From mark.plumbley at elec.qmul.ac.uk Mon Apr 3 10:56:56 2006 From: mark.plumbley at elec.qmul.ac.uk (Mark Plumbley) Date: Mon, 3 Apr 2006 15:56:56 +0100 Subject: Connectionists: CFP: ICA Research Network Workshop, Liverpool, UK, 18-19 Sept 2006 Message-ID: <9D47A2D30B0BFB4C920786C25EC693456DCEAD@staff-mail.vpn.elec.qmul.ac.uk> Dear Connectionsts, I hope this workshop may be of interest to those of you working in ICA or source separation. Best wishes, Mark Plumbley ----------------- *** CALL FOR PAPERS *** 2006 ICA Research Network Workshop www.icarn.org Liverpool, UK 18 - 19 September 2006 The ICA Research Network is sponsored by the Engineering and Physical Sciences Research Council (EPSRC) in the UK, and is aimed at improving communications in the area of Blind Source Separation (BSS) and Independent Component Analysis (ICA). The 2006 ICA Research Network Workshop will be held at the University of Liverpool covering the latest developments and techniques in the area of BSS/ICA. Topics The workshop will feature keynote addresses and technical presentations (oral and poster), which will be included in the registration. Papers are solicited for, but not limited to, the following areas: * Algorithms and Architectures for BSS/ICA - Nonlinear ICA - Probabilistic Models - Sparse Coding - etc * Theory of BSS/ICA - Optimization - Complex Methods - Time-Frequency Representations - etc * Applications of BSS/ICA - Audio - Bio-Informatics - Biomedical Engineering - Communications - Finance - Image Processing - Psychology - Computational Auditory Scene Analysis (CASA) - etc Extended Abstract Submission Procedure Prospective authors are invited to submit extended abstracts of no more than two A4-size pages, including: * Title * Authors' details * the work with contexts and * preliminary results (a Table or a Figure) Submission Please submit your extended abstract by e-mail (with a PDF attachment) with the subject "Extended Abstract Submission" to icarnw06 at liverpool.ac.uk. Full Paper Submission Procedure Authors of accepted extended abstracts will be invited to submit a paper of up to four pages in the PDF format. At least one author of each accepted paper must undertake to attend the workshop. Accepted papers will be published in a bound volume. Authors of the most innovative papers will be invited to submit substantially extended and updated versions of their papers for further review and possible publication in the International Journal of Neural Systems. Important Dates/Deadlines Submission of extended abstract 5 May 2006 Notification of acceptance 2 June 2006 Submission of camera-ready accepted paper 7 August 2006 Author registration 7 August 2006 Workshop 18-19 September 2006 Contact For more information visit www.icarn.org or email icarnw06 at liverpool.ac.uk ************************************************************** Professor A K Nandi David Jardine Chair of Signal Processing Department of Electrical Engineering and Electronics The University of Liverpool Brownlow Hill, Liverpool, L69 3GJ, UK Tel: +44 151 794 4525 Fax: +44 151 794 4540 http://www.liv.ac.uk/eee/academicstaff/nandi.htm ************************************************************* --- Dr Mark D Plumbley Centre for Digital Music Department of Electronic Engineering Queen Mary University of London Mile End Road, London E1 4NS, UK Tel: +44 (0)20 7882 7518 Fax: +44 (0)20 7882 7997 Email: mark.plumbley at elec.qmul.ac.uk http://www.elec.qmul.ac.uk/people/markp/ From zhaoping at gatsby.ucl.ac.uk Mon Apr 3 15:04:38 2006 From: zhaoping at gatsby.ucl.ac.uk (Dr Zhaoping Li) Date: Mon, 3 Apr 2006 20:04:38 +0100 (BST) Subject: Connectionists: Postdoc position in vision/computational neuroscience in London Message-ID: Applications are invited for the post of Research Assistant to work with Dr. Li Zhaoping (http://www.gatsby.ucl.ac.uk/~zhaoping ) in the area of vision/neuroscience, particularly on biological vision, using theoretical and/or psychophysical investigation tools. It is essential that the candidate should have good capability/experience in either theoretical/modeling area or in visual psychophysical area, and skills/experience in both areas is not essential. The research assistant is expected to contribute to the research environment of the laboratory and should have the capability to work well in a team. The post is available around or after September 2006. Salary is on the Grade 6 of the new salary scales (?19,645-?23,457 plus ?2,400London allowance) and will depend upon qualifications and experience. Applications (email or hard copy ) by cover letter, CV and Personal Information form (the latter available at http://www.psychol.ucl.ac.uk/info/Personal_Information.doc) to Anouchka Sterling, Department of Psychology, UCL, Gower Street, London WC1E 6BT, a.sterling at ucl.ac.uk . If applying by email please submit all requested information in one .pdf file names by your surname eg Smith.pdf. Further information concerning the post are on the web at http://www.psychol.ucl.ac.uk/info/psychophysics_li.htm while interested candidates can also contact Li Zhaoping, z.li at ucl.ac.uk 44 20 7679 1174. The closing date for the application is 1 June 2006 From ted.carnevale at yale.edu Mon Apr 3 16:00:59 2006 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 03 Apr 2006 16:00:59 -0400 Subject: Connectionists: NEURON 2006 Summer Course Message-ID: <44317EFB.7010003@yale.edu> COURSE ANNOUNCEMENT What: "The NEURON Simulation Environment" (NEURON 2006 Summer Course) http://www.neuron.yale.edu/neuron/sdsc2006/sdsc2006.html When: Saturday, June 24, through Wednesday, June 28, 2006 Where: SDSC/CalIt2 Synthesis Center University of California at San Diego, CA Organizers: N.T. Carnevale and M.L. Hines Description: This intensive hands-on course covers the design, construction, and use of models in the NEURON simulation environment. It is intended primarily for those who are concerned with models of biological neurons and neural networks that are closely linked to empirical observations, e.g. experimentalists who wish to incorporate modeling in their research plans, and theoreticians who are interested in the principles of biological computation. The course is designed to be useful and informative for registrants at all levels of experience, from those who are just beginning to those who are already quite familiar with NEURON or other simulation tools. Registration is limited to 20, and the deadline for receipt of applications is Monday, June 5, 2006. For more information see http://www.neuron.yale.edu/neuron/sdsc2006/sdsc2006.html or contact Ted Carnevale Psychology Dept. PO Box 208205 Yale University New Haven, CT 06520-8205 USA phone 203-432-7363 fax 203-432-7172 email ted.carnevale at yale.edu Supported in part by: National Institutes of Health National Science Foundation The San Diego Supercomputer Center California Institute for Telecommunications and Information Technology Contractual terms require inclusion of the following statement: This course is not sponsored by the University of California. --Ted From J.Triesch at fias.uni-frankfurt.de Tue Apr 4 11:22:39 2006 From: J.Triesch at fias.uni-frankfurt.de (J.Triesch@fias.uni-frankfurt.de) Date: Tue, 4 Apr 2006 17:22:39 +0200 (CEST) Subject: Connectionists: Summer School: Theoretical Neuroscience & Complex Systems Message-ID: Final Call for Applications: Frankfurt Institute for Advanced Studies (FIAS) Summer School: Theoretical Neuroscience & Complex Systems We invite applications for a three-week summer workshop in Frankfurt, Germany from Saturday, August 5 to Sunday, August 27, 2006. The application deadline is Saturday, April 15. Application instructions are at the bottom of this announcement. FACULTY: Larry ABBOTT, Columbia University, USA Dana BALLARD, University of Texas, Austin, USA Emery BROWN, Harvard and MIT, USA Gyorgy BUZSAKI, Rutgers University, USA Gustavo DECO, Univ. Pompeu Fabra, Spain Yves FREGNAC, Centre National de la Recherche Scientifique, France Ralf GALUSKE, Max-Planck-Institute for Brain Research, Germany Wulfram GERSTNER*, Ecole Polytechnique Federale de Lausanne, France Rainer GOEBEL, Maastricht University, Netherlands Claudius GROS, Goethe University, Germany Aapo HYVARINEN, Univ. of Helsinki, Finland Christof KOCH, Caltech, USA Wolfgang MAASS, FIAS, Germany and Technische Universit????t Graz, Austria Bartlett MEL, University of South California, USA Lars MUCKLI, Max-Planck-Institute for Brain Research, Germany Sergio NEUENSCHWADER, Max-Planck-Institute for Brain Research, Germany Gordon PIPA, FIAS and Max-Planck Institute for Brain Research, Germany Wolf SINGER, FIAS and Max-Planck Institute for Brain Research, Germany Andrey SOLOV'YOV, FIAS, Germany Jochen TRIESCH, FIAS, Germany and UC San Diego, USA Misha TSODYKS, Weizmann Institute, Israel Christoph VON DER MALSBURG, FIAS, Germany Carl VAN VREESWIJK, Rene Descartes University, France Michael WIBRAL, Max-Planck Institute for Brain Research, Germany *not yet confirmed GOALS: There is a deficiency in the exchange of ideas between theoretical physicists and experimental biologists. This arises from different background knowledge bases and viewpoints, even when addressing the same problem. The aim of the FIAS Summer School on Theoretical Neuroscience and Complex Systems is to provide a bridge linking experimentalists and theorists. The school also addresses the challenge of further developing theoretical sciences and transferring existing concepts into the interdisciplinary field of neuroscience. This transference will be highly dependent on the successful training of students able to bridge the different fields. Participants will work on self-defined projects in interdisciplinary teams comprising at least one experimental neuroscientist and one theoretician. FORMAT: The three-week summer workshop will include a preschool that will take place at the Max-Planck Institute for Brain Research in Frankfurt. During these three days, theoretical physicists will be trained in basic concepts of neuroscience, experimental neuroscientists will be trained in basic concepts of network theory and complex systems, and theoretical neuroscientists will be trained in experimental neuroscience. The first two days of the summer school will be used to introduce the main concepts of neuronal systems and information processing. The second week is devoted to the characterization and analysis of neural recordings, as well as to the description and modeling of neurons, synapses, and small networks. The third week introduces approaches for modeling higher cognitive functions. Throughout, participants work on projects that they themselves propose, and this work will be carried out in collaboration with an interdisciplinary working-group comprising one experimental neuroscientist, one theoretical neuroscientist, and one theoretical physicist. Lectures will be held in the mornings from Monday-Friday, while students will work on their projects in the afternoons from Monday-Wednesday. Intra-group progress reports will be presented on Wednesday and Friday evenings. A preview of the following week's lectures will be provided on Thursday afternoons to ensure that all participants are comfortable with the material to be discussed. Saturdays will be devoted to "theory in practe" and participants will have the chance to visit research laboratories including the Max-Planck Institute for Brain Research in Frankfurt and the Honda Research Institute in Offenbach. Each Sunday will be reserved for recreational opportunities, and on the final day of the summer school, the projects will be presented. The scientific program will cover the following areas: - Neuroanatomy and Neurophysiology - Basics in modeling of neurons - Models of neural microcircuits - Abstract models of higher-level functions - Outlook to other complex systems LOCATION AND ARRANGEMENTS: FIAS is a Foundation of the Johann Wolfgang Goethe-University and is located on the natural science campus, Riedberg, in Frankfurt am Main. It also has close collaboration with the Faculty of Natural Sciences at the J.W. Goethe-University and the Max Planck Institutes for Brain Research and Biophysics. The preschool will take place at the Max-Planck Institute for Brain Research. Students and Lecturers will stay in the Marriott Courtyard Frankfurt Nordwestzentrum. The hotel is located very close to the FIAS Institute and has excellent access to the public transport system. FINANCIAL ARRANGEMENT: FIAS organizes the summer school and covers the accommodation and the cultural Program. Students have to pay a registration fee of 150 Euro. Students from Eastern European countries or students in general who need support for their travel expenses can apply for reimbursement and a waiver for the registration fee. Please indicate this in your application if you are considering applying for reimbursement. We will also need an estimation of your travel expenses. HOW TO APPLY: Students who have a bachelor, a master, a Ph.D., or other equivalent degrees can apply for this summer school. To apply, please provide two letters of recommendation, a curriculum vitae, as well as a one page description of a small project you are planning to work on during the course. Based on the proposal, the committee will group students to teams and assign interdisciplinary faculty to each team. Information about applying and the summer school in general can be found at the website: http://www.fias.uni-frankfurt.de/neuro_school/ A copy of the summer school announcement can be downloaded from: http://www.fias.uni-frankfurt.de/neuro_school/FIAS_summerschool_Poster_A2.pdf Applications should include: * First name, last name, affiliation, valid e-mail address * Two letters of recommendation * Curriculum Vitae * Project proposal (max. one page) * Request for reimbursement of travel expenses (if applicable) Please send your documents in an electronic format to: neuro_school at fias.uni-frankfurt.de The application deadline is Saturday, April 15, 2006. Applicants will be notified by e-mail by May 1, 2006. For further information, please contact: Denise Meixler (neuro_school at fias.uni-frankfurt.de) Frankfurt Institute for Advanced Studies Johann Wolfgang Goethe University Max-von-Laue-Str. 1 60438 Frankfurt am Main Germany tel: +49 69 798 47851 fax: +49 69 798 47876 From ted.carnevale at yale.edu Thu Apr 6 13:00:12 2006 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Thu, 06 Apr 2006 13:00:12 -0400 Subject: Connectionists: talks and tutorials at the NEURON Simulator Meeting Message-ID: <4435491C.4030008@yale.edu> The agenda for the 2006 NEURON Simulator Meeting continues to grow. Here are three more reasons to join us at UT Austin, May 5-7-- Discussion: "NEURON: quo vadis?" Moderator: Michael Hines The agenda is to discuss future directions for NEURON, in order to help it continue to evolve to meet the changing needs of its users. Topics that will be considered include strategies for improving the development process, possible enhancements of computational efficiency and power, and tactics for increasing functionality and ease of use. Tutorial: "Converting morphometric data to models with the Import3D tool" Speaker: Ted Carnevale One recent addition to NEURON is the Import3D tool, which was created to simplify the task of converting detailed morphometric data to NEURON models. Import3D can read Eutectic, SWC, and Neurolucida classic and Version 3 files, and can export the data directly into the CellBuilder or generate a "top level" instance of a model. It automatically identifies and repairs many common problems, and helps users identify other errors that require the exercise of judgment and manual editing of a copy of the original morphometric data. Workshop: "Hacking NEURON." Moderators: Ted Carnevale and Bill Lytton The aim of this event is to exchange "power programming" tips for getting the most out of NEURON. Discussion and specific practical examples will range over topics such as: ? essential idioms in hoc ? organizing programs for efficiency and clarity ? combining hoc code and the GUI to exploit the strengths of both ? discovering and exploiting the single largest collection of useful hoc code ? hacking session files ? hacking NEURON's run-time system ? custom initializations ? automating execution of simulations and analysis of results The moderators will present many of their own tips and tricks, and audience participation is strongly encouraged. Register now--the registration deadline is Friday, April 21. For more information see http://www.utexas.edu/neuroscience/NEURON2006/nsm2006.html --Ted From doya at irp.oist.jp Thu Apr 6 14:59:51 2006 From: doya at irp.oist.jp (Kenji Doya) Date: Fri, 7 Apr 2006 03:59:51 +0900 Subject: Connectionists: Okinawa Computational Neuroscience Course 2006: Call for Applications References: <9766557bd8a85e3eca7a9175d6973c9b@irp.oist.jp> Message-ID: <0FD0BCBF-68ED-449C-9F29-86647023DCFA@irp.oist.jp> The deadline of OCNC 2006 application is next Monday. **************************************************************** Call for Applications OKINAWA COMPUTATIONAL NEUROSCIENCE COURSE 2006 "Computing Neurons" June 26 - July 7, 2006. Okinawa, Japan. http://www.irp.oist.jp/ocnc/2006 Application Deadline: APRIL 10TH, 2006 The aim of Okinawa Computational Neuroscience Course is to provide opportunities for young researchers with theoretical backgrounds to learn latest advances in neuroscience, and those with experiment backgrounds to have hands-on experience in computational modeling. We invite graduate students and postgraduate researchers to participate in the course, held from June 26th through July 7th at an oceanfront seminar house of Okinawa Institute of Science and Technology. Those interested in attending the course should send the materials below by e-mail or the course web page by APRIL 10th, 2006. We hope that this course will be a good opportunity for theoretical and experimental neuroscientists to meet together and to explore the attractive nature and culture of Okinawa, the southernmost island prefecture of Japan. ******* Course Outline ******* Okinawa Computational Neuroscience Course (OCNC2006) Theme: Computing Neurons - What neurons compute; How we know by computing - Our brain is a network of billions of neurons, but even a single neuron is a fantastically complex computing device. Technology has made it possible to look into the detailed structure of dendritic branches, variety of ionic channels and receptors, molecular reactions at the synapses, and the network of genes that regulate all these. The challenge is to understand the meaning and function of these components of the neural machine. To do this we need to put together data from many experiments at different levels into a computational model, and to analyze the kinds of computation that single neurons and their networks can perform. This course invites graduate students and postgraduate researchers who are interested in studies integrating experimental and computational approaches for understanding cellular mechanisms of neurons. Lectures: Upi Bhalla (NCBS) Haruhiko Bito (U Tokyo) Sydney Brenner (OIST) Yang Dan (UC Berkeley) Erik DeSchutter (U Antwerp) Kenji Doya (OIST) Bard Ermentrout (U Pittsburgh) Geoff Goodhill (U Queensland) David Holcman (Weizmann institute of Science) Shin Ishii (NAIST) Shinya Kuroda (U Tokyo) Nicolas Le Novere (European Bioinformatics Institute) Roberto Malinow (Cold Spring Harbor Lab) Ion Moraru (U of Connecticut) Felix Schuermann (EPFL) Terry Sejnowski (Salk Institute) Susumu Tonegawa (MIT) Jeff Wickens (U Otago) Student Projects a) Introduction to neural/cellular simulator platforms b) Model construction from experimental data c) Analysis of neuron models Students will present posters on their current works early in the course and the results of their projects at the end of the course. Date: June 26th to July 7th, 2006 Place: Okinawa Institute of Science and Technology Onna village, Okinawa, Japan Sponsors: Okinawa Institute of Science and Technology Nara Institute of Science and Technology Japanese Neural Network Society Co-organizers: Upinder Bhalla, National Center for Biological Sciences, India Kenji Doya, Okinawa Institute of Science and Technology Shinya Kuroda, University of Tokyo Nicolas Le Novere (European Bioinformatics Institute) Advisors: Sydney Brenner, Okinawa Institute of Science and Technology Hiroaki Kitano, SONY Computer Science Laboratory Terrence Sejnowski, Salk Institute Susumu Tonegawa, Massachusetts Institute of Technology ******* Application ******* Please send the following by e-mail (ocnc at irp.oist.jp) or the web application page by APRIL 10TH, 2006. 1) First name, 2) Middle initial (if any), 3) Family name, 4) Degree, 5) Date of birth, 6) Gender, 7) Nationality, 8) Affiliation, 9) Position, 10) Advisor, 11) Postal address, 12) Phone, 13) Fax, 14) E-mail, 15) Web page (if any), 16) Educational background, 17) Work experience, 18) List of publications, 19) Research interests (up to 500 words), 20) Motivations for attending the course (up to 500 words), 21) Two referees whom can ask recommendations (names, affiliations, e-mail addresses), 22) Need for travel support, 23) How you learned about the course. We will accept 30 students based primarily on their research interests (19) and motivations (20). We will also consider the balance of members' research disciplines, geographic origins, and genders. The sponsor will provide lodging and meals during the course. Support for roundtrip airfare to Okinawa will be considered for students without funding. The result of selection will be informed to applicants via e-mail by May 10th. The details of OCNC2004 and 2005 are available on the web page (http://www.irp.oist.jp/ocnc/). ******* Secretariat ******* Okinawa Computational Neuroscience Course c/o Initial Research Project, Okinawa Institute of Science and Technology 12-22 Suzaki, Gushikawa Okinawa 904-2234, Japan Phone: +81-98-921-3933 Fax: +81-98-921-3873 Email: ocnc at irp.oist.jp For more information, please visit the web page: http://www.irp.oist.jp/ocnc/2006 ---- Kenji Doya Initial Research Project, Okinawa Institute of Science and Technology 12-22 Suzaki, Uruma, Okinawa 904-2234, Japan Phone:+81-98-921-3843; Fax:+81-98-921-3873 http://www.irp.oist.jp/ From saighi at ixl.fr Thu Apr 6 05:59:40 2006 From: saighi at ixl.fr (Sylvain SAIGHI) Date: Thu, 06 Apr 2006 11:59:40 +0200 Subject: Connectionists: Post-Doc position (1 year) Message-ID: <4434E68C.9090305@ixl.fr> Post-doc position (1 year) in IXL- CNRS UMR 5818 - Bordeaux, France Subject : ? Design of living-artificial interface IC for hybrid neural networks ? <>Offer description : The proposed subject is related to the EU project Neuro-vers-IT (FP6-2004-Mobility 019247, start 1/01/2006), in which IXL is a partner. The goal of that project is to reinforce the European multi -disciplinary research activities in Information Technology, Biomedical Engineering, and Robotics. IXL is in charge of designing systems to interface biological and artificial neurons, using dedicated integrated circuits (IC) and systems running in real time. The developed platforms will allow the characterization (including modeling) of learning and plasticity phenomenas in cultured neural networks on a long-term basis. <>Candidate profile : The candidate has to be an expert in analog and mixed IC design. Basis knowledge in neurophysiology or in cognitive science will be appreciated. He/she will have frequent missions (up to a few weeks) in partners laboratories (in France and abroad) : good English skills are necessary. Duration : 1 year(s) Laboratory : IXL, CNRS UMR 5818, ENSEIRB-Universit? Bordeaux 1 (Laboratoire d'?tudes de l'int?gration des composants et syst?mes ?lectroniques) 351 cours de la Lib?ration, 33405 Talence, France. http://www.ixl.fr/ Contact : Pr Sylvie RENAUD +33 540002796 renaud at ixl.fr From saighi at ixl.fr Thu Apr 6 06:05:31 2006 From: saighi at ixl.fr (Sylvain SAIGHI) Date: Thu, 06 Apr 2006 12:05:31 +0200 Subject: Connectionists: PhD position in the field of Engineering of Neuromorphic Systems Message-ID: <4434E7EB.7000405@ixl.fr> In the framework of the European Union's Marie Curie network for human resources and mobility activity, a new project "NeuroVers-IT" investigating Neuro-Cognitive Science and Information Technology has been set up. The project aims at collaborative, highly multidisciplinary research between 11 European well-known research institutions in the areas of neuro-/cognitive sciences/biophysics and robotics/information technologies/ mathematics. <>For this project, IXL Microelectronics Laboratory in Bordeaux, France, is looking for Early-Stage Researcher (holding a Master's degree entitling him/her to pursue a PhD degree, beginning September 2006) The ideal candidate should have a university degree in electrical engineering. An expertise in mixed-analog IC design and VHDL language, a good knowledge of spoken and written English and a strong interest in computational neurosciences are required. The project concerns the development of VLSI circuits and electronics systems of high biological relevance that emulate in real-time multi-conductances neurons and neural networks with adaptive properties. The work will be conducted at the IXL Microelectronics laboratory (www.ixl.fr ), a CNRS institution associated to ENSEIRB-Universit? Bordeaux 1. IXL is located on the Bordeaux Science campus. The PhD student will join the research group "Engineering of Neuromorphic Systems"; <>To be eligible the candidate shall not be French citizen and not have resided in France for more than 12 months in the last 3 years. For information about this position you may contact Prof. Sylvie RENAUD IXL Laboratory, CNRS, ENSEIRB, Universit? Bordeaux 1 Email: renaud at ixl.fr Tel. +33 5 4000 2796. Please send your written application including your CV and other relevant material. From fschwenker at neuro.informatik.uni-ulm.de Fri Apr 7 04:24:19 2006 From: fschwenker at neuro.informatik.uni-ulm.de (Friedhelm Schwenker) Date: Fri, 07 Apr 2006 10:24:19 +0200 Subject: Connectionists: Positions at the University of Ulm Message-ID: <443621B3.3050408@neuro.informatik.uni-ulm.de> The Institute for Neural Information Processing at the University of Ulm (Germany) is a lab with two full professors, 4 postdocs and about 20 students and researchers in different areas of neural network research. Ongoing work includes mobile autonomous robots, computer vision, neural modelling, and pattern recognition. Successful applicants will be expected to conduct research involving ? pattern recognition or sensor fusion with artificial neural networks, or ? information processing in networks of spiking neurons, or ? large associative memory systems with possible applications in autonomous vehicles, bioinformatics, medicine, speech or vision, or modelling and recognition of emotions. Candidates should have a recent PhD-degree for example in computer science, physics, mathematics or electrical engineering. Applications for PhD-work are also possible. In this case the applicants should already have some experience in one of the fields mentioned above. Two positions will become available during 2006. The appointment will be for at least 2 years. Salary will be BAT IIa (details depend on age and family status). Applications should be sent to Prof. Dr. Palm by May 05, 2006, via email. Please make sure that they are complete and in a convenient format. Prof. Dr. G?nther Palm Head of the Department of Neural Information Processing University of Ulm 89069 Ulm Germany Email: guenther.palm at uni-ulm.de URL: http://www.informatik.uni-ulm.de/neuro/ -- ---------------------------------------------------------------------- Dr. Friedhelm Schwenker University of Ulm | email: friedhelm.schwenker at uni-ulm.de Department of Neural | fax: +49-731-50-24156 Information Processing | phone: +49-731-50-24159 D-89069 Ulm (Germany) | www: http://www.informatik.uni-ulm.de/ni/mitarbeiter/FSchwenker.html ---------------------------------------------------------------------- From christian.igel at neuroinformatik.ruhr-uni-bochum.de Mon Apr 10 09:31:22 2006 From: christian.igel at neuroinformatik.ruhr-uni-bochum.de (Christian Igel) Date: Mon, 10 Apr 2006 15:31:22 +0200 Subject: Connectionists: PhD positions in theoretical cognitive science / neuroscience Message-ID: <443A5E2A.7030305@neuroinformatik.rub.de> PhD positions in theoretical cognitive science / neuroscience Institut f?r Neuroinformatik, Ruhr-Universit?t Bochum, Germany The chair in Theoretical Biology at the Ruhr-University Bochum is seeking applications for doctoral studentships in the areas of theoretical cognitive science and theoretical neuroscience. Our research program is centered on embodied and situated cognition and is based on the theoretical framework of Dynamical Systems Theory, of which Dynamical Field Theory is a particular branch that emphasizes the neuronal foundations of these concepts. Doctoral students will select a research topic within three areas: (a) serial order; (b) learning theory; (c) multi-degree of freedom motor control. All projects will have a core modelling component, around which new theoretical ideas will be developed, but will also involve close collaboration with associated experimental research groups. Additional background information is available at http://www.neuroinformatik.rub.de/thbio/group/cognition/index.html The positions will be paid at the BATIIa/2 level (approximately 1800 Euro/month depending on age and family status). Applications including curriculum vitae and transcripts, as well, whenever possible, the name of one or more references are welcome. Application via email to Institut at neuroinformatik.ruhr-uni-bochum.de is encouraged. Alternatively send your material to Prof. Dr. Gregor Sch?ner, Institut f?r Neuroinformatik, Ruhr-Universit?t Bochum, 44780 Bochum, Germany. The selection process will begin May 1, 2006 and will continue until the positions are filled. Prof. Dr. Gregor Sch?ner Lehrstuhl Theoretische Biologie Institut f?r Neuroinformatik Ruhr-Universit?t Bochum 44780 Bochum, Germany tel: +49-234-322-7965 (office) +49-234-6406461 (home) fax: +49-234-321-4209 email: Gregor.Schoener at neuroinformatik.ruhr-uni-bochum.de http://www.neuroinformatik.rub.de/thbio/members/profil/Schoener/index.html From terry at salk.edu Mon Apr 10 18:34:33 2006 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 10 Apr 2006 15:34:33 -0700 Subject: Connectionists: NEURAL COMPUTATION 18:5 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 18, Number 5 - May 1, 2006 Article Singularities Affect Dynamics of Learning in Neuromanifolds Shun-ichi Amari, Hyeyoung Park, and Tomoro Ozeki Letters How Noise Affects the Synchronization Properties of Recurrent Networks of Inhibitory Neurons Nicolas Brunel and David Hansel Analysis of Synchronization between Two Modules of Pulse Neural Networks with Excitatory and Inhibitory Connections Takashi Kanamaru A Sensorimotor Map: Modulating Lateral Interactions for Anticipation and Planning Marc Toussaint Coupling of Neural Computation with Physical Computation for Stable Dynamic Biped Walking Control Tao Geng, Bernd Porr and Florentin Woergoetter A Set Probability Technique for Detecting Relative Time Order Across Multiple Neurons Anne C. Smith and Peter Smith Payoff-Monotonic Game Dynamics and the Maximum Clique Problem Marcello Pelillo and Andrea Torsello ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2006 - VOLUME 18 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $154 $90 $96.30 Institution $730 $781.10 $784 $657 $702.99 * 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 epitkane at cs.helsinki.fi Fri Apr 7 08:04:27 2006 From: epitkane at cs.helsinki.fi (Esa A Pitkanen) Date: Fri, 07 Apr 2006 15:04:27 +0300 Subject: Connectionists: CFP: Probabilistic Modeling and Machine Learning in Structural and Systems Biology Message-ID: <4436554B.1070104@cs.helsinki.fi> CALL FOR PAPERS Workshop on Probabilistic Modeling and Machine Learning in Structural and Systems Biology http://www.cs.helsinki.fi/group/bioinfo/events/pmsb06/ Tuusula, Finland, 17-18 June 2006 Deadline for submission: April 23, 2006 Motivation The ever-ongoing growth in the amount of biological data, the development of genome-wide measurement technologies, and the shift from the study of individual genes to systems view all contribute to the need to develop computational techniques for learning models from data. At the same time, the increase in available computational resources has enabled new, more realistic modeling methods to be adopted. In bioinformatics, most of the targets of interest deal with complex structured objects: sequences, 2D and 3D structures or interaction networks. In many cases these structures are naturally described by probabilistic graphical models, such as Hidden Markov Models, Conditional Random Fields or Bayesian Networks. Recently, approaches that combine Support Vector Machines and probabilistic models have been introduced (Fisher kernels, Max-margin Markov Networks, Structured SVM). These techniques benefit from efficient convex optimization approaches and thus are potentially well-scalable to large problems in bioinformatics. The increasing amount of high-throughput experimental data begins to enable the use of these advanced modelling methods in bioinformatics and systems biology. At the same time new computational challenges emerge. Statistical methods are required to process the data so that underlying potentially complex statistical patterns can be discerned from spurious patterns created by random effects. At its simplest this problem calls for data normalization and statistical hypothesis testing, in the more general case, one is required to select a model (e.g. gene network) that best explains the data. Objective The aim of this workshop is to provide a broad look at the state of the art in the probabilistic modeling and machine learning methods involving biological structures and systems, and to bring together method developers and experimentalists working with the problems. We encourage submissions bringing forward methods for discovering complex structures (e.g. interaction networks, molecule/cellular structures) and methods supporting genome-wide data analysis. A non-exhaustive list of topics suitable of this workshop: Methods * Algorithms * Bayesian Methods * Data integration/fusion * Feature/subspace selection * High-throughput methods * Kernel Methods * Machine Learning * Probabilistic Inference * Structured output prediction Applications * Sequence Annotation * Gene Expression * Gene Networks * Gene Prediction * Metabolic Profiling * Metabolic Reconstruction * Protein Structure Prediction * Protein Function Prediction * Protein-protein interaction networks The workshop is organized by the European Network of Excellence PASCAL (Pattern Analysis, Statistical Modelling and Computational Learning) and belongs to the thematic programme on 'Learning with Complex and Structured Outputs'. The workshop is immediately followed by the International Specialised Symposium on Yeasts (ISSY25, June 18-21 2006) that has the theme 'Systems biology of Yeast - From Models to Applications'. Submissions We invite to submit an extended abstract of maximum four pages, formatted according to the Springer Lecture Notes in Computer Science style, to the email address juho.rousu at cs.helsinki.fi Selected papers from the workshop will be published in BMC Bioinformatics special issue. BMC Bioinformatics has impact factor 5.42, which makes it the second highest ranked bioinformatics journal. Important dates * April 23, 2006: Abstract submission deadline * May 7, 2006: Notification of acceptance * May 31, 2006: Final version due * June 17-18, 2006: Workshop Invited Speakers (confirmed) * Tommi Jaakkola, MIT * Koji Tsuda, CBRC / AIST, Japan Organizing Committee * Florence d'Alch?-Buc, Universit? d'Evry-Val d'Essonne * Jaakko Astola, Tampere University of Technology * Nello Cristianini, UC Davis / University of Bristol * Liisa Holm, University of Helsinki * Mark Girolami, University of Glasgow * Samuel Kaski, Helsinki University of Technology * Matej Oresic, Technical Research Centre of Finland * Juho Rousu, University of Helsinki * Esko Ukkonen, Helsinki Institute for Information Technology * Jean-Philippe Vert, Ecole des Mines de Paris Local Organization * Juho Rousu, University of Helsinki * Samuel Kaski, Helsinki University of Technology * Esko Ukkonen, Helsinki Institute for Information Technology * Esa Pitk?nen, University of Helsinki, workshop secretary Location * The workshop will be held in Conference Hotel Gustavelund, 15 minute trip from Helsinki-Vantaa airport. -------------- next part -------------- CALL FOR PAPERS Workshop on Probabilistic Modeling and Machine Learning in Structural and Systems Biology http://www.cs.helsinki.fi/group/bioinfo/events/pmsb06/ Tuusula, Finland, 17-18 June 2006 Motivation The ever-ongoing growth in the amount of biological data, the development of genome-wide measurement technologies, and the shift from the study of individual genes to systems view all contribute to the need to develop computational techniques for learning models from data. At the same time, the increase in available computational resources has enabled new, more realistic modeling methods to be adopted. In bioinformatics, most of the targets of interest deal with complex structured objects: sequences, 2D and 3D structures or interaction networks. In many cases these structures are naturally described by probabilistic graphical models, such as Hidden Markov Models, Conditional Random Fields or Bayesian Networks. Recently, approaches that combine Support Vector Machines and probabilistic models have been introduced (Fisher kernels, Max-margin Markov Networks, Structured SVM). These techniques benefit from efficient convex optimization approaches and thus are potentially well-scalable to large problems in bioinformatics. The increasing amount of high-throughput experimental data begins to enable the use of these advanced modelling methods in bioinformatics and systems biology. At the same time new computational challenges emerge. Statistical methods are required to process the data so that underlying potentially complex statistical patterns can be discerned from spurious patterns created by random effects. At its simplest this problem calls for data normalization and statistical hypothesis testing, in the more general case, one is required to select a model (e.g. gene network) that best explains the data. Objective The aim of this workshop is to provide a broad look at the state of the art in the probabilistic modeling and machine learning methods involving biological structures and systems, and to bring together method developers and experimentalists working with the problems. We encourage submissions bringing forward methods for discovering complex structures (e.g. interaction networks, molecule/cellular structures) and methods supporting genome-wide data analysis. A non-exhaustive list of topics suitable of this workshop: Methods * Algorithms * Bayesian Methods * Data integration/fusion * Feature/subspace selection * High-throughput methods * Kernel Methods * Machine Learning * Probabilistic Inference * Structured output prediction Applications * Sequence Annotation * Gene Expression * Gene Networks * Gene Prediction * Metabolic Profiling * Metabolic Reconstruction * Protein Structure Prediction * Protein Function Prediction * Protein-protein interaction networks The workshop is organized by the European Network of Excellence PASCAL (Pattern Analysis, Statistical Modelling and Computational Learning) and belongs to the thematic programme on 'Learning with Complex and Structured Outputs'. The workshop is immediately followed by the International Specialised Symposium on Yeasts (ISSY25, June 18-21 2006) that has the theme 'Systems biology of Yeast - From Models to Applications'. Submissions We invite to submit an extended abstract of maximum four pages, formatted according to the Springer Lecture Notes in Computer Science style, to the email address juho.rousu at cs.helsinki.fi Selected papers from the workshop will be published in BMC Bioinformatics special issue. BMC Bioinformatics has impact factor 5.42, which makes it the second highest ranked bioinformatics journal. Important dates * April 23, 2006: Abstract submission deadline * May 7, 2006: Notification of acceptance * May 31, 2006: Final version due * June 17-18, 2006: Workshop Invited Speakers (confirmed) * Tommi Jaakkola, MIT * Koji Tsuda, CBRC / AIST, Japan Organizing Committee * Florence d'Alch?-Buc, Universit? d'Evry-Val d'Essonne * Jaakko Astola, Tampere University of Technology * Nello Cristianini, UC Davis / University of Bristol * Liisa Holm, University of Helsinki * Mark Girolami, University of Glasgow * Samuel Kaski, Helsinki University of Technology * Matej Oresic, Technical Research Centre of Finland * Juho Rousu, University of Helsinki * Esko Ukkonen, Helsinki Institute for Information Technology * Jean-Philippe Vert, Ecole des Mines de Paris Local Organization * Juho Rousu, University of Helsinki * Samuel Kaski, Helsinki University of Technology * Esko Ukkonen, Helsinki Institute for Information Technology * Esa Pitk?nen, University of Helsinki, workshop secretary Location * The workshop will be held in Conference Hotel Gustavelund, 15 minute trip from Helsinki-Vantaa airport. From knorman at Princeton.EDU Mon Apr 10 12:29:35 2006 From: knorman at Princeton.EDU (Ken Norman) Date: Mon, 10 Apr 2006 12:29:35 -0400 Subject: Connectionists: Postdoctoral position, Princeton Computational Memory Lab Message-ID: <443A87EF.8080002@princeton.edu> Dear connectionists, I have a job opening for a postdoctoral researcher in my laboratory (job description appended below). In my lab, we use connectionist models of hippocampus and cortex to generate predictions about behavioral memory performance, and also about how neural representations change (over short and long time scales) during learning and memory tasks; we test these predictions in both normal and amnesic subjects. We are particularly interested in achieving better integration between neural network models and neuroimaging data (e.g., by using pattern classification methods, applied to fMRI and EEG data, to decode what information is represented in the brain and how these representations change over time). Please email me (knorman at princeton.edu) if you have any questions. Best! Ken Norman here is the official job description: RESEARCH ASSOCIATE, PRINCETON UNIVERSITY. A postdoctoral position is available in the Psychology Department at Princeton University. The project, led by Dr. Ken Norman, uses computational models, combined with behavioral and fMRI studies of brain damaged patients and normal subjects, to study the neural mechanisms of episodic memory. REQUIREMENTS: completed Ph.D. and strong background in the cognitive and/or computational neuroscience of memory. Submit CVs to Carol Agans, Department of Psychology, Green Hall, Princeton University, Princeton, NJ 08540 or by email to agans at princeton.edu. For more information about Dr. Norman's Computational Memory Lab, please visit http://compmem.princeton.edu. For information about applying to Princeton, please link to http://web.princeton.edu/sites/dof/ApplicantsInfo.htm.PU/EO/AAE From neuralassembly at yahoo.co.jp Tue Apr 11 12:16:42 2006 From: neuralassembly at yahoo.co.jp (Takashi KANAMARU) Date: Wed, 12 Apr 2006 01:16:42 +0900 (JST) Subject: Connectionists: Two papers on periodic or chaotic synchronization in PNN Message-ID: <20060411161642.56644.qmail@web3411.mail.bbt.yahoo.co.jp> Dear all, I would like to announce two papers on periodic or chaotic synchronization in PNN are available from the following page. http://brain.cc.kogakuin.ac.jp/~kanamaru/research/ Takashi Kanamaru, Analysis of synchronization between two modules of pulse neural networks with excitatory and inhibitory connections, Neural Computation, vol.18, no.5 (2006) pp.1111-1131. http://brain.cc.kogakuin.ac.jp/~kanamaru/research/kanamaru-nc2006.pdf Abstract To study the synchronized oscillations among distant neurons in the visual cortex, the synchronization between two modules of pulse neural networks was analyzed using the phase response function. It was found that the inter-module connections from excitatory to excitatory ensembles tend to stabilize the anti-phase synchronization, and that the inter-module connections from excitatory to inhibitory ensembles tend to stabilize the in-phase synchronization. It was also found that the inter-module synchronization was more noticeable when the inner-module synchronization was weak. Takashi Kanamaru, Blowout bifurcation and on-off intermittency in pulse neural networks with multiple modules, International Journal of Bifurcation and Chaos, vol.16, no.11 (2006) (in press). http://brain.cc.kogakuin.ac.jp/~kanamaru/research/kanamaru-ijbc2006.pdf Abstract To study the mechanism by which high-dimensional chaos emerges in neural systems, the synchronization of chaotic firings in class 1 pulse neural networks composed of excitatory and inhibitory ensembles was analyzed. In the system with two modules (i.e., two pulse neural networks), blowout bifurcation and on-off intermittency were observed when the inter-module connection strengths were reduced from large values. In the system with three modules, rearrangement of synchronized clusters and chaotic itinerancy were observed. Such dynamics may be one of the mechanisms through which high-dimensional chaos is generated in neural systems. Best regards, Takashi KANAMARU http://brain.cc.kogakuin.ac.jp/~kanamaru/ Department of Innovative Mechanical Engineering, Faculty of Global Engineering, Kogakuin University, 2665-1 Nakano, Hachioji-city, Tokyo 192-0015, Japan From fschwenker at neuro.informatik.uni-ulm.de Tue Apr 11 08:46:36 2006 From: fschwenker at neuro.informatik.uni-ulm.de (Friedhelm Schwenker) Date: Tue, 11 Apr 2006 14:46:36 +0200 Subject: Connectionists: Positions at the University of Ulm Message-ID: <443BA52C.8080907@neuro.informatik.uni-ulm.de> Two post-doc (or PhD-student) positions will become available during 2006 at the Department of Neural Information Processing at the University of Ulm. The Institute for Neural Information Processing at the University of Ulm (Germany) is a lab with two full professors, 4 postdocs and about 20 students and researchers in different areas of neural network research. Ongoing work includes mobile autonomous robots, computer vision, neural modelling, and pattern recognition. Successful applicants will be expected to conduct research involving ? pattern recognition or sensor fusion with artificial neural networks, or ? information processing in networks of spiking neurons, or ? large associative memory systems with possible applications in autonomous vehicles, bioinformatics, medicine, speech or vision, or modelling and recognition of emotions. Candidates should have a recent PhD-degree for example in computer science, physics, mathematics or electrical engineering. Applications for PhD-work are also possible. In this case the applicants should already have some experience in one of the fields mentioned above. The appointment will be for at least 2 years. Salary will be BAT IIa (details depend on age and family status). Applications should be sent to Prof. Dr. Palm by May 05, 2006, via email. Please make sure that they are complete and in a convenient format. Prof. Dr. G?nther Palm Head of the Department of Neural Information Processing University of Ulm 89069 Ulm Germany Email: guenther.palm at uni-ulm.de URL: http://www.informatik.uni-ulm.de/neuro/ - From mark.plumbley at elec.qmul.ac.uk Tue Apr 11 07:39:35 2006 From: mark.plumbley at elec.qmul.ac.uk (Mark Plumbley) Date: Tue, 11 Apr 2006 12:39:35 +0100 Subject: Connectionists: PhD Study in Centre for Digital Music, Queen Mary University of London Message-ID: <9D47A2D30B0BFB4C920786C25EC693456DD23F@staff-mail.vpn.elec.qmul.ac.uk> Dear Connectionists, Apologies for cross-posting: please forward to anyone in your group who may be interested. Yes I know "digital music" may not sound very connectionist at first, but we have a particular interest in techniques such as independent component analysis (ICA) and Bayesian inference methods applied to musical audio analysis and separation, as well as in biologically-inspired audio processing, so applications anyone interested in PhD research study in those areas would be most welcome. Also, for those of you near to London, we will be taking part in our department's Research Open Day on 27 April 2006. For more information and registration instructions, see http://www.elec.qmul.ac.uk/opendayposter/. Best wishes, Mark Plumbley ------------ PhD Study in Centre for Digital Music, Queen Mary University of London The Centre for Digital Music at Queen Mary University of London is a world-leading research group in the field of Music & Audio Technology. Our research covers everything in digital music and audio: from analysis, understanding and retrieval to delivery, synthesis and sound rendering. We seek not only to investigate new applications of digital signal processing (DSP), but also to push forward the frontiers of DSP itself. Applications are invited for PhD research study in any of our areas of interest. Possible topic areas might include: automatic music transcription; harmony analysis; auditory scene analysis; beat tracking & rhythm analysis; blind source separation & independent component analysis (ICA); joint audio/video tracking and transcription; A/D & D/A conversion; sigma delta modulation; scalable audio codecs; object based coding; sparse representations & sparse coding; music information retrieval; semantic markup, musical metadata & MPEG7 applications; audio effects; 3D sound & multi-loudspeaker rendering systems; intelligent microphone arrays; automatic accompaniment; interactive performance/internet jamming; interactive compositional tools; biologically inspired audio processing; and pervasive audio ("my music wherever I am"). We have recently invested ?300k in a new state-of-the-art audio listening facility, and we are keen to encourage at least one project in the area of 3D sound which would be allied to this new facility. For more information about the Centre for Digital Music and our research, see http://www.elec.qmul.ac.uk/digitalmusic/ Funding: The Centre for Digital Music is part of the Department of Electronic Engineering, which has a number of EPSRC-funded Research Studentships that cover fees and maintenance for UK students, or fees-only for EU students. One additional Studentship is available that can cover fees and maintenance for a UK or EU student. There is always strong competition for Research Studentships, so early application is recommended. Applications are also welcomed from self-funded students. Application Applicants should follow the guidelines that can be found at http://www.elec.qmul.ac.uk/study/phd/res-stud.htm For informal enquiries, please contact Dr Mark Plumbley (mark.plumbley at elec.qmul.ac.uk) --- Dr Mark D Plumbley Centre for Digital Music Department of Electronic Engineering Queen Mary University of London Mile End Road, London E1 4NS, UK Tel: +44 (0)20 7882 7518 Fax: +44 (0)20 7882 7997 Email: mark.plumbley at elec.qmul.ac.uk http://www.elec.qmul.ac.uk/people/markp/ From ckiw at inf.ed.ac.uk Wed Apr 12 13:24:59 2006 From: ckiw at inf.ed.ac.uk (Chris Williams) Date: Wed, 12 Apr 2006 18:24:59 +0100 (BST) Subject: Connectionists: WORKSHOP: Mathematical Models of Development and Learning in the Nervous System Message-ID: Workshop on Mathematical Models of Development and Learning in the Nervous System University of Edinburgh, UK 21-22 July 2006 Call for Participation The aim of this workshop is to bring together mathematical modellers and key experimenters in the field of neural development and learning with the objective of: * Exposing new experimental areas that would benefit from mathematical methods; * Identifying innovative applications of mathematics to modelling problems; and * Mapping new frontiers of research. The workshop will consist of around twelve invited talks and two discussion sessions. Expected lecturers include Gordon Arbuthnott (University of Otago, New Zealand) Peter Dayan (Gatsby Computational Neuroscience Unit, UCL) Stephen Eglen (University of Cambridge) Marcus Frean (Victoria University of Wellington, New Zealand) Andrew Gillies (University of Edinburgh) Geoff Goodhill (University of Queensland, Australia) Bruce Graham (University of Stirling) Martin Simmen (University of Edinburgh) Arjen van Ooyen (Free University of Amsterdam, Netherlands) Christoph von der Malsburg (Bochum University, Germany) David Willshaw (University of Edinburgh) The meeting is limited to around 50 attendees in order to maintain its workshop character. Applications are invited now from people wishing to participate in the workshop. Some financial support is available for applicants from the UK. The deadline for applications is 1 May 2006. See http://www.icms.org.uk/meetings/2006/nervous/index.html for further details and the online application form. The meeting is being held as part of the International Centre for Mathematical Sciences (ICMS) 2006 workshop programme and will take place directly after the Computational Neuroscience (CNS*2006) conference. The workshop is made possible by grants awarded to ICMS from EPSRC Mathematical Sciences Programme, the Scottish Higher Education Funding Council and the London Mathematical Society. The meeting is also directly supported by the Institute for Adaptive and Neural Computation and the School of Informatics of the University of Edinburgh. Organizers: Chris Williams (University of Edinburgh) Peter Dayan (Gatsby Computational Neuroscience Unit, UCL) Andrew Gillies (University of Edinburgh) David Sterratt (University of Edinburgh) From ted.carnevale at yale.edu Wed Apr 12 22:02:16 2006 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Wed, 12 Apr 2006 22:02:16 -0400 Subject: Connectionists: more talks and tutorials at the NEURON Simulator Meeting Message-ID: <443DB128.1050707@yale.edu> Register now for the NEURON Simulator Meeting, which will be held May 5-7 at UT Austin--see http://www.utexas.edu/neuroscience/NEURON2006/nsm2006.html The registration deadline is Friday, April 21. Here are two more reasons to attend: Talk: "Rule-based artificial cell (RBAC) models in NEURON" Speaker: Bill Lytton There are a variety of artificial cell models available in NEURON. These have the advantage of using forward prediction of spike times in order to avoid the overhead of integration. Additionally, they can be used in hybrid networks with compartmental models in order to run large models at vastly increased speed. We have developed new artificial neuron models that use rule sets to determine firing based on different types of inputs and several internal state variables. In addition to speed, this approach cleanly isolates the various synaptic and internal state variables so that they can be manipulated in a way that is difficult in the complex parameterizations of full multi-compartment/multi-ion-channel/ multi-synapse models. The basic rule remains the same as that of the integrate-and-fire model: fire when the state variable exceeds a fixed threshold. Additional rules were added to provide adaptation, bursting, depolarization blockade, Mg-sensitive NMDA conductance, anode-break depolarization, and others. The implementation is event driven, providing additional speed-up by avoiding numerical integration. Tutorial: "Recent advances in the CellBuilder: managing models with spatially varying parameters" Speaker: Ted Carnevale This tutorial will show how to use the CellBuilder, one of NEURON's GUI tools, to construct and manage neuron models in which one or more parameters vary with location as functions of an independent variable. This recent enhancement graphically supports the idiom forsec subset for (x, 0) { rangevar_suffix(x) = f(p(x)) } where rangevar_suffix(x) is the parameter of interest, p(x) is a domain function over the subset, and f is any expression. Built-in domain functions are arc (path) distance from the soma, radial distance from a point, and distance along an axis in the xy plane. --Ted From deneve at isc.cnrs.fr Thu Apr 13 12:37:41 2006 From: deneve at isc.cnrs.fr (deneve@isc.cnrs.fr) Date: Thu, 13 Apr 2006 18:37:41 +0200 (CEST) Subject: Connectionists: Postdoctoral Position in the Group for Neural Theory, Paris Message-ID: <45425.193.52.23.5.1144946261.squirrel@webmail.isc.cnrs.fr> A postdoctoral research position is available in the Group for Neural Theory in Ecole Normale Sup?rieure Paris, for a project funded by a Marie Curie Team of Excellence grant. The overall theme of the project is "Bayesian inference and neural dynamics", and the research will involve building and analyzing probabilistic treatments of representation, inference and learning in biophysical models of cortical neuron and circuits. To do so we will integrate complementary computational neuroscience approaches. The first studies neurons and neural networks as biophysical entities. The second reinterpret cognitive and neural processes as bayesian computations. The faculty of this group includes Misha Tsodyks, Boris Gutkin, Sophie Deneve and Rava Da Silvera. It is part of the Department of Cognitive Science in Ecole Normale Sup?rieure, regrouping major scientists in computational Neuroscience, Brain imaging, Psychology, Philosophy, and Mathematics. We are situated in central Paris, at a walking distance to top scientific research and educational institutions. The positions are for two years duration, with attractive salaries, including mobility allowance if applicable. Generous travel support will be provided. Candidates should have 1- A strong mathematical/biophysical background previously applied to neuroscience, 2- Demonstrable interest in experimental collaborations. 3- Good communication skills. Candidates should send a CV, a 1 page research project and the address of two referees, to Sophie Deneve (Sophie.Deneve at ens.fr) and Boris Gutkin (Boris.Gutkin at ens.fr). For further information please contact Sophie Deneve or Boris Gutkin. From deneve at isc.cnrs.fr Thu Apr 13 13:06:11 2006 From: deneve at isc.cnrs.fr (deneve@isc.cnrs.fr) Date: Thu, 13 Apr 2006 19:06:11 +0200 (CEST) Subject: Connectionists: PhD Student Position-Group for Neural Theory in Paris Message-ID: <46093.193.52.23.5.1144947971.squirrel@webmail.isc.cnrs.fr> A PhD student position is available in the Group for Neural Theory in Ecole Normale Sup?rieure Paris, for a project funded by a Marie Curie Team of Excellence grant. The overall theme of the project is "Bayesian inference and neural dynamics", and the research will involve building and analyzing probabilistic treatments of representation, inference and learning in biophysical models of cortical neuron and circuits. The faculty of this group includes Misha Tsodyks, Boris Gutkin, Sophie Deneve and Rava Da Silvera. It is part of the Department of Cognitive Science in Ecole Normale Sup?rieure, a unique teaching and research institution regrouping major scientists in computational Neuroscience, Brain imaging, Psychology, Philosophy, and Mathematics. We are situated in central Paris, at a walking distance to top scientific research and educational institutions. There will be ample opportunities to follow graduate classes in the field of Theoretical Neuroscience. The position is for three years duration, starting in September 2006. It has an attractive salary, including mobility allowance if applicable. Generous travel support will be provided. Candidates should have 1- A strong background in mathematics or physics and strong interest for Neuroscience. Or 2- A strong neuroscience background and good basis in math and/or biophysics. 3- Demonstrable interest in experimental collaborations. 4- Good communication skills. Candidates should send a CV, a 1 page research project and the address of two referees to Sophie Deneve (Sophie.Deneve at ens.fr) and Boris Gutkin (Boris.Gutkin at ens.fr). From mpolycar at ucy.ac.cy Thu Apr 13 16:55:46 2006 From: mpolycar at ucy.ac.cy (Marios M. Polycarpou) Date: Thu, 13 Apr 2006 23:55:46 +0300 Subject: Connectionists: IEEE Transactions on Neural Networks, vol. 16, No. 2, March 2006 Message-ID: <039701c65f3c$a38385e0$04172ac2@IBM36165813261> Dear Colleagues, The following articles appear in the latest issue of IEEE Transactions on Neural Networks vol.17, no.2, March 2006. The articles can be retrieved on IEEE Xplore: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=72 Marios M. Polycarpou IEEE-TNN Editor-in-Chief email: ieeetnn at ucy.ac.cy ++++++++++++++++++++++++++++++++++++++ A node pruning algorithm based on a Fourier amplitude sensitivity test method Lauret, P.; Fock, E.; Mara, T.A. Pages: 273- 293 Generalizing self-organizing map for categorical data Chung-Chian Hsu Pages: 294- 304 The parameterless self-organizing map algorithm Berglund, E.; Sitte, J. Pages: 305- 316 Implementing online natural gradient learning: problems and solutions Weishui Wan Pages: 317- 329 The linear separability problem: some testing methods Elizondo, D. Pages: 330- 344 Modulated Hebb-Oja learning Rule-a method for principal subspace analysis Jankovic, M.V.; Ogawa, H. Pages: 345- 356 Toward the training of feed-forward neural networks with the D-optimum input sequence Witczak, M. Pages: 357- 373 Orthogonal search-based rule extraction (OSRE) for trained neural networks: a practical and efficient approach Etchells, T.A.; Lisboa, P.J.G. Pages: 374- 384 A bidirectional heteroassociative memory for binary and grey-level patterns Chartier, S.; Boukadoum, M. Pages: 385- 396 Basins of attraction in fully asynchronous discrete-time discrete-state dynamic networks Bahi, J.M.; Contassot-Vivier, S. Pages: 397- 408 Dynamics analysis and analog associative memory of networks with LT neurons Huajin Tang; Tan, K.C.; Teoh, E.J. Pages: 409- 418 Blind estimation of channel parameters and source components for EEG signals: a sparse factorization approach Yuanqing Li; Cichocki, A.; Amari, S.-I. Pages: 419- 431 Adaptive wavelet neural network control with hysteresis estimation for piezo-positioning mechanism Faa-Jeng Lin; Shieh, H.-J.; Po-Kai Huang Pages: 432- 444 Modeling and inverse controller design for an unmanned aerial vehicle based on the self-organizing map Jeongho Cho; Principe, J.C.; Erdogmus, D.; Motter, M.A. Pages: 445- 460 Neural-network-based adaptive UPFC for improving transient stability performance of power system Mishra, S. Pages: 461- 470 Sparse bayesian kernel survival analysis for modeling the growth domain of microbial pathogens Cawley, G.C.; Talbot, N.L.C.; Janacek, G.J.; Peck, M.W. Pages: 471- 481 A neuromorphic depth-from-motion vision model with STDP adaptation Zhijun Yang; Murray, A.; Worgotter, F.; Cameron, K.; Boonsobhak, V. Pages: 482- 495 Neuromorphic walking gait control Still, S.; Hepp, K.; Douglas, R.J. Pages: 496- 508 Adaptive neural network control for a class of low-triangular-structured nonlinear systems Hongbin Du; Huihe Shao; Pingjing Yao Pages: 509- 514 Computation of Adalines' sensitivity to weight perturbation Xiaoqin Zeng; Yingfeng Wang; Kang Zhang Pages: 515- 519 Associative memory design for 256 gray-level images using a multilayer neural network Costantini, G.; Casali, D.; Perfetti, R. Pages: 519- 522 Convergence of gradient method with momentum for two-Layer feedforward neural networks Naimin Zhang; Wei Wu; Gaofeng Zheng Pages: 522- 525 On the new method for the control of discrete nonlinear dynamic systems using neural networks Hua Deng; Han-Xiong Li Pages: 526- 529 Batch map extensions of the kernel-based maximum entropy learning rule Gautama, T.; Van Hulle, M.M. Pages: 529- 532 Comments on "The 1993 DIMACS graph coloring Challenge" and "Energy function-based approaches to graph Coloring" Jing Liu; Weicai Zhong; Licheng Jiao Pages: 533 From Randy.OReilly at colorado.edu Sat Apr 15 01:47:38 2006 From: Randy.OReilly at colorado.edu (Randall C. O'Reilly) Date: Fri, 14 Apr 2006 23:47:38 -0600 Subject: Connectionists: Fwd: Computational Cognitive Neuroscience: Call for Abstracts Message-ID: <200604142347.38871.Randy.OReilly@colorado.edu> ~ Call for Abstracts ~ 2ND ANNUAL CONFERENCE ON COMPUTATIONAL COGNITIVE NEUROSCIENCE www.ccnconference.org To be held in conjunction with the 2006 PSYCHONOMIC SOCIETY CONFERENCE, November 16-19, 2006 at the Hilton Americas hotel in Houston, TX. * CONFERENCE DATES: Wed-Thu November 15 & 16, 2006 The inaugural CCNC 2005 meeting held prior to Society for Neuroscience (SfN) in Washington, DC was a great success, with approximately 250 attendees, 60 presented posters, and strongly positive reviews. In future years, it will continue to be held on a rotating basis with other meetings such as (tentative list): Cognitive Neuroscience Society (CNS), Organization for Human Brain Mapping (OHBM), Cognitive Science Society (CogSci), Neural Information Processing Systems (NIPS), and Computational and Systems Neuroscience (COSYNE). ____________________________________________________________________________ * DEADLINE FOR SUBMISSION OF ABSTRACTS: June 3, 2006 Abstracts to be submitted online via the website: www.ccnconference.org. Notice will be given by early May when the online submission form becomes operational. Like last year, there will be two categories of submissions: -Poster only -Poster, plus short talk (15 min) to highlight the poster Abstracts should be limited to 250 words. Women and underrepresented minorities are especially encouraged to apply. Reviewing for posters will be inclusive and only to ensure appropriateness to the meeting. Short talks will be selected on the basis of research quality, relevance to conference theme, and expected accessibility in a talk format. Abstracts not selected for short talks will still be accepted as posters as long as they meet appropriateness criteria. * NOTIFICATION OF ACCEPTANCE: July 1, 2005. __________________________________________________________________________ Preliminary Program: * 2006 Keynote Speakers (confirmed): Mike Kahana, University of Pennsylvania Mark Seidenberg, University of Wisconsin Madison * 3-4 Symposia, selected from submitted proposals, that will be discussion oriented and include a mixture of modelers and non-modelers, all focused on a common theme or issue. * 12 short talks featuring selected posters * Poster sessions ____________________________________________________________________________ 2006 Planning Committee: Suzanna Becker, McMaster University Jonathan Cohen, Princeton University Yuko Munakata, University of Colorado, Boulder David Noelle, Vanderbilt University Randall O'Reilly, University of Colorado, Boulder Maximilian Riesenhuber, Georgetown University Medical Center Executive Organizer: Thomas Hazy, University of Colorado, Boulder For more information and to sign up for the mailing list visit: www.ccnconference.org From otterlo at cs.utwente.nl Thu Apr 13 10:09:23 2006 From: otterlo at cs.utwente.nl (Martijn van Otterlo) Date: Thu, 13 Apr 2006 16:09:23 +0200 Subject: Connectionists: Relational RL Survey Message-ID: <443E5B93.8070209@cs.utwente.nl> Dear reader, A comprehensive survey of relational reinforcement learning is available from my webpage: "A Survey of Reinforcement Learning in Relational Domains". M. van Otterlo -- TR-CTIT-05-31 - (70pp) CTIT Technical Report Series ISSN 1381-3625 Abstract. Reinforcement learning has developed into a primary approach for learning control strategies for autonomous agents. However, most of the work has focused on the algorithmic aspect, i.e. various ways of computing value functions and policies. Usually the representational aspects were limited to the use of attribute-value or propositional languages to describe states, actions etc. A recent direction -- under the general name of relational reinforcement learning -- is concerned with upgrading the representation of reinforcement learning methods to the first-order case, being able to speak, reason and learn about objects and relations between objects. This survey aims at presenting an introduction to this new field, starting from the classical reinforcement learning framework. We will describe the main motivations and challenges, and give a comprehensive survey of methods that have been proposed in the literature. The aim is to give a complete survey of the available literature, of the underlying motivations and of the implications of the new methods for learning in large, relational and probabilistic environments. Work is underway to provide an updated version soon. Any comments, suggestions, and pointers to (new) work that does not yet appear in this survey will be greatly appreciated. Regards, Martijn van Otterlo. http://www.cs.utwente.nl/~otterlo/ From BGabrys at bournemouth.ac.uk Wed Apr 12 11:48:46 2006 From: BGabrys at bournemouth.ac.uk (Bogdan Gabrys) Date: Wed, 12 Apr 2006 16:48:46 +0100 Subject: Connectionists: 4 PhD Studentships in the area of Computational Intelligence Message-ID: <5DA146E1E559B341A0C85AB49E01F22213B5F1F4@tamar.bournemouth.ac.uk> PhD Studentships Computational Intelligence Research Group (CIRG) School of Design, Engineering and Computing Bournemouth University, United Kingdom Four 3 year, fully funded PhD studentships are available on a range of exciting research projects at the Computational Intelligence Research Group (CIRG) at Bournemouth University, United Kingdom. The students will be joining a Computational Intelligence Research Group (CIRG) and will be primarily based in the School of Design, Engineering & Computing in Bournemouth but in 3 of the projects will also have an opportunity to frequently visit and work in the top R&D labs of such companies as British Telecommunications Plc, Lufthansa Systems Berlin GmbH or Degussa AG. The studentships carry a basic remuneration of ?12500 pa tax-free (with some possible higher bursaries on specific industry co-funded projects) and payment of tuition fees at home/EU rate. The successful applicants will normally need to be EU citizens though a limited number of studentships is available for outstanding non-EU candidates. For all projects applicants should have a strong mathematical background and hold a first or upper second class honours degree or equivalent in computer science, mathematics, physics, engineering, statistics or a similar discipline. Additionally the candidates should have strong programming experience using any or combination of C++, Matlab or Java. For further details please contact Prof Bogdan Gabrys, bgabrys at bournemouth.ac.uk or visit the following www pages: http://dec.bournemouth.ac.uk/staff/bgabrys/PhD_Studentships_2006.html Interested candidates should follow the application procedure listed on the University of Bournemouth web pages: http://www.bournemouth.ac.uk/thegraduateschool/phd_studentships/how_to_apply.html Further details concerning the studentships and application procedure can be also obtained from the School of DEC Research Administrator - Ms Jo Sawyer, Email: jsawyer at bournemouth.ac.uk. Tel: +44 (0)1202 965985 All the following projects are expected to start by September 2006 at the latest but all interested candidates are encouraged to apply as soon as possible. Project 1: Data Mining and Multi Level Combination for Cancellation Forecasting Prof Bogdan Gabrys (CIRG), Ms Silvia Riedel (LSB), Prof John Fletcher (BU SM School) Accurate forecasting of the demand for airline tickets is critical within revenue management applications used by large airlines like Lufthansa. In this project the information stored in the airline Passenger Name Records (PNRs) will be exploited through the use of data mining techniques and used within novel adaptable (multilevel) classifier and forecast combination framework for improvement of the cancellation forecasts and overall demand prediction quality. This is a collaborative research project between Computational Intelligence Research Group (CIRG) and Lufthansa Systems Berlin (LSB), the world leading IT service provider for the airline and aviation industry. The PhD student will have an opportunity to frequently visit and work in LSB offices in Berlin. Project 2: Self-adapting and Monitoring Soft Sensors for Process Industry Prof Bogdan Gabrys (CIRG), Dr Paul Rogers (CIRG), Dr Uwe Tanger (Degussa AG) This project will be an application driven investigation of the possible exploitation of various computational intelligence and nature-inspired techniques for development of self-aware, -monitoring, -validating and -adapting soft sensors for process industry based on a more general class of locally adaptable and highly flexible predictive models required in industrial environments. This is a collaborative research project between Computational Intelligence Research Group (CIRG) and Degussa AG, a multinational specialty chemistry company with EUR11.2 billion turn-over in 2004. As part of the project, the PhD student will have an opportunity to frequently visit and work in Degussa Labs in Germany. Project 3: Physically Inspired Artificial Learning Models Dr Dymitr Ruta (BT Intelligent Systems Labs), Prof Bogdan Gabrys (CIRG) The main aim of this research project is to explore and investigate the tremendous similarities between physical world and artificial intelligence in the context of machine learning in order to find inspirations and design the new breed of nature-inspired classification, clustering and regression techniques that would be capable of learning more efficiently from large sources of uncertain multi-type data and information. The work will include theoretical and explorative modelling in Matlab and Java addressing variety of problems in quantum computing, thermodynamics of information, Kolmogorov complexity, information uncertainty, kernel methods and many more. This is a collaborative research project between Computational Intelligence Research Group (CIRG) and British Telecommunications (BT) Intelligent Systems Labs, one the largest industrial R&D labs of this type in UK. Project 4: Using Computation Intelligence Techniques to Support Incidental Learning Michael Jones (CIRG), Prof. Bogdan Gabrys (CIRG) and Dr Paul Rogers (CIRG) Incidental Learning is a term, originating in the Computational Intelligence Research Group at Bournemouth University, which describes a novel approach to providing online learners with a more active role in the learning process. Incidental Learning involves the development of a 'cognitive assistant', which continuously filters a wide range of additional support materials (gathered from a variety of external sources) in a manner which is appropriate to the learner's current cognitive load. The focus for the proposed research is the design of the filtering process, which will use computational intelligence techniques to create a system which will classify the potential usefulness of the additional support materials, most of which will be unstructured. Statistical, machine learning, and hybrid intelligent techniques will be used in the design of the filtering system. The continuous nature of the filtering process imposes performance constraints, which will also form part of the research. Best regards, Bogdan Gabrys ---------------------------------------------------------------------------- Prof Bogdan Gabrys Computational Intelligence Research Group School of Design, Engineering & Computing Bournemouth University, Poole House Talbot Campus, Fern Barrow Poole, BH12 5BB United Kingdom Tel: +44 (0)1202 965298 Fax: +44 (0) 1202 965314 E-mail: bgabrys at bournemouth.ac.uk WWW: http://dec.bournemouth.ac.uk/staff/bgabrys/ --------------------------------------------------------------------------- From aenadekamps at xs4all.nl Fri Apr 14 04:04:11 2006 From: aenadekamps at xs4all.nl (A en A de Kamps) Date: Fri, 14 Apr 2006 10:04:11 +0200 Subject: Connectionists: Reminder: 'First Workshop on Topics of the nEUro-IT.net Roadmap' Message-ID: <000001c65f9a$079d7600$9600000a@lan> There are still some spots available at the 'First Workshop on Topics of the nEUro-IT.net Roadmap'. The topics are: Bio-inspired and evolvable hardware, Brain-Machine Interfacing, Peripheral Processing The full programme can be found below. Information page: http://www.neuro-it.net/NeuroIT/Activities/Roadmapworkshop Attending the workshop is free, but a registration is required. Please send mail to: kamps at in.tum.de Please indicate which workshop(s) you would like to attend on Friday. ---------------------Programme--------------------- First Workshop on Topics of the nEUro-IT.net Roadmap Antwerp, 21/22 April 2006 Programme Friday April 21 --Parallel Session 1: Bio-inspired and evolvable hardware-- Location: Campus Universiteit Antwerpen, Room K101, Kleine Kauwenberg, Antwerpen Presentations: 9.30 -10.00 Welcome and registration 10.00 - 10.45 Tetsuya Higuchi (AIST, Japan) The potential of evolvable hardware for semiconductor engineering 10.45 - 11.15 Break 11.15 - 12.00 Pauline Haddow (NTNU, Norway) Development and hardware design 12.00 - 12.30 Andy Tyrrell (University of York, UK) Fault-tolerance and Evolvable Hardware 12.30 - 1.30 Lunch 1.30 - 2.15 Gianluca Tempesti (EPFL Switzerland) Bio-inspired processing in molecular-scale devices 2.15 - 3.00 Jim Torresen (University of Oslo, Norway) Evolvable Hardware Supplementing the Hardware Designer 3.00 - 3.30 Break 3.30 - 4.15 Adrian Stoica, D. Keymeulen, R. Zebulum, R. Rajeshani, V. Lacayo, J. Neff, B. Meadows and S. Graves (NASA JPL, USA) Evolvable Hardware for extreme temperature and radiation environments 4.15 - 5.15 Wrap-up session 5.15 Finish '--Parallel Session 2: Brain-Machine interfacing-- Location: Campus Universiteit Antwerpen, Room K102, Kleine Kauwenberg, Antwerpen Presentations: Erik De Schutter (University of Antwerp, Belgium): Introduction and some reflections on BMI as an experimental paradigm Ad Aertsen (Bernstein Center, University of Freiburg, Germany): Inference of hand movements from population activity in monkey and human sensorimotor cortex Silvestro Micera and Paolo Dario (ARTS and CRIM Labs, Scuola Superiore Sant'Anna): Peripheral neural interfaces for the control of cybernetic hands: current activities and future perspectives Miguel Nicolelis (Duke University, USA and Brain Mind Institute, Lausanne, Switzerland): Exploring the future of neuroprosthetic research Eilon Vaadia (Hebrew University, Jerusalem, Israel): On the yellow brick road towards neural prosthesis: New neuronal representations in motor cortical fields evolve during learning --Parallel Session 3: Peripheral Processing-- Location: Campus Universiteit Antwerpen, Room K103, Kleine Kauwenberg, Antwerpen Presentations: Morning: (10.00-10.30) George Jeronimidis (Reading University) and Herbert Peremans (Universiteit Antwerpen): CICADA + CIRCE = CILIA (10.30-11.30) Stefaan Peeters and Filiep Vanpoucke (Universiteit Antwerpen): Cochlear electrode stimulating neurons (11.30-12.30) Gijs Krijnen (Universiteit Twente): MEMS arrays of hairs Afternoon: (13.30-14.30) Joachim Mogdans (Universit?t Bonn): Neural representation of hydrodynamic stimuli by the fish lateral line (14.30-15.30) Leo van Hemmen (Technische Universit?t M?nchen): Estimating position and velocity of a submerged moving object by the clawed frog Xenopus and by fish Coffe Break (16.00-17.00) Annemie Van Der Linden (Universiteit Antwerpen): In vivo high resolution MRI: an excellent tool for neurological research in small animals (17.00-18.00) Heike Scheuerpflug (European Research and Project Office): Intellectual Property Rights and EU projects -----Saturday April 22------- Location Campus Universiteit Antwerpen, Room R007, Rodestraat, 14, Antwerpen, Belgium 9.00-9.15 FET: Comments on FP7 9.15-9.30 nEUro-IT.net: Roadmap 9.30 - 10.15 Tetsuya Higuchi: Evolvable Hardware and its industrial applications 10.15 - 11.00 Adrian Stoica: Evolvable Hardware: lessons learned, challenges ahead 11.00 - 11.30 Coffee 11.30 - 12.15 Leo van Hemmen: Mechanosensory Localization: What Owls, Frogs, and Scorpions Have in Common 12.15 - 13.00 Giacomo Indiveri: Neuromorphic Address-Event Systems: Computing with spikes, in Silicon 13.00 - 13.30 Lunch 13.30 - 14.15 Miguel Nicolelis: Computing with Neural Ensembles 14.15 - 14.16 Closure From hitzler at aifb.uni-karlsruhe.de Sat Apr 15 16:14:22 2006 From: hitzler at aifb.uni-karlsruhe.de (Pascal Hitzler) Date: Sat, 15 Apr 2006 22:14:22 +0200 Subject: Connectionists: CfP: ECAI06 Workshop on Neural-Symbolic Learning and Reasoning, NeSy'06 Message-ID: <4441541E.5060403@aifb.uni-karlsruhe.de> Note: Submission deadline extended to 22nd of April! Call for Papers --------------- Second International Workshop on Neural-Symbolic Learning and Reasoning ***NeSy'06*** A Workshop at ECAI2006, Riva del Garda, Italy, 1st of August 2006 Website http://www.neural-symbolic.org/NeSy06/ Deadline for submission: 22nd of April, 2006 NeSy'05 took place at IJCAI-05, Edinburgh, Scotland, August 2005. Scope ----- Artificial Intelligence researchers continue to face huge challenges in their quest to develop truly intelligent systems. The recent developments in the field of neural-symbolic integration bring an opportunity to integrate well-founded symbolic artificial intelligence with robust neural computing machinery to help tackle some of these challenges. The Workshop on Neural-Symbolic Learning and Reasoning is intended to create an atmosphere of exchange of ideas, providing a forum for the presentation and discussion of the key topics related to neural-symbolic integration. Topics of interest include: * The representation of symbolic knowledge by connectionist systems; * Learning in neural-symbolic systems; * Extraction of symbolic knowledge from trained neural networks; * Reasoning in neural-symbolic systems; * Biological inspiration for neural-symbolic integration; * Applications in robotics, semantic web, engineering, bioinformatics, etc. Submission ---------- Researchers and practitioners are invited to submit original papers that have not been submitted for review or published elsewhere. Submitted papers must be written in English and should not exceed 6 pages in the case of research and experience papers, and 2 pages in the case of position papers (including figures, bibliography and appendices) in ECAI format. All submitted papers will be judged based on their quality, relevance, originality, significance, and soundness. Papers must be submitted directly by email in PDF format to nesy at soi.city.ac.uk Presentation ------------ Selected papers will be presented during the workshop. The workshop will include extra time for audience discussion of the presentation allowing the group to have a better understanding of the issues, challenges, and ideas being presented. Publication ----------- Accepted papers will be published in official workshop proceedings, which will be distributed during the workshop. Authors of the best papers will be invited to submit a revised and extended version of their papers to the journal of logic and computation, OUP. Important Dates --------------- Deadline for submission: 22nd of April, 2006 Notification of acceptance: 10th of May, 2006 Camera-ready paper due: 17th of May, 2006 Workshop date: 29th of August ECAI 2006 main conference dates: 28th of August to 1st of September, 2006. Workshop Organisers ------------------- Artur d'Avila Garcez (City University London, UK) Pascal Hitzler (University Karlsruhe, Germany) Guglielmo Tamburrini (Universit? di Napoli, Italy) Programme Committee (preliminary) --------------------------------- Artur d'Avila Garcez (City University London, UK) Sebastian Bader (TU Dresden, Germany) Howard Blair (Syracuse University, USA) Dov Gabbay (Kings College London, UK) Marco Gori (Univeristy of Siena, Italy) Barbara Hammer (TU Clausthal, Germany) Ioannis Hatzilygeroudis (University of Patras, Greece) Pascal Hitzler (University of Karlsruhe, Germany) Luis Lamb (Federal University of Rio Grande do Sul, Brazil) John Lloyd (The Australian National University, Australia) Vasile Palade (Oxford University, UK) Antony K. Seda (University College Cork, Ireland) Ron Sun (Rensselaer Polytechnic Institute, USA) Guglielmo Tamburrini (Universit? di Napoli Feredico II, Italy) Stefan Wermter (University of Sunderland, UK) Gerson Zaverucha (Federal University of Rio de Janeiro, Brazil) Invited speakers ---------------- Marco Gori, University of Siena, Italy Heat Kernel Learning Machines for Symbolic Problems (tentative titel) Stefan Wermter, University of Sunderland, UK Hybrid Intelligent Systems and Cognitive Robotics (tentative title) Additional Information ---------------------- Up-to-date information can be obtained from http://www.neural-symbolic.org/NeSy06/ General questions concerning the workshop should be addressed to nesy at soi.city.ac.uk. You are also invited to subscribe to the neural-symbolic integration mailing list at http://www.aifb.uni-karlsruhe.de/mailman/listinfo/nesy -- Dr. habil. Pascal Hitzler Institute AIFB, University of Karlsruhe, 76128 Karlsruhe email: hitzler at aifb.uni-karlsruhe.de fax: +49 721 608 6580 web: http://www.pascal-hitzler.de phone: +49 721 608 4751 http://www.neural-symbolic.org From dekamps at t-online.de Sun Apr 16 09:15:27 2006 From: dekamps at t-online.de (Marc de Kamps) Date: Sun, 16 Apr 2006 15:15:27 +0200 Subject: Connectionists: 4th European School of Neuro-IT and Neuroengineering, , Message-ID: <4442436F.9060400@in.tum.de> 4^th European School of Neuro-IT and Neuroengineering *Dynamics, Computation and Learning in Neural Systems* * * ** June 13-17, 2006 The University of Genova (Department of Biophysical and Electronic Engineering -- DIBE , Department of Informatics, Sistems and Telematics -- DIST , and the Faculty of Engineering, curriculum on Bioengineering), Doctorate school on Information Society and Technologies, University of Genova (ITALY), PhD Program in Bioengineering, Doctorate school on Humanoid Technologies, Italian Institute of Technology (IIT), and University of Genova (ITALY), PhD Program in Humanoid Technologies nEUro-it.net (EU network of excellence), NEUROversIT (EU Marie Curie program) *are organizing the fourth edition * *of the European Summer School of Neuro-IT and Neuroengineering. * The school, named after Massimo Grattarola who initiated the series in 2000, will take place from June 13 to June 17, 2006 at the Faculty of Engineering, University of Genoa in a beautiful historical building: Villa Giustiniani-Cambiaso The school is intended for junior and senior researchers and other professionals (doctors, engineers, biologists and psychologists etc.) working in these areas as well as for students attending faculties of engineering, medicine, biology or psychology. A total of 50 PhD students or postdocs will be admitted. Admissions will be on first-come first-serve basis. Organization and sponsorship Neuro-IT (EU network of excellence) NEUROversIT (EU Marie Curie program) University of Genova Scientific organizers: Alois Knoll (M?nchen, Germany) Marc de Kamps (M?nchen, Germany) Andreas Engel (Hamburg, Germany) Sergio Martinoia (Genova, Italy) Giulio Sandini (Genova, Italy) Vittorio Sanguineti (Genova, Italy) Goals The school will focus on a new and rapidly growing field -- the areas of neuro-information technologies (Neuro-IT) and neuroengineering where neuroscience, information technologies and robotics merge. The school will be organized and partly funded by Neuro-IT.net, and NEUROversIT, an EU-funded Marie Curie program. The 2006 edition of the school will specifically focuses on the */_dynamical, adaptive and computational properties of neural systems_/*, seen as 'devices' that process information and can control external devices. This includes neural prostheses, brain-machine interfaces and neurally controlled robots. The objective is to move beyond the well established neuroinformatics or AI (Artificial Intelligence) domains by fostering research that would benefit both the neuroscience (NS) and Information Technology (IT) communities by helping solve the fundamental problems linked to the emergence and the modelling of computational properties, learning and cognitive processes in natural systems. The goal is for IT to profit from NS results to improve IT artifacts and for NS to validate models or hypotheses with a better use of IT. Neuro-IT.net and the NEUROversIT consortium is therefore committed to spearheading the emergence of visionary long term research objectives that could fully exploit the potential of collaboration between neurosciences and information technology. *Overall organisation* The school will have a duration of 5 days in total (Tuesday to Saturday morning). The first day will feature /advanced tutorials/ with the goal of equalizing the backgrounds of students from different disciplines. These tutorials will focus on background materials directly relevant to the topic of the summer school, that will improve understanding of the expert presentations that will follow in day 2-4 of the school. Friday afternoon and Saturday morning will be devoted to practical lecturers and Lab activities. The first day will be devoted to presenting important concepts and data from neuroscience for students from technical disciplines, and for presenting topics in neuro-IT and neuroengineering for student from life science. The other three days of the school feature expert lectures on selected topics under the theme "Dynamics, Computation and Learning in Neural Systems". These lectures will cover state-of-the-art research related to one or multiple of the topics mentioned below. Students participating to the school are invited to present their own activity in specific dedicated sessions. Lab sessions will be organized on Friday 16^th (afternoon) and Saturday 17^th (morning) and they will be devoted to practical presentations and activities on: - NEURON simulator - Data analysis for multisite recorded neuronal signals (sponsored by eTT, http://www.ettsolutions.com ) Students interested in such activities are requested to specifically enroll to one or both Lab. The Lab activity are included in the registration fees. * Topics * * Speakers * * Program * * Information * * Fees * * Accomodations * * * * * *Topics* The school will address key topics in the Neuroengineering field, with a focus on "Dynamics, Computation and Learning in Neural Systems" and their technical realization in artificial systems. All issues should be dealt with, in an interdisciplinary way, both from the biological and the IT/engineering perspective. Key topics will include: . Neural-network dynamics - Neurobiology of in-vivo and in-vitro neuronal systems - non linear dynamics and neuronal signal analysis - theoretical and experimental models . Coding and decoding neuronal signals - rate/time coding - ...... . Neural plasticity - learning -- development - neurobiology of learning and memory - closed-loop system and learning - learning and plasticity in in-vitro neuronal system . Advanced neuro-prosthetics - brain-machine interfaces - technological advances in BMI - decodying of neuronal signals . Neuro-robotics - biologically inspired robots - bi-directional neuro-robotic interfaces - cognitive ... *Faculty members* /(to be filled)/ *REGISTRATION FEES* (*) *CATEGORIES* *BEFORE MAY 15* *AFTER MAY 15* PhD students 200 ? 250 ? Postdocs 250 ? 300 ? Business and medical professionals 350 ? 400 ? (*) includes program, reception, two coffee breaks and lunch each day lab activities and lecture notes * * *LOCAL ORGANIZATION:* Prof. Sergio Martinoia University of Genova e -mail: martinoia at dibe.unieg.it Phone: +39-010-3532251 Fax: +39-010-3532133 Prof. Vittorio Sanguineti University of Genova e -mail: _vittorio.sanguineti at unige.it _ Phone: +39-010-3536487 Fax: +39-010-3532154 *ADMINISTRATIVE INFORMATION:* Ms. Jessica Gaggero University of Genova e -mail: jessica at dibe.unige.it Phone: +39-010-3532787 Fax: +39-010-3532133 From F.AlmeidaCosta at sussex.ac.uk Tue Apr 18 09:41:07 2006 From: F.AlmeidaCosta at sussex.ac.uk (Fernando Almeida e Costa) Date: Tue, 18 Apr 2006 14:41:07 +0100 Subject: Connectionists: Last CFP with important update - Workshop on Morphologies Motion and Cognition Message-ID: <000001c662ed$c78bffd0$efea1e52@salome> ********************************************************************* Morphologies, Motion and Cognition Workshop @ Alife X Last call for papers and demos (Check below for an important update regarding deadlines) Organized by the Morphodynamics and Cognition Group University of Sussex www.informatics.sussex.ac.uk/morphodynamicsgroup/alifexwk ********************************************************************* AlifeX, in June, taking place at Indiana University, USA, is to host a workshop on "Morphologies, Motion and Cognition" organised by the Morphodynamics and Cognition Group from the University of Sussex. This workshop will take place on the 3rd of June (all-day session), and on the evening of the 4th. Venue: Indiana Memorial Union, in the same area as the main conference presentations. We are accepting submissions of papers and/or proposals of demos. *********************** Aim of the workshop *********************** Our intention is to bring together researchers from robotics, psychology, and ethology to examine and discuss how morphology and motion shapes the perceptual worlds and cognitive behaviours of robots and natural organisms. Although we welcome simulations, we want to encourage work on "physical" robots, or simulated robots that have interesting morphologies. In the approach to cognition that we will be discussing, cognitive activity is regarded as crucially dependent upon, and emerging from, the exploitation of all the physical properties available to the agent, namely its morphology and motion. The key principle of this approach is to minimise the amount of control at the algorithmic level by exploiting the dynamics of the agent, produced by its interaction with the environment. This approach views organisms and robots as dynamic systems, whose parts are continually perturbed by cues from their environments that act to modulate their behaviours. **************** Keynote Speakers **************** Inman Harvey, University of Sussex Rolf Pfeifer, University of Zurich ********* Topics ********* The work to be submitted may include (but is not limited to) the following topics: - the exploitation by an agent of its morphodynamics (morphologies and motion) for cognitive purposes, at any level of "cognition" in both humans and robots. - passive dynamic walkers - relation with the environment through active perception - evolution of morphologies, morphogenesis - developmental issues in both humans/animals and robots - dynamical theories of cognition - embodied and situated robotics - constructed worlds of robots - articulated motion in robots and animals - sensorimotor and movement coordination - evolvable hardware - design principles for fully embodied and situated robots - automatic robot manufacture - 3D rapid prototyping printers - non-holonomic robot control - control for underactuated or compliant structures - methods for the analysis of the interaction of morphology, motion, and control ************ Papers ************ Papers can either be technical or conceptual, in the area covered by the workshop. Length should not exceed 10 pages, double spaced, and must be emailed in pdf format to one of the organisers (see addresses below in "organising committee") ************ Demos ************ Demos can be presented as physical robots, computer simulations or videos of physical robots. If you are interested in presenting a demo please contact one of the members of the organising committee as soon as possible. ****************** Important dates ****************** UPDATE: Abstracts of the papers must be submitted by April 27 Papers deadline submission: May 1 Notification of acceptance: May 5 Abstracts and papers must be sent to the organising committee (email addresses below) ************ Publication ************ If the submitted contributions are of sufficient quality, papers emerging from the workshop will be forwarded to undergo the review process of a scientific journal, for a special issue. ************ Details ************ You may find detailed information about the workshop in our webpage at www.informatics.sussex.ac.uk/morphodynamicsgroup/alifexwk or through the conference webpage at www.alifex.org ******************** PROGRAMME COMMITTEE ******************** Bill Bigge, University of Sussex Josh Bongard, Cornell University Inman Harvey, University of Sussex Phil Husbands, University of Sussex Fumiya Iida, University of Zurich Eduardo Izquierdo-Torres, University of Sussex Akio Ishiguro, University of Nagoya Hod Lipson, Cornell University Max Lungarella, University of Tokyo Romi Nijhawan, University of Sussex Chandana Paul, Cornell University Rolf Pfeifer, University of Zurich Linda Smith, Indiana University Olaf Sporns, Indiana University Kasper St?y, University of Southern Denmark Tim Taylor, Timberpost, Ltd. Eric Vaughan, University of Sussex Rachel Wood, University of Sussex Tom Ziemke, University of Sk?vde ************************** Organising Committee ************************** Fernando Almeida e Costa F.AlmeidaCosta at sussex.ac.uk Ian Macinnes ian at british-cybernetics.co.uk ************************************************* www.informatics.sussex.ac.uk/morphodynamicsgroup From jbednar at inf.ed.ac.uk Tue Apr 18 16:44:49 2006 From: jbednar at inf.ed.ac.uk (James A. Bednar) Date: Tue, 18 Apr 2006 21:44:49 +0100 Subject: Connectionists: Computational maps book and software Message-ID: <17477.20417.345695.66710@lodestar.inf.ed.ac.uk> We are pleased to announce the publication of the book "Computational Maps in the Visual Cortex" by Miikkulainen, Bednar, Choe, and Sirosh (New York: Springer). This book presents a computational approach to understanding how the map-like structures in the visual cortex develop and adapt to support visual function. It reviews current theories and biological data, and presents a detailed analysis of the laterally connected self-organizing map model (LISSOM) and results obtained to date. The TOC and a sample chapter, electronic versions of the figures and references, animated demos, talks, and course material are available at the book website: http://computationalmaps.org The book was developed together with "Topographica", a general simulator for computational modeling of cortical maps. Topographica is intended to serve as a common software tool for the research community, and is freely available at: http://topographica.org We hope that these tools will be useful in future research on the computational mechanisms of the visual cortex! -- Risto, Jim, Yoonsuck, and Joe From g.goodhill at imb.uq.edu.au Thu Apr 20 02:43:48 2006 From: g.goodhill at imb.uq.edu.au (Geoffrey Goodhill) Date: Thu, 20 Apr 2006 16:43:48 +1000 Subject: Connectionists: Network 17.1 Table of Contents Message-ID: <44472DA4.3090509@imb.uq.edu.au> Network: Computation in Neural Systems Vol 17, Number 1 (March 2006) TABLE OF CONTENTS Editorial: Welcome to the new Network Geoffrey Goodhill pp. 1 - 2 Dynamics of neural populations: Stability and synchrony Lawrence Sirovich, Ahmet Omurtag, Kip Lubliner pp. 3 - 29 Excitability changes that complement Hebbian learning Maia K. Janowitz and Mark C. W. Van Rossum pp. 31 - 41 Decoupling functional mechanisms of adaptive encoding Nicholas A. Lesica and Garrett B. Stanley pp. 43 - 60 Dopamine, prediction error and associative learning: A model-based account Andrew Smith, Ming Li, Sue Becker, Shitij Kapur pp. 61 - 84 V1 non-linear properties emerge from local-to-global non-linear ICA Jes?s Malo and Juan Guti?rrez pp. 85 - 102 Journal homepage including links to above articles: http://www.tandf.co.uk/journals/titles/0954898X.asp Submissions: http://mc.manuscriptcentral.com/ncns Geoff Goodhill Editor-in-Chief, Network: Computation in Neural Systems ncns at uq.edu.au From pjt9 at case.edu Thu Apr 20 12:36:30 2006 From: pjt9 at case.edu (Peter Thomas) Date: Thu, 20 Apr 2006 12:36:30 -0400 Subject: Connectionists: coupled cortical maps paper Message-ID: <2D4D8146-CA5C-456E-993F-F9CEBD6B7141@case.edu> Dear Colleagues: I am pleased to draw your attention to the following article, available at http://imammb.oxfordjournals.org/cgi/rapidpdf/dql006? ijkey=TjqJPARL6JsfmFT&keytype=ref > Simultaneous constraints on pre- and post-synaptic cells couple > cortical > feature maps in a 2D geometric model of orientation preference > > Peter J. Thomas (Oberlin College & Case Western Reserve University) > Jack D. Cowan (The University of Chicago) > > The most prominent feature of mammalian striate cortex (V1) is the > spatial organization of response preferences for the position and > orientation of elementary visual stimuli. Models for the formation > of cortical maps of orientation and retinotopic position typically > rely on a combination of Hebbian or correlation-based synaptic > plasticity, and constraints on the distribution of synaptic > weights. We consider a simplified model of orientation and > retinotopic specificity based on the geometry of the feedforward > synaptic weight distribution from an unoriented layer of cells to a > first weakly oriented layer. We model the feed-forward weight > distribution as a system of planar Gaussian receptive fields each > elongated in the direction matching the preferred orientation of > the postsynaptic cell. Under the constraint of presynaptic weight > normalization (each cell in the oriented layer receives the same > net synaptic weight) and a uniform retinotopic map (displacement of > centres of mass of receptive fields in the unoriented layer is > strictly proportional to the displacement of the corresponding > cells in the oriented layer), we find that imposing a pattern of > orientation preference forces the system to violate postsynaptic > weight normalization (each cell in the unoriented layer no longer > sends forth the same net synaptic weight). We study this deviation > from uniformity of the postsynaptic weight, and find that the > deviation has a distinct form in the vicinity of the pinwheel > singularities of the orientation map. We show that uniform synaptic > coverage of the unoriented layer can be restored by introducing a > distortion in the retinotopic locations of the receptive fields. We > calculate, to first order in the relative elongation of the > receptive fields, the retinotopic distortion vector field. Both the > pattern of postsynaptic weight non-uniformity and the corrective > retinotopic distortion vector field fail to possess the reflection > symmetry commonly assumed to relate orientation singularities with > topological index +-pi. Hence, we show that right-handed and left- > handed orientation singularities are fundamentally distinct > anatomical structures when full 2D synaptic architecture is taken > into account. Finally, we predict specific patterns of retinotopic > distortion that should obtain in the vicinity of +-pi-fold > orientation singularities, if uniform pre- and post-synaptic weight > constraints are strongly enforced. > > Keywords: visual cortex; orientation; retinotopy; fan-in; fan-out; > neural network; cortical map. Best wishes, Peter J. Thomas [as of July 1, 2006:] Assistant Professor of Mathematics, Biology & Cognitive Science Case Western Reserve University Department of Mathematics Yost Hall, 10900 Euclid Ave, Cleveland, OH 44106-7058 pjt9 -- at -- case.edu // 216-368-8998 From nnrev at atr.jp Fri Apr 21 01:23:51 2006 From: nnrev at atr.jp (Neural Networks Editorial Office) Date: Fri, 21 Apr 2006 14:23:51 +0900 Subject: Connectionists: CFP: Neural Networks Special Issue on Neuroscience and Robotics Message-ID: [Apologies if you receive this announcement more than once.] ************************************************************************ CALL FOR PAPERS 2007 Special Issue of Neural Networks " Neuroscience and Robotics " ************************************************************************ Co-Editors Yoshihiko Nakamura Paolo Dario Stefan Schaal Submission Deadline for submission: November 30, 2006 Notification of acceptance: February 28, 2007 Deadline for submission of revised papers: April 10, 2007 Notification of final acceptance: May 31, 2007 Deadline for submission of final papers: June 30, 2007 Format: as for normal papers in the journal Address for Papers Dr. Mitsuo Kawato ATR Computational Neuroscience Laboratories 2-2-2 Hikaridai, Seika-cho Soraku-gun, Kyoto 619-0288, Japan. Neuroscience and computational neuroscience has recently made major advances in systems level, more specifically in understanding the neural control of behaviors. In a parallel perspective, robotics research has reached out its scope toward increasingly more complex systems. Full-scale humanoid robots and animal-like robots for human interaction set robotics research to face high-dimensional problems of motor control, perception, and decision-making, which necessitate exploring biological paradigms. Such advances of robotics technology have also opened a door for computational research on biological motor control to experimental study of its theories and algorithms. Moreover, brain-robot interfaces have been demonstrated in recent pioneering projects. Since the domain of many research problems is shared between brain science and robotics, a natural exchange of inspirations, theories, and algorithms is more demanded and encouraged than ever. The goal of this special issue is to provide an overview of state-of-the-art of research on projects where robotics has had a major impact on neuroscience, and where neuroscientific ideas have found successful application in the behavioral control of complex robots. Examples of research projects of interest include, but are not restricted to, - humanoid robotics and principles of neuroscience, - human behavioral research with innovative robotic technology, - robotic intelligence/behavior research based on neuroscientific paradigms - innovative robotic tools (hardware/software) for neuroscience - technologies interfacing biological neural systems and machines Neural Networks Official home page: http://www.elsevier.com/wps/find/journaldescription.cws_home/841/description Instructions to Authors: See Guide For Authors in the above web page -- """""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" NEURAL NETWORKS Editorial Office ATR Computational Neuroscience Laboratories 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan TEL +81-774-95-1204 FAX +81-774-95-1236 E-MAIL nnrev at atr.jp """""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" From nips06pub at hotmail.com Wed Apr 19 11:26:31 2006 From: nips06pub at hotmail.com (M.O. Franz) Date: Wed, 19 Apr 2006 17:26:31 +0200 Subject: Connectionists: CALL FOR PAPERS NIPS*2006 Message-ID: CALL FOR PAPERS – NIPS*2006 Deadline for Paper Submissions: June 9, 2006 Submissions are solicited for the twentieth annual meeting of an interdisciplinary conference (December 5-7) which brings together researchers interested in all aspects of neural and statistical processing and 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 4), and following it will be two days of workshops at Whistler/Blackcomb ski resort (December 8-9). Invited Speakers: To be announced. Tutorial Speakers: To be announced. Submissions: Papers are solicited in all areas of neural information processing, including (but not limited to) the following: * Algorithms and Architectures: statistical learning algorithms, neural networks, kernel methods, graphical models, Gaussian processes, dimensionality reduction and manifold learning, model selection, combinatorial optimization. * Applications: innovative applications or fielded systems that use machine learning, including systems for time series prediction, bioinformatics, text/web analysis, multimedia processing, and robotics. * Brain Imaging: neuroimaging, cognitive neuroscience, EEG (electroencephalogram), ERP (event related potentials), MEG (magnetoencephalogram), fMRI (functional magnetic resonance imaging), brain mapping, brain segmentation, brain computer interfaces. * Cognitive Science and Artificial Intelligence: theoretical, computational, or experimental studies of perception, psychophysics, human or animal learning, memory, reasoning, problem solving, natural language processing, and neuropsychology. * 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. * Hardware Technologies: analog and digital VLSI, neuromorphic engineering, computational sensors and actuators, microrobotics, bioMEMS, neural prostheses, photonics, molecular and quantum computing. * Learning Theory: generalization, regularization and model selection, Bayesian learning, spaces of functions and kernels, statistical physics of learning, online learning and competitive analysis, hardness of learning and approximations, large deviations and asymptotic analysis, information theory. * 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. * Speech and Signal Processing: recognition, coding, synthesis, denoising, segmentation, source separation, auditory perception, psychoacoustics, dynamical systems, recurrent networks, Language Models, Dynamic and Temporal models. * Visual Processing: biological and machine vision, image processing and coding, segmentation, object detection and recognition, motion detection and tracking, visual psychophysics, visual scene analysis and interpretation. Review Criteria: New as of 2006, NIPS submissions will be reviewed double-blind: the reviewers will not know the identities of the authors. Submissions will be refereed on the basis of technical quality, novelty, potential impact on the field, and clarity. There will be an opportunity after the meeting to revise accepted manuscripts. We particularly encourage submissions by authors new to NIPS, as well as application papers that combine concrete results on novel or previously unachievable applications with analysis of the underlying difficulty from a machine learning perspective. Paper Format: The paper format is fully described at http://research.microsoft.com/conferences/nips06/. Please use the latest style file for your submission. Submission Instructions: NIPS accepts only electronic submissions at http://papers.nips.cc. These submissions must be in postscript or PDF format. The Conference web site will accept electronic submissions from May 26, 2006 until midnight, June 9, 2006, Pacific daylight time. Demonstrations: There is a separate demonstration track at NIPS. Authors wishing to submit to the demonstration track should consult the conference web site. Organizing Committee: General Chair --- Bernhard Schölkopf (MPI for Biological Cybernetics) Program Chair --- John Platt (Microsoft Research) Tutorials Chair --- Daphne Koller (Stanford) Workshop Chairs --- Charles Isbell (Georgia Tech) Rajesh Rao (University of Washington) Demonstrations Chairs --- Alan Stocker (New York University) Giacomo Indiveri (UNI ETH Zurich) Publications Chair --- Thomas Hofmann (TU Darmstadt) Volunteers Chair --- Fernando Perez Cruz (Gatsby Unit, London) Publicity Chair --- Matthias Franz (Max Plack Institute, Tübingen) Online Proceedings Chair --- Andrew McCallum (Univ. Massachusetts, Amherst) Program Committee: Chair --- John Platt (Microsoft Research) Bob Williamson (National ICT Australia) Cordelia Schmid (INRIA) Corinna Cortes (Google) Dan Ellis (Columbia University) Dan Hammerstrom (Portland State University) Dan Pelleg (IBM) Dennis DeCoste (Yahoo Research) Dieter Fox (University of Washington) Hubert Preissl (University of Tuebingen) John Langford (Toyota Technical Institute) Kamal Nigam (Google) Kevin Murphy (University of British Columbia) Koji Tsuda (MPI for Biological Cybernetics) Maneesh Sahani (University College London) Neil Lawrence (University of Sheffield) Samy Bengio (IDIAP) Satinder Singh (University of Michigan) Shimon Edelman (Cornell University) Thomas Griffiths (UC Berkeley) Deadline for Paper Submissions: June 9, 2006 _________________________________________________________________ FREE pop-up blocking with the new MSN Toolbar - get it now! http://toolbar.msn.click-url.com/go/onm00200415ave/direct/01/ From dayan at gatsby.ucl.ac.uk Fri Apr 21 10:44:05 2006 From: dayan at gatsby.ucl.ac.uk (Peter Dayan) Date: Fri, 21 Apr 2006 15:44:05 +0100 Subject: Connectionists: Gatsby Annual Seminar: 17th May: 2:30pm In-Reply-To: <20060113094900.GC23422@flies.gatsby.ucl.ac.uk> References: <20060113094900.GC23422@flies.gatsby.ucl.ac.uk> Message-ID: <20060421144404.GF3517@flies.gatsby.ucl.ac.uk> 17 May 2006 2.30pm Gatsby Unit Annual Seminar We are delighted to announce the first in an annual series of Gatsby Seminars, with talks by distinguished researchers in theoretical neuroscience and machine learning. This year's talks will be given by Dr Li Zhaoping, from the Dept of Psychology at UCL, and Prof John Shawe-Taylor, from the Dept of Computer Science at the University of Southampton. They will be held at 2.30pm in the Wolfson House Haldane Lecture Theatre, and will be followed by a wine reception at 5.00pm at The Gatsby Unit, Alexandra House, 17 Queen Square Titles and abstracts below. All are welcome. --------------------------------------------- 2.30pm: Dr Li Zhaoping The More Briefly one Looks, the More Effectively one `Sees': Vision by V1 I show that a visual search task can be better performed when one views the search array for a shorter time, and suggest an account of this phenomenon based on an analysis of V1's contribution to vision. The cost of a prolonged view comes from the interference of higher level object recognition on lower level image feature processing. A similar effect underlies the trick for art novices of drawing a portrait upside down in order to reproduce lower level image features, such as contours, with less interference from higher level face cognition. In our task, the search target has an uniquely oriented bar but is identical in shape to distractors. Lower level image feature processes enable the unique orientation to pop out, attracting gaze towards the target. Subsequently, higher level object processes, involving focused attention, recognize the target object in a viewpoint invariant manner, confusing the target as being a distractor and interfering with the task. Lower and higher processes lead to their respective behavioural decisions manifested in eye movements and ultimate task performances. I will show physiological and computational evidence implicating V1 mechanisms for the lower level feature pop out, and review data about higher object processes in higher brain areas. 3.45pm: Prof John Shawe-Taylor Inferring Semantic Representations from Data The talk addresses the question of how effectively we can learn underlying semantics from data. We concentrate on text analysis as a domain where semantics are relatively cleanly defined and on which learning approaches have made significant advances. The links between Latent Semantic Indexing, Latent Semantic Kernels and kernel Principal Components Analysis are discussed and the generalisation of such representations is discussed. Cross-lingual information retrieval suggests the use of Canonical Correlation Analysis as a Semantic inference tool. Again a kernel version can be defined and with appropriate regularisation applied in high-dimensional feature spaces. Applications of the same approach to non-text data will also be presented. ------------------------------------------ From cns at cnsorg.org Sat Apr 22 16:43:55 2006 From: cns at cnsorg.org (CNS) Date: Sat, 22 Apr 2006 13:43:55 -0700 Subject: Connectionists: CNS 2006 registration open Message-ID: <20060422204357.M70142@cnsorg.org> CNS 2006 will be held in Edinburgh, UK from July 16-20th 2006. The main meeting will start with an oral session at 9am on Sunday, July 16th and end on Tuesday, July 18th with an evening session. Workshops will start Wednesday, July 19th at 9am and end Thursday, July 20th in the evening. CNS 2006 Registration and lodging reservations are now open. Details can be found at www.cnsorg.org -- CNS - Organization for Computational Neurosciences From angelo.arleo at csl.sony.fr Mon Apr 24 10:52:19 2006 From: angelo.arleo at csl.sony.fr (angelo arleo) Date: Mon, 24 Apr 2006 16:52:19 +0200 Subject: Connectionists: Call for papers: Workshop on "Multisensory Integration and Parallel Memory Systems for Spatial Cognition" Message-ID: <444CE623.4010000@csl.sony.fr> (We apologise for multiple copies of this message) ********************************************************************* 1st C A L L F O R P A P E R S Workshop on "Multisensory Integration and Concurrent Parallel Memory Systems for Spatial Cognition" http://www.idiap.ch/~rchava/sab06wk/ October 1, 2006, Rome, Italy as part of the 9th International Conference on the Simulation of Adaptive Behavior (SAB2006) http://www.sab06.org ********************************************************************* ----------------------------------- WORKSHOP DESCRIPTION and OBJECTIVES ----------------------------------- Spatial cognition involves the ability of an animal to acquire spatial knowledge (e.g., spatio-temporal relations among environmental cues or events), organise it properly, and employ it to adapt its motor behaviour to the specific context. Alike other high-level brain functions, spatial memory calls upon parallel information processing mediated by multiple neural substrates that interact, either cooperatively or competitively, to promote appropriate spatial learning. Similar to animals, autonomous navigating artefacts need to interact with their environment and learn both low-level sensory-motor couplings and more abstract context representations supporting their spatial behaviour. I. At the sensory level, different perceptual modalities provide the navigator with a manifold description of the spatial context. The integration of these multimodal signals into a coherent representation is at the core of spatial cognition. The first part of the workshop will address issues such as: * What are the learning mechanisms (both at the synaptic plasticity level and at a more abstract level) mediating the integration of multimodal signals? * What are the spatial information properties determining the cue selection process during the exploration of a novel environment? * What are the principles underlying the minimisation of destructive interference between spatial memories acquired during lifelong learning? II. At the action selection level, determining and maintaining a goal-directed trajectory involves multiple mnemonic processes, each of which promotes a specific solution (i.e., a navigation strategy) to the overall task. The capability of dynamically weighing the contribution of distinct memory systems is relevant to the issue of adapting the spatial behaviour to the complexity of the task. The second part of the workshop will explore this topic, which is currently the focus of a large research effort in both experimental and computational neuroscience. Among others, the following issues will be addressed: * What are the multiple co-existing memory systems promoting spatial navigation? * What are the anatomo-functional interrelations between the neural substrates (e.g., hippocampus, prefrontal and parietal cortices, basal ganglia, and cerebellum) mediating these multiple spatial memory systems? * What are the principles regulating the cooperative/competitive relations between these parallel memory systems and determining the on-line shift between distinct navigation strategies? This workshop aims at fostering a multidisciplinary forum between experimentalists, theoreticians, and engineers in order to improve our understanding of animal and bio-inspired spatial learning capabilities. Please, refer to the web-site: http://www.idiap.ch/~rchava/sab06wk/ for more information about the workshop programme. ------------- CONTRIBUTIONS ------------- 1. CALL for POSTER ABSTRACTS: DEADLINE JULY 1, 2006 Posters will be exposed during the full length of the workshop, though authors will be asked to present their work only during specific time slots (see the programme). We invite authors to submit a short abstract (less than 400 words including references) in order to be selected for a poster presentation. Due to the limited number of posters that can be actually exposed, accepted contributions shall have high scientific quality and relevance to the workshop. Selected abstracts will be posted on the workshop website, and a hard-copy abstract collection will be distributed during the workshop. Abstracts must be sent (as pdf files) to spatial.learning at gmail.com before July 1, 2006. 2. CALL for FULL PAPERS: DEADLINE NOVEMBER 1, 2006 A Special Issue of the *Journal of Integrative Neuroscience* (http://www.worldscinet.com/jin/jin.shtml) will be edited as a follow-up of the workshop. All submitted papers will be peer-reviewed by both the programme committee of the workshop and the journal's editorial board. Three types of contributions can be submitted: * articles, * brief communications, and * review-like papers. Authors are requested to explicitly address issues such as the biological plausibility of the proposed models, as well as how the proposed theoretical approaches may improve the knowledge of the neurobiological bases of spatial cognition. Drafts must be submitted to spatial.learning at gmail.com before November 1, 2006, and must be prepared according to the journal's "Guidelines for contributions" (http://www.worldscinet.com/jin/mkt/guidelines.shtml). -------------------------- SUMMARY of IMPORTANT DATES -------------------------- We encourage authors to submit both abstracts and full papers even though there is no restriction in this respect. Deadline for abstract submission July 1, 2006 Deadline for full paper submission November 1, 2006 Workshop date October 1, 2006 Expected journal publication date June, 2007 ----------------- PROGRAM COMMITTEE ----------------- Nathaniel Daw. Gatsby Unit, London, UK. Philippe Gaussier. Universit? de Cergy-Pontoise, France. Jeff Krichmar. The Neuroscience Institute, San Diego, USA. Benoit Girard. LPPA - Coll?ge de France, France. Tony Prescott. Adaptive Behaviour Research Group, Sheffield, UK. Agn?s Guillot. Animatlab, University Paris VI, France. Verena Hafner. TU Berlin, Germany Bruno Poucet. CNRS, Marseille, France. Mehdi Khamassi. Animatlab, University Paris VI, France. Denis Sheynikhovich. EPFL, Lausanne, Switzerland. Angelo Arleo. Sony Computer Science Laboratory, France. Ricardo Chavarriaga. IDIAP Research Institute, Switzerland. ------------------- WORKSHOP ORGANIZERS ------------------- Angelo Arleo http://www.csl.sony.fr/~angelo/ Sony Computer Science Laboratory, Paris, France Ricardo Chavarriaga http://www.idiap.ch/~rchava/ IDIAP Research institute, Martigny, Switzerland For further information: spatial.learning at gmail.com From M.Casey at surrey.ac.uk Fri Apr 21 04:16:08 2006 From: M.Casey at surrey.ac.uk (M.Casey@surrey.ac.uk) Date: Fri, 21 Apr 2006 09:16:08 +0100 Subject: Connectionists: International Workshop on Biologically Inspired Information Fusion: Second Call Message-ID: ======================================================================== ==================== International Workshop on Biologically Inspired Information Fusion Second Call for Contributions Tuesday 22 August - Wednesday 23 August 2006, University of Surrey, Guildford, UK. http://www.soc.surrey.ac.uk/ias/workshops/biif/ ======================================================================== ==================== We invite contributions to an international workshop on biologically inspired information fusion. The workshop is designed to bring together complementary researchers in the broad areas of computer science, engineering, psychology and biology who have an interest in the multi-disciplinary aspects of information fusion. The programme consists of tutorials from discipline leaders, discussions, and research student poster and oral presentations. Contributions are being sought for the discussion sessions and research student presentations from all of the target disciplines: computer science, engineering, psychology and biology. Confirmed tutorial guests include: Professor Barry Stein, Department of Neurobiology and Anatomy, Wake Forest University School of Medicine Dr Gemma Calvert, Multisensory Research Group in the Department of Psychology, University of Bath ======================================================================== ==================== Natural and Artificial Multi-sensory Processing The ability to process, interpret and act upon sensory information is perhaps one of the most remarkable aspects of human and animal cognition. Our sensory systems process large volumes of information at different scales in short periods of time, far out-performing current artificial systems, which struggle to usefully process just a single modality of information. For example, whereas speech recognition systems have achieved real-time continuous operation, artificial systems, designed for vision or olfaction are far less advanced, yet the combination of different information sources, or senses, may help overcome some of the processing limitations. This disparity between natural and artificial cognitive systems has been recognised in the recent UK Foresight Cognitive Systems Review, which suggests that our understanding of both natural and artificial systems of sensory processing can be achieved through collaboration between life and physical scientists. About the Workshop The workshop is sponsored by the University of Surrey's Institute of Advanced Studies. The aim is to promote collaboration between disciplines to develop an understanding of how to build adaptive information fusion systems by improving our knowledge from both natural and artificial systems research. The programme is designed to facilitate a cross-discipline understanding of multi-sensory fusion, with discussions on key topics and future directions, and presentation of current ideas. This is to be achieved through tutorials from leaders in each of the target disciplines, brainstorming and debate sessions lead by relevant researchers, and both oral and poster presentations from research students. Example topics include, but are not limited to: Sensory and multi-sensory processing: neurobiology, behaviour, computational modelling and artificial sensors - Vision, audition, olfaction, taste, touch - Attention: pre-attention or task-driven attention - Emotional bias on senses - Artificial sensors Information fusion and multi-modal systems: - Computer vision, speech processing, gesture recognition - Sensor fusion - Multiple regressor or classifier systems - Biometrics, human-computer interaction, intelligent systems - Bio-logically inspired robotics ======================================================================== ==================== Discussions Topics for the discussion sessions should aim to promote new or controversial ideas, perhaps posing unanswered questions related to the workshop. These should be in the form of abstracts (maximum 500 words) stating the key topic of discussion and highlighting possible solutions and current points of view. Proposals for debates, where two participants offer their point of view prior to discussion, should be clearly highlighted. All contributions will be peer reviewed by the workshop programme committee. Those with accepted topics will be invited to give a 10 minute presentation of their idea. For sessions focused around a debate, both participants will be invited to present their ideas in a 10 minute slot each, prior to discussion. An open brainstorming session will then follow for 50 minutes with a focus on initially evaluating the proposed idea or giving thoughts on unanswered questions. Notes and outcomes of these sessions will be recorded. Abstracts should be submitted via e-mail to biif2006 at surrey.ac.uk by the deadline: 15 May 2006. ======================================================================== ==================== Student Presentations Papers are invited from research students only to promote discussion of new ideas and to foster training and development of new researchers. All papers will be peer reviewed by the workshop programme committee to assess originality, significance, quality and clarity. Those students with accepted papers will be invited to either present a poster or to give a 20 minute oral presentation. Papers should not exceed 6 pages in length, including references, tables, figures and appendices, and should follow the LNCS format, details of which can be found at http://www.springer.com/sgw/cda/frontpage/0,11855,3-164-2-72376-0,00.htm l. Papers should be submitted via e-mail to biif2006 at surrey.ac.uk by the deadline: 15 May 2006. ======================================================================== ==================== Enquiries regarding abstract and paper submission should be directed to biif2006 at surrey.ac.uk. Abstracts and papers will be available to workshop attendees via the website and printed proceedings. After the workshop, participants will be invited to submit papers based upon their work to two journal special issues (journals to be confirmed). These will contain a mixture of review/discussion articles and presentations of current research work. ======================================================================== ==================== Important Dates 15 May 2006 Deadline for submitting discussion topics and student papers 19 June 2006 Notification of acceptance 17 July 2006 Camera ready papers 22-23 August 2006 Workshop at the University of Surrey Guests looking for accommodation on campus (the cheapest in Guildford) are advised to register by the 15th May 2006. Otherwise, registration is open up until the workshop. For papers to be presented at the workshop, all guests must be registered by the 17th July 2006 to secure a place on the programme. Further information can be obtained from: - Website: http://www.soc.surrey.ac.uk/ias/workshops/biif/ - Enquiries about paper submission: biif2006 at surrey.ac.uk - General and administrative enquiries: Mrs Gautier O'Shea, S.Gautier at surrey.ac.uk; Mrs Heather Norman, H.Norman at surrey.ac.uk - Dr Matthew Casey, M.Casey at surrey.ac.uk; tel. +44 (0)1483 689635 - Dr Paul Sowden, P.Sowden at surrey.ac.uk - Dr Hujun Yin, Hujun.Yin at manchester.ac.uk - Dr Tony Browne, A.Browne at surrey.ac.uk From p.husbands at sussex.ac.uk Mon Apr 24 05:57:17 2006 From: p.husbands at sussex.ac.uk (Phil Husbands) Date: Mon, 24 Apr 2006 10:57:17 +0100 Subject: Connectionists: faculty positions available at Sussex University Message-ID: <5671531.1145876237@[192.168.123.100]> Faculty positions available at Sussex University, UK. Professorship in Informatics and Head of Department Department of Informatics We are seeking to further strengthen research in the Department with a high-profile appointment as Professor of Informatics. The successful candidate will have an international reputation for excellence in research, and a proven record of research or academic management. The appointment involves being Head of the Department of Informatics for an agreed length of time, normally three years. Applicants should have an academic background in an area of Informatics, and their research should align with one or more areas being pursued by existing research groups in the Department. These include computational neuroscience, evolutionary and adaptive systems, neural computation, as well as other areas of AI, Cognitive Science and CS. Full details: Lecturer in Informatics Department of Informatics The successful applicant will have a strong peer reviewed publication record, and will have teaching experience. Applicants should have an academic background in an area of Informatics, and their research should align with one or more areas being pursued by existing research groups in the Department. These include computational neuroscience, evolutionary and adaptive systems, neural computation, as well as other areas of AI, Cognitive Science and CS. Full details: From Pierre.Bessiere at imag.fr Thu Apr 20 11:58:59 2006 From: Pierre.Bessiere at imag.fr (=?ISO-8859-1?Q?Pierre_Bessi=E8re?=) Date: Thu, 20 Apr 2006 17:58:59 +0200 Subject: Connectionists: Research Engineer in Bayesian Programming Message-ID: <7B5512F3-B286-4227-86F4-05F37BA9F7C8@imag.fr> Position Title: ------------------ Research Engineer in Bayesian Programming Where: ------------ Grenoble (Capital of the French Alps), France When: --------- Immediately, for 3 to 4 years Description of the Position: ------------------------------------ You will have to develop Bayesian models, programs, applications and experiments. You will be a key element of a research group devoted to "Stochastic Models for Perception, Inference, Learning and Action". Your main mission will be to take in charge the software development of the group related to the starting european project BACS (Bayesian Approach to Cognitive Systems) and some experiments on various robotic platforms. Your employer will be INRIA (Institut National de la Recherche en Informatique et Automatique) a major international institute for research in computer science and applied math. Example of possible models, experiment or application you may have to work on are : - Bayesian models of neurons and population of neurons - Bayesian models of human object perception - Bayesian models of human and rat navigation - Bayesian based autonomous navigation of mobile robots and cars - Bayesian based body and face motion tracking - Bayesian reconstruction of 3D realistic scene - Bayesian based multi-modal sensor integration and analysis - Bayesian driver assistance for enhanced vehicle safety All this models are build using the Bayesian Programming formalism (an extension of Bayes Nets) and use the ProBT? toolbox and API to automate the inference and computation. You will be the ProBT guru of the group and will assist researchers and PhD student in their models and software development. Requirements: -------------------- Necessary : - A master, an engineering degree or a PhD in computer science. - Fluent in C and C++ - Fluent in either French or English (If not fluent in French, at least some good bases are required and a strong willing to learn more rapidly) Plus : - Bilingual of fluent in both language - Experience of software development and maintenance - Holding a PhD - Experience of robotics and/or artificial intelligence - Proficiency in probability or statistics - Experience in other computer languages and tools Additional Informations: -------------------------------- - Grenoble Grenoble is 600K inhabitants city right in the middle of the French alps. It has a very big university and at least 10% of the population is made of students. Grenoble activity is turned toward high technology industry and research. Its domains of excellence are nanotechnology, computer sciences and electronic. All mountain outdoors leisure are next door (the closest ski resort is 30 minutes from downtown). - eMOTION research group The research group (www-laplace.imag.fr) is made of 25 persons (permanent researchers, engineers and PhD students). It is a very international group as presently 6 countries are represented beside France (Brazil, China, India, Italy, Mexico & Singapore). The group has a long experience (>15 years) of research in Bayesian modeling. It applies theese technics to robotics, artificial intelligence, cognitive science and developing industrial applications. The group has been the leader of the european project BIBA (Bayesian Inspired Brain and Artifacts) which, after 4 years of work, is just terminated. - BACS project: BACS is the continuation of BIBA. Its a new european project started in january for 4 years. The abstract of the project is the following: Despite very extensive research efforts contemporary robots and other cognitive artifacts are not yet ready to autonomously operate in complex real world environments. One of the major reasons for this failure in creating cognitive situated systems is the difficulty in the handling of incomplete knowledge and uncertainty. In this project we will investigate and apply Bayesian models and approaches in order to develop artificial cognitive systems that can carry out complex tasks in real world environments. We will take inspiration from the brains of mammals including humans and apply our findings to the developments of cognitive systems. The Bayesian approach will be used to model different levels of brain function, from neural functions up to complex behaviors. This will enable us to show that neural functions and higher-level cognitive activities can coherently be modeled within the Bayesian framework. The Bayesian models will be validated and adapted as necessary according to neuro-physiological data from rats and humans and through psychophysical experiments on human. The Bayesian approach will also be used to develop four artificial cognitive systems concerned with (i) autonomous navigation, (ii) multi-modal perception and reconstruction of the environment, (iii) Semantic facial motion tracking, and (iv) human body motion recognition and behavior analysis. The conducted research shall result in a consistent Bayesian framework offering enhanced tools for probabilistic reasoning in complex real world situations. The performance will be demonstrated through its applications to drive assistant systems and 3D mapping, both very complex real world tasks. - INRIA: (see http://www.inria.fr/inria/enbref.en.html) - Bayesian Programming and ProBT toolbox: Bayesian Programming is a methodology and a formalism to develop software able to deal with incomplete and uncertain information. ProBT is a C++ library that implement Bayesian inference and learning on various kind of computers and operating systems. ProBT is a commercial product (www.probayes.com) but is also available for free for research and teaching utilization (www.Bayesian-programming.org). Salary: ---------- 27K? <-> 37K?(according to qualifications) Contact: ----------- Pierre.Bessiere at imag.fr, Christian.Laugier at imag.fr _______________________________ Dr Pierre Bessi?re - CNRS ***************************** GRAVIR Lab INRIA 655 avenue de l'Europe 38334 Montbonnot FRANCE Mail: Pierre.Bessiere at imag.fr Http: www-laplace.imag.fr Tel: +33 4 76 61 55 09 _______________________________ From chunnan at iis.sinica.edu.tw Sun Apr 30 23:56:04 2006 From: chunnan at iis.sinica.edu.tw (Chun-Nan Hsu) Date: Mon, 1 May 2006 11:56:04 +0800 (CST) Subject: Connectionists: Invitation to the Machine Learning Summer School 2006 Message-ID: ** Invitation to the Machine Learning Summer School ** July 24- August 4, 2006, Taipei, Taiwan Quick Link: http://www.iis.sinica.edu.tw/MLSS2006 Registrations are now open for MLSS Taipei 2006. MLSS Taipei 2006 is the 2006 version of the "Machine Learning Summer School" series held previously in Canberra, Tubingen, Berder and Chicago. The two-week summer school program consists of about 40+ hours of tutorial lectures from 7/24 to 8/4. The late afternoon sessions will provide a chance for the participants to discuss the latest research problems with the invited speakers. This summer school will cover a broad range of subjects from statistical learning theory to state of the art applications. Please check the summer school Web site for the topics covered and the list of invited speakers. Dates: Monday 24 July to Friday 4 August 2006 (2 weeks) Location: National Taiwan University of Science and Technology, Taipei, Taiwan Important Dates: May 31, 2006: Deadline for financial aid application for students. June 7, 2006: Results of financial aid applications informed. June 20, 2006: Deadline for early registration and discounted housing. July 24, 2006: The summer school. Past Schools: http://www.mlss.cc The topics covered in this summer school include o Kernel Methods o Reinforcement Learning o Learning Ensembles o Graphical Models o Variational Methods o Online Learning o Bioinformatics o Text Mining International students are qualified for scholarships with two levels: USD 800 and USD 400. Applications will be reviewed and decided by the steering committee. For more information, go to http://www.iis.sinica.edu.tw/MLSS2006, or contact mlss at iis.sinica.edu.tw Come and enjoy a summer in Taiwan with plenty of great food! Poster (please help advertise the MLSS series in your school): http://www.iis.sinica.edu.tw/MLSS2006/flyer.pdf From cspence at sarnoff.com Wed Apr 26 10:05:06 2006 From: cspence at sarnoff.com (CLAY SPENCE) Date: Wed, 26 Apr 2006 10:05:06 -0400 Subject: Connectionists: Paper: Varying complexity in image models Message-ID: <444F7E12.4050500@sarnoff.com> The following paper appeared in the Feb. 2006 issue of IEEE Trans. on Image Proc., Vol. 15, No. 2, pp. 319-330. It's also available at http://liinc.bme.columbia.edu/publications/hip-tip.pdf. > Varying Complexity in Tree-Structured Image Distribution Models > Clay Spence, Lucas Parra, and Paul Sajda > > Abstract > > Probabilistic models of image statistics underlie many approaches in > image analysis and processing. An important class of such models have > variables whose dependency graph is a tree. If the hidden variables > take values on a finite set, most computations with the model can be > performed exactly, including the likelihood calculation, training with > the EM algorithm, etc. Crouse, et al developed one such model, the > Hidden Markov Tree (HMT). They took particular care to limit the > complexity of their model. We argue that it is beneficial to allow > more complex tree-structured models, describe the use of information > theoretic penalties to choose the model complexity, and present > experimental results to support these proposals. For these experiments > we use what we call the hierarchical image probability (HIP) > model. The differences between the HIP and the HMT models include the > use of multi-variate Gaussians to model the distributions of local > vectors of wavelet coefficients and the use of different numbers of > hidden states at each resolution. We demonstrate the broad utility of > image distributions by applying the HIP model to classification, > synthesis, and compression, across a variety of image types, namely, > electro-optical (EO), synthetic aperture radar (SAR), and mammograms > (digitized x-rays). In all cases we compare with the HMT. > > Keywords: image model, hidden Markov tree, Bayesian network, minimum > description length, hidden variables, classification, synthesis, > compression, tree-structured belief network Clay Spence From tgd at eecs.oregonstate.edu Thu Apr 27 18:21:09 2006 From: tgd at eecs.oregonstate.edu (Thomas G. Dietterich) Date: Thu, 27 Apr 2006 15:21:09 -0700 Subject: Connectionists: Post-Doc/Transfer Learning/Oregon State-MIT Message-ID: <7756-Thu27Apr2006152109-0700-tgd@cs.orst.edu> Oregon State University School of Electrical Engineering and Computer Science Join the Oregon State Machine Learning research group as a post-doc! We are looking for one or more Research Associates to drive our research in transfer learning within the DARPA-funded CALO project, whose goal is to build an integrated intelligent system for the computer desktop. You will be a member of a team jointly led by Leslie Kaelbling (MIT) and Tom Dietterich (Oregon State). Required qualifications include a Ph.D. in computer science or related field; strong mathematical background; experience with at least 3 of the following: (a) machine learning algorithms, (b) experimental machine learning methods, (c) probabilistic representation and reasoning methods including Bayesian networks, (d) logic-based representation and reasoning methods including ontology design tools; excellent written and spoken communication skills; excellent programming and software engineering skills; excitement about computer science research; and the ability to manage graduate and undergraduate students working on research projects. Position is full-time, 12 month, fixed term with reappointment at the discretion of the hiring official. For full consideration, applications must be received by 5/10/06. Send resume, letter of interest, evidence of 2 relevant publications and 3 professional references w/address, phone # to: Research Associate Search, 1148 Kelly Engineering Center, Corvallis, OR 97331-5501 or by email to sullipat at eecs.oregonstate.edu. For full position announcement see: http://oregonstate.edu/jobs, other inquires contact Thomas G. Dietterich (tgd at cs.orst.edu). OSU is an AA/EOE. Pat Sullivan Grant Coordinator ~ Intelligent Information Systems School of Electrical Engineering & Computer Science Oregon State University 2065 Kelley Engineering Center ~ Corvallis, OR 97331~5501 phone 541-737-4536 ~ fax 541-737-1300 email sullipat at eecs.oregonstate.edu From mark.plumbley at elec.qmul.ac.uk Mon Apr 3 10:56:56 2006 From: mark.plumbley at elec.qmul.ac.uk (Mark Plumbley) Date: Mon, 3 Apr 2006 15:56:56 +0100 Subject: Connectionists: CFP: ICA Research Network Workshop, Liverpool, UK, 18-19 Sept 2006 Message-ID: <9D47A2D30B0BFB4C920786C25EC693456DCEAD@staff-mail.vpn.elec.qmul.ac.uk> Dear Connectionsts, I hope this workshop may be of interest to those of you working in ICA or source separation. Best wishes, Mark Plumbley ----------------- *** CALL FOR PAPERS *** 2006 ICA Research Network Workshop www.icarn.org Liverpool, UK 18 - 19 September 2006 The ICA Research Network is sponsored by the Engineering and Physical Sciences Research Council (EPSRC) in the UK, and is aimed at improving communications in the area of Blind Source Separation (BSS) and Independent Component Analysis (ICA). The 2006 ICA Research Network Workshop will be held at the University of Liverpool covering the latest developments and techniques in the area of BSS/ICA. Topics The workshop will feature keynote addresses and technical presentations (oral and poster), which will be included in the registration. Papers are solicited for, but not limited to, the following areas: * Algorithms and Architectures for BSS/ICA - Nonlinear ICA - Probabilistic Models - Sparse Coding - etc * Theory of BSS/ICA - Optimization - Complex Methods - Time-Frequency Representations - etc * Applications of BSS/ICA - Audio - Bio-Informatics - Biomedical Engineering - Communications - Finance - Image Processing - Psychology - Computational Auditory Scene Analysis (CASA) - etc Extended Abstract Submission Procedure Prospective authors are invited to submit extended abstracts of no more than two A4-size pages, including: * Title * Authors' details * the work with contexts and * preliminary results (a Table or a Figure) Submission Please submit your extended abstract by e-mail (with a PDF attachment) with the subject "Extended Abstract Submission" to icarnw06 at liverpool.ac.uk. Full Paper Submission Procedure Authors of accepted extended abstracts will be invited to submit a paper of up to four pages in the PDF format. At least one author of each accepted paper must undertake to attend the workshop. Accepted papers will be published in a bound volume. Authors of the most innovative papers will be invited to submit substantially extended and updated versions of their papers for further review and possible publication in the International Journal of Neural Systems. Important Dates/Deadlines Submission of extended abstract 5 May 2006 Notification of acceptance 2 June 2006 Submission of camera-ready accepted paper 7 August 2006 Author registration 7 August 2006 Workshop 18-19 September 2006 Contact For more information visit www.icarn.org or email icarnw06 at liverpool.ac.uk ************************************************************** Professor A K Nandi David Jardine Chair of Signal Processing Department of Electrical Engineering and Electronics The University of Liverpool Brownlow Hill, Liverpool, L69 3GJ, UK Tel: +44 151 794 4525 Fax: +44 151 794 4540 http://www.liv.ac.uk/eee/academicstaff/nandi.htm ************************************************************* --- Dr Mark D Plumbley Centre for Digital Music Department of Electronic Engineering Queen Mary University of London Mile End Road, London E1 4NS, UK Tel: +44 (0)20 7882 7518 Fax: +44 (0)20 7882 7997 Email: mark.plumbley at elec.qmul.ac.uk http://www.elec.qmul.ac.uk/people/markp/ From zhaoping at gatsby.ucl.ac.uk Mon Apr 3 15:04:38 2006 From: zhaoping at gatsby.ucl.ac.uk (Dr Zhaoping Li) Date: Mon, 3 Apr 2006 20:04:38 +0100 (BST) Subject: Connectionists: Postdoc position in vision/computational neuroscience in London Message-ID: Applications are invited for the post of Research Assistant to work with Dr. Li Zhaoping (http://www.gatsby.ucl.ac.uk/~zhaoping ) in the area of vision/neuroscience, particularly on biological vision, using theoretical and/or psychophysical investigation tools. It is essential that the candidate should have good capability/experience in either theoretical/modeling area or in visual psychophysical area, and skills/experience in both areas is not essential. The research assistant is expected to contribute to the research environment of the laboratory and should have the capability to work well in a team. The post is available around or after September 2006. Salary is on the Grade 6 of the new salary scales (?19,645-?23,457 plus ?2,400London allowance) and will depend upon qualifications and experience. Applications (email or hard copy ) by cover letter, CV and Personal Information form (the latter available at http://www.psychol.ucl.ac.uk/info/Personal_Information.doc) to Anouchka Sterling, Department of Psychology, UCL, Gower Street, London WC1E 6BT, a.sterling at ucl.ac.uk . If applying by email please submit all requested information in one .pdf file names by your surname eg Smith.pdf. Further information concerning the post are on the web at http://www.psychol.ucl.ac.uk/info/psychophysics_li.htm while interested candidates can also contact Li Zhaoping, z.li at ucl.ac.uk 44 20 7679 1174. The closing date for the application is 1 June 2006 From ted.carnevale at yale.edu Mon Apr 3 16:00:59 2006 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 03 Apr 2006 16:00:59 -0400 Subject: Connectionists: NEURON 2006 Summer Course Message-ID: <44317EFB.7010003@yale.edu> COURSE ANNOUNCEMENT What: "The NEURON Simulation Environment" (NEURON 2006 Summer Course) http://www.neuron.yale.edu/neuron/sdsc2006/sdsc2006.html When: Saturday, June 24, through Wednesday, June 28, 2006 Where: SDSC/CalIt2 Synthesis Center University of California at San Diego, CA Organizers: N.T. Carnevale and M.L. Hines Description: This intensive hands-on course covers the design, construction, and use of models in the NEURON simulation environment. It is intended primarily for those who are concerned with models of biological neurons and neural networks that are closely linked to empirical observations, e.g. experimentalists who wish to incorporate modeling in their research plans, and theoreticians who are interested in the principles of biological computation. The course is designed to be useful and informative for registrants at all levels of experience, from those who are just beginning to those who are already quite familiar with NEURON or other simulation tools. Registration is limited to 20, and the deadline for receipt of applications is Monday, June 5, 2006. For more information see http://www.neuron.yale.edu/neuron/sdsc2006/sdsc2006.html or contact Ted Carnevale Psychology Dept. PO Box 208205 Yale University New Haven, CT 06520-8205 USA phone 203-432-7363 fax 203-432-7172 email ted.carnevale at yale.edu Supported in part by: National Institutes of Health National Science Foundation The San Diego Supercomputer Center California Institute for Telecommunications and Information Technology Contractual terms require inclusion of the following statement: This course is not sponsored by the University of California. --Ted From J.Triesch at fias.uni-frankfurt.de Tue Apr 4 11:22:39 2006 From: J.Triesch at fias.uni-frankfurt.de (J.Triesch@fias.uni-frankfurt.de) Date: Tue, 4 Apr 2006 17:22:39 +0200 (CEST) Subject: Connectionists: Summer School: Theoretical Neuroscience & Complex Systems Message-ID: Final Call for Applications: Frankfurt Institute for Advanced Studies (FIAS) Summer School: Theoretical Neuroscience & Complex Systems We invite applications for a three-week summer workshop in Frankfurt, Germany from Saturday, August 5 to Sunday, August 27, 2006. The application deadline is Saturday, April 15. Application instructions are at the bottom of this announcement. FACULTY: Larry ABBOTT, Columbia University, USA Dana BALLARD, University of Texas, Austin, USA Emery BROWN, Harvard and MIT, USA Gyorgy BUZSAKI, Rutgers University, USA Gustavo DECO, Univ. Pompeu Fabra, Spain Yves FREGNAC, Centre National de la Recherche Scientifique, France Ralf GALUSKE, Max-Planck-Institute for Brain Research, Germany Wulfram GERSTNER*, Ecole Polytechnique Federale de Lausanne, France Rainer GOEBEL, Maastricht University, Netherlands Claudius GROS, Goethe University, Germany Aapo HYVARINEN, Univ. of Helsinki, Finland Christof KOCH, Caltech, USA Wolfgang MAASS, FIAS, Germany and Technische Universit????t Graz, Austria Bartlett MEL, University of South California, USA Lars MUCKLI, Max-Planck-Institute for Brain Research, Germany Sergio NEUENSCHWADER, Max-Planck-Institute for Brain Research, Germany Gordon PIPA, FIAS and Max-Planck Institute for Brain Research, Germany Wolf SINGER, FIAS and Max-Planck Institute for Brain Research, Germany Andrey SOLOV'YOV, FIAS, Germany Jochen TRIESCH, FIAS, Germany and UC San Diego, USA Misha TSODYKS, Weizmann Institute, Israel Christoph VON DER MALSBURG, FIAS, Germany Carl VAN VREESWIJK, Rene Descartes University, France Michael WIBRAL, Max-Planck Institute for Brain Research, Germany *not yet confirmed GOALS: There is a deficiency in the exchange of ideas between theoretical physicists and experimental biologists. This arises from different background knowledge bases and viewpoints, even when addressing the same problem. The aim of the FIAS Summer School on Theoretical Neuroscience and Complex Systems is to provide a bridge linking experimentalists and theorists. The school also addresses the challenge of further developing theoretical sciences and transferring existing concepts into the interdisciplinary field of neuroscience. This transference will be highly dependent on the successful training of students able to bridge the different fields. Participants will work on self-defined projects in interdisciplinary teams comprising at least one experimental neuroscientist and one theoretician. FORMAT: The three-week summer workshop will include a preschool that will take place at the Max-Planck Institute for Brain Research in Frankfurt. During these three days, theoretical physicists will be trained in basic concepts of neuroscience, experimental neuroscientists will be trained in basic concepts of network theory and complex systems, and theoretical neuroscientists will be trained in experimental neuroscience. The first two days of the summer school will be used to introduce the main concepts of neuronal systems and information processing. The second week is devoted to the characterization and analysis of neural recordings, as well as to the description and modeling of neurons, synapses, and small networks. The third week introduces approaches for modeling higher cognitive functions. Throughout, participants work on projects that they themselves propose, and this work will be carried out in collaboration with an interdisciplinary working-group comprising one experimental neuroscientist, one theoretical neuroscientist, and one theoretical physicist. Lectures will be held in the mornings from Monday-Friday, while students will work on their projects in the afternoons from Monday-Wednesday. Intra-group progress reports will be presented on Wednesday and Friday evenings. A preview of the following week's lectures will be provided on Thursday afternoons to ensure that all participants are comfortable with the material to be discussed. Saturdays will be devoted to "theory in practe" and participants will have the chance to visit research laboratories including the Max-Planck Institute for Brain Research in Frankfurt and the Honda Research Institute in Offenbach. Each Sunday will be reserved for recreational opportunities, and on the final day of the summer school, the projects will be presented. The scientific program will cover the following areas: - Neuroanatomy and Neurophysiology - Basics in modeling of neurons - Models of neural microcircuits - Abstract models of higher-level functions - Outlook to other complex systems LOCATION AND ARRANGEMENTS: FIAS is a Foundation of the Johann Wolfgang Goethe-University and is located on the natural science campus, Riedberg, in Frankfurt am Main. It also has close collaboration with the Faculty of Natural Sciences at the J.W. Goethe-University and the Max Planck Institutes for Brain Research and Biophysics. The preschool will take place at the Max-Planck Institute for Brain Research. Students and Lecturers will stay in the Marriott Courtyard Frankfurt Nordwestzentrum. The hotel is located very close to the FIAS Institute and has excellent access to the public transport system. FINANCIAL ARRANGEMENT: FIAS organizes the summer school and covers the accommodation and the cultural Program. Students have to pay a registration fee of 150 Euro. Students from Eastern European countries or students in general who need support for their travel expenses can apply for reimbursement and a waiver for the registration fee. Please indicate this in your application if you are considering applying for reimbursement. We will also need an estimation of your travel expenses. HOW TO APPLY: Students who have a bachelor, a master, a Ph.D., or other equivalent degrees can apply for this summer school. To apply, please provide two letters of recommendation, a curriculum vitae, as well as a one page description of a small project you are planning to work on during the course. Based on the proposal, the committee will group students to teams and assign interdisciplinary faculty to each team. Information about applying and the summer school in general can be found at the website: http://www.fias.uni-frankfurt.de/neuro_school/ A copy of the summer school announcement can be downloaded from: http://www.fias.uni-frankfurt.de/neuro_school/FIAS_summerschool_Poster_A2.pdf Applications should include: * First name, last name, affiliation, valid e-mail address * Two letters of recommendation * Curriculum Vitae * Project proposal (max. one page) * Request for reimbursement of travel expenses (if applicable) Please send your documents in an electronic format to: neuro_school at fias.uni-frankfurt.de The application deadline is Saturday, April 15, 2006. Applicants will be notified by e-mail by May 1, 2006. For further information, please contact: Denise Meixler (neuro_school at fias.uni-frankfurt.de) Frankfurt Institute for Advanced Studies Johann Wolfgang Goethe University Max-von-Laue-Str. 1 60438 Frankfurt am Main Germany tel: +49 69 798 47851 fax: +49 69 798 47876 From ted.carnevale at yale.edu Thu Apr 6 13:00:12 2006 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Thu, 06 Apr 2006 13:00:12 -0400 Subject: Connectionists: talks and tutorials at the NEURON Simulator Meeting Message-ID: <4435491C.4030008@yale.edu> The agenda for the 2006 NEURON Simulator Meeting continues to grow. Here are three more reasons to join us at UT Austin, May 5-7-- Discussion: "NEURON: quo vadis?" Moderator: Michael Hines The agenda is to discuss future directions for NEURON, in order to help it continue to evolve to meet the changing needs of its users. Topics that will be considered include strategies for improving the development process, possible enhancements of computational efficiency and power, and tactics for increasing functionality and ease of use. Tutorial: "Converting morphometric data to models with the Import3D tool" Speaker: Ted Carnevale One recent addition to NEURON is the Import3D tool, which was created to simplify the task of converting detailed morphometric data to NEURON models. Import3D can read Eutectic, SWC, and Neurolucida classic and Version 3 files, and can export the data directly into the CellBuilder or generate a "top level" instance of a model. It automatically identifies and repairs many common problems, and helps users identify other errors that require the exercise of judgment and manual editing of a copy of the original morphometric data. Workshop: "Hacking NEURON." Moderators: Ted Carnevale and Bill Lytton The aim of this event is to exchange "power programming" tips for getting the most out of NEURON. Discussion and specific practical examples will range over topics such as: ? essential idioms in hoc ? organizing programs for efficiency and clarity ? combining hoc code and the GUI to exploit the strengths of both ? discovering and exploiting the single largest collection of useful hoc code ? hacking session files ? hacking NEURON's run-time system ? custom initializations ? automating execution of simulations and analysis of results The moderators will present many of their own tips and tricks, and audience participation is strongly encouraged. Register now--the registration deadline is Friday, April 21. For more information see http://www.utexas.edu/neuroscience/NEURON2006/nsm2006.html --Ted From doya at irp.oist.jp Thu Apr 6 14:59:51 2006 From: doya at irp.oist.jp (Kenji Doya) Date: Fri, 7 Apr 2006 03:59:51 +0900 Subject: Connectionists: Okinawa Computational Neuroscience Course 2006: Call for Applications References: <9766557bd8a85e3eca7a9175d6973c9b@irp.oist.jp> Message-ID: <0FD0BCBF-68ED-449C-9F29-86647023DCFA@irp.oist.jp> The deadline of OCNC 2006 application is next Monday. **************************************************************** Call for Applications OKINAWA COMPUTATIONAL NEUROSCIENCE COURSE 2006 "Computing Neurons" June 26 - July 7, 2006. Okinawa, Japan. http://www.irp.oist.jp/ocnc/2006 Application Deadline: APRIL 10TH, 2006 The aim of Okinawa Computational Neuroscience Course is to provide opportunities for young researchers with theoretical backgrounds to learn latest advances in neuroscience, and those with experiment backgrounds to have hands-on experience in computational modeling. We invite graduate students and postgraduate researchers to participate in the course, held from June 26th through July 7th at an oceanfront seminar house of Okinawa Institute of Science and Technology. Those interested in attending the course should send the materials below by e-mail or the course web page by APRIL 10th, 2006. We hope that this course will be a good opportunity for theoretical and experimental neuroscientists to meet together and to explore the attractive nature and culture of Okinawa, the southernmost island prefecture of Japan. ******* Course Outline ******* Okinawa Computational Neuroscience Course (OCNC2006) Theme: Computing Neurons - What neurons compute; How we know by computing - Our brain is a network of billions of neurons, but even a single neuron is a fantastically complex computing device. Technology has made it possible to look into the detailed structure of dendritic branches, variety of ionic channels and receptors, molecular reactions at the synapses, and the network of genes that regulate all these. The challenge is to understand the meaning and function of these components of the neural machine. To do this we need to put together data from many experiments at different levels into a computational model, and to analyze the kinds of computation that single neurons and their networks can perform. This course invites graduate students and postgraduate researchers who are interested in studies integrating experimental and computational approaches for understanding cellular mechanisms of neurons. Lectures: Upi Bhalla (NCBS) Haruhiko Bito (U Tokyo) Sydney Brenner (OIST) Yang Dan (UC Berkeley) Erik DeSchutter (U Antwerp) Kenji Doya (OIST) Bard Ermentrout (U Pittsburgh) Geoff Goodhill (U Queensland) David Holcman (Weizmann institute of Science) Shin Ishii (NAIST) Shinya Kuroda (U Tokyo) Nicolas Le Novere (European Bioinformatics Institute) Roberto Malinow (Cold Spring Harbor Lab) Ion Moraru (U of Connecticut) Felix Schuermann (EPFL) Terry Sejnowski (Salk Institute) Susumu Tonegawa (MIT) Jeff Wickens (U Otago) Student Projects a) Introduction to neural/cellular simulator platforms b) Model construction from experimental data c) Analysis of neuron models Students will present posters on their current works early in the course and the results of their projects at the end of the course. Date: June 26th to July 7th, 2006 Place: Okinawa Institute of Science and Technology Onna village, Okinawa, Japan Sponsors: Okinawa Institute of Science and Technology Nara Institute of Science and Technology Japanese Neural Network Society Co-organizers: Upinder Bhalla, National Center for Biological Sciences, India Kenji Doya, Okinawa Institute of Science and Technology Shinya Kuroda, University of Tokyo Nicolas Le Novere (European Bioinformatics Institute) Advisors: Sydney Brenner, Okinawa Institute of Science and Technology Hiroaki Kitano, SONY Computer Science Laboratory Terrence Sejnowski, Salk Institute Susumu Tonegawa, Massachusetts Institute of Technology ******* Application ******* Please send the following by e-mail (ocnc at irp.oist.jp) or the web application page by APRIL 10TH, 2006. 1) First name, 2) Middle initial (if any), 3) Family name, 4) Degree, 5) Date of birth, 6) Gender, 7) Nationality, 8) Affiliation, 9) Position, 10) Advisor, 11) Postal address, 12) Phone, 13) Fax, 14) E-mail, 15) Web page (if any), 16) Educational background, 17) Work experience, 18) List of publications, 19) Research interests (up to 500 words), 20) Motivations for attending the course (up to 500 words), 21) Two referees whom can ask recommendations (names, affiliations, e-mail addresses), 22) Need for travel support, 23) How you learned about the course. We will accept 30 students based primarily on their research interests (19) and motivations (20). We will also consider the balance of members' research disciplines, geographic origins, and genders. The sponsor will provide lodging and meals during the course. Support for roundtrip airfare to Okinawa will be considered for students without funding. The result of selection will be informed to applicants via e-mail by May 10th. The details of OCNC2004 and 2005 are available on the web page (http://www.irp.oist.jp/ocnc/). ******* Secretariat ******* Okinawa Computational Neuroscience Course c/o Initial Research Project, Okinawa Institute of Science and Technology 12-22 Suzaki, Gushikawa Okinawa 904-2234, Japan Phone: +81-98-921-3933 Fax: +81-98-921-3873 Email: ocnc at irp.oist.jp For more information, please visit the web page: http://www.irp.oist.jp/ocnc/2006 ---- Kenji Doya Initial Research Project, Okinawa Institute of Science and Technology 12-22 Suzaki, Uruma, Okinawa 904-2234, Japan Phone:+81-98-921-3843; Fax:+81-98-921-3873 http://www.irp.oist.jp/ From saighi at ixl.fr Thu Apr 6 05:59:40 2006 From: saighi at ixl.fr (Sylvain SAIGHI) Date: Thu, 06 Apr 2006 11:59:40 +0200 Subject: Connectionists: Post-Doc position (1 year) Message-ID: <4434E68C.9090305@ixl.fr> Post-doc position (1 year) in IXL- CNRS UMR 5818 - Bordeaux, France Subject : ? Design of living-artificial interface IC for hybrid neural networks ? <>Offer description : The proposed subject is related to the EU project Neuro-vers-IT (FP6-2004-Mobility 019247, start 1/01/2006), in which IXL is a partner. The goal of that project is to reinforce the European multi -disciplinary research activities in Information Technology, Biomedical Engineering, and Robotics. IXL is in charge of designing systems to interface biological and artificial neurons, using dedicated integrated circuits (IC) and systems running in real time. The developed platforms will allow the characterization (including modeling) of learning and plasticity phenomenas in cultured neural networks on a long-term basis. <>Candidate profile : The candidate has to be an expert in analog and mixed IC design. Basis knowledge in neurophysiology or in cognitive science will be appreciated. He/she will have frequent missions (up to a few weeks) in partners laboratories (in France and abroad) : good English skills are necessary. Duration : 1 year(s) Laboratory : IXL, CNRS UMR 5818, ENSEIRB-Universit? Bordeaux 1 (Laboratoire d'?tudes de l'int?gration des composants et syst?mes ?lectroniques) 351 cours de la Lib?ration, 33405 Talence, France. http://www.ixl.fr/ Contact : Pr Sylvie RENAUD +33 540002796 renaud at ixl.fr From saighi at ixl.fr Thu Apr 6 06:05:31 2006 From: saighi at ixl.fr (Sylvain SAIGHI) Date: Thu, 06 Apr 2006 12:05:31 +0200 Subject: Connectionists: PhD position in the field of Engineering of Neuromorphic Systems Message-ID: <4434E7EB.7000405@ixl.fr> In the framework of the European Union's Marie Curie network for human resources and mobility activity, a new project "NeuroVers-IT" investigating Neuro-Cognitive Science and Information Technology has been set up. The project aims at collaborative, highly multidisciplinary research between 11 European well-known research institutions in the areas of neuro-/cognitive sciences/biophysics and robotics/information technologies/ mathematics. <>For this project, IXL Microelectronics Laboratory in Bordeaux, France, is looking for Early-Stage Researcher (holding a Master's degree entitling him/her to pursue a PhD degree, beginning September 2006) The ideal candidate should have a university degree in electrical engineering. An expertise in mixed-analog IC design and VHDL language, a good knowledge of spoken and written English and a strong interest in computational neurosciences are required. The project concerns the development of VLSI circuits and electronics systems of high biological relevance that emulate in real-time multi-conductances neurons and neural networks with adaptive properties. The work will be conducted at the IXL Microelectronics laboratory (www.ixl.fr ), a CNRS institution associated to ENSEIRB-Universit? Bordeaux 1. IXL is located on the Bordeaux Science campus. The PhD student will join the research group "Engineering of Neuromorphic Systems"; <>To be eligible the candidate shall not be French citizen and not have resided in France for more than 12 months in the last 3 years. For information about this position you may contact Prof. Sylvie RENAUD IXL Laboratory, CNRS, ENSEIRB, Universit? Bordeaux 1 Email: renaud at ixl.fr Tel. +33 5 4000 2796. Please send your written application including your CV and other relevant material. From fschwenker at neuro.informatik.uni-ulm.de Fri Apr 7 04:24:19 2006 From: fschwenker at neuro.informatik.uni-ulm.de (Friedhelm Schwenker) Date: Fri, 07 Apr 2006 10:24:19 +0200 Subject: Connectionists: Positions at the University of Ulm Message-ID: <443621B3.3050408@neuro.informatik.uni-ulm.de> The Institute for Neural Information Processing at the University of Ulm (Germany) is a lab with two full professors, 4 postdocs and about 20 students and researchers in different areas of neural network research. Ongoing work includes mobile autonomous robots, computer vision, neural modelling, and pattern recognition. Successful applicants will be expected to conduct research involving ? pattern recognition or sensor fusion with artificial neural networks, or ? information processing in networks of spiking neurons, or ? large associative memory systems with possible applications in autonomous vehicles, bioinformatics, medicine, speech or vision, or modelling and recognition of emotions. Candidates should have a recent PhD-degree for example in computer science, physics, mathematics or electrical engineering. Applications for PhD-work are also possible. In this case the applicants should already have some experience in one of the fields mentioned above. Two positions will become available during 2006. The appointment will be for at least 2 years. Salary will be BAT IIa (details depend on age and family status). Applications should be sent to Prof. Dr. Palm by May 05, 2006, via email. Please make sure that they are complete and in a convenient format. Prof. Dr. G?nther Palm Head of the Department of Neural Information Processing University of Ulm 89069 Ulm Germany Email: guenther.palm at uni-ulm.de URL: http://www.informatik.uni-ulm.de/neuro/ -- ---------------------------------------------------------------------- Dr. Friedhelm Schwenker University of Ulm | email: friedhelm.schwenker at uni-ulm.de Department of Neural | fax: +49-731-50-24156 Information Processing | phone: +49-731-50-24159 D-89069 Ulm (Germany) | www: http://www.informatik.uni-ulm.de/ni/mitarbeiter/FSchwenker.html ---------------------------------------------------------------------- From christian.igel at neuroinformatik.ruhr-uni-bochum.de Mon Apr 10 09:31:22 2006 From: christian.igel at neuroinformatik.ruhr-uni-bochum.de (Christian Igel) Date: Mon, 10 Apr 2006 15:31:22 +0200 Subject: Connectionists: PhD positions in theoretical cognitive science / neuroscience Message-ID: <443A5E2A.7030305@neuroinformatik.rub.de> PhD positions in theoretical cognitive science / neuroscience Institut f?r Neuroinformatik, Ruhr-Universit?t Bochum, Germany The chair in Theoretical Biology at the Ruhr-University Bochum is seeking applications for doctoral studentships in the areas of theoretical cognitive science and theoretical neuroscience. Our research program is centered on embodied and situated cognition and is based on the theoretical framework of Dynamical Systems Theory, of which Dynamical Field Theory is a particular branch that emphasizes the neuronal foundations of these concepts. Doctoral students will select a research topic within three areas: (a) serial order; (b) learning theory; (c) multi-degree of freedom motor control. All projects will have a core modelling component, around which new theoretical ideas will be developed, but will also involve close collaboration with associated experimental research groups. Additional background information is available at http://www.neuroinformatik.rub.de/thbio/group/cognition/index.html The positions will be paid at the BATIIa/2 level (approximately 1800 Euro/month depending on age and family status). Applications including curriculum vitae and transcripts, as well, whenever possible, the name of one or more references are welcome. Application via email to Institut at neuroinformatik.ruhr-uni-bochum.de is encouraged. Alternatively send your material to Prof. Dr. Gregor Sch?ner, Institut f?r Neuroinformatik, Ruhr-Universit?t Bochum, 44780 Bochum, Germany. The selection process will begin May 1, 2006 and will continue until the positions are filled. Prof. Dr. Gregor Sch?ner Lehrstuhl Theoretische Biologie Institut f?r Neuroinformatik Ruhr-Universit?t Bochum 44780 Bochum, Germany tel: +49-234-322-7965 (office) +49-234-6406461 (home) fax: +49-234-321-4209 email: Gregor.Schoener at neuroinformatik.ruhr-uni-bochum.de http://www.neuroinformatik.rub.de/thbio/members/profil/Schoener/index.html From terry at salk.edu Mon Apr 10 18:34:33 2006 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 10 Apr 2006 15:34:33 -0700 Subject: Connectionists: NEURAL COMPUTATION 18:5 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 18, Number 5 - May 1, 2006 Article Singularities Affect Dynamics of Learning in Neuromanifolds Shun-ichi Amari, Hyeyoung Park, and Tomoro Ozeki Letters How Noise Affects the Synchronization Properties of Recurrent Networks of Inhibitory Neurons Nicolas Brunel and David Hansel Analysis of Synchronization between Two Modules of Pulse Neural Networks with Excitatory and Inhibitory Connections Takashi Kanamaru A Sensorimotor Map: Modulating Lateral Interactions for Anticipation and Planning Marc Toussaint Coupling of Neural Computation with Physical Computation for Stable Dynamic Biped Walking Control Tao Geng, Bernd Porr and Florentin Woergoetter A Set Probability Technique for Detecting Relative Time Order Across Multiple Neurons Anne C. Smith and Peter Smith Payoff-Monotonic Game Dynamics and the Maximum Clique Problem Marcello Pelillo and Andrea Torsello ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2006 - VOLUME 18 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $154 $90 $96.30 Institution $730 $781.10 $784 $657 $702.99 * 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 epitkane at cs.helsinki.fi Fri Apr 7 08:04:27 2006 From: epitkane at cs.helsinki.fi (Esa A Pitkanen) Date: Fri, 07 Apr 2006 15:04:27 +0300 Subject: Connectionists: CFP: Probabilistic Modeling and Machine Learning in Structural and Systems Biology Message-ID: <4436554B.1070104@cs.helsinki.fi> CALL FOR PAPERS Workshop on Probabilistic Modeling and Machine Learning in Structural and Systems Biology http://www.cs.helsinki.fi/group/bioinfo/events/pmsb06/ Tuusula, Finland, 17-18 June 2006 Deadline for submission: April 23, 2006 Motivation The ever-ongoing growth in the amount of biological data, the development of genome-wide measurement technologies, and the shift from the study of individual genes to systems view all contribute to the need to develop computational techniques for learning models from data. At the same time, the increase in available computational resources has enabled new, more realistic modeling methods to be adopted. In bioinformatics, most of the targets of interest deal with complex structured objects: sequences, 2D and 3D structures or interaction networks. In many cases these structures are naturally described by probabilistic graphical models, such as Hidden Markov Models, Conditional Random Fields or Bayesian Networks. Recently, approaches that combine Support Vector Machines and probabilistic models have been introduced (Fisher kernels, Max-margin Markov Networks, Structured SVM). These techniques benefit from efficient convex optimization approaches and thus are potentially well-scalable to large problems in bioinformatics. The increasing amount of high-throughput experimental data begins to enable the use of these advanced modelling methods in bioinformatics and systems biology. At the same time new computational challenges emerge. Statistical methods are required to process the data so that underlying potentially complex statistical patterns can be discerned from spurious patterns created by random effects. At its simplest this problem calls for data normalization and statistical hypothesis testing, in the more general case, one is required to select a model (e.g. gene network) that best explains the data. Objective The aim of this workshop is to provide a broad look at the state of the art in the probabilistic modeling and machine learning methods involving biological structures and systems, and to bring together method developers and experimentalists working with the problems. We encourage submissions bringing forward methods for discovering complex structures (e.g. interaction networks, molecule/cellular structures) and methods supporting genome-wide data analysis. A non-exhaustive list of topics suitable of this workshop: Methods * Algorithms * Bayesian Methods * Data integration/fusion * Feature/subspace selection * High-throughput methods * Kernel Methods * Machine Learning * Probabilistic Inference * Structured output prediction Applications * Sequence Annotation * Gene Expression * Gene Networks * Gene Prediction * Metabolic Profiling * Metabolic Reconstruction * Protein Structure Prediction * Protein Function Prediction * Protein-protein interaction networks The workshop is organized by the European Network of Excellence PASCAL (Pattern Analysis, Statistical Modelling and Computational Learning) and belongs to the thematic programme on 'Learning with Complex and Structured Outputs'. The workshop is immediately followed by the International Specialised Symposium on Yeasts (ISSY25, June 18-21 2006) that has the theme 'Systems biology of Yeast - From Models to Applications'. Submissions We invite to submit an extended abstract of maximum four pages, formatted according to the Springer Lecture Notes in Computer Science style, to the email address juho.rousu at cs.helsinki.fi Selected papers from the workshop will be published in BMC Bioinformatics special issue. BMC Bioinformatics has impact factor 5.42, which makes it the second highest ranked bioinformatics journal. Important dates * April 23, 2006: Abstract submission deadline * May 7, 2006: Notification of acceptance * May 31, 2006: Final version due * June 17-18, 2006: Workshop Invited Speakers (confirmed) * Tommi Jaakkola, MIT * Koji Tsuda, CBRC / AIST, Japan Organizing Committee * Florence d'Alch?-Buc, Universit? d'Evry-Val d'Essonne * Jaakko Astola, Tampere University of Technology * Nello Cristianini, UC Davis / University of Bristol * Liisa Holm, University of Helsinki * Mark Girolami, University of Glasgow * Samuel Kaski, Helsinki University of Technology * Matej Oresic, Technical Research Centre of Finland * Juho Rousu, University of Helsinki * Esko Ukkonen, Helsinki Institute for Information Technology * Jean-Philippe Vert, Ecole des Mines de Paris Local Organization * Juho Rousu, University of Helsinki * Samuel Kaski, Helsinki University of Technology * Esko Ukkonen, Helsinki Institute for Information Technology * Esa Pitk?nen, University of Helsinki, workshop secretary Location * The workshop will be held in Conference Hotel Gustavelund, 15 minute trip from Helsinki-Vantaa airport. -------------- next part -------------- CALL FOR PAPERS Workshop on Probabilistic Modeling and Machine Learning in Structural and Systems Biology http://www.cs.helsinki.fi/group/bioinfo/events/pmsb06/ Tuusula, Finland, 17-18 June 2006 Motivation The ever-ongoing growth in the amount of biological data, the development of genome-wide measurement technologies, and the shift from the study of individual genes to systems view all contribute to the need to develop computational techniques for learning models from data. At the same time, the increase in available computational resources has enabled new, more realistic modeling methods to be adopted. In bioinformatics, most of the targets of interest deal with complex structured objects: sequences, 2D and 3D structures or interaction networks. In many cases these structures are naturally described by probabilistic graphical models, such as Hidden Markov Models, Conditional Random Fields or Bayesian Networks. Recently, approaches that combine Support Vector Machines and probabilistic models have been introduced (Fisher kernels, Max-margin Markov Networks, Structured SVM). These techniques benefit from efficient convex optimization approaches and thus are potentially well-scalable to large problems in bioinformatics. The increasing amount of high-throughput experimental data begins to enable the use of these advanced modelling methods in bioinformatics and systems biology. At the same time new computational challenges emerge. Statistical methods are required to process the data so that underlying potentially complex statistical patterns can be discerned from spurious patterns created by random effects. At its simplest this problem calls for data normalization and statistical hypothesis testing, in the more general case, one is required to select a model (e.g. gene network) that best explains the data. Objective The aim of this workshop is to provide a broad look at the state of the art in the probabilistic modeling and machine learning methods involving biological structures and systems, and to bring together method developers and experimentalists working with the problems. We encourage submissions bringing forward methods for discovering complex structures (e.g. interaction networks, molecule/cellular structures) and methods supporting genome-wide data analysis. A non-exhaustive list of topics suitable of this workshop: Methods * Algorithms * Bayesian Methods * Data integration/fusion * Feature/subspace selection * High-throughput methods * Kernel Methods * Machine Learning * Probabilistic Inference * Structured output prediction Applications * Sequence Annotation * Gene Expression * Gene Networks * Gene Prediction * Metabolic Profiling * Metabolic Reconstruction * Protein Structure Prediction * Protein Function Prediction * Protein-protein interaction networks The workshop is organized by the European Network of Excellence PASCAL (Pattern Analysis, Statistical Modelling and Computational Learning) and belongs to the thematic programme on 'Learning with Complex and Structured Outputs'. The workshop is immediately followed by the International Specialised Symposium on Yeasts (ISSY25, June 18-21 2006) that has the theme 'Systems biology of Yeast - From Models to Applications'. Submissions We invite to submit an extended abstract of maximum four pages, formatted according to the Springer Lecture Notes in Computer Science style, to the email address juho.rousu at cs.helsinki.fi Selected papers from the workshop will be published in BMC Bioinformatics special issue. BMC Bioinformatics has impact factor 5.42, which makes it the second highest ranked bioinformatics journal. Important dates * April 23, 2006: Abstract submission deadline * May 7, 2006: Notification of acceptance * May 31, 2006: Final version due * June 17-18, 2006: Workshop Invited Speakers (confirmed) * Tommi Jaakkola, MIT * Koji Tsuda, CBRC / AIST, Japan Organizing Committee * Florence d'Alch?-Buc, Universit? d'Evry-Val d'Essonne * Jaakko Astola, Tampere University of Technology * Nello Cristianini, UC Davis / University of Bristol * Liisa Holm, University of Helsinki * Mark Girolami, University of Glasgow * Samuel Kaski, Helsinki University of Technology * Matej Oresic, Technical Research Centre of Finland * Juho Rousu, University of Helsinki * Esko Ukkonen, Helsinki Institute for Information Technology * Jean-Philippe Vert, Ecole des Mines de Paris Local Organization * Juho Rousu, University of Helsinki * Samuel Kaski, Helsinki University of Technology * Esko Ukkonen, Helsinki Institute for Information Technology * Esa Pitk?nen, University of Helsinki, workshop secretary Location * The workshop will be held in Conference Hotel Gustavelund, 15 minute trip from Helsinki-Vantaa airport. From knorman at Princeton.EDU Mon Apr 10 12:29:35 2006 From: knorman at Princeton.EDU (Ken Norman) Date: Mon, 10 Apr 2006 12:29:35 -0400 Subject: Connectionists: Postdoctoral position, Princeton Computational Memory Lab Message-ID: <443A87EF.8080002@princeton.edu> Dear connectionists, I have a job opening for a postdoctoral researcher in my laboratory (job description appended below). In my lab, we use connectionist models of hippocampus and cortex to generate predictions about behavioral memory performance, and also about how neural representations change (over short and long time scales) during learning and memory tasks; we test these predictions in both normal and amnesic subjects. We are particularly interested in achieving better integration between neural network models and neuroimaging data (e.g., by using pattern classification methods, applied to fMRI and EEG data, to decode what information is represented in the brain and how these representations change over time). Please email me (knorman at princeton.edu) if you have any questions. Best! Ken Norman here is the official job description: RESEARCH ASSOCIATE, PRINCETON UNIVERSITY. A postdoctoral position is available in the Psychology Department at Princeton University. The project, led by Dr. Ken Norman, uses computational models, combined with behavioral and fMRI studies of brain damaged patients and normal subjects, to study the neural mechanisms of episodic memory. REQUIREMENTS: completed Ph.D. and strong background in the cognitive and/or computational neuroscience of memory. Submit CVs to Carol Agans, Department of Psychology, Green Hall, Princeton University, Princeton, NJ 08540 or by email to agans at princeton.edu. For more information about Dr. Norman's Computational Memory Lab, please visit http://compmem.princeton.edu. For information about applying to Princeton, please link to http://web.princeton.edu/sites/dof/ApplicantsInfo.htm.PU/EO/AAE From neuralassembly at yahoo.co.jp Tue Apr 11 12:16:42 2006 From: neuralassembly at yahoo.co.jp (Takashi KANAMARU) Date: Wed, 12 Apr 2006 01:16:42 +0900 (JST) Subject: Connectionists: Two papers on periodic or chaotic synchronization in PNN Message-ID: <20060411161642.56644.qmail@web3411.mail.bbt.yahoo.co.jp> Dear all, I would like to announce two papers on periodic or chaotic synchronization in PNN are available from the following page. http://brain.cc.kogakuin.ac.jp/~kanamaru/research/ Takashi Kanamaru, Analysis of synchronization between two modules of pulse neural networks with excitatory and inhibitory connections, Neural Computation, vol.18, no.5 (2006) pp.1111-1131. http://brain.cc.kogakuin.ac.jp/~kanamaru/research/kanamaru-nc2006.pdf Abstract To study the synchronized oscillations among distant neurons in the visual cortex, the synchronization between two modules of pulse neural networks was analyzed using the phase response function. It was found that the inter-module connections from excitatory to excitatory ensembles tend to stabilize the anti-phase synchronization, and that the inter-module connections from excitatory to inhibitory ensembles tend to stabilize the in-phase synchronization. It was also found that the inter-module synchronization was more noticeable when the inner-module synchronization was weak. Takashi Kanamaru, Blowout bifurcation and on-off intermittency in pulse neural networks with multiple modules, International Journal of Bifurcation and Chaos, vol.16, no.11 (2006) (in press). http://brain.cc.kogakuin.ac.jp/~kanamaru/research/kanamaru-ijbc2006.pdf Abstract To study the mechanism by which high-dimensional chaos emerges in neural systems, the synchronization of chaotic firings in class 1 pulse neural networks composed of excitatory and inhibitory ensembles was analyzed. In the system with two modules (i.e., two pulse neural networks), blowout bifurcation and on-off intermittency were observed when the inter-module connection strengths were reduced from large values. In the system with three modules, rearrangement of synchronized clusters and chaotic itinerancy were observed. Such dynamics may be one of the mechanisms through which high-dimensional chaos is generated in neural systems. Best regards, Takashi KANAMARU http://brain.cc.kogakuin.ac.jp/~kanamaru/ Department of Innovative Mechanical Engineering, Faculty of Global Engineering, Kogakuin University, 2665-1 Nakano, Hachioji-city, Tokyo 192-0015, Japan From fschwenker at neuro.informatik.uni-ulm.de Tue Apr 11 08:46:36 2006 From: fschwenker at neuro.informatik.uni-ulm.de (Friedhelm Schwenker) Date: Tue, 11 Apr 2006 14:46:36 +0200 Subject: Connectionists: Positions at the University of Ulm Message-ID: <443BA52C.8080907@neuro.informatik.uni-ulm.de> Two post-doc (or PhD-student) positions will become available during 2006 at the Department of Neural Information Processing at the University of Ulm. The Institute for Neural Information Processing at the University of Ulm (Germany) is a lab with two full professors, 4 postdocs and about 20 students and researchers in different areas of neural network research. Ongoing work includes mobile autonomous robots, computer vision, neural modelling, and pattern recognition. Successful applicants will be expected to conduct research involving ? pattern recognition or sensor fusion with artificial neural networks, or ? information processing in networks of spiking neurons, or ? large associative memory systems with possible applications in autonomous vehicles, bioinformatics, medicine, speech or vision, or modelling and recognition of emotions. Candidates should have a recent PhD-degree for example in computer science, physics, mathematics or electrical engineering. Applications for PhD-work are also possible. In this case the applicants should already have some experience in one of the fields mentioned above. The appointment will be for at least 2 years. Salary will be BAT IIa (details depend on age and family status). Applications should be sent to Prof. Dr. Palm by May 05, 2006, via email. Please make sure that they are complete and in a convenient format. Prof. Dr. G?nther Palm Head of the Department of Neural Information Processing University of Ulm 89069 Ulm Germany Email: guenther.palm at uni-ulm.de URL: http://www.informatik.uni-ulm.de/neuro/ - From mark.plumbley at elec.qmul.ac.uk Tue Apr 11 07:39:35 2006 From: mark.plumbley at elec.qmul.ac.uk (Mark Plumbley) Date: Tue, 11 Apr 2006 12:39:35 +0100 Subject: Connectionists: PhD Study in Centre for Digital Music, Queen Mary University of London Message-ID: <9D47A2D30B0BFB4C920786C25EC693456DD23F@staff-mail.vpn.elec.qmul.ac.uk> Dear Connectionists, Apologies for cross-posting: please forward to anyone in your group who may be interested. Yes I know "digital music" may not sound very connectionist at first, but we have a particular interest in techniques such as independent component analysis (ICA) and Bayesian inference methods applied to musical audio analysis and separation, as well as in biologically-inspired audio processing, so applications anyone interested in PhD research study in those areas would be most welcome. Also, for those of you near to London, we will be taking part in our department's Research Open Day on 27 April 2006. For more information and registration instructions, see http://www.elec.qmul.ac.uk/opendayposter/. Best wishes, Mark Plumbley ------------ PhD Study in Centre for Digital Music, Queen Mary University of London The Centre for Digital Music at Queen Mary University of London is a world-leading research group in the field of Music & Audio Technology. Our research covers everything in digital music and audio: from analysis, understanding and retrieval to delivery, synthesis and sound rendering. We seek not only to investigate new applications of digital signal processing (DSP), but also to push forward the frontiers of DSP itself. Applications are invited for PhD research study in any of our areas of interest. Possible topic areas might include: automatic music transcription; harmony analysis; auditory scene analysis; beat tracking & rhythm analysis; blind source separation & independent component analysis (ICA); joint audio/video tracking and transcription; A/D & D/A conversion; sigma delta modulation; scalable audio codecs; object based coding; sparse representations & sparse coding; music information retrieval; semantic markup, musical metadata & MPEG7 applications; audio effects; 3D sound & multi-loudspeaker rendering systems; intelligent microphone arrays; automatic accompaniment; interactive performance/internet jamming; interactive compositional tools; biologically inspired audio processing; and pervasive audio ("my music wherever I am"). We have recently invested ?300k in a new state-of-the-art audio listening facility, and we are keen to encourage at least one project in the area of 3D sound which would be allied to this new facility. For more information about the Centre for Digital Music and our research, see http://www.elec.qmul.ac.uk/digitalmusic/ Funding: The Centre for Digital Music is part of the Department of Electronic Engineering, which has a number of EPSRC-funded Research Studentships that cover fees and maintenance for UK students, or fees-only for EU students. One additional Studentship is available that can cover fees and maintenance for a UK or EU student. There is always strong competition for Research Studentships, so early application is recommended. Applications are also welcomed from self-funded students. Application Applicants should follow the guidelines that can be found at http://www.elec.qmul.ac.uk/study/phd/res-stud.htm For informal enquiries, please contact Dr Mark Plumbley (mark.plumbley at elec.qmul.ac.uk) --- Dr Mark D Plumbley Centre for Digital Music Department of Electronic Engineering Queen Mary University of London Mile End Road, London E1 4NS, UK Tel: +44 (0)20 7882 7518 Fax: +44 (0)20 7882 7997 Email: mark.plumbley at elec.qmul.ac.uk http://www.elec.qmul.ac.uk/people/markp/ From ckiw at inf.ed.ac.uk Wed Apr 12 13:24:59 2006 From: ckiw at inf.ed.ac.uk (Chris Williams) Date: Wed, 12 Apr 2006 18:24:59 +0100 (BST) Subject: Connectionists: WORKSHOP: Mathematical Models of Development and Learning in the Nervous System Message-ID: Workshop on Mathematical Models of Development and Learning in the Nervous System University of Edinburgh, UK 21-22 July 2006 Call for Participation The aim of this workshop is to bring together mathematical modellers and key experimenters in the field of neural development and learning with the objective of: * Exposing new experimental areas that would benefit from mathematical methods; * Identifying innovative applications of mathematics to modelling problems; and * Mapping new frontiers of research. The workshop will consist of around twelve invited talks and two discussion sessions. Expected lecturers include Gordon Arbuthnott (University of Otago, New Zealand) Peter Dayan (Gatsby Computational Neuroscience Unit, UCL) Stephen Eglen (University of Cambridge) Marcus Frean (Victoria University of Wellington, New Zealand) Andrew Gillies (University of Edinburgh) Geoff Goodhill (University of Queensland, Australia) Bruce Graham (University of Stirling) Martin Simmen (University of Edinburgh) Arjen van Ooyen (Free University of Amsterdam, Netherlands) Christoph von der Malsburg (Bochum University, Germany) David Willshaw (University of Edinburgh) The meeting is limited to around 50 attendees in order to maintain its workshop character. Applications are invited now from people wishing to participate in the workshop. Some financial support is available for applicants from the UK. The deadline for applications is 1 May 2006. See http://www.icms.org.uk/meetings/2006/nervous/index.html for further details and the online application form. The meeting is being held as part of the International Centre for Mathematical Sciences (ICMS) 2006 workshop programme and will take place directly after the Computational Neuroscience (CNS*2006) conference. The workshop is made possible by grants awarded to ICMS from EPSRC Mathematical Sciences Programme, the Scottish Higher Education Funding Council and the London Mathematical Society. The meeting is also directly supported by the Institute for Adaptive and Neural Computation and the School of Informatics of the University of Edinburgh. Organizers: Chris Williams (University of Edinburgh) Peter Dayan (Gatsby Computational Neuroscience Unit, UCL) Andrew Gillies (University of Edinburgh) David Sterratt (University of Edinburgh) From ted.carnevale at yale.edu Wed Apr 12 22:02:16 2006 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Wed, 12 Apr 2006 22:02:16 -0400 Subject: Connectionists: more talks and tutorials at the NEURON Simulator Meeting Message-ID: <443DB128.1050707@yale.edu> Register now for the NEURON Simulator Meeting, which will be held May 5-7 at UT Austin--see http://www.utexas.edu/neuroscience/NEURON2006/nsm2006.html The registration deadline is Friday, April 21. Here are two more reasons to attend: Talk: "Rule-based artificial cell (RBAC) models in NEURON" Speaker: Bill Lytton There are a variety of artificial cell models available in NEURON. These have the advantage of using forward prediction of spike times in order to avoid the overhead of integration. Additionally, they can be used in hybrid networks with compartmental models in order to run large models at vastly increased speed. We have developed new artificial neuron models that use rule sets to determine firing based on different types of inputs and several internal state variables. In addition to speed, this approach cleanly isolates the various synaptic and internal state variables so that they can be manipulated in a way that is difficult in the complex parameterizations of full multi-compartment/multi-ion-channel/ multi-synapse models. The basic rule remains the same as that of the integrate-and-fire model: fire when the state variable exceeds a fixed threshold. Additional rules were added to provide adaptation, bursting, depolarization blockade, Mg-sensitive NMDA conductance, anode-break depolarization, and others. The implementation is event driven, providing additional speed-up by avoiding numerical integration. Tutorial: "Recent advances in the CellBuilder: managing models with spatially varying parameters" Speaker: Ted Carnevale This tutorial will show how to use the CellBuilder, one of NEURON's GUI tools, to construct and manage neuron models in which one or more parameters vary with location as functions of an independent variable. This recent enhancement graphically supports the idiom forsec subset for (x, 0) { rangevar_suffix(x) = f(p(x)) } where rangevar_suffix(x) is the parameter of interest, p(x) is a domain function over the subset, and f is any expression. Built-in domain functions are arc (path) distance from the soma, radial distance from a point, and distance along an axis in the xy plane. --Ted From deneve at isc.cnrs.fr Thu Apr 13 12:37:41 2006 From: deneve at isc.cnrs.fr (deneve@isc.cnrs.fr) Date: Thu, 13 Apr 2006 18:37:41 +0200 (CEST) Subject: Connectionists: Postdoctoral Position in the Group for Neural Theory, Paris Message-ID: <45425.193.52.23.5.1144946261.squirrel@webmail.isc.cnrs.fr> A postdoctoral research position is available in the Group for Neural Theory in Ecole Normale Sup?rieure Paris, for a project funded by a Marie Curie Team of Excellence grant. The overall theme of the project is "Bayesian inference and neural dynamics", and the research will involve building and analyzing probabilistic treatments of representation, inference and learning in biophysical models of cortical neuron and circuits. To do so we will integrate complementary computational neuroscience approaches. The first studies neurons and neural networks as biophysical entities. The second reinterpret cognitive and neural processes as bayesian computations. The faculty of this group includes Misha Tsodyks, Boris Gutkin, Sophie Deneve and Rava Da Silvera. It is part of the Department of Cognitive Science in Ecole Normale Sup?rieure, regrouping major scientists in computational Neuroscience, Brain imaging, Psychology, Philosophy, and Mathematics. We are situated in central Paris, at a walking distance to top scientific research and educational institutions. The positions are for two years duration, with attractive salaries, including mobility allowance if applicable. Generous travel support will be provided. Candidates should have 1- A strong mathematical/biophysical background previously applied to neuroscience, 2- Demonstrable interest in experimental collaborations. 3- Good communication skills. Candidates should send a CV, a 1 page research project and the address of two referees, to Sophie Deneve (Sophie.Deneve at ens.fr) and Boris Gutkin (Boris.Gutkin at ens.fr). For further information please contact Sophie Deneve or Boris Gutkin. From deneve at isc.cnrs.fr Thu Apr 13 13:06:11 2006 From: deneve at isc.cnrs.fr (deneve@isc.cnrs.fr) Date: Thu, 13 Apr 2006 19:06:11 +0200 (CEST) Subject: Connectionists: PhD Student Position-Group for Neural Theory in Paris Message-ID: <46093.193.52.23.5.1144947971.squirrel@webmail.isc.cnrs.fr> A PhD student position is available in the Group for Neural Theory in Ecole Normale Sup?rieure Paris, for a project funded by a Marie Curie Team of Excellence grant. The overall theme of the project is "Bayesian inference and neural dynamics", and the research will involve building and analyzing probabilistic treatments of representation, inference and learning in biophysical models of cortical neuron and circuits. The faculty of this group includes Misha Tsodyks, Boris Gutkin, Sophie Deneve and Rava Da Silvera. It is part of the Department of Cognitive Science in Ecole Normale Sup?rieure, a unique teaching and research institution regrouping major scientists in computational Neuroscience, Brain imaging, Psychology, Philosophy, and Mathematics. We are situated in central Paris, at a walking distance to top scientific research and educational institutions. There will be ample opportunities to follow graduate classes in the field of Theoretical Neuroscience. The position is for three years duration, starting in September 2006. It has an attractive salary, including mobility allowance if applicable. Generous travel support will be provided. Candidates should have 1- A strong background in mathematics or physics and strong interest for Neuroscience. Or 2- A strong neuroscience background and good basis in math and/or biophysics. 3- Demonstrable interest in experimental collaborations. 4- Good communication skills. Candidates should send a CV, a 1 page research project and the address of two referees to Sophie Deneve (Sophie.Deneve at ens.fr) and Boris Gutkin (Boris.Gutkin at ens.fr). From mpolycar at ucy.ac.cy Thu Apr 13 16:55:46 2006 From: mpolycar at ucy.ac.cy (Marios M. Polycarpou) Date: Thu, 13 Apr 2006 23:55:46 +0300 Subject: Connectionists: IEEE Transactions on Neural Networks, vol. 16, No. 2, March 2006 Message-ID: <039701c65f3c$a38385e0$04172ac2@IBM36165813261> Dear Colleagues, The following articles appear in the latest issue of IEEE Transactions on Neural Networks vol.17, no.2, March 2006. The articles can be retrieved on IEEE Xplore: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=72 Marios M. Polycarpou IEEE-TNN Editor-in-Chief email: ieeetnn at ucy.ac.cy ++++++++++++++++++++++++++++++++++++++ A node pruning algorithm based on a Fourier amplitude sensitivity test method Lauret, P.; Fock, E.; Mara, T.A. Pages: 273- 293 Generalizing self-organizing map for categorical data Chung-Chian Hsu Pages: 294- 304 The parameterless self-organizing map algorithm Berglund, E.; Sitte, J. Pages: 305- 316 Implementing online natural gradient learning: problems and solutions Weishui Wan Pages: 317- 329 The linear separability problem: some testing methods Elizondo, D. Pages: 330- 344 Modulated Hebb-Oja learning Rule-a method for principal subspace analysis Jankovic, M.V.; Ogawa, H. Pages: 345- 356 Toward the training of feed-forward neural networks with the D-optimum input sequence Witczak, M. Pages: 357- 373 Orthogonal search-based rule extraction (OSRE) for trained neural networks: a practical and efficient approach Etchells, T.A.; Lisboa, P.J.G. Pages: 374- 384 A bidirectional heteroassociative memory for binary and grey-level patterns Chartier, S.; Boukadoum, M. Pages: 385- 396 Basins of attraction in fully asynchronous discrete-time discrete-state dynamic networks Bahi, J.M.; Contassot-Vivier, S. Pages: 397- 408 Dynamics analysis and analog associative memory of networks with LT neurons Huajin Tang; Tan, K.C.; Teoh, E.J. Pages: 409- 418 Blind estimation of channel parameters and source components for EEG signals: a sparse factorization approach Yuanqing Li; Cichocki, A.; Amari, S.-I. Pages: 419- 431 Adaptive wavelet neural network control with hysteresis estimation for piezo-positioning mechanism Faa-Jeng Lin; Shieh, H.-J.; Po-Kai Huang Pages: 432- 444 Modeling and inverse controller design for an unmanned aerial vehicle based on the self-organizing map Jeongho Cho; Principe, J.C.; Erdogmus, D.; Motter, M.A. Pages: 445- 460 Neural-network-based adaptive UPFC for improving transient stability performance of power system Mishra, S. Pages: 461- 470 Sparse bayesian kernel survival analysis for modeling the growth domain of microbial pathogens Cawley, G.C.; Talbot, N.L.C.; Janacek, G.J.; Peck, M.W. Pages: 471- 481 A neuromorphic depth-from-motion vision model with STDP adaptation Zhijun Yang; Murray, A.; Worgotter, F.; Cameron, K.; Boonsobhak, V. Pages: 482- 495 Neuromorphic walking gait control Still, S.; Hepp, K.; Douglas, R.J. Pages: 496- 508 Adaptive neural network control for a class of low-triangular-structured nonlinear systems Hongbin Du; Huihe Shao; Pingjing Yao Pages: 509- 514 Computation of Adalines' sensitivity to weight perturbation Xiaoqin Zeng; Yingfeng Wang; Kang Zhang Pages: 515- 519 Associative memory design for 256 gray-level images using a multilayer neural network Costantini, G.; Casali, D.; Perfetti, R. Pages: 519- 522 Convergence of gradient method with momentum for two-Layer feedforward neural networks Naimin Zhang; Wei Wu; Gaofeng Zheng Pages: 522- 525 On the new method for the control of discrete nonlinear dynamic systems using neural networks Hua Deng; Han-Xiong Li Pages: 526- 529 Batch map extensions of the kernel-based maximum entropy learning rule Gautama, T.; Van Hulle, M.M. Pages: 529- 532 Comments on "The 1993 DIMACS graph coloring Challenge" and "Energy function-based approaches to graph Coloring" Jing Liu; Weicai Zhong; Licheng Jiao Pages: 533 From Randy.OReilly at colorado.edu Sat Apr 15 01:47:38 2006 From: Randy.OReilly at colorado.edu (Randall C. O'Reilly) Date: Fri, 14 Apr 2006 23:47:38 -0600 Subject: Connectionists: Fwd: Computational Cognitive Neuroscience: Call for Abstracts Message-ID: <200604142347.38871.Randy.OReilly@colorado.edu> ~ Call for Abstracts ~ 2ND ANNUAL CONFERENCE ON COMPUTATIONAL COGNITIVE NEUROSCIENCE www.ccnconference.org To be held in conjunction with the 2006 PSYCHONOMIC SOCIETY CONFERENCE, November 16-19, 2006 at the Hilton Americas hotel in Houston, TX. * CONFERENCE DATES: Wed-Thu November 15 & 16, 2006 The inaugural CCNC 2005 meeting held prior to Society for Neuroscience (SfN) in Washington, DC was a great success, with approximately 250 attendees, 60 presented posters, and strongly positive reviews. In future years, it will continue to be held on a rotating basis with other meetings such as (tentative list): Cognitive Neuroscience Society (CNS), Organization for Human Brain Mapping (OHBM), Cognitive Science Society (CogSci), Neural Information Processing Systems (NIPS), and Computational and Systems Neuroscience (COSYNE). ____________________________________________________________________________ * DEADLINE FOR SUBMISSION OF ABSTRACTS: June 3, 2006 Abstracts to be submitted online via the website: www.ccnconference.org. Notice will be given by early May when the online submission form becomes operational. Like last year, there will be two categories of submissions: -Poster only -Poster, plus short talk (15 min) to highlight the poster Abstracts should be limited to 250 words. Women and underrepresented minorities are especially encouraged to apply. Reviewing for posters will be inclusive and only to ensure appropriateness to the meeting. Short talks will be selected on the basis of research quality, relevance to conference theme, and expected accessibility in a talk format. Abstracts not selected for short talks will still be accepted as posters as long as they meet appropriateness criteria. * NOTIFICATION OF ACCEPTANCE: July 1, 2005. __________________________________________________________________________ Preliminary Program: * 2006 Keynote Speakers (confirmed): Mike Kahana, University of Pennsylvania Mark Seidenberg, University of Wisconsin Madison * 3-4 Symposia, selected from submitted proposals, that will be discussion oriented and include a mixture of modelers and non-modelers, all focused on a common theme or issue. * 12 short talks featuring selected posters * Poster sessions ____________________________________________________________________________ 2006 Planning Committee: Suzanna Becker, McMaster University Jonathan Cohen, Princeton University Yuko Munakata, University of Colorado, Boulder David Noelle, Vanderbilt University Randall O'Reilly, University of Colorado, Boulder Maximilian Riesenhuber, Georgetown University Medical Center Executive Organizer: Thomas Hazy, University of Colorado, Boulder For more information and to sign up for the mailing list visit: www.ccnconference.org From otterlo at cs.utwente.nl Thu Apr 13 10:09:23 2006 From: otterlo at cs.utwente.nl (Martijn van Otterlo) Date: Thu, 13 Apr 2006 16:09:23 +0200 Subject: Connectionists: Relational RL Survey Message-ID: <443E5B93.8070209@cs.utwente.nl> Dear reader, A comprehensive survey of relational reinforcement learning is available from my webpage: "A Survey of Reinforcement Learning in Relational Domains". M. van Otterlo -- TR-CTIT-05-31 - (70pp) CTIT Technical Report Series ISSN 1381-3625 Abstract. Reinforcement learning has developed into a primary approach for learning control strategies for autonomous agents. However, most of the work has focused on the algorithmic aspect, i.e. various ways of computing value functions and policies. Usually the representational aspects were limited to the use of attribute-value or propositional languages to describe states, actions etc. A recent direction -- under the general name of relational reinforcement learning -- is concerned with upgrading the representation of reinforcement learning methods to the first-order case, being able to speak, reason and learn about objects and relations between objects. This survey aims at presenting an introduction to this new field, starting from the classical reinforcement learning framework. We will describe the main motivations and challenges, and give a comprehensive survey of methods that have been proposed in the literature. The aim is to give a complete survey of the available literature, of the underlying motivations and of the implications of the new methods for learning in large, relational and probabilistic environments. Work is underway to provide an updated version soon. Any comments, suggestions, and pointers to (new) work that does not yet appear in this survey will be greatly appreciated. Regards, Martijn van Otterlo. http://www.cs.utwente.nl/~otterlo/ From BGabrys at bournemouth.ac.uk Wed Apr 12 11:48:46 2006 From: BGabrys at bournemouth.ac.uk (Bogdan Gabrys) Date: Wed, 12 Apr 2006 16:48:46 +0100 Subject: Connectionists: 4 PhD Studentships in the area of Computational Intelligence Message-ID: <5DA146E1E559B341A0C85AB49E01F22213B5F1F4@tamar.bournemouth.ac.uk> PhD Studentships Computational Intelligence Research Group (CIRG) School of Design, Engineering and Computing Bournemouth University, United Kingdom Four 3 year, fully funded PhD studentships are available on a range of exciting research projects at the Computational Intelligence Research Group (CIRG) at Bournemouth University, United Kingdom. The students will be joining a Computational Intelligence Research Group (CIRG) and will be primarily based in the School of Design, Engineering & Computing in Bournemouth but in 3 of the projects will also have an opportunity to frequently visit and work in the top R&D labs of such companies as British Telecommunications Plc, Lufthansa Systems Berlin GmbH or Degussa AG. The studentships carry a basic remuneration of ?12500 pa tax-free (with some possible higher bursaries on specific industry co-funded projects) and payment of tuition fees at home/EU rate. The successful applicants will normally need to be EU citizens though a limited number of studentships is available for outstanding non-EU candidates. For all projects applicants should have a strong mathematical background and hold a first or upper second class honours degree or equivalent in computer science, mathematics, physics, engineering, statistics or a similar discipline. Additionally the candidates should have strong programming experience using any or combination of C++, Matlab or Java. For further details please contact Prof Bogdan Gabrys, bgabrys at bournemouth.ac.uk or visit the following www pages: http://dec.bournemouth.ac.uk/staff/bgabrys/PhD_Studentships_2006.html Interested candidates should follow the application procedure listed on the University of Bournemouth web pages: http://www.bournemouth.ac.uk/thegraduateschool/phd_studentships/how_to_apply.html Further details concerning the studentships and application procedure can be also obtained from the School of DEC Research Administrator - Ms Jo Sawyer, Email: jsawyer at bournemouth.ac.uk. Tel: +44 (0)1202 965985 All the following projects are expected to start by September 2006 at the latest but all interested candidates are encouraged to apply as soon as possible. Project 1: Data Mining and Multi Level Combination for Cancellation Forecasting Prof Bogdan Gabrys (CIRG), Ms Silvia Riedel (LSB), Prof John Fletcher (BU SM School) Accurate forecasting of the demand for airline tickets is critical within revenue management applications used by large airlines like Lufthansa. In this project the information stored in the airline Passenger Name Records (PNRs) will be exploited through the use of data mining techniques and used within novel adaptable (multilevel) classifier and forecast combination framework for improvement of the cancellation forecasts and overall demand prediction quality. This is a collaborative research project between Computational Intelligence Research Group (CIRG) and Lufthansa Systems Berlin (LSB), the world leading IT service provider for the airline and aviation industry. The PhD student will have an opportunity to frequently visit and work in LSB offices in Berlin. Project 2: Self-adapting and Monitoring Soft Sensors for Process Industry Prof Bogdan Gabrys (CIRG), Dr Paul Rogers (CIRG), Dr Uwe Tanger (Degussa AG) This project will be an application driven investigation of the possible exploitation of various computational intelligence and nature-inspired techniques for development of self-aware, -monitoring, -validating and -adapting soft sensors for process industry based on a more general class of locally adaptable and highly flexible predictive models required in industrial environments. This is a collaborative research project between Computational Intelligence Research Group (CIRG) and Degussa AG, a multinational specialty chemistry company with EUR11.2 billion turn-over in 2004. As part of the project, the PhD student will have an opportunity to frequently visit and work in Degussa Labs in Germany. Project 3: Physically Inspired Artificial Learning Models Dr Dymitr Ruta (BT Intelligent Systems Labs), Prof Bogdan Gabrys (CIRG) The main aim of this research project is to explore and investigate the tremendous similarities between physical world and artificial intelligence in the context of machine learning in order to find inspirations and design the new breed of nature-inspired classification, clustering and regression techniques that would be capable of learning more efficiently from large sources of uncertain multi-type data and information. The work will include theoretical and explorative modelling in Matlab and Java addressing variety of problems in quantum computing, thermodynamics of information, Kolmogorov complexity, information uncertainty, kernel methods and many more. This is a collaborative research project between Computational Intelligence Research Group (CIRG) and British Telecommunications (BT) Intelligent Systems Labs, one the largest industrial R&D labs of this type in UK. Project 4: Using Computation Intelligence Techniques to Support Incidental Learning Michael Jones (CIRG), Prof. Bogdan Gabrys (CIRG) and Dr Paul Rogers (CIRG) Incidental Learning is a term, originating in the Computational Intelligence Research Group at Bournemouth University, which describes a novel approach to providing online learners with a more active role in the learning process. Incidental Learning involves the development of a 'cognitive assistant', which continuously filters a wide range of additional support materials (gathered from a variety of external sources) in a manner which is appropriate to the learner's current cognitive load. The focus for the proposed research is the design of the filtering process, which will use computational intelligence techniques to create a system which will classify the potential usefulness of the additional support materials, most of which will be unstructured. Statistical, machine learning, and hybrid intelligent techniques will be used in the design of the filtering system. The continuous nature of the filtering process imposes performance constraints, which will also form part of the research. Best regards, Bogdan Gabrys ---------------------------------------------------------------------------- Prof Bogdan Gabrys Computational Intelligence Research Group School of Design, Engineering & Computing Bournemouth University, Poole House Talbot Campus, Fern Barrow Poole, BH12 5BB United Kingdom Tel: +44 (0)1202 965298 Fax: +44 (0) 1202 965314 E-mail: bgabrys at bournemouth.ac.uk WWW: http://dec.bournemouth.ac.uk/staff/bgabrys/ --------------------------------------------------------------------------- From aenadekamps at xs4all.nl Fri Apr 14 04:04:11 2006 From: aenadekamps at xs4all.nl (A en A de Kamps) Date: Fri, 14 Apr 2006 10:04:11 +0200 Subject: Connectionists: Reminder: 'First Workshop on Topics of the nEUro-IT.net Roadmap' Message-ID: <000001c65f9a$079d7600$9600000a@lan> There are still some spots available at the 'First Workshop on Topics of the nEUro-IT.net Roadmap'. The topics are: Bio-inspired and evolvable hardware, Brain-Machine Interfacing, Peripheral Processing The full programme can be found below. Information page: http://www.neuro-it.net/NeuroIT/Activities/Roadmapworkshop Attending the workshop is free, but a registration is required. Please send mail to: kamps at in.tum.de Please indicate which workshop(s) you would like to attend on Friday. ---------------------Programme--------------------- First Workshop on Topics of the nEUro-IT.net Roadmap Antwerp, 21/22 April 2006 Programme Friday April 21 --Parallel Session 1: Bio-inspired and evolvable hardware-- Location: Campus Universiteit Antwerpen, Room K101, Kleine Kauwenberg, Antwerpen Presentations: 9.30 -10.00 Welcome and registration 10.00 - 10.45 Tetsuya Higuchi (AIST, Japan) The potential of evolvable hardware for semiconductor engineering 10.45 - 11.15 Break 11.15 - 12.00 Pauline Haddow (NTNU, Norway) Development and hardware design 12.00 - 12.30 Andy Tyrrell (University of York, UK) Fault-tolerance and Evolvable Hardware 12.30 - 1.30 Lunch 1.30 - 2.15 Gianluca Tempesti (EPFL Switzerland) Bio-inspired processing in molecular-scale devices 2.15 - 3.00 Jim Torresen (University of Oslo, Norway) Evolvable Hardware Supplementing the Hardware Designer 3.00 - 3.30 Break 3.30 - 4.15 Adrian Stoica, D. Keymeulen, R. Zebulum, R. Rajeshani, V. Lacayo, J. Neff, B. Meadows and S. Graves (NASA JPL, USA) Evolvable Hardware for extreme temperature and radiation environments 4.15 - 5.15 Wrap-up session 5.15 Finish '--Parallel Session 2: Brain-Machine interfacing-- Location: Campus Universiteit Antwerpen, Room K102, Kleine Kauwenberg, Antwerpen Presentations: Erik De Schutter (University of Antwerp, Belgium): Introduction and some reflections on BMI as an experimental paradigm Ad Aertsen (Bernstein Center, University of Freiburg, Germany): Inference of hand movements from population activity in monkey and human sensorimotor cortex Silvestro Micera and Paolo Dario (ARTS and CRIM Labs, Scuola Superiore Sant'Anna): Peripheral neural interfaces for the control of cybernetic hands: current activities and future perspectives Miguel Nicolelis (Duke University, USA and Brain Mind Institute, Lausanne, Switzerland): Exploring the future of neuroprosthetic research Eilon Vaadia (Hebrew University, Jerusalem, Israel): On the yellow brick road towards neural prosthesis: New neuronal representations in motor cortical fields evolve during learning --Parallel Session 3: Peripheral Processing-- Location: Campus Universiteit Antwerpen, Room K103, Kleine Kauwenberg, Antwerpen Presentations: Morning: (10.00-10.30) George Jeronimidis (Reading University) and Herbert Peremans (Universiteit Antwerpen): CICADA + CIRCE = CILIA (10.30-11.30) Stefaan Peeters and Filiep Vanpoucke (Universiteit Antwerpen): Cochlear electrode stimulating neurons (11.30-12.30) Gijs Krijnen (Universiteit Twente): MEMS arrays of hairs Afternoon: (13.30-14.30) Joachim Mogdans (Universit?t Bonn): Neural representation of hydrodynamic stimuli by the fish lateral line (14.30-15.30) Leo van Hemmen (Technische Universit?t M?nchen): Estimating position and velocity of a submerged moving object by the clawed frog Xenopus and by fish Coffe Break (16.00-17.00) Annemie Van Der Linden (Universiteit Antwerpen): In vivo high resolution MRI: an excellent tool for neurological research in small animals (17.00-18.00) Heike Scheuerpflug (European Research and Project Office): Intellectual Property Rights and EU projects -----Saturday April 22------- Location Campus Universiteit Antwerpen, Room R007, Rodestraat, 14, Antwerpen, Belgium 9.00-9.15 FET: Comments on FP7 9.15-9.30 nEUro-IT.net: Roadmap 9.30 - 10.15 Tetsuya Higuchi: Evolvable Hardware and its industrial applications 10.15 - 11.00 Adrian Stoica: Evolvable Hardware: lessons learned, challenges ahead 11.00 - 11.30 Coffee 11.30 - 12.15 Leo van Hemmen: Mechanosensory Localization: What Owls, Frogs, and Scorpions Have in Common 12.15 - 13.00 Giacomo Indiveri: Neuromorphic Address-Event Systems: Computing with spikes, in Silicon 13.00 - 13.30 Lunch 13.30 - 14.15 Miguel Nicolelis: Computing with Neural Ensembles 14.15 - 14.16 Closure From hitzler at aifb.uni-karlsruhe.de Sat Apr 15 16:14:22 2006 From: hitzler at aifb.uni-karlsruhe.de (Pascal Hitzler) Date: Sat, 15 Apr 2006 22:14:22 +0200 Subject: Connectionists: CfP: ECAI06 Workshop on Neural-Symbolic Learning and Reasoning, NeSy'06 Message-ID: <4441541E.5060403@aifb.uni-karlsruhe.de> Note: Submission deadline extended to 22nd of April! Call for Papers --------------- Second International Workshop on Neural-Symbolic Learning and Reasoning ***NeSy'06*** A Workshop at ECAI2006, Riva del Garda, Italy, 1st of August 2006 Website http://www.neural-symbolic.org/NeSy06/ Deadline for submission: 22nd of April, 2006 NeSy'05 took place at IJCAI-05, Edinburgh, Scotland, August 2005. Scope ----- Artificial Intelligence researchers continue to face huge challenges in their quest to develop truly intelligent systems. The recent developments in the field of neural-symbolic integration bring an opportunity to integrate well-founded symbolic artificial intelligence with robust neural computing machinery to help tackle some of these challenges. The Workshop on Neural-Symbolic Learning and Reasoning is intended to create an atmosphere of exchange of ideas, providing a forum for the presentation and discussion of the key topics related to neural-symbolic integration. Topics of interest include: * The representation of symbolic knowledge by connectionist systems; * Learning in neural-symbolic systems; * Extraction of symbolic knowledge from trained neural networks; * Reasoning in neural-symbolic systems; * Biological inspiration for neural-symbolic integration; * Applications in robotics, semantic web, engineering, bioinformatics, etc. Submission ---------- Researchers and practitioners are invited to submit original papers that have not been submitted for review or published elsewhere. Submitted papers must be written in English and should not exceed 6 pages in the case of research and experience papers, and 2 pages in the case of position papers (including figures, bibliography and appendices) in ECAI format. All submitted papers will be judged based on their quality, relevance, originality, significance, and soundness. Papers must be submitted directly by email in PDF format to nesy at soi.city.ac.uk Presentation ------------ Selected papers will be presented during the workshop. The workshop will include extra time for audience discussion of the presentation allowing the group to have a better understanding of the issues, challenges, and ideas being presented. Publication ----------- Accepted papers will be published in official workshop proceedings, which will be distributed during the workshop. Authors of the best papers will be invited to submit a revised and extended version of their papers to the journal of logic and computation, OUP. Important Dates --------------- Deadline for submission: 22nd of April, 2006 Notification of acceptance: 10th of May, 2006 Camera-ready paper due: 17th of May, 2006 Workshop date: 29th of August ECAI 2006 main conference dates: 28th of August to 1st of September, 2006. Workshop Organisers ------------------- Artur d'Avila Garcez (City University London, UK) Pascal Hitzler (University Karlsruhe, Germany) Guglielmo Tamburrini (Universit? di Napoli, Italy) Programme Committee (preliminary) --------------------------------- Artur d'Avila Garcez (City University London, UK) Sebastian Bader (TU Dresden, Germany) Howard Blair (Syracuse University, USA) Dov Gabbay (Kings College London, UK) Marco Gori (Univeristy of Siena, Italy) Barbara Hammer (TU Clausthal, Germany) Ioannis Hatzilygeroudis (University of Patras, Greece) Pascal Hitzler (University of Karlsruhe, Germany) Luis Lamb (Federal University of Rio Grande do Sul, Brazil) John Lloyd (The Australian National University, Australia) Vasile Palade (Oxford University, UK) Antony K. Seda (University College Cork, Ireland) Ron Sun (Rensselaer Polytechnic Institute, USA) Guglielmo Tamburrini (Universit? di Napoli Feredico II, Italy) Stefan Wermter (University of Sunderland, UK) Gerson Zaverucha (Federal University of Rio de Janeiro, Brazil) Invited speakers ---------------- Marco Gori, University of Siena, Italy Heat Kernel Learning Machines for Symbolic Problems (tentative titel) Stefan Wermter, University of Sunderland, UK Hybrid Intelligent Systems and Cognitive Robotics (tentative title) Additional Information ---------------------- Up-to-date information can be obtained from http://www.neural-symbolic.org/NeSy06/ General questions concerning the workshop should be addressed to nesy at soi.city.ac.uk. You are also invited to subscribe to the neural-symbolic integration mailing list at http://www.aifb.uni-karlsruhe.de/mailman/listinfo/nesy -- Dr. habil. Pascal Hitzler Institute AIFB, University of Karlsruhe, 76128 Karlsruhe email: hitzler at aifb.uni-karlsruhe.de fax: +49 721 608 6580 web: http://www.pascal-hitzler.de phone: +49 721 608 4751 http://www.neural-symbolic.org From dekamps at t-online.de Sun Apr 16 09:15:27 2006 From: dekamps at t-online.de (Marc de Kamps) Date: Sun, 16 Apr 2006 15:15:27 +0200 Subject: Connectionists: 4th European School of Neuro-IT and Neuroengineering, , Message-ID: <4442436F.9060400@in.tum.de> 4^th European School of Neuro-IT and Neuroengineering *Dynamics, Computation and Learning in Neural Systems* * * ** June 13-17, 2006 The University of Genova (Department of Biophysical and Electronic Engineering -- DIBE , Department of Informatics, Sistems and Telematics -- DIST , and the Faculty of Engineering, curriculum on Bioengineering), Doctorate school on Information Society and Technologies, University of Genova (ITALY), PhD Program in Bioengineering, Doctorate school on Humanoid Technologies, Italian Institute of Technology (IIT), and University of Genova (ITALY), PhD Program in Humanoid Technologies nEUro-it.net (EU network of excellence), NEUROversIT (EU Marie Curie program) *are organizing the fourth edition * *of the European Summer School of Neuro-IT and Neuroengineering. * The school, named after Massimo Grattarola who initiated the series in 2000, will take place from June 13 to June 17, 2006 at the Faculty of Engineering, University of Genoa in a beautiful historical building: Villa Giustiniani-Cambiaso The school is intended for junior and senior researchers and other professionals (doctors, engineers, biologists and psychologists etc.) working in these areas as well as for students attending faculties of engineering, medicine, biology or psychology. A total of 50 PhD students or postdocs will be admitted. Admissions will be on first-come first-serve basis. Organization and sponsorship Neuro-IT (EU network of excellence) NEUROversIT (EU Marie Curie program) University of Genova Scientific organizers: Alois Knoll (M?nchen, Germany) Marc de Kamps (M?nchen, Germany) Andreas Engel (Hamburg, Germany) Sergio Martinoia (Genova, Italy) Giulio Sandini (Genova, Italy) Vittorio Sanguineti (Genova, Italy) Goals The school will focus on a new and rapidly growing field -- the areas of neuro-information technologies (Neuro-IT) and neuroengineering where neuroscience, information technologies and robotics merge. The school will be organized and partly funded by Neuro-IT.net, and NEUROversIT, an EU-funded Marie Curie program. The 2006 edition of the school will specifically focuses on the */_dynamical, adaptive and computational properties of neural systems_/*, seen as 'devices' that process information and can control external devices. This includes neural prostheses, brain-machine interfaces and neurally controlled robots. The objective is to move beyond the well established neuroinformatics or AI (Artificial Intelligence) domains by fostering research that would benefit both the neuroscience (NS) and Information Technology (IT) communities by helping solve the fundamental problems linked to the emergence and the modelling of computational properties, learning and cognitive processes in natural systems. The goal is for IT to profit from NS results to improve IT artifacts and for NS to validate models or hypotheses with a better use of IT. Neuro-IT.net and the NEUROversIT consortium is therefore committed to spearheading the emergence of visionary long term research objectives that could fully exploit the potential of collaboration between neurosciences and information technology. *Overall organisation* The school will have a duration of 5 days in total (Tuesday to Saturday morning). The first day will feature /advanced tutorials/ with the goal of equalizing the backgrounds of students from different disciplines. These tutorials will focus on background materials directly relevant to the topic of the summer school, that will improve understanding of the expert presentations that will follow in day 2-4 of the school. Friday afternoon and Saturday morning will be devoted to practical lecturers and Lab activities. The first day will be devoted to presenting important concepts and data from neuroscience for students from technical disciplines, and for presenting topics in neuro-IT and neuroengineering for student from life science. The other three days of the school feature expert lectures on selected topics under the theme "Dynamics, Computation and Learning in Neural Systems". These lectures will cover state-of-the-art research related to one or multiple of the topics mentioned below. Students participating to the school are invited to present their own activity in specific dedicated sessions. Lab sessions will be organized on Friday 16^th (afternoon) and Saturday 17^th (morning) and they will be devoted to practical presentations and activities on: - NEURON simulator - Data analysis for multisite recorded neuronal signals (sponsored by eTT, http://www.ettsolutions.com ) Students interested in such activities are requested to specifically enroll to one or both Lab. The Lab activity are included in the registration fees. * Topics * * Speakers * * Program * * Information * * Fees * * Accomodations * * * * * *Topics* The school will address key topics in the Neuroengineering field, with a focus on "Dynamics, Computation and Learning in Neural Systems" and their technical realization in artificial systems. All issues should be dealt with, in an interdisciplinary way, both from the biological and the IT/engineering perspective. Key topics will include: . Neural-network dynamics - Neurobiology of in-vivo and in-vitro neuronal systems - non linear dynamics and neuronal signal analysis - theoretical and experimental models . Coding and decoding neuronal signals - rate/time coding - ...... . Neural plasticity - learning -- development - neurobiology of learning and memory - closed-loop system and learning - learning and plasticity in in-vitro neuronal system . Advanced neuro-prosthetics - brain-machine interfaces - technological advances in BMI - decodying of neuronal signals . Neuro-robotics - biologically inspired robots - bi-directional neuro-robotic interfaces - cognitive ... *Faculty members* /(to be filled)/ *REGISTRATION FEES* (*) *CATEGORIES* *BEFORE MAY 15* *AFTER MAY 15* PhD students 200 ? 250 ? Postdocs 250 ? 300 ? Business and medical professionals 350 ? 400 ? (*) includes program, reception, two coffee breaks and lunch each day lab activities and lecture notes * * *LOCAL ORGANIZATION:* Prof. Sergio Martinoia University of Genova e -mail: martinoia at dibe.unieg.it Phone: +39-010-3532251 Fax: +39-010-3532133 Prof. Vittorio Sanguineti University of Genova e -mail: _vittorio.sanguineti at unige.it _ Phone: +39-010-3536487 Fax: +39-010-3532154 *ADMINISTRATIVE INFORMATION:* Ms. Jessica Gaggero University of Genova e -mail: jessica at dibe.unige.it Phone: +39-010-3532787 Fax: +39-010-3532133 From F.AlmeidaCosta at sussex.ac.uk Tue Apr 18 09:41:07 2006 From: F.AlmeidaCosta at sussex.ac.uk (Fernando Almeida e Costa) Date: Tue, 18 Apr 2006 14:41:07 +0100 Subject: Connectionists: Last CFP with important update - Workshop on Morphologies Motion and Cognition Message-ID: <000001c662ed$c78bffd0$efea1e52@salome> ********************************************************************* Morphologies, Motion and Cognition Workshop @ Alife X Last call for papers and demos (Check below for an important update regarding deadlines) Organized by the Morphodynamics and Cognition Group University of Sussex www.informatics.sussex.ac.uk/morphodynamicsgroup/alifexwk ********************************************************************* AlifeX, in June, taking place at Indiana University, USA, is to host a workshop on "Morphologies, Motion and Cognition" organised by the Morphodynamics and Cognition Group from the University of Sussex. This workshop will take place on the 3rd of June (all-day session), and on the evening of the 4th. Venue: Indiana Memorial Union, in the same area as the main conference presentations. We are accepting submissions of papers and/or proposals of demos. *********************** Aim of the workshop *********************** Our intention is to bring together researchers from robotics, psychology, and ethology to examine and discuss how morphology and motion shapes the perceptual worlds and cognitive behaviours of robots and natural organisms. Although we welcome simulations, we want to encourage work on "physical" robots, or simulated robots that have interesting morphologies. In the approach to cognition that we will be discussing, cognitive activity is regarded as crucially dependent upon, and emerging from, the exploitation of all the physical properties available to the agent, namely its morphology and motion. The key principle of this approach is to minimise the amount of control at the algorithmic level by exploiting the dynamics of the agent, produced by its interaction with the environment. This approach views organisms and robots as dynamic systems, whose parts are continually perturbed by cues from their environments that act to modulate their behaviours. **************** Keynote Speakers **************** Inman Harvey, University of Sussex Rolf Pfeifer, University of Zurich ********* Topics ********* The work to be submitted may include (but is not limited to) the following topics: - the exploitation by an agent of its morphodynamics (morphologies and motion) for cognitive purposes, at any level of "cognition" in both humans and robots. - passive dynamic walkers - relation with the environment through active perception - evolution of morphologies, morphogenesis - developmental issues in both humans/animals and robots - dynamical theories of cognition - embodied and situated robotics - constructed worlds of robots - articulated motion in robots and animals - sensorimotor and movement coordination - evolvable hardware - design principles for fully embodied and situated robots - automatic robot manufacture - 3D rapid prototyping printers - non-holonomic robot control - control for underactuated or compliant structures - methods for the analysis of the interaction of morphology, motion, and control ************ Papers ************ Papers can either be technical or conceptual, in the area covered by the workshop. Length should not exceed 10 pages, double spaced, and must be emailed in pdf format to one of the organisers (see addresses below in "organising committee") ************ Demos ************ Demos can be presented as physical robots, computer simulations or videos of physical robots. If you are interested in presenting a demo please contact one of the members of the organising committee as soon as possible. ****************** Important dates ****************** UPDATE: Abstracts of the papers must be submitted by April 27 Papers deadline submission: May 1 Notification of acceptance: May 5 Abstracts and papers must be sent to the organising committee (email addresses below) ************ Publication ************ If the submitted contributions are of sufficient quality, papers emerging from the workshop will be forwarded to undergo the review process of a scientific journal, for a special issue. ************ Details ************ You may find detailed information about the workshop in our webpage at www.informatics.sussex.ac.uk/morphodynamicsgroup/alifexwk or through the conference webpage at www.alifex.org ******************** PROGRAMME COMMITTEE ******************** Bill Bigge, University of Sussex Josh Bongard, Cornell University Inman Harvey, University of Sussex Phil Husbands, University of Sussex Fumiya Iida, University of Zurich Eduardo Izquierdo-Torres, University of Sussex Akio Ishiguro, University of Nagoya Hod Lipson, Cornell University Max Lungarella, University of Tokyo Romi Nijhawan, University of Sussex Chandana Paul, Cornell University Rolf Pfeifer, University of Zurich Linda Smith, Indiana University Olaf Sporns, Indiana University Kasper St?y, University of Southern Denmark Tim Taylor, Timberpost, Ltd. Eric Vaughan, University of Sussex Rachel Wood, University of Sussex Tom Ziemke, University of Sk?vde ************************** Organising Committee ************************** Fernando Almeida e Costa F.AlmeidaCosta at sussex.ac.uk Ian Macinnes ian at british-cybernetics.co.uk ************************************************* www.informatics.sussex.ac.uk/morphodynamicsgroup From jbednar at inf.ed.ac.uk Tue Apr 18 16:44:49 2006 From: jbednar at inf.ed.ac.uk (James A. Bednar) Date: Tue, 18 Apr 2006 21:44:49 +0100 Subject: Connectionists: Computational maps book and software Message-ID: <17477.20417.345695.66710@lodestar.inf.ed.ac.uk> We are pleased to announce the publication of the book "Computational Maps in the Visual Cortex" by Miikkulainen, Bednar, Choe, and Sirosh (New York: Springer). This book presents a computational approach to understanding how the map-like structures in the visual cortex develop and adapt to support visual function. It reviews current theories and biological data, and presents a detailed analysis of the laterally connected self-organizing map model (LISSOM) and results obtained to date. The TOC and a sample chapter, electronic versions of the figures and references, animated demos, talks, and course material are available at the book website: http://computationalmaps.org The book was developed together with "Topographica", a general simulator for computational modeling of cortical maps. Topographica is intended to serve as a common software tool for the research community, and is freely available at: http://topographica.org We hope that these tools will be useful in future research on the computational mechanisms of the visual cortex! -- Risto, Jim, Yoonsuck, and Joe From g.goodhill at imb.uq.edu.au Thu Apr 20 02:43:48 2006 From: g.goodhill at imb.uq.edu.au (Geoffrey Goodhill) Date: Thu, 20 Apr 2006 16:43:48 +1000 Subject: Connectionists: Network 17.1 Table of Contents Message-ID: <44472DA4.3090509@imb.uq.edu.au> Network: Computation in Neural Systems Vol 17, Number 1 (March 2006) TABLE OF CONTENTS Editorial: Welcome to the new Network Geoffrey Goodhill pp. 1 - 2 Dynamics of neural populations: Stability and synchrony Lawrence Sirovich, Ahmet Omurtag, Kip Lubliner pp. 3 - 29 Excitability changes that complement Hebbian learning Maia K. Janowitz and Mark C. W. Van Rossum pp. 31 - 41 Decoupling functional mechanisms of adaptive encoding Nicholas A. Lesica and Garrett B. Stanley pp. 43 - 60 Dopamine, prediction error and associative learning: A model-based account Andrew Smith, Ming Li, Sue Becker, Shitij Kapur pp. 61 - 84 V1 non-linear properties emerge from local-to-global non-linear ICA Jes?s Malo and Juan Guti?rrez pp. 85 - 102 Journal homepage including links to above articles: http://www.tandf.co.uk/journals/titles/0954898X.asp Submissions: http://mc.manuscriptcentral.com/ncns Geoff Goodhill Editor-in-Chief, Network: Computation in Neural Systems ncns at uq.edu.au From pjt9 at case.edu Thu Apr 20 12:36:30 2006 From: pjt9 at case.edu (Peter Thomas) Date: Thu, 20 Apr 2006 12:36:30 -0400 Subject: Connectionists: coupled cortical maps paper Message-ID: <2D4D8146-CA5C-456E-993F-F9CEBD6B7141@case.edu> Dear Colleagues: I am pleased to draw your attention to the following article, available at http://imammb.oxfordjournals.org/cgi/rapidpdf/dql006? ijkey=TjqJPARL6JsfmFT&keytype=ref > Simultaneous constraints on pre- and post-synaptic cells couple > cortical > feature maps in a 2D geometric model of orientation preference > > Peter J. Thomas (Oberlin College & Case Western Reserve University) > Jack D. Cowan (The University of Chicago) > > The most prominent feature of mammalian striate cortex (V1) is the > spatial organization of response preferences for the position and > orientation of elementary visual stimuli. Models for the formation > of cortical maps of orientation and retinotopic position typically > rely on a combination of Hebbian or correlation-based synaptic > plasticity, and constraints on the distribution of synaptic > weights. We consider a simplified model of orientation and > retinotopic specificity based on the geometry of the feedforward > synaptic weight distribution from an unoriented layer of cells to a > first weakly oriented layer. We model the feed-forward weight > distribution as a system of planar Gaussian receptive fields each > elongated in the direction matching the preferred orientation of > the postsynaptic cell. Under the constraint of presynaptic weight > normalization (each cell in the oriented layer receives the same > net synaptic weight) and a uniform retinotopic map (displacement of > centres of mass of receptive fields in the unoriented layer is > strictly proportional to the displacement of the corresponding > cells in the oriented layer), we find that imposing a pattern of > orientation preference forces the system to violate postsynaptic > weight normalization (each cell in the unoriented layer no longer > sends forth the same net synaptic weight). We study this deviation > from uniformity of the postsynaptic weight, and find that the > deviation has a distinct form in the vicinity of the pinwheel > singularities of the orientation map. We show that uniform synaptic > coverage of the unoriented layer can be restored by introducing a > distortion in the retinotopic locations of the receptive fields. We > calculate, to first order in the relative elongation of the > receptive fields, the retinotopic distortion vector field. Both the > pattern of postsynaptic weight non-uniformity and the corrective > retinotopic distortion vector field fail to possess the reflection > symmetry commonly assumed to relate orientation singularities with > topological index +-pi. Hence, we show that right-handed and left- > handed orientation singularities are fundamentally distinct > anatomical structures when full 2D synaptic architecture is taken > into account. Finally, we predict specific patterns of retinotopic > distortion that should obtain in the vicinity of +-pi-fold > orientation singularities, if uniform pre- and post-synaptic weight > constraints are strongly enforced. > > Keywords: visual cortex; orientation; retinotopy; fan-in; fan-out; > neural network; cortical map. Best wishes, Peter J. Thomas [as of July 1, 2006:] Assistant Professor of Mathematics, Biology & Cognitive Science Case Western Reserve University Department of Mathematics Yost Hall, 10900 Euclid Ave, Cleveland, OH 44106-7058 pjt9 -- at -- case.edu // 216-368-8998 From nnrev at atr.jp Fri Apr 21 01:23:51 2006 From: nnrev at atr.jp (Neural Networks Editorial Office) Date: Fri, 21 Apr 2006 14:23:51 +0900 Subject: Connectionists: CFP: Neural Networks Special Issue on Neuroscience and Robotics Message-ID: [Apologies if you receive this announcement more than once.] ************************************************************************ CALL FOR PAPERS 2007 Special Issue of Neural Networks " Neuroscience and Robotics " ************************************************************************ Co-Editors Yoshihiko Nakamura Paolo Dario Stefan Schaal Submission Deadline for submission: November 30, 2006 Notification of acceptance: February 28, 2007 Deadline for submission of revised papers: April 10, 2007 Notification of final acceptance: May 31, 2007 Deadline for submission of final papers: June 30, 2007 Format: as for normal papers in the journal Address for Papers Dr. Mitsuo Kawato ATR Computational Neuroscience Laboratories 2-2-2 Hikaridai, Seika-cho Soraku-gun, Kyoto 619-0288, Japan. Neuroscience and computational neuroscience has recently made major advances in systems level, more specifically in understanding the neural control of behaviors. In a parallel perspective, robotics research has reached out its scope toward increasingly more complex systems. Full-scale humanoid robots and animal-like robots for human interaction set robotics research to face high-dimensional problems of motor control, perception, and decision-making, which necessitate exploring biological paradigms. Such advances of robotics technology have also opened a door for computational research on biological motor control to experimental study of its theories and algorithms. Moreover, brain-robot interfaces have been demonstrated in recent pioneering projects. Since the domain of many research problems is shared between brain science and robotics, a natural exchange of inspirations, theories, and algorithms is more demanded and encouraged than ever. The goal of this special issue is to provide an overview of state-of-the-art of research on projects where robotics has had a major impact on neuroscience, and where neuroscientific ideas have found successful application in the behavioral control of complex robots. Examples of research projects of interest include, but are not restricted to, - humanoid robotics and principles of neuroscience, - human behavioral research with innovative robotic technology, - robotic intelligence/behavior research based on neuroscientific paradigms - innovative robotic tools (hardware/software) for neuroscience - technologies interfacing biological neural systems and machines Neural Networks Official home page: http://www.elsevier.com/wps/find/journaldescription.cws_home/841/description Instructions to Authors: See Guide For Authors in the above web page -- """""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" NEURAL NETWORKS Editorial Office ATR Computational Neuroscience Laboratories 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan TEL +81-774-95-1204 FAX +81-774-95-1236 E-MAIL nnrev at atr.jp """""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" From nips06pub at hotmail.com Wed Apr 19 11:26:31 2006 From: nips06pub at hotmail.com (M.O. Franz) Date: Wed, 19 Apr 2006 17:26:31 +0200 Subject: Connectionists: CALL FOR PAPERS NIPS*2006 Message-ID: CALL FOR PAPERS – NIPS*2006 Deadline for Paper Submissions: June 9, 2006 Submissions are solicited for the twentieth annual meeting of an interdisciplinary conference (December 5-7) which brings together researchers interested in all aspects of neural and statistical processing and 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 4), and following it will be two days of workshops at Whistler/Blackcomb ski resort (December 8-9). Invited Speakers: To be announced. Tutorial Speakers: To be announced. Submissions: Papers are solicited in all areas of neural information processing, including (but not limited to) the following: * Algorithms and Architectures: statistical learning algorithms, neural networks, kernel methods, graphical models, Gaussian processes, dimensionality reduction and manifold learning, model selection, combinatorial optimization. * Applications: innovative applications or fielded systems that use machine learning, including systems for time series prediction, bioinformatics, text/web analysis, multimedia processing, and robotics. * Brain Imaging: neuroimaging, cognitive neuroscience, EEG (electroencephalogram), ERP (event related potentials), MEG (magnetoencephalogram), fMRI (functional magnetic resonance imaging), brain mapping, brain segmentation, brain computer interfaces. * Cognitive Science and Artificial Intelligence: theoretical, computational, or experimental studies of perception, psychophysics, human or animal learning, memory, reasoning, problem solving, natural language processing, and neuropsychology. * 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. * Hardware Technologies: analog and digital VLSI, neuromorphic engineering, computational sensors and actuators, microrobotics, bioMEMS, neural prostheses, photonics, molecular and quantum computing. * Learning Theory: generalization, regularization and model selection, Bayesian learning, spaces of functions and kernels, statistical physics of learning, online learning and competitive analysis, hardness of learning and approximations, large deviations and asymptotic analysis, information theory. * 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. * Speech and Signal Processing: recognition, coding, synthesis, denoising, segmentation, source separation, auditory perception, psychoacoustics, dynamical systems, recurrent networks, Language Models, Dynamic and Temporal models. * Visual Processing: biological and machine vision, image processing and coding, segmentation, object detection and recognition, motion detection and tracking, visual psychophysics, visual scene analysis and interpretation. Review Criteria: New as of 2006, NIPS submissions will be reviewed double-blind: the reviewers will not know the identities of the authors. Submissions will be refereed on the basis of technical quality, novelty, potential impact on the field, and clarity. There will be an opportunity after the meeting to revise accepted manuscripts. We particularly encourage submissions by authors new to NIPS, as well as application papers that combine concrete results on novel or previously unachievable applications with analysis of the underlying difficulty from a machine learning perspective. Paper Format: The paper format is fully described at http://research.microsoft.com/conferences/nips06/. Please use the latest style file for your submission. Submission Instructions: NIPS accepts only electronic submissions at http://papers.nips.cc. These submissions must be in postscript or PDF format. The Conference web site will accept electronic submissions from May 26, 2006 until midnight, June 9, 2006, Pacific daylight time. Demonstrations: There is a separate demonstration track at NIPS. Authors wishing to submit to the demonstration track should consult the conference web site. Organizing Committee: General Chair --- Bernhard Schölkopf (MPI for Biological Cybernetics) Program Chair --- John Platt (Microsoft Research) Tutorials Chair --- Daphne Koller (Stanford) Workshop Chairs --- Charles Isbell (Georgia Tech) Rajesh Rao (University of Washington) Demonstrations Chairs --- Alan Stocker (New York University) Giacomo Indiveri (UNI ETH Zurich) Publications Chair --- Thomas Hofmann (TU Darmstadt) Volunteers Chair --- Fernando Perez Cruz (Gatsby Unit, London) Publicity Chair --- Matthias Franz (Max Plack Institute, Tübingen) Online Proceedings Chair --- Andrew McCallum (Univ. Massachusetts, Amherst) Program Committee: Chair --- John Platt (Microsoft Research) Bob Williamson (National ICT Australia) Cordelia Schmid (INRIA) Corinna Cortes (Google) Dan Ellis (Columbia University) Dan Hammerstrom (Portland State University) Dan Pelleg (IBM) Dennis DeCoste (Yahoo Research) Dieter Fox (University of Washington) Hubert Preissl (University of Tuebingen) John Langford (Toyota Technical Institute) Kamal Nigam (Google) Kevin Murphy (University of British Columbia) Koji Tsuda (MPI for Biological Cybernetics) Maneesh Sahani (University College London) Neil Lawrence (University of Sheffield) Samy Bengio (IDIAP) Satinder Singh (University of Michigan) Shimon Edelman (Cornell University) Thomas Griffiths (UC Berkeley) Deadline for Paper Submissions: June 9, 2006 _________________________________________________________________ FREE pop-up blocking with the new MSN Toolbar - get it now! http://toolbar.msn.click-url.com/go/onm00200415ave/direct/01/ From dayan at gatsby.ucl.ac.uk Fri Apr 21 10:44:05 2006 From: dayan at gatsby.ucl.ac.uk (Peter Dayan) Date: Fri, 21 Apr 2006 15:44:05 +0100 Subject: Connectionists: Gatsby Annual Seminar: 17th May: 2:30pm In-Reply-To: <20060113094900.GC23422@flies.gatsby.ucl.ac.uk> References: <20060113094900.GC23422@flies.gatsby.ucl.ac.uk> Message-ID: <20060421144404.GF3517@flies.gatsby.ucl.ac.uk> 17 May 2006 2.30pm Gatsby Unit Annual Seminar We are delighted to announce the first in an annual series of Gatsby Seminars, with talks by distinguished researchers in theoretical neuroscience and machine learning. This year's talks will be given by Dr Li Zhaoping, from the Dept of Psychology at UCL, and Prof John Shawe-Taylor, from the Dept of Computer Science at the University of Southampton. They will be held at 2.30pm in the Wolfson House Haldane Lecture Theatre, and will be followed by a wine reception at 5.00pm at The Gatsby Unit, Alexandra House, 17 Queen Square Titles and abstracts below. All are welcome. --------------------------------------------- 2.30pm: Dr Li Zhaoping The More Briefly one Looks, the More Effectively one `Sees': Vision by V1 I show that a visual search task can be better performed when one views the search array for a shorter time, and suggest an account of this phenomenon based on an analysis of V1's contribution to vision. The cost of a prolonged view comes from the interference of higher level object recognition on lower level image feature processing. A similar effect underlies the trick for art novices of drawing a portrait upside down in order to reproduce lower level image features, such as contours, with less interference from higher level face cognition. In our task, the search target has an uniquely oriented bar but is identical in shape to distractors. Lower level image feature processes enable the unique orientation to pop out, attracting gaze towards the target. Subsequently, higher level object processes, involving focused attention, recognize the target object in a viewpoint invariant manner, confusing the target as being a distractor and interfering with the task. Lower and higher processes lead to their respective behavioural decisions manifested in eye movements and ultimate task performances. I will show physiological and computational evidence implicating V1 mechanisms for the lower level feature pop out, and review data about higher object processes in higher brain areas. 3.45pm: Prof John Shawe-Taylor Inferring Semantic Representations from Data The talk addresses the question of how effectively we can learn underlying semantics from data. We concentrate on text analysis as a domain where semantics are relatively cleanly defined and on which learning approaches have made significant advances. The links between Latent Semantic Indexing, Latent Semantic Kernels and kernel Principal Components Analysis are discussed and the generalisation of such representations is discussed. Cross-lingual information retrieval suggests the use of Canonical Correlation Analysis as a Semantic inference tool. Again a kernel version can be defined and with appropriate regularisation applied in high-dimensional feature spaces. Applications of the same approach to non-text data will also be presented. ------------------------------------------ From cns at cnsorg.org Sat Apr 22 16:43:55 2006 From: cns at cnsorg.org (CNS) Date: Sat, 22 Apr 2006 13:43:55 -0700 Subject: Connectionists: CNS 2006 registration open Message-ID: <20060422204357.M70142@cnsorg.org> CNS 2006 will be held in Edinburgh, UK from July 16-20th 2006. The main meeting will start with an oral session at 9am on Sunday, July 16th and end on Tuesday, July 18th with an evening session. Workshops will start Wednesday, July 19th at 9am and end Thursday, July 20th in the evening. CNS 2006 Registration and lodging reservations are now open. Details can be found at www.cnsorg.org -- CNS - Organization for Computational Neurosciences From angelo.arleo at csl.sony.fr Mon Apr 24 10:52:19 2006 From: angelo.arleo at csl.sony.fr (angelo arleo) Date: Mon, 24 Apr 2006 16:52:19 +0200 Subject: Connectionists: Call for papers: Workshop on "Multisensory Integration and Parallel Memory Systems for Spatial Cognition" Message-ID: <444CE623.4010000@csl.sony.fr> (We apologise for multiple copies of this message) ********************************************************************* 1st C A L L F O R P A P E R S Workshop on "Multisensory Integration and Concurrent Parallel Memory Systems for Spatial Cognition" http://www.idiap.ch/~rchava/sab06wk/ October 1, 2006, Rome, Italy as part of the 9th International Conference on the Simulation of Adaptive Behavior (SAB2006) http://www.sab06.org ********************************************************************* ----------------------------------- WORKSHOP DESCRIPTION and OBJECTIVES ----------------------------------- Spatial cognition involves the ability of an animal to acquire spatial knowledge (e.g., spatio-temporal relations among environmental cues or events), organise it properly, and employ it to adapt its motor behaviour to the specific context. Alike other high-level brain functions, spatial memory calls upon parallel information processing mediated by multiple neural substrates that interact, either cooperatively or competitively, to promote appropriate spatial learning. Similar to animals, autonomous navigating artefacts need to interact with their environment and learn both low-level sensory-motor couplings and more abstract context representations supporting their spatial behaviour. I. At the sensory level, different perceptual modalities provide the navigator with a manifold description of the spatial context. The integration of these multimodal signals into a coherent representation is at the core of spatial cognition. The first part of the workshop will address issues such as: * What are the learning mechanisms (both at the synaptic plasticity level and at a more abstract level) mediating the integration of multimodal signals? * What are the spatial information properties determining the cue selection process during the exploration of a novel environment? * What are the principles underlying the minimisation of destructive interference between spatial memories acquired during lifelong learning? II. At the action selection level, determining and maintaining a goal-directed trajectory involves multiple mnemonic processes, each of which promotes a specific solution (i.e., a navigation strategy) to the overall task. The capability of dynamically weighing the contribution of distinct memory systems is relevant to the issue of adapting the spatial behaviour to the complexity of the task. The second part of the workshop will explore this topic, which is currently the focus of a large research effort in both experimental and computational neuroscience. Among others, the following issues will be addressed: * What are the multiple co-existing memory systems promoting spatial navigation? * What are the anatomo-functional interrelations between the neural substrates (e.g., hippocampus, prefrontal and parietal cortices, basal ganglia, and cerebellum) mediating these multiple spatial memory systems? * What are the principles regulating the cooperative/competitive relations between these parallel memory systems and determining the on-line shift between distinct navigation strategies? This workshop aims at fostering a multidisciplinary forum between experimentalists, theoreticians, and engineers in order to improve our understanding of animal and bio-inspired spatial learning capabilities. Please, refer to the web-site: http://www.idiap.ch/~rchava/sab06wk/ for more information about the workshop programme. ------------- CONTRIBUTIONS ------------- 1. CALL for POSTER ABSTRACTS: DEADLINE JULY 1, 2006 Posters will be exposed during the full length of the workshop, though authors will be asked to present their work only during specific time slots (see the programme). We invite authors to submit a short abstract (less than 400 words including references) in order to be selected for a poster presentation. Due to the limited number of posters that can be actually exposed, accepted contributions shall have high scientific quality and relevance to the workshop. Selected abstracts will be posted on the workshop website, and a hard-copy abstract collection will be distributed during the workshop. Abstracts must be sent (as pdf files) to spatial.learning at gmail.com before July 1, 2006. 2. CALL for FULL PAPERS: DEADLINE NOVEMBER 1, 2006 A Special Issue of the *Journal of Integrative Neuroscience* (http://www.worldscinet.com/jin/jin.shtml) will be edited as a follow-up of the workshop. All submitted papers will be peer-reviewed by both the programme committee of the workshop and the journal's editorial board. Three types of contributions can be submitted: * articles, * brief communications, and * review-like papers. Authors are requested to explicitly address issues such as the biological plausibility of the proposed models, as well as how the proposed theoretical approaches may improve the knowledge of the neurobiological bases of spatial cognition. Drafts must be submitted to spatial.learning at gmail.com before November 1, 2006, and must be prepared according to the journal's "Guidelines for contributions" (http://www.worldscinet.com/jin/mkt/guidelines.shtml). -------------------------- SUMMARY of IMPORTANT DATES -------------------------- We encourage authors to submit both abstracts and full papers even though there is no restriction in this respect. Deadline for abstract submission July 1, 2006 Deadline for full paper submission November 1, 2006 Workshop date October 1, 2006 Expected journal publication date June, 2007 ----------------- PROGRAM COMMITTEE ----------------- Nathaniel Daw. Gatsby Unit, London, UK. Philippe Gaussier. Universit? de Cergy-Pontoise, France. Jeff Krichmar. The Neuroscience Institute, San Diego, USA. Benoit Girard. LPPA - Coll?ge de France, France. Tony Prescott. Adaptive Behaviour Research Group, Sheffield, UK. Agn?s Guillot. Animatlab, University Paris VI, France. Verena Hafner. TU Berlin, Germany Bruno Poucet. CNRS, Marseille, France. Mehdi Khamassi. Animatlab, University Paris VI, France. Denis Sheynikhovich. EPFL, Lausanne, Switzerland. Angelo Arleo. Sony Computer Science Laboratory, France. Ricardo Chavarriaga. IDIAP Research Institute, Switzerland. ------------------- WORKSHOP ORGANIZERS ------------------- Angelo Arleo http://www.csl.sony.fr/~angelo/ Sony Computer Science Laboratory, Paris, France Ricardo Chavarriaga http://www.idiap.ch/~rchava/ IDIAP Research institute, Martigny, Switzerland For further information: spatial.learning at gmail.com From M.Casey at surrey.ac.uk Fri Apr 21 04:16:08 2006 From: M.Casey at surrey.ac.uk (M.Casey@surrey.ac.uk) Date: Fri, 21 Apr 2006 09:16:08 +0100 Subject: Connectionists: International Workshop on Biologically Inspired Information Fusion: Second Call Message-ID: ======================================================================== ==================== International Workshop on Biologically Inspired Information Fusion Second Call for Contributions Tuesday 22 August - Wednesday 23 August 2006, University of Surrey, Guildford, UK. http://www.soc.surrey.ac.uk/ias/workshops/biif/ ======================================================================== ==================== We invite contributions to an international workshop on biologically inspired information fusion. The workshop is designed to bring together complementary researchers in the broad areas of computer science, engineering, psychology and biology who have an interest in the multi-disciplinary aspects of information fusion. The programme consists of tutorials from discipline leaders, discussions, and research student poster and oral presentations. Contributions are being sought for the discussion sessions and research student presentations from all of the target disciplines: computer science, engineering, psychology and biology. Confirmed tutorial guests include: Professor Barry Stein, Department of Neurobiology and Anatomy, Wake Forest University School of Medicine Dr Gemma Calvert, Multisensory Research Group in the Department of Psychology, University of Bath ======================================================================== ==================== Natural and Artificial Multi-sensory Processing The ability to process, interpret and act upon sensory information is perhaps one of the most remarkable aspects of human and animal cognition. Our sensory systems process large volumes of information at different scales in short periods of time, far out-performing current artificial systems, which struggle to usefully process just a single modality of information. For example, whereas speech recognition systems have achieved real-time continuous operation, artificial systems, designed for vision or olfaction are far less advanced, yet the combination of different information sources, or senses, may help overcome some of the processing limitations. This disparity between natural and artificial cognitive systems has been recognised in the recent UK Foresight Cognitive Systems Review, which suggests that our understanding of both natural and artificial systems of sensory processing can be achieved through collaboration between life and physical scientists. About the Workshop The workshop is sponsored by the University of Surrey's Institute of Advanced Studies. The aim is to promote collaboration between disciplines to develop an understanding of how to build adaptive information fusion systems by improving our knowledge from both natural and artificial systems research. The programme is designed to facilitate a cross-discipline understanding of multi-sensory fusion, with discussions on key topics and future directions, and presentation of current ideas. This is to be achieved through tutorials from leaders in each of the target disciplines, brainstorming and debate sessions lead by relevant researchers, and both oral and poster presentations from research students. Example topics include, but are not limited to: Sensory and multi-sensory processing: neurobiology, behaviour, computational modelling and artificial sensors - Vision, audition, olfaction, taste, touch - Attention: pre-attention or task-driven attention - Emotional bias on senses - Artificial sensors Information fusion and multi-modal systems: - Computer vision, speech processing, gesture recognition - Sensor fusion - Multiple regressor or classifier systems - Biometrics, human-computer interaction, intelligent systems - Bio-logically inspired robotics ======================================================================== ==================== Discussions Topics for the discussion sessions should aim to promote new or controversial ideas, perhaps posing unanswered questions related to the workshop. These should be in the form of abstracts (maximum 500 words) stating the key topic of discussion and highlighting possible solutions and current points of view. Proposals for debates, where two participants offer their point of view prior to discussion, should be clearly highlighted. All contributions will be peer reviewed by the workshop programme committee. Those with accepted topics will be invited to give a 10 minute presentation of their idea. For sessions focused around a debate, both participants will be invited to present their ideas in a 10 minute slot each, prior to discussion. An open brainstorming session will then follow for 50 minutes with a focus on initially evaluating the proposed idea or giving thoughts on unanswered questions. Notes and outcomes of these sessions will be recorded. Abstracts should be submitted via e-mail to biif2006 at surrey.ac.uk by the deadline: 15 May 2006. ======================================================================== ==================== Student Presentations Papers are invited from research students only to promote discussion of new ideas and to foster training and development of new researchers. All papers will be peer reviewed by the workshop programme committee to assess originality, significance, quality and clarity. Those students with accepted papers will be invited to either present a poster or to give a 20 minute oral presentation. Papers should not exceed 6 pages in length, including references, tables, figures and appendices, and should follow the LNCS format, details of which can be found at http://www.springer.com/sgw/cda/frontpage/0,11855,3-164-2-72376-0,00.htm l. Papers should be submitted via e-mail to biif2006 at surrey.ac.uk by the deadline: 15 May 2006. ======================================================================== ==================== Enquiries regarding abstract and paper submission should be directed to biif2006 at surrey.ac.uk. Abstracts and papers will be available to workshop attendees via the website and printed proceedings. After the workshop, participants will be invited to submit papers based upon their work to two journal special issues (journals to be confirmed). These will contain a mixture of review/discussion articles and presentations of current research work. ======================================================================== ==================== Important Dates 15 May 2006 Deadline for submitting discussion topics and student papers 19 June 2006 Notification of acceptance 17 July 2006 Camera ready papers 22-23 August 2006 Workshop at the University of Surrey Guests looking for accommodation on campus (the cheapest in Guildford) are advised to register by the 15th May 2006. Otherwise, registration is open up until the workshop. For papers to be presented at the workshop, all guests must be registered by the 17th July 2006 to secure a place on the programme. Further information can be obtained from: - Website: http://www.soc.surrey.ac.uk/ias/workshops/biif/ - Enquiries about paper submission: biif2006 at surrey.ac.uk - General and administrative enquiries: Mrs Gautier O'Shea, S.Gautier at surrey.ac.uk; Mrs Heather Norman, H.Norman at surrey.ac.uk - Dr Matthew Casey, M.Casey at surrey.ac.uk; tel. +44 (0)1483 689635 - Dr Paul Sowden, P.Sowden at surrey.ac.uk - Dr Hujun Yin, Hujun.Yin at manchester.ac.uk - Dr Tony Browne, A.Browne at surrey.ac.uk From p.husbands at sussex.ac.uk Mon Apr 24 05:57:17 2006 From: p.husbands at sussex.ac.uk (Phil Husbands) Date: Mon, 24 Apr 2006 10:57:17 +0100 Subject: Connectionists: faculty positions available at Sussex University Message-ID: <5671531.1145876237@[192.168.123.100]> Faculty positions available at Sussex University, UK. Professorship in Informatics and Head of Department Department of Informatics We are seeking to further strengthen research in the Department with a high-profile appointment as Professor of Informatics. The successful candidate will have an international reputation for excellence in research, and a proven record of research or academic management. The appointment involves being Head of the Department of Informatics for an agreed length of time, normally three years. Applicants should have an academic background in an area of Informatics, and their research should align with one or more areas being pursued by existing research groups in the Department. These include computational neuroscience, evolutionary and adaptive systems, neural computation, as well as other areas of AI, Cognitive Science and CS. Full details: Lecturer in Informatics Department of Informatics The successful applicant will have a strong peer reviewed publication record, and will have teaching experience. Applicants should have an academic background in an area of Informatics, and their research should align with one or more areas being pursued by existing research groups in the Department. These include computational neuroscience, evolutionary and adaptive systems, neural computation, as well as other areas of AI, Cognitive Science and CS. Full details: From Pierre.Bessiere at imag.fr Thu Apr 20 11:58:59 2006 From: Pierre.Bessiere at imag.fr (=?ISO-8859-1?Q?Pierre_Bessi=E8re?=) Date: Thu, 20 Apr 2006 17:58:59 +0200 Subject: Connectionists: Research Engineer in Bayesian Programming Message-ID: <7B5512F3-B286-4227-86F4-05F37BA9F7C8@imag.fr> Position Title: ------------------ Research Engineer in Bayesian Programming Where: ------------ Grenoble (Capital of the French Alps), France When: --------- Immediately, for 3 to 4 years Description of the Position: ------------------------------------ You will have to develop Bayesian models, programs, applications and experiments. You will be a key element of a research group devoted to "Stochastic Models for Perception, Inference, Learning and Action". Your main mission will be to take in charge the software development of the group related to the starting european project BACS (Bayesian Approach to Cognitive Systems) and some experiments on various robotic platforms. Your employer will be INRIA (Institut National de la Recherche en Informatique et Automatique) a major international institute for research in computer science and applied math. Example of possible models, experiment or application you may have to work on are : - Bayesian models of neurons and population of neurons - Bayesian models of human object perception - Bayesian models of human and rat navigation - Bayesian based autonomous navigation of mobile robots and cars - Bayesian based body and face motion tracking - Bayesian reconstruction of 3D realistic scene - Bayesian based multi-modal sensor integration and analysis - Bayesian driver assistance for enhanced vehicle safety All this models are build using the Bayesian Programming formalism (an extension of Bayes Nets) and use the ProBT? toolbox and API to automate the inference and computation. You will be the ProBT guru of the group and will assist researchers and PhD student in their models and software development. Requirements: -------------------- Necessary : - A master, an engineering degree or a PhD in computer science. - Fluent in C and C++ - Fluent in either French or English (If not fluent in French, at least some good bases are required and a strong willing to learn more rapidly) Plus : - Bilingual of fluent in both language - Experience of software development and maintenance - Holding a PhD - Experience of robotics and/or artificial intelligence - Proficiency in probability or statistics - Experience in other computer languages and tools Additional Informations: -------------------------------- - Grenoble Grenoble is 600K inhabitants city right in the middle of the French alps. It has a very big university and at least 10% of the population is made of students. Grenoble activity is turned toward high technology industry and research. Its domains of excellence are nanotechnology, computer sciences and electronic. All mountain outdoors leisure are next door (the closest ski resort is 30 minutes from downtown). - eMOTION research group The research group (www-laplace.imag.fr) is made of 25 persons (permanent researchers, engineers and PhD students). It is a very international group as presently 6 countries are represented beside France (Brazil, China, India, Italy, Mexico & Singapore). The group has a long experience (>15 years) of research in Bayesian modeling. It applies theese technics to robotics, artificial intelligence, cognitive science and developing industrial applications. The group has been the leader of the european project BIBA (Bayesian Inspired Brain and Artifacts) which, after 4 years of work, is just terminated. - BACS project: BACS is the continuation of BIBA. Its a new european project started in january for 4 years. The abstract of the project is the following: Despite very extensive research efforts contemporary robots and other cognitive artifacts are not yet ready to autonomously operate in complex real world environments. One of the major reasons for this failure in creating cognitive situated systems is the difficulty in the handling of incomplete knowledge and uncertainty. In this project we will investigate and apply Bayesian models and approaches in order to develop artificial cognitive systems that can carry out complex tasks in real world environments. We will take inspiration from the brains of mammals including humans and apply our findings to the developments of cognitive systems. The Bayesian approach will be used to model different levels of brain function, from neural functions up to complex behaviors. This will enable us to show that neural functions and higher-level cognitive activities can coherently be modeled within the Bayesian framework. The Bayesian models will be validated and adapted as necessary according to neuro-physiological data from rats and humans and through psychophysical experiments on human. The Bayesian approach will also be used to develop four artificial cognitive systems concerned with (i) autonomous navigation, (ii) multi-modal perception and reconstruction of the environment, (iii) Semantic facial motion tracking, and (iv) human body motion recognition and behavior analysis. The conducted research shall result in a consistent Bayesian framework offering enhanced tools for probabilistic reasoning in complex real world situations. The performance will be demonstrated through its applications to drive assistant systems and 3D mapping, both very complex real world tasks. - INRIA: (see http://www.inria.fr/inria/enbref.en.html) - Bayesian Programming and ProBT toolbox: Bayesian Programming is a methodology and a formalism to develop software able to deal with incomplete and uncertain information. ProBT is a C++ library that implement Bayesian inference and learning on various kind of computers and operating systems. ProBT is a commercial product (www.probayes.com) but is also available for free for research and teaching utilization (www.Bayesian-programming.org). Salary: ---------- 27K? <-> 37K?(according to qualifications) Contact: ----------- Pierre.Bessiere at imag.fr, Christian.Laugier at imag.fr _______________________________ Dr Pierre Bessi?re - CNRS ***************************** GRAVIR Lab INRIA 655 avenue de l'Europe 38334 Montbonnot FRANCE Mail: Pierre.Bessiere at imag.fr Http: www-laplace.imag.fr Tel: +33 4 76 61 55 09 _______________________________ From chunnan at iis.sinica.edu.tw Sun Apr 30 23:56:04 2006 From: chunnan at iis.sinica.edu.tw (Chun-Nan Hsu) Date: Mon, 1 May 2006 11:56:04 +0800 (CST) Subject: Connectionists: Invitation to the Machine Learning Summer School 2006 Message-ID: ** Invitation to the Machine Learning Summer School ** July 24- August 4, 2006, Taipei, Taiwan Quick Link: http://www.iis.sinica.edu.tw/MLSS2006 Registrations are now open for MLSS Taipei 2006. MLSS Taipei 2006 is the 2006 version of the "Machine Learning Summer School" series held previously in Canberra, Tubingen, Berder and Chicago. The two-week summer school program consists of about 40+ hours of tutorial lectures from 7/24 to 8/4. The late afternoon sessions will provide a chance for the participants to discuss the latest research problems with the invited speakers. This summer school will cover a broad range of subjects from statistical learning theory to state of the art applications. Please check the summer school Web site for the topics covered and the list of invited speakers. Dates: Monday 24 July to Friday 4 August 2006 (2 weeks) Location: National Taiwan University of Science and Technology, Taipei, Taiwan Important Dates: May 31, 2006: Deadline for financial aid application for students. June 7, 2006: Results of financial aid applications informed. June 20, 2006: Deadline for early registration and discounted housing. July 24, 2006: The summer school. Past Schools: http://www.mlss.cc The topics covered in this summer school include o Kernel Methods o Reinforcement Learning o Learning Ensembles o Graphical Models o Variational Methods o Online Learning o Bioinformatics o Text Mining International students are qualified for scholarships with two levels: USD 800 and USD 400. Applications will be reviewed and decided by the steering committee. For more information, go to http://www.iis.sinica.edu.tw/MLSS2006, or contact mlss at iis.sinica.edu.tw Come and enjoy a summer in Taiwan with plenty of great food! Poster (please help advertise the MLSS series in your school): http://www.iis.sinica.edu.tw/MLSS2006/flyer.pdf From cspence at sarnoff.com Wed Apr 26 10:05:06 2006 From: cspence at sarnoff.com (CLAY SPENCE) Date: Wed, 26 Apr 2006 10:05:06 -0400 Subject: Connectionists: Paper: Varying complexity in image models Message-ID: <444F7E12.4050500@sarnoff.com> The following paper appeared in the Feb. 2006 issue of IEEE Trans. on Image Proc., Vol. 15, No. 2, pp. 319-330. It's also available at http://liinc.bme.columbia.edu/publications/hip-tip.pdf. > Varying Complexity in Tree-Structured Image Distribution Models > Clay Spence, Lucas Parra, and Paul Sajda > > Abstract > > Probabilistic models of image statistics underlie many approaches in > image analysis and processing. An important class of such models have > variables whose dependency graph is a tree. If the hidden variables > take values on a finite set, most computations with the model can be > performed exactly, including the likelihood calculation, training with > the EM algorithm, etc. Crouse, et al developed one such model, the > Hidden Markov Tree (HMT). They took particular care to limit the > complexity of their model. We argue that it is beneficial to allow > more complex tree-structured models, describe the use of information > theoretic penalties to choose the model complexity, and present > experimental results to support these proposals. For these experiments > we use what we call the hierarchical image probability (HIP) > model. The differences between the HIP and the HMT models include the > use of multi-variate Gaussians to model the distributions of local > vectors of wavelet coefficients and the use of different numbers of > hidden states at each resolution. We demonstrate the broad utility of > image distributions by applying the HIP model to classification, > synthesis, and compression, across a variety of image types, namely, > electro-optical (EO), synthetic aperture radar (SAR), and mammograms > (digitized x-rays). In all cases we compare with the HMT. > > Keywords: image model, hidden Markov tree, Bayesian network, minimum > description length, hidden variables, classification, synthesis, > compression, tree-structured belief network Clay Spence From tgd at eecs.oregonstate.edu Thu Apr 27 18:21:09 2006 From: tgd at eecs.oregonstate.edu (Thomas G. Dietterich) Date: Thu, 27 Apr 2006 15:21:09 -0700 Subject: Connectionists: Post-Doc/Transfer Learning/Oregon State-MIT Message-ID: <7756-Thu27Apr2006152109-0700-tgd@cs.orst.edu> Oregon State University School of Electrical Engineering and Computer Science Join the Oregon State Machine Learning research group as a post-doc! We are looking for one or more Research Associates to drive our research in transfer learning within the DARPA-funded CALO project, whose goal is to build an integrated intelligent system for the computer desktop. You will be a member of a team jointly led by Leslie Kaelbling (MIT) and Tom Dietterich (Oregon State). Required qualifications include a Ph.D. in computer science or related field; strong mathematical background; experience with at least 3 of the following: (a) machine learning algorithms, (b) experimental machine learning methods, (c) probabilistic representation and reasoning methods including Bayesian networks, (d) logic-based representation and reasoning methods including ontology design tools; excellent written and spoken communication skills; excellent programming and software engineering skills; excitement about computer science research; and the ability to manage graduate and undergraduate students working on research projects. Position is full-time, 12 month, fixed term with reappointment at the discretion of the hiring official. For full consideration, applications must be received by 5/10/06. Send resume, letter of interest, evidence of 2 relevant publications and 3 professional references w/address, phone # to: Research Associate Search, 1148 Kelly Engineering Center, Corvallis, OR 97331-5501 or by email to sullipat at eecs.oregonstate.edu. For full position announcement see: http://oregonstate.edu/jobs, other inquires contact Thomas G. Dietterich (tgd at cs.orst.edu). OSU is an AA/EOE. Pat Sullivan Grant Coordinator ~ Intelligent Information Systems School of Electrical Engineering & Computer Science Oregon State University 2065 Kelley Engineering Center ~ Corvallis, OR 97331~5501 phone 541-737-4536 ~ fax 541-737-1300 email sullipat at eecs.oregonstate.edu