From lincj at ntu.edu.tw Tue Apr 1 01:45:24 2003 From: lincj at ntu.edu.tw (Chih-Jen Lin) Date: Tue, 01 Apr 2003 14:45:24 +0800 Subject: "libsvm tools" and new version of libsvm Message-ID: Dear Colleagues: We announce the new version 2.4 of the software libsvm: libsvm: a library for support vector machines http://www.csie.ntu.edu.tw/~cjlin/libsvm and a new page "libsvm tools" containing additional codes/data sets based on libsvm: http://www.csie.ntu.edu.tw/~cjlin/libsvmtools Due to popular requests, in this new page we include MANY our past and current experimental codes/data sets such as svm probability output, minimization of leave-one-out bounds, different multi-class svms, reduced SVM, etc. Moreover, we now provide an integrated development environment to libsvm. Users can create and connect components (like scaler, trainer, predictor, etc) in this environment. Improvements of the new libsvm include 1. a script for users who know NOTHING about svm. It makes everything automatic--from data scaling to parameter selection. 2. handling non-PSD kernels such as sigmoid and others. Theoretical convergence for such cases has been established. 3. significant improvements of the python model selection tool. 4. improvements of the program for data scaling. Any comments are very welcome. Sincerely, Chih-Chung Chang and Chih-Jen Lin Department of Computer Science National Taiwan University Taipei, Taiwan cjlin at csie.ntu.edu.tw From UE001861 at guest.telecomitalia.it Tue Apr 1 06:58:47 2003 From: UE001861 at guest.telecomitalia.it (Corsini Filippo) Date: Tue, 1 Apr 2003 13:58:47 +0200 Subject: First European School on Neuroengineering "Massimo Grattarola" Message-ID: <5C052AA22466074FADC82C208D5C5719E5D3C1@EVS02.idc.cww.telecomitalia.it> ************************************************************************* First European School on Neuroengineering "Massimo Grattarola" Venice 16-20 June 2003 Telecom Italia Learning Services (TILS), and the University of Genoa (DIBE, DIST, Bioengineering course) are currently organizing the first edition of an European Summer School on Neuroengineering. The school will be entitled to Massimo Grattarola. The first edition , which will last for five days, will be held from June 16 to June 20, 2003 at Telecom Italia's Future Center in Venice. The School will cover the following main themes: 1. Neural code and plasticity o Development and implementation of methods to identify, represent and analyze hierarchical and self-organizing systems o Cortical computational paradigms for perception and action 2. Brain-like adaptive information processing systems o Development and implementation of methods to identify, represent and analyze hierarchical and self-organizing systems o Models of learning, representation and adaptability based on knowledge of the nervous system. o Exploration of the capabilities of natural neurobiological systems as flexible computational devices. o Use of information from nervous systems to engineer new control techniques and new artificial systems. o Development of highly innovative Artificial Neural Networks capable of reproducing the functioning of vertebrate nervous systems. 3. Bio-artificial systems o Development of novel brain-computer interfaces o Development of new techniques for neuro-rehabilitation and neuro-prostheses o Hybrid silicon/biological systems In response to current reforms in training, at the Italian and European levels, the Summer School on Neuroengineering is certified to grant credits. These include: ECM (Educazione Continua in Medicina) credits recognized by the Italian Ministry of Health ECTS (European Credit Transfer System) credits recognized by all European Universities More information and application forms can be obtained from: www.tils.com/neurobit www.bio.dibe.unige.it Scientific Board: Sun -ichi Amari RIKKEN, Brain Science Institute Laboratory for Mathematical Neuroscience, Japan Fabrizio Davide Telecom Italia Learning Services, Italy Walter J. Freeman University of Berkeley, USA Stephen Grossberg University of Boston, USA Milena Koudelka-Hep IMT, Institute of Microtechnology, University of Neuchatel, Switzerland Gwendal Le Masson INSERM, French Institute of Health and Medical Research, France Sergio Martinoia DIBE, Unversity of Genoa, Italy Pietro Morasso DIST, University of Genoa, Italy Sylvie Renaud-Le Masson ENSEIRB - IXL Bordeaux, France Wim Rutten University of Twente, Netherlands Jaap Van Pelt Netherlands Institute for Brain Research, Netherlands Confirmed Lecturers: Abbruzzese G. Non-invasive exploration of human cerebral cortex by transcranial magnetic stimulation Benfenati F. Molecular dissection of neurotransmitter release mechanisms: a key to understand short-term memory processes Torre V., Ruaro M. E., Bonifazi P. Towards the neurocomputer: image processing and learning with neuronal cultures Aleksander I. Digital Neuromodelling Based on the Architecture of the Brain: Basics and Applications Destexhe A. The stochastic integrative properties of neocortical neurons in vivo Gielen S. Quantitative models to explain the degree-of-freedom problem in motor control Le Masson G. Cyborgs : from fiction to science Rutten W. Neuro-electronic interface engineering and neuronal network learning Van Pelt J. Computational and experimental approaches in neuronal morphogenesis and network formation Mussa-Ivaldi F. The Engineering of motor learning and adaptive control Sandini G. Cognitive Development in Robot Cubs Morasso P. Motor control of unstable tasks Knoll A. Neuro-IT - an overview of network scope and activities Orban G. Investigating the primate brain at different levels of organisation: linking single cell recording and fMRI in the awake monkey Pearce T. Olfactory machines on the move Engel A. Synchrony as an integrative principle for cognitive architectures Two Practical Laboratory: Davide F., Stillo G, Morabito F. Chosen exempla of neuronal signals decoding, analysis and features extractions Renaud-Le Masson Bioengineering: on-silicon solutions for biologically realistic artificial neural networks (state-of-the-art and development perspectives for integrated ANN Registration Fee*: Undergraduate and graduate: 100 EUR PhD students and young researcher: 250 EUR Business and medical professional: 500 EUR * The School registration fee includes the meeting program, reception, two coffee breaks and a lunch each day, and meeting proceedings. For informations you can contact: Filippo Corsini ue001861 at guest.telecomitalia.it For informations about hotel in Venice: www.venicehotel.com and www.turismovenezia.it _________________________________________________ Dr. Filippo Corsini Telecom Italia- Learning Services S.p.A. Business Development Viale Parco de' Medici, 61, 00148 Roma Italy tel: +39.06.368.72379 fax: +39.06.368.80101 e-mail: UE001861 at guest.telecomitalia.it _________________________________________________ This e-mail, including any attachments, may contain private or confidential information. If you think you may not be the intended recipient, or if you have received this e-mail in error, please contact the sender immediately and delete all copies of this e-mail. If you are not the intended recipient, you must not reproduce any part of this e-mail or disclose its contents to any other party. From benjamin.blankertz at first.fhg.de Tue Apr 1 16:25:48 2003 From: benjamin.blankertz at first.fhg.de (Benjamin Blankertz) Date: Tue, 1 Apr 2003 22:25:48 +0100 Subject: BCI [Brain Computer Interfaces] Competition 2003 deadline is approaching Message-ID: <200304012326.05797.benjamin.blankertz@first.fhg.de> Dear Colleagues, The deadline for submissions to the BCI [Brain Computer Interfaces] Competition 2003 is approaching: it is in one month, on May 1st 2003 - a good opportunity to remind you of this date. There were over 120 downloads, so it is going to be a hot competition. If you have not already checked the competition web site http://ida.first.fraunhofer.de/~blanker/competition/ do it right now! It is not too late to participate. Best wishes, Benjamin Blankertz The BCI Competition 2003 is organized by: Albany: Theresa M. Vaughan, Gerwin Schalk, Jonathan R. Wolpaw Berlin: Benjamin Blankertz, Gabriel Curio, Klaus-Robert Mueller Graz: Alois Schloegl, Christa Neuper, Gernot Mueller, Bernhard Graimann, Gert Pfurtscheller Tuebingen: Thilo Hinterberger, Michael Schroeder, Niels Birbaumer Contact: Dr. Benjamin Blankertz, +49.30.6392-1875 Fraunhofer FIRST.IDA Kekulestr. 7, D-12489 Berlin, Germany benjamin.blankertz at first.fraunhofer.de From nestor at ftnp.ft.uam.es Tue Apr 1 06:13:39 2003 From: nestor at ftnp.ft.uam.es (Nestor Parga) Date: Tue, 1 Apr 2003 13:13:39 +0200 (MET DST) Subject: "Ramon y Cajal" and postdoctoral positions Message-ID: 1. "RAMON y CAJAL" position Computational and Systems Neuroscience / a five year position in Madrid Interested candidates are invited to apply for a "Ramon y Cajal" position for research work in Computational and Systems Neuroscience at the "Group of Computational Neuroscience", Universidad Autonoma de Madrid, Spain. These are five year positions co-funded by the Spanish Ministery of Science and Technology and the Universities. This is the third year that these contracts are given in Spain and more information about them and about how to apply can be found at the web address: http://www.mcyt.es/CAJAL/default.htm Candidates are expected to work in interaction with the theoretical team of the Computational Neuroscience group to carry out joint work on information processing in the brain Details about the current work of the group can be found at the web site: http://ket.ft.uam.es/~neurociencia/ Interested candidates are encouraged to send a research proposal, their curriculum vitae including a list of all publications, a statement of research interests and the names of three scientists who could send recommendation letters to the address below, Notice however that final applications have to done according to the instructions in http://www.mcyt.es/CAJAL/default.htm Nestor Parga | | Phone : (+34) 91-397-4542 Dpto. de Fisica Teorica, C-XI | Fax : (+34) 91-397-3936 Universidad Autonoma de Madrid | E-mail: nestor at ftnp.ft.uam.es 28049 Madrid, SPAIN | parga at delta.ft.uam.es http://ket.ft.uam.es/~neurociencia/nestor %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 2. POSTDOCTORAL position (Fundacion Carolina) Postdoctoral position available in Theoretical Neuroscience in the Universidad Autonoma de Madrid (UAM, Spain) for nationals from Latin-american countries. The Carolina Foundation (Spain) is receiving applications for postdoctoral fellowships in Neuroscience. Their webpage is: http://www.fundacioncarolina.es/esp/becas/index.htm and details about how to apply to the Neuroscience Program can be found in: http://www.fundacioncarolina.es/esp/becas/CIE/3/NEUROCIENCIAS/prg_ficha.htm Candidates should first select a research group in a Spanish University or Institute. The "Computational Neuroscience Group", Universidad Autonoma de Madrid, offers the possibility to work on several aspects of theoretical neuroscience. Eligible candidates with a Ph. D. in neuroscience or a related scientific discipline (e.g. physics, maths or computer science) and with good background and interest in theoretical neurobiology are encouraged to send their curriculum vitae and a brief description of fields of interest to the address below, if possible by e-mail (parga at delta.ft.uam.es). For more information about the "Computational Neuroscience Group", UAM, please see: http://ket.ft.uam.es/~neurociencia/index.html Nestor Parga | | Phone : (+34) 91-397-4542 Dpto. de Fisica Teorica, C-XI | Fax : (+34) 91-397-3936 Universidad Autonoma de Madrid | E-mail: nestor at ftnp.ft.uam.es 28049 Madrid, SPAIN | parga at delta.ft.uam.es http://ket.ft.uam.es/~neurociencia/nestor From oby at cs.tu-berlin.de Wed Apr 2 10:13:58 2003 From: oby at cs.tu-berlin.de (Klaus Obermayer) Date: Wed, 2 Apr 2003 17:13:58 +0200 (MEST) Subject: Advanced Course in Computational Neuroscience Message-ID: ***NEW DEADLINE APRIL 27TH 2003*** ***REGISTRATION FEE REDUCED*** Due to a last minute success in fundraising for the school we were able to reduce the registration fee to EUR 600,-. We now also have fellowships for covering the tuition fee and travel expenses for students who need financial help for attending the course. =========================================================================== ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE (A FENS/IBRO NEUROSCIENCE SCHOOL) August 11th - September 5th, 2003 MUNICIPALITY OF OBIDOS, PORTUGAL DIRECTORS: Ad Aertsen (University of Freiburg, Germany) Alain Destexhe (CNRS, Gif-sur-Yvette, France) Klaus Obermayer (Technical University of Berlin, Germany) Eilon Vaadia (Hebrew University, Jerusalem, Israel) The Advanced Course in Computational Neuroscience introduces students to the panoply of problems and methods of computational neuroscience, simultaneously addressing several levels of neural organisation, from subcellular processes to operations of the entire brain. The course consists of two complementary parts. A distinguished international faculty gives morning lectures on topics in experimental and computational neuroscience. The rest of the day is devoted to practical training, including learning how to use simulation software and how to implement a model of the system the student wishes to study on individual UNIX workstations. The first week of the course introduces students to essential neurobiological concepts and to the most important techniques in modelling single cells, networks and neural systems. Students learn how to apply software packages like GENESIS, MATLAB, NEURON, XPP, etc. to the solution of their problems. During the following three weeks the lectures will cover specific brain functions. Each week topics ranging from modelling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the brain will be covered. The course ends with a presentation of the students' projects. The Advanced Course in Computational Neuroscience is designed for advanced graduate students and postdoctoral fellows in a variety of disciplines, including neuroscience, physics, electrical engineering, computer science and psychology. Students are expected to have a basic background in neurobiology as well as some computer experience. Students of any nationality can apply. A maximum total of 30 students will be accepted and we specifically encourage applications from researchers who work in less-favoured regions and women. There will be a fee of EUR 600,- per student covering costs for lodging, meals and other course expenses, but - due to additional funding - we expect to provide tuition fee waivers and travel stipends for students who need financial help for attending the course. Students from unfavored countries are strongly encouraged to apply. More information and application forms can be obtained from: http://www.neuroinf.org/courses/EUCOURSE/EU03/ Please apply electronically using a web browser. Contact address: - mail: Klaus Obermayer, FR2-1, Fakultaet IV, Technical University of Berlin, Franklinstrasse 28/29, 10587 Berlin, Germany phone: +49-(0)30-314-73442 fax: +49-(0)30-314-73121 - e-mail: obidos at cs.tu-berlin.de APPLICATION DEADLINE: April 27th, 2003 Applicants will be notified of the results of the selection procedures by May 23rd, 2003. CONFIRMED FACULTY: Larry Abbott, Brandeis University, USA Moshe Abeles, Hebrew University, Israel Ad Aertsen, University of Freiburg, Germany Amos Arieli, Weizmann Institute, Israel Thierry Bal, CNRS, France Dave Beeman, University of Colorado Boulder, USA Diego Contreras, University of Pennsylvania, USA Peter Dayan, University College London, UK Erik de Schutter, University of Antwerp, Belgium Alain Destexhe, CNRS, France Marcus Diessmann, University of Freiburg, Germany Andreas Engel, University of Hamburg, Germany Karl Friston, University College London, UK Michael Hines, Yale University, USA Israel Nelken, Hebrew University, Israel Miguel Nicolelis, Duke University, USA Klaus Obermayer, TU Berlin, Germany Tim Pearce, University of Leicester, UK John Rinzel, New York University, USA Arnd Roth, Max Planck Inst. Heidelberg, Germany Michael Rudolph, CNRS, France Lars Schwabe, TU Berlin, Germany Idan Segev, Hebrew University, Israel Volker Steuber, University of Antwerp, Belgium Alex Thomson, University College London, UK Charlie Wilson, University of Texas San Antonio, USA Daniel Wolpert, University College London, UK Eilon Vaadia, Hebrew University, Israel Carl van Vreeswijk, CNRS, France Paul Verschure, Inst. Neuroinformatics, Switzerland From clabiouse at ulg.ac.be Wed Apr 2 12:50:26 2003 From: clabiouse at ulg.ac.be (Christophe Labiouse) Date: Wed, 2 Apr 2003 19:50:26 +0200 Subject: Eighth Neural Computation and Psychology Workshop (NCPW 8): Connectionist Models of Cognition, Perception, and Emotion Message-ID: <001f01c2f940$581130e0$3200000a@COGSCILABIOUSE> Eighth Neural Computation and Psychology Workshop (NCPW 8) Connectionist Models of Cognition, Perception and Emotion 28-30 August 2003 at the University of Kent at Canterbury, UK The Eighth Neural Computation and Psychology Workshop (NCPW8) will be held in Canterbury, England from 28-30th August 2003. The NCPW series is now a well established and lively forum that brings together researchers from such diverse disciplines as artificial intelligence, cognitive science, computer science, neuroscience, philosophy and psychology. Between 25-30 papers will be accepted as oral presentations. In addition to the high quality of the papers presented, this Workshop takes place in an informal setting, in order to encourage interaction among the researchers present. Publication ----------- Proceedings of the workshop will appear in the series Progress in Neural Processing, which is published by World Scientific. Speakers -------- The list of speakers who have already agreed to attend includes: John Bullinaria (Birmingham) Gary Cottrell (San Diego) Bob French (Liege) Peter Hancock (Stirling) Richard Shillcock (Edinburgh) Chris Solomon (Kent at Canterbury) John Taylor (Kings College) Marius Usher (Birkbeck College) Important Dates --------------- Deadline for submission of abstracts: June 13th 2003 Notification of acceptance/rejection: June 29th 2003 Website ------- More details can be found on the conference website, http://www.cs.ukc.ac.uk/events/conf/2003/ncpw/ Conference Chair ---------------- Howard Bowman, University of Kent, UK Conference Organisers --------------------- Howard Bowman, UKC Colin G. Johnson, UKC Miguel Mendao, UKC Vikki Roberts, UKC Proceedings Editors -------------------- Howard Bowman, UKC Christophe Labiouse, Liege ******************************************************************** Christophe L. Labiouse Research Fellow of the Belgian National Fund for Scientific Research University of Liege, Department of Cognitive Science (B33) Boulevard du Rectorat, 3 B-4000 Liege, Belgium Tel 00 32 (0)4 3664870 Fax 00 32 (0)4 3662859 e-mail: clabiouse at ulg.ac.be http://www.ulg.ac.be/cogsci/clabiouse/intro.html ******************************************************************** From simone at dsi.unifi.it Thu Apr 3 02:54:15 2003 From: simone at dsi.unifi.it (Simone Marinai) Date: Thu, 3 Apr 2003 09:54:15 +0200 Subject: IAPR-TC3 workshop DEADLINE EXTENSION Message-ID: <200304030754.h337sFf22612@diamante.dsi.unifi.it> ** apologies if you receive multiple copies of this document ** In response to many requests, we are pleased to announce an extension of the deadline for paper sumbmission to ANNPR: April 22nd 2003 (Midnight GMT) Any information on the workshop can be found in the following web page: www.dsi.unifi.it/ANNPR ---------------------------------------------- IAPR - TC3 International Workshop on Artificial Neural Networks in Pattern Recognition Location: University of Florence, Italy, September 12-13, 2003 Important Dates: Deadline for paper submission: 22-4-2003 Deadline for poster submission: 22-4-2003 Notification of acceptance: 15-6-2003 Camera Ready due: 15-7-2003 Further information: Contact Marco Gori (Email: marco at dii.unisi.it ), Simone Marinai (Email: simone at dsi.unifi.it) or visit the workshop web page (www.dsi.unifi.it/ANNPR). ***** Note: You can reply to this email with REMOVE in the subject to be eliminated by this list. ***** Best regards, Simone Marinai --------------------------------------------- Simone Marinai Dipartimento di Sistemi e Informatica Via di Santa Marta, 3 50139 Firenze (Italy) +39 (55) 479-6452 Email: simone at dsi.unifi.it From Manuel.Davy at irccyn.ec-nantes.fr Fri Apr 4 10:07:01 2003 From: Manuel.Davy at irccyn.ec-nantes.fr (Manuel Davy) Date: Fri, 04 Apr 2003 17:07:01 +0200 Subject: MACHINE LEARNING SUMMER SCHOOL 2003 Message-ID: <3E8D9F95.8000706@irccyn.ec-nantes.fr> * Apologises if you receive this email several times * CALL FOR PATICIPATION ----------------------------------------------------- MACHINE LEARNING SUMMER SCHOOL 2003 August 4-16, 2003, Tuebingen, Germany http://www.irccyn.ec-nantes.fr/mlschool/ ----------------------------------------------------- Organised by CNRS-AS 66 (France), MPIK Tuebingen (Germany), and the Australian National University **** Applications are now open **** **** Deadline for application is April 30th 2003 **** **** For applications, please visit our web site **** The Summer School is intended for students and researchers alike, who are interested in Machine Learning. Its goal is to present some of the topics which are at the core of modern Learning Theory. The school will be held in the Max Plank Institut fuer Biologische Kybernetik, Tuebingen, Germany between the 4th and the 16th of August, 2003. During this time, we shall present six basic courses, each one covering one of the topics listed below. In addition, there will be advance courses which may focus on additional topics and which will provide background knowledge in machine learning and statistics. Four practical sessions will be organized in small groups. The goal is to provide a 'hands-on' experience of working with machine learning algorithms. They will be directly related to the material introduced in the courses. Basic Courses: * Statistical Learning Theory (O. Bousquet, MPIK Tuebingen) - 8 hours * Independent Component Analysis (J.-F. Cardoso, ENST Paris) - 8 hours * Gaussian Processes (C. Rasmussen, MPIK Tuebingen) - 8 hours * Kernel Algorithms I (A. Smola, ANU) - 6 hours * Kernel Algorithms II (B. Schoelkopf, MPIK Tuebingen) - 6 hours * Pattern Classification (E. Yom-Tov, Technion, Haifa) - 4 hours Advanced Courses: * Monte Carlo Simulation methods (C. Andrieu, University of Bristol) - 4 hours * Bioinformatics (P. Baldi, UC Irvine) - 4 hours * Stochastic Approximation (L. Bottou, NEC Research, Princeton) - 4 hours * Concentration Inequalities (S. Boucheron, LRI Orsay) - 4 hours * Some Mathematical Tools for Machine Learning (C. Burges, Microsoft Research, Redmond) - 4 hours * Minimum Description Length (P. Grunwald, CWI Amsterdam) - 4 hours * Information Retrieval and Language Technology (T. Joachims, Cornell University) - 4 hours * Foundations of Learning (S. Smale, UC Berkeley) - 4 hours * Bayesian Approaches, RVM (M. Tipping, Microsoft Research, Cambridge) - 4 hours * Empirical Inference (V. Vapnik) - evening lecture Practical sessions: * Pattern classification - From data to decision (E. Yom-Tov) * Support Vector Machines (A. Gretton, A. Elisseeff, J. Weston) * Simulation Methods (Manuel Davy) -- ------------------------------------------ Manuel DAVY http://www.irccyn.ec-nantes.fr/~davy/ ------------------------------------------ IRCCyN/CNRS, 1 rue de la Noe, BP 92101, 44321 Nantes cedex 3, France Manuel.Davy at irccyn.ec-nantes.fr T?l: +33 2 40 37 69 09 Fax: +33 2 40 37 69 30 ------------------------------------------- From lorincz at inf.elte.hu Sat Apr 5 01:14:49 2003 From: lorincz at inf.elte.hu (LORINCZ Andras) Date: Sat, 5 Apr 2003 08:14:49 +0200 (CEST) Subject: Software tool for "How to decide what to read" Message-ID: Dear Connectionists: Geoff Hinton was asking for a tool to support decision on what to read (see attachment). The tool, which will be free for Academic use, can be downloaded and tried. Please, visit http://www.coraler.com Related projects on -- hand-free navigation -- anonymous and accountable self-organizing communities can be found at http://people.inf.elte.hu/lorincz/Files/Head_Mouse/Head_Mouse.html http://people.inf.elte.hu/lorincz/pub.html. The present state of the software: It is made of three main parts: 1. Hostess (This is the server. Install kit is under development) 2. MapViewer (Flash and applet versions are ready) 3. MapEditor (Ready) How it works: You view the maps through the MapViewer from your computer You modify, correct and edit maps with MapEditor (Download it and test it!) You publish the maps at your Hostess (the Hostess of your group). The MapEditor allows you -- to connect nodes (html pages, or your own files) with directed arrows -- to insert comments to the nodes -- to render images to the nodes -- to initiate a search at Yahoo (Google requries query limitations or payment) -- to use drag and drop function when adding html pages or documents Other functionalities, which will be included for the end of the summer: -- breaking news detector -- automated domain mapping tool -- automated bookmark integration tool -- automated keyword keyphrase extraction using KEA -- RL based link-highlighting when surfing on the maps Each community can have distributed cryptographic key system for publishing, for editing, and for accountable anonymity. This key system will make use of the ITTC crypto software http://theory.stanford.edu/~dabo/ITTC/ and will be available in the fourth quarter of this year. Looking forward to your feedback, Andras Lorincz From akira at bstu.by Sat Apr 5 05:52:48 2003 From: akira at bstu.by (Akira Imada) Date: Sat, 5 Apr 2003 13:52:48 +0300 Subject: ICNNAI'2003 Call for Papers Message-ID: <01c701c2fb61$7fc7df80$5d1511ac@brpi.local> The Third International Conference on Neural Networks and Artificial Intelligence (ICNNAI'2003) November 12-14, Minsk, Belarus Organized by: Ministry of Education (Belarus) Belarusian State University of Informatics and Radioelectronics Belarus SIG of INNS In cooperation with: International Neural Network Society Brest State Technical University (Belarus) United Institute of Informatics Problems of National Academy of Sciences of Belarus Institute of Computer Information Technologies (Ukraine, Ternopil) Scope The aim of the conference is to present and discuss research results and their applications, to support and accelerate worldwide exchange of ideas. The continuous exchange of scientific and echnical information is of particular importance for the research and the transfer of research to practice. The scope of this conference covers the theory and application of neural networks and techniques of artificial intelligence. New techniques, instruments and both software and hardware components are included. Key-note speakers Prof. Kurosh Madani "Industrial Applications of ANNs". Senart Institute of Technology, University PARIS XII - Val de Marne, http://www.univ-paris12.fr/www/rech/ann/i2s.htm madani at univ-paris12.fr Prof. Helmut A. Mayer "Ontogenetic Teaching of Mobile Autonomous Robots with Dynamic Neurocontrollers". University of Salzburg, Austria, http://www.cosy.sbg.ac.at/~helmut/helmut.html helmut at cosy.sbg.ac.at Prof. Qiangfu Zhao "Recognition, learning and understanding". University of Aizu, Tsuruga, Ikki-machi, Aizu-Wakamatsu City, Fukushima, Japan, qf-zhao at u-aizu.ac.jp http://www.u-aizu.ac.jp/~qf-zhao/ Topics 1. Cognitive Science * Neuro psychological systems * Brain-like models * Learning and memory * Neuro cognition * Models of behaviour * Models of perception 2. Theory and Algorithms * Neural network architectures * Learning algorithms * Self-organizing systems * Chaos theory * Fuzzy neural systems * Genetic algorithms * Neuro dynamics and spiking neuron 3. Neural Networks Applications * Data mining * Signal processing * Intelligent control and mobile robots * Time-series prediction * Pattern recognition and image processing * Speech recognition and language processing * Hardware implementation * Multi-agents systems * Application in engineering, medicine and business * High performance computing * Intelligent sensors General Conference Chair: Mikhail Batura (Belarus) General Conference Co-chairs: Valentin Muravyew (Belarus) Rauf Sadykhov (Belarus) Vladimir Golovko (Belarus) International Program Committee Sung-Bae Cho (Korea) Ian Cloete (Germany) Pasquale Daponte (Italy) Darryl Davis (United Kingdom) Donald MacDonald (United Kingdom) Colin Fyfe (United Kingdom) Akira Imada (Japan) Alexander Galushkin (Russia) Vladimir Golenkov (Belarus) Kurosh Madani (France) Carlo Morabito (Italy) Anatoly Pashkevich (Belarus) Alexander Petrovsky (Belarus) Vincenzo Piuri (Italy) Vladimir Ptitchkin (Belarus) Sarunas Raudys (Lithuania) Hubert Roth (Germany) Vladimir Rubanov (Belarus) Anatoly Sachenko (Ukraine) Valery Terekhov (Russia) Herwig Unger (Germany) Antanas Zilinskas (Lithuania) Local Organizing Committee (Belarus) Alexander Doudkin - Chairman Yury Savitsky - Vice Chairman Valery Ivkovich Marina Loukasheviuchr Anatroly Khomenko Serge Bayrack Leonid Mahnist Oleg Ignatiuk Andrew Dunets Denis Vershok Maksim Vatkin Leonid Podenok Aleksey Otvagin Alexander Inutin Conference location The International Conference on Neural Networks and Artificial Intelligence will be held at Belarusian State University of Informatics and Radioelectronics, Belarus in November 12-14, 2003. Proceedings Accepted papers will be published in conference proceedings. Deadlines Submission Deadline: July 15, 2003 Notification of Acceptance: August 15, 2003 International Program Committee Address: Prof. Rauf Sadykhov (Co-Chairman) Belarusian State University of Informatics and Radioelectronics Brovka str. 6 Minsk, 220027 Belarus fax: +375017 231 09 82 e-mail: rsadykhov at gw.bsuir.unibel.by Prof. Vladimir Golovko (Co-Chairman) Brest State Technical University Moskowskaja 267 Brest, 224017 Belarus fax: +375162 422 127 e-mail: gva at bstu.by Submission instructions Prospective authors are requested to send a paper (maximum 7 pages including figures, tables and references) for review by the International Program Committee. All submissions must be written in English, starting with a succinct statement of the problem, the result achieved, their significance and comparison with previous works (if any), as well as a list of references.The submissions should also include: title of proposed paper, authors names, affiliations, addresses, name of author to contact for correspondence, e-mail address and fax of contact author, topics which best describe the paper (max. 5 keywords). Please submit your paper exclusively in electronic media. Paper should be submitted electronically by 15 July 2003 in doc, postscript or pdf format in accordance with the following address: DOUDKIN at newman.bas-net.by Please put the conference name - ICNNAI'2003 on all correspondence and on the mailing envelope. Detailed information about the conference is available on the web http://lsi.bas-net.by/icnnai.html The City of Minsk Minsk is the capital of the Republic of Belarus. It is located in a picturesque place on the river Svisloch, which was in ancient times one of the busiest trade-routes connecting the Baltic and the Black seas. Minsk is the city where one can find the best pieces of Belarusian cultural heritage: museums and exhibitions, theaters, world famous Belarusian ballet, folklore dancing ensembles and choirs. Numerous scientific centres and leading institutions of higher education, situated in Minsk, are well-known abroad for their fundamental and applied researches. Minsk is a cross-road of the most popular European tours. It is connected by motorways, railways and airlines with all the European capitals and also with the main cities of the world. From David.Cohn at acm.org Sat Apr 5 17:20:01 2003 From: David.Cohn at acm.org (David 'Pablo' Cohn) Date: Sat, 05 Apr 2003 14:20:01 -0800 Subject: Special Issue on Variable and Feature Selection available! Message-ID: <5.2.0.9.0.20030405140200.033fedd0@ux7.sp.cs.cmu.edu> The Journal of Machine Learning Research is very pleased to announce publication of a Special Issue on Variable and Feature Selection. This issue, organized and edited by Isabelle Guyon and Andre Elisseeff, contains 14 papers, including an introduction to the field by the guest editors. In addition to the papers, the many of the authors have made available the data sets and software used in their research. Please visit http://www.jmlr.org for details. ------------------ An Introduction to Variable and Feature Selection Isabelle Guyon, Andr=E9 Elisseeff; JMLR 3(Mar):1157-1182, 2003. Distributional Word Clusters vs. Words for Text Categorization Ron Bekkerman, Ran El-Yaniv, Naftali Tishby, and Yoad Winter; JMLR 3(Mar):1183-1208, 2003. Extensions to Metric-Based Model Selection Yoshua Bengio, Nicolas Chapados; JMLR 3(Mar):1209-1227, 2003. Dimensionality Reduction via Sparse Support Vector Machines Jinbo Bi, Kristin Bennett, Mark Embrechts, Curt Breneman, Minghu Song; JMLR 3(Mar):1229-1243, 2003. Benefitting from the Variables that Variable Selection Discards Rich Caruana, Virginia R. de Sa; JMLR 3(Mar):1245-1264, 2003. A Divisive Information-Theoretic Feature Clustering Algorithm for Text Classification Inderjit S. Dhillon, Subramanyam Mallela, Rahul Kumar; JMLR 3(Mar):1265-1287, 2003. An Extensive Empirical Study of Feature Selection Metrics for Text Classification George Forman; JMLR 3(Mar):1289-1305, 2003. Sufficient Dimensionality Reduction Amir Globerson, Naftali Tishby; JMLR 3(Mar):1307-1331, 2003. Grafting: Fast, Incremental Feature Selection by Gradient Descent in Function Space Simon Perkins, Kevin Lacker, James Theiler; JMLR 3(Mar):1333-1356, 2003. Variable Selection Using SVM-based Criteria Alain Rakotomamonjy; JMLR 3(Mar):1357-1370, 2003. Overfitting in Making Comparisons Between Variable Selection Methods Juha Reunanen; JMLR 3(Mar):1371-1382, 2003. MLPs (Mono-Layer Polynomials and Multi-Layer Perceptrons) for Nonlinear Modeling Isabelle Rivals, L=E9on Personnaz; JMLR 3(Mar):1383-1398, 2003. Ranking a Random Feature for Variable and Feature Selection Herv=E9 Stoppiglia, G=E9rard Dreyfus, R=E9mi Dubois, Yacine Oussar; JMLR 3(Mar):1399-1414, 2003. Feature Extraction by Non-Parametric Mutual Information Maximization Kari Torkkola; JMLR 3(Mar):1415-1438, 2003. Use of the Zero-Norm with Linear Models and Kernel Methods Jason Weston, Andr=E9 Elisseeff, Bernhard Sch=F6lkopf, Mike Tipping; JMLR 3(Mar):1439-1461, 2003. ------------------ These, and all previous papers are available electronically at http://www.jmlr.org/ in PostScript and PDF formats. Many are also available in HTML. The papers of Volume 1 and 2 are also available in hardcopy from the MIT Press; please see http://mitpress.mit.edu/JMLR for details. From giro-ci0 at wpmail.paisley.ac.uk Sun Apr 6 08:39:01 2003 From: giro-ci0 at wpmail.paisley.ac.uk (Mark Girolami) Date: Sun, 06 Apr 2003 13:39:01 +0100 Subject: Paper Available : Sparse Kernel Density Estimation Message-ID: Probability Density Estimation from Optimally Condensed Data Samples. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2003, in press. Mark Girolami & Chao He. Paper and MATLAB Code Available from: http://cis.paisley.ac.uk/giro-ci0/reddens/ Abstract The requirement to reduce the computational cost of evaluating a point probability density estimate when employing a Parzen window estimator is a well known problem. This paper presents the Reduced Set Density Estimator that provides a kernel based density estimator which employs a small percentage of the available data sample and is optimal in the L2 sense. Whilst only requiring O(N^2) optimisation routines to estimate the required weighting coefficients, the proposed method provides similar levels of performance accuracy and sparseness of representation as Support Vector Machine density estimation, which requires O(N^3) optimisation routines, and which has previously been shown to consistently outperform Gaussian Mixture Models. It is also demonstrated that the proposed density estimator consistently provides superior density estimates for similar levels of data reduction to that provided by the recently proposed Density Based Multiscale Data Condensation algorithm and in addition has comparable computational scaling. The additional advantage of the proposed method is that no extra free parameters are introduced such as regularisation, bin width or condensation ratios making this method a very simple and straightforward approach to providing a reduced set density estimator with comparable accuracy to that of the full sample Parzen density estimator. Legal disclaimer -------------------------- The information transmitted is the property of the University of Paisley and is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Statements and opinions expressed in this e-mail may not represent those of the company. Any review, retransmission, dissemination and other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender immediately and delete the material from any computer. -------------------------- From levys at wlu.edu Sun Apr 6 22:59:18 2003 From: levys at wlu.edu (Simon Levy) Date: Sun, 06 Apr 2003 22:59:18 -0400 Subject: Invitation to submit to JCIS 2003 special session on recurrent neural nets Message-ID: <3E90E986.6020401@wlu.edu> Dear Connectionists, I am soliciting submissions for a special session of the next Joint Conference on Information Sciences (http://www.ee.duke.edu/jcis/). The conference will be held Sep 26-30 2003 at the Embassy Suites Hotel and Conference Center in Cary, North Carolina, and the session will take place one morning or afternoon during those four days. The topic of the session will be "New Frontiers for Recurrent Neural Networks", with the goal of sharing news on current work (including work in progress) with other connectionists, in a friendly atmosphere. Last year's special session included presentations on using recurrent networks for modeling lexical development, goal management, short-term memory, and emergent rule-like behavior. Papers presented at the session (four pages in length) will be published in the JCIS 2003 Conference Proceedings. All submission and questions should be directed to me (levys at wlu.edu). The camera-ready deadline is June 16. Thank you for your attention, and I look forward to hearing from you. Sincerely, Simon ======================== Simon D. Levy Assistant Professor Computer Science Department Washington & Lee University Lexington, VA 24450 540-458-8419 (voice) 540-458-8479 (fax) levys at wlu.edu http://www.cs.wlu.edu/~levy From a.van.ooyen at nih.knaw.nl Mon Apr 7 04:46:01 2003 From: a.van.ooyen at nih.knaw.nl (Arjen van Ooyen) Date: Mon, 07 Apr 2003 10:46:01 +0200 Subject: Summer School of Brain Research Message-ID: <3E913AC9.336D3773@nih.knaw.nl> Dear colleague, The Netherlands Institute for Brain Research and the Netherlands Ophthalmic Research Institute are organizing this year the 23rd International Summer School of Brain Research from August 25-29, 2003, in Amsterdam. The program is dedicated to the theme: Development, dynamics and pathology of neuronal networks: from molecules to functional circuits. The Summer School will focus on key mechanisms in the development of neurons into circuits with functional dynamics, and will link the dynamics in neural circuits with cognitive / behavioral processes. In this respect we wish to emphasize (1) molecular and cell-biological mechanisms of neuronal network development and plasticity, (2) understanding activity in neuronal networks in relation to their structure, and (3) understanding normal and deficient neural circuitry at the cognitive and behavioral level. The Summer School aims at providing a forum for discussing broad views as well as latest developments on the above topics. The lectures are presented by internationally renowned scientists. The target groups are PhD students, postdoctoral fellows, senior researchers and clinicians. Please visit the Summer School website http://www.nih.knaw.nl/summerschool for information and registration. Best regards, -- Dr. Arjen van Ooyen Netherlands Institute for Brain Research Meibergdreef 33, 1105 AZ Amsterdam, The Netherlands Email: A.van.Ooyen at nih.knaw.nl Website: http://www.anc.ed.ac.uk/~arjen Phone: +31.20.5665483 Fax: +31.20.6961006 From juergen at idsia.ch Mon Apr 7 08:30:04 2003 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Mon, 07 Apr 2003 14:30:04 +0200 Subject: New AI & 2 postdoc positions Message-ID: <3E916F4C.5010403@idsia.ch> The New AI: General & Sound & Relevant for Physics by J. Schmidhuber, IDSIA. To appear in "Artificial General Intelligence" (edited by B. Goertzel and C. Pennachin). Also avaliable as arxiv:cs.AI/0302012: http://www.idsia.ch/~juergen/newai/newai.html Abstract. Most traditional artificial intelligence (AI) systems of the past 50 years are either very limited, or based on heuristics, or both. The new millennium, however, has brought substantial progress in the field of theoretically optimal and practically feasible algorithms for prediction, search, inductive inference based on Occam's razor, problem solving, decision making, and reinforcement learning in environments of a very general type. Since inductive inference is at the heart of all inductive sciences, some of the results are relevant not only for AI and computer science but also for physics, provoking nontraditional predictions based on Zuse's thesis of the computer-generated universe. Related link to Schmidhuber's law ;-) http://www.idsia.ch/~juergen/computerhistory.html --------------------------------------------------------- Two postdoc jobs (optimal search and recurrent networks): http://www.idsia.ch/~juergen/jobs2003.html http://www.idsia.ch/~juergen/oops.html http://www.idsia.ch/~juergen/rnn.html Please forward to potential candidates! JS http://www.idsia.ch/~juergen/ From mark.laubach at yale.edu Tue Apr 8 14:16:34 2003 From: mark.laubach at yale.edu (Mark Laubach) Date: Tue, 08 Apr 2003 14:16:34 -0400 Subject: POSTDOCTORAL POSITION AVAILABLE: NEURONAL ENSEMBLE RECORDING Message-ID: Hello, My group is currently seeking to fill a postdoctoral slot for a DARPA-supported project on the auditory cortex and brain-machine interfaces (see below). The position offers an excellent opportunity to learn how to do neuronal ensemble recordings and state-of-the-art methods for analyzing multi-channel spike train and field potential data. I would appreciate hearing from anyone interested in the position via email. Thanks. -Mark ----- POSTDOCTORAL POSITION AVAILABLE: NEURONAL ENSEMBLE RECORDING IN AUDITORY CORTEX A postdoctoral position is available starting September 1, 2003 as part of a DARPA-sponsored collaborative project involving the laboratories of Drs. Jon Kaas and Troy Hackett at Vanderbilt University, Dr. Mandayam Srinivasan at MIT, and Dr. Mark Laubach at The John B Pierce Laboratory, a research institute affiliated with Yale University. The position is available in the Laubach group at the Pierce Laboratory. The ideal candidate would be an expert on the auditory cortex, have experience using neurophysiological and operant conditioning methods, and familiarity with software such as NEx, Matlab, and R/S-Plus. Prior experience with neuronal ensemble recording methods or, at the very least, a background in neurophysiology or behavioral neuroscience and a strong desire to learn ensemble recording is required. Strong skills in teamwork and communication are also essential for the position. This person will collect and analyze data from ensembles of neurons in the auditory cortex collected during the learning and performance of simple and choice reaction time tasks. In addition, methods for microstimulation of cortical neurons (developed through a collaboration with Dr. John Chapin's group at SUNY Brooklyn) will be implemented and tested. The candidate will also learn about novel methods for analyzing neuronal ensemble data sets that are being developed by our group in collaboration with Prof. Ronald Coifman's group in the Applied Mathematics Dept at Yale. If interested, please send a vita, list of publications, summary of research experience, and names of three individuals who can be contacted as references to: Mark Laubach, Ph.D. The John B. Pierce Laboratory Yale University School of Medicine 290 Congress Ave New Haven CT 06519 E-mail - mark.laubach at yale.edu WWW - http://spikelab.jbpierce.org The review of applications will begin April 15, 2003 and will continue until the position is filled. E.O.E. From kawamura at mail.sci.yamaguchi-u.ac.jp Wed Apr 9 00:23:49 2003 From: kawamura at mail.sci.yamaguchi-u.ac.jp (kawamura@mail.sci.yamaguchi-u.ac.jp) Date: Wed, 09 Apr 2003 13:23:49 +0900 (JST) Subject: Paper Available : Low-dimensional chaos induced by frustration Message-ID: <20030409.132349.846948971.kawamura@sci.yamaguchi-u.ac.jp> Dear Connectionists, We are pleased to announce the availability of our recent paper. "Low-dimensional chaos induced by frustration in a non-monotonic system" M. Kawamura, R. Tokunaga and M. Okada Europhysics Letters (will be appeared) Preprint is available at http://arxiv.org/abs/cond-mat/0205471 Abstract: We report a novel mechanism for the occurrence of chaos at the macroscopic level induced by the frustration of interaction, namely frustration-induced chaos, in a non-monotonic sequential associative memory model. We succeed in deriving exact macroscopic dynamical equations from the microscopic dynamics in the case of the thermodynamic limit and prove that two order parameters dominate this large-degree-of-freedom system. Two-parameter bifurcation diagrams are obtained from the order-parameter equations. Then we analytically show that the chaos is low-dimensional at the macroscopic level when the system has some degree of frustration, but that the chaos definitely does not occur without the frustration. Best regards, Masaki Kawamura Faculty of Science, Yamaguchi University, Yoshida 1677-1, Yamaguchi 753-8512 Japan E-mail: kawamura at sci.yamaguchi-u.ac.jp From Nicolas.Rougier at loria.fr Fri Apr 11 03:58:59 2003 From: Nicolas.Rougier at loria.fr (Nicolas Rougier) Date: 11 Apr 2003 09:58:59 +0200 Subject: Post-doctoral fellowship Message-ID: <1050047939.13555.29.camel@hopfield.loria.fr> The LORIA laboratory offers a one-year fellowship for a post-doctoral researcher: --------------------------------------------------------------------- A connectionist architecture for a multi-level approach of navigation --------------------------------------------------------------------- We are studying the different kinds of information representations that may be useful to an autonomous robot seen as a cognitive system. Recent studies corresponded to integrate data from neurosciences in connectionist computational models and we studied in this framework how both procedural, declarative and working memories were identified as emerging from specific neuronal structures and critical at different levels of information processing. For navigational tasks, there exists today an extensive literature on computational models that are grounded on a core mechanism: the chaining together of neighboring locations in space. Having a precise goal to reach, this kind of chaining can then be used through the equivalent of a backward search to reach the goal from a given place. Nonetheless, if this strategy can account for quite short spatio-temporal sequences, it is our belief it cannot account for a more global and complex navigational behaviour. Based on our understanding on the role of the different information representation, we think that going from one place to another distant one implies scheduling of action at several different levels, both in time and space. Specifically, we anticipate that a model grounded on data from prefrontal cortex studies could encode navigational information at varying levels of spatial and temporal resolutions and would then be able to perform a precise contention scheduling of the task. For example, going from one place A1 to another place A2 does not necessarily imply to know that at any given time it is necessary to go through each of the Ai places. It is more likely that at any given time only a small subset of the current path is known while the whole path can be described at a higher resolution (by using abstract representations like rooms or places for example). In this framework, we aim at understanding how such multi-level representations can emerge from a connectionist computationnal model and how it can promote an efficient navigation based on multi-level representations. From previous work and collaboration, we have found that data describing the prefrontal and basal ganglia systems give hints concerning the design of an efficient system and we would like to go further this way by designing a computational model for the navigation of a real robot. ------------------------------------------------------------------------ The candidate must have a PhD in cognitive science, computer science, or a related discipline and expertise in neural network modelling. Experience in robotic would be an asset but is not essential. Deadline for applications is 04/15/2003. Contact: rougier at loria.fr Dr Nicolas Rougier. From l.wiskott at biologie.hu-berlin.de Fri Apr 11 09:54:43 2003 From: l.wiskott at biologie.hu-berlin.de (Laurenz Wiskott) Date: 11 Apr 2003 13:54:43 -0000 Subject: paper available: improved cumulant based ICA Message-ID: <20030411135443.11683.qmail@huxley.biologie.hu-berlin.de> CuBICA: INDEPENDENT COMPONENT ANALYSIS BY SIMULTANEOUS THIRD- AND FOURTH-ORDER CUMULANT DIAGONALIZATION by Tobias Blaschke and Laurenz Wiskott Abstract: CuBICA, an improved method for independent component analysis (ICA) based on the diagonalization of cumulant tensors is proposed. It is based on Comon's algorithm [Comon, 1994] but it takes third- and fourth-order cumulant tensors into account simultaneously. The underlying contrast function is also mathematically much simpler and has a more intuitive interpretation. It is therefore easier to optimize and approximate. A comparison with Comon's and three other ICA-algorithms on different data sets demonstrates its performance. Available from: http://www.compscipreprints.com/comp/Preprint/blaschke/20030409/1/ http://itb.biologie.hu-berlin.de/~wiskott/Abstracts/BlasWisk2003a.html Reference: Blaschke, T. and Wiskott, L. (2003). CuBICA: Independent Component Analysis by Simultaneous Third- and Fourth-Order Cumulant Diagonalization. Computer Science Preprint Server (CSPS): Computational Intelligence/0304002, http://www.compscipreprints.com/comp/Preprint/blaschke/20030409/1/ (). -- Dr. Laurenz Wiskott, Institute for Theoretical Biology, Berlin http://itb.biologie.hu-berlin.de/~wiskott/ l.wiskott at biologie.hu-berlin.de From kdharris at andromeda.rutgers.edu Fri Apr 11 09:52:33 2003 From: kdharris at andromeda.rutgers.edu (Ken Harris) Date: Fri, 11 Apr 2003 09:52:33 -0400 Subject: Postdoctoral positions Message-ID: POSTDOCTORAL POSITIONS IN COMPUTATIONAL NEUROSCIENCE Two postdoctoral positions are available to conduct interdisciplinary research on neuronal population coding, working with Drs Kenneth Harris and Gyorgy Buzsaki, at Rutgers University. Information is processed in the brain by the co-operative action of large numbers of neurons. It is now possible to record from hundreds of neurons in parallel, offering an unprecedented opportunity to discover the operating principles of neuronal circuits. However, the full potential of this data will only be realized through radical innovation in the techniques used for its analysis and interpretation. We are seeking postdoctoral associates to develop and use new methods for analysis of simultaneously recorded spike trains from hippocampus, neocortex, and other systems, and to build models of population function based on their conclusions. The ideal candidate would have a background in mathematics, physics, statistics, computer science, or a related field, as well as a strong interest in neuroscience. Ability to program in C/C++ and MATLAB is also highly desirable. Rutgers University is an equal opportunity/affirmative action employer. Qualified women and minority candidates are encouraged to apply. Interested candidates should send a CV, statement of research interests, and names and email addresses of two references to kdharris at andromeda.rutgers.edu. ------------------------ Kenneth D. Harris, Ph.D. Center for Molecular and Behavioral Neuroscience Rutgers, The State University of New Jersey 197 University Avenue Newark NJ 07102, USA phone: 973 353 1080, x3360 fax: 973 353 1820 email: kdharris at andromeda.rutgers.edu From piuri at elet.polimi.it Sat Apr 12 08:16:53 2003 From: piuri at elet.polimi.it (Vincenzo Piuri) Date: Sat, 12 Apr 2003 14:16:53 +0200 Subject: IEEE Neural Networks Society: Competition for a New Logo Message-ID: <5.1.0.14.0.20030412141031.02a9a830@mail.elet.polimi.it> A New Logo for a New Society Participate to the competition to design our new logo! Dear Colleague the areas of interest of the IEEE Neural Networks Society encompass the entire breadth of computational intelligence. Our well-known logo from the IEEE Neural Networks Council, used successfully to identify our events and activities, no longer fully represents our collective research, applications, interests, and challenges. It is therefore time to look for a new logo that will represent all of us!! Neural paradigms should still be present in our insignia, but also fuzzy systems and evolutionary computation should be recognized. A competition, open to all members of our Society, is launched to design the new logo. It should have preferably a horizontal layout, similar to the IEEE logo. Any idea (including the craziest) is welcome! How can you participate to the competition? Its easy! Draw your proposals for the IEEE NNS logo and submit them electronically to me at piuri at dti.unimi.it by 10 July 2003. Any major electronic format is acceptable (e.g., jpeg, tiff, gif, pdf, ps). When submitting the logo, please, include your first and last name, your complete affiliation, and your IEEE membership number. The winner will be required to transfer all rights concerning the logo to the IEEE NN Society. For further information, please do not hesitate to contact me. Best regards Vincenzo Piuri IEEE Neural Networks Society Vice President for Members Activities Vincenzo Piuri University of Milan, Department of Information Technologies via Bramante 65, 26013 Crema (CR), Italy phone: +39-02-5033-0066 or +39-0373-898-066 secretary: +39-02-5033-0011 or +39-0373-898-011 fax: +39-02-5033-0010 email: piuri at elet.polimi.it From T.J.Prescott at sheffield.ac.uk Thu Apr 17 07:18:53 2003 From: T.J.Prescott at sheffield.ac.uk (Tony Prescott) Date: Thu, 17 Apr 2003 12:18:53 +0100 Subject: post doctoral position Message-ID: *** Please forward to interested parties, apologies for repeat postings *** Adaptive Behaviour Research Group Department of Psychology The University of Sheffield RESEARCH ASSOCIATE Applications are invited for a research associate post, tenable for three years from 1st July 2003. This is a joint project between the Adaptive Behaviour Research Group at the University of Sheffield (www.shef.ac.uk/~abrg) and the Intelligent Autonomous Systems Laboratory at the University of the West of England in Bristol (www.ias.uwe.ac.uk). The aim of this interdisciplinary project is to develop a tactile 'whisker' sensor array for an autonomous robot with response characteristics similar to those of the rat facial vibrissae. The work at Sheffield will focus on the development of computational models of the whisker-processing pathways in the rat brain (although no work on animals is involved). Applicants should have a good honours degree in Neuroscience, Mathematics, Physics, Engineering or related field, and should hold or expect to hold a PhD, preferably in computational neuroscience or a related field of mathematical modelling. Salary on the IA/IB scale for Research Staff in the range of 18,265-23,296 UKP per annum, according to experience. Informal enquiries to: Dr. Tony Prescott (Tel: +44 (0)114 222 6547; e-mail: t.j.prescott at shef.ac.uk). Further particulars are obtainable from: The Recruitment Service, Personnel Department, Firth Court, Western Bank, Sheffield S10 2UH (Tel: +44 (0)114 279 9800; e-mail: jobs @sheffield.ac.uk), where applications (including a curriculum vitae and the names and addresses of three referees) should be sent. Closing date for applications: 16th May 2003. From bogus@does.not.exist.com Thu Apr 17 09:50:13 2003 From: bogus@does.not.exist.com () Date: Thu, 17 Apr 2003 14:50:13 +0100 Subject: Postdoctoral Research Positions at Microsoft Research Cambridge Message-ID: <6EDEB53BA6EA96458F3CEC96BB0282D20343C6C1@tvp-msg-03.europe.corp.microsoft.com> From terry at salk.edu Thu Apr 17 23:50:34 2003 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 17 Apr 2003 20:50:34 -0700 (PDT) Subject: NEURAL COMPUTATION 15:5 In-Reply-To: <200303101837.h2AIbeS22678@purkinje.salk.edu> Message-ID: <200304180350.h3I3oYC94290@purkinje.salk.edu> Neural Computation - Contents - Volume 15, Number 5 - May 1, 2003 ARTICLE Estimating a State-Space Model From Point Process Observations Anne C. Smith and Emery N. Brown LETTERS Sequential Bayesian Decoding with a Population of Neurons Si Wu, Danmei Chen, Mehesan Niranjan, and Shun-ichi Amari Learning Coefficients of Layered Models When the True Distribution Mismatches the Singularities Sumio Watanabe and Shun-ichi Amari Gamma Rhythmic Bursts: Coherence Control in Networks of Cortical Pyramidal Neurons Toshio Aoyagi, Takashi Takekawa and Tomoki Fukai Manhattan World: Orientation and Outlier Detection by Bayesian Inference James M. Coughlan and A. L. Yuille Kernal-Based Nonlinear Blind Source Separation Stefan Harmeling, Andreas Ziehe, Motoaki Kawanabe, and Klaus-Robert Mueller An Algorithm of Supervised Learning for Multilayer Neural Networks Zheng Tang, XuGang Wang, Hiroki Tamura, Masahiro Ishii The Time-Organized Map Algorithm: Extending the Self-Organizing Map to Spatiotemporal Signals Jan C. Wiemer New Conditions for Global Stability of Cohen-Grossberg Neural Networks Wenlian Lu and Tianping Chen ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2003 - VOLUME 15 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $95 $101.65 $143 Institution $590 $631.30 $638 * 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 Sebastian_Thrun at heaven.learning.cs.cmu.edu Sat Apr 19 15:14:46 2003 From: Sebastian_Thrun at heaven.learning.cs.cmu.edu (Sebastian Thrun) Date: Sat, 19 Apr 2003 15:14:46 -0400 Subject: NIPS*2003 Call For Papers Message-ID: --- please post --- ------------------------------------------------------------ CALL FOR PAPERS Neural Information Processing Systems, Natural and Synthetic Monday, December 8 - Saturday December 13, 2003 Vancouver, British Columbia, Canada www.nips.cc ------------------------------------------------------------ Submissions are solicited for the seventeenth meeting of an interdisciplinary conference which brings together researchers interested in all aspects of neural and statistical computation. The conference will include invited talks as well as oral and poster presentations of refereed papers. It is single track and highly selective. Preceding the main conference will be one day of tutorials (December 8), and following it will be two days of workshops at Whistler/Blackcomb ski resort (December 12-13). INVITED SPEAKERS: Anders Dale, Harvard University: Relating Brain Imaging Signals to Biophysical Models of Neuronal Circuits; Paul Ekman, UC San Francisco: About Face: What We Have Learned Through Measuring Facial Movements; Michale Fee, Bell Labs, Lucent Technologies: Time and Sequence in the Brain: Insights from a Songbird; Marc Mezard, Universite de Paris Sud: Analytic and Algorithmic Solutions of Random Satisfiability Problems; Elissa Newport, University of Rochester, Statistical language learning in human infants and adults; David Salesin, University of Washington and Microsoft Research: The Need for Machine Learning in Computer Graphics. TUTORIAL SPEAKERS: Stephen Boyd, Stanford University: Convex Optimization and Applications; David Karger, MIT: Algorithmic Tools Applied to Learning and Inference Problems; Daniel D. Lee, University of Pennsylvania: Learning in Sensorimotor Systems; David Lowe, University of British Columbia: Real-time Object Recognition using Invariant Local Image Features; Klaus-Robert Mueller, Fraunhofer FIRST: Towards Brain Computer Interfacing; Zach Mainen, Cold Spring Harbor Laboratory: Neural Coding and the Olfactory System; SUBMISSIONS: Papers are solicited in all areas of neural and statistical computation, including (but not limited to) the following: o Algorithms and Architectures: statistical learning algorithms, neural networks, kernel methods, graphical models, Gaussian processes, independent component analysis, model selection, combinatorial optimization. o Applications: innovative applications or fielded systems that use machine learning, including systems for time series prediction, bioinformatics, text/web analysis, multimedia processing, and robotics. o Brain Imaging: neuroimaging, cognitive neuroscience, EEG (electroencephalogram), ERP (event related potentials), MEG (magnetoencephalogram), fMRI (functional magnetic resonance imaging), brain mapping, brain segmentation. o Cognitive Science and Artificial Intelligence: theoretical, computational, or experimental studies of perception, psychophysics, human or animal learning, memory, reasoning, problem solving, language, and neuropsychology. o Control and Reinforcement Learning: decision and control, exploration, planning, navigation, Markov decision processes, game-playing, multi-agent coordination, computational models of classical and operant conditioning. o Emerging Technologies: analog and digital VLSI, neuromorphic engineering, computational sensors and actuators, microrobotics, bioMEMS, neural prostheses, photonics, molecular and quantum computing. o Learning Theory: generalization and regularization, information theory, statistical physics of learning, Bayesian methods, approximation bounds, online learning and dynamics. o Neuroscience: theoretical and experimental studies of processing, and transmission of information in biological neurons and networks, including spike train generation, synaptic modulation, plasticity and adaptation. o Speech and Signal Processing: recognition, coding, synthesis, denoising, segmentation, source separation, auditory perception, psychoacoustics, dynamical systems, recurrent networks, Markov models. o Visual Processing: image processing and coding, segmentation, object detection and recognition, motion detection and tracking, visual psychophysics, visual scene analysis and interpretation. o Demonstrations: Authors wishing to submit to the demonstration track should consult the conference web site. REVIEW CRITERIA: Submissions will be refereed on the basis of technical quality, novelty, significance, and clarity. Authors new to NIPS are particularly encouraged to submit. There will be an opportunity after the meeting to revise accepted manuscripts. PAPER FORMAT: Submissions may be up to eight pages in length, including figures and references, using a font no smaller than 10 point. Text is to be confined within a 8.25in by 5in rectangle. Submissions violating these guidelines will not be considered. Templates will be posted at the NIPS Website nips.cc. SUBMISSION INSTRUCTIONS: NIPS accepts only electronic submissions in postscript and PDF format. The conference web site will accept electronic submissions from May 19, 2003 until midnight, June 6, 2003, Pacific daylight time. ORGANIZING COMMITTEE: General Chair, Sebastian Thrun, Carnegie Mellon University; Program Chair, Lawrence Saul, University of Pennsylvania; Tutorials Chair, Sam Roweis, University of Toronto; Workshops Co-chairs, Robert Jacobs, University of Rochester, Satinder Singh Baveja, University of Michigan; Demonstrations Chairs, Shih-Chii Liu, ETH/University of Zurich, Tobi Delbruck, ETH/University of Zurich; Publications Chair, Bernhard Schoelkopf, Max Planck Gesellschaft Tuebingen; Publicity Chair, Klaus Robert Mueller, Fraunhofer FIRST; Online Proceedings Chair, Andrew McCallum, University of Massachusetts Amherst; Volunteers Chair, Dale Schuurmans, University of Waterloo. PROGRAM COMMITTEE: Lawrence Saul (Chair), University of Pennsylvania; Peter Bartlett, UC Berkeley; Samy Bengio, IDIAP; Chris Burges, Microsoft Research; Rich Caruana, Cornell University; Ralph Etienne-Cummings, Johns Hopkins University and University of Maryland, College Park; Geoff Hinton, University of Toronto; John Lafferty, Carnegie Mellon University; Mike Lewicki, Carnegie Mellon University; Michael Littman, Rutgers University; Andrew McCallum, University of Massachusetts Amherst; Rajesh Rao, University of Washington; Jianbo Shi, University of Pennsylvania; Richard Shiffrin, Indiana University; Yoram Singer, Hebrew University; Alexander Smola, Australian National University; Martin Wainwright, UC Berkeley. PAPERS MUST BE SUBMITTED BY JUNE 6, 2003 --- Please Post --- From Sebastian_Thrun at heaven.learning.cs.cmu.edu Tue Apr 22 12:55:31 2003 From: Sebastian_Thrun at heaven.learning.cs.cmu.edu (Sebastian Thrun) Date: Tue, 22 Apr 2003 12:55:31 -0400 Subject: NIPS*2003 Call for Workshop Proposals Message-ID: --- Please Post --- ------------------------------------------------------------ CALL FOR WORKSHOP PROPOSALS Neural Information Processing Systems, Natural and Synthetic NIPS*2003 Post-Conference Workshops, December 12 and 13, 2003 Whistler/Blackcomb Resort, BC, Canada www.nips.cc ------------------------------------------------------------ Following the regular program of the Neural Information Processing Systems 2003 conference in Vancouver, BC, Canada, workshops on various current topics in neural information processing will be held on December 12 and 13, 2003, in Whistler, BC, Canada. We invite researchers interested in chairing one of these workshops to submit workshop proposals. The goal of the workshops is to provide an informal forum for researchers to discuss important research questions and challenges. Controversial issues, open problems, and comparisons of competing approaches are encouraged and preferred as workshop topics. Representation of alternative viewpoints and panel-style discussions are particularly encouraged. Workshop topics include, but are not limited to, the following: Active Learning, Attention, Audition, Bayesian Networks, Bayesian Statistics, Benchmarking, Bioinformatics, Brain Imaging, Computational Complexity, Control, Genetic Algorithms, Graphical Models, Hippocampus and Memory, Human-Computer Interfaces, Hybrid Supervised/Unsupervised Learning, Implementations, Independent Component Analysis, Kernel Methods, Mean-Field Methods, Music, Network Dynamics, Neural Coding, Neural Plasticity, On-Line Learning, Optimization, Recurrent Nets, Robot Learning, Rule Extraction, Self-Organization, Sensory Biophysics, Signal Processing, Spike Timing, Support Vector Machines, Speech, Time Series, Topological Maps, and Vision. Detailed descriptions of previous workshops may be found at http://www.cs.cmu.edu/afs/cs/project/nips-6/nips2002/nips-papers.html. There will be six hours of workshop meetings per day, split into morning and afternoon sessions, with free time in between for ongoing individual exchange or outdoor activities. Selected workshops may be invited to submit proceedings for publication in the post-NIPS workshops monographs series published by the MIT Press. Workshop organizers have several responsibilities including: o Coordinating workshop participation and content, which includes arranging short informal presentations by experts, arranging for expert commentators to sit on a discussion panel, formulating a set of discussion topics, etc. o Moderating the discussion, and reporting its findings and conclusions to the group during evening plenary sessions o Writing a brief summary and/or coordinating submitted material for post-conference electronic dissemination. Interested parties must submit a proposal for a workshop via email by August 1, 2003. Proposals should include title, description of what the workshop is to address and accomplish, proposed workshop length (1 or 2 days), planned format (e.g., lectures, group discussions, panel discussion, combinations of the above, etc.), and proposed speakers. Names of potential invitees should be given where possible. Preference will be given to workshops that reserve a significant portion of time for open discussion or panel discussion, as opposed to pure "mini-conference" format. An example format is: o Tutorial lecture providing background and introducing terminology relevant to the topic. o Two short lectures introducing different approaches, alternating with discussions after each lecture. o Discussion or panel presentation. o Short talks or panels alternating with discussion and question/answer sessions. o General discussion and wrap-up. We suggest that organizers allocate at least 50% of the workshop schedule to questions, discussion, and breaks. Past experience suggests that workshops otherwise degrade into mini-conferences as talks begin to run over. For the same reason, we strongly recommend that each workshop include no more than 12 talks per day. The proposal should motivate why the topic is of interest, why it should be discussed, and who the targeted group of participants is. It also should include a brief resume of the prospective workshop chair with a list of publications to establish scholarship in the field. We encourage workshops that build, continue, or arise from one or more workshops from previous years. Please mention any such connections. NIPS does not provide travel funding for workshop speakers. In the past, some workshops have sought and received funding from external sources to bring in outside speakers. In addition, the organizers of each accepted workshop can name up to four people (six people for 2-day workshops) to receive discounted registration for the workshop program. Submissions should include the name, address, email address, phone and fax numbers for all organizers. If there is more than one organizer, please designate one organizer as the primary contact. Proposals should be emailed as plain text to: nips-workshop-proposal at bcs.rochester.edu Please do not use attachments, Microsoft Word, postscript, html, or pdf files. Questions may be addressed to: nips-workshop-admin at bcs.rochester.edu Information about the main conference and the workshop program can be found at http://nips.cc/ Robert A. Jacobs, University of Rochester Satinder Singh, University of Michigan NIPS*2003 Workshops Co-Chairs PROPOSALS MUST BE RECEIVED BY AUGUST 1, 2003 --- Please Post --- From Sebastian_Thrun at heaven.learning.cs.cmu.edu Tue Apr 22 12:56:23 2003 From: Sebastian_Thrun at heaven.learning.cs.cmu.edu (Sebastian Thrun) Date: Tue, 22 Apr 2003 12:56:23 -0400 Subject: NIPS*2003 Call for Demonstrations Message-ID: --- Please Post --- ------------------------------------------------------------ CALL FOR DEMONSTRATIONS Neural Information Processing Systems, Natural and Synthetic Monday, December 8 - Saturday December 13, 2003 Vancouver, British Columbia, Canada www.nips.cc ------------------------------------------------------------ Based on the success in 2002, the Neural Information Processing Systems conference will once again include a separate track for demonstrations. The demonstrations will take place in parallel with the poster sessions at the NIPS*2003 conference. Example areas of interest for the demonstrations track include, but are by no means limited to the following: o Analog and digital VLSI o Neuromorphic Engineering o Computational sensors and actuators o Robotics o bioMEMS (microelectromechanical systems) o Biomedical instrumentation o Neural prostheses o Photonics o Real-time multimedia systems o Large-scale neural emulators o Software demonstrations of novel algorithms NIPS is an interdisciplinary conference, which attracts cognitive scientists, computer scientists, engineers, neuroscientists, physicists, statisticians, and mathematicians interested in all aspects of neural and statistical processing and computation. The demonstration track enables researchers to highlight scientific advances, systems, and technologies in ways that go beyond conventional poster presentations. It will provide a unique forum for demonstrating advanced technologies (hardware and software), and fostering the direct exchange of knowledge. We hope that this track will stimulate interactions between researchers from different fields (for example, roboticists and neuromorphic engineers) and encourage new collaboration between researchers in theoretical fields and those in more applied fields. Submissions accepted in the demonstrations track will be published on the NIPS web site, but will not appear in printed proceedings. However, submitting your work to the demonstration track by no means precludes the submission of a companion paper to the regular NIPS conference. In fact, joint submissions are very much encouraged. We also encourage authors submitting demonstrations to consider organizing a workshop at NIPS*2003. Note that the deadline for paper submissions is July 1, 2003, and for demonstration and workshop proposals the submission deadline is August 1, 2003. Please see http://nips.cc for further details. There will be a separate room for these demonstrations and participants will have access to power strips, tables and poster boards. VCRs and monitors will also be provided on request. Participants are responsible for ensuring that their demonstration is sufficiently portable; additional hardware beyond that specified above will not be provided by NIPS but might be provided at a cost if available. SUBMISSION INSTRUCTIONS: All proposals for demonstrations will be reviewed by the Demonstrations Co-Chairs. Interested parties should submit a brief description of their proposed demonstration via email by August 1, 2003. Proposals should include a title, description of the device or system to be demonstrated, main results, novelty and significance of the work, any related publications, and estimated space requirements for the demonstration. Please include the name, address, email address, phone and fax numbers for all co-authors on the submitted work, and indicate whether a related paper has also been submitted to NIPS*2003. Proposals should be emailed to shih at ini.phys.ethz.ch, and should be in plain ascii text, postscript or pdf. Questions may also be addressed to shih at ini.phys.ethz.ch. Information about the main conference and the workshop program can be found at http://nips.cc. Shih-Chii Liu and Tobi Delbrueck, Institute of Neuroinformatics, University of Zurich, ETH Zurich NIPS*2003 Demonstrations Co-Chairs PROPOSALS MUST BE RECEIVED BY AUGUST 1, 2003 --- Please Post --- From S.M.Bohte at cwi.nl Wed Apr 23 10:00:56 2003 From: S.M.Bohte at cwi.nl (Sander Bohte) Date: Wed, 23 Apr 2003 16:00:56 +0200 Subject: PhD thesis available: Spiking Neural Networks Message-ID: <000001c309a0$c4605210$80f4a8c0@cwiware> Dear Connectionists, My PhD thesis on Computation with Asynchronous Spiking Neural Networks is now available on the WWW at http://www.cwi.nl/~sbohte/pub_thesis.htm For those interested, I have appended the index Best regards, Sander Bohte ======================================================= Keywords: spiking neural networks, spike time coding, sparse distributed coding, unsupervised clustering, supervised learning, dynamic feature binding, higher-order correlations. Index: 1. Introduction 1.1 Artificial Neural Networks 1.2 Computing with asynchronous spike-times 2. Unsupervised Clustering with Spiking Neurons by Sparse Temporal Coding and Multi-Layer RBF Networks 2.1 Introduction 2.2 Networks of delayed spiking neurons 2.3 Encoding continuous input variables in spike-times 2.4 Clustering with Receptive Fields 2.5 Hierarchical clustering in a multi-layer network 2.6 Complex clusters 2.7 Discussion and Conclusions 3. Error-Backpropagation in Temporally Encoded Networks of Spiking Neurons 3.1 Introduction 3.2 Error-backpropagation 3.3 The XOR-problem 3.4 Other Benchmark Problems 3.5 Discussion 3.6 Conclusion 4. A Framework for Position-invariant Detection of Feature-conjunctions 4.1 Introduction 4.2 Local Computation with Distributed Encodings 4.3 Implementation 4.4 Experiments 4.5 Discussion 4.6 Conclusions 5. Formal Specification of Invariant Feature-conjunction Detection 5.1 Introduction 5.2 Formal Description 5.3 Conclusion 6. The effects of pair-wise and higher order correlations on the firing rate of a post-synaptic neuron 6.1 Introduction 6.2 Mathematical Solution of the three-neuron problem 6.3 Calculating the Distribution with N Identical Neurons 6.4 An artificial neural network 6.5 Discussion 6.6 Conclusion 7. The Biology of Spiking Neurons 7.1 Real Neurons Spike 7.2 Precision and Reliability of Real Spikes From sunny at sunnybains.com Wed Apr 23 13:04:14 2003 From: sunny at sunnybains.com (Sunny Bains) Date: Wed, 23 Apr 2003 18:04:14 +0100 Subject: Physical (Analogue) computation and AI Message-ID: <3EA6C78E.2010703@sunnybains.com> The following paper, due for publication in the AISBJ later this year, may be of interest to those concerned with analogue vs. digital (vs. Turing machine) issues. Though written at a fairly abstract physical/mathematical level, the new model's connection with real machines, and particularly analogue neural networks, is discussed at the end. http://www.sunnybains.com/AISBJ2003.pdf All comments gratefully received... Sunny Bains Imperial College London/The Open Universty http://www.sunnybains.com ***** Intelligence as Physical Computation Abstract In this paper, we describe a model of physical computation that allows us to understand how embodied intelligent agents can simultaneously be considered to be objects operating under the laws of nature (or physics) and information processing devices. Using this type of analysis has two major advantages. First, it allows us to make concrete those issues relating to the relative merits of using analogue values or symbolic representations such as numbers: our analysis allows this longstanding point of contention in artificial intelligence to be transformed from a question of philosophy to one of physics. Second, it gives us a framework that should eventually allow us to produce design rules that will enable our artificially-intelligent (physical) agents to make better use of influences from the physical environment. As should be expected, for well-defined tasks, the results of this analysis are identical to Shannon?s information theory. However, for large, multi-functional systems with ill-defined roles, the new model provides a novel way of thinking about the complementarity of hardware and software. From gluck at pavlov.rutgers.edu Wed Apr 23 12:19:32 2003 From: gluck at pavlov.rutgers.edu (Mark A. Gluck) Date: Wed, 23 Apr 2003 12:19:32 -0400 Subject: Postdoc & RA/Programming Positions in Comp. Modeling of Memory Message-ID: Postdoc & RA/Programming Positions in Comp. Modeling of Memory We have two openings in our lab in the area of computational neuroscience, to develop and evaluate computational models of the neural bases of learning and memory, with special reference to the hippocampus and medial temporal lobes, the basal ganglia and striatum, cortico-striatal loops, and the role of key neuromodulators of these brain systems. For more information on our research and current lab personnel, see http://www.gluck.edu. All modeling takes places in the context, and is informed by, our ongoing experimental studies of learning and memory, including animal research, clinical studies of memory disordered patients (e.g., with Alzheimer's, Parkinson's, and schizophrenia), and functional brain imaging of healthy and impaired human subjects. One opening is for a postdoctoral fellow. The other is for a full-time Research Assistant/Programmer, ideally someone with a BA who is looking to gain research experience and publications, prior to applying to graduate school in the cognitive, neural, or computational sciences. For both positions, strong computer programming skills are essential (C, Java, or equivalent) as is prior programming experience, course work, and/or extensive independent reading in neural networks and computational neuroscience. Our lab is located at the Center for Molecular and Behavioral Neuroscience, at Rutgers University -Newark, located in downtown Newark, New Jersey, just 17 minutes by train from downtown New York City, NY. See http://www.cmbn.rutgers.edu. To apply, please send email to Mark Gluck, gluck at pavlov.rutgers.edu, with a full description of relevant past experience and future career goals. Both positions are available to be filled either immediately, this summer, or this coming fall. ________________________________________________ Dr. Mark A. Gluck, Associate Professor Center for Molecular and Behavioral Neuroscience Rutgers University - Newark Ph: (973) 353-1080 x3221 197 University Ave. Fx: (973) 353-1272 Newark, New Jersey 07102 E: gluck at pavlov.rutgers.edu Web pages: Research Lab: http://www.gluck.edu Rutgers Memory Disorders Project: http://www.memory.rutgers.edu Memory Loss & Brain Newsletter: http://www.memorylossonline.com/ "Gateway to Memory": http://mitpress.mit.edu/gatewaytomemory/ ________________________________________________ From d.mareschal at psychology.bbk.ac.uk Wed Apr 23 08:28:04 2003 From: d.mareschal at psychology.bbk.ac.uk (DR D MARESCHAL) Date: Wed, 23 Apr 2003 13:28:04 +0100 (BST) Subject: Lectureship available Message-ID: The following postion may be of interest to readersof this list/PLEASE DO NOT RESPOND DIRECTLY TO ME. cheers, Denis ======================= Birkbeck, University of London The School of Psychology Lecturer - Ref no: APS007 The School (RAE 5) is seeking to add to its existing strengths in developmental and cognitive psychology or cognitive neuroscience and needs a person to contribute teaching and research in one or both of these areas, and also to take responsibility for teaching research methods at undergraduate level. With a PhD, or equivalent in research and publications, in Psychology or related areas, you should have outstanding research ability or potential, focused on experimental, electrophysiological and computational approaches to cognition and brain development, attention and perception or language and memory. The posts are tenable from 1 October 2003. Salary range: 24,325 - 35,813 pa inc depending on qualifications and experience. Closing date: 7 May 2003. Full applications details from http://www.bbk.ac.uk or email: personnel at bbk.ac.uk or send a (A4) sae to the Personnel Department, Birkbeck, Malet Street, Bloomsbury, London WC1E 7HX (quoting the relevant reference number in all communications). NB: The College will be closed from 17-22 April inclusive & 5 May 2003 For informal enquiries contact: mark.johnson at bbk.ac.uk or m.eimer at bbk.ac.uk From ishikawa at brain.kyutech.ac.jp Fri Apr 25 05:57:52 2003 From: ishikawa at brain.kyutech.ac.jp (Masumi Ishikawa) Date: Fri, 25 Apr 2003 18:57:52 +0900 Subject: Special Issue of Neural Networks In-Reply-To: <5.0.2.5.2.20030425083702.00c5bed0@mail.brain.kyutech.ac.jp > References: <200304242054.h3OKsUud030520@haring.cs.utexas.edu> <5.0.2.5.2.20030424102040.039fae90@mail.brain.kyutech.ac.jp> <5.0.2.5.2.20030413092611.00f720b8@mail.brain.kyutech.ac.jp> <5.0.2.5.2.20030412095412.00f6b0d0@mail.brain.kyutech.ac.jp> <5.0.2.5.2.20030412095412.00f6b0d0@mail.brain.kyutech.ac.jp> <5.0.2.5.2.20030413092611.00f720b8@mail.brain.kyutech.ac.jp> <5.0.2.5.2.20030414162228.0278d588@mail.brain.kyutech.ac.jp> <5.0.2.5.2.20030424102040.039fae90@mail.brain.kyutech.ac.jp> Message-ID: <5.0.2.5.2.20030425183354.00c1d048@mail.brain.kyutech.ac.jp> Call for Papers 2004 Special Issue of Neural Networks New Developments in Self-Organizing Systems Research on self-organizing systems including self-organizing maps (SOMs) is an important area of unsupervised learning and has been rapidly growing in various directions: theoretical developments, applications in various fields, in-depth analysis of self-organizing systems in neuroscience and so forth. The Workshop on Self-Organizing Maps (WSOM) has been held biennially since 1997. In October, 2002, a Special Issue on Self-Organizing Maps was published in the journal Neural Networks selected from presentations at WSOM'01. The next workshop, WSOM'03, is scheduled to be held in September 2003 in Kitakyushu, Japan (for submission and participation details, see http://www.brain.kyutech.ac.jp/~wsom). Considering the extensive growth of this area, we plan another special issue related to self-organization in 2004, ranging from theoretical aspects to various applications. We will select papers from those submitted to this special issue of Neural Networks; papers will be either revisions of those presented at WSOM'03 or those directly submitted to the special issue. A limited number of invited papers by leading scientists are also planned. Technical areas include, but are not limited to: - Theory of self-organizing systems - Data visualization and mining - Applications to WEB intelligence - Applications to text and document analysis - Applications to robotics - Applications to image processing and vision - Applications to pattern recognition - Hardware and architecture - Self-organizing systems in neuroscience Co-Editors Masumi Ishikawa, Kyushu Institute of Technology Risto Miikkulainen, The University of Texas at Austin Helge Ritter, University of Bielefeld Submission Deadline for submission: December 10, 2003 Notification of acceptance: April 15, 2004 Deadline for submission of accepted papers: June 20, 2004 Deadline for submission of final papers: August 30, 2004 Format: as normal papers in the journal Address for Papers: Dr. Mitsuo Kawato ATR Human Information Science Laboratories 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan From becker at mcmaster.ca Wed Apr 30 16:16:27 2003 From: becker at mcmaster.ca (S. Becker) Date: Wed, 30 Apr 2003 16:16:27 -0400 (EDT) Subject: 2 positions in signal processing Message-ID: Dear colleagues, below are advertisements for two positions in my department, a Signal Processing Scientist and an Imaging Laboratory Technician. Please pass these on to any suitable candidates you know of. cheers, Sue Sue Becker, Associate Professor Department of Psychology, McMaster University becker at mcmaster.ca Building 34, Room 312 Fax: (905)529-6225 1280 Main Street West, Hamilton, Ont. L8S 4K1 Tel: 525-9140 ext. 23020 www.science.mcmaster.ca/Psychology/sb.html Signal Processing Scientist McMaster University invites applications for the position of Signal Processing Scientist in the Department of Psychology. The candidate will be expected to work with departmental brain imaging laboratories in the development and implementation of signal processing tools for EEG, MEG, and fMRI data, and to contribute an instructional role in the graduate programme under the supervision of faculty. The candidate should hold a PhD or MSc degree in a neuroscience field (e.g. biomedical engineering, experimental psychology, or neural computation) or present equivalent credentials from their work history. The initial appointment will be made for a three-year term with subsequent renewals contingent on budget approval. Salary will be commensurate with qualifications and experience. Candidates should send their curriculum vitae, a statement of their interests and relevant experience, representative publications (if available), and 3 letters of reference to: Scientist Search Committee Department of Psychology McMaster University 1280 Main Street West Hamilton, Ontario Canada L8S 4K1 Review of the applications will begin May 15 2003 and continue until the position is filled. All qualified candidates are encouraged to apply; however, Canadian citizens and permanent residents will be considered first for the position. McMaster University is strongly committed to employment equity within its community, and to recruiting a diverse faculty and staff. The University encourages applications from all qualified candidates, including women, members of visible minorities, aboriginal persons, members of sexual minorities, and persons with disabilities. Imaging Laboratory Technician McMaster University invites applications for the position of Imaging Laboratory Technician in the Department of Psychology. The candidate will be expected to be familiar with auditory and visual stimulus generation equipment, to write computer programmes for implementation of experiments on brain imaging, to assist in maintaining computer networks and security, and to support an undergraduate laboratory course in human electrophysiology under the supervision of faculty. Previous experience with state of the art EEG systems, MEG, or fMRI would be an asset. This is an entry-level position for a candidate holding a bachelor's degree in a relevant field (e.g., computer science, engineering, experimental psychology, neuroscience) or with equivalent work history. Initial appointment will be for a two-year term with subsequent renewals contingent on budget approval. Starting salary will be commensurate with qualifications and experience. Candidates should send their curriculum vitae, a statement of their interests and relevant experience, and 3 letters of reference to: ILT Search Committee Department of Psychology McMaster University 1280 Main Street West Hamilton, Ontario Canada L8S 4K1 Review of the applications will begin May 15 2003 and continue until the position is filled. All qualified candidates are encouraged to apply; however, Canadian citizens and permanent residents will be considered first for the position. McMaster University is strongly committed to employment equity within its community, and to recruiting a diverse faculty and staff. The University encourages applications from all qualified candidates, including women, members of visible minorities, aboriginal persons, members of sexual minorities, and persons with disabilities. From lincj at ntu.edu.tw Tue Apr 1 01:45:24 2003 From: lincj at ntu.edu.tw (Chih-Jen Lin) Date: Tue, 01 Apr 2003 14:45:24 +0800 Subject: "libsvm tools" and new version of libsvm Message-ID: Dear Colleagues: We announce the new version 2.4 of the software libsvm: libsvm: a library for support vector machines http://www.csie.ntu.edu.tw/~cjlin/libsvm and a new page "libsvm tools" containing additional codes/data sets based on libsvm: http://www.csie.ntu.edu.tw/~cjlin/libsvmtools Due to popular requests, in this new page we include MANY our past and current experimental codes/data sets such as svm probability output, minimization of leave-one-out bounds, different multi-class svms, reduced SVM, etc. Moreover, we now provide an integrated development environment to libsvm. Users can create and connect components (like scaler, trainer, predictor, etc) in this environment. Improvements of the new libsvm include 1. a script for users who know NOTHING about svm. It makes everything automatic--from data scaling to parameter selection. 2. handling non-PSD kernels such as sigmoid and others. Theoretical convergence for such cases has been established. 3. significant improvements of the python model selection tool. 4. improvements of the program for data scaling. Any comments are very welcome. Sincerely, Chih-Chung Chang and Chih-Jen Lin Department of Computer Science National Taiwan University Taipei, Taiwan cjlin at csie.ntu.edu.tw From UE001861 at guest.telecomitalia.it Tue Apr 1 06:58:47 2003 From: UE001861 at guest.telecomitalia.it (Corsini Filippo) Date: Tue, 1 Apr 2003 13:58:47 +0200 Subject: First European School on Neuroengineering "Massimo Grattarola" Message-ID: <5C052AA22466074FADC82C208D5C5719E5D3C1@EVS02.idc.cww.telecomitalia.it> ************************************************************************* First European School on Neuroengineering "Massimo Grattarola" Venice 16-20 June 2003 Telecom Italia Learning Services (TILS), and the University of Genoa (DIBE, DIST, Bioengineering course) are currently organizing the first edition of an European Summer School on Neuroengineering. The school will be entitled to Massimo Grattarola. The first edition , which will last for five days, will be held from June 16 to June 20, 2003 at Telecom Italia's Future Center in Venice. The School will cover the following main themes: 1. Neural code and plasticity o Development and implementation of methods to identify, represent and analyze hierarchical and self-organizing systems o Cortical computational paradigms for perception and action 2. Brain-like adaptive information processing systems o Development and implementation of methods to identify, represent and analyze hierarchical and self-organizing systems o Models of learning, representation and adaptability based on knowledge of the nervous system. o Exploration of the capabilities of natural neurobiological systems as flexible computational devices. o Use of information from nervous systems to engineer new control techniques and new artificial systems. o Development of highly innovative Artificial Neural Networks capable of reproducing the functioning of vertebrate nervous systems. 3. Bio-artificial systems o Development of novel brain-computer interfaces o Development of new techniques for neuro-rehabilitation and neuro-prostheses o Hybrid silicon/biological systems In response to current reforms in training, at the Italian and European levels, the Summer School on Neuroengineering is certified to grant credits. These include: ECM (Educazione Continua in Medicina) credits recognized by the Italian Ministry of Health ECTS (European Credit Transfer System) credits recognized by all European Universities More information and application forms can be obtained from: www.tils.com/neurobit www.bio.dibe.unige.it Scientific Board: Sun -ichi Amari RIKKEN, Brain Science Institute Laboratory for Mathematical Neuroscience, Japan Fabrizio Davide Telecom Italia Learning Services, Italy Walter J. Freeman University of Berkeley, USA Stephen Grossberg University of Boston, USA Milena Koudelka-Hep IMT, Institute of Microtechnology, University of Neuchatel, Switzerland Gwendal Le Masson INSERM, French Institute of Health and Medical Research, France Sergio Martinoia DIBE, Unversity of Genoa, Italy Pietro Morasso DIST, University of Genoa, Italy Sylvie Renaud-Le Masson ENSEIRB - IXL Bordeaux, France Wim Rutten University of Twente, Netherlands Jaap Van Pelt Netherlands Institute for Brain Research, Netherlands Confirmed Lecturers: Abbruzzese G. Non-invasive exploration of human cerebral cortex by transcranial magnetic stimulation Benfenati F. Molecular dissection of neurotransmitter release mechanisms: a key to understand short-term memory processes Torre V., Ruaro M. E., Bonifazi P. Towards the neurocomputer: image processing and learning with neuronal cultures Aleksander I. Digital Neuromodelling Based on the Architecture of the Brain: Basics and Applications Destexhe A. The stochastic integrative properties of neocortical neurons in vivo Gielen S. Quantitative models to explain the degree-of-freedom problem in motor control Le Masson G. Cyborgs : from fiction to science Rutten W. Neuro-electronic interface engineering and neuronal network learning Van Pelt J. Computational and experimental approaches in neuronal morphogenesis and network formation Mussa-Ivaldi F. The Engineering of motor learning and adaptive control Sandini G. Cognitive Development in Robot Cubs Morasso P. Motor control of unstable tasks Knoll A. Neuro-IT - an overview of network scope and activities Orban G. Investigating the primate brain at different levels of organisation: linking single cell recording and fMRI in the awake monkey Pearce T. Olfactory machines on the move Engel A. Synchrony as an integrative principle for cognitive architectures Two Practical Laboratory: Davide F., Stillo G, Morabito F. Chosen exempla of neuronal signals decoding, analysis and features extractions Renaud-Le Masson Bioengineering: on-silicon solutions for biologically realistic artificial neural networks (state-of-the-art and development perspectives for integrated ANN Registration Fee*: Undergraduate and graduate: 100 EUR PhD students and young researcher: 250 EUR Business and medical professional: 500 EUR * The School registration fee includes the meeting program, reception, two coffee breaks and a lunch each day, and meeting proceedings. For informations you can contact: Filippo Corsini ue001861 at guest.telecomitalia.it For informations about hotel in Venice: www.venicehotel.com and www.turismovenezia.it _________________________________________________ Dr. Filippo Corsini Telecom Italia- Learning Services S.p.A. Business Development Viale Parco de' Medici, 61, 00148 Roma Italy tel: +39.06.368.72379 fax: +39.06.368.80101 e-mail: UE001861 at guest.telecomitalia.it _________________________________________________ This e-mail, including any attachments, may contain private or confidential information. If you think you may not be the intended recipient, or if you have received this e-mail in error, please contact the sender immediately and delete all copies of this e-mail. If you are not the intended recipient, you must not reproduce any part of this e-mail or disclose its contents to any other party. From benjamin.blankertz at first.fhg.de Tue Apr 1 16:25:48 2003 From: benjamin.blankertz at first.fhg.de (Benjamin Blankertz) Date: Tue, 1 Apr 2003 22:25:48 +0100 Subject: BCI [Brain Computer Interfaces] Competition 2003 deadline is approaching Message-ID: <200304012326.05797.benjamin.blankertz@first.fhg.de> Dear Colleagues, The deadline for submissions to the BCI [Brain Computer Interfaces] Competition 2003 is approaching: it is in one month, on May 1st 2003 - a good opportunity to remind you of this date. There were over 120 downloads, so it is going to be a hot competition. If you have not already checked the competition web site http://ida.first.fraunhofer.de/~blanker/competition/ do it right now! It is not too late to participate. Best wishes, Benjamin Blankertz The BCI Competition 2003 is organized by: Albany: Theresa M. Vaughan, Gerwin Schalk, Jonathan R. Wolpaw Berlin: Benjamin Blankertz, Gabriel Curio, Klaus-Robert Mueller Graz: Alois Schloegl, Christa Neuper, Gernot Mueller, Bernhard Graimann, Gert Pfurtscheller Tuebingen: Thilo Hinterberger, Michael Schroeder, Niels Birbaumer Contact: Dr. Benjamin Blankertz, +49.30.6392-1875 Fraunhofer FIRST.IDA Kekulestr. 7, D-12489 Berlin, Germany benjamin.blankertz at first.fraunhofer.de From nestor at ftnp.ft.uam.es Tue Apr 1 06:13:39 2003 From: nestor at ftnp.ft.uam.es (Nestor Parga) Date: Tue, 1 Apr 2003 13:13:39 +0200 (MET DST) Subject: "Ramon y Cajal" and postdoctoral positions Message-ID: 1. "RAMON y CAJAL" position Computational and Systems Neuroscience / a five year position in Madrid Interested candidates are invited to apply for a "Ramon y Cajal" position for research work in Computational and Systems Neuroscience at the "Group of Computational Neuroscience", Universidad Autonoma de Madrid, Spain. These are five year positions co-funded by the Spanish Ministery of Science and Technology and the Universities. This is the third year that these contracts are given in Spain and more information about them and about how to apply can be found at the web address: http://www.mcyt.es/CAJAL/default.htm Candidates are expected to work in interaction with the theoretical team of the Computational Neuroscience group to carry out joint work on information processing in the brain Details about the current work of the group can be found at the web site: http://ket.ft.uam.es/~neurociencia/ Interested candidates are encouraged to send a research proposal, their curriculum vitae including a list of all publications, a statement of research interests and the names of three scientists who could send recommendation letters to the address below, Notice however that final applications have to done according to the instructions in http://www.mcyt.es/CAJAL/default.htm Nestor Parga | | Phone : (+34) 91-397-4542 Dpto. de Fisica Teorica, C-XI | Fax : (+34) 91-397-3936 Universidad Autonoma de Madrid | E-mail: nestor at ftnp.ft.uam.es 28049 Madrid, SPAIN | parga at delta.ft.uam.es http://ket.ft.uam.es/~neurociencia/nestor %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 2. POSTDOCTORAL position (Fundacion Carolina) Postdoctoral position available in Theoretical Neuroscience in the Universidad Autonoma de Madrid (UAM, Spain) for nationals from Latin-american countries. The Carolina Foundation (Spain) is receiving applications for postdoctoral fellowships in Neuroscience. Their webpage is: http://www.fundacioncarolina.es/esp/becas/index.htm and details about how to apply to the Neuroscience Program can be found in: http://www.fundacioncarolina.es/esp/becas/CIE/3/NEUROCIENCIAS/prg_ficha.htm Candidates should first select a research group in a Spanish University or Institute. The "Computational Neuroscience Group", Universidad Autonoma de Madrid, offers the possibility to work on several aspects of theoretical neuroscience. Eligible candidates with a Ph. D. in neuroscience or a related scientific discipline (e.g. physics, maths or computer science) and with good background and interest in theoretical neurobiology are encouraged to send their curriculum vitae and a brief description of fields of interest to the address below, if possible by e-mail (parga at delta.ft.uam.es). For more information about the "Computational Neuroscience Group", UAM, please see: http://ket.ft.uam.es/~neurociencia/index.html Nestor Parga | | Phone : (+34) 91-397-4542 Dpto. de Fisica Teorica, C-XI | Fax : (+34) 91-397-3936 Universidad Autonoma de Madrid | E-mail: nestor at ftnp.ft.uam.es 28049 Madrid, SPAIN | parga at delta.ft.uam.es http://ket.ft.uam.es/~neurociencia/nestor From oby at cs.tu-berlin.de Wed Apr 2 10:13:58 2003 From: oby at cs.tu-berlin.de (Klaus Obermayer) Date: Wed, 2 Apr 2003 17:13:58 +0200 (MEST) Subject: Advanced Course in Computational Neuroscience Message-ID: ***NEW DEADLINE APRIL 27TH 2003*** ***REGISTRATION FEE REDUCED*** Due to a last minute success in fundraising for the school we were able to reduce the registration fee to EUR 600,-. We now also have fellowships for covering the tuition fee and travel expenses for students who need financial help for attending the course. =========================================================================== ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE (A FENS/IBRO NEUROSCIENCE SCHOOL) August 11th - September 5th, 2003 MUNICIPALITY OF OBIDOS, PORTUGAL DIRECTORS: Ad Aertsen (University of Freiburg, Germany) Alain Destexhe (CNRS, Gif-sur-Yvette, France) Klaus Obermayer (Technical University of Berlin, Germany) Eilon Vaadia (Hebrew University, Jerusalem, Israel) The Advanced Course in Computational Neuroscience introduces students to the panoply of problems and methods of computational neuroscience, simultaneously addressing several levels of neural organisation, from subcellular processes to operations of the entire brain. The course consists of two complementary parts. A distinguished international faculty gives morning lectures on topics in experimental and computational neuroscience. The rest of the day is devoted to practical training, including learning how to use simulation software and how to implement a model of the system the student wishes to study on individual UNIX workstations. The first week of the course introduces students to essential neurobiological concepts and to the most important techniques in modelling single cells, networks and neural systems. Students learn how to apply software packages like GENESIS, MATLAB, NEURON, XPP, etc. to the solution of their problems. During the following three weeks the lectures will cover specific brain functions. Each week topics ranging from modelling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the brain will be covered. The course ends with a presentation of the students' projects. The Advanced Course in Computational Neuroscience is designed for advanced graduate students and postdoctoral fellows in a variety of disciplines, including neuroscience, physics, electrical engineering, computer science and psychology. Students are expected to have a basic background in neurobiology as well as some computer experience. Students of any nationality can apply. A maximum total of 30 students will be accepted and we specifically encourage applications from researchers who work in less-favoured regions and women. There will be a fee of EUR 600,- per student covering costs for lodging, meals and other course expenses, but - due to additional funding - we expect to provide tuition fee waivers and travel stipends for students who need financial help for attending the course. Students from unfavored countries are strongly encouraged to apply. More information and application forms can be obtained from: http://www.neuroinf.org/courses/EUCOURSE/EU03/ Please apply electronically using a web browser. Contact address: - mail: Klaus Obermayer, FR2-1, Fakultaet IV, Technical University of Berlin, Franklinstrasse 28/29, 10587 Berlin, Germany phone: +49-(0)30-314-73442 fax: +49-(0)30-314-73121 - e-mail: obidos at cs.tu-berlin.de APPLICATION DEADLINE: April 27th, 2003 Applicants will be notified of the results of the selection procedures by May 23rd, 2003. CONFIRMED FACULTY: Larry Abbott, Brandeis University, USA Moshe Abeles, Hebrew University, Israel Ad Aertsen, University of Freiburg, Germany Amos Arieli, Weizmann Institute, Israel Thierry Bal, CNRS, France Dave Beeman, University of Colorado Boulder, USA Diego Contreras, University of Pennsylvania, USA Peter Dayan, University College London, UK Erik de Schutter, University of Antwerp, Belgium Alain Destexhe, CNRS, France Marcus Diessmann, University of Freiburg, Germany Andreas Engel, University of Hamburg, Germany Karl Friston, University College London, UK Michael Hines, Yale University, USA Israel Nelken, Hebrew University, Israel Miguel Nicolelis, Duke University, USA Klaus Obermayer, TU Berlin, Germany Tim Pearce, University of Leicester, UK John Rinzel, New York University, USA Arnd Roth, Max Planck Inst. Heidelberg, Germany Michael Rudolph, CNRS, France Lars Schwabe, TU Berlin, Germany Idan Segev, Hebrew University, Israel Volker Steuber, University of Antwerp, Belgium Alex Thomson, University College London, UK Charlie Wilson, University of Texas San Antonio, USA Daniel Wolpert, University College London, UK Eilon Vaadia, Hebrew University, Israel Carl van Vreeswijk, CNRS, France Paul Verschure, Inst. Neuroinformatics, Switzerland From clabiouse at ulg.ac.be Wed Apr 2 12:50:26 2003 From: clabiouse at ulg.ac.be (Christophe Labiouse) Date: Wed, 2 Apr 2003 19:50:26 +0200 Subject: Eighth Neural Computation and Psychology Workshop (NCPW 8): Connectionist Models of Cognition, Perception, and Emotion Message-ID: <001f01c2f940$581130e0$3200000a@COGSCILABIOUSE> Eighth Neural Computation and Psychology Workshop (NCPW 8) Connectionist Models of Cognition, Perception and Emotion 28-30 August 2003 at the University of Kent at Canterbury, UK The Eighth Neural Computation and Psychology Workshop (NCPW8) will be held in Canterbury, England from 28-30th August 2003. The NCPW series is now a well established and lively forum that brings together researchers from such diverse disciplines as artificial intelligence, cognitive science, computer science, neuroscience, philosophy and psychology. Between 25-30 papers will be accepted as oral presentations. In addition to the high quality of the papers presented, this Workshop takes place in an informal setting, in order to encourage interaction among the researchers present. Publication ----------- Proceedings of the workshop will appear in the series Progress in Neural Processing, which is published by World Scientific. Speakers -------- The list of speakers who have already agreed to attend includes: John Bullinaria (Birmingham) Gary Cottrell (San Diego) Bob French (Liege) Peter Hancock (Stirling) Richard Shillcock (Edinburgh) Chris Solomon (Kent at Canterbury) John Taylor (Kings College) Marius Usher (Birkbeck College) Important Dates --------------- Deadline for submission of abstracts: June 13th 2003 Notification of acceptance/rejection: June 29th 2003 Website ------- More details can be found on the conference website, http://www.cs.ukc.ac.uk/events/conf/2003/ncpw/ Conference Chair ---------------- Howard Bowman, University of Kent, UK Conference Organisers --------------------- Howard Bowman, UKC Colin G. Johnson, UKC Miguel Mendao, UKC Vikki Roberts, UKC Proceedings Editors -------------------- Howard Bowman, UKC Christophe Labiouse, Liege ******************************************************************** Christophe L. Labiouse Research Fellow of the Belgian National Fund for Scientific Research University of Liege, Department of Cognitive Science (B33) Boulevard du Rectorat, 3 B-4000 Liege, Belgium Tel 00 32 (0)4 3664870 Fax 00 32 (0)4 3662859 e-mail: clabiouse at ulg.ac.be http://www.ulg.ac.be/cogsci/clabiouse/intro.html ******************************************************************** From simone at dsi.unifi.it Thu Apr 3 02:54:15 2003 From: simone at dsi.unifi.it (Simone Marinai) Date: Thu, 3 Apr 2003 09:54:15 +0200 Subject: IAPR-TC3 workshop DEADLINE EXTENSION Message-ID: <200304030754.h337sFf22612@diamante.dsi.unifi.it> ** apologies if you receive multiple copies of this document ** In response to many requests, we are pleased to announce an extension of the deadline for paper sumbmission to ANNPR: April 22nd 2003 (Midnight GMT) Any information on the workshop can be found in the following web page: www.dsi.unifi.it/ANNPR ---------------------------------------------- IAPR - TC3 International Workshop on Artificial Neural Networks in Pattern Recognition Location: University of Florence, Italy, September 12-13, 2003 Important Dates: Deadline for paper submission: 22-4-2003 Deadline for poster submission: 22-4-2003 Notification of acceptance: 15-6-2003 Camera Ready due: 15-7-2003 Further information: Contact Marco Gori (Email: marco at dii.unisi.it ), Simone Marinai (Email: simone at dsi.unifi.it) or visit the workshop web page (www.dsi.unifi.it/ANNPR). ***** Note: You can reply to this email with REMOVE in the subject to be eliminated by this list. ***** Best regards, Simone Marinai --------------------------------------------- Simone Marinai Dipartimento di Sistemi e Informatica Via di Santa Marta, 3 50139 Firenze (Italy) +39 (55) 479-6452 Email: simone at dsi.unifi.it From Manuel.Davy at irccyn.ec-nantes.fr Fri Apr 4 10:07:01 2003 From: Manuel.Davy at irccyn.ec-nantes.fr (Manuel Davy) Date: Fri, 04 Apr 2003 17:07:01 +0200 Subject: MACHINE LEARNING SUMMER SCHOOL 2003 Message-ID: <3E8D9F95.8000706@irccyn.ec-nantes.fr> * Apologises if you receive this email several times * CALL FOR PATICIPATION ----------------------------------------------------- MACHINE LEARNING SUMMER SCHOOL 2003 August 4-16, 2003, Tuebingen, Germany http://www.irccyn.ec-nantes.fr/mlschool/ ----------------------------------------------------- Organised by CNRS-AS 66 (France), MPIK Tuebingen (Germany), and the Australian National University **** Applications are now open **** **** Deadline for application is April 30th 2003 **** **** For applications, please visit our web site **** The Summer School is intended for students and researchers alike, who are interested in Machine Learning. Its goal is to present some of the topics which are at the core of modern Learning Theory. The school will be held in the Max Plank Institut fuer Biologische Kybernetik, Tuebingen, Germany between the 4th and the 16th of August, 2003. During this time, we shall present six basic courses, each one covering one of the topics listed below. In addition, there will be advance courses which may focus on additional topics and which will provide background knowledge in machine learning and statistics. Four practical sessions will be organized in small groups. The goal is to provide a 'hands-on' experience of working with machine learning algorithms. They will be directly related to the material introduced in the courses. Basic Courses: * Statistical Learning Theory (O. Bousquet, MPIK Tuebingen) - 8 hours * Independent Component Analysis (J.-F. Cardoso, ENST Paris) - 8 hours * Gaussian Processes (C. Rasmussen, MPIK Tuebingen) - 8 hours * Kernel Algorithms I (A. Smola, ANU) - 6 hours * Kernel Algorithms II (B. Schoelkopf, MPIK Tuebingen) - 6 hours * Pattern Classification (E. Yom-Tov, Technion, Haifa) - 4 hours Advanced Courses: * Monte Carlo Simulation methods (C. Andrieu, University of Bristol) - 4 hours * Bioinformatics (P. Baldi, UC Irvine) - 4 hours * Stochastic Approximation (L. Bottou, NEC Research, Princeton) - 4 hours * Concentration Inequalities (S. Boucheron, LRI Orsay) - 4 hours * Some Mathematical Tools for Machine Learning (C. Burges, Microsoft Research, Redmond) - 4 hours * Minimum Description Length (P. Grunwald, CWI Amsterdam) - 4 hours * Information Retrieval and Language Technology (T. Joachims, Cornell University) - 4 hours * Foundations of Learning (S. Smale, UC Berkeley) - 4 hours * Bayesian Approaches, RVM (M. Tipping, Microsoft Research, Cambridge) - 4 hours * Empirical Inference (V. Vapnik) - evening lecture Practical sessions: * Pattern classification - From data to decision (E. Yom-Tov) * Support Vector Machines (A. Gretton, A. Elisseeff, J. Weston) * Simulation Methods (Manuel Davy) -- ------------------------------------------ Manuel DAVY http://www.irccyn.ec-nantes.fr/~davy/ ------------------------------------------ IRCCyN/CNRS, 1 rue de la Noe, BP 92101, 44321 Nantes cedex 3, France Manuel.Davy at irccyn.ec-nantes.fr T?l: +33 2 40 37 69 09 Fax: +33 2 40 37 69 30 ------------------------------------------- From lorincz at inf.elte.hu Sat Apr 5 01:14:49 2003 From: lorincz at inf.elte.hu (LORINCZ Andras) Date: Sat, 5 Apr 2003 08:14:49 +0200 (CEST) Subject: Software tool for "How to decide what to read" Message-ID: Dear Connectionists: Geoff Hinton was asking for a tool to support decision on what to read (see attachment). The tool, which will be free for Academic use, can be downloaded and tried. Please, visit http://www.coraler.com Related projects on -- hand-free navigation -- anonymous and accountable self-organizing communities can be found at http://people.inf.elte.hu/lorincz/Files/Head_Mouse/Head_Mouse.html http://people.inf.elte.hu/lorincz/pub.html. The present state of the software: It is made of three main parts: 1. Hostess (This is the server. Install kit is under development) 2. MapViewer (Flash and applet versions are ready) 3. MapEditor (Ready) How it works: You view the maps through the MapViewer from your computer You modify, correct and edit maps with MapEditor (Download it and test it!) You publish the maps at your Hostess (the Hostess of your group). The MapEditor allows you -- to connect nodes (html pages, or your own files) with directed arrows -- to insert comments to the nodes -- to render images to the nodes -- to initiate a search at Yahoo (Google requries query limitations or payment) -- to use drag and drop function when adding html pages or documents Other functionalities, which will be included for the end of the summer: -- breaking news detector -- automated domain mapping tool -- automated bookmark integration tool -- automated keyword keyphrase extraction using KEA -- RL based link-highlighting when surfing on the maps Each community can have distributed cryptographic key system for publishing, for editing, and for accountable anonymity. This key system will make use of the ITTC crypto software http://theory.stanford.edu/~dabo/ITTC/ and will be available in the fourth quarter of this year. Looking forward to your feedback, Andras Lorincz From akira at bstu.by Sat Apr 5 05:52:48 2003 From: akira at bstu.by (Akira Imada) Date: Sat, 5 Apr 2003 13:52:48 +0300 Subject: ICNNAI'2003 Call for Papers Message-ID: <01c701c2fb61$7fc7df80$5d1511ac@brpi.local> The Third International Conference on Neural Networks and Artificial Intelligence (ICNNAI'2003) November 12-14, Minsk, Belarus Organized by: Ministry of Education (Belarus) Belarusian State University of Informatics and Radioelectronics Belarus SIG of INNS In cooperation with: International Neural Network Society Brest State Technical University (Belarus) United Institute of Informatics Problems of National Academy of Sciences of Belarus Institute of Computer Information Technologies (Ukraine, Ternopil) Scope The aim of the conference is to present and discuss research results and their applications, to support and accelerate worldwide exchange of ideas. The continuous exchange of scientific and echnical information is of particular importance for the research and the transfer of research to practice. The scope of this conference covers the theory and application of neural networks and techniques of artificial intelligence. New techniques, instruments and both software and hardware components are included. Key-note speakers Prof. Kurosh Madani "Industrial Applications of ANNs". Senart Institute of Technology, University PARIS XII - Val de Marne, http://www.univ-paris12.fr/www/rech/ann/i2s.htm madani at univ-paris12.fr Prof. Helmut A. Mayer "Ontogenetic Teaching of Mobile Autonomous Robots with Dynamic Neurocontrollers". University of Salzburg, Austria, http://www.cosy.sbg.ac.at/~helmut/helmut.html helmut at cosy.sbg.ac.at Prof. Qiangfu Zhao "Recognition, learning and understanding". University of Aizu, Tsuruga, Ikki-machi, Aizu-Wakamatsu City, Fukushima, Japan, qf-zhao at u-aizu.ac.jp http://www.u-aizu.ac.jp/~qf-zhao/ Topics 1. Cognitive Science * Neuro psychological systems * Brain-like models * Learning and memory * Neuro cognition * Models of behaviour * Models of perception 2. Theory and Algorithms * Neural network architectures * Learning algorithms * Self-organizing systems * Chaos theory * Fuzzy neural systems * Genetic algorithms * Neuro dynamics and spiking neuron 3. Neural Networks Applications * Data mining * Signal processing * Intelligent control and mobile robots * Time-series prediction * Pattern recognition and image processing * Speech recognition and language processing * Hardware implementation * Multi-agents systems * Application in engineering, medicine and business * High performance computing * Intelligent sensors General Conference Chair: Mikhail Batura (Belarus) General Conference Co-chairs: Valentin Muravyew (Belarus) Rauf Sadykhov (Belarus) Vladimir Golovko (Belarus) International Program Committee Sung-Bae Cho (Korea) Ian Cloete (Germany) Pasquale Daponte (Italy) Darryl Davis (United Kingdom) Donald MacDonald (United Kingdom) Colin Fyfe (United Kingdom) Akira Imada (Japan) Alexander Galushkin (Russia) Vladimir Golenkov (Belarus) Kurosh Madani (France) Carlo Morabito (Italy) Anatoly Pashkevich (Belarus) Alexander Petrovsky (Belarus) Vincenzo Piuri (Italy) Vladimir Ptitchkin (Belarus) Sarunas Raudys (Lithuania) Hubert Roth (Germany) Vladimir Rubanov (Belarus) Anatoly Sachenko (Ukraine) Valery Terekhov (Russia) Herwig Unger (Germany) Antanas Zilinskas (Lithuania) Local Organizing Committee (Belarus) Alexander Doudkin - Chairman Yury Savitsky - Vice Chairman Valery Ivkovich Marina Loukasheviuchr Anatroly Khomenko Serge Bayrack Leonid Mahnist Oleg Ignatiuk Andrew Dunets Denis Vershok Maksim Vatkin Leonid Podenok Aleksey Otvagin Alexander Inutin Conference location The International Conference on Neural Networks and Artificial Intelligence will be held at Belarusian State University of Informatics and Radioelectronics, Belarus in November 12-14, 2003. Proceedings Accepted papers will be published in conference proceedings. Deadlines Submission Deadline: July 15, 2003 Notification of Acceptance: August 15, 2003 International Program Committee Address: Prof. Rauf Sadykhov (Co-Chairman) Belarusian State University of Informatics and Radioelectronics Brovka str. 6 Minsk, 220027 Belarus fax: +375017 231 09 82 e-mail: rsadykhov at gw.bsuir.unibel.by Prof. Vladimir Golovko (Co-Chairman) Brest State Technical University Moskowskaja 267 Brest, 224017 Belarus fax: +375162 422 127 e-mail: gva at bstu.by Submission instructions Prospective authors are requested to send a paper (maximum 7 pages including figures, tables and references) for review by the International Program Committee. All submissions must be written in English, starting with a succinct statement of the problem, the result achieved, their significance and comparison with previous works (if any), as well as a list of references.The submissions should also include: title of proposed paper, authors names, affiliations, addresses, name of author to contact for correspondence, e-mail address and fax of contact author, topics which best describe the paper (max. 5 keywords). Please submit your paper exclusively in electronic media. Paper should be submitted electronically by 15 July 2003 in doc, postscript or pdf format in accordance with the following address: DOUDKIN at newman.bas-net.by Please put the conference name - ICNNAI'2003 on all correspondence and on the mailing envelope. Detailed information about the conference is available on the web http://lsi.bas-net.by/icnnai.html The City of Minsk Minsk is the capital of the Republic of Belarus. It is located in a picturesque place on the river Svisloch, which was in ancient times one of the busiest trade-routes connecting the Baltic and the Black seas. Minsk is the city where one can find the best pieces of Belarusian cultural heritage: museums and exhibitions, theaters, world famous Belarusian ballet, folklore dancing ensembles and choirs. Numerous scientific centres and leading institutions of higher education, situated in Minsk, are well-known abroad for their fundamental and applied researches. Minsk is a cross-road of the most popular European tours. It is connected by motorways, railways and airlines with all the European capitals and also with the main cities of the world. From David.Cohn at acm.org Sat Apr 5 17:20:01 2003 From: David.Cohn at acm.org (David 'Pablo' Cohn) Date: Sat, 05 Apr 2003 14:20:01 -0800 Subject: Special Issue on Variable and Feature Selection available! Message-ID: <5.2.0.9.0.20030405140200.033fedd0@ux7.sp.cs.cmu.edu> The Journal of Machine Learning Research is very pleased to announce publication of a Special Issue on Variable and Feature Selection. This issue, organized and edited by Isabelle Guyon and Andre Elisseeff, contains 14 papers, including an introduction to the field by the guest editors. In addition to the papers, the many of the authors have made available the data sets and software used in their research. Please visit http://www.jmlr.org for details. ------------------ An Introduction to Variable and Feature Selection Isabelle Guyon, Andr=E9 Elisseeff; JMLR 3(Mar):1157-1182, 2003. Distributional Word Clusters vs. Words for Text Categorization Ron Bekkerman, Ran El-Yaniv, Naftali Tishby, and Yoad Winter; JMLR 3(Mar):1183-1208, 2003. Extensions to Metric-Based Model Selection Yoshua Bengio, Nicolas Chapados; JMLR 3(Mar):1209-1227, 2003. Dimensionality Reduction via Sparse Support Vector Machines Jinbo Bi, Kristin Bennett, Mark Embrechts, Curt Breneman, Minghu Song; JMLR 3(Mar):1229-1243, 2003. Benefitting from the Variables that Variable Selection Discards Rich Caruana, Virginia R. de Sa; JMLR 3(Mar):1245-1264, 2003. A Divisive Information-Theoretic Feature Clustering Algorithm for Text Classification Inderjit S. Dhillon, Subramanyam Mallela, Rahul Kumar; JMLR 3(Mar):1265-1287, 2003. An Extensive Empirical Study of Feature Selection Metrics for Text Classification George Forman; JMLR 3(Mar):1289-1305, 2003. Sufficient Dimensionality Reduction Amir Globerson, Naftali Tishby; JMLR 3(Mar):1307-1331, 2003. Grafting: Fast, Incremental Feature Selection by Gradient Descent in Function Space Simon Perkins, Kevin Lacker, James Theiler; JMLR 3(Mar):1333-1356, 2003. Variable Selection Using SVM-based Criteria Alain Rakotomamonjy; JMLR 3(Mar):1357-1370, 2003. Overfitting in Making Comparisons Between Variable Selection Methods Juha Reunanen; JMLR 3(Mar):1371-1382, 2003. MLPs (Mono-Layer Polynomials and Multi-Layer Perceptrons) for Nonlinear Modeling Isabelle Rivals, L=E9on Personnaz; JMLR 3(Mar):1383-1398, 2003. Ranking a Random Feature for Variable and Feature Selection Herv=E9 Stoppiglia, G=E9rard Dreyfus, R=E9mi Dubois, Yacine Oussar; JMLR 3(Mar):1399-1414, 2003. Feature Extraction by Non-Parametric Mutual Information Maximization Kari Torkkola; JMLR 3(Mar):1415-1438, 2003. Use of the Zero-Norm with Linear Models and Kernel Methods Jason Weston, Andr=E9 Elisseeff, Bernhard Sch=F6lkopf, Mike Tipping; JMLR 3(Mar):1439-1461, 2003. ------------------ These, and all previous papers are available electronically at http://www.jmlr.org/ in PostScript and PDF formats. Many are also available in HTML. The papers of Volume 1 and 2 are also available in hardcopy from the MIT Press; please see http://mitpress.mit.edu/JMLR for details. From giro-ci0 at wpmail.paisley.ac.uk Sun Apr 6 08:39:01 2003 From: giro-ci0 at wpmail.paisley.ac.uk (Mark Girolami) Date: Sun, 06 Apr 2003 13:39:01 +0100 Subject: Paper Available : Sparse Kernel Density Estimation Message-ID: Probability Density Estimation from Optimally Condensed Data Samples. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2003, in press. Mark Girolami & Chao He. Paper and MATLAB Code Available from: http://cis.paisley.ac.uk/giro-ci0/reddens/ Abstract The requirement to reduce the computational cost of evaluating a point probability density estimate when employing a Parzen window estimator is a well known problem. This paper presents the Reduced Set Density Estimator that provides a kernel based density estimator which employs a small percentage of the available data sample and is optimal in the L2 sense. Whilst only requiring O(N^2) optimisation routines to estimate the required weighting coefficients, the proposed method provides similar levels of performance accuracy and sparseness of representation as Support Vector Machine density estimation, which requires O(N^3) optimisation routines, and which has previously been shown to consistently outperform Gaussian Mixture Models. It is also demonstrated that the proposed density estimator consistently provides superior density estimates for similar levels of data reduction to that provided by the recently proposed Density Based Multiscale Data Condensation algorithm and in addition has comparable computational scaling. The additional advantage of the proposed method is that no extra free parameters are introduced such as regularisation, bin width or condensation ratios making this method a very simple and straightforward approach to providing a reduced set density estimator with comparable accuracy to that of the full sample Parzen density estimator. Legal disclaimer -------------------------- The information transmitted is the property of the University of Paisley and is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Statements and opinions expressed in this e-mail may not represent those of the company. Any review, retransmission, dissemination and other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender immediately and delete the material from any computer. -------------------------- From levys at wlu.edu Sun Apr 6 22:59:18 2003 From: levys at wlu.edu (Simon Levy) Date: Sun, 06 Apr 2003 22:59:18 -0400 Subject: Invitation to submit to JCIS 2003 special session on recurrent neural nets Message-ID: <3E90E986.6020401@wlu.edu> Dear Connectionists, I am soliciting submissions for a special session of the next Joint Conference on Information Sciences (http://www.ee.duke.edu/jcis/). The conference will be held Sep 26-30 2003 at the Embassy Suites Hotel and Conference Center in Cary, North Carolina, and the session will take place one morning or afternoon during those four days. The topic of the session will be "New Frontiers for Recurrent Neural Networks", with the goal of sharing news on current work (including work in progress) with other connectionists, in a friendly atmosphere. Last year's special session included presentations on using recurrent networks for modeling lexical development, goal management, short-term memory, and emergent rule-like behavior. Papers presented at the session (four pages in length) will be published in the JCIS 2003 Conference Proceedings. All submission and questions should be directed to me (levys at wlu.edu). The camera-ready deadline is June 16. Thank you for your attention, and I look forward to hearing from you. Sincerely, Simon ======================== Simon D. Levy Assistant Professor Computer Science Department Washington & Lee University Lexington, VA 24450 540-458-8419 (voice) 540-458-8479 (fax) levys at wlu.edu http://www.cs.wlu.edu/~levy From a.van.ooyen at nih.knaw.nl Mon Apr 7 04:46:01 2003 From: a.van.ooyen at nih.knaw.nl (Arjen van Ooyen) Date: Mon, 07 Apr 2003 10:46:01 +0200 Subject: Summer School of Brain Research Message-ID: <3E913AC9.336D3773@nih.knaw.nl> Dear colleague, The Netherlands Institute for Brain Research and the Netherlands Ophthalmic Research Institute are organizing this year the 23rd International Summer School of Brain Research from August 25-29, 2003, in Amsterdam. The program is dedicated to the theme: Development, dynamics and pathology of neuronal networks: from molecules to functional circuits. The Summer School will focus on key mechanisms in the development of neurons into circuits with functional dynamics, and will link the dynamics in neural circuits with cognitive / behavioral processes. In this respect we wish to emphasize (1) molecular and cell-biological mechanisms of neuronal network development and plasticity, (2) understanding activity in neuronal networks in relation to their structure, and (3) understanding normal and deficient neural circuitry at the cognitive and behavioral level. The Summer School aims at providing a forum for discussing broad views as well as latest developments on the above topics. The lectures are presented by internationally renowned scientists. The target groups are PhD students, postdoctoral fellows, senior researchers and clinicians. Please visit the Summer School website http://www.nih.knaw.nl/summerschool for information and registration. Best regards, -- Dr. Arjen van Ooyen Netherlands Institute for Brain Research Meibergdreef 33, 1105 AZ Amsterdam, The Netherlands Email: A.van.Ooyen at nih.knaw.nl Website: http://www.anc.ed.ac.uk/~arjen Phone: +31.20.5665483 Fax: +31.20.6961006 From juergen at idsia.ch Mon Apr 7 08:30:04 2003 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Mon, 07 Apr 2003 14:30:04 +0200 Subject: New AI & 2 postdoc positions Message-ID: <3E916F4C.5010403@idsia.ch> The New AI: General & Sound & Relevant for Physics by J. Schmidhuber, IDSIA. To appear in "Artificial General Intelligence" (edited by B. Goertzel and C. Pennachin). Also avaliable as arxiv:cs.AI/0302012: http://www.idsia.ch/~juergen/newai/newai.html Abstract. Most traditional artificial intelligence (AI) systems of the past 50 years are either very limited, or based on heuristics, or both. The new millennium, however, has brought substantial progress in the field of theoretically optimal and practically feasible algorithms for prediction, search, inductive inference based on Occam's razor, problem solving, decision making, and reinforcement learning in environments of a very general type. Since inductive inference is at the heart of all inductive sciences, some of the results are relevant not only for AI and computer science but also for physics, provoking nontraditional predictions based on Zuse's thesis of the computer-generated universe. Related link to Schmidhuber's law ;-) http://www.idsia.ch/~juergen/computerhistory.html --------------------------------------------------------- Two postdoc jobs (optimal search and recurrent networks): http://www.idsia.ch/~juergen/jobs2003.html http://www.idsia.ch/~juergen/oops.html http://www.idsia.ch/~juergen/rnn.html Please forward to potential candidates! JS http://www.idsia.ch/~juergen/ From mark.laubach at yale.edu Tue Apr 8 14:16:34 2003 From: mark.laubach at yale.edu (Mark Laubach) Date: Tue, 08 Apr 2003 14:16:34 -0400 Subject: POSTDOCTORAL POSITION AVAILABLE: NEURONAL ENSEMBLE RECORDING Message-ID: Hello, My group is currently seeking to fill a postdoctoral slot for a DARPA-supported project on the auditory cortex and brain-machine interfaces (see below). The position offers an excellent opportunity to learn how to do neuronal ensemble recordings and state-of-the-art methods for analyzing multi-channel spike train and field potential data. I would appreciate hearing from anyone interested in the position via email. Thanks. -Mark ----- POSTDOCTORAL POSITION AVAILABLE: NEURONAL ENSEMBLE RECORDING IN AUDITORY CORTEX A postdoctoral position is available starting September 1, 2003 as part of a DARPA-sponsored collaborative project involving the laboratories of Drs. Jon Kaas and Troy Hackett at Vanderbilt University, Dr. Mandayam Srinivasan at MIT, and Dr. Mark Laubach at The John B Pierce Laboratory, a research institute affiliated with Yale University. The position is available in the Laubach group at the Pierce Laboratory. The ideal candidate would be an expert on the auditory cortex, have experience using neurophysiological and operant conditioning methods, and familiarity with software such as NEx, Matlab, and R/S-Plus. Prior experience with neuronal ensemble recording methods or, at the very least, a background in neurophysiology or behavioral neuroscience and a strong desire to learn ensemble recording is required. Strong skills in teamwork and communication are also essential for the position. This person will collect and analyze data from ensembles of neurons in the auditory cortex collected during the learning and performance of simple and choice reaction time tasks. In addition, methods for microstimulation of cortical neurons (developed through a collaboration with Dr. John Chapin's group at SUNY Brooklyn) will be implemented and tested. The candidate will also learn about novel methods for analyzing neuronal ensemble data sets that are being developed by our group in collaboration with Prof. Ronald Coifman's group in the Applied Mathematics Dept at Yale. If interested, please send a vita, list of publications, summary of research experience, and names of three individuals who can be contacted as references to: Mark Laubach, Ph.D. The John B. Pierce Laboratory Yale University School of Medicine 290 Congress Ave New Haven CT 06519 E-mail - mark.laubach at yale.edu WWW - http://spikelab.jbpierce.org The review of applications will begin April 15, 2003 and will continue until the position is filled. E.O.E. From kawamura at mail.sci.yamaguchi-u.ac.jp Wed Apr 9 00:23:49 2003 From: kawamura at mail.sci.yamaguchi-u.ac.jp (kawamura@mail.sci.yamaguchi-u.ac.jp) Date: Wed, 09 Apr 2003 13:23:49 +0900 (JST) Subject: Paper Available : Low-dimensional chaos induced by frustration Message-ID: <20030409.132349.846948971.kawamura@sci.yamaguchi-u.ac.jp> Dear Connectionists, We are pleased to announce the availability of our recent paper. "Low-dimensional chaos induced by frustration in a non-monotonic system" M. Kawamura, R. Tokunaga and M. Okada Europhysics Letters (will be appeared) Preprint is available at http://arxiv.org/abs/cond-mat/0205471 Abstract: We report a novel mechanism for the occurrence of chaos at the macroscopic level induced by the frustration of interaction, namely frustration-induced chaos, in a non-monotonic sequential associative memory model. We succeed in deriving exact macroscopic dynamical equations from the microscopic dynamics in the case of the thermodynamic limit and prove that two order parameters dominate this large-degree-of-freedom system. Two-parameter bifurcation diagrams are obtained from the order-parameter equations. Then we analytically show that the chaos is low-dimensional at the macroscopic level when the system has some degree of frustration, but that the chaos definitely does not occur without the frustration. Best regards, Masaki Kawamura Faculty of Science, Yamaguchi University, Yoshida 1677-1, Yamaguchi 753-8512 Japan E-mail: kawamura at sci.yamaguchi-u.ac.jp From Nicolas.Rougier at loria.fr Fri Apr 11 03:58:59 2003 From: Nicolas.Rougier at loria.fr (Nicolas Rougier) Date: 11 Apr 2003 09:58:59 +0200 Subject: Post-doctoral fellowship Message-ID: <1050047939.13555.29.camel@hopfield.loria.fr> The LORIA laboratory offers a one-year fellowship for a post-doctoral researcher: --------------------------------------------------------------------- A connectionist architecture for a multi-level approach of navigation --------------------------------------------------------------------- We are studying the different kinds of information representations that may be useful to an autonomous robot seen as a cognitive system. Recent studies corresponded to integrate data from neurosciences in connectionist computational models and we studied in this framework how both procedural, declarative and working memories were identified as emerging from specific neuronal structures and critical at different levels of information processing. For navigational tasks, there exists today an extensive literature on computational models that are grounded on a core mechanism: the chaining together of neighboring locations in space. Having a precise goal to reach, this kind of chaining can then be used through the equivalent of a backward search to reach the goal from a given place. Nonetheless, if this strategy can account for quite short spatio-temporal sequences, it is our belief it cannot account for a more global and complex navigational behaviour. Based on our understanding on the role of the different information representation, we think that going from one place to another distant one implies scheduling of action at several different levels, both in time and space. Specifically, we anticipate that a model grounded on data from prefrontal cortex studies could encode navigational information at varying levels of spatial and temporal resolutions and would then be able to perform a precise contention scheduling of the task. For example, going from one place A1 to another place A2 does not necessarily imply to know that at any given time it is necessary to go through each of the Ai places. It is more likely that at any given time only a small subset of the current path is known while the whole path can be described at a higher resolution (by using abstract representations like rooms or places for example). In this framework, we aim at understanding how such multi-level representations can emerge from a connectionist computationnal model and how it can promote an efficient navigation based on multi-level representations. From previous work and collaboration, we have found that data describing the prefrontal and basal ganglia systems give hints concerning the design of an efficient system and we would like to go further this way by designing a computational model for the navigation of a real robot. ------------------------------------------------------------------------ The candidate must have a PhD in cognitive science, computer science, or a related discipline and expertise in neural network modelling. Experience in robotic would be an asset but is not essential. Deadline for applications is 04/15/2003. Contact: rougier at loria.fr Dr Nicolas Rougier. From l.wiskott at biologie.hu-berlin.de Fri Apr 11 09:54:43 2003 From: l.wiskott at biologie.hu-berlin.de (Laurenz Wiskott) Date: 11 Apr 2003 13:54:43 -0000 Subject: paper available: improved cumulant based ICA Message-ID: <20030411135443.11683.qmail@huxley.biologie.hu-berlin.de> CuBICA: INDEPENDENT COMPONENT ANALYSIS BY SIMULTANEOUS THIRD- AND FOURTH-ORDER CUMULANT DIAGONALIZATION by Tobias Blaschke and Laurenz Wiskott Abstract: CuBICA, an improved method for independent component analysis (ICA) based on the diagonalization of cumulant tensors is proposed. It is based on Comon's algorithm [Comon, 1994] but it takes third- and fourth-order cumulant tensors into account simultaneously. The underlying contrast function is also mathematically much simpler and has a more intuitive interpretation. It is therefore easier to optimize and approximate. A comparison with Comon's and three other ICA-algorithms on different data sets demonstrates its performance. Available from: http://www.compscipreprints.com/comp/Preprint/blaschke/20030409/1/ http://itb.biologie.hu-berlin.de/~wiskott/Abstracts/BlasWisk2003a.html Reference: Blaschke, T. and Wiskott, L. (2003). CuBICA: Independent Component Analysis by Simultaneous Third- and Fourth-Order Cumulant Diagonalization. Computer Science Preprint Server (CSPS): Computational Intelligence/0304002, http://www.compscipreprints.com/comp/Preprint/blaschke/20030409/1/ (). -- Dr. Laurenz Wiskott, Institute for Theoretical Biology, Berlin http://itb.biologie.hu-berlin.de/~wiskott/ l.wiskott at biologie.hu-berlin.de From kdharris at andromeda.rutgers.edu Fri Apr 11 09:52:33 2003 From: kdharris at andromeda.rutgers.edu (Ken Harris) Date: Fri, 11 Apr 2003 09:52:33 -0400 Subject: Postdoctoral positions Message-ID: POSTDOCTORAL POSITIONS IN COMPUTATIONAL NEUROSCIENCE Two postdoctoral positions are available to conduct interdisciplinary research on neuronal population coding, working with Drs Kenneth Harris and Gyorgy Buzsaki, at Rutgers University. Information is processed in the brain by the co-operative action of large numbers of neurons. It is now possible to record from hundreds of neurons in parallel, offering an unprecedented opportunity to discover the operating principles of neuronal circuits. However, the full potential of this data will only be realized through radical innovation in the techniques used for its analysis and interpretation. We are seeking postdoctoral associates to develop and use new methods for analysis of simultaneously recorded spike trains from hippocampus, neocortex, and other systems, and to build models of population function based on their conclusions. The ideal candidate would have a background in mathematics, physics, statistics, computer science, or a related field, as well as a strong interest in neuroscience. Ability to program in C/C++ and MATLAB is also highly desirable. Rutgers University is an equal opportunity/affirmative action employer. Qualified women and minority candidates are encouraged to apply. Interested candidates should send a CV, statement of research interests, and names and email addresses of two references to kdharris at andromeda.rutgers.edu. ------------------------ Kenneth D. Harris, Ph.D. Center for Molecular and Behavioral Neuroscience Rutgers, The State University of New Jersey 197 University Avenue Newark NJ 07102, USA phone: 973 353 1080, x3360 fax: 973 353 1820 email: kdharris at andromeda.rutgers.edu From piuri at elet.polimi.it Sat Apr 12 08:16:53 2003 From: piuri at elet.polimi.it (Vincenzo Piuri) Date: Sat, 12 Apr 2003 14:16:53 +0200 Subject: IEEE Neural Networks Society: Competition for a New Logo Message-ID: <5.1.0.14.0.20030412141031.02a9a830@mail.elet.polimi.it> A New Logo for a New Society Participate to the competition to design our new logo! Dear Colleague the areas of interest of the IEEE Neural Networks Society encompass the entire breadth of computational intelligence. Our well-known logo from the IEEE Neural Networks Council, used successfully to identify our events and activities, no longer fully represents our collective research, applications, interests, and challenges. It is therefore time to look for a new logo that will represent all of us!! Neural paradigms should still be present in our insignia, but also fuzzy systems and evolutionary computation should be recognized. A competition, open to all members of our Society, is launched to design the new logo. It should have preferably a horizontal layout, similar to the IEEE logo. Any idea (including the craziest) is welcome! How can you participate to the competition? Its easy! Draw your proposals for the IEEE NNS logo and submit them electronically to me at piuri at dti.unimi.it by 10 July 2003. Any major electronic format is acceptable (e.g., jpeg, tiff, gif, pdf, ps). When submitting the logo, please, include your first and last name, your complete affiliation, and your IEEE membership number. The winner will be required to transfer all rights concerning the logo to the IEEE NN Society. For further information, please do not hesitate to contact me. Best regards Vincenzo Piuri IEEE Neural Networks Society Vice President for Members Activities Vincenzo Piuri University of Milan, Department of Information Technologies via Bramante 65, 26013 Crema (CR), Italy phone: +39-02-5033-0066 or +39-0373-898-066 secretary: +39-02-5033-0011 or +39-0373-898-011 fax: +39-02-5033-0010 email: piuri at elet.polimi.it From T.J.Prescott at sheffield.ac.uk Thu Apr 17 07:18:53 2003 From: T.J.Prescott at sheffield.ac.uk (Tony Prescott) Date: Thu, 17 Apr 2003 12:18:53 +0100 Subject: post doctoral position Message-ID: *** Please forward to interested parties, apologies for repeat postings *** Adaptive Behaviour Research Group Department of Psychology The University of Sheffield RESEARCH ASSOCIATE Applications are invited for a research associate post, tenable for three years from 1st July 2003. This is a joint project between the Adaptive Behaviour Research Group at the University of Sheffield (www.shef.ac.uk/~abrg) and the Intelligent Autonomous Systems Laboratory at the University of the West of England in Bristol (www.ias.uwe.ac.uk). The aim of this interdisciplinary project is to develop a tactile 'whisker' sensor array for an autonomous robot with response characteristics similar to those of the rat facial vibrissae. The work at Sheffield will focus on the development of computational models of the whisker-processing pathways in the rat brain (although no work on animals is involved). Applicants should have a good honours degree in Neuroscience, Mathematics, Physics, Engineering or related field, and should hold or expect to hold a PhD, preferably in computational neuroscience or a related field of mathematical modelling. Salary on the IA/IB scale for Research Staff in the range of 18,265-23,296 UKP per annum, according to experience. Informal enquiries to: Dr. Tony Prescott (Tel: +44 (0)114 222 6547; e-mail: t.j.prescott at shef.ac.uk). Further particulars are obtainable from: The Recruitment Service, Personnel Department, Firth Court, Western Bank, Sheffield S10 2UH (Tel: +44 (0)114 279 9800; e-mail: jobs @sheffield.ac.uk), where applications (including a curriculum vitae and the names and addresses of three referees) should be sent. Closing date for applications: 16th May 2003. From bogus@does.not.exist.com Thu Apr 17 09:50:13 2003 From: bogus@does.not.exist.com () Date: Thu, 17 Apr 2003 14:50:13 +0100 Subject: Postdoctoral Research Positions at Microsoft Research Cambridge Message-ID: <6EDEB53BA6EA96458F3CEC96BB0282D20343C6C1@tvp-msg-03.europe.corp.microsoft.com> From terry at salk.edu Thu Apr 17 23:50:34 2003 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 17 Apr 2003 20:50:34 -0700 (PDT) Subject: NEURAL COMPUTATION 15:5 In-Reply-To: <200303101837.h2AIbeS22678@purkinje.salk.edu> Message-ID: <200304180350.h3I3oYC94290@purkinje.salk.edu> Neural Computation - Contents - Volume 15, Number 5 - May 1, 2003 ARTICLE Estimating a State-Space Model From Point Process Observations Anne C. Smith and Emery N. Brown LETTERS Sequential Bayesian Decoding with a Population of Neurons Si Wu, Danmei Chen, Mehesan Niranjan, and Shun-ichi Amari Learning Coefficients of Layered Models When the True Distribution Mismatches the Singularities Sumio Watanabe and Shun-ichi Amari Gamma Rhythmic Bursts: Coherence Control in Networks of Cortical Pyramidal Neurons Toshio Aoyagi, Takashi Takekawa and Tomoki Fukai Manhattan World: Orientation and Outlier Detection by Bayesian Inference James M. Coughlan and A. L. Yuille Kernal-Based Nonlinear Blind Source Separation Stefan Harmeling, Andreas Ziehe, Motoaki Kawanabe, and Klaus-Robert Mueller An Algorithm of Supervised Learning for Multilayer Neural Networks Zheng Tang, XuGang Wang, Hiroki Tamura, Masahiro Ishii The Time-Organized Map Algorithm: Extending the Self-Organizing Map to Spatiotemporal Signals Jan C. Wiemer New Conditions for Global Stability of Cohen-Grossberg Neural Networks Wenlian Lu and Tianping Chen ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2003 - VOLUME 15 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $95 $101.65 $143 Institution $590 $631.30 $638 * 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 Sebastian_Thrun at heaven.learning.cs.cmu.edu Sat Apr 19 15:14:46 2003 From: Sebastian_Thrun at heaven.learning.cs.cmu.edu (Sebastian Thrun) Date: Sat, 19 Apr 2003 15:14:46 -0400 Subject: NIPS*2003 Call For Papers Message-ID: --- please post --- ------------------------------------------------------------ CALL FOR PAPERS Neural Information Processing Systems, Natural and Synthetic Monday, December 8 - Saturday December 13, 2003 Vancouver, British Columbia, Canada www.nips.cc ------------------------------------------------------------ Submissions are solicited for the seventeenth meeting of an interdisciplinary conference which brings together researchers interested in all aspects of neural and statistical computation. The conference will include invited talks as well as oral and poster presentations of refereed papers. It is single track and highly selective. Preceding the main conference will be one day of tutorials (December 8), and following it will be two days of workshops at Whistler/Blackcomb ski resort (December 12-13). INVITED SPEAKERS: Anders Dale, Harvard University: Relating Brain Imaging Signals to Biophysical Models of Neuronal Circuits; Paul Ekman, UC San Francisco: About Face: What We Have Learned Through Measuring Facial Movements; Michale Fee, Bell Labs, Lucent Technologies: Time and Sequence in the Brain: Insights from a Songbird; Marc Mezard, Universite de Paris Sud: Analytic and Algorithmic Solutions of Random Satisfiability Problems; Elissa Newport, University of Rochester, Statistical language learning in human infants and adults; David Salesin, University of Washington and Microsoft Research: The Need for Machine Learning in Computer Graphics. TUTORIAL SPEAKERS: Stephen Boyd, Stanford University: Convex Optimization and Applications; David Karger, MIT: Algorithmic Tools Applied to Learning and Inference Problems; Daniel D. Lee, University of Pennsylvania: Learning in Sensorimotor Systems; David Lowe, University of British Columbia: Real-time Object Recognition using Invariant Local Image Features; Klaus-Robert Mueller, Fraunhofer FIRST: Towards Brain Computer Interfacing; Zach Mainen, Cold Spring Harbor Laboratory: Neural Coding and the Olfactory System; SUBMISSIONS: Papers are solicited in all areas of neural and statistical computation, including (but not limited to) the following: o Algorithms and Architectures: statistical learning algorithms, neural networks, kernel methods, graphical models, Gaussian processes, independent component analysis, model selection, combinatorial optimization. o Applications: innovative applications or fielded systems that use machine learning, including systems for time series prediction, bioinformatics, text/web analysis, multimedia processing, and robotics. o Brain Imaging: neuroimaging, cognitive neuroscience, EEG (electroencephalogram), ERP (event related potentials), MEG (magnetoencephalogram), fMRI (functional magnetic resonance imaging), brain mapping, brain segmentation. o Cognitive Science and Artificial Intelligence: theoretical, computational, or experimental studies of perception, psychophysics, human or animal learning, memory, reasoning, problem solving, language, and neuropsychology. o Control and Reinforcement Learning: decision and control, exploration, planning, navigation, Markov decision processes, game-playing, multi-agent coordination, computational models of classical and operant conditioning. o Emerging Technologies: analog and digital VLSI, neuromorphic engineering, computational sensors and actuators, microrobotics, bioMEMS, neural prostheses, photonics, molecular and quantum computing. o Learning Theory: generalization and regularization, information theory, statistical physics of learning, Bayesian methods, approximation bounds, online learning and dynamics. o Neuroscience: theoretical and experimental studies of processing, and transmission of information in biological neurons and networks, including spike train generation, synaptic modulation, plasticity and adaptation. o Speech and Signal Processing: recognition, coding, synthesis, denoising, segmentation, source separation, auditory perception, psychoacoustics, dynamical systems, recurrent networks, Markov models. o Visual Processing: image processing and coding, segmentation, object detection and recognition, motion detection and tracking, visual psychophysics, visual scene analysis and interpretation. o Demonstrations: Authors wishing to submit to the demonstration track should consult the conference web site. REVIEW CRITERIA: Submissions will be refereed on the basis of technical quality, novelty, significance, and clarity. Authors new to NIPS are particularly encouraged to submit. There will be an opportunity after the meeting to revise accepted manuscripts. PAPER FORMAT: Submissions may be up to eight pages in length, including figures and references, using a font no smaller than 10 point. Text is to be confined within a 8.25in by 5in rectangle. Submissions violating these guidelines will not be considered. Templates will be posted at the NIPS Website nips.cc. SUBMISSION INSTRUCTIONS: NIPS accepts only electronic submissions in postscript and PDF format. The conference web site will accept electronic submissions from May 19, 2003 until midnight, June 6, 2003, Pacific daylight time. ORGANIZING COMMITTEE: General Chair, Sebastian Thrun, Carnegie Mellon University; Program Chair, Lawrence Saul, University of Pennsylvania; Tutorials Chair, Sam Roweis, University of Toronto; Workshops Co-chairs, Robert Jacobs, University of Rochester, Satinder Singh Baveja, University of Michigan; Demonstrations Chairs, Shih-Chii Liu, ETH/University of Zurich, Tobi Delbruck, ETH/University of Zurich; Publications Chair, Bernhard Schoelkopf, Max Planck Gesellschaft Tuebingen; Publicity Chair, Klaus Robert Mueller, Fraunhofer FIRST; Online Proceedings Chair, Andrew McCallum, University of Massachusetts Amherst; Volunteers Chair, Dale Schuurmans, University of Waterloo. PROGRAM COMMITTEE: Lawrence Saul (Chair), University of Pennsylvania; Peter Bartlett, UC Berkeley; Samy Bengio, IDIAP; Chris Burges, Microsoft Research; Rich Caruana, Cornell University; Ralph Etienne-Cummings, Johns Hopkins University and University of Maryland, College Park; Geoff Hinton, University of Toronto; John Lafferty, Carnegie Mellon University; Mike Lewicki, Carnegie Mellon University; Michael Littman, Rutgers University; Andrew McCallum, University of Massachusetts Amherst; Rajesh Rao, University of Washington; Jianbo Shi, University of Pennsylvania; Richard Shiffrin, Indiana University; Yoram Singer, Hebrew University; Alexander Smola, Australian National University; Martin Wainwright, UC Berkeley. PAPERS MUST BE SUBMITTED BY JUNE 6, 2003 --- Please Post --- From Sebastian_Thrun at heaven.learning.cs.cmu.edu Tue Apr 22 12:55:31 2003 From: Sebastian_Thrun at heaven.learning.cs.cmu.edu (Sebastian Thrun) Date: Tue, 22 Apr 2003 12:55:31 -0400 Subject: NIPS*2003 Call for Workshop Proposals Message-ID: --- Please Post --- ------------------------------------------------------------ CALL FOR WORKSHOP PROPOSALS Neural Information Processing Systems, Natural and Synthetic NIPS*2003 Post-Conference Workshops, December 12 and 13, 2003 Whistler/Blackcomb Resort, BC, Canada www.nips.cc ------------------------------------------------------------ Following the regular program of the Neural Information Processing Systems 2003 conference in Vancouver, BC, Canada, workshops on various current topics in neural information processing will be held on December 12 and 13, 2003, in Whistler, BC, Canada. We invite researchers interested in chairing one of these workshops to submit workshop proposals. The goal of the workshops is to provide an informal forum for researchers to discuss important research questions and challenges. Controversial issues, open problems, and comparisons of competing approaches are encouraged and preferred as workshop topics. Representation of alternative viewpoints and panel-style discussions are particularly encouraged. Workshop topics include, but are not limited to, the following: Active Learning, Attention, Audition, Bayesian Networks, Bayesian Statistics, Benchmarking, Bioinformatics, Brain Imaging, Computational Complexity, Control, Genetic Algorithms, Graphical Models, Hippocampus and Memory, Human-Computer Interfaces, Hybrid Supervised/Unsupervised Learning, Implementations, Independent Component Analysis, Kernel Methods, Mean-Field Methods, Music, Network Dynamics, Neural Coding, Neural Plasticity, On-Line Learning, Optimization, Recurrent Nets, Robot Learning, Rule Extraction, Self-Organization, Sensory Biophysics, Signal Processing, Spike Timing, Support Vector Machines, Speech, Time Series, Topological Maps, and Vision. Detailed descriptions of previous workshops may be found at http://www.cs.cmu.edu/afs/cs/project/nips-6/nips2002/nips-papers.html. There will be six hours of workshop meetings per day, split into morning and afternoon sessions, with free time in between for ongoing individual exchange or outdoor activities. Selected workshops may be invited to submit proceedings for publication in the post-NIPS workshops monographs series published by the MIT Press. Workshop organizers have several responsibilities including: o Coordinating workshop participation and content, which includes arranging short informal presentations by experts, arranging for expert commentators to sit on a discussion panel, formulating a set of discussion topics, etc. o Moderating the discussion, and reporting its findings and conclusions to the group during evening plenary sessions o Writing a brief summary and/or coordinating submitted material for post-conference electronic dissemination. Interested parties must submit a proposal for a workshop via email by August 1, 2003. Proposals should include title, description of what the workshop is to address and accomplish, proposed workshop length (1 or 2 days), planned format (e.g., lectures, group discussions, panel discussion, combinations of the above, etc.), and proposed speakers. Names of potential invitees should be given where possible. Preference will be given to workshops that reserve a significant portion of time for open discussion or panel discussion, as opposed to pure "mini-conference" format. An example format is: o Tutorial lecture providing background and introducing terminology relevant to the topic. o Two short lectures introducing different approaches, alternating with discussions after each lecture. o Discussion or panel presentation. o Short talks or panels alternating with discussion and question/answer sessions. o General discussion and wrap-up. We suggest that organizers allocate at least 50% of the workshop schedule to questions, discussion, and breaks. Past experience suggests that workshops otherwise degrade into mini-conferences as talks begin to run over. For the same reason, we strongly recommend that each workshop include no more than 12 talks per day. The proposal should motivate why the topic is of interest, why it should be discussed, and who the targeted group of participants is. It also should include a brief resume of the prospective workshop chair with a list of publications to establish scholarship in the field. We encourage workshops that build, continue, or arise from one or more workshops from previous years. Please mention any such connections. NIPS does not provide travel funding for workshop speakers. In the past, some workshops have sought and received funding from external sources to bring in outside speakers. In addition, the organizers of each accepted workshop can name up to four people (six people for 2-day workshops) to receive discounted registration for the workshop program. Submissions should include the name, address, email address, phone and fax numbers for all organizers. If there is more than one organizer, please designate one organizer as the primary contact. Proposals should be emailed as plain text to: nips-workshop-proposal at bcs.rochester.edu Please do not use attachments, Microsoft Word, postscript, html, or pdf files. Questions may be addressed to: nips-workshop-admin at bcs.rochester.edu Information about the main conference and the workshop program can be found at http://nips.cc/ Robert A. Jacobs, University of Rochester Satinder Singh, University of Michigan NIPS*2003 Workshops Co-Chairs PROPOSALS MUST BE RECEIVED BY AUGUST 1, 2003 --- Please Post --- From Sebastian_Thrun at heaven.learning.cs.cmu.edu Tue Apr 22 12:56:23 2003 From: Sebastian_Thrun at heaven.learning.cs.cmu.edu (Sebastian Thrun) Date: Tue, 22 Apr 2003 12:56:23 -0400 Subject: NIPS*2003 Call for Demonstrations Message-ID: --- Please Post --- ------------------------------------------------------------ CALL FOR DEMONSTRATIONS Neural Information Processing Systems, Natural and Synthetic Monday, December 8 - Saturday December 13, 2003 Vancouver, British Columbia, Canada www.nips.cc ------------------------------------------------------------ Based on the success in 2002, the Neural Information Processing Systems conference will once again include a separate track for demonstrations. The demonstrations will take place in parallel with the poster sessions at the NIPS*2003 conference. Example areas of interest for the demonstrations track include, but are by no means limited to the following: o Analog and digital VLSI o Neuromorphic Engineering o Computational sensors and actuators o Robotics o bioMEMS (microelectromechanical systems) o Biomedical instrumentation o Neural prostheses o Photonics o Real-time multimedia systems o Large-scale neural emulators o Software demonstrations of novel algorithms NIPS is an interdisciplinary conference, which attracts cognitive scientists, computer scientists, engineers, neuroscientists, physicists, statisticians, and mathematicians interested in all aspects of neural and statistical processing and computation. The demonstration track enables researchers to highlight scientific advances, systems, and technologies in ways that go beyond conventional poster presentations. It will provide a unique forum for demonstrating advanced technologies (hardware and software), and fostering the direct exchange of knowledge. We hope that this track will stimulate interactions between researchers from different fields (for example, roboticists and neuromorphic engineers) and encourage new collaboration between researchers in theoretical fields and those in more applied fields. Submissions accepted in the demonstrations track will be published on the NIPS web site, but will not appear in printed proceedings. However, submitting your work to the demonstration track by no means precludes the submission of a companion paper to the regular NIPS conference. In fact, joint submissions are very much encouraged. We also encourage authors submitting demonstrations to consider organizing a workshop at NIPS*2003. Note that the deadline for paper submissions is July 1, 2003, and for demonstration and workshop proposals the submission deadline is August 1, 2003. Please see http://nips.cc for further details. There will be a separate room for these demonstrations and participants will have access to power strips, tables and poster boards. VCRs and monitors will also be provided on request. Participants are responsible for ensuring that their demonstration is sufficiently portable; additional hardware beyond that specified above will not be provided by NIPS but might be provided at a cost if available. SUBMISSION INSTRUCTIONS: All proposals for demonstrations will be reviewed by the Demonstrations Co-Chairs. Interested parties should submit a brief description of their proposed demonstration via email by August 1, 2003. Proposals should include a title, description of the device or system to be demonstrated, main results, novelty and significance of the work, any related publications, and estimated space requirements for the demonstration. Please include the name, address, email address, phone and fax numbers for all co-authors on the submitted work, and indicate whether a related paper has also been submitted to NIPS*2003. Proposals should be emailed to shih at ini.phys.ethz.ch, and should be in plain ascii text, postscript or pdf. Questions may also be addressed to shih at ini.phys.ethz.ch. Information about the main conference and the workshop program can be found at http://nips.cc. Shih-Chii Liu and Tobi Delbrueck, Institute of Neuroinformatics, University of Zurich, ETH Zurich NIPS*2003 Demonstrations Co-Chairs PROPOSALS MUST BE RECEIVED BY AUGUST 1, 2003 --- Please Post --- From S.M.Bohte at cwi.nl Wed Apr 23 10:00:56 2003 From: S.M.Bohte at cwi.nl (Sander Bohte) Date: Wed, 23 Apr 2003 16:00:56 +0200 Subject: PhD thesis available: Spiking Neural Networks Message-ID: <000001c309a0$c4605210$80f4a8c0@cwiware> Dear Connectionists, My PhD thesis on Computation with Asynchronous Spiking Neural Networks is now available on the WWW at http://www.cwi.nl/~sbohte/pub_thesis.htm For those interested, I have appended the index Best regards, Sander Bohte ======================================================= Keywords: spiking neural networks, spike time coding, sparse distributed coding, unsupervised clustering, supervised learning, dynamic feature binding, higher-order correlations. Index: 1. Introduction 1.1 Artificial Neural Networks 1.2 Computing with asynchronous spike-times 2. Unsupervised Clustering with Spiking Neurons by Sparse Temporal Coding and Multi-Layer RBF Networks 2.1 Introduction 2.2 Networks of delayed spiking neurons 2.3 Encoding continuous input variables in spike-times 2.4 Clustering with Receptive Fields 2.5 Hierarchical clustering in a multi-layer network 2.6 Complex clusters 2.7 Discussion and Conclusions 3. Error-Backpropagation in Temporally Encoded Networks of Spiking Neurons 3.1 Introduction 3.2 Error-backpropagation 3.3 The XOR-problem 3.4 Other Benchmark Problems 3.5 Discussion 3.6 Conclusion 4. A Framework for Position-invariant Detection of Feature-conjunctions 4.1 Introduction 4.2 Local Computation with Distributed Encodings 4.3 Implementation 4.4 Experiments 4.5 Discussion 4.6 Conclusions 5. Formal Specification of Invariant Feature-conjunction Detection 5.1 Introduction 5.2 Formal Description 5.3 Conclusion 6. The effects of pair-wise and higher order correlations on the firing rate of a post-synaptic neuron 6.1 Introduction 6.2 Mathematical Solution of the three-neuron problem 6.3 Calculating the Distribution with N Identical Neurons 6.4 An artificial neural network 6.5 Discussion 6.6 Conclusion 7. The Biology of Spiking Neurons 7.1 Real Neurons Spike 7.2 Precision and Reliability of Real Spikes From sunny at sunnybains.com Wed Apr 23 13:04:14 2003 From: sunny at sunnybains.com (Sunny Bains) Date: Wed, 23 Apr 2003 18:04:14 +0100 Subject: Physical (Analogue) computation and AI Message-ID: <3EA6C78E.2010703@sunnybains.com> The following paper, due for publication in the AISBJ later this year, may be of interest to those concerned with analogue vs. digital (vs. Turing machine) issues. Though written at a fairly abstract physical/mathematical level, the new model's connection with real machines, and particularly analogue neural networks, is discussed at the end. http://www.sunnybains.com/AISBJ2003.pdf All comments gratefully received... Sunny Bains Imperial College London/The Open Universty http://www.sunnybains.com ***** Intelligence as Physical Computation Abstract In this paper, we describe a model of physical computation that allows us to understand how embodied intelligent agents can simultaneously be considered to be objects operating under the laws of nature (or physics) and information processing devices. Using this type of analysis has two major advantages. First, it allows us to make concrete those issues relating to the relative merits of using analogue values or symbolic representations such as numbers: our analysis allows this longstanding point of contention in artificial intelligence to be transformed from a question of philosophy to one of physics. Second, it gives us a framework that should eventually allow us to produce design rules that will enable our artificially-intelligent (physical) agents to make better use of influences from the physical environment. As should be expected, for well-defined tasks, the results of this analysis are identical to Shannon?s information theory. However, for large, multi-functional systems with ill-defined roles, the new model provides a novel way of thinking about the complementarity of hardware and software. From gluck at pavlov.rutgers.edu Wed Apr 23 12:19:32 2003 From: gluck at pavlov.rutgers.edu (Mark A. Gluck) Date: Wed, 23 Apr 2003 12:19:32 -0400 Subject: Postdoc & RA/Programming Positions in Comp. Modeling of Memory Message-ID: Postdoc & RA/Programming Positions in Comp. Modeling of Memory We have two openings in our lab in the area of computational neuroscience, to develop and evaluate computational models of the neural bases of learning and memory, with special reference to the hippocampus and medial temporal lobes, the basal ganglia and striatum, cortico-striatal loops, and the role of key neuromodulators of these brain systems. For more information on our research and current lab personnel, see http://www.gluck.edu. All modeling takes places in the context, and is informed by, our ongoing experimental studies of learning and memory, including animal research, clinical studies of memory disordered patients (e.g., with Alzheimer's, Parkinson's, and schizophrenia), and functional brain imaging of healthy and impaired human subjects. One opening is for a postdoctoral fellow. The other is for a full-time Research Assistant/Programmer, ideally someone with a BA who is looking to gain research experience and publications, prior to applying to graduate school in the cognitive, neural, or computational sciences. For both positions, strong computer programming skills are essential (C, Java, or equivalent) as is prior programming experience, course work, and/or extensive independent reading in neural networks and computational neuroscience. Our lab is located at the Center for Molecular and Behavioral Neuroscience, at Rutgers University -Newark, located in downtown Newark, New Jersey, just 17 minutes by train from downtown New York City, NY. See http://www.cmbn.rutgers.edu. To apply, please send email to Mark Gluck, gluck at pavlov.rutgers.edu, with a full description of relevant past experience and future career goals. Both positions are available to be filled either immediately, this summer, or this coming fall. ________________________________________________ Dr. Mark A. Gluck, Associate Professor Center for Molecular and Behavioral Neuroscience Rutgers University - Newark Ph: (973) 353-1080 x3221 197 University Ave. Fx: (973) 353-1272 Newark, New Jersey 07102 E: gluck at pavlov.rutgers.edu Web pages: Research Lab: http://www.gluck.edu Rutgers Memory Disorders Project: http://www.memory.rutgers.edu Memory Loss & Brain Newsletter: http://www.memorylossonline.com/ "Gateway to Memory": http://mitpress.mit.edu/gatewaytomemory/ ________________________________________________ From d.mareschal at psychology.bbk.ac.uk Wed Apr 23 08:28:04 2003 From: d.mareschal at psychology.bbk.ac.uk (DR D MARESCHAL) Date: Wed, 23 Apr 2003 13:28:04 +0100 (BST) Subject: Lectureship available Message-ID: The following postion may be of interest to readersof this list/PLEASE DO NOT RESPOND DIRECTLY TO ME. cheers, Denis ======================= Birkbeck, University of London The School of Psychology Lecturer - Ref no: APS007 The School (RAE 5) is seeking to add to its existing strengths in developmental and cognitive psychology or cognitive neuroscience and needs a person to contribute teaching and research in one or both of these areas, and also to take responsibility for teaching research methods at undergraduate level. With a PhD, or equivalent in research and publications, in Psychology or related areas, you should have outstanding research ability or potential, focused on experimental, electrophysiological and computational approaches to cognition and brain development, attention and perception or language and memory. The posts are tenable from 1 October 2003. Salary range: 24,325 - 35,813 pa inc depending on qualifications and experience. Closing date: 7 May 2003. Full applications details from http://www.bbk.ac.uk or email: personnel at bbk.ac.uk or send a (A4) sae to the Personnel Department, Birkbeck, Malet Street, Bloomsbury, London WC1E 7HX (quoting the relevant reference number in all communications). NB: The College will be closed from 17-22 April inclusive & 5 May 2003 For informal enquiries contact: mark.johnson at bbk.ac.uk or m.eimer at bbk.ac.uk From ishikawa at brain.kyutech.ac.jp Fri Apr 25 05:57:52 2003 From: ishikawa at brain.kyutech.ac.jp (Masumi Ishikawa) Date: Fri, 25 Apr 2003 18:57:52 +0900 Subject: Special Issue of Neural Networks In-Reply-To: <5.0.2.5.2.20030425083702.00c5bed0@mail.brain.kyutech.ac.jp > References: <200304242054.h3OKsUud030520@haring.cs.utexas.edu> <5.0.2.5.2.20030424102040.039fae90@mail.brain.kyutech.ac.jp> <5.0.2.5.2.20030413092611.00f720b8@mail.brain.kyutech.ac.jp> <5.0.2.5.2.20030412095412.00f6b0d0@mail.brain.kyutech.ac.jp> <5.0.2.5.2.20030412095412.00f6b0d0@mail.brain.kyutech.ac.jp> <5.0.2.5.2.20030413092611.00f720b8@mail.brain.kyutech.ac.jp> <5.0.2.5.2.20030414162228.0278d588@mail.brain.kyutech.ac.jp> <5.0.2.5.2.20030424102040.039fae90@mail.brain.kyutech.ac.jp> Message-ID: <5.0.2.5.2.20030425183354.00c1d048@mail.brain.kyutech.ac.jp> Call for Papers 2004 Special Issue of Neural Networks New Developments in Self-Organizing Systems Research on self-organizing systems including self-organizing maps (SOMs) is an important area of unsupervised learning and has been rapidly growing in various directions: theoretical developments, applications in various fields, in-depth analysis of self-organizing systems in neuroscience and so forth. The Workshop on Self-Organizing Maps (WSOM) has been held biennially since 1997. In October, 2002, a Special Issue on Self-Organizing Maps was published in the journal Neural Networks selected from presentations at WSOM'01. The next workshop, WSOM'03, is scheduled to be held in September 2003 in Kitakyushu, Japan (for submission and participation details, see http://www.brain.kyutech.ac.jp/~wsom). Considering the extensive growth of this area, we plan another special issue related to self-organization in 2004, ranging from theoretical aspects to various applications. We will select papers from those submitted to this special issue of Neural Networks; papers will be either revisions of those presented at WSOM'03 or those directly submitted to the special issue. A limited number of invited papers by leading scientists are also planned. Technical areas include, but are not limited to: - Theory of self-organizing systems - Data visualization and mining - Applications to WEB intelligence - Applications to text and document analysis - Applications to robotics - Applications to image processing and vision - Applications to pattern recognition - Hardware and architecture - Self-organizing systems in neuroscience Co-Editors Masumi Ishikawa, Kyushu Institute of Technology Risto Miikkulainen, The University of Texas at Austin Helge Ritter, University of Bielefeld Submission Deadline for submission: December 10, 2003 Notification of acceptance: April 15, 2004 Deadline for submission of accepted papers: June 20, 2004 Deadline for submission of final papers: August 30, 2004 Format: as normal papers in the journal Address for Papers: Dr. Mitsuo Kawato ATR Human Information Science Laboratories 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan From becker at mcmaster.ca Wed Apr 30 16:16:27 2003 From: becker at mcmaster.ca (S. Becker) Date: Wed, 30 Apr 2003 16:16:27 -0400 (EDT) Subject: 2 positions in signal processing Message-ID: Dear colleagues, below are advertisements for two positions in my department, a Signal Processing Scientist and an Imaging Laboratory Technician. Please pass these on to any suitable candidates you know of. cheers, Sue Sue Becker, Associate Professor Department of Psychology, McMaster University becker at mcmaster.ca Building 34, Room 312 Fax: (905)529-6225 1280 Main Street West, Hamilton, Ont. L8S 4K1 Tel: 525-9140 ext. 23020 www.science.mcmaster.ca/Psychology/sb.html Signal Processing Scientist McMaster University invites applications for the position of Signal Processing Scientist in the Department of Psychology. The candidate will be expected to work with departmental brain imaging laboratories in the development and implementation of signal processing tools for EEG, MEG, and fMRI data, and to contribute an instructional role in the graduate programme under the supervision of faculty. The candidate should hold a PhD or MSc degree in a neuroscience field (e.g. biomedical engineering, experimental psychology, or neural computation) or present equivalent credentials from their work history. The initial appointment will be made for a three-year term with subsequent renewals contingent on budget approval. Salary will be commensurate with qualifications and experience. Candidates should send their curriculum vitae, a statement of their interests and relevant experience, representative publications (if available), and 3 letters of reference to: Scientist Search Committee Department of Psychology McMaster University 1280 Main Street West Hamilton, Ontario Canada L8S 4K1 Review of the applications will begin May 15 2003 and continue until the position is filled. All qualified candidates are encouraged to apply; however, Canadian citizens and permanent residents will be considered first for the position. McMaster University is strongly committed to employment equity within its community, and to recruiting a diverse faculty and staff. The University encourages applications from all qualified candidates, including women, members of visible minorities, aboriginal persons, members of sexual minorities, and persons with disabilities. Imaging Laboratory Technician McMaster University invites applications for the position of Imaging Laboratory Technician in the Department of Psychology. The candidate will be expected to be familiar with auditory and visual stimulus generation equipment, to write computer programmes for implementation of experiments on brain imaging, to assist in maintaining computer networks and security, and to support an undergraduate laboratory course in human electrophysiology under the supervision of faculty. Previous experience with state of the art EEG systems, MEG, or fMRI would be an asset. This is an entry-level position for a candidate holding a bachelor's degree in a relevant field (e.g., computer science, engineering, experimental psychology, neuroscience) or with equivalent work history. Initial appointment will be for a two-year term with subsequent renewals contingent on budget approval. Starting salary will be commensurate with qualifications and experience. Candidates should send their curriculum vitae, a statement of their interests and relevant experience, and 3 letters of reference to: ILT Search Committee Department of Psychology McMaster University 1280 Main Street West Hamilton, Ontario Canada L8S 4K1 Review of the applications will begin May 15 2003 and continue until the position is filled. All qualified candidates are encouraged to apply; however, Canadian citizens and permanent residents will be considered first for the position. McMaster University is strongly committed to employment equity within its community, and to recruiting a diverse faculty and staff. The University encourages applications from all qualified candidates, including women, members of visible minorities, aboriginal persons, members of sexual minorities, and persons with disabilities.