From Raphael.Maree at ULg.ac.be Tue Jul 5 09:51:30 2005 From: Raphael.Maree at ULg.ac.be (Raphael.Maree.) Date: Tue, 05 Jul 2005 15:51:30 +0200 Subject: Connectionists: PhD Studentship 'Random Tree Kernels' Message-ID: <20050705155126.0FB4.RAPHAEL.MAREE@ULg.ac.be> Dear colleagues, Please find below a PhD research studentship position at the University of Li?ge, Belgium. ---------------------------------------------------------------------------- ?Kernel properties of Random Tree Models? Random tree models have been extensively developed in the field of Machine Learning in the recent years. Instances of such methods are for example bagging, random subspace, random forests, and extra-trees. Random trees can be generated efficiently and the combination of large sets of random trees generally leads to accurate models. Under some hypothesis on the random distribution of trees, it is possible to characterize analytically the approximation produced by an infinite ensemble of trees. These models can also be interpreted as Kernel interpolators where the kernel is a mixture of randomized piece-wise constant kernels. Different random distribution of the tree models lead to different geometrical and statistical properties of the resulting models and kernels. The subject of this thesis project concerns the theoretical study of the properties of various Random Tree Models in order to improve our basic understanding of these methods and create new algorithms with pre-specified properties. Subject areas: machine learning, random processes, statistics, geometry and functional analysis References: 1. Zhao, G., `A new perspective on classification'. Ph.D. thesis, Utah State University, Department of Mathematics and Statistics, 2000. 2. Breiman, L., `Some infinity theory for predictor ensembles'. Technical Report 579, University of California, Department of Statistics, 2000. 3. Lin, Y. and Y. Jeon, `Random forests and adaptive nearest neighbors'. Technical Report 1055, University of Wisconsin, Department of Statistics, 2002. 4. Breiman, L., `Consistency for a simple model of random forests', Technical Report 579, University of California, Department of Statistics, 2004 5. P. Geurts, ?Contributions to decision tree induction: bias/variance tradeoff and time series classification?, PhD Thesis, University of Li?ge, Department of Electrical Engineering and Computer Science?, 2002. Contact: Prof. Louis Wehenkel L.Wehenkel at ulg.ac.be http://www.montefiore.ulg.ac.be/services/stochastic/ ---------------------------------------------------------------------------- From ishikawa at brain.kyutech.ac.jp Thu Jul 7 19:53:30 2005 From: ishikawa at brain.kyutech.ac.jp (Masumi Ishikawa) Date: Fri, 08 Jul 2005 08:53:30 +0900 Subject: Connectionists: Second Call for Papers (BrainIT2005) Message-ID: <6.0.0.20.2.20050708084935.0297e970@mail.brain.kyutech.ac.jp> ==================================================== We apologize if you receive multiple copies of this email. Please distribute this announcement to all interested parties. ==================================================== BrainIT2005 Second CALL FOR PAPERS The second international conference, BrainIT 2005, will be held in Kitakyushu, Japan, on October 7-9, 2005, in order to establish the foundations of the Brain-Inspired Information Technology. All working at the frontiers of Brain Science to Information Technology including Robotics are invited to participate in the second international conference, BrainIT 2005. At this conference, we will organize a special session on "Decision and Behavioral Choice Organized by Natural and Artificial Brain" in addition to invited papers from a wide range of fields from Brain Science to Information Technology. Invited Speakers Edmund T. Rolls (Oxford University, UK) Rolf Pfeifer (University of Zurich, Switzerland) Mandyam V. Srinivasan (Australian National University, Australia) Kenji Doya (Okinawa Institute of Science and Technology, Japan) Joshua I. Gold (University of Pennsylvania, USA) Walter J. Freeman (University of California, Berkeley, USA) Andreas Konig (Technische Univ. Kaiserslautern, Germany) Shu-Rong Wang (Institute of Biophysics, Chinese Academy of Sciences, China) Samuel Kaski (Helsinki University of Technology, Finland) Important Dates Abstract (for presentation) Submission Deadline: July 25, 2005 Notification of Acceptance: August 31, 2005 Pre-registration Deadline: September 9, 2005 Paper (for Edited Book) Submission Deadline: October 31, 2005 Scope and Topics BrainIT 2005 solicits experimental, computational, theoretical as well as engineering papers relating the topics in the following non-exhaustive, non-exclusive categories and keywords. Categories and Keywords: 1. Vision system 2. Other sensory systems 3. Cognition 4. Emotion 5. Learning and Memory 6. Behavior 7. Motor controls 8. Languages 9. Dynamics 10. Neural computation 11. Neural networks 12. Brain-inspired intelligent machines Papers that bridge brain science and information technology are especially welcome. Regular papers may include speculative discussions on Brain-Inspired Information Technology. BrainIT 2005 is open to all working at the frontiers of Brain Science to Information Technology (modeling and hardware realization) and provides the opportunity for presenting and discussing ideas that pave the way for the new field, Brain-Inspired Information Technology. Instructions for Authors Authors are requested to submit a 1-page A4-sized abstract by e-mail attachment as a PDF file to brian-it at lsse.kyutech.ac.jp. Each abstract will be independently reviewed by two reviewers. For further information, please refer to the web site. BrainIT Young Investigator Award (New!!) The purpose of this award is to encourage young researchers to make contributions to Brain-Inspired Information Technologies. Selection will be made by the BrianIT2005 Award Committee based on the abstract, the short oral presentation and the poster presentation. The awardee(s) will be given a testimonial and a prize at the Welcome Party. You can see the details on our web site. Registration Registration is free of charge. However, we recommend your early registration as the number of abstract books and other materials may be limited. # Submission and Registration Site is now open. Sponsors * "World of brain computing interwoven out of animals and robots": The 21st Century Center of Excellence Program of the Ministry of Education, Culture, Sports, Science and Technology, Japan * Kyushu Institute of Technology * Kitakyushu Foundation for the Advancement of Industry, Science and Technology (FAIS) Secretariat: Tetsuo FURUKAWA, PhD, Associate Professor Phone: +81-93-695-6124, Fax: +81-93-695-6134 E-mail: brain-it at lsse.kyutech.ac.jp For further information, please visit our web site: http://conf.lsse.kyutech.ac.jp/~brain-it/ 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 mvanross at inf.ed.ac.uk Wed Jul 6 05:22:12 2005 From: mvanross at inf.ed.ac.uk (Mark van Rossum) Date: Wed, 06 Jul 2005 10:22:12 +0100 Subject: Connectionists: Job Opening Computational Neuroscience Message-ID: <1120641733.3780.439.camel@localhost> Job Opening Computational Neuroscience. For our rapidly growing Doctoral Training Centre in Neuroinformatics, the School of Informatics invites applications for Lectureship or Readership in Neuroinformatics, with a focus on Computational Neuroscience. These positions are comparable to assistant/associate professor, but are permanent appointments. We are particularly interested in candidates engaged in computational modelling at either a molecular, cellular, systems, or cognitive level, as well as candidates who combine experimental approaches with computational modelling. You should be able to demonstrate an outstanding research record and commitment to excellence in teaching. You will be based in the Institute for Adaptive and Neural Computation (www.anc.ed.ac.uk). You will be expected to play a key role in the EPSRC/MRC Doctoral Training Centre in Neuroinformatics that is hosted within the School. This interdisciplinary training programme encompasses computational and cognitive neuroscience, software systems and tools to support neuroscience research and neurally inspired systems including neurorobotics and neural engineering. You will be expected to develop collaborative links and joint activities both nationally and internationally. For more information and how to apply see www.jobs.ed.ac.uk (ref 3004711). Deadline: July 29 2005. Informal inquiries to Dr Mark van Rossum, mvanrossATinf.ed.ac.uk, who will be present at CNS in Madison, WI. From Marcus.Frean at mcs.vuw.ac.nz Fri Jul 8 09:29:35 2005 From: Marcus.Frean at mcs.vuw.ac.nz (Marcus Frean) Date: Sat, 9 Jul 2005 01:29:35 +1200 (NZST) Subject: Connectionists: PhD scholarship Message-ID: PhD Scholarship Victoria University of Wellington is offering a PhD scholarship in the area of Intelligent Systems. The scholarship will be worth $NZ 20,000 plus domestic fees. Note, the New Zealand government recently announced a scheme under which new PhD international students from 2006 only need to pay domestic fees. The ideal candidate will have, or be expecting to complete, a strong undergraduate degree (honours) or masters in computer science, statistics, or a related discipline, with interests in probabilistic machine learning algorithms such as graphical models, Gaussian processes, and reinforcement learning. Informal enquiries can be made to Marcus Frean (marcus at mcs.vuw.ac.nz). General information and application forms are available via http://www.mcs.vuw.ac.nz/research/ai/ The deadline for applications is 18 July 2005. Marcus Frean http://www.mcs.vuw.ac.nz/~marcus From t.heskes at science.ru.nl Sat Jul 9 14:25:49 2005 From: t.heskes at science.ru.nl (Tom Heskes) Date: Sat, 09 Jul 2005 20:25:49 +0200 Subject: Connectionists: Neurocomputing volume 67 Message-ID: <42D016AD.90600@science.ru.nl> Neurocomputing Volume 67 (August 2005) ------- SPECIAL PAPERS (Geometrical Methods in Neural Networks and Learning edited by Simone Fiori and Shun-ichi Amari) Geometrical methods in neural networks and learning Simone Fiori and Shun-ichi Amari Geometrical learning, descriptive geometry, and biomimetic pattern recognition Wang Shoujue and Lai Jiangliang Nonlinear dimensionality reduction of data manifolds with essential loops John Aldo Lee and Michel Verleysen Geometric preprocessing, geometric feedforward neural networks and Clifford support vector machines for visual learning Eduardo Bayro-Corrochano, Refugio Vallejo and Nancy Arana-Daniel Learning algorithms utilizing quasi-geodesic flows on the Stiefel manifold Yasunori Nishimori and Shotaro Akaho Tools for application-driven linear dimension reduction Anuj Srivastava and Xiuwen Liu Geometrical methods for non-negative ICA: Manifolds, Lie groups and toral subalgebras Mark D. Plumbley Algebraic geometry of singular learning machines and symmetry of generalization and training errors Sumio Watanabe The geometry of prior selection Hichem Snoussi Lattice duality: The origin of probability and entropy Kevin H. Knuth ------- LETTERS Hyperchaos in Hopfield-type neural networks Qingdu Li, Xiao-Song Yang and Fangyan Yang GraySOFM network for solving classification problems Ming-Feng Yeh and Kuang-Chiung Chang A robust approach to empirical PDF estimate Sungho Jo Dimensional complexity analysis of human EEG in visual processing Shan Tong, Hua Huang, Ju Luan and Huaiqing Chen LMI-based robust stability analysis of neural networks with time-varying delay Hongbin Zhang and Xiaofeng Liao GreyART network for data clustering Ming-Feng Yeh and Shao-Shan Chiang Global convergence analysis of a self-stabilizing MCA learning algorithm Mao Ye An uncorrelated fisherface approach Xiao-Yuan Jing, Hau-San Wong, David Zhang and Yuan-Yan Tang Seeking multi-thresholds directly from support vectors for image segmentation Songcan Chen and Min Wang Applications of a neural network to watermarking capacity of digital image Fan Zhang and Hongbin Zhang Non-uniform image compression using a biologically motivated selective attention model Seung-Hyun Lee, Sang-Bok Choi, Minho Lee and Hyun-Seung Yang Weighted maximum margin discriminant analysis with kernels Wenming Zheng, Cairong Zou and Li Zhao Learning similarity for semantic images classification Dianhui Wang, Joon Shik Lim, Myung-Mook Han and Byung-Wook Lee A simple functional neural network for computing the largest and smallest eigenvalues and corresponding eigenvectors of a real symmetric matrix Yiguang Liu, Zhisheng You and Liping Cao A functional neural network for computing the largest modulus eigenvalues and their corresponding eigenvectors of an anti-symmetric matrix Yiguang Liu, Zhisheng You and Liping Cao Regaining sparsity in kernel principal components C. Garc?a-Osorio and Colin Fyfe Boosting Na?ve Bayes text classification using uncertainty-based selective sampling Han-Joon Kim, Je-Uk Kim and Young-Gook Ra An efficient parallel algorithm for the minimum crossing number problem Rong Long Wang and Kozo Okazaki A binary Hopfield neural network with hysteresis for large crossbar packet-switches Guangpu Xia, Zheng Tang, Yong Li and Jiahai Wang Fuzzy linear proximal support vector machines for multi-category data classification Jayadeva, Reshma Khemchandani and Suresh Chandra A discrete competitive Hopfield neural network for cellular channel assignment problems Jiahai Wang, Zheng Tang, Xinshun Xu and Yong Li Supervised kernel locality preserving projections for face recognition Jian Cheng, Qingshan Liu, Hanqing Lu and Yen-Wei Chen On the possible use of ICA to identify synaptic inputs from observations of several neurons Pando Gr. Georgiev and Henry C. Tuckwell A method to improve the transiently chaotic neural network Xinshun Xu, Zheng Tang and Jiahai Wang ------- JOURNAL SITE: http://www.elsevier.com/locate/neucom SCIENCE DIRECT: http://www.sciencedirect.com/science/issue/5660-2005-999329999-601289 From hinton at cs.toronto.edu Wed Jul 6 13:51:44 2005 From: hinton at cs.toronto.edu (Geoffrey Hinton) Date: Wed, 06 Jul 2005 13:51:44 -0400 Subject: Connectionists: Two new papers on generative models Message-ID: Preprints of the following two papers are available at http://www.cs.toronto.edu/~hinton/ "A FAST LEARNING ALGORITHM FOR DEEP BELIEF NETS" Geoffrey Hinton, Simon Osindero, and Yee-Whye Teh ABSTRACT We show how to use ``complementary priors'' to eliminate the explaining away effects that make inference difficult in densely-connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory. The fast, greedy algorithm is used to initialize a slower learning procedure that fine-tunes the weights using a contrastive version of the wake-sleep algorithm. After fine-tuning, a network with three hidden layers forms a very good generative model of the joint distribution of handwritten digit images and their labels. This generative model gives better digit classification than the best discriminative learning algorithms. The low-dimensional manifolds on which the digits lie are modelled by long ravines in the free-energy landscape of the top-level associative memory and it is easy to explore these ravines by using the directed connections to display what the associative memory has in mind. (submitted to Neural Computation) _______________________________________________________________ "INFERRING MOTOR PROGRAMS FROM IMAGES OF HANDWRITTEN DIGITS" Geoffrey Hinton and Vinod Nair ABSTRACT We describe a generative model for handwritten digits that uses two pairs of opposing springs whose stiffnesses are controlled by a motor program. We show how neural networks can be trained to infer the motor programs required to accurately reconstruct the MNIST digits. The inferred motor programs can be used directly for digit classification, but they can also be used in other ways. By adding noise to the motor program inferred from an MNIST image we can generate a large set of very different images of the same class, thus enlarging the training set available to other methods. We can also use the motor programs as additional, highly informative outputs which reduce overfitting when training a feed-forward classifier. (submitted to NIPS) From d.mandic at imperial.ac.uk Mon Jul 11 10:34:48 2005 From: d.mandic at imperial.ac.uk (Danilo P. Mandic) Date: Mon, 11 Jul 2005 15:34:48 +0100 Subject: Connectionists: Research Position in Blind Source Separation at Imperial College London Message-ID: <00a701c58625$b0f8bb50$432e16ac@MandicLaptop> Dear All, may I draw your attention to the following opening:- Research Assistant/Associate in Signal Processing Area: Blind Source Extraction Department of Electrical and Electronic Engineering, Imperial College London. Salary in the range ?22,116 - ?25,259 inclusive per annum, dependent on experience Fixed-Term appointment September 2005 - April 2007 A research position is available for a Research Assistant or Associate to work on blind source extraction for brain signals. The candidate will be working with Dr Danilo Mandic, based in the Communications and Signal Processing Research Group of the Department of Electrical and Electronic Engineering, South Kensington Campus. This research will be conducted in collaboration with the Brain Science Institute, RIKEN, Japan. The purpose of this project is to develop a theoretical, computational, and experimental framework for online blind extraction of only one or a few sources from large and complex mixtures. The position involves work on the development, mathematical characterisation and simulations on EEG and MEG measurements. The project will show whether applying some fundamental properties of signals, such as their predictability, smoothness and sparseness, in BSE has advantages over existing methods, for complex temporally and spatially correlated sources. The successful candidate will have a strong mathematical background especially in information theory, statistical estimation and optimisation theory. Applicants should normally hold a PhD (or equivalent) or be near to completion of a PhD in engineering, mathematics, physics or relevant disciplines. Previous experience in blind source separation, blind source extraction or adaptive filtering is desirable. Experience in using MATLAB is essential. For further details see http://www.commsp.ee.ic.ac.uk/~mandic/. To apply, please send your completed application form (downloadable from http://www.imperial.ac.uk/employment/academicform.htm), CV, names of two referees, and covering letter explaining your current interests and relevant background for this project to Mrs Mazie Paul (m.paul at imperial.ac.uk), Communications and Signal Processing Group, Department of Electrical and Electronic Engineering, Imperial College London, South Kensington Campus, London, SW7 2AZ. Closing date: 17 July 2005 More details can be found at http://www.jobs.ac.uk/jobfiles/LM805.html Best wishes Danilo =================================== Dr Danilo Mandic Reader in Signal Processing Imperial College London From g.goodhill at imb.uq.edu.au Mon Jul 11 21:58:53 2005 From: g.goodhill at imb.uq.edu.au (Geoffrey Goodhill) Date: Tue, 12 Jul 2005 11:58:53 +1000 Subject: Connectionists: 5 Positions Available Message-ID: 5 POSITIONS AVAILABLE IN COMPUTATIONAL NEUROSCIENCE / AXON GUIDANCE My lab recently moved from Georgetown University to the University of Queensland, Australia, and five positions are now available: - 2 postdoc positions in the area of the computational modelling of visual cortical map development. One of these positions is for a collaboration with Kwabena Boahen, Matt Dalva and Marcos Frank at the University of Pennsylvania. - 1 postdoc and 1 research faculty position in the area of axon guidance. These would suit people with broad backgrounds in tissue culture, immunohistochemistry and small animal surgery. - 1 research assistant position to provide computational support for the above projects. According to http://www.thes.co.uk/worldrankings the University of Queensland is one of the top 50 universities in the world, on a par with Edinburgh in the UK and Duke in the US. It provides an excellent environment for interdisciplinary research, and is currently investing AU$200M in the general area of Biotechnology. This includes AU$50M for a new neuroscience institute, http://www.qbi.uq.edu.au, for which a new 7000sqm building is currently under construction. UQ is in Brisbane, the capital of Queensland, a cosmopolitan city of 1.5 million people with excellent facilities, a vibrant cultural environment, and a subtropical climate. Queensland is also home to attractions such as tropical rainforests and the Great Barrier Reef. Australia was recently ranked by the United Nations in the top 5 countries in the world to live (http://news.bbc.co.uk/2/hi/europe/2149799.stm). Informal enquiries are welcome, but to be formally considered you must respond by the closing date of August 5th to one of the job adverts posted at http://www.uq.edu.au/staff - click on "browse" and then scroll to the jobs posted on July 11th. More details of these positions and the skills required for each are also provided here. More information about the lab can be found at www.goodhill.org, and some recent publications are listed below. Thanks, Geoffrey J Goodhill, PhD Associate Professor Queensland Brain Institute and Department of Mathematics University of Queensland St Lucia, QLD 4072, Australia Phone: +61 7 3346 2612 Fax: +61 7 3346 8836 Email: goodhill at uq.edu.au RECENT PUBLICATIONS Rosoff et al (2004). A new chemotaxis assay shows the extreme sensitivity of axons to molecular gradients. Nature Neuroscience, 7, 678-682. Goodhill et al (2004). Predicting axonal response to molecular gradients with a computational model of filopodial dynamics. Neural Computation, 16, 2221-2243. Carreira-Perpinan & Goodhill (2004). The influence of lateral connections on the structure of cortical maps. Journal of Neurophysiology, 92, 2947-2959. Carreira-Perpinan et al (2005). A computational model for the development of multiple maps in primary visual cortex. Cerebral Cortex, in press. Goodhill & Xu (2005). The development of retinotectal maps: a review of models. Network, in press. Rosoff et al (2005). Generating controlled molecular gradients in 3D gels. Biotechnology and Bioengineering, in press. From mo at ecs.soton.ac.uk Tue Jul 12 10:27:09 2005 From: mo at ecs.soton.ac.uk (Manfred Opper) Date: Tue, 12 Jul 2005 15:27:09 +0100 Subject: Connectionists: postdoctoral position in Southampton Message-ID: <42D3D33D.FD1A79D8@ecs.soton.ac.uk> The ISIS group at the School of Electronics and Computer Science of Southampton University invites applications for a 3 year postdoctoral position for the project "Inference in Complex Stochastic Dynamic Environmental Models" funded by EPSRC and NERC. The project is a collaboration between ISIS, groups at Aston and Surrey universities and the Met Office as a project partners. The goal of this exciting multi-institution project is to develop a theoretical framework for probabilistic forecasting in environmental models relevant to meteorology, climatology and oceanography. Such models are described by very large systems of nonlinear stochastic differential equations with often unknown parameters. We will develop methods for an approximate inference of probability distributions and parameters for these models using variational techniques developed in statistical physics and machine learning. In particular we will extend recently developed methods for inference in Gaussian processes to the dynamical case, where we will combine the models and observations (much as in data assimilation) to infer both the model state through time and the unknown model parameters. Hence, the ideal candidate for this position has a background in statistical physics or mathematics with a strong interest in applying probability theory to complex systems. Salary will be in the range of 22,774 - 28,009 British Pounds per annum. The deadline for applications is August 23, 2005. The Image, Speech and Intelligent Systems (ISIS) group activities are centred in fundamental theory and algorithm development associated with adaptive data modelling, machine learning, control theory and signal processing. The group is part of the School of Electronics and Computer Science that received top ratings in both Electronics and Computer Science at the last RAE. {\tt \bf http://www.ecs.soton.ac.uk/info/groups/isis/}. Informal enquires can be made to Manfred Opper (mo at ecs.soton.ac.uk) or John Shawe--Taylor (jst at ecs.soton.ac.uk). Further details about how to apply can be found under http://www.jobs.soton.ac.uk/adminweb/jsp/jobs/sJobview.jsp?function=View&id=04R0842 From netta at comp.leeds.ac.uk Mon Jul 11 22:23:26 2005 From: netta at comp.leeds.ac.uk (N Cohen) Date: Tue, 12 Jul 2005 03:23:26 +0100 (BST) Subject: Connectionists: Permanent position: Biosystems, School of Computing, Leeds Message-ID: Dear Connectionists, The School of Computing at the University of Leeds, UK is seeking to fill a permanent position, preferably in the Biosystems/ Biorobotics/ Neuroscience areas. The position is available immediately at the level of Lecturer or Senior Lecturer or Reader. We are particularly keen to attract a candidate either in bio-robotics (or bio-inspired robotics) or in computational neuroscience, but candidates in any biosystems area (biological computation/bio-inspired computing, etc.) are welcome. The official advert is on: http://www.comp.leeds.ac.uk/vacancies/20050726lecturer.shtml The closing date is 26 July, 05. Netta Cohen netta at comp.leeds.ac.uk ====================================================================== Biosystems Group School of Computing University of Leeds Leeds, LS2 9JT United Kingdom www.comp.leeds.ac.uk/netta/ From aimath06 at golem.cs.umass.edu Fri Jul 15 16:49:03 2005 From: aimath06 at golem.cs.umass.edu (aimath06@golem.cs.umass.edu) Date: Fri, 15 Jul 2005 16:49:03 -0400 (EDT) Subject: Connectionists: CFP: AI and Math 2006 Message-ID: FIRST CALL FOR PAPERS Ninth International Symposium on Artificial Intelligence and Mathematics http://anytime.cs.umass.edu/aimath06/ January 4-6, 2006 Fort Lauderdale, Florida Paper Submission Deadline: October 2, 2005 The International Symposium on Artificial Intelligence and Mathematics is a biennial meeting that fosters interactions between mathematics, theoretical computer science, and artificial intelligence. This is the ninth symposium in a series, which is sponsored by Annals of Mathematics and Artificial Intelligence. We seek submissions of recent results with a particular emphasis on the foundations of AI and mathematical methods used in AI. Papers describing applications are also encouraged, but the focus should be on principled lessons learned from the development of the application. Traditionally, the Symposium attracts participants from a variety of disciplines, thereby providing a unique forum for scientific exchange. The three-day symposium includes invited speakers, presentations of technical papers, and special topic sessions. INVITED SPEAKERS o Thomas Dean, Brown University, USA o Carla Gomes, Cornell University, USA o Jeffrey S. Rosenschein, The Hebrew University of Jerusalem, Israel SPECIAL TOPIC SESSIONS TBA PAPER SUBMISSION: Paper submission will be electronic via the submission link on the symposium web site. Papers, no more than (8) pages long, must be submitted in PDF or PS format. Fonts must be at least 10 point, and either a single or double column format may be used. The submission deadline is October 2, 2005 (11:59PM EST). Papers will be reviewed by members of the Program Committee. Authors will be notified of acceptance or rejection by October 31, 2005. Final versions of accepted papers, for inclusion in the conference electronic proceedings, are due by November 21, 2005. Note that papers may be submitted to the Symposium even if submitted to other conferences or journals, because the Symposium web site is not archival. Full versions of a selected set of papers from the Symposium will be included in a special volume of Annals of Mathematics and Artificial Intelligence, published by Springer. Authors of these selected papers will be invited to submit their full version subject to refereeing at the usual high standards of the journal and will receive more details with the acceptance notice. Any questions regarding paper submission should be sent to the program chair, Shlomo Zilberstein . IMPORTANT DATES: Paper submission: Sunday, October 2, 2005 Notification: Monday, October 31, 2005 Final version due: Monday, November 21, 2005 SPONSORS: The Symposium is partially supported by the Annals of Math and AI and Florida Atlantic University. ORGANIZERS: o General Chair: Martin Charles Golumbic, University of Haifa, Israel o Conference Chair: Frederick Hoffman, Florida Atlantic University, USA o Program Chair: Shlomo Zilberstein, University of Massachusetts Amherst, USA o Publicity Chair: Daniel Bernstein, University of Massachusetts Amherst, USA PROGRAM COMMITTEE: Peter Bartlett (University of California Berkeley, USA), Peter van Beek (University of Waterloo, Canada), Ronen Brafman (Ben-Gurion University, Israel), François Charpillet (INRIA, France), Berthe Choueiry (University of Nebraska-Lincoln, USA), Adnan Darwiche (University of California Los Angeles, USA), Thomas Eiter (Vienna University of Technology, Austria), Boi Faltings (EPFL, Switzerland), Daniela Pucci de Farias (Massachusetts Institute of Technology, USA), John Franco (University of Cincinnati, USA), Hector Geffner (UPF, Spain), Enrico Giunchiglia (University of Genova, Italy), Claudia Goldman (University of Haifa, Israel), Amy Greenwald (Brown University, USA), Joseph Halpern (Cornell University, USA), Peter Hammer (Rutgers University, USA), Eric Hansen (Mississippi State University, USA), Lisa Hellerstein (Polytechnic University, USA), Andreas Herzig (Université Paul Sabatier, France), Peter Jonsson (University of Linkoping, Sweden), Michael Kaminski (Technion, Israel), Henry Kautz (University of Washington, USA), Hélène Kirchner (LORIA CNRS and INRIA, France), Sven Koenig (University of Southern California, USA), Richard Korf (University of California Los Angeles, USA), Hector Levesque (University of Toronto, Canada), Michael Littman (Rutgers University, USA), Alan Mackworth (University of British Columbia, Canada), David Parkes (Harvard University, USA), Ronald Parr (Duke University, USA), David Poole (University of British Columbia, Canada), Dan Roth (University of Illinois at Urbana-Champaign, USA), Bart Selman (Cornell University, USA), Milind Tambe (University of Southern California, USA), Moshe Tennenholtz (Technion, Israel), Toby Walsh (University of New South Wales, Australia), Michael Wooldridge (University of Liverpool, England) ADVISORY COMMITTEE: The Editor-in-Chief (Martin Charles Golumbic) and the members of the Editorial Board of Annals of Mathematics and Artificial Intelligence serve as the permanent Advisory Committee of the Symposium. Further details can be found at: http://anytime.cs.umass.edu/aimath06/ From derdogmus at ieee.org Tue Jul 12 17:15:42 2005 From: derdogmus at ieee.org (Deniz Erdogmus) Date: Tue, 12 Jul 2005 14:15:42 -0700 Subject: Connectionists: Research Assistantship in Adaptive Signal Processing and Machine Learning Message-ID: <42D432FE.6090006@ieee.org> PHD RESEARCH ASSISTANTSHIP IN ADAPTIVE SYSTEMS AT THE OGI SCHOOL OF SCIENCE AND ENGINEERING AT OHSU A 3-year research assistantship position is available at OGI for individuals interested in pursuing a PhD in Machine Learning or Adaptive Signal Processing towards a CS or EE degree at the CSEE department. The successful candidate will have a strong background on mathematical techniques essential to the areas mentioned above, and will conduct research on developing robust sequential state estimation algorithms for complex systems using measurements from unreliable sensors. This research position will be based in the Adaptive Systems Lab (adsyl.cse.ogi.edu), but will require close interaction with the Point-of-Care Laboratory of the BME department. The RA position includes tuition waiver and a stipend of approximately US$23,000. The desired starting date is October 1st, 2005. Students of any nationality may apply. OGI is one of the four schools of Oregon Health & Science University (OHSU). OGI is located 12 miles west of Portland, Oregon, in the heart of the Silicon Forest. Portland's extensive high-tech community, diverse cultural amenities and spectacular natural surroundings combine to make the quality of life here extraordinary. To learn more about the department, OGI, OHSU and Portland, please visit http://www.cse.ogi.edu. Informal inquiries can be made by sending email (with supporting CV, statement of research interests, and copies of transcripts) to Deniz Erdogmus at derdogmus at ieee.org. For information on submitting a full application to the PhD program in Computer Science and Electrical Engineering, see the OGI admissions information at www.ogi.edu/admissions/. -- Deniz Erdogmus Assistant Professor Departments of CSEE and BME Oregon Health & Science University 20000 NW Walker Road, Beaverton, OR 97006 (Tel) 1-503-7482007, (Fax) 1-503-7481548 http://www.cse.ogi.edu/~deniz derdogmus at ieee.org From nkasabov at aut.ac.nz Tue Jul 12 17:27:38 2005 From: nkasabov at aut.ac.nz (Nik Kasabov) Date: Wed, 13 Jul 2005 09:27:38 +1200 Subject: Connectionists: Workshop on the Synergism of ANN, Bioinformatics and Neuroinformatics, IJCNN, 4.08.05 Message-ID: Dear colleagues, The following Workshop is free to attend and to present your views/results: http://faculty.uwb.edu/ijcnn05/Workshops/bio-neuro-info.html See you there. Nik Kasabov *---------------------------------------------------------------------------------------------------- Artificial Neural Networks, Bioinformatics and Neuroinformatics - A Synergistic ApproachTopics and Goals: The aim of the workshop is to bring together researchers from at least three areas of science: information and mathematical sciences, neuroscience, and molecular biology, in order to discuss in an open forum the synergistic development of these areas in the future. Opportunities to develop new artificial neural network (ANN) models and new models of brain functions that take into account the latest discoveries in molecular biology and bioinformatics will be discussed, along with methods and systems for solving problems in bioinformatics and neuro-informatics with the use of novel ANN approaches. Topics Include: Novel, biologically plausible models of ANN and their dynamics. Spiking neurons and spiking neural networks. Evolving and evolutionary neural networks. New mathematical approaches to modeling biologically plausible ANN. Software and hardware systems that facilitate the synergistic study of brain functions, molecular biology and ANN dynamics. Learning and adaptation in molecular biology related to brain functions. Genes and gene regulatory networks related to brain functions. Neurogenetic models of brain development, brain diseases, learning and memory, evolution and plasticity. Molecular computing Applications Where are ANNs going next? Organizers: Prof. Nik Kasabov (nkasabov at aut.ac.nz) and Prof. Amir Assadi.Intended audience: The workshop is aimed at a broader audience of computer scientists, mathematicians, cognitive scientists, engineers, bioinformaticians, molecular biologists, neurophysiologists. In a sense it will be a summary of the IJCNN conference aimed at outlining new directions for further research in ANN. Prof. Nik Kasabov, MSc, PhD FRSNZ, FNZCS, SrMIEEE Founding Director and Chief Scientist - Knowledge Engineering and Discovery Research Institute, KEDRI Chair of Knowledge Engineering, School of Computer and Information Sciences Auckland University of Technology phone: +64 9 917 9506 ; fax: +64 9 917 9501 WWW http://www.kedri.info email: nkasabov at aut.ac.nz (PA Joyce D'Mello: jdmello at aut.ac.nz; +64 9 917 9504) From terry at salk.edu Wed Jul 13 02:39:18 2005 From: terry at salk.edu (Terry Sejnowski) Date: Tue, 12 Jul 2005 23:39:18 -0700 Subject: Connectionists: NEURAL COMPUTATION 17:8 In-Reply-To: <200505200528.j4K5SbO59466@kepler.snl.salk.edu> Message-ID: Neural Computation - Contents - Volume 17, Number 8 - August 1, 2005 Notes Motion Contrast Classification Is a Linearly Nonseparable Problem Alireza S. Mahani and Ralf Wessel Edgeworth-Expanded Gaussian Mixture Density Modeling Marc M. Van Hulle Letters Movement Generation with Circuits of Spiking Neurons Prashant Joshi and Wolfgang Maass Cognitive Enhancement Mediated Through Postsynaptic Actions of Norepinephrine on Ongoing Cortical Activity Osamu Hoshino Advancing the Boundaries of High-Connectivity Network Simulation with Distributed Computing Abigail Morrison, Carsten Mehring, Theo Geisel, Ad Aertsen, and Markus Diesmann Dynamical Analysis of Continuous Higher-Order Hopfield Networks for Combinatorial Optimization Miguel Atencia, Gonzalo Joya,and Francisco Sandoval Some Generalized Sufficient Convergence Criteria for Nonlinear Continuous Neural Networks Jito Vanualailai and Shin-ichi Nakagiri Estimation and Marginalization Using Kikuchi Approximation Methods Payam Pakzad and Venkat Anantharam ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2005 - VOLUME 17 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $143 $90 $96.30 Institution $680 $727.60 $734 $612 $654.84 * 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 oreilly at psych.colorado.edu Fri Jul 15 01:26:19 2005 From: oreilly at psych.colorado.edu (Randall C. O'Reilly) Date: Thu, 14 Jul 2005 23:26:19 -0600 Subject: Connectionists: REMINDER: Call for Abstracts for CCN/NIMH Dynamical Neuroscience Conference Message-ID: <200507142326.20216.oreilly@psych.colorado.edu> ~ FINAL REMINDER ~ ~ CALL-FOR-ABSTRACTS ~ DEADLINE: August 1, 2005 1ST ANNUAL CONFERENCE ON COMPUTATIONAL COGNITIVE NEUROSCIENCE and NIMH DYNAMICAL NEUROSCIENCE SATELLITE SYMPOSIUM of the Annual Meeting of the Society for Neuroscience, Washington DC Thu-Fri November 10 & 11, 2005 WWW.CCNCONFERENCE.ORG ______________________________________________________________________ Deadline for submissions: August 1, 2005 Meeting Registration and Abstract Submission are processed on-line at: http://www.cmpinc.net/dynamical/ There are two categories of submissions: * Poster only * Short talk (15 min), with accompanying poster Abstracts should be limited to 250 words. Women and underrepresented minorities are especially encouraged to apply. Reviewing for posters will be light and only to ensure appropriateness to the meeting. Talks will be selected on the basis of research quality, relevance to conference theme, and expected accessibility in a talk format. Notification of acceptance will be made by September 1, 2005. ______________________________________________________________________ Conference information: This is the inaugural meeting of what will be a rotating satellite with other meetings, such as (tentative list): CNS (Cognitive Neuroscience Society), HBM (Organization for Human Brain Mapping), CogSci (Cognitive Science Society), Psychonomic Society, NIPS (Neural Information Processing Systems Foundation), and COSYNE (Computational and Systems Neuroscience)). Featured Keynote Speakers: James L. McClelland, Carnegie Mellon University Title: Principles of Cognitive and Neural Processing Daniel M. Wolpert, University College London/University of Cambridge Title: Probabilistic Models of Sensorimotor Control Discussion-Focused Symposia: Decision Making Chair: Michael Shadlen, University of Washington Speakers: Carlos Brody, Cold Spring Harbor Laboratory Yael Niv, Hebrew University Leo Sugrue, Stanford University Developmental Disorders Chair: Michael Thomas, University of London Speakers: Marc Joanisse, University of Western Ontario Fred Dick, University of London April Benasich, Rutgers University Category Learning Chair: Brad Love, University of Texas Speakers: Greg Ashby, UC Santa Barbara Paul Reber, Northwestern University Episodic Memory Chair: Michael Hasselmo, Boston University Speakers: Kenneth Norman, Princeton University Charan Ranganath, UC, Davis Chantal Stern, Boston University ______________________________________________________________________ BACKGROUND: The field of cognitive neuroscience has flourished due to advances using multiple methodologies such as anatomy, physiology, imaging, and behavior. Given the progress that has been made in each of these areas, the time is ripe for strong theoretical frameworks that can relate different levels of analysis, moving beyond basic brain/behavior correlations. The emerging field of Computational Cognitive Neuroscience (CCN) is ideally suited to help fill this need through the use of mathematical analysis and explicit computational models that bridge the gap between biological mechanisms and cognitive function. This meeting focuses on research at the intersection of neuroscience, cognitive psychology, and computational modeling, where neuroscience-based computational models are used to simulate and understand cognitive functions such as perception, attention, learning and memory, language, and higher-level cognitive functions. CCN research benefits greatly from collaboration with various non-modeling researchers for developing and interpreting relevant empirical data. A major goal for this conference is to create fruitful opportunities for modelers and non-modelers to interact. ______________________________________________________________________ PLANNING COMMITTEE: Todd Braver, Washington University, St Louis Carlos Brody, Cold Spring Harbor Jonathan Cohen, Princeton University Dennis Glanzman, NIMH Yuko Munakata, University of Colorado, Boulder David Noelle, Vanderbilt University Randall O'Reilly, University of Colorado, Boulder (Chair) For more information and to sign up for the mailing list visit: WWW.CCNCONFERENCE.ORG ______________________________________________________________________ From gasser at cs.indiana.edu Fri Jul 15 10:36:16 2005 From: gasser at cs.indiana.edu (Michael Gasser) Date: Fri, 15 Jul 2005 09:36:16 -0500 (EST) Subject: Connectionists: Job: Computation, Language, Cognition: Indiana U CogSci Message-ID: [Connectionist language researchers are encouraged to apply. -Mike Gasser] Indiana University, Bloomington, Indiana. Faculty position beginning Fall, 2006 As one of a series of new appointments, the Cognitive Science Program at Indiana University seeks applicants with a developing strong record of research in 'Computational Approaches to Language and Cognition', broadly defined. Rank is open. We are looking for someone with vision, energy, and a desire to explore new forms of interdisciplinary study. The right candidate is more important than the specific disciplinary background. Junior applicants should send full dossiers, including letters of recommendation and sample papers. Senior applicants may do the same, but we also encourage potential senior applicants to contact us directly to discuss possibilities. Indiana University is an equal opportunity/affirmative action employer. Applications from women and minority group members are especially encouraged. We may also be able to consider joint hiring of two affiliated applicants both in the field. As far as possible, e-mail all materials (ideally in PDF format) to cogsrch at indiana.edu. Materials may also be mailed to Professor Michael Gasser, Computation, Language, Cognition Search Committee, Cognitive Science Program, Eigenmann 819, 1910 E. 10th St., Bloomington, IN 47406-7512. Applications received by December 1, 2005 are assured full consideration. Address any questions you have about the position to gasser at indiana.edu. From soeren.lorenz at uni-bielefeld.de Fri Jul 15 13:41:23 2005 From: soeren.lorenz at uni-bielefeld.de (Soeren Lorenz) Date: Fri, 15 Jul 2005 19:41:23 +0200 Subject: Connectionists: Brains, Minds and Media - first publications online Message-ID: <42D7F543.9060600@uni-bielefeld.de> ******** Apologies for multiple postings ******** ____________________________________________________________ ------------ FIRST PUBLICATIONS ONLINE ------------ --------- eJournal Brains, Minds & Media ---------- ------------- Journal of New Media in ------------- --- Neural and Cognitive Science and Education ---- -------- http://www.brains-minds-media.org -------- ____________________________________________________________ FIRST PUBLICATIONS ONLINE Brains, Minds & Media, the novel open access online journal of new media in neural and cognitive science and education, has started publishing. The first publications are now online: http://www.brains-minds-media.org/current. CURRENT ARTICLES ***Research "The Role of Consciousness in Memory" by Stan Franklin, Bernard J. Baars, Uma Ramamurthy, Matthew Ventura. ***Tutorials "Learning Paradigms Exemplified by Virtual Experiments with Honey Bees" by Juliane Ullrich, Soeren Lorenz, Corinna Pelz, Randolf Menzel. "Transfer Functions in Artificial Neural Networks - A Simulation-Based Tutorial " by Klaus Debes, Alexander Koenig and Horst-Michael Gross. ***Project Notes "CELEST - The Center of Excellence for Learning in Education, Science, and Technology " by Stephen Grossberg. "Transforming Education, Collaboration, and Research in Neuroscience: The GENESIS Project - approaching its third decade" by James M. Bower. CALL FOR SUBMISSION "Brains, Minds & Media" publishes peer-reviewed articles and media from research and education in neural and cognitive science (see http://www.brains-minds-media.org/aims"). Future accepted contributions will be published consecutively and integrated ex post into volumes or (special) issues. You are invited to submit contributions to 'Brains, Minds & Media'. More information about manuscipt submissions can be found at http://www.brains-minds-media.org/guidelines. Please send your submission to editors at brains-minds-media.org. If you have any questions, please contact info at brains-minds-media.org. Thank you! Soeren Lorenz (editorial assistance) soeren.lorenz at uni-bielefeld.de From yves.moreau at esat.kuleuven.ac.be Thu Jul 14 09:25:39 2005 From: yves.moreau at esat.kuleuven.ac.be (Yves Moreau) Date: Thu, 14 Jul 2005 15:25:39 +0200 Subject: Connectionists: Ph.D. fellowship in bioinformatics - University of Leuven, Belgium Message-ID: Dear Connectionists, We have currently one Ph.D. fellowship available for a candidate with a strong interest in machine learning (probabilistic graphical models and kernel methods) and in bioinformatics (genomic data fusion). See full announcement below. Best regards, Yves Moreau K.U.Leuven ESAT-SCD DESCRIPTION: One 3-year Ph.D. fellowship supported by the European Commission is available starting on November 1st, 2005 with the Bioinformatics team (http://www.esat.kuleuven.ac.be/~dna/bioi/) at the University of Leuven under the supervision of Prof. Yves Moreau and Prof. Bart De Moor. The research project, part of the EU funded BIOPTRAIN program, will tackle the development of new algorithms for genomic data fusion using probabilistic graphical models and kernel methods. These methods will be applied to the prioritization of candidate genes from high-throughput genomic studies using multiple heterogeneous sources of information (sequence analysis, gene expression data, functional annotation, literature mining). A functional prototype has already been developed and is available at http://www.esat.kuleuven.ac.be/endeavour. The goal of the Ph.D. will be to develop powerful new algorithms on top of the existing software architecture. Our bioinformatics group (http://www.esat.kuleuven.ac.be/~dna/bioi/) is highly dynamic (currently about twenty members) and the University of Leuven is one of Europe's leading universities in the Life Sciences, which offers many collaboration opportunities. Leuven is a charming Renaissance-style city next to Brussels, Belgium. It is ideally located in Europe with excellent flight and train connections to the rest of Europe. QUALIFICATIONS: The ideal candidate will have a master's degree (or equivalent) in, for example, statistics, mathematics, engineering, computer science, or physics. A solid mathematical background is required. Previous knowledge of artificial intelligence, statistics, or bioinformatics is highly desirable. EMPLOYMENT AND SALARY: Fellows will be recruited under an employment contract and will benefit from travel and mobility allowances. The remuneration package is highly competitive for a position at this level. Additional details about these positions (in particular, salary and eligibility) can be found in the EST Handbook (http://europa.eu.int/comm/research/fp6/mariecurie-actions/pdf/est_hand.pdf; pp.21-29). Women in particular are invited to apply. If several applicants have approximately equivalent qualifications, EU rules on equal opportunities will be applied. ELIGIBILITY CRITERIA: An approximate summary of the complex eligibility criteria is as follows: * Candidates should NOT have more than 4 years of research or R&D experience (following the first university degree that allows them to enter a Ph.D. program) and NOT yet hold a Ph.D. * Candidates should NOT be Belgian (or, if Belgian, must have resided outside the EU for four of the last five years). * Candidates should NOT have resided in Belgium for more than 12 months in the past 3 years. * Non-EU candidates can apply (but competition is fierce because only 30% of all fellowships can be awarded to non-EU citizens). * Non-EU candidates who have been residing in a European country for 4 of the last 5 years are assimilated to EU candidates (and thus are not constrained by the previous 30% rule). HOW TO APPLY: Applications should include your CV, a one-page statement of your research interests and motivations for pursuing Ph.D. studies, and contact information (including email addresses) for at least two references. Please send your application, preferably by email, to the attention of Prof. Yves Moreau at Bart.Motmans at esat.kuleuven.ac.be (using PDF or plain text for your attachments) or by surface mail to Prof. Yves Moreau K.U.Leuven ESAT-SCD (Bioinformatics) Kasteelpark Arenberg 10 B-3001 Leuven Belgium DEADLINE: The positions will be filled a.s.a.p. 10 other EST positions are currently open with the other BIOPTRAIN partners, see http://www.bioptrain.org/index.php/Applications. From shadmehr at jhu.edu Mon Jul 18 09:14:28 2005 From: shadmehr at jhu.edu (Reza Shadmehr) Date: Mon, 18 Jul 2005 09:14:28 -0400 Subject: Connectionists: Computational Motor Control Message-ID: <200507181310.j6IDARe24741@storey.bme.jhu.edu> Dear colleagues: Emo Todorov and I would like to invite you to the fourth computational motor control symposium at the Society for Neuroscience conference. The symposium will take place on Friday, Nov. 11 2005 at the Washington DC convention center. The purpose of the meeting is to highlight computational modeling and theories in motor control. This is an opportunity to meet and hear from some of the bright minds in the field. The program consists of two distinguished speakers and 12 contributed talk, selected from the submitted abstracts. The speakers this year are: Daniel Wolpert, University College London Andrew Schwartz, University of Pittsburg We encourage you to consider submitting an abstract. The abstracts will be reviewed by a panel and ranked. The top 12 abstracts will be selected for oral presentation. We encourage oral presentation by students who have had a major role in the work described in the abstracts. More information is available here: www.bme.jhu.edu/acmc The deadline for abstract submission is September 30. Abstracts should be no more than two pages in length, including figures and references. with our best wishes, Reza Shadmehr and Emo Todorov From terry at salk.edu Mon Jul 18 17:40:00 2005 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 18 Jul 2005 14:40:00 -0700 Subject: Connectionists: Re: NEURAL COMPUTATION 17:8 In-Reply-To: Message-ID: In addition to the papers listed in the recent posting, the August, 2005 issue of Neural Computation also includes: Review How Close Are We to Understanding V1 ? Bruno A. Olshausen and David J. Field Terry ----- From beer at eecs.cwru.edu Tue Jul 19 17:25:46 2005 From: beer at eecs.cwru.edu (Randall Beer) Date: Tue, 19 Jul 2005 17:25:46 -0400 Subject: Connectionists: Job: Embodied Cognitive Science: Indiana U CogSci Message-ID: Indiana University, Bloomington, Indiana. Faculty position beginning Fall, 2006 As part of a series of new appointments, the Cognitive Science Program at Indiana University seeks a junior level appointment in the general area of intersection of cognitive science and robotics. We are particularly interested in applicants with expertise in evolutionary robotics and situated, embodied and dynamical approaches to cognition. Applicants should have a record that demonstrates an excellent potential in the areas of research and teaching. Successful applicants will take a leadership role in the planning and execution of a new, state-of-the-art laboratory for teaching and research. Indiana University is an equal opportunity/affirmative action employer. Applications from women and minority group members are especially encouraged. As far as possible, e-mail all materials (ideally in PDF format) to cogsrch at indiana.edu. Materials may also be mailed to Professor Richard Shiffrin, Robotics Search Committee, Cognitive Science Program, Eigenmann 819, 1910 E. 10th St., Bloomington, IN 47406-7512. Applications received by December 1, 2005 are assured full consideration. From bernhard.schoelkopf at tuebingen.mpg.de Wed Jul 20 04:48:30 2005 From: bernhard.schoelkopf at tuebingen.mpg.de (=?iso-8859-1?Q?Bernhard_Sch=F6lkopf?=) Date: Wed, 20 Jul 2005 10:48:30 +0200 Subject: Connectionists: One Day Symposium in Tuebingen, Germany Message-ID: Dear Connectionists, on 15 August 2005, we are running a one day symposium on Empirical Inference, including some excellent speakers. Participation is free of charge. For further details, see http://www.kyb.tuebingen.mpg.de/~bs/ei-symposium.html. best regards bernhard sch?lkopf From oury at bic.mni.mcgill.ca Wed Jul 20 13:37:25 2005 From: oury at bic.mni.mcgill.ca (Oury MONCHI) Date: Wed, 20 Jul 2005 13:37:25 -0400 Subject: Connectionists: workshops IJCNN Message-ID: Dear all, The organisers of IJCNN 2005, Montreal would like to bring your attention to the workshops being organised at the end of the conference (4th and 5th of august). These workshops are a great opportunity to increase your knowledge on specific topics linked to neural networks, information processing and computational neuroscience and are given by leaders in the field. The costs are 35$ dollars for a single workshop and 70$ to attend all of them. For more information please go to: http://faculty.uwb.edu/ijcnn05/Workshops/ Regards, ------------------------------------------------------------------------------- Oury Monchi, Ph.D. Research Assistant Professor, Department of Radiology, Universite de Montreal & Assistant Scientific Director, Unite de Neuroimagerie Fonctionnelle, Centre de Recherche, Institut Universitaire de Geriatrie de Montreal. 4565, chemin Queen Mary, Montreal (Quebec), H3W 1W5, CANADA e-mails: oury at bic.mni.mcgill.ca & oury.monchi at umontreal.ca tel: (514) 340-3540 ext 4013; fax: (514) 340-3548 ------------------------------------------------------------------------------- From cindy at bu.edu Tue Jul 26 16:35:18 2005 From: cindy at bu.edu (Cynthia Bradford) Date: Tue, 26 Jul 2005 16:35:18 -0400 Subject: Connectionists: Neural Networks 18(5/6): Special Issue on "Advances in Neural Networks Research: IJCNN'05" Message-ID: <200507262035.j6QKZJu9016458@kenmore.bu.edu> NEURAL NETWORKS 18(5/6) Contents - Volume 18, Number 5/6 - 2005 Special Issue on "Advances in Neural Networks Research: IJCNN'05" Danil Prokhorov, Daniel Levine, Fredric Ham, and William Howell (editors) ------------------------------------------------------------------ Introduction to the Special Issue Danil Prokhorov, Daniel Levine, Fredric Ham, and William Howell COMPUTATIONAL NEUROSCIENCE A model of STDP based on spatially and temporally local information: Derivation and combination with gated decay Anatoli Gorchetchnikov, Massimiliano Versace, and Michael E. Hasselmo Stochastic resonance in noisy spiking retinal and sensory neuron models Ashok Patel and Bart Kosko Quantifying information and performance for flash detection in the blowfly photoreceptor Peng Xu and Pamela Abshire Optimizing conductance parameters of cortical neural models via electronic partitions Keith Bush, James Knight, and Charles Anderson NEURODYNAMICS AND HARDWARE Metastability, instability, and state transition in neocortex Walter J. Freeman and Mark D. Holmes A mixed analog/digital chaotic neuro-computer system for quadratic assignment problems Yoshihiko Horio, Tohru Ikeguchi, and Kazuyuki Aihara FPGA implementation of self organizing map with digital phase locked loops Hiroomi Hikawa Rich dynamics of pulse-coupled spiking neurons with a triangular base signal Yoshio Kon, Toshimichi Saito, and Hiroyuki Torikai Non-homogenous neural networks with chaotic recursive nodes: Connectivity and multi-assemblies structures in recursive processing elements architectures Emilio Del Moral Hernandez PATTERN RECOGNITION, PERCEPTION, & MOTOR FUNCTIONS A hierarchical classifier using new support vector machines for automatic target recognition David Casasent and Yu-Chiang Wang Neural network model for extracting optic flow Kazuya Tohyama and Kunihiko Fukushima On-chip visual perception of motion: A bio-inspired connectionist model on FPGA C?sar Torres-Huitzil, Bernard Girau, and Claudio Castellanos-S?nchez Interactive image data labeling using self-organizing maps in an augmented reality scenario Holger Bekel, Gunther Heidemann, and Helge Ritter Incremental learning of feature space and classifier for face recognition Seiichi Ozawa, Soon Lee Toh, Shigeo Abe, Shaoning Pang, and Nikola Kasabov Generalized 2D principal component analysis for face image representation and recognition Hui Kong, Lei Wang, Eam Khwang Teoh, Xuchun Li, Jian-Gang Wang, and Ronda Venkateswarlu Training neural networks with heterogeneous data John A. Drakopoulos and Ahmad Abdulkader Framewise phoneme classification with bidirectional LSTM and other neural network architectures Alex Graves and J?rgen Schmidhuber COGNITIVE FUNCTIONS Subfield variations in hippocampal processing-components of a spatial navigation system Matthew Hartley, Neill Taylor, and John Taylor Modelling divided visual attention with a winner-take-all network Dominic I. Standage, Thomas P. Trappenberg, and Raymond M. Klein Dynamical systems and cognitive linguistics toward an active morphodynamical semantics Ren? Doursat and Jean Petitot Neural dynamics of psychotherapy: What modeling might tell us about us Ana Maria C. Aleksandrowicz and Daniel S. Levine Model of multi-modal cortical processing: Coherent learning in self organizing modules Oivier M?nard and Herv? Frezza-Buet The contribution of active body movement to visual development in evolutionary robots Mototaka Suzuki, Dario Floreano, and Ezequiel A. Di Paolo Application of neural network to humanoid robotics: Development of co-associative memory model Kazuko Itoh, Hiroyasu Miwa, Hideaki Takanobu, and Atsuo Takanish ADAPTATION AND DECISION MAKING Constructing Bayesian formulations of sparse kernel learning methods Gavin C. Cawley and Nicola L.C. Talbot Handling missing values in support vector machine classifiers K. Pelckmans, J.A.K. Suykens, B. De Mor, and J. De Brabanter Bayesian approach to feature selection and parameter tuning for support vector machine classifiers Carl Gold, Alex Holub, and Peter Sollich Improving dimensionality reduction with spectral gradient descent Roland Memisevic and Geoffrey Hinton Unifying cost and information in information-theoretic competitive learning Ryotaro Kamimura A new classifier based on information theoretic learning with unlabeled data Kyu-Hwa Jeong, Jian-Wu Xu, Deniz Erdogmus, and Jose C. Principe Cross-entropy embedding of high-dimensional data using the neural gas model Pablo A. Est?vez, Cristi?n J. Figueroa, and Kazumi Saito A model of evolution and learning Vladmir G. Red?ko, Oleg P. Mosalov, and Danil V. Prokhorov A regenerating spiking neural network Diego Federici Recurrent neural networks with backtrack-points and negative reinforcement applied to cost-based abduction Ashraf M. Abdelbar, Mostafa A El-Hemaly, Emad A.M. Andrews, and Donald C. Wunsch II APPLICATIONS Broadcast scheduling in wireless multihop networks using a neural-network based hybrid algorithm Haixiang Shi and Lipo Wang The control of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle using a CMAC neural network Frederick G. Harmon, Andrew A. Prank, and Sanjay S. Joshi A comparative study of autoregressive neural network hybrids Tugba Taskaya-Temizel and Matthew C. Casey Efficient streaming text clustering Shi Zhong Efficient information theoretic strategies for classifier combination, feature extraction and performance evaluation in improving false positives and false negatives for spam e-mail filtering V. Zorkadis, D.A. Karras, and M. Panayotou Modelling ordinal relations with SVMs: An application to objective aesthetic evaluation of breast cancer conservative treatment Jaime S. Cardoso, Joaquim F. Pinto da Costa, and Maria J. Cardoso Ovarian cancer diagnosis by hippocampus and neocortex-inspired learning memory structures T.Z. Tan, C. Quek, and G.S. Ng Individualization of pharmacological anemia management using reinforcement learning Adam E. Gaweda, Mehmet K. Muezzinoglu, George R. Aronoff, Alfred A. Jacobs, Jacek M. Zurada, and Michael E. Brier Identification of motifs with insertions and deletions in protein sequences using self-organizing neural networks Derong Liu, Xiaoxu Xiong, Zeng-Guang Hou, and Bhaskar DasGupta Bayesian model selection for mining mass spectrometry data Anshu Saksena, Dennis Lucarelli, and I-Jeng Wang Refining competition in the self-organising tree map for unsupervised biofilm image segmentation Matthew Kyan, Ling Guan, and Steven Liss ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 (regular) SEK 660 Y 13,000 Neural Networks (plus Y 2,000 enrollment fee) $20 (student) SEK 460 Y 11,000 (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- membership without $30 SEK 200 not available Neural Networks to non-student (subscribe through another society) Y 5,000 student (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- Name: ______________________________________________________ Title: ______________________________________________________ Address: ______________________________________________________ Phone: ______________________________________________________ Fax: ______________________________________________________ Email: ______________________________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number _______________________________ expiration date _____________________________ INNS Membership 2810 Crossroads Drive, Suite 3800 Madison WI 53718 USA 608 443 2461, ext. 138 (phone) 608 443 2474 (fax) srees at reesgroupinc.com http://www.inns.org ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership JNNS Secretariat c/o Fuzzy Logic Systems Institute 680-41 Kawazu, Iizuka Fukuoka 820-0067 Japan 81 948 24 2771 (phone) 81 948 24 3002 (fax) jnns at flsi.cird.or.jp http://www.jnns.org/ ---------------------------------------------------------------------------- From ted.carnevale at yale.edu Mon Jul 25 13:46:18 2005 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 25 Jul 2005 13:46:18 -0400 Subject: Connectionists: NEURON course at SFN 2005 Meeting Message-ID: <42E5256A.7030108@yale.edu> Short Course Announcement USING THE NEURON SIMULATION ENVIRONMENT Satellite Symposium, Society for Neuroscience Meeting 9 AM - 5 PM on Friday, Nov. 11, 2005 Speakers to include M.L. Hines and N.T. Carnevale NEURON is a powerful and convenient simulator that handles realistic models of biophysical mechanisms, individual neurons, and networks of cells, and runs under MSWindows, OS X, and UNIX/Linux. This one day course will present information essential for research and teaching applications of NEURON. The emphasis is on practical issues that are key to its most productive use. Topics that will be covered include: constructing and managing models of cells and networks importing detailed morphometric data expanding NEURON's repertoire of biophysical mechanisms database resources for empirically-based modeling New tools that will be presented include the Channel Builder, Model Viewer, and the Import3D tool. Each registrant will a comprehensive set of notes, plus selected reprints from The NEURON Book. Registration is limited to 40 individuals on a first-come, first serve basis. For more information see http://www.neuron.yale.edu/neuron/sfn2005/dc2005.html --Ted Carnevale From fellous at duke.edu Thu Jul 28 13:51:04 2005 From: fellous at duke.edu (Jean-Marc Fellous) Date: Thu, 28 Jul 2005 13:51:04 -0400 Subject: Connectionists: Position- Duke University Message-ID: <200507281751.j6SHpGWV029605@wilson.acpub.duke.edu> Could you please post? Thank you, Jean-Marc Fellous ---------------------------------------------------------------------------- --------------------------------------------------------- Cognitive Neuroscience Duke University The Center for Cognitive Neuroscience at Duke University seeks applications for a junior or mid-level faculty position in the general area of behavioral neurology or cognitive neuropsychology. A good candidate for the position could have either an MD or a PhD (or both). The major criterion for appointment will be exceptional promise for developing an imaginative research program in cognitive neuroscience that includes a patient-related component. The research interests of applicants might include, but are not limited to, language, social cognition, attention, emotion, executive function and/or cognitive aging. The successful candidate will hold tenure-track or tenured appointments in appropriate University or Medical Center departments, and will participate in related aspects of both graduate and undergraduate education. Available research facilities include 1.5T and 4T MRI scanners dedicated to neuroimaging research, state of the art ERP facilities, and extensive facilities for human psychophysics. Nearby patient facilities include Duke Hospital and the adjacent Durham VA Hospital. Candidates should submit a statement of research and teaching interests, a curriculum vita, representative publications, and arrange to have three letters of recommendation sent to: Dr. Dale Purves, Director, Center for Cognitive Neuroscience, Box 90999, Duke University, Durham, NC 27708 (for courier use LSRC Bldg. Rm B203, Tel: 919-668-2512); Fax: 919-681-0815, (http://www.mind.duke.edu) Email: purves at neuro.duke.edu Applications received by December 1, 2005 will be guaranteed consideration. Duke University is an Equal Opportunity/Affirmative Action Employer. ---------------------------------------------------------------------------- --------------------------------------------------------- From saighi at ixl.fr Thu Jul 28 05:02:43 2005 From: saighi at ixl.fr (Sylvain SAIGHI) Date: Thu, 28 Jul 2005 11:02:43 +0200 Subject: Connectionists: PhD position proposal In-Reply-To: <42E77906.60107@ixl.fr> References: <42E77906.60107@ixl.fr> Message-ID: <42E89F33.3010603@ixl.fr> PhD student position in the field of Neuromorphic Engineering IXL ? CNRS, Bordeaux, France The starting date should be between September 1, and December 31, 2005. The project concerns the development of VLSI circuits and electronics systems of high biological relevance that emulate in real-time multi-conductances neurons and neural networks with adaptive properties. This work is a part of a European Commission Integrated Project, in the "Future and Emerging Technologies" program of the 6th framework, starting September 1st 2005. The tasks will involve: - evaluation, development, and use of mathematical models for computational neuroscience - optimized design on digital VLSI of dedicated functions - benchmarking the hardware/software system and disseminating it to European partners - dissemination of the results in progress reports and international publications The work will be conducted at the IXL Microelectronics laboratory (www.ixl.fr), a CNRS institution associated to ENSEIRB-Universit? Bordeaux 1. IXL is located on the Bordeaux Science campus. The PhD student will join a research group (?Neurones artificiels sur Silicium?) working for more than 10 years on neuromorphic design, with a special emphasis on analog and mixed IC design. Applicants should have expertise on: - signal processing - design and synthesis of digital VLSI (including VHDL) - C language programming And a strong interest in: - computational neuroscience - microelectronics design For application or further information, please contact: Sylvie Renaud: renaudixl.fr Jean Tomas: tomasixl.fr From Hualou.Liang at uth.tmc.edu Sat Jul 30 16:42:39 2005 From: Hualou.Liang at uth.tmc.edu (Hualou Liang) Date: Sat, 30 Jul 2005 15:42:39 -0500 Subject: Connectionists: Positions Available: PostDoc & Scientific Programmer Message-ID: Positions Available: PostDoc & Scientific Programmer University of Texas Health Science Center at Houston Applications are invited for Postdoctoral fellow and Programmer positions currently open in the group of Dr. Hualou Liang (http://www.sahs.uth.tmc.edu/hliang/) at the University of Texas Health Science Center at Houston to participate in ongoing research projects that analyze large time series datasets being gathered under various tasks (e.g. visual selective attention and visuomotor pattern discrimination). 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. WHAT IS REQUIRED? * Postdoctoral fellow: 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. * Programmer: similar to the postdoctoral requirements (MS also considered), but with excellent computer skills (UNIX, Windows) to work on in-house multivariate autoregressive modeling software for analysis of neurobiological time series, as well as general web programming (e.g. cgi). HOW TO APPLY? Interested individuals should email a curriculum vitae, a brief statement of research interests, and the names of three references to Dr. Hualou Liang at Hualou.liang at uth.tmc.edu. -------------------------------- Hualou Liang, Ph.D. Assistant Professor The University of Texas at Houston 7000 Fannin, Suite 600 Houston, TX 77030 From Raphael.Maree at ULg.ac.be Tue Jul 5 09:51:30 2005 From: Raphael.Maree at ULg.ac.be (Raphael.Maree.) Date: Tue, 05 Jul 2005 15:51:30 +0200 Subject: Connectionists: PhD Studentship 'Random Tree Kernels' Message-ID: <20050705155126.0FB4.RAPHAEL.MAREE@ULg.ac.be> Dear colleagues, Please find below a PhD research studentship position at the University of Li?ge, Belgium. ---------------------------------------------------------------------------- ?Kernel properties of Random Tree Models? Random tree models have been extensively developed in the field of Machine Learning in the recent years. Instances of such methods are for example bagging, random subspace, random forests, and extra-trees. Random trees can be generated efficiently and the combination of large sets of random trees generally leads to accurate models. Under some hypothesis on the random distribution of trees, it is possible to characterize analytically the approximation produced by an infinite ensemble of trees. These models can also be interpreted as Kernel interpolators where the kernel is a mixture of randomized piece-wise constant kernels. Different random distribution of the tree models lead to different geometrical and statistical properties of the resulting models and kernels. The subject of this thesis project concerns the theoretical study of the properties of various Random Tree Models in order to improve our basic understanding of these methods and create new algorithms with pre-specified properties. Subject areas: machine learning, random processes, statistics, geometry and functional analysis References: 1. Zhao, G., `A new perspective on classification'. Ph.D. thesis, Utah State University, Department of Mathematics and Statistics, 2000. 2. Breiman, L., `Some infinity theory for predictor ensembles'. Technical Report 579, University of California, Department of Statistics, 2000. 3. Lin, Y. and Y. Jeon, `Random forests and adaptive nearest neighbors'. Technical Report 1055, University of Wisconsin, Department of Statistics, 2002. 4. Breiman, L., `Consistency for a simple model of random forests', Technical Report 579, University of California, Department of Statistics, 2004 5. P. Geurts, ?Contributions to decision tree induction: bias/variance tradeoff and time series classification?, PhD Thesis, University of Li?ge, Department of Electrical Engineering and Computer Science?, 2002. Contact: Prof. Louis Wehenkel L.Wehenkel at ulg.ac.be http://www.montefiore.ulg.ac.be/services/stochastic/ ---------------------------------------------------------------------------- From ishikawa at brain.kyutech.ac.jp Thu Jul 7 19:53:30 2005 From: ishikawa at brain.kyutech.ac.jp (Masumi Ishikawa) Date: Fri, 08 Jul 2005 08:53:30 +0900 Subject: Connectionists: Second Call for Papers (BrainIT2005) Message-ID: <6.0.0.20.2.20050708084935.0297e970@mail.brain.kyutech.ac.jp> ==================================================== We apologize if you receive multiple copies of this email. Please distribute this announcement to all interested parties. ==================================================== BrainIT2005 Second CALL FOR PAPERS The second international conference, BrainIT 2005, will be held in Kitakyushu, Japan, on October 7-9, 2005, in order to establish the foundations of the Brain-Inspired Information Technology. All working at the frontiers of Brain Science to Information Technology including Robotics are invited to participate in the second international conference, BrainIT 2005. At this conference, we will organize a special session on "Decision and Behavioral Choice Organized by Natural and Artificial Brain" in addition to invited papers from a wide range of fields from Brain Science to Information Technology. Invited Speakers Edmund T. Rolls (Oxford University, UK) Rolf Pfeifer (University of Zurich, Switzerland) Mandyam V. Srinivasan (Australian National University, Australia) Kenji Doya (Okinawa Institute of Science and Technology, Japan) Joshua I. Gold (University of Pennsylvania, USA) Walter J. Freeman (University of California, Berkeley, USA) Andreas Konig (Technische Univ. Kaiserslautern, Germany) Shu-Rong Wang (Institute of Biophysics, Chinese Academy of Sciences, China) Samuel Kaski (Helsinki University of Technology, Finland) Important Dates Abstract (for presentation) Submission Deadline: July 25, 2005 Notification of Acceptance: August 31, 2005 Pre-registration Deadline: September 9, 2005 Paper (for Edited Book) Submission Deadline: October 31, 2005 Scope and Topics BrainIT 2005 solicits experimental, computational, theoretical as well as engineering papers relating the topics in the following non-exhaustive, non-exclusive categories and keywords. Categories and Keywords: 1. Vision system 2. Other sensory systems 3. Cognition 4. Emotion 5. Learning and Memory 6. Behavior 7. Motor controls 8. Languages 9. Dynamics 10. Neural computation 11. Neural networks 12. Brain-inspired intelligent machines Papers that bridge brain science and information technology are especially welcome. Regular papers may include speculative discussions on Brain-Inspired Information Technology. BrainIT 2005 is open to all working at the frontiers of Brain Science to Information Technology (modeling and hardware realization) and provides the opportunity for presenting and discussing ideas that pave the way for the new field, Brain-Inspired Information Technology. Instructions for Authors Authors are requested to submit a 1-page A4-sized abstract by e-mail attachment as a PDF file to brian-it at lsse.kyutech.ac.jp. Each abstract will be independently reviewed by two reviewers. For further information, please refer to the web site. BrainIT Young Investigator Award (New!!) The purpose of this award is to encourage young researchers to make contributions to Brain-Inspired Information Technologies. Selection will be made by the BrianIT2005 Award Committee based on the abstract, the short oral presentation and the poster presentation. The awardee(s) will be given a testimonial and a prize at the Welcome Party. You can see the details on our web site. Registration Registration is free of charge. However, we recommend your early registration as the number of abstract books and other materials may be limited. # Submission and Registration Site is now open. Sponsors * "World of brain computing interwoven out of animals and robots": The 21st Century Center of Excellence Program of the Ministry of Education, Culture, Sports, Science and Technology, Japan * Kyushu Institute of Technology * Kitakyushu Foundation for the Advancement of Industry, Science and Technology (FAIS) Secretariat: Tetsuo FURUKAWA, PhD, Associate Professor Phone: +81-93-695-6124, Fax: +81-93-695-6134 E-mail: brain-it at lsse.kyutech.ac.jp For further information, please visit our web site: http://conf.lsse.kyutech.ac.jp/~brain-it/ 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 mvanross at inf.ed.ac.uk Wed Jul 6 05:22:12 2005 From: mvanross at inf.ed.ac.uk (Mark van Rossum) Date: Wed, 06 Jul 2005 10:22:12 +0100 Subject: Connectionists: Job Opening Computational Neuroscience Message-ID: <1120641733.3780.439.camel@localhost> Job Opening Computational Neuroscience. For our rapidly growing Doctoral Training Centre in Neuroinformatics, the School of Informatics invites applications for Lectureship or Readership in Neuroinformatics, with a focus on Computational Neuroscience. These positions are comparable to assistant/associate professor, but are permanent appointments. We are particularly interested in candidates engaged in computational modelling at either a molecular, cellular, systems, or cognitive level, as well as candidates who combine experimental approaches with computational modelling. You should be able to demonstrate an outstanding research record and commitment to excellence in teaching. You will be based in the Institute for Adaptive and Neural Computation (www.anc.ed.ac.uk). You will be expected to play a key role in the EPSRC/MRC Doctoral Training Centre in Neuroinformatics that is hosted within the School. This interdisciplinary training programme encompasses computational and cognitive neuroscience, software systems and tools to support neuroscience research and neurally inspired systems including neurorobotics and neural engineering. You will be expected to develop collaborative links and joint activities both nationally and internationally. For more information and how to apply see www.jobs.ed.ac.uk (ref 3004711). Deadline: July 29 2005. Informal inquiries to Dr Mark van Rossum, mvanrossATinf.ed.ac.uk, who will be present at CNS in Madison, WI. From Marcus.Frean at mcs.vuw.ac.nz Fri Jul 8 09:29:35 2005 From: Marcus.Frean at mcs.vuw.ac.nz (Marcus Frean) Date: Sat, 9 Jul 2005 01:29:35 +1200 (NZST) Subject: Connectionists: PhD scholarship Message-ID: PhD Scholarship Victoria University of Wellington is offering a PhD scholarship in the area of Intelligent Systems. The scholarship will be worth $NZ 20,000 plus domestic fees. Note, the New Zealand government recently announced a scheme under which new PhD international students from 2006 only need to pay domestic fees. The ideal candidate will have, or be expecting to complete, a strong undergraduate degree (honours) or masters in computer science, statistics, or a related discipline, with interests in probabilistic machine learning algorithms such as graphical models, Gaussian processes, and reinforcement learning. Informal enquiries can be made to Marcus Frean (marcus at mcs.vuw.ac.nz). General information and application forms are available via http://www.mcs.vuw.ac.nz/research/ai/ The deadline for applications is 18 July 2005. Marcus Frean http://www.mcs.vuw.ac.nz/~marcus From t.heskes at science.ru.nl Sat Jul 9 14:25:49 2005 From: t.heskes at science.ru.nl (Tom Heskes) Date: Sat, 09 Jul 2005 20:25:49 +0200 Subject: Connectionists: Neurocomputing volume 67 Message-ID: <42D016AD.90600@science.ru.nl> Neurocomputing Volume 67 (August 2005) ------- SPECIAL PAPERS (Geometrical Methods in Neural Networks and Learning edited by Simone Fiori and Shun-ichi Amari) Geometrical methods in neural networks and learning Simone Fiori and Shun-ichi Amari Geometrical learning, descriptive geometry, and biomimetic pattern recognition Wang Shoujue and Lai Jiangliang Nonlinear dimensionality reduction of data manifolds with essential loops John Aldo Lee and Michel Verleysen Geometric preprocessing, geometric feedforward neural networks and Clifford support vector machines for visual learning Eduardo Bayro-Corrochano, Refugio Vallejo and Nancy Arana-Daniel Learning algorithms utilizing quasi-geodesic flows on the Stiefel manifold Yasunori Nishimori and Shotaro Akaho Tools for application-driven linear dimension reduction Anuj Srivastava and Xiuwen Liu Geometrical methods for non-negative ICA: Manifolds, Lie groups and toral subalgebras Mark D. Plumbley Algebraic geometry of singular learning machines and symmetry of generalization and training errors Sumio Watanabe The geometry of prior selection Hichem Snoussi Lattice duality: The origin of probability and entropy Kevin H. Knuth ------- LETTERS Hyperchaos in Hopfield-type neural networks Qingdu Li, Xiao-Song Yang and Fangyan Yang GraySOFM network for solving classification problems Ming-Feng Yeh and Kuang-Chiung Chang A robust approach to empirical PDF estimate Sungho Jo Dimensional complexity analysis of human EEG in visual processing Shan Tong, Hua Huang, Ju Luan and Huaiqing Chen LMI-based robust stability analysis of neural networks with time-varying delay Hongbin Zhang and Xiaofeng Liao GreyART network for data clustering Ming-Feng Yeh and Shao-Shan Chiang Global convergence analysis of a self-stabilizing MCA learning algorithm Mao Ye An uncorrelated fisherface approach Xiao-Yuan Jing, Hau-San Wong, David Zhang and Yuan-Yan Tang Seeking multi-thresholds directly from support vectors for image segmentation Songcan Chen and Min Wang Applications of a neural network to watermarking capacity of digital image Fan Zhang and Hongbin Zhang Non-uniform image compression using a biologically motivated selective attention model Seung-Hyun Lee, Sang-Bok Choi, Minho Lee and Hyun-Seung Yang Weighted maximum margin discriminant analysis with kernels Wenming Zheng, Cairong Zou and Li Zhao Learning similarity for semantic images classification Dianhui Wang, Joon Shik Lim, Myung-Mook Han and Byung-Wook Lee A simple functional neural network for computing the largest and smallest eigenvalues and corresponding eigenvectors of a real symmetric matrix Yiguang Liu, Zhisheng You and Liping Cao A functional neural network for computing the largest modulus eigenvalues and their corresponding eigenvectors of an anti-symmetric matrix Yiguang Liu, Zhisheng You and Liping Cao Regaining sparsity in kernel principal components C. Garc?a-Osorio and Colin Fyfe Boosting Na?ve Bayes text classification using uncertainty-based selective sampling Han-Joon Kim, Je-Uk Kim and Young-Gook Ra An efficient parallel algorithm for the minimum crossing number problem Rong Long Wang and Kozo Okazaki A binary Hopfield neural network with hysteresis for large crossbar packet-switches Guangpu Xia, Zheng Tang, Yong Li and Jiahai Wang Fuzzy linear proximal support vector machines for multi-category data classification Jayadeva, Reshma Khemchandani and Suresh Chandra A discrete competitive Hopfield neural network for cellular channel assignment problems Jiahai Wang, Zheng Tang, Xinshun Xu and Yong Li Supervised kernel locality preserving projections for face recognition Jian Cheng, Qingshan Liu, Hanqing Lu and Yen-Wei Chen On the possible use of ICA to identify synaptic inputs from observations of several neurons Pando Gr. Georgiev and Henry C. Tuckwell A method to improve the transiently chaotic neural network Xinshun Xu, Zheng Tang and Jiahai Wang ------- JOURNAL SITE: http://www.elsevier.com/locate/neucom SCIENCE DIRECT: http://www.sciencedirect.com/science/issue/5660-2005-999329999-601289 From hinton at cs.toronto.edu Wed Jul 6 13:51:44 2005 From: hinton at cs.toronto.edu (Geoffrey Hinton) Date: Wed, 06 Jul 2005 13:51:44 -0400 Subject: Connectionists: Two new papers on generative models Message-ID: Preprints of the following two papers are available at http://www.cs.toronto.edu/~hinton/ "A FAST LEARNING ALGORITHM FOR DEEP BELIEF NETS" Geoffrey Hinton, Simon Osindero, and Yee-Whye Teh ABSTRACT We show how to use ``complementary priors'' to eliminate the explaining away effects that make inference difficult in densely-connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory. The fast, greedy algorithm is used to initialize a slower learning procedure that fine-tunes the weights using a contrastive version of the wake-sleep algorithm. After fine-tuning, a network with three hidden layers forms a very good generative model of the joint distribution of handwritten digit images and their labels. This generative model gives better digit classification than the best discriminative learning algorithms. The low-dimensional manifolds on which the digits lie are modelled by long ravines in the free-energy landscape of the top-level associative memory and it is easy to explore these ravines by using the directed connections to display what the associative memory has in mind. (submitted to Neural Computation) _______________________________________________________________ "INFERRING MOTOR PROGRAMS FROM IMAGES OF HANDWRITTEN DIGITS" Geoffrey Hinton and Vinod Nair ABSTRACT We describe a generative model for handwritten digits that uses two pairs of opposing springs whose stiffnesses are controlled by a motor program. We show how neural networks can be trained to infer the motor programs required to accurately reconstruct the MNIST digits. The inferred motor programs can be used directly for digit classification, but they can also be used in other ways. By adding noise to the motor program inferred from an MNIST image we can generate a large set of very different images of the same class, thus enlarging the training set available to other methods. We can also use the motor programs as additional, highly informative outputs which reduce overfitting when training a feed-forward classifier. (submitted to NIPS) From d.mandic at imperial.ac.uk Mon Jul 11 10:34:48 2005 From: d.mandic at imperial.ac.uk (Danilo P. Mandic) Date: Mon, 11 Jul 2005 15:34:48 +0100 Subject: Connectionists: Research Position in Blind Source Separation at Imperial College London Message-ID: <00a701c58625$b0f8bb50$432e16ac@MandicLaptop> Dear All, may I draw your attention to the following opening:- Research Assistant/Associate in Signal Processing Area: Blind Source Extraction Department of Electrical and Electronic Engineering, Imperial College London. Salary in the range ?22,116 - ?25,259 inclusive per annum, dependent on experience Fixed-Term appointment September 2005 - April 2007 A research position is available for a Research Assistant or Associate to work on blind source extraction for brain signals. The candidate will be working with Dr Danilo Mandic, based in the Communications and Signal Processing Research Group of the Department of Electrical and Electronic Engineering, South Kensington Campus. This research will be conducted in collaboration with the Brain Science Institute, RIKEN, Japan. The purpose of this project is to develop a theoretical, computational, and experimental framework for online blind extraction of only one or a few sources from large and complex mixtures. The position involves work on the development, mathematical characterisation and simulations on EEG and MEG measurements. The project will show whether applying some fundamental properties of signals, such as their predictability, smoothness and sparseness, in BSE has advantages over existing methods, for complex temporally and spatially correlated sources. The successful candidate will have a strong mathematical background especially in information theory, statistical estimation and optimisation theory. Applicants should normally hold a PhD (or equivalent) or be near to completion of a PhD in engineering, mathematics, physics or relevant disciplines. Previous experience in blind source separation, blind source extraction or adaptive filtering is desirable. Experience in using MATLAB is essential. For further details see http://www.commsp.ee.ic.ac.uk/~mandic/. To apply, please send your completed application form (downloadable from http://www.imperial.ac.uk/employment/academicform.htm), CV, names of two referees, and covering letter explaining your current interests and relevant background for this project to Mrs Mazie Paul (m.paul at imperial.ac.uk), Communications and Signal Processing Group, Department of Electrical and Electronic Engineering, Imperial College London, South Kensington Campus, London, SW7 2AZ. Closing date: 17 July 2005 More details can be found at http://www.jobs.ac.uk/jobfiles/LM805.html Best wishes Danilo =================================== Dr Danilo Mandic Reader in Signal Processing Imperial College London From g.goodhill at imb.uq.edu.au Mon Jul 11 21:58:53 2005 From: g.goodhill at imb.uq.edu.au (Geoffrey Goodhill) Date: Tue, 12 Jul 2005 11:58:53 +1000 Subject: Connectionists: 5 Positions Available Message-ID: 5 POSITIONS AVAILABLE IN COMPUTATIONAL NEUROSCIENCE / AXON GUIDANCE My lab recently moved from Georgetown University to the University of Queensland, Australia, and five positions are now available: - 2 postdoc positions in the area of the computational modelling of visual cortical map development. One of these positions is for a collaboration with Kwabena Boahen, Matt Dalva and Marcos Frank at the University of Pennsylvania. - 1 postdoc and 1 research faculty position in the area of axon guidance. These would suit people with broad backgrounds in tissue culture, immunohistochemistry and small animal surgery. - 1 research assistant position to provide computational support for the above projects. According to http://www.thes.co.uk/worldrankings the University of Queensland is one of the top 50 universities in the world, on a par with Edinburgh in the UK and Duke in the US. It provides an excellent environment for interdisciplinary research, and is currently investing AU$200M in the general area of Biotechnology. This includes AU$50M for a new neuroscience institute, http://www.qbi.uq.edu.au, for which a new 7000sqm building is currently under construction. UQ is in Brisbane, the capital of Queensland, a cosmopolitan city of 1.5 million people with excellent facilities, a vibrant cultural environment, and a subtropical climate. Queensland is also home to attractions such as tropical rainforests and the Great Barrier Reef. Australia was recently ranked by the United Nations in the top 5 countries in the world to live (http://news.bbc.co.uk/2/hi/europe/2149799.stm). Informal enquiries are welcome, but to be formally considered you must respond by the closing date of August 5th to one of the job adverts posted at http://www.uq.edu.au/staff - click on "browse" and then scroll to the jobs posted on July 11th. More details of these positions and the skills required for each are also provided here. More information about the lab can be found at www.goodhill.org, and some recent publications are listed below. Thanks, Geoffrey J Goodhill, PhD Associate Professor Queensland Brain Institute and Department of Mathematics University of Queensland St Lucia, QLD 4072, Australia Phone: +61 7 3346 2612 Fax: +61 7 3346 8836 Email: goodhill at uq.edu.au RECENT PUBLICATIONS Rosoff et al (2004). A new chemotaxis assay shows the extreme sensitivity of axons to molecular gradients. Nature Neuroscience, 7, 678-682. Goodhill et al (2004). Predicting axonal response to molecular gradients with a computational model of filopodial dynamics. Neural Computation, 16, 2221-2243. Carreira-Perpinan & Goodhill (2004). The influence of lateral connections on the structure of cortical maps. Journal of Neurophysiology, 92, 2947-2959. Carreira-Perpinan et al (2005). A computational model for the development of multiple maps in primary visual cortex. Cerebral Cortex, in press. Goodhill & Xu (2005). The development of retinotectal maps: a review of models. Network, in press. Rosoff et al (2005). Generating controlled molecular gradients in 3D gels. Biotechnology and Bioengineering, in press. From mo at ecs.soton.ac.uk Tue Jul 12 10:27:09 2005 From: mo at ecs.soton.ac.uk (Manfred Opper) Date: Tue, 12 Jul 2005 15:27:09 +0100 Subject: Connectionists: postdoctoral position in Southampton Message-ID: <42D3D33D.FD1A79D8@ecs.soton.ac.uk> The ISIS group at the School of Electronics and Computer Science of Southampton University invites applications for a 3 year postdoctoral position for the project "Inference in Complex Stochastic Dynamic Environmental Models" funded by EPSRC and NERC. The project is a collaboration between ISIS, groups at Aston and Surrey universities and the Met Office as a project partners. The goal of this exciting multi-institution project is to develop a theoretical framework for probabilistic forecasting in environmental models relevant to meteorology, climatology and oceanography. Such models are described by very large systems of nonlinear stochastic differential equations with often unknown parameters. We will develop methods for an approximate inference of probability distributions and parameters for these models using variational techniques developed in statistical physics and machine learning. In particular we will extend recently developed methods for inference in Gaussian processes to the dynamical case, where we will combine the models and observations (much as in data assimilation) to infer both the model state through time and the unknown model parameters. Hence, the ideal candidate for this position has a background in statistical physics or mathematics with a strong interest in applying probability theory to complex systems. Salary will be in the range of 22,774 - 28,009 British Pounds per annum. The deadline for applications is August 23, 2005. The Image, Speech and Intelligent Systems (ISIS) group activities are centred in fundamental theory and algorithm development associated with adaptive data modelling, machine learning, control theory and signal processing. The group is part of the School of Electronics and Computer Science that received top ratings in both Electronics and Computer Science at the last RAE. {\tt \bf http://www.ecs.soton.ac.uk/info/groups/isis/}. Informal enquires can be made to Manfred Opper (mo at ecs.soton.ac.uk) or John Shawe--Taylor (jst at ecs.soton.ac.uk). Further details about how to apply can be found under http://www.jobs.soton.ac.uk/adminweb/jsp/jobs/sJobview.jsp?function=View&id=04R0842 From netta at comp.leeds.ac.uk Mon Jul 11 22:23:26 2005 From: netta at comp.leeds.ac.uk (N Cohen) Date: Tue, 12 Jul 2005 03:23:26 +0100 (BST) Subject: Connectionists: Permanent position: Biosystems, School of Computing, Leeds Message-ID: Dear Connectionists, The School of Computing at the University of Leeds, UK is seeking to fill a permanent position, preferably in the Biosystems/ Biorobotics/ Neuroscience areas. The position is available immediately at the level of Lecturer or Senior Lecturer or Reader. We are particularly keen to attract a candidate either in bio-robotics (or bio-inspired robotics) or in computational neuroscience, but candidates in any biosystems area (biological computation/bio-inspired computing, etc.) are welcome. The official advert is on: http://www.comp.leeds.ac.uk/vacancies/20050726lecturer.shtml The closing date is 26 July, 05. Netta Cohen netta at comp.leeds.ac.uk ====================================================================== Biosystems Group School of Computing University of Leeds Leeds, LS2 9JT United Kingdom www.comp.leeds.ac.uk/netta/ From aimath06 at golem.cs.umass.edu Fri Jul 15 16:49:03 2005 From: aimath06 at golem.cs.umass.edu (aimath06@golem.cs.umass.edu) Date: Fri, 15 Jul 2005 16:49:03 -0400 (EDT) Subject: Connectionists: CFP: AI and Math 2006 Message-ID: FIRST CALL FOR PAPERS Ninth International Symposium on Artificial Intelligence and Mathematics http://anytime.cs.umass.edu/aimath06/ January 4-6, 2006 Fort Lauderdale, Florida Paper Submission Deadline: October 2, 2005 The International Symposium on Artificial Intelligence and Mathematics is a biennial meeting that fosters interactions between mathematics, theoretical computer science, and artificial intelligence. This is the ninth symposium in a series, which is sponsored by Annals of Mathematics and Artificial Intelligence. We seek submissions of recent results with a particular emphasis on the foundations of AI and mathematical methods used in AI. Papers describing applications are also encouraged, but the focus should be on principled lessons learned from the development of the application. Traditionally, the Symposium attracts participants from a variety of disciplines, thereby providing a unique forum for scientific exchange. The three-day symposium includes invited speakers, presentations of technical papers, and special topic sessions. INVITED SPEAKERS o Thomas Dean, Brown University, USA o Carla Gomes, Cornell University, USA o Jeffrey S. Rosenschein, The Hebrew University of Jerusalem, Israel SPECIAL TOPIC SESSIONS TBA PAPER SUBMISSION: Paper submission will be electronic via the submission link on the symposium web site. Papers, no more than (8) pages long, must be submitted in PDF or PS format. Fonts must be at least 10 point, and either a single or double column format may be used. The submission deadline is October 2, 2005 (11:59PM EST). Papers will be reviewed by members of the Program Committee. Authors will be notified of acceptance or rejection by October 31, 2005. Final versions of accepted papers, for inclusion in the conference electronic proceedings, are due by November 21, 2005. Note that papers may be submitted to the Symposium even if submitted to other conferences or journals, because the Symposium web site is not archival. Full versions of a selected set of papers from the Symposium will be included in a special volume of Annals of Mathematics and Artificial Intelligence, published by Springer. Authors of these selected papers will be invited to submit their full version subject to refereeing at the usual high standards of the journal and will receive more details with the acceptance notice. Any questions regarding paper submission should be sent to the program chair, Shlomo Zilberstein . IMPORTANT DATES: Paper submission: Sunday, October 2, 2005 Notification: Monday, October 31, 2005 Final version due: Monday, November 21, 2005 SPONSORS: The Symposium is partially supported by the Annals of Math and AI and Florida Atlantic University. ORGANIZERS: o General Chair: Martin Charles Golumbic, University of Haifa, Israel o Conference Chair: Frederick Hoffman, Florida Atlantic University, USA o Program Chair: Shlomo Zilberstein, University of Massachusetts Amherst, USA o Publicity Chair: Daniel Bernstein, University of Massachusetts Amherst, USA PROGRAM COMMITTEE: Peter Bartlett (University of California Berkeley, USA), Peter van Beek (University of Waterloo, Canada), Ronen Brafman (Ben-Gurion University, Israel), François Charpillet (INRIA, France), Berthe Choueiry (University of Nebraska-Lincoln, USA), Adnan Darwiche (University of California Los Angeles, USA), Thomas Eiter (Vienna University of Technology, Austria), Boi Faltings (EPFL, Switzerland), Daniela Pucci de Farias (Massachusetts Institute of Technology, USA), John Franco (University of Cincinnati, USA), Hector Geffner (UPF, Spain), Enrico Giunchiglia (University of Genova, Italy), Claudia Goldman (University of Haifa, Israel), Amy Greenwald (Brown University, USA), Joseph Halpern (Cornell University, USA), Peter Hammer (Rutgers University, USA), Eric Hansen (Mississippi State University, USA), Lisa Hellerstein (Polytechnic University, USA), Andreas Herzig (Université Paul Sabatier, France), Peter Jonsson (University of Linkoping, Sweden), Michael Kaminski (Technion, Israel), Henry Kautz (University of Washington, USA), Hélène Kirchner (LORIA CNRS and INRIA, France), Sven Koenig (University of Southern California, USA), Richard Korf (University of California Los Angeles, USA), Hector Levesque (University of Toronto, Canada), Michael Littman (Rutgers University, USA), Alan Mackworth (University of British Columbia, Canada), David Parkes (Harvard University, USA), Ronald Parr (Duke University, USA), David Poole (University of British Columbia, Canada), Dan Roth (University of Illinois at Urbana-Champaign, USA), Bart Selman (Cornell University, USA), Milind Tambe (University of Southern California, USA), Moshe Tennenholtz (Technion, Israel), Toby Walsh (University of New South Wales, Australia), Michael Wooldridge (University of Liverpool, England) ADVISORY COMMITTEE: The Editor-in-Chief (Martin Charles Golumbic) and the members of the Editorial Board of Annals of Mathematics and Artificial Intelligence serve as the permanent Advisory Committee of the Symposium. Further details can be found at: http://anytime.cs.umass.edu/aimath06/ From derdogmus at ieee.org Tue Jul 12 17:15:42 2005 From: derdogmus at ieee.org (Deniz Erdogmus) Date: Tue, 12 Jul 2005 14:15:42 -0700 Subject: Connectionists: Research Assistantship in Adaptive Signal Processing and Machine Learning Message-ID: <42D432FE.6090006@ieee.org> PHD RESEARCH ASSISTANTSHIP IN ADAPTIVE SYSTEMS AT THE OGI SCHOOL OF SCIENCE AND ENGINEERING AT OHSU A 3-year research assistantship position is available at OGI for individuals interested in pursuing a PhD in Machine Learning or Adaptive Signal Processing towards a CS or EE degree at the CSEE department. The successful candidate will have a strong background on mathematical techniques essential to the areas mentioned above, and will conduct research on developing robust sequential state estimation algorithms for complex systems using measurements from unreliable sensors. This research position will be based in the Adaptive Systems Lab (adsyl.cse.ogi.edu), but will require close interaction with the Point-of-Care Laboratory of the BME department. The RA position includes tuition waiver and a stipend of approximately US$23,000. The desired starting date is October 1st, 2005. Students of any nationality may apply. OGI is one of the four schools of Oregon Health & Science University (OHSU). OGI is located 12 miles west of Portland, Oregon, in the heart of the Silicon Forest. Portland's extensive high-tech community, diverse cultural amenities and spectacular natural surroundings combine to make the quality of life here extraordinary. To learn more about the department, OGI, OHSU and Portland, please visit http://www.cse.ogi.edu. Informal inquiries can be made by sending email (with supporting CV, statement of research interests, and copies of transcripts) to Deniz Erdogmus at derdogmus at ieee.org. For information on submitting a full application to the PhD program in Computer Science and Electrical Engineering, see the OGI admissions information at www.ogi.edu/admissions/. -- Deniz Erdogmus Assistant Professor Departments of CSEE and BME Oregon Health & Science University 20000 NW Walker Road, Beaverton, OR 97006 (Tel) 1-503-7482007, (Fax) 1-503-7481548 http://www.cse.ogi.edu/~deniz derdogmus at ieee.org From nkasabov at aut.ac.nz Tue Jul 12 17:27:38 2005 From: nkasabov at aut.ac.nz (Nik Kasabov) Date: Wed, 13 Jul 2005 09:27:38 +1200 Subject: Connectionists: Workshop on the Synergism of ANN, Bioinformatics and Neuroinformatics, IJCNN, 4.08.05 Message-ID: Dear colleagues, The following Workshop is free to attend and to present your views/results: http://faculty.uwb.edu/ijcnn05/Workshops/bio-neuro-info.html See you there. Nik Kasabov *---------------------------------------------------------------------------------------------------- Artificial Neural Networks, Bioinformatics and Neuroinformatics - A Synergistic ApproachTopics and Goals: The aim of the workshop is to bring together researchers from at least three areas of science: information and mathematical sciences, neuroscience, and molecular biology, in order to discuss in an open forum the synergistic development of these areas in the future. Opportunities to develop new artificial neural network (ANN) models and new models of brain functions that take into account the latest discoveries in molecular biology and bioinformatics will be discussed, along with methods and systems for solving problems in bioinformatics and neuro-informatics with the use of novel ANN approaches. Topics Include: Novel, biologically plausible models of ANN and their dynamics. Spiking neurons and spiking neural networks. Evolving and evolutionary neural networks. New mathematical approaches to modeling biologically plausible ANN. Software and hardware systems that facilitate the synergistic study of brain functions, molecular biology and ANN dynamics. Learning and adaptation in molecular biology related to brain functions. Genes and gene regulatory networks related to brain functions. Neurogenetic models of brain development, brain diseases, learning and memory, evolution and plasticity. Molecular computing Applications Where are ANNs going next? Organizers: Prof. Nik Kasabov (nkasabov at aut.ac.nz) and Prof. Amir Assadi.Intended audience: The workshop is aimed at a broader audience of computer scientists, mathematicians, cognitive scientists, engineers, bioinformaticians, molecular biologists, neurophysiologists. In a sense it will be a summary of the IJCNN conference aimed at outlining new directions for further research in ANN. Prof. Nik Kasabov, MSc, PhD FRSNZ, FNZCS, SrMIEEE Founding Director and Chief Scientist - Knowledge Engineering and Discovery Research Institute, KEDRI Chair of Knowledge Engineering, School of Computer and Information Sciences Auckland University of Technology phone: +64 9 917 9506 ; fax: +64 9 917 9501 WWW http://www.kedri.info email: nkasabov at aut.ac.nz (PA Joyce D'Mello: jdmello at aut.ac.nz; +64 9 917 9504) From terry at salk.edu Wed Jul 13 02:39:18 2005 From: terry at salk.edu (Terry Sejnowski) Date: Tue, 12 Jul 2005 23:39:18 -0700 Subject: Connectionists: NEURAL COMPUTATION 17:8 In-Reply-To: <200505200528.j4K5SbO59466@kepler.snl.salk.edu> Message-ID: Neural Computation - Contents - Volume 17, Number 8 - August 1, 2005 Notes Motion Contrast Classification Is a Linearly Nonseparable Problem Alireza S. Mahani and Ralf Wessel Edgeworth-Expanded Gaussian Mixture Density Modeling Marc M. Van Hulle Letters Movement Generation with Circuits of Spiking Neurons Prashant Joshi and Wolfgang Maass Cognitive Enhancement Mediated Through Postsynaptic Actions of Norepinephrine on Ongoing Cortical Activity Osamu Hoshino Advancing the Boundaries of High-Connectivity Network Simulation with Distributed Computing Abigail Morrison, Carsten Mehring, Theo Geisel, Ad Aertsen, and Markus Diesmann Dynamical Analysis of Continuous Higher-Order Hopfield Networks for Combinatorial Optimization Miguel Atencia, Gonzalo Joya,and Francisco Sandoval Some Generalized Sufficient Convergence Criteria for Nonlinear Continuous Neural Networks Jito Vanualailai and Shin-ichi Nakagiri Estimation and Marginalization Using Kikuchi Approximation Methods Payam Pakzad and Venkat Anantharam ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2005 - VOLUME 17 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $143 $90 $96.30 Institution $680 $727.60 $734 $612 $654.84 * 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 oreilly at psych.colorado.edu Fri Jul 15 01:26:19 2005 From: oreilly at psych.colorado.edu (Randall C. O'Reilly) Date: Thu, 14 Jul 2005 23:26:19 -0600 Subject: Connectionists: REMINDER: Call for Abstracts for CCN/NIMH Dynamical Neuroscience Conference Message-ID: <200507142326.20216.oreilly@psych.colorado.edu> ~ FINAL REMINDER ~ ~ CALL-FOR-ABSTRACTS ~ DEADLINE: August 1, 2005 1ST ANNUAL CONFERENCE ON COMPUTATIONAL COGNITIVE NEUROSCIENCE and NIMH DYNAMICAL NEUROSCIENCE SATELLITE SYMPOSIUM of the Annual Meeting of the Society for Neuroscience, Washington DC Thu-Fri November 10 & 11, 2005 WWW.CCNCONFERENCE.ORG ______________________________________________________________________ Deadline for submissions: August 1, 2005 Meeting Registration and Abstract Submission are processed on-line at: http://www.cmpinc.net/dynamical/ There are two categories of submissions: * Poster only * Short talk (15 min), with accompanying poster Abstracts should be limited to 250 words. Women and underrepresented minorities are especially encouraged to apply. Reviewing for posters will be light and only to ensure appropriateness to the meeting. Talks will be selected on the basis of research quality, relevance to conference theme, and expected accessibility in a talk format. Notification of acceptance will be made by September 1, 2005. ______________________________________________________________________ Conference information: This is the inaugural meeting of what will be a rotating satellite with other meetings, such as (tentative list): CNS (Cognitive Neuroscience Society), HBM (Organization for Human Brain Mapping), CogSci (Cognitive Science Society), Psychonomic Society, NIPS (Neural Information Processing Systems Foundation), and COSYNE (Computational and Systems Neuroscience)). Featured Keynote Speakers: James L. McClelland, Carnegie Mellon University Title: Principles of Cognitive and Neural Processing Daniel M. Wolpert, University College London/University of Cambridge Title: Probabilistic Models of Sensorimotor Control Discussion-Focused Symposia: Decision Making Chair: Michael Shadlen, University of Washington Speakers: Carlos Brody, Cold Spring Harbor Laboratory Yael Niv, Hebrew University Leo Sugrue, Stanford University Developmental Disorders Chair: Michael Thomas, University of London Speakers: Marc Joanisse, University of Western Ontario Fred Dick, University of London April Benasich, Rutgers University Category Learning Chair: Brad Love, University of Texas Speakers: Greg Ashby, UC Santa Barbara Paul Reber, Northwestern University Episodic Memory Chair: Michael Hasselmo, Boston University Speakers: Kenneth Norman, Princeton University Charan Ranganath, UC, Davis Chantal Stern, Boston University ______________________________________________________________________ BACKGROUND: The field of cognitive neuroscience has flourished due to advances using multiple methodologies such as anatomy, physiology, imaging, and behavior. Given the progress that has been made in each of these areas, the time is ripe for strong theoretical frameworks that can relate different levels of analysis, moving beyond basic brain/behavior correlations. The emerging field of Computational Cognitive Neuroscience (CCN) is ideally suited to help fill this need through the use of mathematical analysis and explicit computational models that bridge the gap between biological mechanisms and cognitive function. This meeting focuses on research at the intersection of neuroscience, cognitive psychology, and computational modeling, where neuroscience-based computational models are used to simulate and understand cognitive functions such as perception, attention, learning and memory, language, and higher-level cognitive functions. CCN research benefits greatly from collaboration with various non-modeling researchers for developing and interpreting relevant empirical data. A major goal for this conference is to create fruitful opportunities for modelers and non-modelers to interact. ______________________________________________________________________ PLANNING COMMITTEE: Todd Braver, Washington University, St Louis Carlos Brody, Cold Spring Harbor Jonathan Cohen, Princeton University Dennis Glanzman, NIMH Yuko Munakata, University of Colorado, Boulder David Noelle, Vanderbilt University Randall O'Reilly, University of Colorado, Boulder (Chair) For more information and to sign up for the mailing list visit: WWW.CCNCONFERENCE.ORG ______________________________________________________________________ From gasser at cs.indiana.edu Fri Jul 15 10:36:16 2005 From: gasser at cs.indiana.edu (Michael Gasser) Date: Fri, 15 Jul 2005 09:36:16 -0500 (EST) Subject: Connectionists: Job: Computation, Language, Cognition: Indiana U CogSci Message-ID: [Connectionist language researchers are encouraged to apply. -Mike Gasser] Indiana University, Bloomington, Indiana. Faculty position beginning Fall, 2006 As one of a series of new appointments, the Cognitive Science Program at Indiana University seeks applicants with a developing strong record of research in 'Computational Approaches to Language and Cognition', broadly defined. Rank is open. We are looking for someone with vision, energy, and a desire to explore new forms of interdisciplinary study. The right candidate is more important than the specific disciplinary background. Junior applicants should send full dossiers, including letters of recommendation and sample papers. Senior applicants may do the same, but we also encourage potential senior applicants to contact us directly to discuss possibilities. Indiana University is an equal opportunity/affirmative action employer. Applications from women and minority group members are especially encouraged. We may also be able to consider joint hiring of two affiliated applicants both in the field. As far as possible, e-mail all materials (ideally in PDF format) to cogsrch at indiana.edu. Materials may also be mailed to Professor Michael Gasser, Computation, Language, Cognition Search Committee, Cognitive Science Program, Eigenmann 819, 1910 E. 10th St., Bloomington, IN 47406-7512. Applications received by December 1, 2005 are assured full consideration. Address any questions you have about the position to gasser at indiana.edu. From soeren.lorenz at uni-bielefeld.de Fri Jul 15 13:41:23 2005 From: soeren.lorenz at uni-bielefeld.de (Soeren Lorenz) Date: Fri, 15 Jul 2005 19:41:23 +0200 Subject: Connectionists: Brains, Minds and Media - first publications online Message-ID: <42D7F543.9060600@uni-bielefeld.de> ******** Apologies for multiple postings ******** ____________________________________________________________ ------------ FIRST PUBLICATIONS ONLINE ------------ --------- eJournal Brains, Minds & Media ---------- ------------- Journal of New Media in ------------- --- Neural and Cognitive Science and Education ---- -------- http://www.brains-minds-media.org -------- ____________________________________________________________ FIRST PUBLICATIONS ONLINE Brains, Minds & Media, the novel open access online journal of new media in neural and cognitive science and education, has started publishing. The first publications are now online: http://www.brains-minds-media.org/current. CURRENT ARTICLES ***Research "The Role of Consciousness in Memory" by Stan Franklin, Bernard J. Baars, Uma Ramamurthy, Matthew Ventura. ***Tutorials "Learning Paradigms Exemplified by Virtual Experiments with Honey Bees" by Juliane Ullrich, Soeren Lorenz, Corinna Pelz, Randolf Menzel. "Transfer Functions in Artificial Neural Networks - A Simulation-Based Tutorial " by Klaus Debes, Alexander Koenig and Horst-Michael Gross. ***Project Notes "CELEST - The Center of Excellence for Learning in Education, Science, and Technology " by Stephen Grossberg. "Transforming Education, Collaboration, and Research in Neuroscience: The GENESIS Project - approaching its third decade" by James M. Bower. CALL FOR SUBMISSION "Brains, Minds & Media" publishes peer-reviewed articles and media from research and education in neural and cognitive science (see http://www.brains-minds-media.org/aims"). Future accepted contributions will be published consecutively and integrated ex post into volumes or (special) issues. You are invited to submit contributions to 'Brains, Minds & Media'. More information about manuscipt submissions can be found at http://www.brains-minds-media.org/guidelines. Please send your submission to editors at brains-minds-media.org. If you have any questions, please contact info at brains-minds-media.org. Thank you! Soeren Lorenz (editorial assistance) soeren.lorenz at uni-bielefeld.de From yves.moreau at esat.kuleuven.ac.be Thu Jul 14 09:25:39 2005 From: yves.moreau at esat.kuleuven.ac.be (Yves Moreau) Date: Thu, 14 Jul 2005 15:25:39 +0200 Subject: Connectionists: Ph.D. fellowship in bioinformatics - University of Leuven, Belgium Message-ID: Dear Connectionists, We have currently one Ph.D. fellowship available for a candidate with a strong interest in machine learning (probabilistic graphical models and kernel methods) and in bioinformatics (genomic data fusion). See full announcement below. Best regards, Yves Moreau K.U.Leuven ESAT-SCD DESCRIPTION: One 3-year Ph.D. fellowship supported by the European Commission is available starting on November 1st, 2005 with the Bioinformatics team (http://www.esat.kuleuven.ac.be/~dna/bioi/) at the University of Leuven under the supervision of Prof. Yves Moreau and Prof. Bart De Moor. The research project, part of the EU funded BIOPTRAIN program, will tackle the development of new algorithms for genomic data fusion using probabilistic graphical models and kernel methods. These methods will be applied to the prioritization of candidate genes from high-throughput genomic studies using multiple heterogeneous sources of information (sequence analysis, gene expression data, functional annotation, literature mining). A functional prototype has already been developed and is available at http://www.esat.kuleuven.ac.be/endeavour. The goal of the Ph.D. will be to develop powerful new algorithms on top of the existing software architecture. Our bioinformatics group (http://www.esat.kuleuven.ac.be/~dna/bioi/) is highly dynamic (currently about twenty members) and the University of Leuven is one of Europe's leading universities in the Life Sciences, which offers many collaboration opportunities. Leuven is a charming Renaissance-style city next to Brussels, Belgium. It is ideally located in Europe with excellent flight and train connections to the rest of Europe. QUALIFICATIONS: The ideal candidate will have a master's degree (or equivalent) in, for example, statistics, mathematics, engineering, computer science, or physics. A solid mathematical background is required. Previous knowledge of artificial intelligence, statistics, or bioinformatics is highly desirable. EMPLOYMENT AND SALARY: Fellows will be recruited under an employment contract and will benefit from travel and mobility allowances. The remuneration package is highly competitive for a position at this level. Additional details about these positions (in particular, salary and eligibility) can be found in the EST Handbook (http://europa.eu.int/comm/research/fp6/mariecurie-actions/pdf/est_hand.pdf; pp.21-29). Women in particular are invited to apply. If several applicants have approximately equivalent qualifications, EU rules on equal opportunities will be applied. ELIGIBILITY CRITERIA: An approximate summary of the complex eligibility criteria is as follows: * Candidates should NOT have more than 4 years of research or R&D experience (following the first university degree that allows them to enter a Ph.D. program) and NOT yet hold a Ph.D. * Candidates should NOT be Belgian (or, if Belgian, must have resided outside the EU for four of the last five years). * Candidates should NOT have resided in Belgium for more than 12 months in the past 3 years. * Non-EU candidates can apply (but competition is fierce because only 30% of all fellowships can be awarded to non-EU citizens). * Non-EU candidates who have been residing in a European country for 4 of the last 5 years are assimilated to EU candidates (and thus are not constrained by the previous 30% rule). HOW TO APPLY: Applications should include your CV, a one-page statement of your research interests and motivations for pursuing Ph.D. studies, and contact information (including email addresses) for at least two references. Please send your application, preferably by email, to the attention of Prof. Yves Moreau at Bart.Motmans at esat.kuleuven.ac.be (using PDF or plain text for your attachments) or by surface mail to Prof. Yves Moreau K.U.Leuven ESAT-SCD (Bioinformatics) Kasteelpark Arenberg 10 B-3001 Leuven Belgium DEADLINE: The positions will be filled a.s.a.p. 10 other EST positions are currently open with the other BIOPTRAIN partners, see http://www.bioptrain.org/index.php/Applications. From shadmehr at jhu.edu Mon Jul 18 09:14:28 2005 From: shadmehr at jhu.edu (Reza Shadmehr) Date: Mon, 18 Jul 2005 09:14:28 -0400 Subject: Connectionists: Computational Motor Control Message-ID: <200507181310.j6IDARe24741@storey.bme.jhu.edu> Dear colleagues: Emo Todorov and I would like to invite you to the fourth computational motor control symposium at the Society for Neuroscience conference. The symposium will take place on Friday, Nov. 11 2005 at the Washington DC convention center. The purpose of the meeting is to highlight computational modeling and theories in motor control. This is an opportunity to meet and hear from some of the bright minds in the field. The program consists of two distinguished speakers and 12 contributed talk, selected from the submitted abstracts. The speakers this year are: Daniel Wolpert, University College London Andrew Schwartz, University of Pittsburg We encourage you to consider submitting an abstract. The abstracts will be reviewed by a panel and ranked. The top 12 abstracts will be selected for oral presentation. We encourage oral presentation by students who have had a major role in the work described in the abstracts. More information is available here: www.bme.jhu.edu/acmc The deadline for abstract submission is September 30. Abstracts should be no more than two pages in length, including figures and references. with our best wishes, Reza Shadmehr and Emo Todorov From terry at salk.edu Mon Jul 18 17:40:00 2005 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 18 Jul 2005 14:40:00 -0700 Subject: Connectionists: Re: NEURAL COMPUTATION 17:8 In-Reply-To: Message-ID: In addition to the papers listed in the recent posting, the August, 2005 issue of Neural Computation also includes: Review How Close Are We to Understanding V1 ? Bruno A. Olshausen and David J. Field Terry ----- From beer at eecs.cwru.edu Tue Jul 19 17:25:46 2005 From: beer at eecs.cwru.edu (Randall Beer) Date: Tue, 19 Jul 2005 17:25:46 -0400 Subject: Connectionists: Job: Embodied Cognitive Science: Indiana U CogSci Message-ID: Indiana University, Bloomington, Indiana. Faculty position beginning Fall, 2006 As part of a series of new appointments, the Cognitive Science Program at Indiana University seeks a junior level appointment in the general area of intersection of cognitive science and robotics. We are particularly interested in applicants with expertise in evolutionary robotics and situated, embodied and dynamical approaches to cognition. Applicants should have a record that demonstrates an excellent potential in the areas of research and teaching. Successful applicants will take a leadership role in the planning and execution of a new, state-of-the-art laboratory for teaching and research. Indiana University is an equal opportunity/affirmative action employer. Applications from women and minority group members are especially encouraged. As far as possible, e-mail all materials (ideally in PDF format) to cogsrch at indiana.edu. Materials may also be mailed to Professor Richard Shiffrin, Robotics Search Committee, Cognitive Science Program, Eigenmann 819, 1910 E. 10th St., Bloomington, IN 47406-7512. Applications received by December 1, 2005 are assured full consideration. From bernhard.schoelkopf at tuebingen.mpg.de Wed Jul 20 04:48:30 2005 From: bernhard.schoelkopf at tuebingen.mpg.de (=?iso-8859-1?Q?Bernhard_Sch=F6lkopf?=) Date: Wed, 20 Jul 2005 10:48:30 +0200 Subject: Connectionists: One Day Symposium in Tuebingen, Germany Message-ID: Dear Connectionists, on 15 August 2005, we are running a one day symposium on Empirical Inference, including some excellent speakers. Participation is free of charge. For further details, see http://www.kyb.tuebingen.mpg.de/~bs/ei-symposium.html. best regards bernhard sch?lkopf From oury at bic.mni.mcgill.ca Wed Jul 20 13:37:25 2005 From: oury at bic.mni.mcgill.ca (Oury MONCHI) Date: Wed, 20 Jul 2005 13:37:25 -0400 Subject: Connectionists: workshops IJCNN Message-ID: Dear all, The organisers of IJCNN 2005, Montreal would like to bring your attention to the workshops being organised at the end of the conference (4th and 5th of august). These workshops are a great opportunity to increase your knowledge on specific topics linked to neural networks, information processing and computational neuroscience and are given by leaders in the field. The costs are 35$ dollars for a single workshop and 70$ to attend all of them. For more information please go to: http://faculty.uwb.edu/ijcnn05/Workshops/ Regards, ------------------------------------------------------------------------------- Oury Monchi, Ph.D. Research Assistant Professor, Department of Radiology, Universite de Montreal & Assistant Scientific Director, Unite de Neuroimagerie Fonctionnelle, Centre de Recherche, Institut Universitaire de Geriatrie de Montreal. 4565, chemin Queen Mary, Montreal (Quebec), H3W 1W5, CANADA e-mails: oury at bic.mni.mcgill.ca & oury.monchi at umontreal.ca tel: (514) 340-3540 ext 4013; fax: (514) 340-3548 ------------------------------------------------------------------------------- From cindy at bu.edu Tue Jul 26 16:35:18 2005 From: cindy at bu.edu (Cynthia Bradford) Date: Tue, 26 Jul 2005 16:35:18 -0400 Subject: Connectionists: Neural Networks 18(5/6): Special Issue on "Advances in Neural Networks Research: IJCNN'05" Message-ID: <200507262035.j6QKZJu9016458@kenmore.bu.edu> NEURAL NETWORKS 18(5/6) Contents - Volume 18, Number 5/6 - 2005 Special Issue on "Advances in Neural Networks Research: IJCNN'05" Danil Prokhorov, Daniel Levine, Fredric Ham, and William Howell (editors) ------------------------------------------------------------------ Introduction to the Special Issue Danil Prokhorov, Daniel Levine, Fredric Ham, and William Howell COMPUTATIONAL NEUROSCIENCE A model of STDP based on spatially and temporally local information: Derivation and combination with gated decay Anatoli Gorchetchnikov, Massimiliano Versace, and Michael E. Hasselmo Stochastic resonance in noisy spiking retinal and sensory neuron models Ashok Patel and Bart Kosko Quantifying information and performance for flash detection in the blowfly photoreceptor Peng Xu and Pamela Abshire Optimizing conductance parameters of cortical neural models via electronic partitions Keith Bush, James Knight, and Charles Anderson NEURODYNAMICS AND HARDWARE Metastability, instability, and state transition in neocortex Walter J. Freeman and Mark D. Holmes A mixed analog/digital chaotic neuro-computer system for quadratic assignment problems Yoshihiko Horio, Tohru Ikeguchi, and Kazuyuki Aihara FPGA implementation of self organizing map with digital phase locked loops Hiroomi Hikawa Rich dynamics of pulse-coupled spiking neurons with a triangular base signal Yoshio Kon, Toshimichi Saito, and Hiroyuki Torikai Non-homogenous neural networks with chaotic recursive nodes: Connectivity and multi-assemblies structures in recursive processing elements architectures Emilio Del Moral Hernandez PATTERN RECOGNITION, PERCEPTION, & MOTOR FUNCTIONS A hierarchical classifier using new support vector machines for automatic target recognition David Casasent and Yu-Chiang Wang Neural network model for extracting optic flow Kazuya Tohyama and Kunihiko Fukushima On-chip visual perception of motion: A bio-inspired connectionist model on FPGA C?sar Torres-Huitzil, Bernard Girau, and Claudio Castellanos-S?nchez Interactive image data labeling using self-organizing maps in an augmented reality scenario Holger Bekel, Gunther Heidemann, and Helge Ritter Incremental learning of feature space and classifier for face recognition Seiichi Ozawa, Soon Lee Toh, Shigeo Abe, Shaoning Pang, and Nikola Kasabov Generalized 2D principal component analysis for face image representation and recognition Hui Kong, Lei Wang, Eam Khwang Teoh, Xuchun Li, Jian-Gang Wang, and Ronda Venkateswarlu Training neural networks with heterogeneous data John A. Drakopoulos and Ahmad Abdulkader Framewise phoneme classification with bidirectional LSTM and other neural network architectures Alex Graves and J?rgen Schmidhuber COGNITIVE FUNCTIONS Subfield variations in hippocampal processing-components of a spatial navigation system Matthew Hartley, Neill Taylor, and John Taylor Modelling divided visual attention with a winner-take-all network Dominic I. Standage, Thomas P. Trappenberg, and Raymond M. Klein Dynamical systems and cognitive linguistics toward an active morphodynamical semantics Ren? Doursat and Jean Petitot Neural dynamics of psychotherapy: What modeling might tell us about us Ana Maria C. Aleksandrowicz and Daniel S. Levine Model of multi-modal cortical processing: Coherent learning in self organizing modules Oivier M?nard and Herv? Frezza-Buet The contribution of active body movement to visual development in evolutionary robots Mototaka Suzuki, Dario Floreano, and Ezequiel A. Di Paolo Application of neural network to humanoid robotics: Development of co-associative memory model Kazuko Itoh, Hiroyasu Miwa, Hideaki Takanobu, and Atsuo Takanish ADAPTATION AND DECISION MAKING Constructing Bayesian formulations of sparse kernel learning methods Gavin C. Cawley and Nicola L.C. Talbot Handling missing values in support vector machine classifiers K. Pelckmans, J.A.K. Suykens, B. De Mor, and J. De Brabanter Bayesian approach to feature selection and parameter tuning for support vector machine classifiers Carl Gold, Alex Holub, and Peter Sollich Improving dimensionality reduction with spectral gradient descent Roland Memisevic and Geoffrey Hinton Unifying cost and information in information-theoretic competitive learning Ryotaro Kamimura A new classifier based on information theoretic learning with unlabeled data Kyu-Hwa Jeong, Jian-Wu Xu, Deniz Erdogmus, and Jose C. Principe Cross-entropy embedding of high-dimensional data using the neural gas model Pablo A. Est?vez, Cristi?n J. Figueroa, and Kazumi Saito A model of evolution and learning Vladmir G. Red?ko, Oleg P. Mosalov, and Danil V. Prokhorov A regenerating spiking neural network Diego Federici Recurrent neural networks with backtrack-points and negative reinforcement applied to cost-based abduction Ashraf M. Abdelbar, Mostafa A El-Hemaly, Emad A.M. Andrews, and Donald C. Wunsch II APPLICATIONS Broadcast scheduling in wireless multihop networks using a neural-network based hybrid algorithm Haixiang Shi and Lipo Wang The control of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle using a CMAC neural network Frederick G. Harmon, Andrew A. Prank, and Sanjay S. Joshi A comparative study of autoregressive neural network hybrids Tugba Taskaya-Temizel and Matthew C. Casey Efficient streaming text clustering Shi Zhong Efficient information theoretic strategies for classifier combination, feature extraction and performance evaluation in improving false positives and false negatives for spam e-mail filtering V. Zorkadis, D.A. Karras, and M. Panayotou Modelling ordinal relations with SVMs: An application to objective aesthetic evaluation of breast cancer conservative treatment Jaime S. Cardoso, Joaquim F. Pinto da Costa, and Maria J. Cardoso Ovarian cancer diagnosis by hippocampus and neocortex-inspired learning memory structures T.Z. Tan, C. Quek, and G.S. Ng Individualization of pharmacological anemia management using reinforcement learning Adam E. Gaweda, Mehmet K. Muezzinoglu, George R. Aronoff, Alfred A. Jacobs, Jacek M. Zurada, and Michael E. Brier Identification of motifs with insertions and deletions in protein sequences using self-organizing neural networks Derong Liu, Xiaoxu Xiong, Zeng-Guang Hou, and Bhaskar DasGupta Bayesian model selection for mining mass spectrometry data Anshu Saksena, Dennis Lucarelli, and I-Jeng Wang Refining competition in the self-organising tree map for unsupervised biofilm image segmentation Matthew Kyan, Ling Guan, and Steven Liss ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 (regular) SEK 660 Y 13,000 Neural Networks (plus Y 2,000 enrollment fee) $20 (student) SEK 460 Y 11,000 (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- membership without $30 SEK 200 not available Neural Networks to non-student (subscribe through another society) Y 5,000 student (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- Name: ______________________________________________________ Title: ______________________________________________________ Address: ______________________________________________________ Phone: ______________________________________________________ Fax: ______________________________________________________ Email: ______________________________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number _______________________________ expiration date _____________________________ INNS Membership 2810 Crossroads Drive, Suite 3800 Madison WI 53718 USA 608 443 2461, ext. 138 (phone) 608 443 2474 (fax) srees at reesgroupinc.com http://www.inns.org ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership JNNS Secretariat c/o Fuzzy Logic Systems Institute 680-41 Kawazu, Iizuka Fukuoka 820-0067 Japan 81 948 24 2771 (phone) 81 948 24 3002 (fax) jnns at flsi.cird.or.jp http://www.jnns.org/ ---------------------------------------------------------------------------- From ted.carnevale at yale.edu Mon Jul 25 13:46:18 2005 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 25 Jul 2005 13:46:18 -0400 Subject: Connectionists: NEURON course at SFN 2005 Meeting Message-ID: <42E5256A.7030108@yale.edu> Short Course Announcement USING THE NEURON SIMULATION ENVIRONMENT Satellite Symposium, Society for Neuroscience Meeting 9 AM - 5 PM on Friday, Nov. 11, 2005 Speakers to include M.L. Hines and N.T. Carnevale NEURON is a powerful and convenient simulator that handles realistic models of biophysical mechanisms, individual neurons, and networks of cells, and runs under MSWindows, OS X, and UNIX/Linux. This one day course will present information essential for research and teaching applications of NEURON. The emphasis is on practical issues that are key to its most productive use. Topics that will be covered include: constructing and managing models of cells and networks importing detailed morphometric data expanding NEURON's repertoire of biophysical mechanisms database resources for empirically-based modeling New tools that will be presented include the Channel Builder, Model Viewer, and the Import3D tool. Each registrant will a comprehensive set of notes, plus selected reprints from The NEURON Book. Registration is limited to 40 individuals on a first-come, first serve basis. For more information see http://www.neuron.yale.edu/neuron/sfn2005/dc2005.html --Ted Carnevale From fellous at duke.edu Thu Jul 28 13:51:04 2005 From: fellous at duke.edu (Jean-Marc Fellous) Date: Thu, 28 Jul 2005 13:51:04 -0400 Subject: Connectionists: Position- Duke University Message-ID: <200507281751.j6SHpGWV029605@wilson.acpub.duke.edu> Could you please post? Thank you, Jean-Marc Fellous ---------------------------------------------------------------------------- --------------------------------------------------------- Cognitive Neuroscience Duke University The Center for Cognitive Neuroscience at Duke University seeks applications for a junior or mid-level faculty position in the general area of behavioral neurology or cognitive neuropsychology. A good candidate for the position could have either an MD or a PhD (or both). The major criterion for appointment will be exceptional promise for developing an imaginative research program in cognitive neuroscience that includes a patient-related component. The research interests of applicants might include, but are not limited to, language, social cognition, attention, emotion, executive function and/or cognitive aging. The successful candidate will hold tenure-track or tenured appointments in appropriate University or Medical Center departments, and will participate in related aspects of both graduate and undergraduate education. Available research facilities include 1.5T and 4T MRI scanners dedicated to neuroimaging research, state of the art ERP facilities, and extensive facilities for human psychophysics. Nearby patient facilities include Duke Hospital and the adjacent Durham VA Hospital. Candidates should submit a statement of research and teaching interests, a curriculum vita, representative publications, and arrange to have three letters of recommendation sent to: Dr. Dale Purves, Director, Center for Cognitive Neuroscience, Box 90999, Duke University, Durham, NC 27708 (for courier use LSRC Bldg. Rm B203, Tel: 919-668-2512); Fax: 919-681-0815, (http://www.mind.duke.edu) Email: purves at neuro.duke.edu Applications received by December 1, 2005 will be guaranteed consideration. Duke University is an Equal Opportunity/Affirmative Action Employer. ---------------------------------------------------------------------------- --------------------------------------------------------- From saighi at ixl.fr Thu Jul 28 05:02:43 2005 From: saighi at ixl.fr (Sylvain SAIGHI) Date: Thu, 28 Jul 2005 11:02:43 +0200 Subject: Connectionists: PhD position proposal In-Reply-To: <42E77906.60107@ixl.fr> References: <42E77906.60107@ixl.fr> Message-ID: <42E89F33.3010603@ixl.fr> PhD student position in the field of Neuromorphic Engineering IXL ? CNRS, Bordeaux, France The starting date should be between September 1, and December 31, 2005. The project concerns the development of VLSI circuits and electronics systems of high biological relevance that emulate in real-time multi-conductances neurons and neural networks with adaptive properties. This work is a part of a European Commission Integrated Project, in the "Future and Emerging Technologies" program of the 6th framework, starting September 1st 2005. The tasks will involve: - evaluation, development, and use of mathematical models for computational neuroscience - optimized design on digital VLSI of dedicated functions - benchmarking the hardware/software system and disseminating it to European partners - dissemination of the results in progress reports and international publications The work will be conducted at the IXL Microelectronics laboratory (www.ixl.fr), a CNRS institution associated to ENSEIRB-Universit? Bordeaux 1. IXL is located on the Bordeaux Science campus. The PhD student will join a research group (?Neurones artificiels sur Silicium?) working for more than 10 years on neuromorphic design, with a special emphasis on analog and mixed IC design. Applicants should have expertise on: - signal processing - design and synthesis of digital VLSI (including VHDL) - C language programming And a strong interest in: - computational neuroscience - microelectronics design For application or further information, please contact: Sylvie Renaud: renaudixl.fr Jean Tomas: tomasixl.fr From Hualou.Liang at uth.tmc.edu Sat Jul 30 16:42:39 2005 From: Hualou.Liang at uth.tmc.edu (Hualou Liang) Date: Sat, 30 Jul 2005 15:42:39 -0500 Subject: Connectionists: Positions Available: PostDoc & Scientific Programmer Message-ID: Positions Available: PostDoc & Scientific Programmer University of Texas Health Science Center at Houston Applications are invited for Postdoctoral fellow and Programmer positions currently open in the group of Dr. Hualou Liang (http://www.sahs.uth.tmc.edu/hliang/) at the University of Texas Health Science Center at Houston to participate in ongoing research projects that analyze large time series datasets being gathered under various tasks (e.g. visual selective attention and visuomotor pattern discrimination). 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. WHAT IS REQUIRED? * Postdoctoral fellow: 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. * Programmer: similar to the postdoctoral requirements (MS also considered), but with excellent computer skills (UNIX, Windows) to work on in-house multivariate autoregressive modeling software for analysis of neurobiological time series, as well as general web programming (e.g. cgi). HOW TO APPLY? Interested individuals should email a curriculum vitae, a brief statement of research interests, and the names of three references to Dr. Hualou Liang at Hualou.liang at uth.tmc.edu. -------------------------------- Hualou Liang, Ph.D. Assistant Professor The University of Texas at Houston 7000 Fannin, Suite 600 Houston, TX 77030