From terry at salk.edu Tue Aug 1 01:02:07 2006 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 31 Jul 2006 22:02:07 -0700 Subject: Connectionists: NEURAL COMPUTATION September, 2006 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 18, Number 9 - September 1, 2006 Note Bursting Without Slow Kinetics: A Role for a Small World Jie Shao, Tzu-Hsin Tsao, and Robert Butera Letters Error Entropy in Classification Problems: A Univariate Data Analysis Luis M. Silva, Carols S. Felgueiras, Luis A. Alexandre, J. Marques de Sa Online Adaptive Decision trees: Pattern Classification and Function Approximation Jayanta Basak Neuronal Algorithms that Detect the Temporal Order of Events Gonzalo G. de Polavieja Excessive Noise Injection for Marker-Less Tracking in Obscured and Segmented Environments Charles P. Unsworth and George Coghill Integrate-and-Fire Neurons with High-Conductance State Dynamics for Event-Driven Simulation Strategies M. Rudolph and A. Destexhe The Crystallizing Substochastic Sequential Machine Extractor - CrySSMEx Henrik Jacobsson Assessing Neuronal Coherence with Single-Unit, Multi-Unit and Local Field Potentials Magteld Zeitler, Pascal Fries and Stan Gielen ----- 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 esann at dice.ucl.ac.be Tue Aug 1 12:07:11 2006 From: esann at dice.ucl.ac.be (esann) Date: Tue, 1 Aug 2006 18:07:11 +0200 Subject: Connectionists: ESANN'2007: call for special sessions Message-ID: <00e501c6b584$8c87ac10$59ed6882@maxwell.local> *** We apologize for possible duplicates of this message, sent to distributions lists only *** ===================================================== ESANN'2007 15th European Symposium on Artificial Neural Networks Advances in Computational Intelligence and Learning Bruges (Belgium) - April 25-26-27, 2007 Call for special sessions ===================================================== Preliminary information about the ESANN'2007 conference may now be found on the ESANN web site (http://www.dice.ucl.ac.be/esann/). The organizing committee is currently looking for (good) proposals for special sessions to be organized during ESANN'2007. You may have a look to the details of special session organization during ESANN at http://www.dice.ucl.ac.be/esann/index.php?pg=cfss. Proposals are expected no later than August 31, 2006. If you are interested in organizing a special session, please send an e-mail as soon as possible to esann at dice.ucl.ac.be. Thank you in advance, Best regards, Michel Verleysen ===================================================== ESANN - European Symposium on Artificial Neural Networks http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews,... Michel Verleysen Univ. cath. de Louvain - Microelectronics Laboratory 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at dice.ucl.ac.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at dice.ucl.ac.be ===================================================== From mhb0 at lehigh.edu Tue Aug 1 15:07:17 2006 From: mhb0 at lehigh.edu (Mark H. Bickhard) Date: Tue, 1 Aug 2006 15:07:17 -0400 Subject: Connectionists: Call for Papers: Cognitive Robotics and Theoretical Psychology Message-ID: <3b73778d893597bd46c9db3cff13262a@lehigh.edu> CALL FOR PAPERS Cognitive Robotics and Theoretical Psychology Tom Ziemke & Mark Bickhard Cognitive robotics ? the use of robots in the modeling of cognition ? evolved in reaction to disembodied and context free notions of cognition. Cognitive robotics and related orientations emphasize the centrality of agency to cognition, together with multiple corollary properties of dynamic agents interacting in real situations. There are many interrelations and synergies between cognitive robotics and theoretical psychology, and progressively more of them are being explored in both psychology and robotics. We are calling for papers for a special issue of the journal New Ideas in Psychology* addressing the relationships between cognitive robotics in a broad sense ? including, for example, embodied cognition, and autonomous agents ? on the one hand, and theoretical psychology, on the other. We would like to focus on what these approaches offer to psychology ? philosophically, theoretically, methodologically, suggestions for models, and so on ? as well as what opportunities are offered to psychology for application, testing, and exploration of psychological issues and theories. Interested authors should send an abstract of their intended paper to both editors. Initial abstracts are due 15 Nov 2006, and full papers for accepted abstracts will be due 16 Apr 2007. Important dates: Submission of abstracts: 15 Nov 2006 Submission of full papers: 16 Apr 2007 Feedback/notification: 20 June 2007 Completion of final drafts: 15 Oct 2007 Aim for publication: Early 2008 Tom Ziemke Professor of Cognitive Science/Cognitive Robotics School of Humanities & Informatics University of Sk?vde, Sweden tom.ziemke at his.se Mark Bickhard Henry R. Luce Professor of Cognitive Robotics and the Philosophy of Knowledge Lehigh University Bethlehem, PA USA mark at bickhard.name http://www.bickhard.ws/ * A journal for innovative theory in psychology. See our editorial statement: http://ees.elsevier.com/newideas/ Mark H. Bickhard Lehigh University 17 Memorial Drive East Bethlehem, PA 18015 mark at bickhard.name http://bickhard.ws/ From hitzler at aifb.uni-karlsruhe.de Thu Aug 3 07:29:13 2006 From: hitzler at aifb.uni-karlsruhe.de (Pascal Hitzler) Date: Thu, 03 Aug 2006 13:29:13 +0200 Subject: Connectionists: Second CfP: IJCAI-07 Workshop on Neural-Symbolic Learning and Reasoning, NeSy'07 Message-ID: <44D1DE09.9000500@aifb.uni-karlsruhe.de> Third International Workshop on Neural-Symbolic Learning and Reasoning Workshop at IJCAI-07, Hyderabad, India, January 2007 http://www.neural-symbolic.org/NeSy07/ NeSy'05 took place at IJCAI-05 NeSy'06 took place at ECAI2006 Call for Papers --------------- 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 IJCAI-07 format as described in the IJCAI-07 Call for Papers. 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 have to 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. Please note that the number of participants will be strictly limited. 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 September, 2006 Notification of acceptance: 23rd of October, 2006 Camera-ready paper due: 3rd of November, 2006 Workshop date: 6th, 7th or 8th of January, 2007 IJCAI-07 main conference dates: 6th of January 2007 to 12th of January, 2007. Workshop Organisers Artur d'Avila Garcez (City University London, UK) Pascal Hitzler (University Karlsruhe, Germany) Guglielmo Tamburrini (Universit? di Napoli, Italy) Programme Committee (still incomplete) 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 (University of Siena, Italy) Barbara Hammer (TU Clausthal, Germany) Ioannis Hatzilygeroudis (University of Patras, Greece) Pascal Hitzler (University of Karlsruhe, Germany) Kai-Uwe K?hnberger (University of Osnabr?ck, Germany) Luis Lamb (Federal University of Rio Grande do Sul, Brazil) Vasile Palade (Oxford University, UK) Jude W. Shavlik (University of Wisconsin-Madison, USA) 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 (still incomplete) Additional Information 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 via 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 mlittman at cs.rutgers.edu Tue Aug 1 14:21:11 2006 From: mlittman at cs.rutgers.edu (Michael L. Littman) Date: Tue, 1 Aug 2006 14:21:11 -0400 Subject: Connectionists: Workshop for Women in Machine Learning at Grace Hopper Message-ID: <200608011821.k71ILBSI017617@constance.rutgers.edu> [insert the usual apologies for duplication...] CALL FOR STUDENT ABSTRACTS Workshop for Women in Machine Learning Co-located with the Grace Hopper Celebration of Women in Computing San Diego, California October 4, 2006 Deadline for student abstract submissions: August 15, 2006 INTRODUCTION Machine learning is one of the fastest growing areas of computer science. Search engines, face recognition, DNA sequence analysis, speech and handwriting recognition, credit card fraud detection, premature baby monitoring and autonomous locomotion are just some of the applications in which machine learning is routinely used. Despite the variety of machine learning techniques and applications, the percentage of female researchers is lower than in many other areas of computer science. Most women working in machine learning rarely get the chance to interact with other female researchers, making it easy to feel isolated and hard to find role models. This one day workshop will give female faculty, research scientists, and students in the machine learning community an opportunity to meet, exchange ideas and learn from each other, while providing women in other areas of computer science an opportunity to learn about cutting-edge research in a growing field. Workshop registration is free. WORKSHOP FORMAT The workshop will consist of invited talks by established researchers, shorter research talks by Ph.D. students, and a panel discussion intended to address the controversial question: Are women shying away from theoretical machine learning research, in favor of more practical applications? STUDENT ABSTRACT SUBMISSION We strongly encourage female students in all areas of machine learning to submit an abstract (less than 500 words) describing either new or previously published research. Authors of accepted abstracts will be required to give a short talk about their research at the workshop. Abstracts should be submitted via the workshop website: http://www.seas.upenn.edu/~wiml/ IMPORTANT DATES Abstract submission deadline: August 15, 2006 Notification of acceptance: August 25, 2006 Registration deadline: September 15, 2006 Workshop dinner: October 3, 2006 Workshop: October 4, 2006 ORGANIZERS Lisa Wainer, University College London Hanna Wallach, University of Cambridge Jenn Wortman, University of Pennsylvania For more information, please visit: http://www.seas.upenn.edu/~wiml/ From gluck at pavlov.rutgers.edu Thu Aug 3 13:17:25 2006 From: gluck at pavlov.rutgers.edu (Mark A. Gluck) Date: Thu, 3 Aug 2006 13:17:25 -0400 Subject: Connectionists: Job Opening: Applied Neurocomputational Modeling of Learning and Memory Message-ID: Position Offered for Programmer or Postdoctoral Fellowship in Applied Neurocomputational Modeling of Learning and Memory We seek to hire a full time Research Assistant/Programmer or Postdoctoral Fellow to work on computer programming projects developing and testing neurocomputational models of the brain circuits for learning and memory, especially the basal ganglia, frontal cortex, and hippocampal region. The applicant should be prepared and capable of working on applications of these models to two projects: (1) Applying these models to understand and predict the nature of memory and cognitive dysfunction in clinical brain disorders including Parkinson's disease, Huntington's disease, schizophrenia, Alzheimer's, and stroke/amnesia; (2) Applying models to a broad range of applied engineering and Artificial Intelligence applications in control and cognition, to compare them to alternative computing methods for solving problems in robotic-control and pattern recognition. We are open to hiring either a post-BA who would work for at least two years before going on to graduate school or a postdoctoral fellow with a PhD. In either case, it is desirable that the person have (1) very strong computer programming skills, (2) prior experience with mathematical and computational neural-nework models of brain and/or behavior, preferably with exposure and experience with neural-network models, and (3) strong English-language writing and speaking skills. We are located in Northern New Jersey, less than twenty minutes by train from midtown Manhattan. If interested, please email me a letter of interest summarizing your background, training, computer modeling skills and experience, previous publications and presentations of research, and future career goals. Also indicate your current location, citizenship, and Visa/workpermit status in the US. Thank you, Mark Gluck ___________________________________ Dr. Mark A. Gluck, Professor Co-Director, Rutgers Memory Disorders Project Center for Molecular and Behavioral Neuroscience Rutgers University Phone: (973) 353-1080 x3221 197 University Ave. Fax: (973) 353-1272 Newark, New Jersey 07102 Email: gluck at pavlov.rutgers.edu Lab: http://www.gluck.edu Memory Loss & Brain Newsletter: http://www.memorylossonline.com From mail at mkaiser.de Thu Aug 3 13:48:24 2006 From: mail at mkaiser.de (Marcus Kaiser) Date: Thu, 3 Aug 2006 19:48:24 +0200 (MEST) Subject: Connectionists: Nonoptimal Component Placement, but Short Processing Paths, due to Long-Distance Projections in Neural Systems Message-ID: <200608031748.k73HmOTX008208@post.webmailer.de> Dear colleagues, I want to advertise our paper on the spatial organisation of neural systems. We find that an abundance of long-distance connections in primates and C. elegans leads to nonoptimal component placement but ensures a low number of processing steps in these systems. Indeed, a lack of long-distance connections is linked with functional deficits as occuring in Alzheimer and Autism patients. The optimisation for a low number of processing steps also verifies a prediction of John von Neumann who compared the architecture of the Computer and the Brain about 50 years ago. The paper is available at http://dx.doi.org/10.1371/journal.pcbi.0020095 and supporting information and data sets can be found at: http://www.biological-networks.org/ The complete abstract is: Nonoptimal Component Placement, but Short Processing Paths, due to Long-Distance Projections in Neural Systems Marcus Kaiser and Claus C. Hilgetag It has been suggested that neural systems across several scales of organization show optimal component placement, in which any spatial rearrangement of the components would lead to an increase of total wiring. Using extensive connectivity datasets for diverse neural networks combined with spatial coordinates for network nodes, we applied an optimization algorithm to the network layouts, in order to search for wire-saving component rearrangements. We found that optimized component rearrangements could substantially reduce total wiring length in all tested neural networks. Specifically, total wiring among 95 primate (Macaque) cortical areas could be decreased by 32%, and wiring of neuronal networks in the nematode Caenorhabditis elegans could be reduced by 48% on the global level, and by 49% for neurons within frontal ganglia. Wiring length reductions were possible due to the existence of long-distance projections in neural networks. We explored the role of these projections by comparing the original networks with minimally rewired networks of the same size, which possessed only the shortest possible connections. In the minimally rewired networks, the number of processing steps along the shortest paths between components was significantly increased compared to the original networks. Additional benchmark comparisons also indicated that neural networks are more similar to network layouts that minimize the length of processing paths, rather than wiring length. These findings suggest that neural systems are not exclusively optimized for minimal global wiring, but for a variety of factors including the minimization of processing steps. Newcastle University, School of Computing Science, U.K. International University Bremen, School of Engineering and Science, Germany PLoS Computational Biology 21 July 2006. Vol. 2, No. 7, e95 Regards, Marcus -- Marcus Kaiser, Ph.D. School of Computing Science University of Newcastle Claremont Tower Newcastle upon Tyne NE1 7RU, U.K. Phone: +44 191 222 8161 Fax: +44 191 222 8232 http://www.biological-networks.org/ From ASJagath at ntu.edu.sg Sun Aug 6 22:18:59 2006 From: ASJagath at ntu.edu.sg (Jagath C Rajapakse (Assoc Prof)) Date: Mon, 7 Aug 2006 10:18:59 +0800 Subject: Connectionists: New Book: FPGA Implementation of Neural Networks Message-ID: <7CD06E15ADF4104A9F2E4DC2DE678F8903889600@EXCHANGE21.staff.main.ntu.edu.sg> For distribution to the connectionists mailing list, thanks. ----- Title: FPGA Implementations of Neural Networks Amos R. Omondi, Jagath C. Rajapakse (Eds.) 2006, XII, 360 p., Hardcover ISBN: 0-387-28485-0 Online orders shipping within 2-3 days Price=?79.00 About this book The development of neural networks has now reached the stage where they are employed in a large variety of practical contexts. However, to date the majority of such implementations have been in software. While it is generally recognised that hardware implementations could, through performance advantages, greatly increase the use of neural networks, to date the relatively high cost of developing Application-Specific Integrated Circuits (ASICs) has meant that only a small number of hardware neurocomputers has gone beyond the research-prototype stage. The situation has now changed dramatically: with the appearance of large, dense, highly parallel FPGA circuits it has now become possible to envisage putting large-scale neural networks in hardware, to get high performance at low costs. This in turn makes it practical to develop hardware neural-computing devices for a wide range of applications, ranging from embedded devices in high-volume/low-cost consumer electronics to large-scale stand-alone neurocomputers. Not surprisingly, therefore, research in the area has recently rapidly increased, and even sharper growth can be expected in the next decade or so. Nevertheless, the many opportunities offered by FPGAs also come with many challenges, since most of the existing body of knowledge is based on ASICs (which are not as constrained as FPGAs). These challenges range from the choice of data representation, to the implementation of specialized functions, through to the realization of massively parallel neural networks; and accompanying these are important secondary issues, such as development tools and technology transfer. All these issues are currently being investigated by a large number of researchers, who start from different bases and proceed by different methods, in such a way that there is no systematic core knowledge to start from, evaluate alternatives, validate claims, and so forth. FPGA Implementations of Neural Networks aims to be a timely one that fill this gap in three ways: First, it will contain appropriate foundational material and therefore be appropriate for advanced students or researchers new to the field. Second, it will capture the state of the art, in both depth and breadth and therefore be useful researchers currently active in the field. Third, it will cover directions for future research, i.e. embryonic areas as well as more speculative ones. Contents: FPGA Neurocomputers Amos R. Omondi, Jagath C. Rajapakse and Mariusz Bajger Arithmetic precision for BP networks Medhat Moussa and Shawki Areibi and Kristian Nichols FPNA: Concepts and properties Bernard Girau FPNA: Applications and implementations Bernard Girau Back-Propagation Algorithm Achieving 5 GOPS on the Virtex-E Kolin Paul and Sanjay Rajopadhye FPGA Implementation of Very Large Associative Memories Dan Hammerstrom, Changjian Gao, Shaojuan Zhu, Mike Butts* FPGA Implementations of Neocognitrons Alessandro Noriaki Ide and Jos? Hiroki Saito Self Organizing Feature Map for Color Quantization on FPGA Chip-Hong Chang, Menon Shibu and Rui Xiao Implementation of Self-Organizing Feature Maps in Reconfigurable Hardware Mario Porrmann, Ulf Witkowski, and Ulrich R?ckert FPGA Implementation of a Fully and Partially Connected MLP Antonio Canas_ , Eva M. Ortigosa_ , Eduardo Ros_ and Pilar M. Ortigosa_ FPGA Implementation of Non-Linear Predictors 305 Rafael Gadea-Girones and Agustn Ramrez-Agundis The REMAP reconfigurable architecture: a retrospective 333 Lars Bengtsson, Arne Linde, Tomas Nordstr-om, Bertil Svensson, and Mikael Taveniku Written for: University lecturers, university postgraduate students, practising scientists, and other researchers and practitioners in the areas of neural networks and computer architecture Keywords: Computer Architecture, FPGAs, Neural Networks ------------------------------------------- Jagath C. Rajapakse, Ph.D. Associate Professor, School of Computer Engineering Nanyang Technological University N4-2a32 Nanyang Avenue, Singapore 639798 Tel:+65 67905802, Fax:+65 67926559 http://www.ntu.edu.sg/home/asjagath From Hualou.Liang at uth.tmc.edu Thu Aug 3 19:53:38 2006 From: Hualou.Liang at uth.tmc.edu (Hualou Liang) Date: Thu, 3 Aug 2006 18:53:38 -0500 Subject: Connectionists: Postdoctoral Positions Available Message-ID: Postdoctoral Positions Available University of Texas Health Science Center at Houston Applications are invited for two postdoctoral positions currently open in the group of Dr. Hualou Liang at University of Texas Health Science Center at Houston to participate in an ongoing research project that analyzes large time series datasets being gathered under various tasks including visual selective attention, multistable visual perception and visuomotor pattern discrimination etc. The project involves the development and application of modern signal processing techniques to multielectrode neural recordings. The successful candidates should be highly motivated, and are expected to work in a team, with the opportunity to work with distinguished collaborators in neural data acquisition, analysis, and algorithm development. Our current facilities include a 90-node (2 CPUs per node) Linux cluster and a 128-channel EEG system dedicated for research activities. The ideal candidate should have, or be about to receive, a Ph.D. in a relevant discipline with substantial mathematical/computational experience (especially in signal processing, time series analysis, dynamical systems, multivariate statistics). Programming skills in C and Matlab are essential. Experience in neuroscience is advantageous but not required. Interested individuals should email a curriculum vitae, a brief statement of research interests, the expected date of availability and the names of three references to Dr. Hualou Liang at Hualou.liang at uth.tmc.edu --------------------------- Hualou Liang, Ph.D. Associate Professor The University of Texas at Houston 7000 Fannin, Suite 600 Houston, TX 77030 Phone: 713-500-3914 Fax: 713-500-3929 Email: hualou.liang at uth.tmc.edu http://www.sahs.uth.tmc.edu/hliang From ted.carnevale at yale.edu Tue Aug 8 16:00:41 2006 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Tue, 08 Aug 2006 16:00:41 -0400 Subject: Connectionists: Revised NEURON bibliography Message-ID: <44D8ED69.3000709@yale.edu> The latest revision to the NEURON bibliography http://www.neuron.yale.edu/neuron/bib/usednrn.html includes 594 publications that report work that was done with NEURON. Prior experience has taught us that citation tracking services and ISI's Web of Science are far from perfect, so with every update of this list, we ask "If you know of a paper that should be in this list, please tell us and we'll be glad to add it." This request is now more important than ever because important bibliographical information is sometimes relegated to "supplementary materials" that are posted on line but not indexed by citation services. In two cases* that we know of, there was no way to discover what simulator was used without reading the supplementary materials. --Ted Carnevale *--The papers are Clark, BA, Monsivais, P, Branco, T, London, M and Haeusser, M. The site of action potential initiation in cerebellar Purkinje neurons. Nature Neuroscience 8:137-139, 2005. Alle, H. and Geiger, J.R.P. Combined analog and action potential coding in hippocampal mossy fibers. Science 311:1290-1293, 2006. We discovered these quite by accident. Based on past patterns of publication, it seems likely that there may be many more in these and other journals. From tsukada at eng.tamagawa.ac.jp Tue Aug 8 22:16:32 2006 From: tsukada at eng.tamagawa.ac.jp (Tsukada) Date: Wed, 09 Aug 2006 11:16:32 +0900 Subject: Connectionists: DBF'07 Registration deadline extended: The Third "Call for Papers" Message-ID: <6.2.0.14.2.20060809111044.04f60c90@eng.tamagawa.ac.jp> ===========================CFP for DBF'07====================== Deadline for registration is extended to 31 Aug. 2006. The Third Announcement and Call for Papers 10th Tamagawa-Riken Dynamic Brain Forum-DBF'07 5-9 March 2007 Hakuba Tokyu Hotel in Hakuba Village, Nagano Prefecture, Japan Conference Framework????????????? The 10th Tamagawa-Riken Dynamic Brain Forum (DBF?07) will be held on March 5-9, 2007 at Hakuba Tokyu Hotel (http://www.tokyuhotels.co.jp/en/TR/TR_HAKUB/index.html) in Hakuba Village, Nagano Prefecture, Japan. The Dynamic Brain Forum (DBF) is an annual international forum organized by the Tamagawa University Brain Science Research Center. In 2007, the DBF will be co-sponsored by Riken Brain Institute, Integrative Brain Research Project, Japanese Neural Network Society, Aihara Complexity Modelling Project and by the 21st Century COE Programs in Tamagawa University, Kyushu Institute of Technology and Hokkaido University. The theme of DBF'07 is Cortical Dynamics: Physiology, Theory and Applications. The forum is organized in several sessions focused on different aspects of the theme, with lectures in each session followed by a thematic discussion. In addition, there will be poster presentations on newest results by the discussants and participants. Posters will be up during first two days of meeting, allowing comprehensive discussions by participants. Preceding the forum, there will also be two full days of Tutorial Programs, primarily oriented toward young researchers and Ph.D. students interested in the theory and applications of various kinds of dynamic brain function. Eight Tutorial presenters and topics will include, Dr. S. Amari: Mathematical Theories of Dynamics of Neural Information Processing ,? Dr. M. Kawato: Towards manipulative neuroscience based on brain-network-interface, Dr. I. Tsuda: Chaotic dynamics reality in brain dynamics, Dr. K. Doya: Neural implementation of reinforcement learning, Dr. W. Freeman: Recent advances in high-resolution analysis of EEG and MEG, Dr. A. Aertsen: Cortical Network Dynamics - Precision in a Noisy Environment ? Dr. G. L. Gerstein Coding dynamics -- (a) repeating firing patterns, (b) firing irregularity, Dr. M. Abeles Brain structure and neural-network architecture, And, Ten Guest speakers are scheduled to talk: Dr. A.Treves, Dr. N. Kasabov, Dr. W. Schultz, Dr. D. Lee, Dr. M. Fee, Dr. P. Cisek. Dr. O. Hikosaka, Dr. B. Richmond, Dr. H. Robinson and one more person. Application, dates and Program schedule * PDF-format is mandatory for all documments submitted. Other formats (Word, LATEX, etc) are never accepted. 31 Aug. 2006 Deadline for registration to attend Tutorials and/or DBF meeting 31 Aug. 2006 Deadline for electronic submission of abstracts (less than 400 words, English) 01 Sep.-30 Oct. 2006 Oral/poster/acceptance or rejection notification 31 Oct. 2006 Deadline for electronic submission of papers (4 pages/A4-size, English) 30 Nov. 2006 Electronic submission of final paper revisions. 04-06 Mar. 2007 Reception of Tutorials and/or DBF at Hakuba Tokyu Hotel 05-06 Mar. 2007 Tutorials 07-08 Mar. 2007 Poster presentations 07-09 Mar. 2007 DBF meeting Registration fee and Travel Grant Tutorial: Free of charge DBF: US$200 includes banquet fee. Travel Grant : Max. US$1,500 travel cost is financially supported for excellent papers awarded by Program Committee, submitted by Graduate students and Post-docs. Registration and further information Please send e-mail to below Secretary for registration (clarify tutorial, forum or both), hotel reservation (clarify hotel name, room type and check-in/out date) or any other questions at the same time. Secretary: S. Nagayama: nagayama at lab.tamagawa.ac.jp Address: Department of Intelligent Information Systems, Faculty of Engineering, Tamagawa University, 6-1-1 Tamagawagakuen, Machida, Tokyo, 194-8160, Japan And, also must visit our web-site: 10th Tamagawa-Riken Dynamic Brain Forum-DBF?07? for further information. URL: http://www.tamagawa.ac.jp/sisetu/gakujutu/brain/dbf2007/index.html Committee: Advisory Committee, Chairman: Shun-ichi Amari: Riken Brain Science Institute, Japan. -Jun Tanji: Tamagawa University, Japan. -Mitsuo Kawato: ATR, Japan. -Takeshi Yamakawa: Kyusyu Institute of Technology, Japan. -Walter Freeman, University of California at Berkeley, USA. Organizing Committee, Chairman: Minoru Tsukada: Tamagawa University, Japan. Vice-Chairman: Ichiro Tsuda: Hokkaido University, Japan. -Keiji Tanaka: Riken Brain Science Institute, Japan. -Ad Aertsen: University of Freiburg, Germany. -Aike Guo: Chinese Academy of Science, China. - Fanji Gu: Fudan University, China. -Gert Hauske: Munich University of Technology, Germany. -Antonio Roque: University of Sao Paulo, Brazil. -Edger Koemer: HONDA R&D Europe, Germany. - James Wright, Univ. of Auckland, NZ Executive Committee, Chairman: Masamichi Sakagami: Tamagawa University, Japan. -Christph Schreiner: University of California, San Francisco, USA. -Takeshi Kasai, Osaka Univ., Japan -Hiroshi Fujii: Kyoto Sangyo University, Japan. -Kenji Doya: Okinawa Institute of Science and Technology, Japan. -Shuji Aou, Kyushu Institute of Tech, Japan -Hiroshi Kojima: Tamagawa University, Japan. -Takeshi Aihara: Tamagawa University, Japan. -Yutaka Sakai: Tamagawa University, Japan. Program Committee, Chairman: Shigetoshi Nara: Okayama University, Japan -Kazuyuki Aihara: University of Tokyo, Japan. -Shozo Yasui: Kyusyu Institute of Technology, Japan. -:Hatsuo Hayashi: Kyusyu Institute of Technology, Japan. -Hiroyuki Ito: Kyoto Sangyo University, Japan. -Tomoki Fukai: Riken Brain Science Institute, Japan. -Guy Sandner, INSERM, Strasburg, France ----------------------------------------------------------------------------------------------------------------------------------- Prof. Dr Minoru Tsukada Department of Intelligent Information systems, Faculty of Engineering, Tamagawa University. 6-1-1, Tamagawagakuen, Machida, Tokyo, 194-8610, Japan Phone/Fax: +81-42-739-8430 E-mail: tsukada at eng.tamagawa.ac.jp ----------------------------------------------------------------------------------------------------------------------------------- From cpoon at MIT.EDU Tue Aug 8 09:13:54 2006 From: cpoon at MIT.EDU (Chi-Sang Poon) Date: Tue, 8 Aug 2006 09:13:54 -0400 Subject: Connectionists: Brain calculus and brain logic: a firewall for sensory integration? Message-ID: <001001c6baec$93778690$18023812@CHISANG> Nonassociative learning as gated neural integrator and differentiator in stimulus-response pathways http://www.behavioralandbrainfunctions.com/content/pdf/1744-9081-2-29.pdf Synopsis What could drug addiction, the phantom pain experienced by amputees, and a life-threatening respiratory condition called apneustic breathing have in common? A new theory published in the online open-access journal Behavioral and Brain Functions suggests that they all may be signs of brain calculus and brain logic computations gone haywire. So says the paper?s lead author Dr. Chi-Sang Poon, a scientist at the Harvard University-Massachusetts Institute of Technology Division of Health Sciences and Technology. According to Poon, our brain is constantly bombarded with vast amounts of sensory information that must be continuously sorted into actionable and nonactionable items in order to prioritize. Such a complex mental task involves sophisticated mathematical calculations like integral-differential calculus and Boolean logic operations, which are basic to any decision-making process. But unlike the number crunching on digital computers, the new theory proposes that our brain may be doing the math automatically by using built-in neural circuitries capable of learning on the spot. Such behavioral learning has long been thought to be a ?dual process,? as exemplified by the everyday experience of habituation to prolonged exposure to fragrance and sensitization to recurrent shock and pain. Dr. Eric Kandel?s pioneering work at Columbia University in the 1970s on neural circuitries for habituation and sensitization in the sea slug Aplysia resulted in a Nobel Prize in Physiology or Medicine in 2000 ? but is such quotidian behavioral learning really important to one?s well-being? Then earlier in 2000, Poon?s research group discovered that the mammalian brain displayed yet another mode of behavioral learning that had confounded previous studies. They called this new behavior ?desensitization,? in contrast to sensitization and habituation. Their research demonstrated that desensitization and habituation had similar ?differentiator? effects on the stimulus-response relationship, much like a ?high-pass filter? in an audio system. However, habituation was found to be turned on or off by the stimulus itself, much like a Boolean toggle switch. Similarly, the effects of sensitization were shown to be analogous to those of an ?integrator? or ?low-pass filter,? with or without the Boolean on-off switching. These pivotal discoveries provided the pieces to the puzzle that inspired Poon?s current theory in which habituation, sensitization, and desensitization are the basic machinery for online calculus and logic computations in the brain. The theory seems to bring these different concepts together. In effect, behavioral learning is a form of brain intelligence whereby integral-differential calculus and on-off Boolean logics are used to filter incoming sensory signals in order to determine continuously what needs attention and what doesn?t ? which is our brain?s way of telling ?what?s hot and what?s not?. This so-called ?sensory firewall? allows the brain to relax and to economize its activities until warning bells ring. It can also provide a fail-safe compensation when sensory cues are distorted. A mistuning of the habituation or sensitization components in the firewall could leave an individual either numbly insensitive, as in ?hearing without listening,? or excessively sensory defensive, as in hysteria. Alternately, a breakdown of the desensitization component could produce a sensory delusion. The effects of desensitization were discovered by Poon?s team while studying the classic Hering-Breuer respiratory reflex. Here, the inspiratory drive is slaked once the vagus nerves sense the lungs are inflated. (Try it yourself by taking a deep breath and holding it. Momentarily, you will feel like you want to exhale instead of inhale). This simple reflex triggers inspiratory-to-expiratory phase switching, which is essential for maintaining a cyclical respiratory rhythm. Poon?s group discovered that, in animals whose vagus nerves are severed, a specific brainstem region in the pons that is normally desensitized would steer the respiratory rhythm in place of the vagus nerves. The pons seemed to act as a ?phantom? or surrogate for the vagus nerves ? much like the phantom pain sensation experienced by amputees. However, in this case, the compensatory action provided an important respiratory fail-safe mechanism crucial for survival. Indeed, classical experiments have shown that when both the vagus nerves and the pons malfunction, an animal goes into an inhalation-only mode, desperately trying to distend its lungs. This results in a life-threatening neurological state called apneustic breathing. Poon and colleagues believe this inspiratory-craving state is functionally similar to obsessive or addictive behaviors, which may result when craving-inhibiting pathways in reward-related brain regions are desensitized. If so, response desensitization could be a new pattern for brain intelligence, and any resulting errors in individual sensory systems may produce abnormalities ranging from phantom pain to addictive behavior. In recent years, neuroscientists have been increasingly intrigued by the idea that the human mind might be connected with the body?s environment through the construction of certain internal models. This was hinted by the seventeenth-century French philosopher and mathematician Ren? Descartes. If Poon and colleagues are correct, the sensory firewall mediated by nonassociative learning may be the gatekeeper of the internal models that govern sensory integration in the brain. From jeffyoshimi at yahoo.com Wed Aug 9 13:51:43 2006 From: jeffyoshimi at yahoo.com (Jeffrey Yoshimi) Date: Wed, 9 Aug 2006 10:51:43 -0700 Subject: Connectionists: Simbrain 2.0 Released Message-ID: A new version of Simbrain (http://www.simbrain.net/) has been released. Simbrain is an open source program for creating and analyzing neural networks. Unique features of Simbrain include its visually-oriented interface, embedded virtual worlds, and mechanism for representing a network's state space. This version of Simbrain has been in development at UC Merced for almost 2 years, with the help of numerous students, researchers, and other collaborators. It represents a complete redesign of earlier versions, and has too may new features to list. For a quick overview, see the video introduction at: http:// www.simbrain.net/video/trailer1/simbrain_trailer.html Jeff Yoshimi UC Merced cogsci.ucmerced.edu From renaud.jolivet at epfl.ch Tue Aug 8 08:26:03 2006 From: renaud.jolivet at epfl.ch (Renaud Jolivet) Date: Tue, 08 Aug 2006 14:26:03 +0200 Subject: Connectionists: New papers: Predicting spike timing of neocortical pyramidal neurons by simple threshold models Message-ID: <44D882DB.2010409@epfl.ch> Dear colleagues, I would like to advertise two papers that we recently published on effective Integrate-and-Fire-type models of neuronal activity as well as parameter estimation methods for such models. We developed a sequential procedure to quantitatively evaluate an equivalent Integrate-and-Fire-type model based on intracellular recordings of cortical pyramidal neurons. We found that the resulting effective model is sufficient to predict the spike train of real pyramidal neurons with high accuracy. In in vivo-like regimes, predicted and recorded traces are almost indistinguishable and a significant part of the spikes can be predicted at the correct timing. Slow processes like spike-frequency adaptation are shown to be a key feature in this context since they are necessary for the model to connect between different driving regimes. First paper is available at http://dx.doi.org/10.1007/s10827-006-7074-5 Jolivet R, Rauch A, L?scher H-R and Gerstner W. Predicting spike timing of neocortical pyramidal neurons by simple threshold models. Journal of Computational Neuroscience 21, 35-49, 2006. Second paper is available at http://dx.doi.org/10.1016/j.jphysparis.2005.09.010 Jolivet R and Gerstner W. Predicting spike times of a detailed conductance-based neuron model driven by stochastic spike arrival. Journal of Physiology-Paris 98, 442-451, 2004. Full abstracts 1. Neurons generate spikes reliably with millisecond precision if driven by a fluctuating current?is it then possible to predict the spike timing knowing the input? We determined parameters of an adapting threshold model using data recorded in vitro from 24 layer 5 pyramidal neurons from rat somatosensory cortex, stimulated intracellularly by a fluctuating current simulating synaptic bombardment in vivo. The model generates output spikes whenever the membrane voltage (a filtered version of the input current) reaches a dynamic threshold. We find that for input currents with large fluctuation amplitude, up to 75% of the spike times can be predicted with a precision of +-2 ms. Some of the intrinsic neuronal unreliability can be accounted for by a noisy threshold mechanism. Our results suggest that, under random current injection into the soma, (i) neuronal behavior in the subthreshold regime can be well approximated by a simple linear filter; and (ii) most of the nonlinearities are captured by a simple threshold process. 2. Reduced models of neuronal activity such as integrate-and-fire models allow a description of neuronal dynamics in simple, intuitive terms and are easy to simulate numerically. We present a method to fit an integrate-and-fire-type model of neuronal activity, namely a modified version of the spike response model, to a detailed Hodgkin?Huxley-type neuron model driven by stochastic spike arrival. In the Hogkin?Huxley model, spike arrival at the synapse is modeled by a change of synaptic conductance. For such conductance spike input, more than 70% of the postsynaptic action potentials can be predicted with the correct timing by the integrate-and-fire-type model. The modified spike response model is based upon a linearized theory of conductance-driven integrate-and-fire neurons. Regards, Renaud -- Renaud Jolivet PhD Brain Mind Institute EPFL -- http://icwww.epfl.ch/~rjolivet +41 21 693 9687 From mark.plumbley at elec.qmul.ac.uk Thu Aug 10 09:04:38 2006 From: mark.plumbley at elec.qmul.ac.uk (Mark Plumbley) Date: Thu, 10 Aug 2006 14:04:38 +0100 Subject: Connectionists: ICA Research Network Workshop, Liverpool, UK, 18-19 Sept 2006 Message-ID: <9D47A2D30B0BFB4C920786C25EC69345880F15@staff-mail.vpn.elec.qmul.ac.uk> Dear Connectionsts, A reminder about this upcoming workshop, which may be of interest to those of you working in ICA or source separation. Best wishes, Mark Plumbley ----------------- *** CALL FOR PARTICIPATION *** 2006 ICA Research Network International 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 International Workshop will be held at the University of Liverpool covering the latest developments and techniques in the area of BSS/ICA. Keynote speaker and contributed papers Professor Christian Jutten of France will present a paper on "Relevance of independent components". Another thirty-six papers have been accepted for presentation at the workshop (see: http://www.elec.qmul.ac.uk/icarn/events/icarn06/papers.html) Registration Costs Student Registration: UK? 165 Full Registration: UK? 200 The registration costs include tea/coffee on Monday am, pm, Tuesday am, pm, the conference dinner on Monday evening, and lunches on Monday and Tuesday. The proceedings are included in the registration costs. Important Dates/Deadlines Registration deadline 4 Septemer 2006 Workshop 18-19 September 2006 Early registration is recommended! 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 bisant at umbc.edu Tue Aug 8 17:34:56 2006 From: bisant at umbc.edu (bisant@umbc.edu) Date: Tue, 8 Aug 2006 17:34:56 -0400 (EDT) Subject: Connectionists: CFP FLAIRS-2007, Neural Networks Track, Key West, FL Message-ID: <4841.130.85.196.10.1155072896.squirrel@webmail.umbc.edu> Call for Papers FLAIRS-2007 Special Track on Neural Networks The 20th International FLAIRS Conference (FLAIRS-2007) Casa Marina Resort and Beach Club, Key West, Florida May 7-9, 2007 http://www.cise.ufl.edu/~ddd/FLAIRS/flairs2007/ Important Dates Paper submissions due November 20, 2006 Notification letters sent January 21, 2007 Camera ready copy due February 11, 2007 Papers are being solicited for a special track on Neural Networks at the 20th International FLAIRS Conference (FLAIRS-2007). The special track will be devoted to Neural Networks with the aim of presenting new and important contributions in this area. The areas include, but are not limited to, the following: applications such as Pattern Recognition, Control and Process Monitoring, Biomedical Applications, Robotics, Text Mining, Diagnostic Problems, Telecommunications, Power Systems, Signal Processing; algorithms such as new developments in Back Propagation, RBF, SVM, Ensemble Methods, Kernel Approaches; hybrid approaches such as Neural Networks/Genetic Algorithms, Neural Network/Expert Systems, Causal Nets trained with Backpropagation, and Neural Network/Fuzzy Logic; or any other area of Neural Network research which is related to artificial intelligence. FLAIRS is a respectable multidisciplinary conference in artificial intelligence held yearly in the Florida area. FLAIRS 2007 Confirmed Speakers Sebastian Thrun is Associate Professor of Computer Science and Electrical Engineering at Stanford University, where he also serves as the Director of the Stanford AI Lab. His research focuses on robotics and artificial intelligence. Thrun has delivered numerous invited plenary presentations at leading conferences and symposia. Thrun was the leader of the team that won the DARPA Grand Challenge in 2005, was named one of the "Brilliant Ten" by Popular Science in 2005, and was elected an AAAI Fellow in 2006. Tim Finin is a Professor in the Computer Science and Electrical Engineering Department at UMBC, the University of Maryland Baltimore County. Finin is a member of the UMBC ebiquity group where he is working on projects involving intelligent agents, the semantic web, pervasive computing , and mobile computing. He holds degrees from MIT and the University of Illinois. Prior to joining the UMBC, he held positions at Unisys, the University of Pennsylvania, and the MIT AI Laboratory. He is the author of over 250 refereed publications and has received research grants and contracts from a variety of sources. He is currently on the editorial board of several journals and is an editor in chief of the Journal of Web Semantics. Finin is a former AAAI councilor and on the the board of directors of the Computing Research Association. (tentative) Rita Rodriguez is a Program Director at the National Science Foundation. Submission Guidelines Interested authors must submit completed manuscripts by November 20, 2006. Submissions should be no more than 6 pages (4000 words) in length, including figures. Papers should be formatted according to AAAI Guidelines. Submission instructions can be found at the FLAIRS-07 website given above. Notification of acceptance will be mailed around January 21, 2007. Authors of accepted papers will be expected to submit the final camera-ready copies of their full papers by February 11, 2007 for publication in the conference proceedings which will be published by AAAI Press. Authors may be invited to submit a revised copy of their paper to a special issue of an international journal on artificial intelligence. Questions regarding the track should be addressed to: David Bisant at bisant at umbc.edu. Initial Special Track Committee David Bisant (Chair), Laboratory for Physical Sciences, USA Ingrid Russell, University of Hartford, USA Jim Austin, University of York, UK Geof Barrows, Centeye Corporation, USA Serge Dolenko, Moscow State University, Russia Erol Gelenbe, Imperial College London, UK Michael Georgiopoulos, University of Central Florida, USA Luis Mart?, Univ. Carlos III de Madrid, Spain Georgios Anagnostopoulos, Florida Institute of Technology, USA Costas Neocleous, University of Cyprus, Cyprus Lisa Meeden, Swarthmore College, USA Sergio Roa Ovalle, University of Freiburg, Germany Roberto Santana, University of the Basque Country, Spain C. N. Schizas, University of Cyprus, Cyprus Chellu Chandra Sekhar, Indian Institute of Technology, India Fernando Ni?o, National University of Columbia, Columbia From yeewhye at gmail.com Wed Aug 9 02:24:24 2006 From: yeewhye at gmail.com (Yee Whye Teh) Date: Wed, 9 Aug 2006 14:24:24 +0800 Subject: Connectionists: Postdoctoral Training Fellowships in Machine Learning at Gatsby Unit, UCL Message-ID: <90231e670608082324y18022eb5nbf9dd785cc9a1d0b@mail.gmail.com> Postdoctoral Training Fellowships Machine Learning Gatsby Computational Neuroscience Unit, UCL, UK http://www.gatsby.ucl.ac.uk/ The Gatsby Computational Neuroscience Unit invites applications for postdoctoral training fellowships in machine learning and related areas. The Unit is especially keen to recruit researchers with expertise in graphical models, Bayesian statistics, nonparametric methods, kernel methods, semi-supervised learning, reinforcement learning, game theory or machine learning applied to neural data, natural language processing, machine vision or bioinformatics. The Unit is a world-class centre for theoretical neuroscience and machine learning. Yee Whye Teh will join the faculty in January 2007. For further details of our research please see: http://www.gatsby.ucl.ac.uk/research.html The Unit provides a unique environment in which a critical mass of theoreticians interact closely with each other and with other world-class research groups in related departments at University College London (UCL). The Unit's visitor and seminar programmes enable staff and students to engage with leading researchers from across the world. Candidates must have a strong analytical background and demonstrable interest and expertise in statistical machine learning. Stipend according to experience and achievement. Funding for the fellowships is available for up to two years. Applicants should send in pdf, plain text or Word format a CV, a statement of research interests, and the names and full contact details (including e-mail addresses) for three academic referees to: asstadmin at gatsby.ucl.ac.uk Applicants are directed to further particulars about the positions available from: http://www.gatsby.ucl.ac.uk/vacancies/; academic enquiries can be directed to ywteh at gatsby.ucl.ac.uk The closing date for applications is 14 September 2006. From tijl.debie at gmail.com Fri Aug 11 08:53:39 2006 From: tijl.debie at gmail.com (Tijl De Bie) Date: Fri, 11 Aug 2006 14:53:39 +0200 Subject: Connectionists: Call for participation -- Current Challenges in Kernel Methods, 27-28 Nov 2006 In-Reply-To: <682af5170608110533y4c8390c0mdd0cb2f2cf3b4702@mail.gmail.com> References: <682af5170608040923w57c66a6dq2e42132220d9fe21@mail.gmail.com> <682af5170608110451o19471105n8d2b50b7028a4b7e@mail.gmail.com> <682af5170608110511r76735e69g961d3ae03328a5b5@mail.gmail.com> <682af5170608110533y4c8390c0mdd0cb2f2cf3b4702@mail.gmail.com> Message-ID: <682af5170608110553g77d6a402s45edc15671745b7d@mail.gmail.com> Apologies for cross- or double posting. Please distribute freely. First announcement and call for participation: =============================================================== International Workshop on Current Challenges in Kernel Methods (CCKM06) Belgium, Brussels, 27-28 November 2006 www.machine-learning.be/cckm06/ =============================================================== * Format The workshop will consist of two days of invited talks by internationally renown researchers. Additionally, an interactive student poster session will be organized. * Invited speakers Confirmed: - Andreas Christmann (Free University of Brussels) - Nello Cristianini (University of Bristol) - Kristiaan Pelckmans (Katholieke Universiteit Leuven) - Alain Rakotomamonjy (INSA de Rouen) - Sandor Szedmak (University of Southampton) - Jean-Philippe Vert (Ecole de Mines de Paris) To be confirmed: - Ingrid Daubechies (Princeton University) - Thorsten Joachims (Cornell University) - Bernhard Schoelkopf (Max Planck Institute for Biological Cybernetics) - John Shawe-Taylor (University College London) - Johan Suykens (Katholieke Universiteit Leuven) * Important dates - Conference accommodation reserved until: Sunday 15 October. - Poster abstract submission deadline: Friday 27 October. - Early registration deadline: Friday 27 October. - Late registration deadline: Friday 17 November. - Workshop: Monday 27 - Tuesday 28 November 2006. * Description In the past decade, the kernel methods domain has expanded from a single algorithm for classification to a full-grown toolbox of techniques that are currently being applied in a variety of domains. This workshop aims at highlighting the current trends and topics of interest, and at putting these in a synthesized historical perspective, with attention for both theoretical and application challenges. Specific topics range from learning theory, over algorithmic/optimization issues in new kernel methods to practical successes and bottlenecks. Intended audience: researchers interested or working in kernel methods, or application domains that are likely to benefit from the advances in kernel methods. Participants may come from artificial intelligence, machine learning, statistics, bioinformatics, data mining, web mining,... with a special interest in the study and application of kernel methods. Level and scope: the lectures in the workshop are intended to be accessible to a broad audience, including anyone with a broad background in computer science, statistics, mathematics, physics, electrical engineering, or related domain. As a guideline, half of each lecture will be tutorial style, while the other half will cover recent developments. The workshop is sponsored by the WOG machine learning for data mining and applications , such that attendance will be free except for the catering expenses. * Please check the workshop website for more details: www.machine-learning.be/cckm06/ Kind regards, The organizers, Prof. Bernard Manderick Dr. Tijl De Bie From jlm at psych.stanford.edu Sun Aug 13 13:03:59 2006 From: jlm at psych.stanford.edu (Jay McClelland) Date: Sun, 13 Aug 2006 10:03:59 -0700 Subject: Connectionists: Programmer Opening at Stanford Center for Mind, Brain, and Computation Message-ID: <44DF5B7F.4050100@psych.stanford.edu> Opening for Research Programmer Center for Mind, Brain, and Computation and Department of Psychology, Stanford University There is an opening for a Research Programmer at the new Center for Mind, Brain, and Computation at Stanford University. The programmer will report jointly to the Mind Brain and Computation Center Director (J. McClelland) and the Psychology Department Computing Systems Manager (P. Smith) and is responsible for meeting the day-to-day computing needs of the Mind Brain and Computation (MBC) Center. S/he will be responsible for providing research programming and academic computing support to the center faculty, research trainees, and staff. In addition s/he will back up the Psychology Department Systems Manager in supporting the computing facilities of the Psychology Department. Qualifications: Applicant must possess a minimum four-year college degree with emphasis in computer science, information systems or related field and at least 1 (one) year of experience providing programming and computing systems support in a research and/or academic setting, or an equivalent combination of relevant education and experience. Must have strong Unix-based programming skills, and be able to compile, install, and troubleshoot various mathematical, graphical, and word-processing applications. Ability to program in, e.g., C, C++, and perl and to use relevant compilers to adapt mathematical and statistical software to Center researcher's needs is also required. Experience with computational models of human cognition and/or machine learning methods would be ideal. In order to perform the computing facilities support functions of the position, the incumbent must possess or be prepared to acquire ability to manage desktop and server computers in Linux, Windows and Macintosh environments, as well as sufficient familiarity with HTML to help MBC faculty and staff develop course- and research-related web pages. Please contact Jay McClelland, jlm at psych.stanford.edu, if you are interested in this position. From terry at salk.edu Sat Aug 12 20:45:21 2006 From: terry at salk.edu (Terry Sejnowski) Date: Sat, 12 Aug 2006 17:45:21 -0700 Subject: Connectionists: NEURAL COMPUTATION October, 2006 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 18, Number 10 - October 1, 2006 Note Consistency of Pseudolikelihood Estimation of Fully Visible Boltzmann Machines Aapo Hyvarinen Letters Images, Frames and Connectionist Hierarchies Peter Dayan Properties of Synergies Arising from a Theory of Optimal Motor Behavior Manu Chhabra and Robert A. Jacobs Recognition by Variance: Learning Rules for Spatio Temporal Patterns Omri Barak and Misha Tsodyks Estimating Spiking Irregularities Under Changing Environments Keiji Miura, Masato Okada, and Shun-chi Amari Spatio-temporal Structure in Large Neuronal Networks Detected from Cross Correlation Gaby Schnneider, Martha N. Havenith and Danko Nikolic Stable Competitive Dynamics Emerge from Multi-Spike Interactions in a Stochastic Model of Spike Timing Dependent Plasticity Peter A. Appleby and Terry Elliott A State-Space Analysis for Reconstruction of Goal-Directed Movements Using Neural Signals Lakshminarayan Srinivasan, Uri T. Eden, Alan S. Willsky, and Emory N. Brown What is the Relation Between Slow Feature Analysis and Independent Component Analysis Tobias Blaschke, Laurenz Wiskott, and Pietro Berkes Non-Local Estimation of Manifold Structure Yoshua Bengio, Martin Monperrus, and Hugo Larochelle Dynamics and Topographic Organization of Recursive Fields in Recursive Self-Organizing Map Peter Tino, Igo Farkas, and Jort van Mourik On Consistency of a Blocked Neural Network Estimator in Time Series Analysis A. Sarishvili, Ch. Andersson, J. Franke and G. Kroisandt ----- 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 From ted.carnevale at yale.edu Mon Aug 14 10:00:05 2006 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 14 Aug 2006 10:00:05 -0400 Subject: Connectionists: early registration deadline for NEURON course at SFN Message-ID: <44E081E5.90303@yale.edu> The good news: this year's one day NEURON course at the SFN meeting will cover topics such as <> how to use the Import3D tool to convert detailed morphometric data (Neurolucida, swc, and Eutectic) into models <> how to use the CellBuilder to set up spatially nonuniform biophysical properties <> how to use the ModelView tool to quickly discover what's really in a model <> how to speed up network models by distributing them over multiple processors The bad news: this year's registration deadline is earlier than ever--September 29. If you've been thinking about taking the course, sign up now so you don't miss out. Registration is limited to 40 individuals on a first-come, first serve basis. For more information see http://www.neuron.yale.edu/neuron/at2006.html --Ted From stefan.wermter at sunderland.ac.uk Wed Aug 16 08:19:36 2006 From: stefan.wermter at sunderland.ac.uk (Stefan Wermter) Date: Wed, 16 Aug 2006 13:19:36 +0100 Subject: Connectionists: Stipend funding available for MSc Intelligent Systems Message-ID: <44E30D58.5010608@sunderland.ac.uk> Stipends available: MSc Intelligent Systems for EU students ----------------------------------------------------------- The School of Computing and Technology, University of Sunderland is delighted to announce its MSc Intelligent Systems programme for Oct. 2006. Building on the School's leading edge research in intelligent systems this masters programme will be funded partially via the ESF programme and Women into Science programme. We are pleased to announce that for eligible EU students we can offer stipends with free EU fees and a bursary of 500 pounds for our MSc Intelligent Systems. Together this stipend is worth about 4200 pounds or 6200 Euro in fees and bursary. This scheme applies to our October 2006 entry for EU students. Intelligent Systems is an exciting field of study for science and industry since the currently existing computing systems have often not yet reached the various aspects of human performance. "Intelligent Systems" is a term to describe software systems and methods, which simulate aspects of intelligent behaviour. The intention is to learn from nature and human performance in order to build more powerful computing systems. The aim is to learn from cognitive science, neuroscience, biology, engineering, and linguistics for building more powerful computational system architectures. In this programme a wide variety of novel and exciting techniques will be taught including neural networks, intelligent robotics, machine learning, natural language processing, vision, evolutionary computing, data mining, fuzzy methods, and artificial intelligence architectures. For further information in the first instance please see: http://www.his.sunderland.ac.uk/Teaching_frame.html http://osiris.sund.ac.uk/webedit/allweb/courses/progmode.php?prog=G550A&mode=FT&mode2=&dmode=C Application forms: http://www.his.sunderland.ac.uk/teaching/sund_is_app.pdf http://www.his.sunderland.ac.uk/sund_is_app.doc For application questions contact: * Email: cat-courseenqs at sunderland.ac.uk * Tel: +44 (191) 515 2758 * Alfredo.Moscardini at sunderland.ac.uk Please forward to students who may be interested. *************************************** Stefan Wermter Professor for Intelligent Systems Centre for Hybrid Intelligent Systems School of Computing and Technology University of Sunderland St Peters Way Sunderland SR6 0DD United Kingdom email: stefan.wermter *at* sunderland.ac.uk http://www.his.sunderland.ac.uk/~cs0stw/ http://www.his.sunderland.ac.uk/ **************************************** -- University of Sunderland - life-changing: see our new TV advert at http://www.lifechangingsunderland.com or http://www.sunderland.ac.uk From fschwenker at neuro.informatik.uni-ulm.de Wed Aug 16 09:15:49 2006 From: fschwenker at neuro.informatik.uni-ulm.de (Friedhelm Schwenker) Date: Wed, 16 Aug 2006 15:15:49 +0200 Subject: Connectionists: Post-doc/PhD position at University of Ulm Message-ID: <44E31A85.1040202@neuro.informatik.uni-ulm.de> The Department of Neural Information Processing at the University of Ulm invites applications for a post-doc (or PhD-student) position to begin November 1 2006, or later. The Institute for Neural Information Processing at the University of Ulm (Germany) has two full professors, 4 postdocs and about 12 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. Post-doc candidates should have a recent PhD-degree for example in computer science, physics, mathematics or electrical engineering. They will have some small teaching obligations, so some knowledge of German would be useful. 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 comprising a CV, list of publications and statement of research interest should be sent to Prof. Dr. Palm by September 5, 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 a.cichocki at riken.jp Sun Aug 20 09:46:19 2006 From: a.cichocki at riken.jp (A. Cichocki) Date: Sun, 20 Aug 2006 22:46:19 +0900 Subject: Connectionists: NMF and NTF alternative tools for Blind Source Separation and Multidimensional Decompositions/Factorizations Message-ID: <44E867AB.2070105@riken.jp> Re: NMF and NTF alternative tools for Blind Source Separation and/or Multidimensional Decompositions/Factorizations Dear List members, We would like to bring to your attention the availability on our web pages new upgraded versions of MATLAB toolboxes: NTFLAB for Signal Processing and NMFLAB for signal and image processing http://www.bsp.brain.riken.jp/ICALAB/nmflab.html http://www.bsp.brain.riken.jp/ICALAB/Guidebook-NMFLAB_SP.pdf and associated list of publications and unpublished reports. Nonnegative Matrix Factorization (NMF) and 3D Nonnegative Tensor Factorization (NTF) can be considered as alternative tools for some constrained BSS and multi-dimensional signal/image/patterns decompositions problems of nonnegative components or factors which are not necessary independent or sparse. We proposed several novel algorithms and models, including multiplicative, fixed-point regularized ALS, projected gradient, exponentiated gradient algorithms. Especially, multi-layer (recurrent) NMF/ NTF algorithms with multi-start, multiple initialization methods provide improved reliability and excellent performance for wide class of BSS or Multi-dimensional Factorization applications. Although, we have performed successfully thousands of experiments and simulations for various benchmarks and real problems still could be some bugs or errors. We would be grateful for any critical comments or suggestions for improvements. The references to our three MATLAB Toolboxes are given below: [1] A. Cichocki and R. Zdunek, NMFLAB - MATLAB Toolbox for Non-Negative Matrix Factorization, http://www.bsp.brain.riken.jp/ICALAB/nmflab.html [2] A. Cichocki, R. Zdunek, and S. Amari, "Csiszar's Divergences for Non-Negative Matrix Factorization: Family of New Algorithms", 6th International Conference on Independent Component Analysis and Blind Signal Separation, Charleston SC, USA, March 5-8, 2006 Springer LNCS 3889, pp. 32-39. [.pdf] [3] A. Cichocki, S. Amari, R. Zdunek, R. Kompass , G. Hori and Z. He: "Extended SMART Algorithms for Non-Negative Matrix Factorization", 8th International Conference on Artificial Intelligence and Soft Computing,ICAISC, Zakopane, Poland, 25-29 June 2006, Springer Lectures Notes in Artificial Intelligence, Vol. 4029, pp.548-562. [.pdf] [4] R. Zdunek, and A. Cichocki, "Non-Negative Matrix Factorization with Quasi-Newton Optimization", 8th International Conference on Artificial Intelligence and Soft Computing, ICAISC, Zakopane, Poland, 25-29 June, 2006, Springer Lectures Notes in Artificial Intelligence, Vol. 4029, pp.870-879 [.pdf] [5] A. Cichocki, R. Zdunek, and S. Amari, "New Algorithms for Non-Negative Matrix Factorization in Applications to Blind Source Separation", 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP-2006, May 14-19, 2006, Toulouse, France, pp V-621-625 [.pdf] [6] R. Zdunek and A. Cichocki, "Nonnegative Matrix Factorization with Constrained Second Order Optimization, (submitted for publication). [7] A. Cichocki and R. Zdunek, "Nonnegative Matrix Factorization Using Projected Gradient Approaches", (ICONIP-2006, available on request). [8] A. Cichocki and R. Zdunek, "Multilayer Nonnegative Matrix Factorization", Electronics Letters, Vol. 42, No. 16 (2006), pp. 947-948. [9] A. Cichocki, R. Zdunek, R. Plemmons and S. Amari, "Novel Multi-layer Nonnegative 3D Tensor Factorization with Sparsity Constraints" (submitted). [10] A. Cichocki, "Generalized Component Analysis and Blind Source Separation Methods for Analyzing Multichannel Brain Signals" - preliminary version of a chapter in the monograph, "Statistical and Process Models of Cognitive Aging", Notre Dame Series on Quantitative Methods, Editors: M.J. Wenger and C. Schuster, (Mahwah, NJ: Erlbaum, 2007) [http ] Andrzej Cichocki ========== Laboratory for Advanced Brain Signal Processing Riken, Brain Science Institute, JAPAN Wako Shi, Saitama 351-0198 ================== http://www.bsp.brain.riken.jp/index.php http://www.bsp.brain.riken.jp/~cia/ From ps629 at columbia.edu Tue Aug 15 09:10:30 2006 From: ps629 at columbia.edu (Paul Sajda) Date: Tue, 15 Aug 2006 09:10:30 -0400 Subject: Connectionists: Special Symposium on Applied Neural Computing Message-ID: <8D4FEE08-20E2-41CB-B67D-D717B9715E9F@columbia.edu> Applied Neural Computing New York City: August 30th and 31st, 2006 Organizers: Paul Sajda (Columbia University) and Yehoshua (Josh) Zeevi (Technion) New computational strategies suitable for complex tasks, such as motor control and visual scene analysis, have been motivated by ideas originating in the neurosciences. More than ever, there are impressive demonstrations of what could be termed ?applied neuroscience?, and it is interesting to consider whether this nascent field is already at the stage to deliver long-lasting impact on advanced computational technologies. This workshop will bring together internationally recognized leaders in the field to discuss the state-of-the-art and debate open and controversial issues in applied neural computing. Topics that will be covered include, brain computer/machine interfaces, neuromorphic systems, neurorobotics, computational and communication systems motivated by neural structure and function, and neural prosthetics. Schedule Wednesday August 30th, 13:00-14:30 Applied Neuro I: Neuromorphics and Neurorobotics Opening remarks: Paul Sajda/Josh Zeevi Neurogrid: Emulating a Million Neurons in the Cortex Kwabena Boahen (Stanford University) Building Large Networks of Biological Neurons Paul Hasler (Georgia Tech) Principles Underlying the Construction of Brain-Based Devices Jeff Krichmar (The Neurosciences Institute) Wednesday August 30th, 14:45-17:15 Applied Neuro II: Brain-Computer Interfaces (Part 1) EEG/ECoG-based BCIs for Communication and Control Jonathan Wolpaw (Wadsworth Center) Bi-directional brain-machine interfaces for spinal cord injury John Chapin (SUNY Downstate School of Medicine) On-line Differentiation Of Neuroelectric Activities: Algorithms And Applications Klaus-Robert Muller (University of Potsdam and Fraunhofer Institut) Special Talk: Applied Neuroscience and the DoD Amy Kruse (DARPA) Thursday August 31st, 09:00-10:30 Applied Neuro III: Brain-Computer Interfaces (Part 2) Cortically-coupled Computer Vision for High-Throughput Image Search Paul Sajda (Columbia University) Increasing the Performance of Cortically-Controlled Prostheses Krishna Shenoy (Stanford University) Initial Experience with Intracortically-Based Neuromotor Prostheses Leigh Hochberg (Brown University) Thursday August 31th, 10:45-12:15 Applied Neuro IV: Neuro-Inspired Algorithms Hierarchical Temporal Memory: Theory and Applications Dileep George (Numenta, Inc.) Feedback Controlled Computational Structures for Vision Roger Brockett (Harvard University) Natural Signal Classification by Neural Cliques and Phase-Locked Attractors Josh Zeevi (Technion) Concluding remarks: Paul Sajda/Josh Zeevi This workshop will take place in New York, Marriott at Times Square, Aug. 30 & 31, 2006, as part of the general program of the IEEE EMBC 2006. Register for the conference at http://embc2006.njit.edu/ Paul Sajda, Ph.D. Associate Professor Department of Biomedical Engineering Columbia University 351 Engineering Terrace Building, Mail Code 8904 1210 Amsterdam Avenue New York, NY 10027 tel: (212) 854-5279 fax: (212) 854-8725 email: ps629 at columbia.edu http://liinc.bme.columbia.edu From Boris.Gutkin at ens.fr Mon Aug 21 12:30:53 2006 From: Boris.Gutkin at ens.fr (Boris Gutkin) Date: Mon, 21 Aug 2006 18:30:53 +0200 Subject: Connectionists: Faculty Position in Computational Neuroscience, DEC-ENS, Paris Message-ID: <1156177853.44e9dfbd84a3e@mail.lumiere.ens.fr> Tenured Junior Faculty Position in Computational Neuroscience at Ecole Normale Superiore Paris A tenured junior faculty position is open in Depatrment of Cognitive Studies at the ENS-Paris. The position is with a wide profile focusing on neuroscience and modelling and computational neuroscience. The recruited candidate will join the newly created Group for Neural Theory at DEC-ENS and associated with the College de France. The candidate should have a strong background in theoretical neuroscience and/or related disciplines (mathematics, physics, computer science) and a promising carrer in computational neuroscience. The candidate is expected to develop an active research programme and integrate into the GNT. Teaching shall be done at the ENS in neuroscience and computational neuroscience. Collaborative opportunities exist within the department and local laboratories involved in functional imaging, primate electrohysiology and/or psychophysics. Further information information is availabel at www.gnt.ens.fr, candidates can also contact Boris Gutkin (Boris.Gutkin at ens.fr) IMPORTANT!: The next cycle of recruitment for a Junior Faculty (MDC) position in computational neuroscience shall be announced in 2007. In order to apply for the position candidates need to pre-qualify with the National University Council. The deadline for the pre-qualification is October 17. Help with the application shall be given to potential candidates who should contact Boris.Gutkin at ens.fr. From jose.millan at jrc.it Mon Aug 28 11:24:06 2006 From: jose.millan at jrc.it (jose.millan@jrc.it) Date: Mon, 28 Aug 2006 17:24:06 +0200 Subject: Connectionists: Call for Participation: Challenging Brain Computer Interfaces Message-ID: <448E8F370000202C@cheetah-1.jrc.it> ++++++++++++++++++++++++++ Challenging Brain Computer Interfaces: Neural Engineering Meets Clinical Needs in Neurorehabilitation http://www.maia-project.org/workshop-2006.php November, 9-10, 2006 IRCCS Fondazione Santa Lucia, Rome, Italy Last years have witnessed advances in Brain-Computer Interfaces (BCI), but how far is this new field from clinical practice? The goal of the workshop is to draw the current and future scenarios involving the application of advanced neural engineering techniques to interpret brain signals for clinical use in the rehabilitation context. The presentations will consist of a series of invited talks (see below) and poster presentations. Some of the major groups in BCI pursuing clinical applications of this technology will report their experience. The participation of the Associate Editors of relevant international journals in the field on neurotechnologies (IEEE TNSRE, Clinical Neurophysiology) will address how ultimate neural engineering techniques could meet the challenge. Also, the view of clinicians involved in neurorehabilitation programs will complete the picture. Finally, the European MAIA project will report their achievements in non-invasive brain-controlled robots. Abstract Submission --------------------------- Please send a one-page abstract (including figures and references, no less than 200 words) to workshop at maia-project.org Posters will be selected depending on relevance to the workshop topic, quality, and novelty. Selected papers of the workshop will be considered for publication in a special issue on "BCI and Robotics" of the Journal of Computational Intelligence and Neuroscience (http://www.hindawi.com/GetPage.aspx?journal=CIN&page=BCI) Important Dates ---------------------- Deadline for abstract submission: September 14, 2006 Notification of acceptance: September 25, 2006 Deadline for early registration: October 15, 2006 Conference dates: November 9-10, 2006 Invited Speakers ----------------------- Prof. Jos? M. Carmena, University of California Berkeley, USA Prof. Shangkai Gao, Tsinghua University, China Dr. Andrea Kuebler, University of Tuebingen, Germany Prof. Marco Molinari, IRCCS Fondazione Santa Lucia, Rome, Italy Prof. Christa Neuper, University of Graz, Austria Dr. Florin Popescu, Fraunhofer Institut FIRST, Berlin, Germany Dr. Theresa Vaughan, Wadsworth Center, Albany, USA Organizing Committee ------------------------------ Prof. Jos? del R. Mill?n, IDIAP Research Institute, Martigny, Switzerland (co-chair) Prof. Maria Grazia Marciani, IRCCS Fondazione Santa Lucia, Rome, Italy (co-chair) Dr. Sara Gonzalez Andrino, Geneva University Hospital, Switzerland Prof. Fabio Babiloni, University of Rome "La Sapienza", Italy Ac.Prof. Kimmo kaski, Helsinki University of Technology, Finland Prof. Marnix Nuttin, Katholieke Universiteit Leuven, Belgium Registration ---------------- The registration fee is: - 50 EUR for early registration (October 15, 2006) - 100 EUR from October 16th to November 1st - 150 EUR onsite registration Registration includes coffee breaks and workshop material. Sponsors ---------------- The workshop is organized by the EU's 6th Framework Programme MAIA project (http://www.maia-project.org). It is also sponsored by - the EU's 6th Framework Programme PASCAL Network of Excellence, - IEEE EBMS, - International Society of Bioelectromagnetism, - Italian Ministry of Foreign Affairs (Directorate-General for Cultural Promotion and Cooperation). The workshop is also part of the PASCAL's 2006 Thematic Programme on "Computational Neuroscience and BCI". ++++++++++++++++++++++++++ -- Prof. Dr. Jos? del R. Mill?n IDIAP Research Institute Swiss Federal Institute of Technology Lausanne (EPFL) IDIAP. Rue du Simplon 4. 1920 Martigny. Switzerland Tel: +41-27-7217.770 Fax: +41-27-7217.712 jose.millan at idiap.ch From bdbryant at cse.unr.edu Sat Aug 26 01:28:54 2006 From: bdbryant at cse.unr.edu (Bobby D. Bryant) Date: Fri, 25 Aug 2006 23:28:54 -0600 Subject: Connectionists: Graduate study in game applications Message-ID: <1156570134l.19982l.1l@parrot> I am bootstrapping a research laboratory at the Department of Computer Science & Engineering at the University of Nevada, Reno, and would like to recruit two or more graduate students to investigate connectionist approaches to intelligent agents embedded in rich environments such as strategy games, or related topics. A limited number of RAships are available. If you have well-qualified students graduating with a Bachelor's or Master's degree, please encourage them to apply. Application deadlines for starting in the spring of 2007 - October 1, 2006, for US citizens September 15, 2006, for all others Application deadlines for starting in the fall of 2007 - April 15, 2007, for everyone Details of the application procedure can be found at http://www.vpr.unr.edu/grad2/application.htm. General information about our department can be found at http://www.cse.unr.edu/. -- Bobby Bryant Reno, Nevada From jf218 at cam.ac.uk Thu Aug 31 15:56:50 2006 From: jf218 at cam.ac.uk (Prof. J. Feng) Date: 31 Aug 2006 20:56:50 +0100 Subject: Connectionists: spinger school in shanghai Message-ID: Computational Neurobiology Spring School in Shanghai March 19th to 28th, 2007 http://www.dcs.warwick.ac.uk/~feng/school.html CALL FOR PARTICIPATION The first International Spring School on Computational Neurobiology in Shanghai will be organized at the CAS-MPG Partner Institute for Computational Biology, Shanghai, PR China (http://www.icb.ac.cn). The school's speakers are listed below. Please, pass on this information to your interested colleagues and students. The course lasts for ten days. Lectures will be given by distinguished experts on topics across the full breadth of experimental and theoretical neuroscience. The first few days of the course introduces students to essential neurobiological concepts and to the most important techniques in modeling single cells, networks, and neural systems. Each student will be assigned to a tutor. In the afternoon, students are given lectures, practical training in modeling, and time to accomplish their report. At the end of the course, students are expected to submit a report of five pages. The course is designed for advanced graduate students and postdoctoral fellows in related disciplines. Students are expected to have a solid background in either (neuro)biology, mathematics, or computer science and, in addition, some basic knowledge in the other two fields as well as a keen interest in the subject matter. Students of any nationality can apply. A maximum of 30 students will be accepted. The course is free, every student has to cover costs for lodging and meals which will be rather moderate. Applications including a CV and an outline of the applicant's motivation for participation must be submitted electronically through the web site and should be accompanied by two letters of recommendation (also sent electronically). Applications will be assessed by the scientific committee, with selection being based on the following criteria: the scientific quality of the candidate (CV), the letters, and evidence that the course affords substantial benefit to the candidate's training. DEADLINE: Application BEFORE 20th Dec, 2006. Speakers at the Spring School 1. Larry Abbott (Columbia, USA) 2. Alexander Borst (Munich, Germany) 3. Yang Dan (Berkeley, USA) 4. Jianfeng Feng (Warwick, UK) 5. Juergen Jost (Leipzig, Germany) 6. Konrad P Koerding (MIT, USA) 7. Wolfgang Maass (Graz, Austria) 8. Hiroyuki Nakahara (RIKEN, Japan) 9. Miguel AL Nicolelis (Duke, USA) 10. Mu-Ming Poo (Berkeley, USA) 11. Ning Qian (Columbia, USA) 12. John Rinzel (New York, USA) 13. Helge Ritter (Bielefeld, Germany) 14. Xiao-jing Wang (Yale, USA) Scientific Committee: Andreas Dress (Shanghai), Jianfeng Feng (Warwick), Juergen Jost (Leipzig), Mu-Ming Poo (Berkeley), Helge Ritter (Bielefeld)