From doya at oist.jp Sun Apr 1 23:04:05 2007 From: doya at oist.jp (Kenji Doya) Date: Mon, 2 Apr 2007 12:04:05 +0900 Subject: Connectionists: Okinawa Computational Neuroscience Course 2007: Final Call for Applications References: Message-ID: <732E634A-366A-49C6-AEDA-523679F12C18@oist.jp> Application Deadline: APRIL 5TH, 2007 OKINAWA COMPUTATIONAL NEUROSCIENCE COURSE 2007 Neurons, Networks and Behaviors June 25 - July 13, 2007. Okinawa, Japan. http://www.irp.oist.jp/ocnc/2007 The aim of the Okinawa Computational Neuroscience Course is to provide opportunities for young researchers with theoretical backgrounds to learn the latest advances in neuroscience, and for those with experimental backgrounds to have hands-on experience in computational modeling. We invite graduate students and postgraduate researchers to participate in the course, held from June 25th through July 13th at an oceanfront seminar house of the Okinawa Institute of Science and Technology. Those interested in attending the course should send the materials below by e-mail or through the course web page by APRIL 5th, 2007. In the previous three years, OCNC focused on the brain's computation at different levels: Bayesian computation by neural populations (2004), learning and prediction for behavior (2005), and single neurons as computational devices (2006). This year, OCNC will be a comprehensive three-week course covering single neurons, networks, and behaviors with more time for student projects. We invite those who are interested in integrating experimental and computational approaches at each level, as well as in bridging different levels of complexity. The sponsor will provide lodging and meals during the course and support travel for those without funding. We hope that this course will be a good opportunity for theoretical and experimental neuroscientists to meet each other and to explore the attractive nature and culture of Okinawa, the southernmost island prefecture of Japan. Confirmed Lectures: Tutorial 1: math and computing for experimentalists Markus Diesmann (RIKEN) Shin Ishii (NAIST) Tutorial 2: neurobiology for theoreticians Gordon Arbuthnott (OIST) Jeff Wickens (OIST) Single Neuron Computation Tom Bartol (Salk Institute) Mike H?usser (UCL) Dieter Jaeger (Emory University) Klaus Stiefel (OIST) David Terman (Ohio State University) Network Dynamics and Information Coding Ad Aertsen (U Freiburg) Hagai Bergman (Hebrew University) Erik De Schutter (OIST) Sophie Deneve (ENS Paris) Eve Marder (Brandeis University) Behavior and Cognition Nathaniel Daw (New York University) Kenji Doya (OIST) Mitsuo Kawato (ATR) Read Montague (Baylor College of Medicine) Student Projects: a) Single neuron modeling and analysis b) Psychophysics experiments and modeling c) Behavioral experiments and modeling Students will present posters on their current works early in the course and the results of their projects at the end of the course. Sponsors: Okinawa Institute of Science and Technology (OIST) Nara Institute of Science and Technology Japanese Neural Network Society Co-organizers: Erik De Schutter: OIST Kenji Doya, OIST Jeffery Wickens, OIST Klaus Stiefel, OIST Advisors: Sydney Brenner, OIST Mitsuo Kawato, ATR Computational Neuroscience Laboratories Terrence Sejnowski, Salk Institute Torsten Wiezel, Rockefeller University ******* Application ******* Please send the following by e-mail (ocnc2007 at oist.jp) or the web application page by APRIL 5TH, 2007. 1) First name, 2) Middle initial (if any), 3) Family name, 4) Degree, 5) Date of birth, 6) Gender, 7) Nationality, 8) Affiliation (section and organization), 9) Position, 10) Advisor, 11) Postal address, 12) Nearest airpot, 13) Phone, 14) Fax, 15) E-mail, 16) Web page (if any), 17) Educational background, 18) Work experience, 19) List of publications, 20) Research interests (up to 500 words), 21) Motivations for attending the course (up to 500 words), 22) Two referees whom we can ask for reference (names, affiliations, e-mail addresses) *We don't need recommendation letters., 23) Need for travel support, 24) How you learned about the course 25) Preferred project (a:neuron, b:network, c:behavior) 26) Membership of Japanese Neural Network Society (yes/no). We will accept 30 students based primarily on their research interests (20) and motivations (21). We will also consider the balance of members' research disciplines, geographic origins, and genders. The result of selection will be informed to applicants via e-mail by April 20th. For more information, please visit the web page: http://www.irp.oist.jp/ocnc/2007 ******* Secretariat ******* Okinawa Computational Neuroscience Course Okinawa Institute of Science and Technology 12-22 Suzaki, Uruma Okinawa 904-2234, Japan Phone: +81-98-921-3933 Fax: +81-98-921-3873 Email: ocnc2007 at oist.jp ---- 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.oist.jp/ From erik at tnb.ua.ac.be Mon Apr 2 00:43:45 2007 From: erik at tnb.ua.ac.be (Erik De Schutter) Date: Mon, 2 Apr 2007 13:43:45 +0900 Subject: Connectionists: Tenured Academic Staff Computational Neuroscience Message-ID: The University of Antwerp (Belgium) is seeking to fill the following full-time vacancy (m/f) at the Department Biomedical Sciences of the Faculty Pharmaceutical, Biomedical and Veterinary Sciences: Tenured Academic Staff Computational Neuroscience Job description: The assignment consists of lecturing duties, scientific research and service to the Neuroinformatics national node and to society. During the first period of (maximum) ten years, scientific research will be the main activity. The candidate is expected to acquire external funding (national and international). Profile and requirements: - you hold a doctoral degree in (computational) neuroscience - your work interfaces well with experimental neuroscience and integrates with the research of the Laboratory for Theoretical Neurobiology - you have an international scientific CV, your academic achievements are situated within the top 10% of the broader field of study. We offer: A full-time position as ?docent? (= level of lecturer, starting annual salary of about 45,000? without bonuses) or higher, commensurate with the experience and the academic qualifications. The appointment is initially for a period of three years, after which it can become tenured depending on a favourable evaluation. The expected date of appointment is October 1, 2007 or later. Interested? Please fill out the mandatory application form (see http:// www.ua.ac.be/personeelsdienst or call +32 3 265 31 53/54) and send it to the University of Antwerp, Campus Middelheim, Personnel Department (cel AP), Middelheimlaan 1, BE-2020 Antwerpen, Belgium, at the latest on 28th April 2007. Please add to your application form: - a detailed research proposal for the next five years (5-10 pages) - a report of their previous activities of scientific research. Further information can be obtained from: Prof. Dr. D. Snyders (Dirk.Snyders at ua.ac.be), Chairman of the Department of Biomedical Sciences, regarding the profile and the description of duties; Prof. Dr. E. De Schutter (erik at tnb.ua.ac.be) for information about the Laboratory for Theoretical Neurobiology. Dr. E. Spruyt (tel. +32 3 265 30 12), Head of the Research Department, regarding the special research status; Ms. V. Bogaert (tel. +32 3 265 31 64), Head of the Academic Personnel service, regarding the terms of the appointment. From triesch at fias.uni-frankfurt.de Mon Apr 2 10:35:38 2007 From: triesch at fias.uni-frankfurt.de (Jochen Triesch) Date: Mon, 02 Apr 2007 16:35:38 +0200 Subject: Connectionists: FIAS Summer School Theoretical Neuroscience & Complex Systems (4-26 August 2007, Frankfurt, Germany) Message-ID: <461114BA.9080402@fias.uni-frankfurt.de> Announcement and Call for Applications: Frankfurt Institute for Advanced Studies (FIAS) Summer School on: Theoretical Neuroscience & Complex Systems We invite applications for a three-week summer workshop that will be held in Frankfurt, Germany from Saturday, August 4 to Sunday, August 26, 2007. The application deadline is Monday, April 30. Application instructions are described at the bottom of this document. FACULTY: Emery BROWN, Harvard and MIT, USA Peter DAYAN, Gatsby, England Sophie DENEVE, ISC and CNRS, France Yves FREGNAC*, CNRS, France Ralf GALUSKE, TU Darmstadt, Germany Wulfram GERSTNER, EPFL, Switzerland Rainer GOEBEL, Univ. Maastricht, Netherlands Christof KOCH*, Caltech, USA Wolfgang MAASS, TU Graz, Austria Christoph VON DER MALSBURG, FIAS, Germany Bartlett MEL*, USC, USA Matthias MUNK, MPI, Germany Sergio NEUENSCHWANDER, MPI, Germany Danko NIKOLIC, MPI, Germany Gordon PIPA, FIAS and MPI, Germany Kerstin SCHMIDT, MPI, Germany Terrence SEJNOWSKI, Salk Institute, USA Wolf SINGER, FIAS and MPI, Germany Jean-Jacques SLOTINE, MIT, USA Olaf SPORNS, Indiana Univ., USA Jochen TRIESCH, FIAS, Germany Misha TSODYKS, Weizmann Inst., Israel Peter UHLHAAS, MPI, Germany Carl VAN VREESWIJK, Rene Descartes Univ., France Cornelius WEBER, FIAS, Germany Michael WIBRAL, MPI, Germany Laurenz WISKOTT, HU Berlin, Germany *invited GOALS and FORMAT: 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 concepts and transferring them into the interdisciplinary field of neuroscience. The success of this will be dependent on the training of students that can bridge the different fields. The school comprises: - a 4-day pre-school to establish a common foundation and language - daily lectures by renowned international faculty - hands-on work on self-defined projects in interdisciplinary groups - a social and cultural program For details see: http://fias.uni-frankfurt.de/neuro_school/ 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 in need of financial support can apply for a limited number of reimbursements for travel expenses and waivers for the registration fee. Please indicate this in your application and provide an estimate of your travel expenses (in Euro). 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 would like work on. Information about applying and the summer school in general can be found at the website: http://www.fias.uni-frankfurt.de/neuro_school/ Applications must include: - First name, last name, gender, affiliation, valid e-mail address - Two letters of recommendation - Curriculum Vitae - Project proposal (max. one page) - Optional: request for reimbursement of travel expenses - Optional: request for waiver for registration fees Please send your documents electronically to: neuro_school at fias.uni-frankfurt.de The application deadline is April 30, 2006. Applicants will be notified by e-mail by May 26, 2006. For further information, please contact: Neuro School Frankfurt Institute for Advanced Studies Johann Wolfgang Goethe University Max-von-Laue-Str. 1 60438 Frankfurt am Main Germany email: neuro_school at fias.uni-frankfurt.de tel: +49 69 798 47531 fax: +49 69 798 47611 -- Jochen Triesch, Fellow Frankfurt Institute for Advanced Studies Web: http://fias.uni-frankfurt.de/~triesch/ Tel: +49 (0)69 798-47531 Fax: +49 (0)69 798-47611 From erik at oist.jp Wed Apr 4 21:44:59 2007 From: erik at oist.jp (Erik De Schutter) Date: Thu, 5 Apr 2007 10:44:59 +0900 Subject: Connectionists: Postdoc positions in computational neuroscience: cellular and molecular modeling Message-ID: The Computational Neuroscience Unit at the Okinawa Institute of Science and Technology (http://www.oist.jp), Japan is looking for postdocs/group leaders to work on: - reaction-diffusion modeling of signaling pathways involved in synaptic plasticity - cellular modeling of Purkinje cells with an emphasis on channel homeostasis Candidates should have experience in bottom-up modeling of neural systems and have used relevant software packages (like Kinetikit, MCell, Neuron or GENESIS, etc). They should be interested in using computational approaches like those described in: F. Santamaria, S. Wils, E. De Schutter and G.J. Augustine: Anomalous diffusion in Purkinje cell dendrites caused by dendritic spines. Neuron 52: 635-648 (2006). P. Achard and E. De Schutter: Complex parameter landscape for a complex neuron model. PLoS Computational Biology 2: e94 (2006). V. Steuber, W. Mittmann, F.E. Hoebeek, R.A. Silver, C.I. De Zeeuw, M. H?usser and E. De Schutter: Cerebellar LTD and pattern recognition by Purkinje cells. Neuron 53: 121-136 (2007). The Computational Neuroscience Unit is housed in the Seaside House of OIST, a very attractive English language working environment. OIST offers good financial conditions: a salary commensurate with previous experience and family situation, a housing allowance and a relocation package. Duration of initial appointments will depend on previous experience, appointments can last up to 5 years. Appointments can start anytime this year. Send curriculum vitae, summary of previous experience and research interests, and the names of three referees to Prof. Erik De Schutter at erik at oist.jp From ted.carnevale at yale.edu Wed Apr 4 22:42:34 2007 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Wed, 04 Apr 2007 22:42:34 -0400 Subject: Connectionists: NEURON 2007 Summer Course Message-ID: <4614621A.8010709@yale.edu> Seats are still available for the NEURON 2007 Summer Course, which will be held Saturday, June 23, through Wednesday, June 27, at The Institute for Neural Computation on the campus of the University of California, San Diego. A new topic in this year's course will be how to implement distributed models of networks. This can be used on multicore PCs, workstation clusters, and parallel supercomputers to achieve simulation speedup that is proportional to the number of processors. Registration is limited to 20, and the deadline for receipt of applications is Monday, June 4, 2007. For more information see http://www.neuron.yale.edu/neuron/sdsc2007/sdsc2007.html or contact Ted Carnevale Psychology Dept. PO Box 208205 Yale University New Haven, CT 06520-8205 USA phone 203-494-7381 fax 203-432-7172 email ted.carnevale at yale.edu From ntcrook at brookes.ac.uk Thu Apr 5 09:00:22 2007 From: ntcrook at brookes.ac.uk (Nigel Crook) Date: Thu, 05 Apr 2007 14:00:22 +0100 Subject: Connectionists: IPCAT 2007 - Paper submission deadline extended to 23rd April 2007 Message-ID: <4614F2E6.1020502@brookes.ac.uk> Apologies if you have received multiple copies of this message. The paper submission deadline for IPCAT 2007 has been extended to: *23rd April 2007* ================================================================== F I N A L C A L L F O R P A P E R S ================================================================== - I P C A T 2 0 0 7 - Seventh International Workshop on INFORMATION PROCESSING IN CELLS AND TISSUES 29, 30, 31 August, Jesus College, Oxford, United Kingdom The IPCAT workshop series is concerned with the nature of biological information and the ways in which it is processed in both biological and artificial cells and tissues. All submitted papers will be refereed by the IPCAT2007 scientific committee based on the criteria of originality, significance, quality, and clarity. Selected papers from the proceedings of IPCAT2007 will be published in a special edition of the Biosystems journal. IMPORTANT DATES - Submission deadline: *23rd April 2007 (Extended)* - Notification of acceptance: 15th June 2007 - Workshop dates: 29th - 31st August 2007 Conference Website: http://cms.brookes.ac.uk/computing/IPCAT Submission and Registration : http://sotd.brookes.ac.uk/IPCAT2007/openconf/openconf.php Kindest regards, Nigel Crook (General Chair) ntcrook at brookes.ac.uk Tjeerd olde Scheper (Programme Chair) tvolde-scheper at brookes.ac.uk From rgutier at cs.tamu.edu Thu Apr 5 20:14:20 2007 From: rgutier at cs.tamu.edu (Ricardo Gutierrez-Osuna) Date: Thu, 5 Apr 2007 19:14:20 -0500 Subject: Connectionists: Postdoctoral position available in Neurodynamics Message-ID: RESEARCH SCIENTIST POSITION AVAILABLE Department of Computer Science Texas A&M University A postdoctoral position at the level of Assistant Research Scientist is available in the Department of Computer Science at Texas A&M University, under the supervision of Prof. Ricardo Gutierrez-Osuna. The appointment will be for two years; a third year may also be available subject to approval from the sponsor. Salary will be competitive, depending on qualifications and experience. The post is available immediately. U.S. citizenship is required. Candidates should have or be close to completing a Ph.D. in Computer Science, Electrical Engineering, Applied Mathematics, or related disciplines. The project will involve neurodynamical models for the control of chemical microsensor arrays. To accomplish the overall goal of the project, applicants must have experience with dynamical systems models, pattern recognition, neural information processing, or evolutionary techniques. Programming experience is also a must. Familiarity with chemical sensors is desirable, but not essential. During the first year, work will be undertaken at the TAMU Pattern Recognition and Intelligent Sensor Machines Laboratory at TAMU. During the second year, work will be performed jointly at TAMU and at the Process Measurements Division, National Institute of Standards and Technology (Gaithersburg, MD) under the supervision of Dr. Steve Semancik. APPLICATION To be considered for the position, applicants must submit the following materials: - Curriculum vitae, including a list of publications - Statement of research interests and goals - Sample publications (refereed) - Three letters of recommendation, sent directly by the evaluators - A transcript from the institution where the Ph.D. was (or will be) earned To be assured of full consideration, all material must arrive by April 30, 2007. Applications will continue to be accepted until the position is filled. Please send materials by U.S. mail or email to: Prof. Ricardo Gutierrez-Osuna Department of Computer Science Texas A&M University Box 3112 College Station, Texas 77843-3112 Email: prism.pd at cs.tamu.edu Tel: (979) 845-2942 From c.hipp at uke.de Fri Apr 6 01:40:33 2007 From: c.hipp at uke.de (Constanze Hipp) Date: Fri, 6 Apr 2007 07:40:33 +0200 Subject: Connectionists: CALL FOR APPLICATIONS: 5th European Neuro-IT and Neuroengineering School Message-ID: <1BEE0AE8-B3EB-443B-B673-DBCE0E03AFEA@uke.de> CALL FOR APPLICATIONS: 5th European Neuro-IT and Neuroengineering School DATES: July 15-21, 2007 VENUE: Hanse Wissenschaftskolleg (Hanse-Institute for Advanced Study: www.h- w-k.de) in Delmenhorst, Germany THEME: The 5th European Neuro-IT and Neuroengineering school will focus on a new and rapidly growing field - the area of ?Neuro-IT' and ?neuroengineering' where neuroscience, cognitive science, information technology and robotics are approaching each other and starting to merge in interdisciplinary projects. It is intended to be an international, multi-disciplinary platform for junior and senior researchers and other professionals working in the field of Neuro-IT, as well as for students of engineering, physics, medicine, biology, or psychology. The 2007 summerschool will thematically focus on "Cognition & Action". Key topics of the summerschool will include: - Executive functions, action planning & decision making - Movement preparation, skills, habits - Neuroprosthetics & brain-machine interfaces - Emotions, social cognition & reward mechanism The school is organized and funded by two European networks: - Neuro-IT.net (www.neuro-it.net) - a network that aims at developing the field of neuroengineering - euCognition.org (www.eucognition.org) - a network fostering the development of artificial cognitive systems ORGANIZERS: - Andreas K. Engel (University Medical Center Hamburg-Eppendorf, Hamburg/Germany) - Alois Knoll (Technical University of Munich, Munich/Germany) - Rolf Pfeifer (University of Zurich, Zurich/Switzerland) FACULTY: Confirmed speakers are: - Izhar Bar-Gad (Bar-Ilan University, Ramat-Gan/Israel) - Kerstin Dautenhahn (University of Hertfordshire, Hatfield/UK) - Paolo Dario (ARTS, Pisa/Italy) - Rainer Goebel (University of Maastricht, Maastricht/Netherlands) - Auke Ijspeert (EPFL, Lausanne/Switzerland) - G?nther Knoblich (Rutgers, Newark/USA) - Peter K?nig (University of Osnabr?ck, Osnabr?ck/Germany) - Konrad K?rding (Northwestern University, Chicago, USA) - Ezequiel di Paolo (University of Sussex, Brighton/UK) - Hanspeter Scherberger (University of Zurich, Zurich/Switzerland) - Tania Singer (University of Zurich, Zurich/Switzerland) - Andrew Schwartz (University of Pittsburgh, Pittsburgh/USA) - Tom Ziemke (University of Sk?vde, Sk?vde/Sweden) PARTICIPANTS: A total of 50 participants will be admitted on the basis of their publication record (evaluated relative to career status) and the relatedness of the candidate's own research to the theme of the school. The willingness to actively participate in several activities is a prerequisite to attend the school. More information on the school and on how to apply can be found on http://www.neuro-it.net/Activities/Delmenhorst2007/ We are looking forward to your application! -------------------------------------------------------------------- Andreas K. Engel, M.D., Ph.D. Professor of Physiology Adjunct Professor of Psychology Director Dept. of Neurophysiology and Pathophysiology Center of Experimental Medicine University Medical Center Hamburg-Eppendorf Martinistr. 52 20246 Hamburg Germany Phone: +49-40-42803-6170 Fax: +49-40-42803-7752 Email: ak.engel at uke.uni-hamburg.de URL: www.uke.uni-hamburg.de URL: www.40hz.net -------------------------------------------------------------------- From masulli at disi.unige.it Fri Apr 6 05:10:31 2007 From: masulli at disi.unige.it (Francesco Masulli) Date: Fri, 6 Apr 2007 11:10:31 +0200 Subject: Connectionists: CFA: Post-IJCNN 2007 workshop on COMPUTATIONAL INTELLIGENCE APPROACHES FOR THE ANALYSIS OF BIOINFORMATICS DATA Message-ID: <200704061110.32156.masulli@disi.unige.it> Please, accept our apologies for multiple postings. ============================================== CALL FOR ABSTRACTS International Joint Conference on Neural Networks 2007 POST-CONFERENCE WORKSHOP ON COMPUTATIONAL INTELLIGENCE APPROACHES FOR THE ANALYSIS OF BIOINFORMATICS DATA CI-BIO 2007 http://ci-bio2007.disi.unige.it/ August 17th, 2007 Renaissance Orlando Resort at SeaWorld, Florida, USA SPONSORED BY THE INNS BIOINFORMATICS SIG SCOPE & TOPICS Bioinformatics is a fast growing scientific area aimed at managing, analyzing and interpreting information from biological data, sequences and structures. In the past few years, many Computational Intelligence approaches have been successfully applied to the solution of complex problems typical of this field, including signal and image processing, clustering, feature selection, data visualization, and data mining. CI-BIO 2007 will present surveys and contributed papers covering different areas where neural, fuzzy, and genetic approaches have been successfully applied to the analysis of Bioinformatics data. INTERNATIONAL PROGRAM COMMITTEE Pierre Baldi, University of California, Irvine, CA, USA Jake Chen, Purdue University Indianapolis, IN, USA Alexessander Couto Alves, University of Porto, Purtugal Alexandru Floares, Oncological Institute Cluj-Napoca, Romania Jon Garibaldi, University of Nottingham, UK Luciano Milanesi, CNR-ITB, Milano, Italy David Alejandro Pelta, University of Granada, Spain Leif Peterson, The Methodist Hospital, Houston, TX, USA Giorgio Valentini, University of Milan, Italy Jean-Philippe Vert, Ecole des mines de Paris, France INVITED SPEAKER Mark A. Kon, Department of Mathematics and Statistics, Boston University CONTRIBUTION TO THE WORKSHOP We request two kinds of contributions: * surveys papers giving overviews of innovative Computational Intelligence approaches to a specific Bioinformatics area * standard papers presenting new results not already presented at the IJCNN 2007. Standard papers accepted as oral will be presented in a slot of 15-20 min, while survey papers will have a slot of 30-60 min for oral presentation (details will be communicated to the authors by the end of June). Submission of Contributions Extended abstracts submission for the Workshop Notes Extended abstracts no longer than 2 pages must be prepared in Latex following the same style of IJCNN 2007 papers (IEEEtran.cls and a sample tex file are available here). By 10 May 2007 the authors must submit the PDF file with an email to ci-bio2007 at disi.unige.it In the email they must specify: (1) Paper title; (2) Survey/Standard paper (3) Keywords; (4) Authors names and affiliations; (5) Corresponding author's name and contact details, including telephone/fax numbers and e-mail address. ON-LINE PAPER PUBLICATION The authors of accepted abstracts must prepare the final paper in Latex following the same style of IJCNN 2007 papers (IEEEtran.cls and a sample tex file are available here). Papers must be submitted by 15 June 2007 in PDF format with an email to ci-bio2007 at disi.unige.it The papers will be published on-line on this web site. POST-WORKSHOP PUBLICATION We are making agreements with the editor of an international scientific journal in order to publish a special journal issue including extended versions of a selection of papers presented at CI-BIO workshop. IMPORTANT DATES Extended abstract submission deadline: 10 May 2007 Notification of acceptance: 20 May 2007 Accepted papers due: 15 June 2007 Slides of presentations due: 1 July 2007 Workshop: 17 August 2007 Best regards, Francesco Masulli, Univ. Genova (Italy) Roberto Tagliaferri, Univ. Salerno (Italy) CI-BIO 2007 organizers - ************************************************************************* CI-BIO 2007 WORKSHOP ON COMPUTATIONAL INTELLIGENCE APPROACHES FOR THE ANALYSIS OF BIOINFORMATICS DATA http://ci-bio2007.disi.unige.it/ email: ci-bio2007 at disi.unige.it August 17th, 2007 Renaissance Orlando Resort at SeaWorld, Florida, USA ************************************************************************* - From laurent.bougrain at loria.fr Mon Apr 9 16:50:18 2007 From: laurent.bougrain at loria.fr (Laurent Bougrain) Date: Mon, 09 Apr 2007 22:50:18 +0200 Subject: Connectionists: Post-Doctoral position at INRIA, Nancy, France Message-ID: <461AA70A.4070108@loria.fr> [Apologies for cross-posting] ----------------------------- One year post-doctoral position in the INRIA-Cortex research project (http://cortex.loria.fr), Nancy, France Main topic : Brain-Computer Interface Scientific context : Brain-computer interface (BCI) system is a potentially powerful new communication and control option for those with severe motor disabilities. BCI system translates brain-activity into commands for a computer or other devices. In other words, a BCI allows users to act on their environment by using only brain-activity [1]. The success of this approach depends on close and productive interaction of scientists, engineers, and clinicians from many different disciplines and requires recognition and attention to a number of crucial issues. This offer is designed to foster such interdisciplinary interactions and thereby promote the development of BCI systems of practical value to people with disabilities using a non-invasive approach. Electroencephalography (EEG) is the most studied potential non-invasive interface, mainly due to its fine temporal resolution, ease of use, portability and low set-up cost. Unfortunately, non-invasive implants produce poor signal resolution because the skull dampens signals, dispersing and blurring the electromagnetic waves created by the neurons. Although the waves can still be detected it is more difficult to determine the area of the brain that created them or the actions of individual neurons. But as well as the technology's susceptibility to noise, another substantial barrier to using EEG as a brain-computer interface is the extensive training required before users can work the technology. Patterns of P300 waves are generated involuntarily (stimulus-feedback) when people see something they recognize and may allow BCIs to decode categories of thoughts without training patients first. The Cortex project-team challenge is to develop neural networks to understand information processing in the brain and design numerical distributed and adaptive algorithms in interaction with biology and medical science. The project has recently bought a 32-channels high definition EEG/ERP amplifier by A.N.T. and wishes to use its experience on EEG signal analysis using neural networks to achieve this challenge. The candidate will come and reinforce this strategic goal. Description of the post-doc activities : The candidate will use is experience on ERP analysis to define an experimental protocol for healthy persons to collect measures on which a P300-based BCI system will be trained. Several classification techniques [2] will be compared including spatio-temporal artificial neural networks [3] to obtain high classification accuracy. The effect of different electrode configurations on classification accuracy will be also tested. Applicant's required skills : The Ph.D has to have strong knowledge in signal analysis and be familiar with EEG/ERP analysis. Basis knowledge in neurophysiology or in cognitive science will be appreciated. Experience using A.N.T. Amplifier will be also appreciated. The thesis defense should be RECENT (after the 1st of may 2006). To apply for, please send a CV and a covering letter to : http://www.talentsplace.com/syndication1/inria/ukpostdoc/details.html?id=PNGFK026203F3VBQB6G68LOE1&LOV5=4508&LOV6=4513&LG=EN&Resultsperpage=20&nPostingID=1168&nPostingTargetID=3219&option=52&sort=DESC&nDepartmentID=19 Reference letters should be send directly to : bougrain at loria.fr DEADLINE : 15 April 2007 --------------------------------------------------------- Bibliography : [1] Wolpaw J.R. et al. Brain-computer interfaces for communication and control. Clinical Neurophysiology, 113:767-791 (2002). [2] Lotte F., Congedo M., L?cuyer A., Lamarche F., Arnaldi B., "A Review of Classification Algorithms for EEG-based Brain-Computer Interfaces", Journal of Neural Engineering, 4, R1-R13, (2007). [3] Neji Ben Salem Z., Bougrain L., Alexandre F. Spatio-Temporal and Complex-Valued Models based on SOM map applied to Speech Recognition. Workshop on Complex valued neural networks and neuro-computing: novel methods, applications and implementations. Twentieth International Joint Conference on Artificial Intelligence - IJCAI (2007) From Igor.Aizenberg at tamut.edu Tue Apr 10 12:35:36 2007 From: Igor.Aizenberg at tamut.edu (Igor Aizenberg) Date: Tue, 10 Apr 2007 11:35:36 -0500 Subject: Connectionists: Paper on new complex-valued neural network with derivative-free learning Message-ID: Dear Connectionists, I would like to announce a new paper on a new complex-valued feedforward neural network with a highly efficient derivative-free backpropagation learning algorithm published by the Springer's Soft Computing journal: Igor Aizenberg and Claudio Moraga. "Multilayer Feedforward Neural Network based on Multi-Valued Neurons and a Backpropagation Learning Algorithm", Soft Computing, Vol. 11, No 2, January, 2007, pp. 169-183. The paper is available at http://www.freewebs.com/igora/PUBLICATIONS/Soft_Computing_Aizenberg-Mora ga_2007.pdf Abstract. A multilayer neural network based on multi-valued neurons is considered in the paper. A multi-valued neuron (MVN) is based on the principles of multiple-valued threshold logic over the field of the complex numbers. The most important properties of MVN are: the complex-valued weights, inputs and output coded by the kth roots of unity and the activation function, which maps the complex plane into the unit circle. MVN learning is reduced to the movement along the unit circle, it is based on a simple linear error correction rule and it does not require a derivative. It is shown that using a traditional architecture of multilayer feedforward neural network (MLF) and the high functionality of the multi-valued neuron, it is possible to obtain a new powerful neural network. Its training does not require a derivative of the activation function and its functionality is higher than the functionality of MLF containing the same number of layers and neurons. These advantages of MLMVN are confirmed by testing using parity n, two spirals and "sonar" benchmarks and the Mackey-Glass time series prediction. Your comments are very welcome. Best regards, Igor ________________ Dr. Igor Aizenberg Texas A&M University-Texarkana Department of Computer and Information Sciences P.O. Box 5518, 2600 N. Robison Rd. Texarkana, Texas 75505 USA Phone: (1 903) 223-3183; Fax: (1 903) 223-3189; Skype: igor_aizenberg e-mail: igor.aizenberg at tamut.edu or igor.aizenberg at gmail.com URL: http://www.freewebs.com/igora From rhaschke at techfak.uni-bielefeld.de Wed Apr 11 10:52:47 2007 From: rhaschke at techfak.uni-bielefeld.de (Robert Haschke) Date: Wed, 11 Apr 2007 16:52:47 +0200 Subject: Connectionists: WSOM 2007: deadline extension Message-ID: <461CF63F.2020404@techfak.uni-bielefeld.de> *********************************************************** D E A D L I N E E X T E N S I O N 6th Int. Workshop on Self-Organizing Maps (WSOM 2007) September 3rd - 6th 2007, Bielefeld, Germany http://www.wsom07.org *********************************************************** Due to several requests we are pleased to announce that the final submission deadline for papers has been extended until April 22th. The 6th International Workshop on Self-Organizing Maps will bring together researchers and practicioners in the field of self-organizing systems, with a particular emphasis on neural networks and self-organizing maps. It will highlight key advances in these and related fields. It is the sixth conference in a series of bi-annual international conferences started with WSOM'97 in Helsinki. The programme committee cordially invites you to attend WSOM 2007 and submit papers on all aspects of self-organizing systems including: * Self-organization * Unsupervised learning (including PCA/NLPCA, ICA/NLICA, Principal Curves/Surfaces) * Signal processing, image processing and vision * Robotics and Intelligent Systems * Data visualization, mining and sonification * Bioinformatics * Text and document analysis * Financial analysis * Time-series analysis * Theory and extensions * Optimization * Hardware and architecture Papers will be peer reviewed by an international program committee according to the criteria pertinence, scientific quality, impact, generality, and innovation. High-quality submissions will be selected for oral or poster presentation during the conference. Sincerely Your WSOM organizers From v.steuber at herts.ac.uk Thu Apr 12 10:04:10 2007 From: v.steuber at herts.ac.uk (Volker Steuber) Date: Thu, 12 Apr 2007 15:04:10 +0100 Subject: Connectionists: PhD Studentship in Computational Neuroscience Message-ID: <461E3C5A.3000707@herts.ac.uk> PhD Studentship in Computational Neuroscience Applications are invited for a 3 year PhD Studentship in Computational Neuroscience in the Science and Technology Research Institute at the University of Hertfordshire, UK. The studentship will cover a stipend of ?12,300 per year plus payment of the standard UK student fees. Candidates should be interested in information processing in biologically detailed models of neuronal networks. Our research involves close collaborations with experimentalists in Europe and the USA. More details can be found in these recent publications: Steuber, V., Mittmann, W., Hoebeek, F.E., Silver, R.A., De Zeeuw, C.I., Hausser, M. and De Schutter, E. (2007). Cerebellar LTD and pattern recognition by Purkinje cells. Neuron 54, 121-136. Gleeson, P. Steuber, V. and Silver, R.A. (2007). neuroConstruct: A tool for modeling networks of neurons in 3D space. Neuron, in press. Applicants should have good computational and numerical skills and a good first degree in maths, computer science, physics, neuroscience or biology. Previous experience in neuroscience is not required but would be an advantage. The UH Science and Technology Research Institute has been rated as 4 (national excellence with evidence of international excellence) at the last UK university research assessment exercise. It is located in Hatfield in Hertfordshire, just north of London. Applications including a CV, the contact details of two referees and a short statement of research interests should be sent by email to Volker Steuber (v.steuber at herts.ac.uk). Dr Volker Steuber Senior Lecturer (Research) in Biocomputation Science and Technology Research Institute University of Hertfordshire Hatfield Herts AL10 9AB UK Tel +44 1707 284350 http://homepages.feis.herts.ac.uk/~comqvs/ From dk at physics.ucsd.edu Thu Apr 12 15:39:56 2007 From: dk at physics.ucsd.edu (David Kleinfeld) Date: Thu, 12 Apr 2007 12:39:56 -0700 Subject: Connectionists: MBL Summer School on Neuronal Data Analysis Message-ID: Dear Colleague, I write to inform you of the opportunity for graduate students, post-docs and colleagues to participate in the MBL special topics courses, described at the link below, devoted to neuronal data analysis and modeling with a focus on spectra and statistics. This course attracts leaders in the field to teach a unique and intensive schedule. In addition faculty and students have numerous opportunities for informal discussion and to analyze real data sets. We believe that the educational experience and the ability to network with leading scientists from many institutions, provided by our courses, is not available at any single home institution. Substantial financial aid is available to defray the cost of tuition. Neuroinformatics Course Date: August 11 - 26, 2007 Directors: Emery Brown, MIT and MGH David Kleinfeld, UCSD Partha Mitra, CSHL Application Deadline: April 20, 2007 http://www.mbl.edu/education/courses/special_topics/neufo.html This course contains pedagogical lectures on basic statistical techniques as well as focused mini-workshops on specific neuroscience topics where applications of these techniques are critical. Thank you in advance for passing on this information. Based on comments from alumni this educational experience has had a profound effect on their scientific career. Sincerely, Lenny Dawidowicz, Ph.D. Director of Education -- David Kleinfeld Professor - Department of Physics Office/Voice mail: +1(858)822-0342 University of California at San Diego Laboratory: +1(858)534-3562 7202 Urey Hall (Express Delivery) Fax: +1(858)534-7697 9500 Gilman Drive (Postal Service) E-mail: dk at physics.ucsd.edu La Jolla, California 92093-0374 http://www-physics.ucsd.edu/neurophysics/ From mail at hinnerkf.de Fri Apr 13 05:54:13 2007 From: mail at hinnerkf.de (Hinnerk Feldwisch) Date: Fri, 13 Apr 2007 11:54:13 +0200 Subject: Connectionists: Announcement for the Seizure Prediction Workshop in Freiburg, Germany Message-ID: Dear Colleagues, >From September 29th until October 2nd, Freiburg will host the "3rd International Workshop on Epileptic Seizure Prediction": http://epilepsy.uni-freiburg.de The workshop is not dedicated to seizure prediction alone but to all research areas that are related to the prediction of epileptic seizures. Thus, the topics range from modeling single cell behavior via modeling complex networks to ready to apply seizure prediction techniques and the performance evaluation thereof. Experts in seizure detection and seizure control will also contribute to the workshop. For more information, please refer to http://epilepsy.uni-freiburg.de/seizure-prediction-workshop-2007. Talks and posters providing an overview of the state of the art in their fields will be complemented by presentations of more recent results. Abstracts submission is open until June 1st, 2007 through http://epilepsy.uni-freiburg.de/seizure-prediction-workshop-2007/abstract-su bmission. Several world-leading experts in their fields have already agreed to participate at the conference either in the organization committee or as outstanding lecturers. Moreover, we set up a seizure prediction competition. Details can be found here: http://epilepsy.uni-freiburg.de/seizure-prediction-workshop-2007/prediction- contest Please feel free to redistribute this message to possibly interested colleagues. We are looking forward to meeting you in Freiburg, Andreas Schulze-Bonhage, Jens Timmer, Hinnerk Feldwisch and Bj?rn Schelter From renaud.jolivet at epfl.ch Fri Apr 13 08:46:53 2007 From: renaud.jolivet at epfl.ch (Renaud Jolivet) Date: Fri, 13 Apr 2007 14:46:53 +0200 Subject: Connectionists: Workshop: Predicting every spike? Message-ID: <461F7BBD.3000007@epfl.ch> We would like to announce a workshop on Quantitative Neuron Modeling: Predicting every spike? June 25-26, 2007 EPFL, Lausanne, Switzerland http://lcn.epfl.ch/~gerstner/QuantNeuronMod2007/ AIMS: Recently, there have been efforts in several labs towards quantitative neuron models by measuring the model quality over lots of different paradigms - including spike-by-spike predictions for time-dependent input. The aim of the workshop will be to bring these people together, compare methods, and maybe get into a discussion of: 1. What are suitable generic sets of stimuli to test neuron models? 2. What are suitable measures to quantify and optimize the quality of neuron models? We have also opened a challenge: Predicting Single-Neuron Behavior http://lcn.epfl.ch/~gerstner/QuantNeuronMod2007/challenge.html The results will be discussed at the workshop. The number of participants in the workshop will be limited to facilitate discussions. The organization committee Arnd Roth (UCL London) Felix Schuermann (EPFL and Blue Brain Project) Renaud Jolivet (UNIL, Center for Psychiatric Neuroscience) Wulfram Gerstner (EPFL, Brain Mind Institute) -- Renaud Jolivet PhD Neuroscience, MSc Physics, EPFL EPFL Brain Mind Institute Station 15 CH-1015 Lausanne URL: http://icwww.epfl.ch/~rjolivet Tel: +41 21 693 1652 From minikurian at gmail.com Sun Apr 15 08:38:31 2007 From: minikurian at gmail.com (Mini P Kurian) Date: Sun, 15 Apr 2007 08:38:31 -0400 Subject: Connectionists: CNS 2007 : Workshop In-Reply-To: References: Message-ID: Call for Participation: Workshop on *Neuro-Machine Interfaces: Integrating Biology and Technology to Develop Functionally Relevant Devices CNS 2007 Toronto, Canada July 12, 2007 **http://www.cnsorg.org/cns_meeting_workshops.htm * *Description:* A half-day* *workshop. Website: http://www.public.asu.edu/~mputhaya/CNS2007Workshop/ ** Neuroprosthetics are artificial extensions that replace or improve the function of an impaired nervous system. Some examples of neuroprosthetics include: cochlear implants, retinal implants, cortical implants, and functional neuromuscular stimulation (FNS) electrodes. Neuro-machine interfaces (NMI) use neuroprosthetics to read signals from neurons and then computers and algorithms are used to translate those signals into desired actions. Successful development of functional neuroprosthetics requires an interdisciplinary approach, involving experimentalists to understand the physiology and behavior of the nervous system, engineers to develop adaptive biocompatible devices, clinicians to implement and study the interaction between the device and the patient, and computational modelers to integrate the diverse approaches. There are still many important issues that must be addressed for NMI development, such as a need for fully-implantable biocompatible devices, real-time computational algorithms, efficient neural signal acquisition and processing, and improved sensory feedback with links to motor output. Perhaps the most important issue in NMI development is optimizing the behavior of the combined system (biological and technological) by fully utilizing the plasticity of the nervous system. How can computational neuroscience help address these issues? This workshop will explore some of the major challenges in interfacing biological adaptive systems with adaptive NMI devices: - Given that the human nervous system is more complex than *in vitro*preparations and different from *in vivo* animal models how do we transform an experimental device from a laboratory setting to a clinically relevant device? - How can computational neuroscientists help in improving the design of experimental devices? How biologically accurate do models have to be, and on what scales, in order to positively contribute to technological development? - There is a problem in NMI of both too little and too much data. The number of channels available to interact with the nervous system is limited, while the amount of raw *voltage vs. time* data acquired from probes can be overwhelming. How can computational neuroscientists help to maximize use of limited channel data, while extracting only useful information? - How do we incorporate and take advantage of the properties of the musculoskeletal system in order to maximize the utility and effectiveness of NMI devices? - The nervous system is adaptive, so NMI control algorithms have to be versatile enough to accommodate this plasticity. How can we design NMI control algorithms that promote adaptive plasticity in the nervous system throughout the time course of that adaptation? * **Structure:* This will be a half-day workshop, consisting of two or three invited talks, additional short presentations, and a panel discussion. Attendance is open to all CNS attendees. Those interested in presenting are invited to contact the workshop organizer. *Contact*: kurian at mathpost.la.asu.edu *Organizers:* Mini Kurian1, 4, Joe Graham 2, 4, Sharon Crook1, 3, 4, Ranu Jung2, 4 1Department of Mathematics and Statistics 2Harrington Department of Bioengineering 3School of Life Science 4Center for Adaptive Neural Systems at the Biodesign Institute Arizona State University From ishikawa at brain.kyutech.ac.jp Mon Apr 16 04:10:01 2007 From: ishikawa at brain.kyutech.ac.jp (Masumi Ishikawa) Date: Mon, 16 Apr 2007 17:10:01 +0900 Subject: Connectionists: ICONIP2007 Last Call for Papers: Submission deadline is May 1 Message-ID: <7.0.0.16.2.20070416165907.09646d28@brain.kyutech.ac.jp> ICONIP2007 Last Call for Papers 14th International Conference on Neural Information Processing Kitakyushu, Japan November 13-16, 2007 http://www.iconip07.org/ Sponsors: Asia Pacific Neural Network Assembly (APNNA) Japanese Neural Network Society (JNNS) 21st Century COE Program, Kyushu Institute of Technology Co-sponsors: RIKEN Brain Science Institute Advanced Telecommunications Research Institute International (ATR) Japan Society for Fuzzy Theory and Intelligent Informatics (SOFT) IEEE CIS Japan Chapter Fuzzy Logic Systems Institute (FLSI) Papers are solicited for, but not limited to, the following five Tracks: ?1. Computational Neuroscience ?2. neural network models and learning ??(learning algorithms, ICA, SVM, SOM, etc.) ?3. Vision and motor control ??(robot vision, pattern recognition, motor control, visuomotor control, etc.) ?4. Hardware and Applications ??(hardware, signal processing, medical applications, fuzzy, robotics, etc.) ?5. Novel approaches ??(EC, BMI, cognitive science, hybrid systems, brain-like systems, adaptive intelligent systems, etc.) A full paper of up to 10 pages in the Springer LNCS style is to be submitted by May 1, 2007. Ten pages in the Springer LNCS style is roughly equivalent in length to 6 pages in the IEEE Proceedings style. A duly revised accepted paper up to 10 pages in the Springer LNCS style and 1-page abstract are to be submitted by August 1, 2007. During the conference, the conference provides attendees printed abstracts and downloadable provisional electronic proceedings. After the conference, those who wish to revise full papers can resubmit revised version by December 15, 2007. Post conference CD-ROM proceedings and optional paper proceedings will be sent to attendees a few months after this. Important dates: ?Deadline for submission of full papers : May 1, 2007 ?Decision notification : July 1, 2007 ?Camera-ready papers and 1 page abstract due : August 1, 2007 ?Deadline for Authors? registration : August 1, 2007 ?Revision of papers due (if any) : December 15, 2007 Proceedings: Presented papers will be published as post-conference proceedings by Springer (Lecture Notes in Computer Science, LNCS) Keynote Speech Mitsuo Kawato, ATR Computational Neuroscience Laboratories Title: Cerebellar Long Term Depression as a Supervised Learning Rule with All or Nothing Character at Each Synapse Plenary Talks Shin Ishii, Nara Institute of Science and Technology Title: Modeling decision making in a partially observable domain Yoshiyuki Kabashima, Tokyo Institute of Technology Titie: Statistical mechanical approach to CDMA communication -- an offspring of research on perceptrons and associative memory -- Frederic Kaplan, EPFL, Switzerland Title: Curiosity-driven development Andrew Y. Ng, Stanford University Title: STAIR: The STanford Artificial Intelligence Robot project Rajesh P. N. Rao, University of Washington Title: Brain-inspired models of Bayesian computation, with applications to humanoid robotics and brain-machine interfaces Journal Special Issues: Cognitive Neurodynamics Neural Information Processing-Letters and Reviews Intelligent Automation and Soft Computing International Journal of Innovative Computing, Information and Control Neural Networks (Selected papers will be recommended for publication) Call for Tutorials ?ICONIP 2007 will feature pre-conference tutorials dedicated especially to young researchers and Ph.D. students. The tutorials cover fundamental and advanced topics in neural information processing (broardly defined). The proposal for tutorials are to be submitted by e-mail to the secretary of ICONIP at with the name, affiliation, address, country of the speaker, the title of tutorials, 5-10 keywords, 200-word abstract including motivation, appeal to the conference attendees, expected effectiveness, recommended fields, etc. Deadline for proposal of tutorials is extended to 1 May, 2007 and notification of acceptance will be done by 31 May, 2007. The selected tutorial speakers will be financially supported by the conference, concerning the international/domestic air flight, the accommodation and the registration. Call for Demonstrations Important dates: Deadline for proposal :15 July, 2007 Decision notification : 1 August, 2007 Deadline for Demonstrators?registration : 15 August, 2007 Final demonstraction abstract due : 1 September, 2007 Organizing Committees: General Chair: Takeshi Yamakawa (KIT, Japan) Organizing Committee Chair: Shiro Usui (RIKEN, Japan) Steering Committee Chair: Takeshi Yamakawa (KIT,Japan) Program Co-chairs: Masumi Ishikawa (KIT, Japan), Kenji Doya (OIST, Japan) Brain IT Special Sessions Chair: Hatsuo Hayashi (KIT, Japan) Tutorials Chair: Hirokazu Yokoi (KIT, Japan) Exhibitions Chair: Masahiro Nagamatsu (KIT, Japan) Local Arrangement Chair: Satoru Ishizuka (KIT, Japan) Web Master: Tsutomu Miki (KIT, Japan) Publications Chair: Hiroyuki Miyamoto (KIT, Japan) Publicity Chair: Hideki Nakagawa (KIT, Japan) Secretary: Katsumi Tateno (KIT, Japan) Program Co-Chairs Masumi Ishikawa Department of Brain Science and Engineering Graduate School of Life Science and Systems Engineering Kyushu Institute of Technology 2-4 Hibikino, Wakamatsu, Kitakyushu 808-0196, Japan Tel and Fax: +81-93-695-6106 http://www.brain.kyutech.ac.jp/~ishikawa 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 tobias at nld.ds.mpg.de Wed Apr 18 09:47:14 2007 From: tobias at nld.ds.mpg.de (Tobias Niemann) Date: Wed, 18 Apr 2007 15:47:14 +0200 Subject: Connectionists: Bernstein Fellows - Independent Research Positions in Computational Neuroscience In-Reply-To: <461DE9BD.2060606@nld.ds.mpg.de> References: <461DE9BD.2060606@nld.ds.mpg.de> Message-ID: <46262162.3040007@nld.ds.mpg.de> We invite applications for Independent Research Positions in Computational Neuroscience at the Bernstein Center for Computational Neuroscience (BCCN) in G?ttingen, Germany. G?ttingen is a center of neuroscience in Europe hosting numerous internationally recognized neuroscience research institutions, including three Max Planck Institutes, the European Neuroscience Institute, the German Primate Research Center, and the Center for Systems Neuroscience (ZNV) and the Center for the Molecular Physiology of the Brain (CMPB). The BCCN integrates theoretical and experimental research groups from these institutions to foster interdisciplinary research in computational neuroscience specifically supporting close collaboration between theorists and experimental researchers. We are looking for strong research personalities, who are experienced in the field of Computational Neuroscience and/or related disciplines such as theoretical physics, biophysics, mathematics, or computer science and with commitment to a research career in neuroscience. Prior biological or neuroscience training is desirable. The Bernstein Fellow will have the opportunity to collaborate with other members of the BCCN or to pursue an independent research program complementing the activities of the BCCN. Initially the positions are limited to two years and may be extended to up to three years. Application deadline is 31 May 2007. Please submit your application preferably in one single PDF-document, including cover letter, CV, list of publications, research proposal/interests, names of three referees, relevant certificates, and copies of three of your most important publications to: jobs at bccn-goettingen.de (Subject: Bernstein Fellow) For more information please refer to http://www.bccn-goettingen.de While e-mail is preferred, applications may also be submitted in hardcopy to the following address: Prof. Dr. Theo Geisel Keyword: Bernstein Fellow Bernstein Center for Computational Neuroscience (BCCN) G?ttingen Max Planck Institute for Dynamics and Self-Organization Bunsenstrasse 10 D - 37073 G?ttingen, Germany The BCCN is an equal opportunity employer. From t.heskes at science.ru.nl Wed Apr 18 11:51:11 2007 From: t.heskes at science.ru.nl (Tom Heskes) Date: Wed, 18 Apr 2007 17:51:11 +0200 Subject: Connectionists: Neurocomputing volume 70 (issues 7-9) Message-ID: <46263E6F.4030502@science.ru.nl> Neurocomputing volume 70 (issues 7-9) ------- SPECIAL PAPERS (European Symposium on Artificial Neural Networks 2006 edited by Michael Biehl, Erzs?bet Mer?nyi and Fabrice Rossi) Advances in computational intelligence and learning (editorial) Michael Biehl, Erzs?bet Mer?nyi and Fabrice Rossi Displaced strategies optimize connectivity in neocortical networks Andreas Herzog, Karsten Kube, Bernd Michaelis, Ana D. de Lima and Thomas Voigt Learning sensory representations with intrinsic plasticity Nicholas J. Butko and Jochen Triesch Super-lampreys and wave energy: Optimised control of artificially-evolved, simulated swimming lamprey Leena N. Patel, Alan Murray and John Hallam Immune network based ensembles Nicol?s Garc?a-Pedrajas and Colin Fyfe Nonlinear transient computation Nigel Crook Dynamical computation reservoir emerging within a biological model network Carlos Louren?o Massively distributed digital implementation of an integrate-and-fire LEGION network for visual scene segmentation Bernard Girau and Cesar Torres-Huitzil Adaptive sensor modelling and classification using a continuous restricted Boltzmann machine (CRBM) Tong Boon Tang and Alan F. Murray Minimum range approach to blind partial simultaneous separation of bounded sources: Contrast and discriminacy properties Fr?d?ric Vrins and Dinh-Tuan Pham Margin-based active learning for LVQ networks F.-M. Schleif, B. Hammer and T. Villmann Magnification control for batch neural gas Barbara Hammer, Alexander Hasenfuss and Thomas Villmann Adaptive scene dependent filters for segmentation and online learning of visual objects J.J. Steil, M. G?tting, H. Wersing, E. K?rner and H. Ritter Linking non-binned spike train kernels to several existing spike train metrics Benjamin Schrauwen and Jan Van Campenhout Synthesis of maximum margin and multiview learning using unlabeled data Sandor Szedmak and John Shawe-Taylor High-dimensional delay selection for regression models with mutual information and distance-to-diagonal criteria Geoffroy Simon and Michel Verleysen Resampling methods for parameter-free and robust feature selection with mutual information D. Fran?ois, F. Rossi, V. Wertz and M. Verleysen Variants of unsupervised kernel regression: General cost functions Stefan Klanke and Helge Ritter Visualizing distortions and recovering topology in continuous projection techniques Micha?l Aupetit -------- REGULAR PAPERS RLDDE: A novel reinforcement learning-based dimension and delay estimator for neural networks in time series prediction F. Liu, G.S. Ng and C. Quek Improving generalization of MLPs with sliding mode control and the Levenberg?Marquardt algorithm Marcelo Azevedo Costa, Ant?nio de P?dua Braga and Benjamin Rodrigues de Menezes Applying the improved fuzzy cellular neural network IFCNN to white blood cell detection Wang Shitong, Korris F.L. Chung and Fu Duan A novel approach for estimation of optimal embedding parameters of nonlinear time series by structural learning of neural network Yusuke Manabe and Basabi Chakraborty Learning principal directions: Integrated-squared-error minimization Jong-Hoon Ahn, Jong-Hoon Oh and Seungjin Choi An analysis of global exponential stability of bidirectional associative memory neural networks with constant time delays Weirui Zhao, HuanShui Zhang and Shulan Kong A biophysical neural accumulator model of decision making in an antisaccade task Vassilis Cutsuridis, Ioannis Kahramanoglou, Nikolaos Smyrnis, Ioannis Evdokimidis and Stavros Perantonis Genetic tolerance fuzzy neural networks: From data to fuzzy hyperboxes Witold Pedrycz Modelling the Stroop effect: A connectionist approach G. B?y?kaksoy Kaplan, N.S. S,eng?r, H. G?rvit and C. G?zelis, Generalized locally recurrent probabilistic neural networks with application to text-independent speaker verification Todor D. Ganchev, Dimitris K. Tasoulis, Michael N. Vrahatis and Nikos D. Fakotakis Functions bandlimited in frequency are free of the curse of dimensionality Juan Ignacio Mulero-Mart?nez Bandwidth of mechanical systems and design of emulators with RBF Juan Ignacio Mulero-Mart?nez One-class document classification via Neural Networks Larry Manevitz and Malik Yousef Long-term neuronal behavior caused by two synaptic modification mechanisms Xi Shen and Philippe De Wilde Analysis of SVM regression bounds for variable ranking A. Rakotomamonjy A relative trust-region algorithm for independent component analysis Heeyoul Choi and Seungjin Choi Analysis of pattern classification for the multidimensional parity-bit-checking problem with hybrid evolutionary feed-forward neural network Manish Mangal and Manu Pratap Singh A locally recurrent fuzzy neural network with application to the wind speed prediction using spatial correlation T.G. Barbounis and J.B. Theocharis ------ BRIEF PAPERS Face recognition based on orthogonal discriminant locality preserving projections Lei Zhu and Shanan Zhu Linear local tangent space alignment and application to face recognition Tianhao Zhang, Jie Yang, Deli Zhao and Xinliang Ge A fast approximate algorithm for training L1-SVMs in primal space Lei Wang, Shixin Sun and Kai Zhang A hierarchical intrusion detection model based on the PCA neural networks Guisong Liu, Zhang Yi and Shangming Yang Neurally plausible, non-combinatorial iterative independent process analysis Andr?s Lo"rincz and Zolt?n Szab? Semi-blind source extraction for fetal electrocardiogram extraction by combining non-Gaussianity and time-correlation Zhenwei Shi and Changshui Zhang Face and palmprint feature level fusion for single sample biometrics recognition Yong-Fang Yao, Xiao-Yuan Jing and Hau-San Wong ------- JOURNAL SITE: http://www.elsevier.com/locate/neucom SCIENCE DIRECT: http://www.sciencedirect.com/science/journal/09252312 From pfua at fing.edu.uy Fri Apr 20 07:35:25 2007 From: pfua at fing.edu.uy (Pascal Fua) Date: Fri, 20 Apr 2007 09:35:25 -0200 Subject: Connectionists: Post-doctoral Position in Computer Vision at EPFL Message-ID: <4628A57D.7080206@fing.edu.uy> EPFL's Computer Vision Laboratory (http://cvlab.epfl.ch/) has an opening for a post-doctoral fellow in the field of Computer Vision and Human Body Modeling. The position is initially offered for 12 months. Description: The work will be carried out within the context of the Marie Curie Research Training Network (http://visiontrain.inrialpes.fr/) , whose goal is to addresses the problem of understanding vision from both computational and cognitive points of view. EPFL's main role within this project relates to human body modeling from video sequences. Within this context, the successful candidate will be able to work on a subject of his/her own choice. Position: The Computer Vision laboratory offers a creative international environment, a possibility to conduct competitive research on a global scale and involvement in teaching. Within the project, there will be ample opportunities to cooperate with some of the best groups in Europe and elsewhere. EPFL is located next to Lake Geneva in a beautiful setting 60 kilometers away from the city of Geneva. Salaries are in the range EUR 40000 to 45000 per year, the precise amount to be determined by EPFL's department of human resources. Because, the project is funded under the Marie Curie rules, some nationality restrictions apply. See http://visiontrain.inrialpes.fr/?page=post_proposals for details. Education: Applicants are expected to have finished, or be about to finish their Ph.D. degrees, to have strong mathematical background, and to have a track record of publications in top computer vision conferences and journals. Strong programming skills (C or C++) are a plus. French language skills are not required, English is mandatory. Application: Applications must be sent via email to Prof. P. Fua (pascal.fua at epfl.ch). They must contain a statement of interest, a CV, a list of publications, and the names of three references. From terry at salk.edu Mon Apr 23 17:56:26 2007 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 23 Apr 2007 14:56:26 -0700 Subject: Connectionists: NEURAL COMPUTATION - May 2007 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 19, Number 5 - May 1, 2007 Letters Training a Support Vector Machine in the Primal Olivier Chapelle Dynamics of Nonlinear Feedback Control H. P. Snippe and J.H. van Hateren Interspike Interval Statistics in the Stochastic Hodgkin-Huxley Model: Coexistence of Gamma Frequency Bursts and Highly Irregular Firing Peter Rowat The Firing of an Excitable Neuron in the Presence of Stochastic Trains of Strong Synaptic Inputs Krešimir Josic and Jonathan Rubin Optimal Coding Predicts Attentional Modulation of Activity in Neural Systems Barak Pearlmutter and Santiago Jaramillo Efficient Computation Based on Stochastic Spikes Udo Ernst, David Rotermund, and Klaus Pawelzik Exact Inferences in a Neural Implementation of a Hidden Markov Model Jeffrey Beck and Alexandre Pouget Multi-Spike Interactions in a Stochastic Model of Spike Timing Dependent Plasticity Terry Elliott and Peter Appleby 3D Periodic Human Motion Reconstruction from 2D Motion Sequences Zonghua Zhang and Nikolaus F. Troje A New Backpropagation Learning Algorithm for Layered Neural Networks with Nondifferentiable Units Takahumi Oohori, Hidenori Naganuma, and Kazuhisa Watanabe ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2007 - VOLUME 19 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $63.60 $114 $54 $57.24 Individual $100 $106.00 $154 $90 $95.40 Institution $782 $828.92 $836 $704 $746.24 * includes 6% GST MIT Press Journals, 238 Main Street, Suite 500, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu http://mitpressjournals.org/neuralcomp ----- From nnrev at atr.jp Tue Apr 24 02:38:52 2007 From: nnrev at atr.jp (Neural Networks Editorial Office) Date: Tue, 24 Apr 2007 15:38:52 +0900 Subject: Connectionists: Neural Networks launches online submission Message-ID: Neural Networks, the Official Journal of the International Neural Network Society, European Neural Network Society and Japanese Neural Network Society, is proud to announce the launch of online submission. Authors interested in Neural Networks are requested to submit their papers using the submission website from now on. All correspondence is performed by email via the website. By this, Neural Networks would provide user-friendly environment. For example, you could save your time and could easily trace the status of your manuscript. For more information about online submission, please visit the web page: http://ees.elsevier.com/neunet/ We hope this implementation of the new web submission system could be of your interest and convenience. -- """""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" 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 vcu at cs.stir.ac.uk Mon Apr 23 06:28:26 2007 From: vcu at cs.stir.ac.uk (Vassilis Cutsuridis) Date: Mon, 23 Apr 2007 11:28:26 +0100 Subject: Connectionists: Final Call for CNS 07 " Cortical Microcircuits" workshop Message-ID: <003d01c78592$20db2260$6ffd998b@cs.ad.stir.ac.uk> *******Final Call for Participation*************** Workshop on Cortical Microcircuits: Structure, Function and Theory Toronto, Canada, 11-12 July, 2007 http://www.cnsorg.org/cns_meeting_workshops.htm Description: ============ To understand how perception, action, learning and memory work, we need to gather data from multiple levels of complexity and from various brain states (normal and diseased). We need to identify the neuronal groups involved in these functions, identify their different types of neurons, draw detailed circuit diagrams, determine the forms of synaptic transmission and plasticity between different neurons and study the dynamics of the cortical microcircuits at the cellular and synaptic level that comprise these neuronal groups. Mathematical and computer models are then essential in exploring how these microcircuits can account for a given function. The goal of the present workshop is to bring together experts from experimental and computational neuroscience in order to review some of the ongoing experimental and theoretical research concerning cortical microcircuits with particular emphasis on the functional roles of the various inhibitory interneurons in the pertinent information processing. Topics: ======= Specific topics will include (but are not limited to): a.. Microcircuit architectures of - Neocortex - Hippocampus - Sensory and motor systems b.. Cross-comparison of architectures from different brain areas c.. Identified functionality of specific microcircuits d.. Identified functionality of specific neuronal types e.. Plasticity and learning Format and Attendance: ================= The workshop will consist of: Short Presentations: A number of selected speakers will be invited to give short presentations of their work and/or ideas to be followed by extensive discussion. Panel Discussion: Our invited speakers will be asked to engage each other on the various issues concerning cortical microcircuits at the end of the workshop. The audience will be strongly encouraged to participate in the discussion. Workshop will run for a half day. Attendance is open to all CNS attendees, whether or not an abstract is submitted (see below). Confirmed contributors: Drs. Stefan Rotter, Markus Butz and Mayank Mehta --------------------------- Submission: =========== Prospective attendees are invited to submit a short abstract (100-200 words) on the topics outlined above or other related issues. Speakers will be selected by the organisers on the basis of these abstracts. Both position and technical reports will be considered for this workshop. To promote a lively event, with plenty of discussion, the organizers are very interested in papers taking strong positions on the issues listed above. Submissions should be made electronically in plain text, PDF or Postscript format and should be sent (no later than May 15th) by email to Vassilis Cutsuridis or Bruce Graham: vcu at cs.stir.ac.uk or b.graham at cs.stir.ac.uk Organizers: =========== Vassilis Cutsuridis Department of Computing Science and Mathematics University of Stirling Stirling FK9 4LA U.K. Email: vcu at cs.stir.ac.uk Bruce P. Graham Department of Computing Science and Mathematics University of Stirling Stirling FK9 4LA U.K. Email: b.graham at cs.stir.ac.uk Workshop Website: ================= http://www.cnsorg.org/cns_meeting_workshops.htm -- The University of Stirling is a university established in Scotland by charter at Stirling, FK9 4LA. Privileged/Confidential Information may be contained in this message. If you are not the addressee indicated in this message (or responsible for delivery of the message to such person), you may not disclose, copy or deliver this message to anyone and any action taken or omitted to be taken in reliance on it, is prohibited and may be unlawful. In such case, you should destroy this message and kindly notify the sender by reply email. Please advise immediately if you or your employer do not consent to Internet email for messages of this kind. From t.j.prescott at sheffield.ac.uk Mon Apr 23 07:17:43 2007 From: t.j.prescott at sheffield.ac.uk (Tony Prescott) Date: Mon, 23 Apr 2007 12:17:43 +0100 Subject: Connectionists: Theme Issue on Models of Natural Action Selection Message-ID: ******************* Readers of this list may interested in the following theme issue of Philosophical Transactions of the Royal Society B. Biological Science, which was published online this month. Apologies for multiple postings. Theme Issue on "Models of Natural Action Selection" Editors: Tony J. Prescott, Joanna J. Bryson, Anil K. Seth. Phil. Trans. R. Soc. B. ISSN: Print: 0962-8436 Online: 1471-2970 http://www.pubs.royalsoc.ac.uk/index.cfm?page=1318 SUMMARY: Action selection, at its simplest, is the problem that every human and animal faces at each instant of "what to do next?". To scientists this problem raises a plethora of further questions: How do we know how to do the right thing? Why is it that we sometimes make poor choices? How do we plan ahead for complex tasks and remember what we are trying to do as we go along? Are there central decision-making mechanisms in the brain or do actions somehow 'select themselves' through the interaction of many concurrent brain processes? What happens when different parts the brain want to do different things? How do the actions selected by individuals shape and change the social groups in which they live? This theme issue addresses these questions by focusing on a particular strategy for finding scientific explanations - computer modelling. The contributions employ state-of-the-art modelling techniques ranging from large networks of simulated brain cells, through to models of individuals (people or animals) viewed as agents operating in simulated worlds. The research has broad applications, from understanding brain disorders such as Parkinson's disease and attention deficit/hyperactivity disorder, to explaining how we choose which political parties we vote for, and how they adapt to increase their appeal to us. Contents: Introduction. Modelling natural action selection Tony J. Prescott, Joanna J. Bryson, Anil K. Seth http://www.journals.royalsoc.ac.uk/link.asp?id=t492g1hv6x876027 Do we expect natural selection to produce rational behaviour? Alasdair I. Houston, John M. McNamara, Mark D. Steer http://www.journals.royalsoc.ac.uk/link.asp?id=376r0758h2535773 The ecology of action selection: Insights from artificial life Anil K. Seth http://www.journals.royalsoc.ac.uk/link.asp?id=b7552510826h88u5 Compromise strategies for action selection Frederick L. Crabbe http://www.journals.royalsoc.ac.uk/link.asp?id=k233kl08x105608h Action selection and refinement in subcortical loops through basal ganglia and cerebellum J.C. Houk, C. Bastianen, D. Fansler, et al. http://www.journals.royalsoc.ac.uk/link.asp?id=w4077317t235g045 Cortical mechanisms of action selection: the affordance competition hypothesis Paul Cisek http://www.journals.royalsoc.ac.uk/link.asp?id=u80m22400060r56r Towards an executive without a homunculus: computational models of the prefrontal cortex/basal ganglia system Thomas E. Hazy, Michael J. Frank, Randall C. O'Reilly http://www.journals.royalsoc.ac.uk/link.asp?id=4172u10225l40707 Multilevel structure in behaviour and in the brain: a model of Fuster's hierarchy Matthew M. Botvinick http://www.journals.royalsoc.ac.uk/link.asp?id=cmp4015726557200 Is there a brainstem substrate for action selection? M.D. Humphries, K. Gurney, T.J. Prescott http://www.journals.royalsoc.ac.uk/link.asp?id=lh5k330u4v1k8320 Understanding decision-making deficits in neurological conditions: insights from models of natural action selection Michael J. Frank, Anouk Scheres, Scott J. Sherman http://www.journals.royalsoc.ac.uk/link.asp?id=v1153m417480086j Extending a biologically inspired model of choice: multi-alternatives, nonlinearity and value-based multidimensional choice Rafal Bogacz, Marius Usher, Jiaxiang Zhang, et al. http://www.journals.royalsoc.ac.uk/link.asp?id=50v10186675418m1 Biologically constrained action selection improves cognitive control in a model of the Stroop task Tom Stafford and Kevin N. Gurney http://www.journals.royalsoc.ac.uk/link.asp?id=d224283588250646 Agent-based modelling as scientific method: A case study analysing primate social behaviour Joanna J. Bryson, Yasushi Ando, Hagen Lehmann http://www.journals.royalsoc.ac.uk/link.asp?id=k622m6tx3715lgw3 An agent-based model of group decision making in baboons W.I. Sellers, R.A. Hill, B.S. Logan http://www.journals.royalsoc.ac.uk/link.asp?id=60v120716201w758 Spatial models of political competition with endogenous political parties Michael Laver and Michel Schilperoord http://www.journals.royalsoc.ac.uk/link.asp?id=m0044hqx84g16020 -- -------------------------------------------------------------------- Dr Tony J Prescott, Department of Psychology, University of Sheffield, Western Bank, Sheffield, S10 2TN, UK. Email:T.J.Prescott at sheffield.ac.uk Tel: (national 0114, international 44 114) 222 6547, fax: 276 6515 Web: http://www.shef.ac.uk/~abrg/tony/ -------------------------------------------------------------------- From gbrown at cs.man.ac.uk Thu Apr 26 04:42:04 2007 From: gbrown at cs.man.ac.uk (Gavin Brown) Date: Thu, 26 Apr 2007 09:42:04 +0100 Subject: Connectionists: ECML Workshop : Principles and Practice of Multiple Learning Systems Message-ID: <463065DC.10607@cs.man.ac.uk> Apologies for multiple postings.... ============================================================= Principles and Practice of Multiple Learning Systems --- a one-day workshop as part of ECML, Sept 21st 2007 http://www.cs.man.ac.uk/~gbrown/ppmls/ ============================================================= Multiple Learning Systems, aka multiple classifier systems, ensembles, information fusion, have emerged as one of the strongest pattern recognition techniques of the last decade, influencing every area of Machine Learning and Data Mining. These techniques, such as Boosting or Bagging, that create multiple classifiers then combine them by voting or averaging are becoming a staple part of the ML toolbox. On a deeper level, the "combining" principle has been extended in several new directions. Cluster ensembles, semi-supervised learning, changing environments, kernel combining methods are all utilizing this principle. This workshop aims to highlight these advanced uses of the "combining" principle, right across the spectrum of machine learning and data mining. This is the first ECML workshop to address this important principle. PPMLS aims to cover both the deep theoretical questions and practical applications of the idea. ============================================================= Invited Speaker and Programme Committee ============================================================= Invited Speaker: We are honoured to have Dr Ludmila Kuncheva as invited speaker. Dr Kuncheva has been a leading influence in the Multiple Classifier Systems community, and is the author of the main textbook in the field, "Combining Pattern Classifiers". Organisers: Gavin Brown (University of Manchester, UK) Elzbieta Pekalska (University of Manchester, UK) Review Committee: Robert Duin (Delft, Netherlands) Giorgio Fumera (Cagliari, Italy) Tin Kam Ho (Bell Labs, USA) Tim Kovacs (Bristol, UK) Natalio Krasnogor (Nottingham, UK) Ludmila Kuncheva (Bangor, Wales) Nikunj Oza (NASA Ames, USA) Fabio Roli (Cagliari, Italy) Amanda Sharkey (Sheffield, UK) Marina Skurichina (Delft, Netherlands) Terry Windeatt (Surrey, UK) Jeremy Wyatt (Birmingham, UK) ============================================================= Suggested topics for papers are: ============================================================= Learning schemes * Classifier selection vs classifier combination * Boosting and Bagging methods * Feature subspaces / feature projections * Learning classifier systems Paradigm combination * Combining Objective Functions * Combining Discriminative and Generative models * Combining Kernels * Combining Statistical and Structural techniques * Combining proximity measures Theory * Methods of classifier combination * Diversity measures * Classifier selection vs classifier combination * Weak and strong models vs overtraining * Handling noise and outliers Data flexibility * MLS in changing/dynamic environments * Cluster ensembles * Stream mining * Learning from distributed data * Learning from multiple data sets * Semi-supervised learning Applications * Image classification/retrieval * Data mining * Text classification * Computer vision * Biometric identification We particularly encourage researchers to share their both positive *and* negative experiences with the combining paradigm. ============================================================= Important dates ============================================================= Submission deadline: June 30th, 2007 Acceptance notification: July 21st, 2007 Camera-ready deadline: July 28th, 2007 Workshop: September 21, 2007 ============================================================= Submitting a paper ============================================================= The workshop proceedings will be formally published with the ECML proceedings, and in addition distributed on a CD to all ECML participants. Selected extended versions may be considered for a journal special issue. Papers should be sent by E-MAIL (in PDF format) to: ppmls at cs.man.ac.uk with a limit of 10 pages, in the Springer LNCS style. Style files and further details can be downloaded from the workshop website: http://www.cs.man.ac.uk/~gbrown/ppmls/ ============================================================= From marcus at idsia.ch Fri Apr 27 03:48:53 2007 From: marcus at idsia.ch (Marcus Hutter) Date: Fri, 27 Apr 2007 17:48:53 +1000 Subject: Connectionists: PostDoc Position in Machine Learning at the Australian National University Available Message-ID: <049b01c788a8$e00e8640$6601a8c0@crl174ml1s> Employment Position Available ANU College of Engineering & Computer Science Research School of Information Sciences & Engineering Computer Sciences Laboratory Research Fellow Fixed Term - 2 years Academic Level B Salary Package: $66,764 - $78,772 pa plus 17% super Reference No.: CECS3965 Applications are invited for a research position in the Computer Sciences Laboratory to work on a research project in distributed sensor systems. The successful applicant will work with staff in the Statistical Machine Learning Research Group and others in the Laboratory. Applicants should have a PhD in computer science or a related field and/or experience relevant to a research project in distributed sensor systems and a commitment to the supervision and teaching of graduate students. Information about the Laboratory's research areas is available at: http://rsise.anu.edu.au/csl/ Further particulars, including selection criteria, are available from: RSISE reception, phone 02 6125 8821, e-mail reception.rsise at anu.edu.au or http://info.anu.edu.au/hr/Jobs/Academic_Positions/_PDF/CECS3965.pdf. If you wish to discuss the position after obtaining the selection documentation, please contact: Professor John Lloyd, phone 02 6125 8633, e-mail John.Lloyd at anu.edu.au. Information for applicants http://info.anu.edu.au/hr/Jobs/How_To_Apply/index.asp. Job Application Cover sheet - http://info.anu.edu.au/policies/Forms/Human_Resources/Recruitment/HR86.asp. Closing Date: 31 May 2007 From ishikawa at brain.kyutech.ac.jp Fri Apr 27 05:08:09 2007 From: ishikawa at brain.kyutech.ac.jp (Masumi Ishikawa) Date: Fri, 27 Apr 2007 18:08:09 +0900 Subject: Connectionists: ICONIP2007 deadline extension Message-ID: <7.0.0.16.2.20070427180700.03ca2358@brain.kyutech.ac.jp> **************************************************** D E A D L I N E E X T E N S I O N 14th International Conference on Neural Information Processing Kitakyushu, Japan, November 13-16, 2007 http://www.iconip07.org/ **************************************************** Due to several requests, we are pleased to announce that the submission deadline for papers has been extended until June 1, 2007. Those who have already submitted papers can revise their papers at any time by the extended deadline. Sponsors: Asia Pacific Neural Network Assembly (APNNA) Japanese Neural Network Society (JNNS) 21st Century COE Program, Kyushu Institute of Technology Co-sponsors: RIKEN Brain Science Institute Advanced Telecommunications Research Institute International (ATR) Japan Society for Fuzzy Theory and Intelligent Informatics (SOFT) IEEE CIS Japan Chapter Fuzzy Logic Systems Institute (FLSI) Papers are solicited for, but not limited to, the following five Tracks: ?1. Computational Neuroscience ?2. neural network models and learning ??(learning algorithms, ICA, SVM, SOM, etc.) ?3. Vision and motor control ??(robot vision, pattern recognition, motor control, visuomotor control, etc.) ?4. Hardware and Applications ??(hardware, signal processing, medical applications, fuzzy, robotics, etc.) ?5. Novel approaches ??(EC, BMI, cognitive science, hybrid systems, brain-like systems, adaptive intelligent systems, etc.) A full paper of up to 10 pages in the Springer LNCS style is to be submitted by May 1, 2007. Ten pages in the Springer LNCS style is roughly equivalent in length to 6 pages in the IEEE Proceedings style. A duly revised accepted paper up to 10 pages in the Springer LNCS style and 1-page abstract are to be submitted by August 1, 2007. During the conference, the conference provides attendees printed abstracts and downloadable provisional electronic proceedings. After the conference, those who wish to revise full papers can resubmit revised version by December 15, 2007. Post conference CD-ROM proceedings and optional paper proceedings will be sent to attendees a few months after this. Important dates: ?Deadline for submission of full papers : June 1, 2007 ?Decision notification : Aug. 1, 2007 ?Camera-ready papers and 1 page abstract due : August 31, 2007 ?Deadline for Authors? registration : August 31, 2007 ?Revision of papers due (if any) : December 15, 2007 Proceedings: Presented papers will be published as post-conference proceedings by Springer (Lecture Notes in Computer Science, LNCS) Keynote Speech Mitsuo Kawato, ATR Computational Neuroscience Laboratories Title: Cerebellar Long Term Depression as a Supervised Learning Rule with All or Nothing Character at Each Synapse Plenary Talks Shin Ishii, Nara Institute of Science and Technology Title: Modeling decision making in a partially observable domain Yoshiyuki Kabashima, Tokyo Institute of Technology Titie: Statistical mechanical approach to CDMA communication -- an offspring of research on perceptrons and associative memory -- Frederic Kaplan, EPFL, Switzerland Title: Curiosity-driven development Andrew Y. Ng, Stanford University Title: STAIR: The STanford Artificial Intelligence Robot project Rajesh P. N. Rao, University of Washington Title: Brain-inspired models of Bayesian computation, with applications to humanoid robotics and brain-machine interfaces Journal Special Issues: Cognitive Neurodynamics Neural Information Processing-Letters and Reviews Intelligent Automation and Soft Computing International Journal of Innovative Computing, Information and Control Neural Networks (Selected papers will be recommended for publication) Call for Tutorials ?ICONIP 2007 will feature pre-conference tutorials dedicated especially to young researchers and Ph.D. students. The tutorials cover fundamental and advanced topics in neural information processing (broardly defined). The proposal for tutorials are to be submitted by e-mail to the secretary of ICONIP at with the name, affiliation, address, country of the speaker, the title of tutorials, 5-10 keywords, 200-word abstract including motivation, appeal to the conference attendees, expected effectiveness, recommended fields, etc. Deadline for proposal of tutorials is extended to June 1, 2007 and notification of acceptance will be done by June 30, 2007. The selected tutorial speakers will be financially supported by the conference, concerning the international/domestic air flight, the accommodation and the registration. Call for Demonstrations Important dates: Deadline for proposal :15 July, 2007 Decision notification : 1 August, 2007 Deadline for Demonstrators?registration : 15 August, 2007 Final demonstraction abstract due : 1 September, 2007 Program Co-Chair Masumi Ishikawa Department of Brain Science and Engineering Graduate School of Life Science and Systems Engineering Kyushu Institute of Technology 2-4 Hibikino, Wakamatsu, Kitakyushu 808-0196, Japan Tel and Fax: +81-93-695-6106 Email: ishikawa at brain.kyutech.ac.jp URL: http://www.brain.kyutech.ac.jp/~ishikawa URL: http://www.lsse.kyutech.ac.jp/ From p.husbands at sussex.ac.uk Fri Apr 27 10:12:15 2007 From: p.husbands at sussex.ac.uk (Phil Husbands) Date: Fri, 27 Apr 2007 15:12:15 +0100 Subject: Connectionists: PhD scholarships available Message-ID: <17696218.1177686735@[192.168.2.2]> Funded PhD places are available in the department of Informatics, University of Sussex. Studentships are available in various areas of Computer Science, AI and Cognitive Science including adaptive systems, bioinformatics, computational neuroscience and machine learning. For further details, including how to apply, see Faculty involved with various aspects of computational neuroscience, machine learning and adaptive systems are associated with the Sussex Centre for Computational Neuroscience and Robotics (run jointly by the depts. of Informatics and Biology - ) and include: Luc Berthouze, Tom Collett, Ezequiel Di Paolo, Paul Graham, Inman Harvey, Phil Husbands, Thomas Nowotny, Michael O'Shea, Daniel Osorio, Andy Philippides, Anil Seth, Adrian Thompson, Si Wu. Funded places are also available on our MSc in Evolutionary and Adaptive Systems. From ckiw at inf.ed.ac.uk Mon Apr 30 13:10:41 2007 From: ckiw at inf.ed.ac.uk (Chris Williams) Date: Mon, 30 Apr 2007 18:10:41 +0100 (BST) Subject: Connectionists: ANNOUNCE: PASCAL Visual Object Classes Recognition Challenge 2007 Message-ID: PASCAL Visual Object Classes Recognition Challenge 2007 We are running a third PASCAL Visual Object Classes Recognition Challenge. This time there are more classes (twenty), more challenging images, and the possibility of more confusion between classes with similar visual appearance (cars/bus/train, bicycle/motorbike). As before, participants can recognize any or all of the classes, and there are classification and detection tracks. There are also two "taster" competitions, on pixel-wise segmentation and on person layout (detecting head, hands, feet). The development kit (Matlab code for evaluation, and baseline algorithms) and training data is now available at: http://www.pascal-network.org/challenges/VOC/voc2007/index.html where further details are given. The timetable of the challenge is: * April 2007: Development kit and training data available. * 11 June 2007: Test data made available. * 17 Sept 2007, 11pm GMT: DEADLINE for submission of results. * 15 October 2007: Visual Recognition Challenge workshop (Caltech 256 and PASCAL VOC2007) to be held as part of ICCV 2007 in Rio de Janeiro, Brazil, see http://www.robots.ox.ac.uk/~vgg/misc/iccv07/ Mark Everingham Luc Van Gool Chris Williams John Winn Andrew Zisserman