc position available at SNN Nijmegen. SNN Nijmegen is a research group dedicated to fundamental research in the areas of machine learning and computational neuroscience. Specific topics are Bayesian networks, approximate inference methods, time-series modeling, bio-informatics, expert systems, stochastic control and collaborative decision making. The group consists currently of 8 researchers and three programmers. In our group, we have two positions available that can be filled at either the PhD student level or at the postdoc level. See the job anouncements at http://www.mbfys.kun.nl/snn/nijmegen/index.php3?page=29 The requirement for the PhD student position is a completed university degree in physics, mathematics or computer science. The position is full-time for a period of 4 years. The requirement for the postdoc position is a PhD and publications on one of the above research topics. The postdoc position is full-time for a period of 2.5 years. For more information see www.snn.kun.nl/nijmegen or contact dr. H.J. Kappen (bert at snn.kun.nl, +31(0)24 3614241), or dr. W. Wiegerinck (wimw at snn.kun.nl). Applications should contain a complete CV, a brief description of his or her research interests and a copy of a recent publication or dissertation (optional). Send your application before October 1 2004 either by email to dr. H.J. Kappen (bert at snn.kun.nl) and dr. W. Wiegerinck (wimw at snn.kun.nl) or by ordinary mail to SNN, Radboud University Nijmegen, Geert Grooteplein 21, 6525 EZ Nijmegen, the Netherlands. From r.w.clowes at sussex.ac.uk Sun Sep 5 13:22:53 2004 From: r.w.clowes at sussex.ac.uk (Robert Clowes) Date: Sun, 5 Sep 2004 18:22:53 +0100 Subject: CFP : Next Generation approaches to Machine Consciousness: Imagination, Development, Intersubjectivity, and Embodiment. Message-ID: Next Generation approaches to Machine Consciousness: Imagination, Development, Intersubjectivity, and Embodiment. University of Hertfordshire, Hatfield, UK, 12th - 13th April, 2005 *** Submission Deadline: 31st October 2004 *** 1st Call for Papers for: Submissions are invited for presentation at a two-day symposium as part of the AISB 2005 Convention on Social Intelligence and Interaction in Animals, Robots and Agents (12-15 April, University of Hertfordshire, de Havilland Campus, Hatfield, England). ** Scope ** Machine Consciousness (MC) concerns itself with the study and creation of artefacts which have mental characteristics typically associated with consciousness such as (self-) awareness, emotion, affect, phenomenal states, imagination, etc. Recently, developments in AI and robotics, especially through the prisms of behavioural and epigenetic robotics, have stressed the embodied, interactive and developmental nature of intelligent agents which are now regarded by many as essential to engineering human-level intelligence. Some recent work has suggested that giving robots imaginative or simulation capabilities might be a big step towards achieving MC. Other studies have emphasized 'second person' issues such as intersubjectivity and empathy as a substrate for human consciousness. Alongside this, the infant-caregiver relationship has been recognised as essential to the development of consciousness in its specifically human form. Until now, most have considered these issues as, at best, tangential to the creation of artificial consciousness. This symposium proposes to bring them into greater focus and explore the contribution such work might make to next generation approaches to MC. Submissions are especially invited on the following topics in their relation to MC: * Imagination * Development * Enactive Approaches * Heterophenomenology * Synthetic Phenomenology * Intersubjectivity * Ethics * General aspects (techniques, theories, constraints) See http://www.sussex.ac.uk/cogs/mc-background for more information. Preference will be given to submissions that are: * Relevant: closely related to the themes of the symposium * Implemented: based on working robotic or other implemented systems * Novel: not previously presented elsewhere However, it is not expected that all accepted submissions will meet all three criteria of preference. ** Symposium Dates ** Symposium will be held on the 12 and 13th April 2005 as part of the AISB,05 Convention. ** 1 September 2004: First CFP distributed. ** 31 October 2004: Submissions due by this date. ** 22 November 2004: Notification of accepted papers will be sent out. ** 17 December 2004: camera ready copies due (for inclusion in AISB proceedings) ** 14 January 2005: early registration deadline (NB symposium attendees must register for the full convention) ** 12-15 April 2005: AISB 2005 convention ** Publication ** The Chairs intend to publish the proceedings of the Symposium in a book or journal special issue. ** Symposium Co-Chairs ** Ron Chrisley - Centre for Cognitive Science (COGS), University of Sussex Rob Clowes - Centre for Cognitive Science (COGS), University of Sussex ** Scientific Committee ** Igor Aleksander - Imperial College, UK and COGS Sussex Giovanna Colombetti - York University, Canada Owen Holland - University of Essex, UK Takashi Ikegami - University of Tokyo, Japan Murray Shanahan - Imperial College, UK Steve Torrance - Department of Psychology, University of Middlesex, UK and COGS Sussex Tom Ziemke - School of Humanities and Informatics, University of Sk=F6vde, Sweden ** Submissions ** Extended abstracts of not more than 500 words (plus references) should be submitted in plain text to : Rob Clowes Centre for Research in Cognitive Science. University of Sussex Falmer BN1 9QH United Kingdom +44 (0)1273 638317 Email : robertc at cogs.susx.ac.uk (please note '@' should be inserted for ' at '. This is as an attempt to avoid spam). Organised in association with the AISB (The Society for the Study of Artificial Intelligence and the Simulation of Behaviour) From dsmith06 at maine.rr.com Wed Sep 8 08:01:32 2004 From: dsmith06 at maine.rr.com (David Smith) Date: Wed, 8 Sep 2004 08:01:32 -0400 (EDT) Subject: Book Announcement - Why We Lie: The Evolutionary Roots of Deception and the Unconscious Mind Message-ID: <008601c4959b$9570e590$0200a8c0@dad> Why We Lie: The Evolutionary Roots of Deception and the Unconscious Mind David Livingstone Smith St. Martin's Press 256 pages Size: 5-1/2 x 8-1/4 $24.95 Hardcover Pub Date: 07/2004 ISBN: 0-312-31039-0 Deceit, lying, and falsehoods lie at the very heart of our cultural heritage. Even the founding myth of the Judeo-Christian tradition, the story of Adam and Eve, revolves around a lie. We have been talking, writing and singing about deception ever since Eve told God, "The serpent deceived me, and I ate." Our seemingly insatiable appetite for stories of deception spans the extremes of culture from King Lear to Little Red Riding Hood, retaining a grip on our imaginations despite endless repetition. These tales of deception are so enthralling because they speak to something fundamental in the human condition. The ever-present possibility of deceit is a crucial dimension of all human relationships, even the most central: our relationships with our very own selves. David Livingstone Smith elucidates the essential role that deception and self-deception have played in human--and non-human--evolution and shows that the very structure of our minds has been shaped from our earliest beginnings by the need to deceive. Smith shows us that by examining the stories we tell, the falsehoods we weave, and the unconscious signals we send out, we can learn much about ourselves and how our minds work. "Smith combines philosophy, psychology and biology to argue for the importance of deception to our identity as human beings." -- Scientists' Bookshelf Monthly "Intriguing" - Psychology Today "Smith presents a lively survey of the many forms of deception practiced by plants, insects, and animals. He then turns to Homo sapiens and offers cogent and provocative analysis of the link between increasingly complex societies, the evolution of the brain, and the need for 'social lies' in the interest of civility...With an 'aha!' moment on every page, Smith's inquiry is stimulating and unsettling" -- Booklist "Smith draws on Darwin's theory of natural selection, kin altruism, and the basics of sociobiology....Presenting an intriguing theory with skill and imagination" -- Library Journal "David Livingstone Smith unearths the roots of self-deception." - Seed "A leap beyond mainstream science proposes how the unconscious mind could drive our everyday mastery of the art of deceit, both of others and ourselves. . . . Deliciously tantalizing, with morality as the Grandest Deceit of them all." --Kirkus Reviews "Self-deception is one of the most powerful ideas in psychology, indeed, in human affairs, and David Smith's Why We Lie is an excellent synthesis of this crucial topic. The biology is up-to-date and accurate, the psychological implications are clearly worked out, and the writing is inviting and accessible." --Steven Pinker author of The Blank Slate and The Language Instinct "David Smith has thoroughly documented and analyzed the ubiquitous human characteristics of deception and self-deception, drawing from the fields of evolutionary biology, ethology, social psychology and cognitive science and bringing the Freudian concept of the unconscious into the behavioral science of the 21st century. This is an engaging, erudite and powerful book, comprehensible to the layperson as well as the academic, and requisite reading for anyone with a serious interest in human nature." -- Irwin Silverman, Ph.D., Emeritus Professor of Psychology and Senior Scholar, York University, Toronto, Canada "David Smith has pulled off a beaut. Freud, Darwin, Machiavelli (and, oh yes, Liz Smith) meet around the poker table of life. Why We Lie is a wonderfully blended cluster of arguments to support the painful truth that we are a species whose skills at deceiving others is matched only by our ability to deceive ourselves." --Arthur S. Reber, author of The Penguin Dictionary of Psychology "Why We Lie is written with snap, panache, and the sort of insights that stop you in your tracks. Its subject--deception, trickery, pulling a fast one, conning other humans and conning ourselves--is critical to understanding the evolution of the human mind. Getting a handle on deception is crucial to understanding the self with which you and I live from second to second every minute of our conscious and our dreaming lives." --Howard Bloom, author of Global Brain and The Lucifer Principle connectionists at cs.cmu.edu From y.demiris at imperial.ac.uk Thu Sep 9 05:33:45 2004 From: y.demiris at imperial.ac.uk (Yiannis Demiris) Date: Thu, 9 Sep 2004 10:33:45 +0100 Subject: CFP: Imitation in Animals and Artifacts Message-ID: Dear all, details about the third interdisciplinary symposium on imitation in animals and artifacts that will take place in Hatfield UK in April 2005 can be found at the symposium's URL: http://www.iis.ee.ic.ac.uk/yiannis/imitation2005.html Contributions describing connectionist models of the mechanisms underlying imitation skills, and learning by observation are welcome. The deadline for submissions of papers is the 31st of October 2004. Best wishes, Yiannis --- Dr. Yiannis Demiris Lecturer, Intelligent Systems and Networks Group Department of Electrical and Electronic Engineering, Imperial College London, SW7 2BT, London, UK Tel: +44 (0) 2075946300, Fax: +44 (0) 2075946274 http://www.iis.ee.ic.ac.uk/yiannis From whorstma at uni-bielefeld.de Thu Sep 9 09:27:31 2004 From: whorstma at uni-bielefeld.de (whorstma@uni-bielefeld.de) Date: Thu, 09 Sep 2004 15:27:31 +0200 Subject: "Brains, Minds and Media" -- open access eJournal -- call for participation Message-ID: <3f009e3ef192.3ef1923f009e@uni-bielefeld.de> =========================CALL FOR PARTNERS & SUBMISSIONS ========================="Brains, Minds & Media" eJournal of New Media in Neural and Cognitive Science Education ========================= It is the main aim of this novel open-access eJournal to provide peer-reviewed articles and interactive/visual media for education in the neural and cognitive sciences ranging from the advanced school level to all areas of higher education. We seek to ... ... assure citability, content quality and accessibility of your materials through peer-reviewed publication ... adequately represent knowledge beyond papers and textbooks with visualizations and interactive media ... promote an intelligible and serious understanding of neural and cognitive concepts We encourage combined submission of a mandatory short paper and (optional) elaborated, high-quality media (visualizations, simulations, tutorials and the like), which may be browser-ready, but can also be proprietary. Papers on the use and effect of new media in the neural and cognitive sciences and reviews are also welcome. The E-Journal will be open-access, internationally peer-reviewed and initially free of page charge thanks to funding program "Digital Peer Publishing" of the state government NRW, Germany. Sustainable and maintained infrastructure (hard- and software) and permanent administrative manpower is provided through library services (see 'Partners'). The in-house work is fostered by several researchers at Bielefeld University with experience international editorial boards from the fields of Neurobiology, Biological Cybernetics, Biorobotics and Neuroinformatics. We are now to build the international group of supporters and co-workers and prepare an initial issue. We call for your participation! *****CALL***** Please express your interest with an informal eMail (see ?contact?) if you can contribute as ... * AUTHOR if you have visualizations, simulations and the like, which are well-tried in your scientific talks or lessons and can submit a short paper on background and application. (No processing charge for early submissions, guidelines available) * EDITOR / REVIEWER if you have a clear view on a specific section of the neural and/or cognitive sciences, a dedication for visualizations and simulation and can help to process submissions in reviewing. (Professional workflow software for the editorial is already set up.) * ADVISOR / ADVOCAT if you are experienced member in the scientific community and wish to escort the initiative in strategic development as member of the advisory board or as external consultant. * RECIPIENT if you simply want to be kept informed about the initiative (e.g. Newsletter). CONTACT: The procedure is intentionally informal in the initial phase. Please feel free to send a noncommittal and private eMail to the organizational team with the area(s) of interest indicated. For arranging possible next steps, we will come to you with further information. Corresponding eMail: wolfram.horstmann at uni-bielefeld.de Thank you! Your organizational team, Wolfram Horstmann and Soeren Lorenz FURTHER PARTNERS * Bielefeld University Library * University Library Centre "HBZ" of State Government NRW, Germany * Initiative "Digital Peer Publishing" State Government NRW, Germany (funding) From kdharris at andromeda.rutgers.edu Wed Sep 8 18:11:24 2004 From: kdharris at andromeda.rutgers.edu (Ken Harris) Date: Wed, 8 Sep 2004 18:11:24 -0400 Subject: Assistant Professorship in Neuroscience at Rutgers Newark Message-ID: <000401c495f0$c7835860$7db5e6a5@rutgers.edu> The Center for Molecular and Behavioral Neuroscience at Rutgers-Newark has announced an opening for an Assistant Professor, tenure-track faculty position in Behavioral/Cognitive Neuroscience. The Center is primarily dedicated to research and graduate training. We seek a mature candidate with a clear research agenda focused on fundamental questions that link brain and behavior. The candidate should be ready to run an independent laboratory, train graduate students and postdoctoral fellows, and attract substantial independent external funding. Further details on our facilities, faculty, and training programs can be found at http://www.cmbn.rutgers.edu. Local resources include state-of-the art animal labs, human testing facilities, computer facilities and a 3T Siemens Allegra fMRI (see http://www.rutgers-newark.rutgers.edu/fmri/). There is excellent access to a wide variety of neuropsychological, neurological, and psychiatric patient populations of all ages through ongoing cooperative relationships with our medical school and other clinical facilities in nearby northern New Jersey and New York City. Close connections with the CNS research divisions of the extensive New Jersey pharmaceutical industry provides additional opportunities for collaboration and support. Our campus is located in Northern New Jersey, in downtown Newark, just 13 miles -- and 20 minutes -- from midtown Manhattan. Extensive commuter rail lines make is feasible to live either in New York City or in the suburbs or rural areas of New Jersey. Five minutes from the downtown Newark train station, the campus is part of the five-university University Heights section of town with over 10,000 undergraduate and graduate students. Further information at http://www.newark.rutgers.edu/. The Integrative Neuroscience Ph.D. Program is a multidisciplinary program whose strengths range from molecular neurobiology through cognitive neuroscience. Emphasizing the integrative understanding of the links between brain and behavior, the program includes faculty from both Rutgers University - Newark and our medical school, the University of Medicine and Dentistry of New Jersey (UMDNJ). For more information, see http://www.ins.rutgers.edu. To apply, send CV, three letters of references and statement of research goals to: Dr. Paula Tallal, Co-Director, Center for Molecular & Behavioral Neuroscience, Rutgers University - Newark. 197 University Avenue, Newark, New Jersey 07102. For additional information, feel free to contact Dr. Tallal at tallal at axon.rutgers.edu. ------------------------ Kenneth D. Harris, Ph.D. Assistant Professor Center for Molecular and Behavioral Neuroscience Rutgers, The State University of New Jersey 197 University Avenue Newark NJ 07102, USA phone: 973 353 1080, x3331 fax: 973 353 1272 email: kdharris at andromeda.rutgers.edu web: http://qneuro.rutgers.edu From juergen at idsia.ch Fri Sep 10 05:09:25 2004 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Fri, 10 Sep 2004 11:09:25 +0200 Subject: Jobs for postdocs & PhD students at IDSIA (Switzerland) & TU Munich (Germany) Message-ID: <41416F45.6020304@idsia.ch> We are seeking outstanding postdocs and PhD students for research on learning robots. Details: http://www.idsia.ch/~juergen/jobstrep2004.html http://www.idsia.ch/~juergen/bat2004.html (Interviews possible at ANNIE 2004, Nov 7-10, St Louis) Juergen Schmidhuber http://www.idsia.ch/~juergen/ From nnrev at atr.co.jp Fri Sep 10 04:22:44 2004 From: nnrev at atr.co.jp (Neural Networks Editorial Office) Date: Fri, 10 Sep 2004 17:22:44 +0900 Subject: Neural Networks 17(7) Message-ID: NEURAL NETWORKS 17(7) Contents - Volume 17, Number 7- 2004 ------------------------------------------------------------------ ***** Psychology and Cognitive Science ***** Oscillatory model of attention-guided object selection and novelty detection Roman M. Borisyuk, Yakov B. Kazanovich ***** Neuroscience and Neuropsychology ***** Impact of deviation from precise balance of spike-timing-dependent plasticity Narihisa Matsumoto, Masato Okada ***** Mathematical and Computational Analysis ***** Learning to generate combinatorial action sequences utilizing the initial sensitivity of deterministic dynamical systems Ryu Nishimoto, Jun Tani Reliability of internal prediction/estimation and its application. I. Adaptive action selection reflecting reliability of value function Yutaka Sakaguchi, Mitsuo Takano Binocular disparity encoding cells generated through an Infomax based learning algorithm Kenji Okajima Analysis of perfect mappings of the stimuli through neural temporal sequences Francisco B. Rodri'guez, Ramo'n Huerta, Modeling of growing networks with directional attachment and communities Masahiro Kimura, Kazumi Saito1, Naonori Ueda When is approximation by Gaussian networks necessarily a linear process? H.N. Mhaskar A recurrent neural network with exponential convergence for solving convex quadratic program and related linear piecewise equations Youshen Xia, Gang Feng, Jun Wang Boundedness and stability for nonautonomous cellular neural networks with delay Mehbuba Rehim, Haijun Jiang, Zhidong Teng An analysis of exponential stability of delayed neural networks with time varying delays Sabri Arik CURRENT EVENTS ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 (regular) SEK 660 Y 13,000 Neural Networks (plus Y 2,000 enrollment fee) $20 (student) SEK 460 Y 11,000 (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- membership without $30 SEK 200 not available to Neural Networks non-students (subscribe through another society) Y 5,000 student (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- Name: _____________________________________ Title: _____________________________________ Address: _____________________________________ _____________________________________ _____________________________________ Phone: _____________________________________ Fax: _____________________________________ Email: _____________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number ____________________________ expiration date ________________________ INNS Membership International Neural Network Society 7600 Terrace Avenue, Ste. 203 Middleton WI 53562 608-831-0584, ext. 138 (phone) 608-831-5122 (fax) srees at reesgroupinc.com ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership c/o Professor Shozo Yasui Kyushu Institute of Technology Graduate School of Life Science and Engineering 2-4 Hibikino, Wakamatsu-ku Kitakyushu 808-0196 Japan 81 93 695 6108 (phone and fax) jnns at brain.kyutech.ac.jp http://www.jnns.org/ ---------------------------------------------------------------------------- From r.kempter at biologie.hu-berlin.de Fri Sep 10 06:32:39 2004 From: r.kempter at biologie.hu-berlin.de (Richard Kempter) Date: Fri, 10 Sep 2004 12:32:39 +0200 Subject: Berlin Autumn School LEARNING AND MEMORY, Oct 11-13, 2004 Message-ID: <20040910103239.GA18603@pauling.biologie.hu-berlin.de> Announcement, program, and call for participation: Berlin Autumn School LEARNING AND MEMORY: MOLECULAR MECHANISMS - CELLULAR PROCESSES - MATHEMATICAL MODELS October 11-13, 2004 Berlin, Germany Learning and memory are central ingredients for proper biological function in changing environments. Both processes are of particular importance for neuroscience but they also play a significant role in other biological disciplines. This autumn school focuses on the basic molecular and cellular processes underlying learning and memory in neural systems, with emphasis on synaptic plasticity. Experimental approaches will be discussed in close relation with the corresponding mathematical models, both at an introductory level. The last day of the school will bridge between the physiological and behavioral level and also touch on learning and memory in the immune system. PROGRAM Monday, October 11: 8:30 - 9:00 Arrival 9.00 - 9:15 Opening of the Autumn School 9.15 - 10.45 Dietmar Schmitz (NWFZ, Charite) Cellular processes of learning and memory: Development & current state of concepts and experiments (I) 11.15 - 12.45 Andreas Herz (ITB, HU Berlin) Modelling short-term synaptic plasticity with differential equations and iterated maps (I) 15.15 - 16.45 Dietmar Kuhl (Neurobiology, FU Berlin) Molecular and cellular mechanisms of learning and memory (I) 17.15 - 18.45 Hanspeter Herzel (ITB, Charite) Modelling molecular signal transduction chains and networks 19.00 - Reception and Dinner Tuesday, October 12: 9.15 - 10.45 Dietmar Schmitz (NWFZ, Charite) Cellular processes of learning and memory: Development & current state of concepts and experiments (II) 11.15 - 12.45 Andreas Herz (ITB, HU Berlin) Modelling short-term synaptic plasticity with differential equations and iterated maps (II) 15.15 - 16.45 Dietmar Kuhl (Neurobiology, FU Berlin) Molecular and cellular mechanisms of learning and memory (II) 17.15 - 18.45 Laurenz Wiskott (ITB, HU Berlin) Modelling learning and memory: The systems level Wednesday, October 13: 9.15 - 10.15 Dietmar Schmitz (NWFZ, Charite) Short- and long-term plasticity of the mossy fiber synapse 10.15 - 11.15 Richard Kempter (ITB, HU Berlin) Hippocampal plasticity: Learning behavioral sequences 11.45 - 12.45 Andreas Radbruch (DRFZ, Berlin) Learning and memory in the immune system 15.15 - 16.15 Gerd Kempermann (Max Delbrueck Center, Berlin) Adult neurogenesis 16.15 - 17.15 Livia de Hoz (Neurophysiology, Charite) Memory consolidation 17.45 - 19.15 Andreas Herz (ITB, HU Berlin) The Hebbian memory trace: New insight from bee olfaction LOCATION: Lecture Hall 12, Department of Biology, Humboldt-Universitaet zu Berlin, Invalidenstrasse 43, 10115 Berlin-Mitte. REGISTRATION: E-mail to Richard Kempter before October 4: r.kempter at biologie.hu-berlin.de The registration fee of 30 Euro (students 15 Euro) is to be paid upon arrival and includes the buffet on Monday (Oct 11) evening. For details, please visit: http://itb.biologie.hu-berlin.de/events/memory.html PDF poster of this announcement: http://itb.biologie.hu-berlin.de/~kempter/berlin_autumn_school/learning_and_memory_2004.pdf -- The autumn school on "Learning and Memory" is organized by the DFG Collaborative Research Center ("Sonderforschungsbereich", SFB 618) "Theoretical Biology: Robustness, Modularity, and Evolutionary Design of Living Systems" Humboldt-Universitaet zu Berlin Department of Biology Invalidenstrasse 43 10115 Berlin, Germany http://www.biologie.hu-berlin.de/forschung/SFB_618/ From zoubin at gatsby.ucl.ac.uk Sat Sep 11 11:04:47 2004 From: zoubin at gatsby.ucl.ac.uk (Zoubin Ghahramani) Date: Sat, 11 Sep 2004 16:04:47 +0100 Subject: AISTATS 2005 Submission Deadline Extended (Sep 28) Message-ID: <16707.5135.885494.592287@wald.gatsby.ucl.ac.uk> ---------------------------------------------------------------------- Call for Papers Submission Deadline Extended: Sep 28th AISTATS 2005 Tenth International Workshop on Artificial Intelligence and Statistics January 6-8, 2005, The Savannah Hotel, Barbados http://www.gatsby.ucl.ac.uk/aistats/ Submission Deadline: September 28, 2004 ---------------------------------------------------------------------- This is the tenth workshop on Artificial Intelligence and Statistics, an interdisciplinary gathering of researchers at the intersection of computer science, statistics, and related areas. Since its inception in 1985, the primary goal of this workshop has been to broaden research in both of these fields by promoting the exchange of ideas between them. We encourage the submission of all papers which are in keeping with this objective. Presentations will include invited talks, contributed talks, and posters. Papers for poster sessions will be treated equally with papers for presentation in the publication. Submission Requirements: ------------------------- Electronic submission of papers is required. The papers (up to 8 pages in length) should be submitted through the AI and Statistics Conference Management page. See: http://www.gatsby.ucl.ac.uk/aistats/submit.htm Submissions will be considered if they are received by 11:59 PM September 28, 2004, Pacific Daylight Time. Acceptance notices will be emailed by November 3, 2004. Final papers (up to 8 pages, double column) must be received by November 24, 2004. These papers will be made available on the web, published in the proceedings, and distributed at the workshop in electronic form. Invited Speakers ---------------- Craig Boutelier (University of Toronto) Nir Friedman (Hebrew University) Tommi Jaakkola (MIT) Steffen Lauritzen (University of Oxford) Tom Minka (Microsoft Research) Program Chairs: ---------------- Robert Cowell, Actuarial Science and Statistics, City University, London Zoubin Ghahramani, Gatsby Unit, University College London From special at math.unipd.it Mon Sep 13 09:50:38 2004 From: special at math.unipd.it (Login per Congresso Alessandro Sperduti) Date: Mon, 13 Sep 2004 15:50:38 +0200 (CEST) Subject: reminder: call for papers Message-ID: ************************* R E M I N D E R ************************** C A L L F O R P A P E R S Special Issue of Neural Networks on Neural Networks and Kernel Methods for Structured Domains Co-editors:Barbara Hammer, Craig Saunders, Alessandro Sperduti (http://www.informatik.uni-osnabrueck.de/barbara/specialNN/) >>>>> Deadline for submission October 11, 2004 <<<<< ---------------------------------------------------------------------- In recent years several researchers have started to consider the adaptive processing of structured data. This interest is motivated by two main reasons: i) several very important computational problems in Bioinformatics, Chemistry, document classification and filtering (just to name a few), require the use of some Machine Learning procedure to be properly treated because their complexity does not allow a formal and precise definition of the problem and thus no algorithmic solution to the problem is known; on the other hand experimental data is available and usable by a Machine Learning approach; ii) in many of the above problems, the objects of interest are more naturally represented via varying-size structured representations, such as sequences, strings, trees, directed or undirected graphs. Moreover, it is commonly believed that any computational process representing these objects via flat fixed-size vectorial representations, risks to discard structural information relevant for solving the task at hand. The aim of the special issue is to bring together recent works developed mainly into the fields of Recurrent and Recursive Neural Networks, and Kernel Methods, with the hope to function as a conceptual support for the improvement of current technologies and the growth of new integrated methodologies for learning in structured domains. TOPICS: Recurrent and Recursive Neural Networks, Self-Organizing Maps for Structures, Support Vector Machines and Kernel Methods for Structured Domains, Fisher Kernels, Probabilistic Models for Structured Domains, Applications of the above methods to Structured Domains, other relevant topics. ---------------------------------------------------------------------- I M P O R T A N T D A T E S Deadline for submission October 11, 2004 Notification of acceptance: March 14, 2005 Deadline for final paper: June 6, 2005 ---------------------------------------------------------------------- P A P E R S U B M I S S I O N Format: http://www.informatik.uni-osnabrueck.de/barbara/specialNN/ Papers must be submitted in electronic form (either Postscript or PDF) to the following e-mail address: specialNN.structure at math.unipd.it Hard-paper submissions are accepted only if the authors do not have access to electronic facilities, and should be mailed to the following address: Prof. Alessandro Sperduti Dipartimento di Matematica Pura ed Applicata Via Belzoni 7 35131 Padova ITALY ---------------------------------------------------------------------- From DGB at CDRH.FDA.GOV Sat Sep 11 10:31:28 2004 From: DGB at CDRH.FDA.GOV (Brown, David G.) Date: Sat, 11 Sep 2004 10:31:28 -0400 Subject: Call for Special Session Proposals - IJCNN'05 Message-ID: <60E5EBF1DFB4EC498E0ACAE75A49F8ED0C4509E7@DRM558.CDRH.FDA.GOV> Call for Special Session Proposals International Joint INNS-IEEE Conference on Neural Networks (IJCNN) 2005 Hilton Bonaventure Hotel Montreal, Quebec, Canada July 31- August 4, 2005 (IJCNN 2005) The IJCNN 2005 Organizing Committee invites proposals for special sessions to be held during the conference (http://faculty.uwb.edu/ijcnn05 ), taking place July 31- August 4, 2005, in Montreal. Each special session proposal should be well motivated and should consist of 4 to 6 papers. Each paper must have the title, authors with e-mails/web sites, and as detailed an abstract as possible. The special session organizer(s) contact information should also be included. All special session organizers must obtain firm commitments from their special session presenters and authors to submit papers or extended abstracts in a timely fashion (if the special session is accepted) and, of course, present them at the IJCNN 2005. Each special session organizer will be responsible for the quality of the special session papers and manage the review process accordingly. All accepted papers will be published in the IJCNN 2005 Proceedings. Authors who planned papers for special sessions which were not accepted can submit their papers as regular submissions (the deadline is January 31, 2005). Proposals should be submitted in ELECTRONIC FORM to: Fredric Ham, Program Co-Chair Florida Institute of Technology College of Engineering 150 West University Boulevard Melbourne, Florida 32901-6975, U.S.A. phone +1 (321) 674-7124 E-mail: fmh AT fit.edu Important Deadlines November 1, 2004 Special session proposal deadline December 1, 2004 Acceptance notification January 31, 2005 Extended abstracts/full papers due to be submitted through the regular submission site (marked for appropriate special sessions) IMPORTANT! Submissions of full papers for each special session is highly encouraged, but at the minimum extended abstracts (2 to 3 pages in the conference paper format) are required for each presentation at the special session. David David G. Brown, Ph.D. Publicity Chair, IJCNN'05 Center for Devices and Radiological Health (HFZ-140) 12720 Twinbrook Parkway Rockville, MD 20852 301-443-3314 ext. 133 301-443-9101 (fax) david.brown at fda.hhs.gov From d.mareschal at bbk.ac.uk Mon Sep 13 06:01:30 2004 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Mon, 13 Sep 2004 11:01:30 +0100 Subject: Senior Job Opportunity in London Message-ID: Readers of this list may be interested in the following senior job opportunity. PLEASE DO NOT RESPOND TO ME DIRECTLY cheers, Denis ======================================== Faculty of Science Head of School: Reader/Professor in Psychology The School of Psychology (RAE 5) is seeking an exceptional individual to provide strategic leadership for an already successful School, with particular strengths in developmental and cognitive neuroscience, developmental and cognitive psychology, and psychosocial studies. The person appointed will have an established international research reputation, and have demonstrated effective managerial and leadership abilities in an academic or related environment. Tenure is permanent; the post of Head of School is a rotating one and the successful candidate will be expected to fill it for the first four years of their appointment. The post is tenable from 31 March 2005. Salary will be commensurate with qualifications and experience, and level of appointment. Closing date: 1 December 2004 For application forms and further details please see http://www.bbk.ac.uk or send an A4 sae (quoting Ref: APS109), to the Human Resources Team, Birkbeck, Malet Street, Bloomsbury, London, WC1E 7HX or e-mail humanresources at bbk.ac.uk Birkbeck is an Equal Opportunities Employer. -- ================================================= Dr. Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 (0)20 7631-6582/6226 reception: 6207 fax +44 (0)20 7631-6312 http://www.psyc.bbk.ac.uk/people/academic/mareschal_d/ ================================================= From j.v.stone at sheffield.ac.uk Mon Sep 13 07:31:51 2004 From: j.v.stone at sheffield.ac.uk (Jim Stone) Date: Mon, 13 Sep 2004 12:31:51 +0100 Subject: New book: Independent Component Analysis Message-ID: I would like to announce a new book, Independent Component Analysis: A Tutorial Introduction by James V Stone University of Sheffield. Published September 2004 by MIT Press. Price: (pounds) 22.95. For details, see http://www.shef.ac.uk/~pc1jvs/ Contents Part I Independent Component Analysis and Blind Source Separation Chapter 1 Overview of Independent Component Analysis 1.1: Introduction 1.2: Independent Component Analysis: What Is It? 1.3: How Independent Component Analysis Works 1.4: Independent Component Analysis and Perception 1.5: Principal Component Analysis and Factor Analysis 1.6: Independent Component Analysis: What Is It Good For? Chapter 2 Strategies for Blind Source Separation 2.1: Introduction 2.2: Mixing Signals 2.3: Unmixing Signals 2.4: The Number of Sources and Mixtures 2.5: Comparing Strategies 2.6: Summary Part II The Geometry of Mixtures Chapter 3 Mixing and Unmixing 3.1: Introduction 3.2: Signals, Variables, and Scalars 3.3: The Geometry of Signals 3.4: Summary Chapter 4 Unmixing Using the Inner Product 4.1: Introduction 4.2: Unmixing Coefficients as Weight Vectors 4.3: The Inner Product 4.4: Matrices as Geometric Transformations 4.5: The Mixing Matrix Transforms Source Signal Axes 4.6: Summary Chapter 5 Independence and Probability Density Functions 5.1: Introduction 5.2: Histograms 5.3: Histograms and Probability Density Functions 5.4: The Central Limit Theorem 5.5: Cumulative Density Functions 5.6: Moments: Mean, Variance, Skewness and Kurtosis 5.7: Independence and Correlation 5.8: Uncorrelated Pendulums 5.9: Summary Part III Methods for Blind Source Separation Chapter 6 Projection Pursuit 6.1: Introduction 6.2: Mixtures Are Gaussian 6.3: Gaussian Signals: Good News, Bad News 6.4: Kurtosis as a Measure of Non-Normality 6.5: Weight Vector Angle and Kurtosis 6.6: Using Kurtosis to Recover Multiple Source Signals 6.7: Projection Pursuit and ICA Extract the Same Signals 6.8: When to Stop Extracting Signals 6.9: Summary Chapter 7 Independent Component Analysis 7.1: Introduction 7.2: Independence of Joint and Marginal Distributions 7.3: Infomax: Independence and Entropy 7.4: Maximum Likelihood ICA 7.5: Maximum Likelihood and Infomax Equivalence 7.6: Extracting Source Signals Using Gradient Ascent 7.7: Temporal and Spatial ICA 7.8: Summary Chapter 8 Complexity Pursuit 8.1: Introduction 8.2: Predictability and Complexity 8.3: Measuring Complexity Using Signal Predictability 8.4: Extracting Signals by Maximizing Predictability 8.5: Summary Chapter 9 Gradient Ascent 9.1: Introduction 9.2: Gradient Ascent on a Line 9.3: Gradient Ascent on a Hill 9.4: Second Order Methods 9.5: The Natural Gradient 9.6: Global and Local Maxima 9.7: Summary Chapter 10 Principal Component Analysis and Factor Analysis 10.1: Introduction 10.2: ICA and PCA 10.3: Eigenvectors and Eigenvalues 10.4: PCA Applied to Speech Signal Mixtures 10.5: Factor Analysis 10.6: Summary PartIV Applications Chapter 11 Applications of ICA 11.1: Introduction 11.2: Temporal ICA of Voice Mixtures 11.3: Temporal ICA of Electroencephalograms158 11.4: Spatial ICA of fMRI Data 11.5: Spatial ICA for Color MRI Data 11.6: Complexity Pursuit for Fetal Heart Monitoring 11.7: Complexity Pursuit for Learning Stereo Disparity PartV Appendices Appendix A: A Vector Matrix Tutorial Appendix B: Projection Pursuit Gradient Ascent Appendix C: Projection Pursuit: Stepwise Separation of Sources Appendix D: ICA Gradient Ascent Appendix E: Complexity Pursuit Gradient Ascent Appendix F: Principal Component Analysis for Preprocessing Data Appendix G: Independent Component Analysis Resources Appendix H: Recommended Reading From terry at salk.edu Mon Sep 13 22:51:55 2004 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 13 Sep 2004 19:51:55 -0700 (PDT) Subject: NEURAL COMPUTATION 16:10 In-Reply-To: <200408131737.i7DHbKn81419@kepler.snl.salk.edu> Message-ID: <200409140251.i8E2ptP04124@kepler.snl.salk.edu> Neural Computation - Contents - Volume 16, Number 10 - October 1, 2004 LETTERS Understanding the Cortical Specialization for Horizontal Disparity Jenny C. A. Read and Bruce G. Cumming Different Predictions by the Minimum Variance and Minimum Torque-Change Models on the Skewness of Movement Velocity Profiles Hirokazu Tanaka, Meihua Tai, and Ning Qian Disambiguating Visual Motion Through Contextual Feedback Modulation Pierre Bayerl and Heiko Neumann Exact Solution for the Optimal Neuronal Layout Problem Dmitri B. Chklovskii Decoding a Temporal Population Code Philipp Knuesel, Reto Wyss, Peter Koenig and Paul F.M.J. Verschure Minimal Models of Adapted Neuronal Response to In Vivo-Like Input Currents Giancarlo La Camera, Alexander Rauch, Hans-R. Luescher, Walter Senn and Stefano Fusi Including Long-Range Dependence in Integrate-and-Fire Models of the High Interspike-Interval Variability of Cortical Neurons B. Scott Jackson Learning Eigenfunctions Links Spectral Clustering and Kernel PCA Yoshua Bengio, Olivier Delalleau, Nicolas Le Roux, Jean-Francois Paiement, Pascal Vincent and Marie Ouimet ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2004 - VOLUME 16 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $108 $54 $57.78 Individual $95 $101.65 $143 $85 $90.95 Institution $635 $679.45 $689 $572 $612.04 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From chiba at Cogsci.ucsd.edu Tue Sep 14 13:27:07 2004 From: chiba at Cogsci.ucsd.edu (Andrea Chiba) Date: Tue, 14 Sep 2004 10:27:07 -0700 (PDT) Subject: REGISTER NOW! ICDL 2004 Message-ID: THIRD INTERNATIONAL CONFERENCE ON DEVELOPMENT AND LEARNING (ICDL2004) The Salk Institute October 20-23, 2004 San Diego, California http://icdl.cc The ICDL conference brings together leading researchers in neuroscience, machine learning, robotics, and developmental psychology. The goal is to gain new insights about learning and development in biological and artificial systems that have to operate autonomously in the physical and social world. Below is a summary of talks and conference activities. For more information please visit the conference Web Site at http://icdl.cc Wednesday October 20 Tutorials. Pietro Perona: Invited Talk. Alex Pentland: Social Dynamics: The Voice of Power and Influence. Leslie J. Carver: Neural correlates of social referencing. Teresa Farroni, Mark H. Johnson, Gergely Csibra: The perception of direct gaze in human infants. Christof Teuscher, Jochen Triesch: To Care or Not to Care: Analyzing the Caregiver in a Computational Gaze Following Framework. Masato Ito and Jun Tani: Joint attention between a humanoid robot and users in imitation game. Katharina J. Rohlfing, Jannik Fritsch and Britta Wrede: Learning to manipulate objects: A quantitative evaluation of Motionese. Thursday October 21 Dana Ballard: Invited Talk. Frederic Dandurand, Melissa Bowen, Thomas R. Shultz: Learning by Imitation, Reinforcement and Verbal Rules in Problem Solving Tasks. Patricia Zukow-Goldring and Michael Arbib: Caregivers and the Education of the Mirror System James B. Marshall, Douglas Blank, Lisa Meeden: An Emergent Framework for Self-Motivation in Developmental Robotics. Andrew G. Barto, Satinder Singh, Nuttapong Chentanez: Intrinsically Motivated Learning of Hierarchical Collections of Skills. Hidefumi Funakoshi, Wako Yoshida, Shin Ishii: An imaging study on human action selection using hierarchical rules. E. P. Kasten and P. K. McKinley: MESO: Perceptual Memory to Support Online Learning in Adaptive Software. Kaplan, F. and Oudeyer, P-Y.: Neuromodulation and open-ended development. Jay McCLelland: Invited Talk. Rutvik Desai: A Model of Frame and Verb Compliance in Language Acquisition. Karl Pfleger: On-Line Cumulative Learning of Hierarchical Sparse n-grams. Chen Yu and Dana H. Ballard: A Unified Model of Early Word Learning: Integrating Statistical and Social Cues. Arturo E. Hernandez: On Language and Age of Acquisition. Peter Ford Dominey, Jean-David Boucher: Developmental Stages of Perception and Language Acquisition in a Physically Grounded Robot. Friday October 22 Eric Courchesne: Invited Talk. Matthew K Belmonte Simon Baron-Cohen: Small-world Network Properties and the Emergence of Social Cognition: Evidence from Functional Studies of Autism. B.Wicker, B.Hubert, B.Gepner, C.Deruelle: The emotional brain in autism : cerebral correlates of abnormal explicit processing of emotional information. Bill Greenough: Invited Talk. Pawan Sinha: Project PRAKASH: Development of object perception following long-term Visual deprivation. Lingyun Zhang Garrison W. Cottrell: Four Blobs: "Y" or Face? Andrew Lovett, Brian Scassellati: Using a Robot to Reexamine Looking Time Experiments. David Philipona, J. Kevin O'Regan, and Olivier J.-M. D. Coenen: Color perception in sensorimotor theory, or what do we really perceive? Jonathan Nelson, Gary Cottrell, Javier R. Movellan: Explaining Eye Movements During Learning as an Active Sampling Process. Karen Dobkins: Invited Talk Yuichiro Yoshikawa, Koh Hosoda, and Minoru Asada: Cross-anchoring for binding tactile and visual sensations via unique association through self-perception. Jeffrey L. Krichmar, Douglas A. Nitz, Gerald M. Edelman: Object recognition, Adaptive Behavior and Learning in Brain-Based Devices. Terrence Sejnowski: Invited Talk. Saturday October 23 Development of Hiking Abilities at Torrey Pines Park. Development of Golf Skills at the Torrey Pines Golf Course. Learning to Paraglide at the Torrey Pines International Glideport. Learning How To Surf at La Jolla Shores. Learning Ocean Kayaking at La Jolla Shores. From worgott at cn.stir.ac.uk Wed Sep 15 06:17:25 2004 From: worgott at cn.stir.ac.uk (Florentin Woergoetter) Date: Wed, 15 Sep 2004 11:17:25 +0100 Subject: review article on temporal sequence learning Message-ID: <414816B5.9090506@cn.stir.ac.uk> Dear Connectionists, I would like to announce the availability of a review article which could be of broader interest at: http://www.cn.stir.ac.uk/~faw1/Publications/papers/woe_porr_nc2004.pdf Wrgtter, F. and Porr, B. (2004) Temporal sequence learning, prediction and control - A review of different models and their relation to biological mechanisms. Neural Comp. 17, 1-75. Abstract: In this article we compare methods for temporal sequence learning (TSL) across the disciplines machine-control, classical conditioning, neuronal models for TSL as well as spike-timing dependent plasticity. This review will briefly introduce the most influential models and focus on two questions: 1) To what degree are reward-based (e.g. TD-learning) and correlation based (hebbian) learning related? and 2) How do the different models correspond to possibly underlying biological mechanisms of synaptic plasticity? We will first compare the different models in an open-loop condition, where behavioral feedback does not alter the learning. Here we observe, that reward-based and correlation based learning are indeed very similar. Machine-control is then used to introduce the problem of closed-loop control (e.g. actor-critic architectures). Here the problem of evaluative (rewards) versus non-evaluative (correlations) feedback from the environment will be discussed showing that both learning approaches are fundamentally different in the closed-loop condition. In trying to answer the second question we will compare neuronal versions of the different learning architectures to the anatomy of the involved brain structures (basal-ganglia, thalamus and cortex) and to the molecular biophysics of glutamatergic and dopaminergic synapses. Finally we discuss the different algorithms used to model spike-timing dependent plasticity (STDP) and compare them to reward based learning rules. Certain similarities are found in spite of the strongly different time scales. Here we focus on the biophysics of the different Calcium-release mechanisms known to be involved in STDP. best wishes F. Woergoetter From adr at adrlab.ahc.umn.edu Wed Sep 15 16:13:37 2004 From: adr at adrlab.ahc.umn.edu (A David Redish) Date: Wed, 15 Sep 2004 15:13:37 -0500 Subject: Call for Papers: Special issue on navigation Message-ID: <200409152013.i8FKDbvc019067@adrlab.ahc.umn.edu> Call for Papers A Special Issue on Navigation Guest Editor: K.J. Jeffery Biologists and designers of artificial systems share an interest in understanding how mobile agents can not only move around the world in an adaptive manner, but also learn the locations of salient places so that they can return there later. Those who study animal navigation have provided a wealth of data with which to formulate hypotheses about how animals navigate. Roboticists and computational modellers, in turn, have elucidated some of the underlying principles of spatial representation and navigation. Nevertheless, convincing models of animal navigation remain elusive, as do useful artificial navigation systems. This issue aims to bring to the fore some of the most important questions from both domains. Key research issues and topics in the area include: - The evolution of navigation - Navigation across different scales - How are places represented? - Representing and reaching a goal - The problem of multiple goals - Planning trajectories - Shortcutting and detours - Navigating in featureless environments - Interactions between multiple navigation systems - Is there a geometric module in animals? - Multisensory integration - Spatial learning The main aims of this special issue are to approach the theoretical questions pertaining to navigation from a biological perspective. Contributions are encouraged both from biologists with an interest in the theoretical implications of biological data, and from designers of artificial navigational systems (including computer models and robots). Papers may be straightforwardly computational or more theoretical, and presentation of new experimental data is welcomed. Submission Instructions Manuscripts, either full papers or shorter research notes (up to 4000 words), following the Connection Science guidelines http://www.tandf.co.uk/journals/authors/ccosauth.asp) should be emailed to the guest editor by October 14, 2004. Reviews will be completed by December 1, 2004, and final drafts will be accepted no later than February 28, 2005. Guest Editor K.J. Jeffery Department of Psychology University College London 26 Bedford Way London WC1H OAP UK Tel/Fax: +44 (0) 207 679 5308 E-mail: k.jeffery at ucl.ac.uk Web: http://www.psychol.ucl.ac.uk/people/profiles/jeffery_kate.htm Special Editorial board Simon Benhamou, Behavioural Ecology Group, Centre d'Ecologie Fonctionelle et Evolutive, CNRS, Montpelier, France Michael Hasselmo, Department of Psychology, Center for Memory and Brain and Program in Neuroscience, Boston University, Boston, USA David Redish, Department of Neuroscience, University of Minnesota, Minneapolis, USA Matthew Shapiro, Fishberg Research Center for Neurobiology, Kastor Neurobiology of Aging Laboratories, Mount Sinai School of Medicine, New York, USA. From AEL at zurich.ibm.com Tue Sep 14 04:50:10 2004 From: AEL at zurich.ibm.com (Andre Elisseeff) Date: Tue, 14 Sep 2004 10:50:10 +0200 Subject: 1 PhD/1 Post Doc position - IBM Research Lab - Zurich Message-ID: PhD/Post Doc position - IBM Research Lab - Zurich, Switzerland. Algorithm Design for Sequential Decision Making Systems. The machine learning team of the IBM Research Lab in Zurich is looking for students for one PhD position and one Post-doc position in the area of machine learning, artificial intelligence, statistics, and/or related fields. The candidate would work on designing and developing new approaches for sequential/temporal data with applications to marketing and medical data analysis. She/he will be integrated in a scientific environment where academic publications and real data analysis are the main activities. It is expected that the candidate has a strong understanding of advanced statistical algorithms and is ready to get into the implementation of the techniques that she/he will develop in the group. The IBM Research Lab in Zurich is located in Rueschlikon (15min. away from the center of Zurich). The official language of the lab is English. See www.zurich.ibm.com for more information about the lab and its surroundings. -- Introduction to the research topic: -- With the advent of the information technology era, companies and institutions have recorded a lot of data: hospitals have gathered historical records of patients with the evolution of their disease, web companies are monitoring how visitors move from pages to pages, even video game programmers start to look at how players interact with the game. In all those situations, the data is used to analyze how the patient, the visitor or the gamer will react to some action/decision that the doctor/company or game might make. As the number of records and the complexity of real problems increase, this analytical process tends to be performed more and more by machines. This has led to the invention of sequential decision making techniques which use a database of historical records to build a statistical model of the environment (e.g. patient, visitor or gamer) and to find the optimal set of actions to be taken in the future. Although such techniques have been used in a large domain of applications, no generic solution can be taken off the shelves. Designing sequential decision making algorithms that can take into account application specific constraints is an ongoing research subject and is the main topic of our team. -- Please send your application by email (C.V. including a cover letter) to: Andre Elisseeff (ael at zurich.ibm.com) Abderrahim Labbi (abl at zurich.ibm.com) IBM Research Lab, Zurich Saumerstrasse 4, CH-8803 Rueschlikon -- Closing date for all applications by email or post: Friday 29th October 2004. -- Note: the starting dates of the positions will be defined according to the candidate's possibilities. Andre Elisseeff From maass at igi.tu-graz.ac.at Tue Sep 14 06:17:00 2004 From: maass at igi.tu-graz.ac.at (Wolfgang Maass) Date: Tue, 14 Sep 2004 12:17:00 +0200 Subject: Workshop on Biologically Inspired Computing Message-ID: <4146C51C.4030604@igi.tu-graz.ac.at> ------------------------------------------------------------------------ International Workshop on BIOLOGICALLY INSPIRED COMPUTING November 19 and 20, 2004, at Tohoku University, Sendai, Japan ------------------------------------------------------------------------ This workshop has the goal to improve the collaboration between computer scientists and neuroscientists on problems of common interests, such as the investigation of computing and learning in biological neural systems, and the design of biologically inspired computing machinery with autonomous learning capability. Apart from invited talks and tutorials, there will also be sessions for the presentation of some submitted papers. This meeting will be quite informal. It is hoped that this workshop will develop into series of annual joint-meetings of computer scientists and neuroscientists. Papers presented at this workshop will be made publicly available on a webpage. If there exists sufficient interest we will also publish a book or special issue of a journal with selected papers from this workshop. Invited talks will be presented by Kazuyuki Aihara (The University of Tokyo, Japan http://www.sat.t.u-tokyo.ac.jp/index.html) Jianfeng Feng (Sussex University, UK http://www.cogs.susx.ac.uk/informatics_docs/research/bam/) Shigetoshi Nara (Okayama University, Japan) Rajesh P.N. Rao (University of Washington, USA http://www.cs.washington.edu/homes/rao/) Dan Roth (University of Illinois, USA http://l2r.cs.uiuc.edu/~danr/) Ichiro Tsuda (Hokkaido University, Japan http://www.math.hokudai.ac.jp/~tsuda/) Minoru Tsukada (Tamagawa University, Japan) In addition Wolfgang Maass (http://www.igi.tugraz.at/maass/Welcome.html) will give a tutorial on biologically inspired models of computation. The workshop fee is 20,000 yen which includes admission to the workshop, a copy of the proceedings, a welcome reception on November 18 at Tohoku University, a banquet on November 19 at SENDAI EXCEL HOTEL TOKYU, and two lunches. Please return your registration form attached by November 5, 2004. For more information, contact Email : bic at maruoka.ecei.tohoku.ac.jp URL : http://www.maruoka.ecei.tohoku.ac.jp/bic/ Organizers: Wolfgang Maass (Graz University of Technology, Austria) Akira Maruoka (Tohoku University, Sendai, Japan) ------------------------------------------------------------------------ Paper submissions: Extended abstracts (not exceeding 12 pages) with original new results on the theme of this workshop should be submitted electronically by October 15, to bic at maruoka.ecei.tohoku.ac.jp, including all authors' names, contact author's name, mailing addresses, affiliation and email addresses of all authors. All submissions will be reviewed by referees, and notifications of acceptance will be sent out by October 31. ------------------------------------------------------------------------ Participation in the workshop: There will be a registration fee of 20,000 yen, including admission to the workshop, a copy of proceedings, a welcome reception on November 18 at Tohoku University, a banquet on November 19 at SENDAI EXCEL HOTEL TOKYU, and two lunches. Please return the completed registration form by November 5 to Email: bic at maruoka.ecei.tohoku.ac.jp or Fax : +81-22-263-9413 ------------------------------------------------------------------------- Begin of Registration Form ------------------------------------------------------------------------- International Workshop on BIOLOGICALLY INSPIRED COMPUTING REGISTRATION FORM November 19--20,2004 Aoba Memorial Bldg.,Tohoku University, Sendai, Japan Last Name First Name Middle Name Name as you Want to Appear on Badge Affiliation Mailing Address City State Zip Code Country Phone Fax Email URL Arrival Date Departure Date Payment: We accept payment only by credit card (VISA or MasterCard). Please complete the following information and return to Mail: bic at maruoka.ecei.tohoku.ac.jp or Fax : +81-22-263-9413 Note: Because email is not secure, we recommend you to send your credit card information by Fax. Type of credit card: ____________________________ Credit card number: ____________________________ Expiration date: ____________________________ Print name as shown on credit card: ____________________________ Signature: ____________________________ ------------------------------------------------------------------------- End of Registration Form ------------------------------------------------------------------------- Accommodation: A block of rooms has been reserved for the participants of BIC04. Reservations can be made by simply calling the hotel directly. Please be sure to mention "BIC04" when making reservations by telephone by November 5 to obtain the special rates. SENDAI EXCEL HOTEL TOKYU 2-9-25 Ichiban-cho, Aoba-ku, Sendai-Shi Miyagi, Japan 980-0811 Phone : +81-22-262-2412 Fax : +81-22-262-4109 URL : http://www.tokyuhotels.co.jp Email : sendai at tokyuhotel.co.jp -- Wolfgang Maass Professor of Computer Science Technische Universitaet Graz http://www.igi.tugraz.at/maass/ From esann at dice.ucl.ac.be Wed Sep 15 15:10:15 2004 From: esann at dice.ucl.ac.be (esann) Date: Wed, 15 Sep 2004 21:10:15 +0200 Subject: CFP: ESANN'2005 European Symposium on Artificial Neural Networks Message-ID: <001f01c49b57$a4621d50$43ed6882@dice.ucl.ac.be> ESANN'2005 13th European Symposium on Artificial Neural Networks Bruges (Belgium) - April 27-28-29, 2005 Announcement and call for papers ========================== Technically co-sponsored by the International Neural Networks Society, the European Neural Networks Society, the IEEE Computational Intelligence Society, the IEEE Region 8 (to be confirmed), the IEEE Benelux Section. The call for papers for the ESANN'2005 conference is now available on the Web: http://www.dice.ucl.ac.be/esann For those of you who maintain WWW pages including lists of related ANN sites: we would appreciate if you could add the above URL to your list; thank you very much! We try as much as possible to avoid multiple sendings of this call for papers; however we apologize if you receive this e-mail twice, despite our precautions. You will find below a short version of this call for papers, without the instructions to authors (available on the Web). ESANN'2005 is organized in collaboration with the UCL (Universite catholique de Louvain, Louvain-la-Neuve) and the KULeuven (Katholiek Universiteit Leuven). Scope and topics ---------------- Since its first happening in 1993, the European Symposium on Artificial Neural Networks has become the reference for researchers on fundamentals and theoretical aspects of artificial neural networks. Each year, around 100 specialists attend ESANN, in order to present their latest results and comprehensive surveys, and to discuss the future developments in this field. The ESANN'2005 conference will focus on fundamental aspects of ANNs: theory, models, learning algorithms, mathematical and statistical aspects, in the context of function approximation, classification, data analysis, control, time-series prediction, signal processing, vision, etc. Papers on links and comparisons between ANNs and other domains of research (such as statistics, signal processing, biology, psychology, evolutive learning, bio-inspired systems, etc.) are encouraged. Papers will be presented orally (no parallel sessions) and in poster sessions; all posters will be complemented by a short oral presentation during a plenary session. The topic of the paper decides if it better fits into an oral or a poster session, not its quality. The selection of posters will be identical to oral presentations, and both will be printed in the same way in the proceedings. Nevertheless, authors have the choice to indicate their choice for oral or poster presentation only. The following is a non-exhaustive list of topics covered during the ESANN conferences: - Models and architectures - Learning algorithms - Theory - Mathematics - Statistical data analysis - Classification - Approximation of functions - Time series forecasting - Nonlinear dimension reduction - Multi-layer Perceptrons - RBF networks - Self-organizing maps - Vector quantization - Support Vector Machines - Recurrent networks - Fuzzy neural nets - Hybrid networks - Bayesian neural nets - Cellular neural networks - Signal processing - Independent component analysis - Natural and artificial vision - Adaptive control - Identification of non-linear dynamical systems - Biologically plausible networks - Bio-inspired systems - Cognitive psychology - Evolutiv learning - Adaptive behaviour Special sessions ---------------- Special sessions will be organized by renowned scientists in their respective fields. Papers submitted to these sessions are reviewed according to the same rules as any other submission. Authors who submit papers to one of these sessions are invited to mention it on the author submission form; nevertheless, submissions to the special sessions must follow the same format, instructions and deadlines as any other submission, and must be sent to the same address. The following special sessions will be organized at ESANN'2005: 1. Kernel Machines and Exponential Families S. Canu, Australian Nat. Univ. (Australia) & INSA Rouen (France), A. Smola, Australian Nat. Univ. (Australia) 2. Classification using non-standard metrics B. Hammer, Univ. Osnabr?ck, T. Villmann, Univ. Leipzig (Germany) 3. Evolutionary and neural computation C. Igel, Ruhr-Univ. Bochum, B. Sendhoff, Honda Research Institute Europe GmbH (Germany) 4. Dynamical and Numerical Aspects of Neural Computing M. Atencia, University of M?laga (Spain) 5. Artificial Neural Networks and Prognosis in Medicine Jos? M. Jerez, Univ. Malaga (Spain), Leonardo Franco, Univ. Oxford (UK) Location -------- The conference will be held in Bruges (also called "Venice of the North"), one of the most beautiful medieval towns in Europe. Bruges can be reached by train from Brussels in less than one hour (frequent trains). The town of Bruges is world-wide known, and famous for its architectural style, its canals, and its pleasant atmosphere. The conference will be organized in a hotel located near the centre (walking distance) of the town. There is no obligation for the participants to stay in this hotel. Hotels of all level of comfort and price are available in Bruges; there is a possibility to book a room in the hotel of the conference at a preferential rate through the conference secretariat. A list of other smaller hotels is also available. The conference will be held at the Novotel hotel, Katelijnestraat 65B, 8000 Brugge, Belgium. Proceedings and journal special issue ------------------------------------- The proceedings will include all communications presented to the conference (tutorials, oral and posters), and will be available on-site. Extended versions of selected papers will be published in the Neurocomputing journal (Elsevier). Call for contributions ---------------------- Prospective authors are invited to submit their contributions before 3 December 2004. The electronic submission procedure will be available soon on the ESANN Web pages http://www.dice.ucl.ac.be/esann/. Authors must indicate their choice for oral or poster presentation at the submission. They must commit themselves that they will register to the conference and present the paper in case of acceptation of their submission (one paper per registrant). Authors of accepted papers will have to register before February 25, 2005; they will benefit from the advance registration fee. Deadlines --------- Submission of papers December 3, 2004 Notification of acceptance February 4, 2005 Symposium April 27-29, 2005 Registration fees ----------------- Universities Industries speakers registration 440 ? 540 ? (before 28 February 2005) (one paper per speaker) non-speaker registration (before 22 March 2005) 440 ? 540 ? non-speaker registration (after 22 March 2005) 490 ? 590 ? The registration fee includes the attendance to all sessions, the ESANN'2005 dinner, a copy of the proceedings, daily lunches (27-29 April 2005), and the coffee breaks. Conference secretariat ---------------------- ESANN'2005 d-side conference services phone: + 32 2 730 06 11 24 av. L. Mommaerts Fax: + 32 2 730 06 00 B - 1140 Evere (Belgium) E-mail: esann at dice.ucl.ac.be http://www.dice.ucl.ac.be/esann Steering and local committee (to be confirmed) ---------------------------- Hugues Bersini Univ. Libre Bruxelles (B) Fran?ois Blayo Pr?figure (F) Marie Cottrell Univ. Paris I (F) Jeanny H?rault INPG Grenoble (F) Bernard Manderick Vrije Univ. Brussel (B) Eric Noldus Univ. Gent (B) Jean-Pierre Peters FUNDP Namur (B) Joos Vandewalle KUL Leuven (B) Michel Verleysen UCL Louvain-la-Neuve (B) Scientific committee (to be confirmed) -------------------- Samy Bengio IDIAP Martigny (CH) Pierre Bessi?re CNRS (F) Gianluca Bontempi Univ. Libre Bruxelles (B) Herv? Bourlard IDIAP Martigny (CH) Joan Cabestany Univ. Polit. de Catalunya (E) Colin Campbell Bristol Univ. (UK) St?phane Canu Inst. Nat. Sciences App. (F) Valentina Colla Scuola Sup. Sant'Anna Pisa (I) Holk Cruse Universit?t Bielefeld (D) Eric de Bodt Univ. Lille II (F) & UCL Louvain-la-Neuve (B) Dante Del Corso Politecnico di Torino (I) Georg Dorffner University of Vienna (A) Wlodek Duch Nicholas Copernicus Univ. (PL) Marc Duranton Philips Semiconductors (USA) Richard Duro Univ. Coruna (E) Anibal Figueiras-Vidal Univ. Carlos III Madrid (E) Simone Fiori Univ. Perugia (I) Jean-Claude Fort Universit? Nancy I (F) Colin Fyfe Univ. Paisley (UK) Stan Gielen Univ. of Nijmegen (NL) Mirta Gordon IMAG Grenoble (F) Marco Gori Univ. Siena (I) Bernard Gosselin Fac. Polytech. Mons (B) Manuel Grana UPV San Sebastian (E) Anne Gu?rin-Dugu? INPG Grenoble (F) Barbara Hammer Univ. of Osn?bruck (D) Martin Hasler EPFL Lausanne (CH) Laurent H?rault CEA-LETI Grenoble (F) Gonzalo Joya Univ. Malaga (E) Christian Jutten INPG Grenoble (F) Juha Karhunen Helsinki Univ. of Technology (FIN) Stefanos Kollias National Tech. Univ. Athens (GR) Vera Kurkova Acad. of Science of the Czech Rep. (CZ) Jouko Lampinen Helsinki Univ. of Tech. (FIN) Petr Lansky Acad. of Science of the Czech Rep. (CZ) Beatrice Lazzerini Univ. Pisa (I) Mia Loccufier Univ. Gent (B) Erzsebet Merenyi Rice Univ. (USA) Jos? Mira UNED (E) Jean-Pierre Nadal Ecole Normale Sup?rieure Paris (F) Erkki Oja Helsinki Univ. of Technology (FIN) Arlindo Oliveira INESC-ID (P) Gilles Pag?s Univ. Paris 6 (F) Thomas Parisini Univ. Trieste (I) H?l?ne Paugam-Moisy Universit? Lumi?re Lyon 2 (F) Alberto Prieto Universitad de Granada (E) Didier Puzenat Univ. Antilles-Guyane (F) Leonardo Reyneri Politecnico di Torino (I) Jean-Pierre Rospars INRA Versailles (F) Jose Santos Reyes Univ. Coruna (E) Udo Seiffert IPK Gatersleben (D) Jochen Steil Univ. Bielefeld (D) John Stonham Brunel University (UK) Johan Suykens K. U. Leuven (B) John Taylor King?s College London (UK) Claude Touzet Univ. Provence (F) Marc Van Hulle KUL Leuven (B) Thomas Villmann Univ. Leipzig (D) Axel Wism?ller Ludwig-Maximilians-Univ. M?nchen (D) Michalis Zervakis Technical Univ. Crete (GR) ============================ 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 - Machine Learning Group 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 harnad at ecs.soton.ac.uk Wed Sep 15 08:10:38 2004 From: harnad at ecs.soton.ac.uk (Stevan Harnad) Date: Wed, 15 Sep 2004 13:10:38 +0100 (BST) Subject: Cognition and Technology: Call for papers (fwd) Message-ID: ---------- Forwarded message ---------- From kcox at fasfind.com Wed Sep 15 08:00:18 2004 From: kcox at fasfind.com (Kevin Cox) Date: Wed, 15 Sep 2004 12:00:18 -0000 Subject: No subject Message-ID: As technology advances we are witnessing changes in the nature of cognition. A wide range of issues pertaining to technology and cognition will be covered in a series of special issues of the journal Pragmatics & Cognition. We are inviting contributions to our special issues, as specified below (for full details, please see: http://www.ecs.soton.ac.uk/~id/technology.html ) Pragmatics & Cognition (P&C) will henceforth pay special attention to the growing interest in the relationship between technological advances and cognition =96 a field that is intimately related to the journal's basic concerns. Beginning with volume 13 (2005), Pragmatics & Cognition will contain three issues instead of the current two. Each year, one of P&C's issues will be a thematic Special Issue devoted to "Cognition and Technology" (C&T), containing invited as well as submitted refereed papers. Space will also be reserved in these thematic issues for submitted articles, discussion notes, and book reviews in the field of C&T not specifically related to the theme of the Special Issue. Each Special Issue will be co-edited by a Guest Editor and Itiel Dror, who has been appointed P&C's Associate Editor for C&T. For full details, please see: http://www.ecs.soton.ac.uk/~id/technology.html Special Issues 1. New Technologies and the Pragmatics of Cognition Editors: Marcelo Dascal and Itiel Dror 2. Distributed Cognition Editors: Stevan Harnad and Itiel Dror 3. Robotics and Cognition Editors: Pim Haselager, Maria Eunice Qumlice Gonzales, and Itiel Dror 4. Ageing, Impairment, and Technology Editors: Romola Bucks, Jonathan Cole, and Itiel Dror 5. Technologies for Cognitive Research: Achievements, Problems, and Prospects Editors: Boris Velichkovsky and Itiel Dror 6. Cognitive Development and Education in the Mirror of Technology Editors: TBA and Itiel Dror Contributions are invited to the Special Cognition and Technology Series (for full details, please see: http://www.ecs.soton.ac.uk/~id/technology.html ) From kbp at imm.dtu.dk Tue Sep 21 10:54:25 2004 From: kbp at imm.dtu.dk (Kaare Brandt Petersen) Date: Tue, 21 Sep 2004 16:54:25 +0200 (METDST) Subject: The Matrix Cookbook: A Desktop Reference Message-ID: Dear Colleagues In case you might be interested: A 30 pages collection of identities, approximations and related issues regarding matrices, can be found at the following address http://www.imm.dtu.dk/pubdb/views/edoc_download.php/3274/pdf/imm3274.pdf Best regards, Kaare Brandt Petersen -- Kaare Brandt Petersen * http://2302.dk From dwang at cse.ohio-state.edu Tue Sep 21 15:48:52 2004 From: dwang at cse.ohio-state.edu (DeLiang Wang) Date: Tue, 21 Sep 2004 15:48:52 -0400 Subject: Available: IEEE TNN Special Issue on Temporal Coding In-Reply-To: <3E7236CC.203886BC@cis.ohio-state.edu> References: <3DC03C8C.B2A5BA8E@cis.ohio-state.edu> <3E7236CC.203886BC@cis.ohio-state.edu> Message-ID: <415085A4.8000304@cse.ohio-state.edu> IEEE Transactions on Neural Networks - Volume 15, Number 5, September 2004 (http://ieee-cis.org/pubs/tnn/) SPECIAL ISSUE ON TEMPORAL CODING FOR NEURAL INFORMATION PROCESSING (Online accessible from IEEE Xpore, http://ieeexplore.ieee.org/) Guest Editorial D. Wang, W. J. Freeman, R. Kozma, A. G. Lozowski, and A. A. Minai SPECIAL ISSUE PAPERS Coincidence Detection Correlated Inhibitory and Excitatory Inputs to the Coincidence Detector: Analytical Solution S. Mikula and E. Niebur An Instance of Coincidence Detection Architecture Relying on Temporal Coding D. B?roule A Network of Coincidence Detector Neurons With Periodic and Chaotic Dynamics M. Watanabe and K. Aihara Dynamics Dynamics and the Single Spike M. G. Paulin, L. F. Hoffman, and C. Assad On the Sample Complexity of Learning for Networks of Spiking Neurons With Nonlinear Synaptic Interactions M. Schmitt Dynamic Proximity of Spatio-Temporal Sequences D. Horn, G. Dror, and B. Quenet An Analysis of Globally Connected Active Rotators With Excitatory and Inhibitory Connections Having Different Time Constants Using the Nonlinear Fokker?Planck Equations T. Kanamaru and M. Sekine Grouping Synchronization in a Pulse-Coupled Network of Chaotic Spiking Oscillators H. Nakano and T. Saito Synchronization Rates in Classes of Relaxation Oscillators S. R. Campbell, D. Wang, and C. Jayaprakash Neural Modeling Different Types of Signal Coupling in the Visual Cortex Related to Neural Mechanisms of Associative Processing and Perception R. Eckhorn, A. M. Gail, A. Bruns, A. Gabriel, B. Al-Shaikhli, and M. Saam Dynamical Analysis of Neural Oscillators in an Olfactory Cortex Model D. Xu and J. C. Principe Which Model to Use for Cortical Spiking Neurons? E. M. Izhikevich The Role of Temporal Parameters in a Thalamocortical Model of Analogy Y. Choe Stimulus-Specific Oscillations in a Retinal Model G. T. Kenyon, B. J. Travis, J. Theiler, J. S. George, G. J. Stephens, and D. W. Marshak Theta-Modulated Feedforward Network Generates Rate and Phase Coded Firing in the Entorhino-Hippocampal System M. Lengyel and P. ?rdi Auditory Processing Temporal Codes and Computations for Sensory Representation and Scene Analysis P. A. Cariani A Temporal-Analysis-Based Pitch Estimation System for Noisy Speech With a Comparative Study of Performance of Recent Systems A. Khurshid and S. L. Denham Robust Sound Onset Detection Using Leaky Integrate-and-Fire Neurons With Depressing Synapses L. S. Smith and D. S. Fraser Monaural Speech Segregation Based on Pitch Tracking and Amplitude Modulation G. Hu and D. Wang A Computational Model of Auditory Selective Attention S. N. Wrigley and G. J. Brown Visual Processing Coding Static Natural Images Using Spiking Event Times: Do Neurons Cooperate? L. Perrinet, M. Samuelides, and S. Thorpe Pixel Clustering by Adaptive Pixel Moving and Chaotic Synchronization L. Zhao, A. C. P. L. F. de Carvalho, and Z. Li Pulse-Coupled Neural Networks for Contour and Motion Matchings B. Yu and L. Zhang Temporally Sequenced Intelligent Block-Matching and Motion-Segmentation Using Locally Coupled Networks X. Zhang and A. A. Minai Associative Networks Storage Capacity Diverges With Synaptic Efficiency in an Associative Memory Model With Synaptic Delay and Pruning S. Miyoshi and M. Okada A Transient-Chaotic Autoassociative Network (TCAN) Based on Lee Oscillators R. S. T. Lee Identification and Control of Dynamical Systems Using the Self-Organizing Map G. A. Barreto and A. F. R. Ara?jo Temporal Processing Temporal Processing in Primate Motor Control: Relation Between Cortical and EMG Activity O. F. L. Manette and M. A. Maier Signal Processing With Temporal Sequences in Olfactory Systems A. G. Lozowski, M. Lysetskiy, and J. M. Zurada Temporal BYY Encoding, Markovian State Spaces, and Space Dimension Determination L. Xu Hardware Implementation Synchrony Detection and Amplification by Silicon Neurons With STDP Synapses A. Bofill-i-Petit and A. F. Murray Temporal Coding in a Silicon Network of Integrate-and-Fire Neurons S.-C. Liu and R. Douglas Synchronization of Nonlinear Electronic Oscillators for Neural Computation J. Cosp, J. Madrenas, E. Alarc?n, E. Vidal, and G. Villar From cemgil at science.uva.nl Wed Sep 22 05:31:18 2004 From: cemgil at science.uva.nl (Ali Taylan Cemgil) Date: Wed, 22 Sep 2004 11:31:18 +0200 Subject: PhD thesis on music transcription Message-ID: <005701c4a086$ed95dd20$6a42fea9@TaylanLaptop> Dear Connectionists, My PhD thesis on music transcription is available from http://carol.science.uva.nl/~cemgil/papers.html A. Taylan Cemgil %--------------------- Title: Bayesian Music Transcription Institute: Radboud University Nijmegen, the Netherlands Keywords: Graphical models, Dynamic Bayesian Networks, Switching State Space models, Monte Carlo simulation, Music Transcription, Rhythm Quantization, Tempo Tracking, Polyphonic Pitch Tracking Abstract : Music transcription refers to extraction of a human readable and interpretable description from a recording of a music performance. The final goal is to implement a program that can automatically infer a musical notation that lists the pitch levels of notes and corresponding score positions in any arbitrary acoustical input. However, in this full generality, music transcription stays yet as a hard problem and arguably requires simulation of a human level intelligence. On the other hand, under some realistic assumptions, a practical engineering solution is possible by an interplay of scientific knowledge from cognitive science, musicology, musical acoustics and computational techniques from artificial intelligence, machine learning and digital signal processing. In this context, the aim of this thesis is to integrate this vast amount of prior knowledge in a consistent and transparent computational framework and to demonstrate the feasibility of such an approach in moving us closer to a practical solution to music transcription. In this thesis, we approach music transcription as a statistical inference problem where given a signal, we search for a score that is consistent with the encoded music. In this context, we identify three subproblems: Rhythm Quantization, Tempo Tracking and Polyphonic Pitch Tracking. For each subproblem, we define a probabilistic generative model, that relates the observables (i.e. onsets or audio signal) with the underlying score. Conceptually, the transcription task is then to ``invert'' this generative model by using the Bayes Theorem and to estimate the most likely score. From Harel.Shouval at uth.tmc.edu Wed Sep 22 13:51:44 2004 From: Harel.Shouval at uth.tmc.edu (Harel Shouval) Date: Wed, 22 Sep 2004 12:51:44 -0500 Subject: A New Book: Theory of cortical plasticity Message-ID: <4151BBB0.7000402@uth.tmc.edu> Announcing a new book: Theory of cortical plasticity. Authors: Leon N Cooper, Nathan Intrator, Brian S. Blais, & Harel Z. Shouval This book presents a theory of cortical plasticity and shows how this theory leads to experiments that test both its assumptions and consequences. It elucidates, in a manner that is accessible to students as well as researchers, the role which the BCM theory has played in guiding research and suggesting experiments that have led to our present understanding of the mechanisms underlying cortical plasticity. Most of the connections between theory and experiment that are discussed require complex simulations. A unique feature of the book is the accompanying software package, Plasticity . This is provided complete with source code, and enables the reader to repeat any of the simulations quoted in the book as well as to vary either parameters or assumptions. Plasticity is thus a research and an educational tool. Readers can use it to obtain hands-on knowledge of the structure of BCM and various other learning algorithms. They can check and replicate our results as well as test algorithms and refinements of their own. Now available from World Scientific Publishing see also: Amazon.com , Barnesandnoble.com , Booksamillion.com , Cabobble.com , Quantumbooks.com -- Harel Shouval Department of Neurobiology and Anatomy University of Texas Medical School at Houston 6431 Fannin st. Houston TX 77025 Phone: 713-500-5708 Web: http://nba.uth.tmc.edu/resources/faculty/members/shouval.htm From lynn.hazan at myrealbox.com Wed Sep 22 17:24:37 2004 From: lynn.hazan at myrealbox.com (Lynn Hazan) Date: Wed, 22 Sep 2004 17:24:37 -0400 Subject: NeuroScope Message-ID: <200409221724.37608.lynn.hazan@myrealbox.com> We are pleased to announce the release of NeuroScope, an advanced viewer for electrophysiological and behavioral data with limited editing capabilities. NeuroScope allows comparison of analyzed data with the original recordings. It can display original and processed local field potentials (EEG), action potentials recorded from single neurons on groups of electrodes (e.g., tetrodes or multisite siliconprobes), behavioral events, including 2 dimensional information (e.g., the position of a rat). NeuroScope was written by Lynn Hazan (lynn.hazan at myrealbox.com) in the laboratory of Gyorgy Buzsaki at Rutgers University (http://osiris.rutgers.edu), in collaboration with the laboratory of Kenneth D. Harris (http://qneuro.rutgers.edu) and is released under the GNU General Public Licence (www.gnu.org). NeuroScope offers many features enabling the user to explore neuronal recordings: * Selection and grouping of channels according to post-hoc anatomical or physiological information * Selection and grouping of channels for spike sorting and other treatments * Color-coding of traces or groups * Fast and easy navigation in the data, by steps, specific time or markers * Temporal and amplitude zooms * Superimposition of post-hoc data (e. g., spike rasters, events) on original or filtered traces * Editing of behavioral events * Display of the positions of the animal for the currently selected timeframe * Multiple displays of parallel or sequentially recorded sets * Storage in XML format of recording parameters (groups, colors) for subsequent analyses * Session management (XML format) * Ergonomic user interface for maximum speed. NeuroScope is written in C++ for Linux under the KDE environment. The program, source code, and full documentation are available at http://neuroscope.sourceforge.net. From cns-course at jupiter.chaos.gwdg.de Fri Sep 24 07:13:19 2004 From: cns-course at jupiter.chaos.gwdg.de (CNS Course) Date: Fri, 24 Sep 2004 13:13:19 +0200 (CEST) Subject: Professorship in Computational Neuroscience Message-ID: Professorship (W3) in Computational Neuroscience The Georg-August-Universitaet Goettingen invites, pending the approval of the BMBF, applications for a Professorship in Computational Neuroscience (W3) starting as early as possible. We are looking for an internationally recognized research personality, who will represent the field of Computational Neuroscience in research and teaching. The successful candidate should collaborate with existing research groups in the area of Neuroscience in Goettingen and participate in the coordination of the Center for Theoretical Neuroscience Goettingen, which is currently being established. The candidate's research should complement and expand the scientific spectrum of the Center. Possible areas of research include dynamics and coding in biological neural networks, computer-aided analysis of complex neural systems and/or the development of simulation technology for large biological neural networks. We expect a substantial contribution of the candidate towards establishing the PhD program in Computational Neuroscience within the Goettingen Graduate School of Science. The professorship is assigned to the Institute for Informatics in the Faculty of Mathematics of the Georg-August-Universitaet Goettingen. Initially the position is limited to five years but will be extended to tenure following a positive evaluation. Habilitation or alternatively documented evidence of equivalent scientific qualifications is required. The Universitaet Goettingen seeks to increase the proportion of female faculty members. Thus qualified women are especially encouraged to apply. If equally qualified, candidates with disabilities will be preferentially considered. The deadline for applications is October 27, 2004. Please submit your application in English, together with the usual information (curriculum vitae, publication list, names of three possible referees) and copies of your three most important publications to: Prof. Dr. Theo Geisel Institut fuer Nichtlineare Dynamik Universitaet Goettingen Bunsenstrasse 10 37073 Goettingen, Germany http://www.chaos.gwdg.de From Anthony.Pipe at uwe.ac.uk Thu Sep 23 03:55:00 2004 From: Anthony.Pipe at uwe.ac.uk (Tony Pipe) Date: Thu, 23 Sep 2004 08:55:00 +0100 Subject: CFP: FLAIRS'05 conference, Neural Networks Applications track Message-ID: <000a01c4a142$a03703d0$17800ba4@cems.uwe.ac.uk> CALL FOR PAPERS (submission deadline one month from now) Neural Network Applications Special Track at the 18th International FLAIRS Conference In cooperation with the American Association for Artificial Intelligence Adam's Mark Hotel Clearwater Beach, Florida May 16-18, 2005 For the web version of this call, please visit the conference web page at http://ranger.uta.edu/flairs05/ then select 'Special Tracks' and then 'Neural Networks Applications' -------------------------------------------------------------------------------- Papers are being solicited for a special track on Neural Network Applications at the 17th International FLAIRS Conference (FLAIRS-2004). The special track will be devoted to the applications of Neural Networks with the aim of presenting new and important contributions in this area. These application areas include, but are not limited to, the following: Vision Pattern Recognition Control and Process Monitoring Biomedical Applications Robotics Speech Recognition Text Mining Diagnostic Problems Telecommunications Power Systems Signal Processing Image Processing -------------------------------------------------------------------------------- Submission Guidelines Interested authors must submit completed manuscripts by October 22, 2004. Submissions should be no more than 6 pages (4000 words) in length, including figures, and contain no identifying reference to self or organization. Papers should be formatted according to AAAI Guidelines. Submission instructions can be found at FLAIRS-05 website at http://ranger.uta.edu/flairs05. Notification of acceptance will be mailed around January 7, 2005. Authors of accepted papers will be expected to submit the final camera-ready copies of their full papers by February 4, 2005 for publication in the conference proceedings which will be published by AAAI Press. Authors may be invited to submit a revised copy of their paper to a special issue of the International Journal on Artificial Intelligence Tools (IJAIT). -------------------------------------------------------------------------------- FLAIRS 2005 Invited Speakers Lawrence Hunter, University of Colorado Martha Pollack, University of Michigan Ted Senator, DARPA David Stork, Ricoh and Stanford University -------------------------------------------------------------------------------- Important Dates Paper submissions due: October 22, 2004 Notification letters sent: January 7, 2005 Camera ready copy due: February 4, 2005 -------------------------------------------------------------------------------- Special Track Committee Ingrid Russell (Co-Chair), University of Hartford, USA Tony Pipe (Co-Chair), University of the West of England, UK Brian Carse (Co-Chair), University of the West of England, UK Jim Austin, University of York, UK Vijayakumar Bhagavatula, Carnegie Mellon University, USA Douglas S. Blank, Bryn Mawr College, USA Serge Dolenko, Moscow State University, Russia Okan Ersoy, Purdue University, USA Michael Georgiopoulos, University of Central Florida, USA Mike James, York University, UK John Kolen, University of West Florida, USA Luis Marti, Universidad de La Habana, Cuba Lisa Meeden, Swarthmore College, USA Costas Neocleous, Higher Technical Institute, Cyprus Luis Fernando Nio, National University of Colombia, Colombia Sergio Roa, National University of Colombia, Colombia Roberto Santana, Institute of Cybernetics, Mathematics and Physics (ICIMAF), Cuba Bernhard Sendhoff, Honda Research and Development Europe, Offenbach/Main, Germany Chellu Chandra Sekhar, Indian Institute of Technology, India Wai Sum Tang, Chinese University of Hong Kong, Hong Kong Antony J. Waldock, University of theWest of England, UK Stefan Wermter, University of Sunderland, UK Hujun Yin, University of Manchester Institute of Science and Technology, UK -------------------------------------------------------------------------------- Further Information Questions regarding the special track should be addressed to: Tony Pipe Voice: +44-117-344-2818 Fax: +44-117-344-3800 email: Anthony.Pipe at uwe.ac.uk This email has been independently scanned for viruses and any virus detected has been removed using McAfee anti-virus software From dglanzma at mail.nih.gov Thu Sep 23 12:34:57 2004 From: dglanzma at mail.nih.gov (Glanzman, Dennis (NIH/NIMH)) Date: Thu, 23 Sep 2004 12:34:57 -0400 Subject: CORRECTION -- Dynamical Neuroscience Satellite Symposium: Closing the Loop -- CORRECTION Message-ID: <8F3AB322628548428A992EFB0E80F5D30C565604@nihexchange8.nih.gov> Twelfth Annual Dynamical Neuroscience Satellite Symposium Closing the Loop Thursday, October 21, 2004 8 a.m.-9 p.m. Friday, October 22, 2004 8 a.m.-6 p.m. Preceding the 34th Annual Meeting of the Society for Neuroscience San Diego Convention Center San Diego, California From pli at richmond.edu Fri Sep 24 16:27:53 2004 From: pli at richmond.edu (Ping Li) Date: Fri, 24 Sep 2004 16:27:53 -0400 (EDT) Subject: The APA Style Converter Message-ID: <49916.141.166.212.246.1096057673.squirrel@spidermail.richmond.edu> Dear Colleagues, If you are submitting articles to journals that require the APA Style (such as Neural Networks, for the Reference section), you might be interested in a web interface that we have developed, the APA Style Converter. A description of the Converter is attached below. You can access the Converter from our web server at: http://cogsci.richmond.edu/. We welcome your feedback, comments, and suggestions. Sincerely Ping Li pli at richmond.edu http://www.richmond.edu/~pli/ Abstract: The APA Style Converter is a web-based tool for authors to prepare their papers in APA Style according to the APA Publication Manual (5th ed.). The converter provides a user-friendly interface that allows authors to copy and paste text and upload figures through the web, and it automatically turns all texts, references, and figures to a structured article in APA Style. The output is saved in PDF format, ready for either electronic submission or hardcopy printing. Rationale: While the APA Style has widespread use in the scientific community, there are several factors that hinder authors from accurate use of the style. First, many authors find it difficult to keep track of all the details specified in the Manual. For example, when asked, few researchers are certain about, (a) whether the Footnotes section should come before or after the Author Note, (b) whether the Appendices should come before or after the Tables, or (c) what a Page Header is, how it is different from a Running Head, and how these head and headers should be laid out on the Title Page. Second, some authors who are familiar with earlier versions of the APA Style might not have kept up with the newest changes in the current version such as the abolition of underlines and the citation for internet resources. Third, researchers from countries other than North America and Europe are relatively unfamiliar with the APA Style, either because it is not part of their training or because writing conventions and publication guidelines for their native languages differ from the APA Style. Yet more and more researchers find it necessary to deal with the APA Style: the style is widely used in many disciplines, and the journals to which they submit papers require it. Researchers from other countries are also under increasing pressure to publish in international journals that may require the APA Style. From anguita at dibe.unige.it Mon Sep 27 06:25:38 2004 From: anguita at dibe.unige.it (Davide Anguita) Date: Mon, 27 Sep 2004 12:25:38 +0200 Subject: ANN: cSVM software Message-ID: <024701c4a47c$67816610$b759fb82@dibe.unige.it> Our apologies if you receive multiple copies of this message due to overlaps in mailing lists. ========== cSVM 3.0.0 ========== cSVM 3.0.0 implements the training and model selection of a Support Vector Machine for classification tasks (two-classes). People familiar with our MBP package for training Multi Layer Perceptrons should find cSVM easy to use. This software has been developed in Fortran95 and binaries have been successfully tested on x86-based PCs running Windows XP or Red Hat Linux 8, but should run faultlessly on any x86-based Win32 or Linux system. The package can be downloaded from the web pages of our laboratory: http://www.smartlab.dibe.unige.it under the section "software". cSVM is provided "as-is" and is intended for research purposes only. For any other use, information request or comments, please contact one of the authors. D.Anguita*, A.Boni**, S.Ridella*, F.Rivieccio*, D.Sterpi*. * DIBE - Dept. of Biophysical and Electronic Engineering University of Genoa Via Opera Pia 11A, 16145, Genoa ITALY {anguita, ridella, rivieccio, sterpi} AT dibe DOT unige DOT it ** DIT - Dept. of Information and Communication Technology University of Trento, Via Sommarive 14, 38050, Povo (TN), ITALY boni AT dit DOT unitn DOT it From adr at adrlab.ahc.umn.edu Fri Sep 24 10:54:50 2004 From: adr at adrlab.ahc.umn.edu (David Redish) Date: Fri, 24 Sep 2004 09:54:50 -0500 Subject: postdoctoral position available Message-ID: <200409241454.i8OEsoat001253@adrlab.ahc.umn.edu> ------------------------------------------------------------ POSTDOCTORAL POSITION AVAILABLE in the laboratory of A. David Redish Department of Neuroscience University of Minnesota Starting date: 1 January 2005 A postdoctoral position will be available starting 1 January 2005 in my laboratory in the Department of Neuroscience at the University of Minnesota. Research interests include behavioral neuroscience, with specific interests in spatial cognition in rats. My laboratory does both experimental and computational work and postdocs would be expected to participate in both aspects. Possible research projects include (but are not limited to) computational models of addiction, recording neural ensembles in striatum, and dynamics of the hippocampal place cell and post-subicular head-direction systems. Candidates should have recently completed (or be about to complete) their PhD and should have some experience in either computational or experimental neuroscience. Pay will be commensurate with NIH standards. Those interested should contact me via email at the following address redish at ahc.umn.edu The University of Minnesota is an equal-opportunity employer. ----------------------------------------------------- A. David Redish redish at ahc.umn.edu Assistant Professor http://www.cbc.umn.edu/~redish Department of Neuroscience, University of Minnesota Office: 4-142 MCB Postal Address: 6-145 Jackson Hall / 321 Church St SE / Minneapolis MN 55455 ----------------------------------------------------- From nik.kasabov at aut.ac.nz Wed Sep 29 01:07:03 2004 From: nik.kasabov at aut.ac.nz (Nik Kasabov) Date: Wed, 29 Sep 2004 17:07:03 +1200 Subject: CFP - Special session at IJCNN'05 on Computational Neuro-Genetic Modelling Message-ID: Call for Papers for a Special Session "Computational Neuro-Genetic Modelling" International Joint INNS-IEEE Conference on Neural Networks (IJCNN) 2005 Hilton Bonaventure Hotel, Montreal, Quebec, Canada July 31- August 4, 2005, IJCNN 2005, (http://faculty.uwb.edu/ijcnn05) The aim of the session is to bring together researchers in a new research area called Computational Neuro-Genetic Modelling (CNGM), that is concerned with the study and the development of dynamic neuronal models integrated with gene models. This area brings together knowledge from at least three areas of science: computer and information science, neuroscience, and molecular biology. A computational neuro-genetic model is created to model a brain function or a brain disease, or to be used as a general mathematical model for solving complex scientific and engineering problems. The CNGM goes beyond modelling simple relationship between a single gene and a single neuronal function. It is the interaction between tens, hundreds and possibly thousands of genes in a neuron and their relationship with the functioning of a neuronal ensemble and the brain as a whole. The computational neuro-genetic models constitute a new generation of neural network models that are closer to biological neural networks in their complex interaction of neuronal learning dynamics and gene activities. Topics include: Genes and growth functions; Genes and gene regulatory networks related to the brain; Genes and gene regulatory networks related to the brain development, evolution and plasticity; Genes and gene networks related to learning, memory and perception; Genes and gene networks related to brain diseases, such as, epilepsy, mental retardation, schizophrenia, etc; Functional integration of neural networks and gene networks to model brain functions; Models of spiking neurons and spiking neural networks with gene-defined parameters; Evolving and evolutionary neural networks; Software and hardware computational neurogenetic systems; Brain-like neurogenetic architectures; Applications. Organizers: Prof. Nik Kasabov (nkasabov at aut.ac.nz ) and Dr. Luba Benuskova (lbenusko at aut.ac.nz) Knowledge Engineering and Discovery research Institute, KEDRI www.kedri.info, New Zealand Submissions and deadlines: 25 October 2004: An abstract (1 page) should be sent electronically to the organizers 15 December 2004: A full paper (see the IJCNN'05 instructions for submissions) sent to the organizers. 15 January 2005: Reviews and a notification of acceptance/rejection sent to the authors. 31 January 2005: Final paper submitted to the special session electronically (IJCNN'05 portal) All accepted papers will be published in the IJCNN 2005 Proceedings. Papers not accepted for the special session can be submitted as regular submissions for IJCNN'05 (the deadline is also January 31, 2005). Authors will be invited to submit extended versions of their papers to a special issue of an international journal. Each paper must have the title, authors with e-mails/web sites, and as detailed an abstract as possible. All accepted papers must be presented at the conference. -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- Prof. Nik Kasabov, MSc, PhD FRSNZ, FNZCS, SrMIEEE Founding Director and Chief Scientist - Knowledge Engineering and Discovery Research Institute, KEDRI Chair of Knowledge Engineering, School of Computer and Information Sciences Auckland University of Technology phone: +64 9 917 9506 ; fax: +64 9 917 9501 WWW http://www.kedri.info email: nkasabov at aut.ac.nz (PA Joyce D'Mello: jdmello at aut.ac.nz; +64 9 917 9504)