From ted.carnevale at yale.edu Wed Mar 1 18:12:19 2006 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Wed, 01 Mar 2006 18:12:19 -0500 Subject: Connectionists: 2006 NEURON Simulator Meeting Message-ID: <44062A53.4050203@yale.edu> What: the 2006 NEURON Simulator Meeting When: 9 AM Friday - Noon Sunday, May 5-7, 2006 Where: The University of Texas at Austin Registration is now open for the 2006 NEURON Simulator Meeting. The purpose of this meeting is to bring together people who are interested in using computational modeling in neuroscience research and education--especially current users of NEURON, and others who are interested in using it--in order to: * share knowledge about technical aspects of computational modeling * keep informed about the latest advances and "best practices" in the use of NEURON * encourage participation in NEURON's development * stimulate communication and collaboration This conference will alternate between single track sessions for presentations and discussions on topics of general interest, and multiple track breakout sessions for smaller group interactions. We invite proposals for talks, symposia, tutorials, and workshops (see "Proposals Invited" below). Registration is limited to 50 individuals on a first-come, first serve basis. For more information see http://www.utexas.edu/neuroscience/NEURON2006/nsm2006.html Proposals Invited We invite participants to propose and be responsible for talks, symposia, tutorials, or workshops. See http://www.utexas.edu/neuroscience/NEURON2006/nsm2006.html for more information. --Ted From g.goodhill at imb.uq.edu.au Wed Mar 1 22:00:06 2006 From: g.goodhill at imb.uq.edu.au (Geoffrey Goodhill) Date: Thu, 02 Mar 2006 13:00:06 +1000 Subject: Connectionists: Submit to Network via Manuscript Central Message-ID: <44065FB6.4030400@imb.uq.edu.au> Dear Connectionists, I am delighted to announce that the journal "Network: Computation in Neural Systems" is being relaunched by its new publishers, Taylor & Francis. As part of this the journal now has an online manuscript submission site based on Manuscript Central, which can be found at http://mc.manuscriptcentral.com/ncns This is linked from the journal's new homepage at http://www.tandf.co.uk/journals/titles/0954898X.asp Below is the Editorial that will appear in the March 2006 issue introducing the new Network. Among other things it outlines some new categories of papers Network will now consider. The new contact address for the Editorial Office is ncns at uq.edu.au. HOWEVER, during the transition period, please continue to send resubmissions of existing manuscripts and any related correspondence to net at tandf.co.uk as before. Regards, Geoffrey Goodhill Editor-in-Chief, Network: Computation in Neural Systems --------------------------------------------------------------- EDITORIAL: WELCOME TO THE NEW NETWORK Computational approaches are now accepted as useful, important, and sometimes even indispensible in most areas of neuroscience. It has become common to see papers in primarily experimental journals "garnished" by a modelling component. However, sometimes such journals are not equipped to do justice to the many details that are required to fully evaluate a mathematical/computational model. The role of Network is to present models in neuroscience which one can trust have been rigorously evaulated not just for their relevance to biology, but also for their mathematical and computational correctness, novelty, and elegance. It provides an indispensible port of call for both experimentalists and theoreticians who are eager to keep abreast of the latest developments in this fast-moving field. In July 2005 I was honoured to step into the large shoes of the previous Editor-in-Chief, David Willshaw. David's history is almost the modern history of computational neuroscience. He was there "battling", as they say in Australia, when theoretical approaches in some areas were often considered not just dispensible but downright dangerous. However he persevered and ultimately triumphed, establishing many of the basic theoretical foundations for areas including associative memory and topographic maps. Since 1998 he has devoted a huge amount of his time to the success of Network, for which I for one am extremely grateful. I now have the great pleasure of introducing you to a new era of Network. Taylor & Francis, the journal's new publishers, have made a considerable investment in relaunching the journal with a new design and a new online submission system based on Manuscript Central. To the already impressively staffed Editorial Board we have newly recruited two eminent senior neuroscientists (Chuck Stevens and Mu-ming Poo), and two new rising stars (Max Riesenhuber and Nick Brunel). We have also introduced a number of new categories of articles we will consider for publication. In addition to regular Articles, Network has a distinguished tradition of disseminating more lengthy Reviews. Besides continuing with these, we will now regularly publish Editorials, Viewpoints, and Historical Perspectives. Editorials will usually be contributed by a member of the Editorial Board, and will provide a "bully pulpit" for these leaders in the field to discuss issues they feel are of importance to the future of computational neuroscience. Viewpoints allow a more personal view of an area than is appropriate for a Review, and will often be opinionated and controversial. Occasional Historical Perspectives will briefly outline people and/or events that have been crucial in the past development of computational neuroscience, but which are perhaps not as well known or understood by neuroscientists at large as they should be. Usually Reviews, Viewpoints and Historical Perspectives will be invited by the Editorial Office. However unsolicted proposals will also be considered, which should consist in the first instance of a 1-page summary sent to ncns at uq.edu.au. Since becoming Editor-in-Chief I have been extremely impressed by both the commitment and enthusiasm of the Editorial Board, and the very thoughtful and thorough evaluations generously provided by many of our reviewers. I offer my most heartfelt thanks to everyone who contributes their valuable time to protecting and developing the scientific quality of the papers we publish. Besides taking on the job of Editor I recently moved my own lab to the University of Queensland, and my new responsibilities to Network seem ideally served by my joint appointment between the School of Physical Sciences and the new Queensland Brain Institute. I am looking forward with relish and excitement to the development of Network, and of computational neuroscience more generally, in the years to come. Geoffrey Goodhill, Editor-in-Chief University of Queensland, Australia From g.goodhill at imb.uq.edu.au Wed Mar 1 22:03:34 2006 From: g.goodhill at imb.uq.edu.au (Geoffrey Goodhill) Date: Thu, 02 Mar 2006 13:03:34 +1000 Subject: Connectionists: Workshop on Mathematical and Computational Neuroscience Message-ID: <44066086.9080406@imb.uq.edu.au> Dear Connectionists, The Queensland Brain Institute, the Australian Mathematical Sciences Institute, and Network: Computation in Neural Systems invite you to attend the following event: INAUGURAL QUEENSLAND BRAIN INSTITUTE WORKSHOP ON MATHEMATICAL AND COMPUTATIONAL NEUROSCIENCE August 13-14th, 2006. Hillstone St Lucia (www.hillstonestlucia.com.au) Brisbane, Australia. Speakers include: Shun-ichi Amari (Riken) Peter Dayan (University College London) Zhaoping Li (University College London) Mandyam Srinivasan (Australian National University) Peter Robinson (University of Sydney) Anthony Burkitt (Bionic Ear Institute, Melbourne) Kevin Burrage (University of Queensland) Geoffrey Goodhill (University of Queensland) Registration: AU$100 (Students AU$80). Abstract submissions are invited from registered participants for poster presentation. Submission deadline June 1st 2006. For further details please see http://public.qbi.uq.edu.au/cnw Some travel support is available from the Australian Mathematical Sciences Institute for participants from AMSI member organizations. See the above website for more details. Regards, Geoffrey J Goodhill, PhD Associate Professor Queensland Brain Institute, School of Physical Sciences & Institute for Molecular Bioscience University of Queensland St Lucia, QLD 4072, Australia Phone: +61 7 3346 2612 Fax: +61 7 3346 8836 Email: g.goodhill at uq.edu.au http://cns.qbi.uq.edu.au Editor-in-Chief, Network: Computation in Neural Systems From bower at uthscsa.edu Fri Mar 3 17:51:45 2006 From: bower at uthscsa.edu (james Bower) Date: Fri, 03 Mar 2006 16:51:45 -0600 Subject: Connectionists: Liaison Positions in Computational Biology in San Antonio, Texas Message-ID: The University of Texas San Antonio, and the University of Texas Health Science Center in San Antonio, have recently raised several million dollars to establish a facility in computational biology to engage in collaborative research with bench biologists within both institutions. Computational biology in this case is broadly defined, ranging from data-mining and gene sequence analysis to the construction of large scale realistic models of biological systems. The facility, for example, is the home of the GENESIS simulation project (http://www.genesis-sim.org/GENESIS/). The facility already includes staff and faculty who are expert in the technical aspects of computational biology. The Liaison positions offered here (see official announcement below), are intended to add core competence in biological experimentation and interpretation. The primary role of each of the three liaisons will be to serve as the interface between the facility and a number of different individual research laboratories. The ideal candidate is likely someone with a broad experience and interest in biology, who has successfully performed both experimental and computational science. These positions should be of particular interest to comparative studies. Liaisons will be non-tenure track faculty, with the ability to write and manage their own grants, and participate fully as professionals in research collaborations. San Antonio Currently, healthcare and biotechnology industries lead the San Antonio economy with an estimated annual economic impact of over $13 billion while maintaining 100,000 jobs. San Antonio itself is a wonderful place to live with a deep cultural heritage and particularly family friendly. The mean cost of housing is one of the lowest in the United States. Official Job Posting Instructor(s) for Bioinformatics/Computational Biology We are seeking to fill three research faculty positions with the title of Instructor who will be associated with a new Bioinformatics/Computational Biology Core Facility serving both UTHSCSA and UTSA. The primary responsibility of each position will be to foster the development and application of applied computational methodologies within existing individual laboratories and research programs at either or both institutions. Accordingly, each individual can be expected to work with several different laboratories on experimental design, development of analysis plans, and identification of training needs in computational techniques. In doing so, the individuals hired will also work closely with and be supported by the Core Facility's technical staff and associated supervising faculty. Instructor may also be involved in writing grant proposals, general training and instruction, and will play an integral role in planning the further development and extension of the core facility. Minimum requirements for this position are a doctoral degree in a biologically-related scientific discipline and a demonstrated proficiency in experimental design and laboratory technique. Candidates must also be able to demonstrate core competency in computational methods and analytical procedures. These positions are available on either a full- or part-time basis. Currently, the Center for Epidemiology and Biostatistics has 10 doctoral-level faculty and supports several large research programs such as the UTHSCSA/UTSA Bioinformatics/Computational Biology Program, the Children's Cancer Research Institute, the San Antonio Cancer Institute, and the Frederic C. Barter General Clinical Research Center. These programs span basic, translational, clinical and population-based research. Applicants should send current curriculum vitae, a description of research plans, and three letters of reference to: Brad H. Pollock, M.P.H., Ph.D. Professor & Director Center for Epidemiology and Biostatistics The University of Texas Health Science Center at San Antonio MC 7933 7703 Floyd Curl Drive San Antonio, TX 78229-3900 (210) 562-9020 or bpollock at uthscsa.edu All faculty appointments are designated as security sensitive positions. UTHSCSA is an Equal Employment Opportunity/Affirmative Action Employer. -- James M. Bower Ph.D. Research Imaging Center University of Texas Health Science Center at San Antonio 7703 Floyd Curl Drive San Antonio, TX 78284-6240 Cajal Neuroscience Center University of Texas San Antonio Phone: 210 567 8080 Fax: 210 567 8152 From fschwenker at neuro.informatik.uni-ulm.de Thu Mar 2 11:16:18 2006 From: fschwenker at neuro.informatik.uni-ulm.de (Friedhelm Schwenker) Date: Thu, 02 Mar 2006 17:16:18 +0100 Subject: Connectionists: ANNPR 2006 Final CFP and extended deadline Message-ID: <44071A52.6000604@neuro.informatik.uni-ulm.de> [ Apologies for multiple postings ] ************************************************************* !! EXTENDED PAPER SUBMISSION DEADLINE: MARCH 30, 2006 !! ************************************************************* FINAL CALL FOR PAPERS ANNPR 2006 2nd IAPR TC3 International Workshop on Artificial Neural Networks in Pattern Recognition August 31 - September 2 2006 University of Ulm, Reisensburg Castle (Germany) (http://www.informatik.uni-ulm.de/ni/ANNPR06) The workshop proceedings will be published by Springer Verlag (LNAI). Aim of the workshop: ANNPR 2006 follows the success of the first workshop ANNPR 2003 held at the University of Florence, Italy, in September 2003. This 2nd ANNPR workshop will act as a major forum for international researchers and practitioners working in all areas of neural network based pattern recognition to present and discuss the latest research, results, and ideas in these areas. The TC3 "Neural Networks & Computational Intelligence" is one of the 20 technical committees of the International Association on Pattern Recognition (IAPR). The scope of this TC is on all kinds of Computational Intelligence approaches, including artificial neural networks, fuzzy systems, evolutionary computing, with focus on pattern recognition applications. Papers are solicited dealing with neural networks and pattern recognition which emphasize methodological issues arising in applications. They should be related but not limited to the following topics. Methodological issues: - Supervised learning. - Unsupervised learning. - Combination of supervized and unsupervized learning. - Feedforward networks and kernel machines - Recurrent and competitive neural networks. - Hierarchical modular architectures and hybrid systems. - Combination of neural networks and Hidden Markov models. - Multiple classifier systems and ensemble methods. Applications in Pattern Recognition - Image processing and segmentation. - Sensorfusion and multimodal processing. - Feature extraction, dimension reduction. - Clustering and vector quantisation. - Speech and speaker recognition. - Data, text, and web mining. - Bioinformatics. --------------------------------------------------------------------------- Original and unpublished contributions are solicited which include regular papers and extended abstracts. Potential participants should submit a paper describing their work in one of the areas described above. Each regular paper must be accompanied by an abstract summarizing the contribution it makes to the field. Maximum paper length for regular papers is 12 pages in LNCS format. Extended abstracts can have at most four pages. Submission of a paper constitutes a commitment that, if accepted, one or more authors will attend and participate in the workshop. The workshop proceedings will be published in the Springer LNAI series. Electronic submission in camera-ready format is required. Papers must be sent to: Friedhelm Schwenker, Department of Neural Information Processing, University of Ulm (Email: friedhelm.schwenker at uni-ulm.de) --------------------------------------------------------------------------- Important Dates: Paper submission: March 30, 2006 Notification of acceptance: May 15, 2006 Camera ready copies: May 30, 2006 --------------------------------------------------------------------------- Further information: Contact Simone Marinai or Friedhelm Schwenker (Email: annpr2006 at uni-ulm.de) or visit the Workshop web page (http://www.informatik.uni-ulm.de/ni/ANNPR06/). --------------------------------------------------------------------------- General Chair Simone Marinai (University of Florence, Italy) Program Chair Friedhelm Schwenker (University of Ulm, Germany) Program Committee (confirmed members): Shigeo Abe (Kobe University, Japan) Herve Bourlard (IDIAP, Martigny, Switzerland) Horst Bunke (University of Bern, Switzerland) Neamat El Gayar(Cairo University, Egypt) Patrick Gallinari (University Pierre et Marie Curie, Paris, France) Marco Gori (University of Siena, Italy) Barbara Hammer (Technical University of Clausthal, Germany) Tom Heskes (University of Nijmegen, The Netherlands) Jose Manuel Inesta (University of Alicante, Spain) Rudolph Kruse (Otto-von-Guericke University of Magdeburg, Germany) Cheng-Lin Liu (Chinese Academy of Sciences, China) Marco Maggini (University of Siena, Italy) Erkki Oja (Helsinky University of Technology, Finland) Guenther Palm (University of Ulm, Germany) Marcello Pelillo (University Ca Foscari, Venezia, Italy) Raul Rojas (Freie University of Berlin, Germany) Fabio Roli (University of Cagliari, Italy) Ah Chung Tsoi (University of Wollongong, Australia) Michel Verleysen (Catholic University of Louvain, Belgium) Stefan Wermter (University of Sunderland, UK) ----------------------------------------------------- -- ---------------------------------------------------------------------- Dr. Friedhelm Schwenker University of Ulm | email: fschwenker at neuro.informatik.uni-ulm.de Department of Neural | fax: +49-731-50-24156 Information Processing | phone: +49-731-50-24159 D-89069 Ulm (Germany) | www: http://www.informatik.uni-ulm.de/ni/mitarbeiter/FSchwenker.html ---------------------------------------------------------------------- From jose.millan at jrc.it Thu Mar 2 12:09:04 2006 From: jose.millan at jrc.it (jose.millan@jrc.it) Date: Thu, 2 Mar 2006 18:09:04 +0100 Subject: Connectionists: Open position for Senior Researcher in Machine Learning at IDIAP Research Inst Message-ID: <4401D1930000023D@cheetah-1.jrc.it> The IDIAP Research Institute (www.idiap.ch) is currently seeking one talented senior researcher in machine learning with a proven record of high level research and project management, and whose interests are aligned with our existing strengths in speech processing, computer vision, biometric authentication, and multimedia data mining. A candidate with these strengths will be expected to play a leading role in the research, teaching ans strategic development of the Institute. Most of IDIAP's research ativities take place in the framework of National long term research initiatives such as the National Centre of Competence in Research (NCCR) on "Interactive Multimodal Information Management" (IM2, see www.im2.ch) or large European projects such as "Augmented Multi-party Interaction" (AMI, see www.amiproject.org). Specific Knowledge/Skills: * PhD in electrical engineering, computer science, signal processing, mathematics, statistics, or relevant discipline with a minimum of 5 years (post-PhD) experience. * Strong record of research and innovation in the area of pattern recognition and machine learning (incl. HMM, ANN,SVM, kernel approaches, Gaussian processes). * Significant experience in software development, including C/C++. * Experience with large real world audio and video data sets is desirable. * Experience in project management and supervision of researchers, including PhD students. * Good organizational and communication skills, both written and oral. * Ability to interact well with international, multi-disciplinary, R&D teams. Initiated in 1991, and supported by the Swiss Federal Government, the State of Valais, and the City of Martigny, IDIAP (www.idiap.ch) is an independent, nonprofit research institute located in Martigny (at the edge of the Swiss Alps), and is affiliated with EPFL (Ecole Polytechnique Federale de Lausanne) and the University of Geneva. See http://www.idiap.ch/pages/press/faq.pdf for more information and FAQs. IDIAP is building a culturally diverse research community and strongly encourages applications from female and minority candidates. Prospective candidates should apply with a cover letter, CV, statement of research interests and accomplishments, and names and email addresses of 3 references. Please sent these to jobs at idiap.ch, with a clear reference in subject header to "senior position in machine learning"). More information can also be obtained by contacting Prof. Herve Bourlard (bourlard at idiap.ch), Director of IDIAP. Start dates are flexible, but applications received by June 30, 2006, will receive full consideration. See http://www.idiap.ch/jobs.php for other positions available at IDIAP. -- Prof. Herv? Bourlard Director, IDIAP Research Institute, www.idiap.ch Professor, Swiss Federal Institute of Technology at Lausanne (EPFL), www.epfl.ch P.O. Box 592 Rue du Simplon, 4 CH-1920 Martigny, Switzerland Tel: +41-27-721.77.20 Mobile: +41-79-436.00.35 Fax: +41-27-721.77.12 Email: bourlard at idiap.ch http://www.idiap.ch/~bourlard From haeusler at igi.tu-graz.ac.at Fri Mar 3 05:44:16 2006 From: haeusler at igi.tu-graz.ac.at (Stefan Haeusler) Date: Fri, 03 Mar 2006 11:44:16 +0100 Subject: Connectionists: paper by Haeusler and Maass on detailed cortical microcircuit models Message-ID: <44081E00.9080105@igi.tu-graz.ac.at> The paper "A statistical analysis of information processing properties of lamina-specific cortical microcircuit models" by Stefan Haeusler, and Wolfgang Maass (to appear in Cerebral Cortex, 2006) is now available at http://cercor.oxfordjournals.org/cgi/reprint/bhj132 ABSTRACT: A major challenge for computational neuroscience is to understand the computational function of lamina-specific synaptic connection patterns in stereotypical cortical microcircuits. Previous work on this problem had focused on hypothesized specific computational roles of individual layers and connections between layers, and had tested these hypotheses through simulations of abstract neural network models. We approach this problem by studying instead the dynamical system defined by more realistic cortical microcircuit models as a whole, and by investigating the in fluence which its laminar structure has on the transmission and fusion of information within this dynamical system. The circuit models that we examine consist of Hodgkin-Huxley neurons with dynamic synapses, based on detailed data from [Thomson et al., 2002, Markram et al., 1998] and [Gupta et al., 2000]. We investigate to what extent this cortical microcircuit template supports the accumulation and fusion of information contained in generic spike inputs into layer 4 and layers 2/3, and how well it makes this information accessible to projection neurons in layers 2/3 and layer 5. We exhibit specific computational advantages of such data-based lamina-specific cortical microcircuit model by comparing its performance with various types of control models that have the same components and the same global statistics of neurons and synaptic connections, but are missing the lamina-specific structure of real cortical microcircuits. We conclude that computer simulations of detailed lamina-specific cortical microcircuit models provide new insight into computational consequences of anatomical and physiological data. Stefan Haeusler From derdogmus at ieee.org Wed Mar 1 14:39:45 2006 From: derdogmus at ieee.org (Deniz Erdogmus) Date: Wed, 01 Mar 2006 11:39:45 -0800 Subject: Connectionists: MLSP 2006 Data Analysis Competition extended deadline March 31st Message-ID: <4405F881.4000601@ieee.org> Dear Colleagues, I would like to bring to your attention the MLSP 2006 Data Analysis Competition announced at the following website: http://mlsp2006.conwiz.dk/index.php?id=18 The extended submission deadline for the competition is March 31st. If you have already submitted your entries, please feel free to send in revisions. The competition involves three separate problems that will be evaluated independently: 1) Large-scale, ill-conditioned, small-sample ICA 2) fMRI image processing 3) MEG denoising The winners in each category will be invited to submit papers to the Machine Learning for Signal Processing Workshop, as well as a follow-up journal special issue. Regards, Deniz -- 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.csee.ogi.edu/~deniz derdogmus at ieee.org From kampis at axelero.hu Sun Mar 5 12:10:33 2006 From: kampis at axelero.hu (Kampis) Date: Sun, 5 Mar 2006 18:10:33 +0100 Subject: Connectionists: Reminder: Budapest Semester in Cognitive Science 2006 Message-ID: <00a501c64077$bbd93ce0$0e01a8c0@kampis> [Sorry for cross-posting -- please forward to students] -------------------------------------------------------------- This is a reminder about the Budapest Semester in Cognitive Science (or BSCS, http://hps.elte.hu/BSCS) and its Call for Students for 2006. # We have a modified deadline of *May 15, 2006*. # Enclosed pls find a NEW poster (for high res., visit Web site). # Application procedure as seen on the Web site. Courses and teachers in 2006 include: Cognitive Neuroscience Professor John Bickle, UC (USA) Dynamic Brain Modeling Professor Peter Erdi, KCollege (USA) Consciousness Professor Olga Markic, U Ljubljana (Slovenia) Phil. of Mind Professor Lilia Gurova, NBU (Bulgaria) Cognitive Psychology Professor Giselher Guttmann, U Vienna (Austria) and also from Hungary: Foundations of Cogsci Professor George Kampis, ELTE Cognitive Linguistics Professor Laszlo Komlosi, PTE Phil. of Language Professor Gabor Forrai, ME Neural Networks Dr. Fulop Bazso, KFKI BSCS is a one-semester study abroad program run by the Hungarian Foundation in Cognitive Science (www.makog.hu). We welcome US and international students. Fellowships available in proven need. Send all inquiries to jhegedus at kzoo.edu (US Coordinator) or to George Kampis General Director gk at hps.elte.hu http://hps.elte.hu/~kampis From d.cornford at aston.ac.uk Mon Mar 6 04:24:21 2006 From: d.cornford at aston.ac.uk (Dan Cornford) Date: Mon, 06 Mar 2006 09:24:21 +0000 Subject: Connectionists: Research Jobs: Postdoc and PhD's in variational Bayesian inference for large dynamic models Message-ID: <440BFFC5.5090000@aston.ac.uk> POSTDOC: 3 years, 5 months We are looking for an outstanding postdoctoral research fellow to work on the VISDEM project, a collaboration between Aston, Southampton, Surrey Universities and the Met Office. The VISDEM project will look at the creation of novel frameworks for data assimilation (combining partial differential euqation based model with observations, i.e. better Kalman filtering / smoothing for non-linear systems) and will extend recently developed methods from statistical physics and machine learning to large stochastic dynamic systems. Working with Dr Dan Cornford, and a project student at Aston, you will take the theoretical developments from the Southampton team, led by Professor Manfred Opper and Professor John Shaw-Taylor, and apply these to a range of realistic stochastic dynamic models which have similar properties to real atmospheric models. In particular you will assist in creating a novel variational Bayesian approach to inference within realistic stochastic dynamic models. You will develop novel computational methods for space-time Gaussian processes, and also apply these to real systems, including the case with state dependent (multiplicative) model error. You will also work on the development of the hyper-parameter estimation for unknowns such as the variance of the forcing noise that arises from model error. The project is ambitious and exciting; we have a strong team and are looking for an experienced and highly motivated researcher to take the project forward. Applicants should have excellent mathematical and computational skills and be able to communicate effectively. A background in theoretical physics, mathematics, machine learning or equivalent is required. The post holder is expected to start on or before the 1 August 2006. The post is fixed term for 3 years 5 months. A little more information can be found on the rather temporary: http://www.ncrg.aston.ac.uk/~cornfosd/VISDEM/ web page, but for detailed information on the project please email me at d.cornford at aston.ac.uk Application forms etc can be found at: http://www.aston.ac.uk/staff/hr/recruitment/academicresearch/R0637-advert.jsp PHD's: 3.5 years, one at enhanced stipend. There are also a range of funded PhD studentships available within the NCRG at Aston, including a studentship on the VISDEM project which will be looking at the evaluation of the variational Bayesian methods in comparison with state of the art approaches to data assimilation in large stochastic dynamic models. A related MUCM (Managing Uncertainty in Complex Models) PhD studentship is also available on an enhanced stipend, which will look at issues of dimension reduction in large complex models, particularly focussing on the input dimension. Details of the PhD studentships can be found at: http://www.ncrg.aston.ac.uk/studentships/ Any questions feel free to email me, cheers Dan -- Dr Dan Cornford tel: +44 (0)121 204 3451 Lecturer in Computer Science email: d.cornford at aston.ac.uk NCRG, Aston University Birmigham B4 7ET, UK From tom.ziemke at his.se Mon Mar 6 08:24:18 2006 From: tom.ziemke at his.se (Tom Ziemke) Date: Mon, 06 Mar 2006 14:24:18 +0100 Subject: Connectionists: Two postdoc positions in cognitive/emotional robotics Message-ID: <440C3802.5020001@his.se> Applications are invited for two postdoc positions in cognitive/ emotional robotics at the University of Skovde, Sweden. These positions are part of a four-year European research project on bio-inspired cognitive/emotional robotics (www.his.se/icea, Jan 2006 - Dec 2009). The primary aim of the ICEA project is to develop a cognitive systems architecture integrating cognitive, emotional and bioregulatory (self-maintenance) mechanisms, based on the architecture and physiology of the mammalian brain. The two postdoc positions are focused on developing robot/neural net models of (1) the role of anticipation, representation and emotion in agent-environment interaction, (2) the interaction between cognitive and emotional mechanisms. The application deadlines are March 20 and April 18, respectively. For further information and detailed application instructions see: * position 1 (deadline March 20): - http://www.career.edu/index.php?post_id=1081 - http://www.his.se/templates/vanligwebbsida1.aspx?id=24698 * position 2 (deadline April 18): - http://www.career.edu/index.php?post_id=1105 - http://www.his.se/templates/vanligwebbsida1.aspx?id=24811 Starting date (both cases): spring/summer 2006 (as soon as possible). Informal inquiries can be directed to Tom Ziemke (tom.ziemke at his.se). From ken at neurotheory.columbia.edu Mon Mar 6 13:53:04 2006 From: ken at neurotheory.columbia.edu (Ken Miller) Date: Mon, 6 Mar 2006 13:53:04 -0500 Subject: Connectionists: Theoretical Neuroscience Faculty Recruitment, Columbia University Message-ID: <17420.34064.73173.682828@neurotheory.columbia.edu> Theoretical Neuroscience Faculty Recruitment The Center for Theoretical Neuroscience at Columbia University (http://www.neurotheory.columbia.edu) is recruiting for a faculty position in theoretical and computational neuroscience. Candidates who apply mathematical analysis and computer simulation to topics in neuroscience at levels ranging from cellular to systems and cognitive are urged to apply. We encourage applications for a tenure-track Assistant Professor position, but will also consider applications from more senior investigators for tenured positions. The Center for Theoretical Neuroscience is a highly interactive group of faculty (4 full-time and 1 part-time, at this point), postdoctoral researchers and graduate students who also interact extensively with experimentalists within Columbia's well-known program in neurobiology and behavior as well as with members of the scientific departments at the Morningside Heights campus. These interactions will be augmented in the upcoming years by the new Columbia Neuroscience Initiative, which is hiring a significant number of new faculty in the area of circuit-level neuroscience. Applications for this position are requested by March 31, 2006. A CV, cover letter including statement of interests, and three letters of reference under separate cover should be emailed to Andrew Fink, andrew at neurotheory.columbia.edu. In addition, please mail a hard copy of these documents to: Theoretical Neuroscience Search c/o: Andrew Fink Columbia University College of Physicians and Surgeons Kolb Research Annex 1051 Riverside Drive New York, NY 10032-2695 Columbia University takes affirmative action to ensure equal opportunity. From casutton at cs.umass.edu Tue Mar 7 20:45:05 2006 From: casutton at cs.umass.edu (Charles Sutton) Date: Tue, 7 Mar 2006 20:45:05 -0500 Subject: Connectionists: Announcing new tutorial on conditional random fields Message-ID: Andrew McCallum and I have written a new tutorial on conditional random fields: An Introduction to Conditional Random Fields for Relational Learning. Charles Sutton and Andrew McCallum. In Introduction to Statistical Relational Learning. Edited by Lise Getoor and Ben Taskar. To appear. http://www.cs.umass.edu/~casutton/publications/crf-tutorial.pdf It describes linear-chain CRFs, CRFs over general graphs, learning with latent variables, and many implementation concerns that arise when applying CRFs in practice. It also presents a case study of applying a loopy CRF to a practical natural language problem. Best wishes, Charles From terry at salk.edu Sun Mar 5 22:45:57 2006 From: terry at salk.edu (Terry Sejnowski) Date: Sun, 05 Mar 2006 19:45:57 -0800 Subject: Connectionists: NETtalk tape Message-ID: In response to many requests for a NETtalk demonstration tape for teaching, there is an MP3 file of NETalk for download at: http://www.cnl.salk.edu/ParallelNetsPronounce/index.php PDF files for the NETtalk paper and all of my publications are also available at: http://papers.cnl.salk.edu/ These include: Ackley, D. H.; Hinton, G. E.; Sejnowski, T. J.; A Learning Algorithm for Boltzmann Machines, Cognitive Science, 9, 147-169, 1985 Steriade, M.; McCormick, D. A.; Sejnowski, T. J.; Thalamocortical Oscillations in the Sleeping and Aroused Brain, Science, 262, 679-685, 1993 Bell, A. J.; Sejnowski, T. J.; An Information-Maximization Approach to Blind Separation and Blind Deconvolution, Neural Computation, 7, 1129-1159, 1995 Churchland, P. S.; Ramachandran, V. S.; Sejnowski, T. J.; A Critique of Pure Vision Koch, C.; Davis, J.; (Eds.), In: Large-Scale Neuronal Theories of the Brain, Cambridge, MA: MIT Press, 23-60, 1994 Mainen, Z. F.; Sejnowski, T. J.; Reliability of Spike Timing in Neocortical Neurons, Science, 268, 1503-1506, 1995 Montague, P. R.; Dayan, P.; Sejnowski, T. J.; A Framework for Mesencephalic Dopamine Systems Based on Predictive Hebbian Learning, Journal of Neuroscience, 16(5), 1936-1947, 1996 Sejnowski, T. J.; Destexhe, A.; Why Do We Sleep?, Brain Research, 886 (1-2) 208-223, 2000 Salinas, E.; Sejnowski, T. J.; Correlated Neuronal Activity and the Flow of Neural Information, Nature Reviews Neuroscience, 2, 539-550, 2001 Laughlin, S. B.; Sejnowski, T. J.; Communication in Neuronal Networks, Science, 301, 1870-1874, 2003 Coggan, J. S.; Bartol, T. M. Jr.; Esquenazi, E. I.; Stiles, J. R.; Lamont, S.; Martone, M. E.; Berg, D. K.; Ellisman, M. H.; Sejnowski, T. J.; Evidence for Ectopic Neurotransmission at a Neuronal Synapse, Science, 39, 446-451, 2005 Terry ----- From andreas at cs.ntua.gr Wed Mar 8 07:42:10 2006 From: andreas at cs.ntua.gr (andreas) Date: Wed, 8 Mar 2006 14:42:10 +0200 Subject: Connectionists: ICANN 2006 Call for papers and deadline extension Message-ID: <200603081242.k28CgDfU011583@theseas.softlab.ece.ntua.gr> Call for Papers International Conference on Artificial Neural Networks (ICANN 06) *************** The deadline for submission of papers (abstract + full paper) to regular sessions has been extended to 31 March 2006 *************** 10-14 September 2006 Holiday Inn Hotel, Athens, Greece ************Conference Framework************ The 16th International Conference on Artificial Neural Networks, ICANN 2006, will be held from September 10 to September 14, 2006, at the Holiday Inn Hotel, Athens Greece. ICANN is an annual conference organized by the European Neural Network Society in cooperation with the International Neural Network Society, Japanese Neural Network Society, and the IEEE Computational Intelligence Society, and is a premier European event in all topics related to neural networks. ICANN 2006 (www.icann2006.org) welcomes contributions on the theory, algorithms, applications and implementations in the following broad areas: ? Computational neuroscience; ? Connectionist cognitive science; ? Data analysis and pattern recognition; ? Graphical networks models, Bayesian networks; ? Hardware implementations and embedded systems; ? Neural and hybrid architectures and learning algorithms; ? Neural control, reinforcement learning and robotics applications; ? Neuroinformatics; ? Neural dynamics and complex systems; ? Real world applications; ? Robotics, control, planning; ? Signal and time series processing; ? Self-organization; ? Vision and image processing; ? Web semantics; ? Intelligent Multimedia and the Semantic Web. Ideas and nominations for interesting tutorials, special sessions, workshops and experts willing to organize various session tracks are called for. Most active experts will be included in the scientific committee of the conference. Proceedings of ICANN will be published in Springer's "Lecture Notes in Computer Science". Paper length is restricted to a maximum of 10 pages, including figures. ************Deadlines and Conference dates************ 06.01 Submission page opens 31.03 End of submission of papers (abstract+full paper) to regular sessions 31.03 End of submission of papers to special sessions 30.04 Acceptance/rejection notification 15.06 Deadline for camera ready papers 01.07 Deadline for early registration 10.09 Tutorials - first day of the conference 11-13.09 Main part of the conference 14.09 Workshops For further information and/or contacts, send inquiries to Prof. Stefanos Kollias (stefanos at cs.ntua.gr) Prof Andreas Stafylopatis (andreas at cs.ntua.gr) School of Electrical & Computer Engineering National Technical University of Athens 9, Heroon Polytechniou str., 157 80 Zografou, Athens, Greece. General Chair Stefanos Kollias, National Technical University of Athens (NTUA), Greece Co-Chair Andreas Stafylopatis, NTUA, Greece Program Chair Wlodzislaw Duch, Torum, PL & Singapore; ENNS President-elect Erkki Oja, Helsinki, FI; ENNS President Honorary Chair John G. Taylor, Kings College, London, UK; ENNS Past President ************International Program Committee************ ? Peter Andras, U. Newcastle, UK ? Panos Antsaklis, U. N. Dame, USA ? Nikolaos Bourbakis, Wright State Univ., USA ? Peter Erdi, Univ. Budapest, HU & Kalamazoo ? Georg Dorffner, Univ. Wien, AT ? Christophe Garcia, France T?l?com ? Erol Gelenbe, Imperial College London, UK ? Stan Gielen, Univ. Nijmegen, NL ? Nikola Kasabov, Kedri, AUT, NZ ? Janusz Kacprzyk, Warsaw, PL ? Okyay Kaynak, Bogazici Univ., TR ? Chris Koutsougeras, Tulane University, USA ? Thomas Martinetz, Luebeck, DE ? Evangelia Micheli-Tzanakou, Rutgers University, USA ? Lars Niklasson, Sk?vde SE ? Marios Polycarpou, Univ. of Cyprus ? Demetris Psaltis, Caltech, USA ? Olli Simula, Espoo, FI ? Alessandro Sperduti, U.Padova, IT ? Lefteris Tsoukalas, Purdue Uni, USA ? Michel Verleysen, Louvain-la-Neuve, BE ? Alessandro Villa, U. Grenoble, FR ************Local Organizing Committee************ ? Yannis Avrithis, NTUA ? Christos Douligeris, Piraeus Univ ? George Dounias, Aegean Univ ? Kostas Karpouzis, ICCS-NTUA ? Aris Likas, Univ. of Ioannina ? Kostas Margaritis, Univ. Macedonia ? Basil Mertzios,DUTH and ATIT ? Stavros Perantonis, NCSR, Athens ? Yannis Pitas, AUTH, Salonica ? Costas Pattichis, Univ. of Cyprus ? Apostolos Paul Refenes, Athens University Economics & Business ? Christos Schizas, Univ. of Cyprus ? Thanos Skodras, Univ. of Patras ? Kostas Spyropoulos, NCSR, Athens ? Giorgos Stamou, ICCS-NTUA ? Sergios Theodoridis, UoA ? Spyros Tzafestas, NTUA ? Mihalis Zervakis, TUC, Crete From netta at comp.leeds.ac.uk Fri Mar 10 05:26:38 2006 From: netta at comp.leeds.ac.uk (N Cohen) Date: Fri, 10 Mar 2006 10:26:38 +0000 (GMT) Subject: Connectionists: Junion/Senior Faculty Recruitment: University of Leeds Message-ID: Fellow connectionists, Lecturer/Senior Lecturer/Reader in Biosystems University of Leeds, UK Applications are invited for a faculty position at the School of Computing, University of Leeds, in the Biosystems area. We are particularly keen to expand and enhance activity in computational neuroscience, neurocomputation and/or bio-robotics. The successful candidate will join a vibrant Biosystems group led by Dr. Netta Cohen. The Biosystems Group in the School of Computing comprises 4 members of academic staff and 8 postgraduate students. Our research spans theoretical and computational neuroscience, invertebrate neurobiology, foundations and applications of bio-inspired computing, evolutionary dynamics, swarm intelligence, and a range of topics spanning complex adaptive behaviour in ecology, evolution, gene networks, and more. Further details on the Group's research activities can be found at http://www.comp.leeds.ac.uk/biosystems/ Full details of the post can be found at http://www.comp.leeds.ac.uk/vacancies/20060320lecturer.shtml and by following the link to "Further particulars". Closing Date: 20th March 2006 From jose.r.dorronsoro at iic.uam.es Fri Mar 10 09:51:26 2006 From: jose.r.dorronsoro at iic.uam.es (Jose Dorronsoro) Date: Fri, 10 Mar 2006 15:51:26 +0100 Subject: Connectionists: CFP: Special Session on Advances in Neural Network Learning Methods, ICANN 2006 Message-ID: <7.0.0.16.0.20060310155106.01ce1290@iic.uam.es> Special Session on Advances in Neural Network Learning Methods ICANN 2006: 16th International Conference on Artificial Neural Networks 10-14 September 2006 Holiday Inn Athens, Greece http://icann2006.org/ Call for Papers While there are several well established NN construction procedures, there is a constant research work on new ways to improve on them or to apply to NN training new procedures coming from other areas of machine learning. Moreover, there is a clear awareness among NN practitioners of the advantages that alternative procedures or paradigms may bring and a willingness to apply those most promising on new classification or regression problems arising in diverse areas, particularly those involving special difficulties, such as large sample dimension or data noise. The aim of this Special Session is to provide a wide look on the latest applications to NN training of recent advancements in machine learning. As possible topics of the session we mention: * Latest improvements on established NN learning methods. * Advances in ensemble NN methods, such as boosting, bagging and their variants. * Dimension expanding procedures, such as kernel methods. * Evolutionary computation based training. * New training paradigms from neurobiological computation. Submission procedure: Papers are to be submitted through the ICANN 2006 submission webpage, where Instructions for Authors are also available. When submitting these, please mention your interest in this special session and send also the abstract to one of the Special Session Organizers. SPECIAL SESSION ORGANIZERS Jos? Dorronsoro Departamento de Ingenier?a Inform?tica and Instituto de Ingenier?a del Conocimiento Escuela Polit?cnica Superior Universidad Aut?noma de Madrid Madrid, Spain jose.dorronsoro at uam.es Pedro Isasi Departamento de Inform?tica Escuela Polit?cnica Superior Universidad Carlos III de Madrid Madrid, Spain isasi at ia.uc3m.es Important dates: 30 March: End of submission of papers to special sessions 30 April: Acceptance/rejection notification 15 June: Deadline for camera ready papers Jos? R. Dorronsoro Escuela Polit?cnica Superior Universidad Aut?noma de Madrid 28049 Madrid Tel: 34 91 497 2329, 34 91 497 2240 Fax: 34 91 497 2334 From gwestermann at brookes.ac.uk Fri Mar 10 11:35:38 2006 From: gwestermann at brookes.ac.uk (Gert Westermann) Date: Fri, 10 Mar 2006 16:35:38 +0000 Subject: Connectionists: PhD studentship Message-ID: <4411AADA.9050400@brookes.ac.uk> Dear Connectionists, Please see below for an advert for a PhD studentship in our department. One possible area for the studentship is connectionist modelling of cognitive developmental processes. For informal enquiries regarding this area please email Gert Westermann at gwestermann at brookes.ac.uk. The closing date for applications is 19 April 2006. ---------------------------------------------------------------------- Oxford Brookes University Department of Psychology ESRC Psychology Research Studentship Applications are invited for an ESRC quota research Studentship (fees + maintenance grant), available in an area of Psychology that reinforces the Department?s research activities. As a successful applicant, you will join a well-resourced, supportive and research-active department, becoming actively involved in international quality research. Organised around Developmental Psychology and Cognitive Parapsychology's key areas of research expertise include: ? Cognitive development (home and school numeracy, development of writing skills, connectionist modelling of development, deaf children?s development) ? Cultural identity development and immigration; Learning and development in multicultural communities ? Developmental disorders in children and adults (autism, sleeping, motor coordination, dyslexia) ? Cognitive neuropsychology (bipolar disorder, visual perception in normal and clinical populations, connectionist modelling of normal and impaired cognitive processing). The Studentship will be funded for either a '+3' or ?1+3' scheme. The 1+3 award combines a Masters of Research (MRes) in Psychology followed by an MPhil/PhD. See http://ssl.brookes.ac.uk/postgraduates/resmethods-psychology-mres.htm for details of the Oxford Brookes MRes in Psychology. The Department welcomes applications from those who have (or expect to achieve in 2006) a degree (of at least 2:1, or academic equivalent) in Psychology, Education or a related cognate discipline. Applicants who have already completed a Masters programme that is ESRC recognised may alternatively apply for the ?+3' mode (to support an MPhil/PhD research post). The award is available to UK/EU students and will cover fees and a maintenance grant of ?12,300 per year. EU students will receive fees only (unless they have been resident in the UK for at least 3 years). Further guidance is available on the ESRC web site at: http://www.esrcsocietytoday.ac.uk/ESRCInfoCentre/opportunities/postgraduate/fundingopportunities/ The closing date for applications is Wednesday 19 April 2006. Interviews will be held on Friday 26 April 2006. Start date October 2006. To request an application pack, please contact Jennie Cripps, Research Support Officer, e-mail jcripps at brookes.ac.uk, tel 01865 48 3763. Further details about the Department?s research can be found at: http://www.brookes.ac.uk/schools/social/psych/research.html -- ===================================================================== Dr. Gert Westermann gwestermann at brookes.ac.uk Department of Psychology, Oxford Brookes University, Oxford OX3 0BP Tel +44 (0)1865 271 400 Fax: +44 (0)1865 48 38 87 http://www.cbcd.bbk.ac.uk/people/gert/ ===================================================================== From renaud.jolivet at epfl.ch Sat Mar 11 04:00:20 2006 From: renaud.jolivet at epfl.ch (Renaud Jolivet) Date: Sat, 11 Mar 2006 10:00:20 +0100 Subject: Connectionists: EPFL School of life sciences summer research program Message-ID: <441291A4.9030401@epfl.ch> From ahu at cs.stir.ac.uk Sun Mar 12 10:55:48 2006 From: ahu at cs.stir.ac.uk (Dr. Amir Hussain) Date: Sun, 12 Mar 2006 15:55:48 -0000 Subject: Connectionists: Final CFP: Extended Paper Submission Deadline: 25 March 2006 for the 2nd International Conference on BICS 2006, Lesvos, Greece, 10-14 Oct 2006 Message-ID: <00a001c645ed$6e4047f0$3bea0954@hec.gov> Please forward to any relevant people or lists. Thank you in advance! -- Please see the website for more details on the Conference CFP: http://www.icsc-naiso.org/conferences/bics2006/bics06-cfp.html (Click on "BICS 2006" on the left of the page for more info). Note: Due to numerous requests from authors, the paper submission deadline has been extended till: 25 March 2006 - for other important dates, please see: http://www.icsc-naiso.org/conferences/bics2006/bics06_dates.html For submitting a draft paper (4-7 pages) for peer review by the IPC, please see: http://www.x-cd.com/bics06/abstract.cfm The conference features an excellent line-up of invited plenary speakers, including: Shun-ichi Amari, RIKEN Brain Science Institute, Japan Holk Cruse, University of Bielefeld, Germany Pentti Haikonen, Nokia Research Center, Finland Timothy K Horiuchi, University of Maryland, USA John Taylor, Kings College, London, U.K. Steve Potter, Georgia Tech, USA Jacek M Zurada, University of Louisville, USA Marios Polycarpou, University of Cyprus, Cyprus And others to be confirmed. We hope to see you in the Greek Islands in October for a great conference, and we look forward to receiving your submission(s). Amir Hussain On behalf of the BICS 2006 Organizing Committee (BICS 2006 General Chairman: Igor Alexander, Imperial College, London, UK) -- Dr. Amir Hussain Chair IEEE UK & RI Industry Applications Society Chapter Department of Computing Science & Mathematics University of Stirling, Scotland, UK Tel / Fax: +44 (0)1786 467437 / 464551 Email: ahu at cs.stir.ac.uk http://www.cs.stir.ac.uk/~ahu/ From marcilio at dimap.ufrn.br Mon Mar 13 06:35:34 2006 From: marcilio at dimap.ufrn.br (Marcilio Carlos P. de Souto) Date: Mon, 13 Mar 2006 08:35:34 -0300 Subject: Connectionists: Fw: [Sbc-l] 2nd Call for paper SBRN 2006 In-Reply-To: <20060310122258.M85005@dimap.ufrn.br> References: <20060310122258.M85005@dimap.ufrn.br> Message-ID: <20060313113523.M53111@dimap.ufrn.br> --------------------------- Apologies for cross-posting --------------------------- 2nd CALL FOR PAPERS ********************************************************************** SBRN'2006 - IX BRAZILIAN SYMPOSIUM ON NEURAL NETWORKS Ribeirao Preto, October 23-26, 2006 http://www.icmc.usp.br/iarn2006/sbrn.php ********************************************************************** The biannual Brazilian Symposium on Artificial Neural Networks (SBRN) - of which this is the 9th event - is a forum dedicated to Neural Networks (NNs) and other models of computational intelligence. The emphasis of the Symposium will be on original theories and novel applications of these computational models. The Symposium welcomes paper submissions from researchers, practitioners, and students worldwide. SBRN'2006 is sponsored by the Brazilian Computer Society (SBC) and co- sponsored by SIG/INNS/Brazil Special Interest Group of the International Neural Networks Society in Brazil. It will take place October 23-26, and will be held in Ribeirao Preto. Ribeirao preto is a dynamic and sunny city, about 300 km from the city of S?o Paulo. Sao Paulo is the main gateway to Brazil with regular flights to all major cities in Brazil as well as Europe, United states, Asia, among others. SBRN'2006 will be held together with the X Ibero-American Artificial Intelligence Conference (IBERAMIA) and XVIII Brazilian Symposium on Artificial Intelligence (SBIA). All Symposia will feature keynote speeches and tutorials by world-leading researchers. SBIA has its main focus on symbolic AI. Crossfertilization of these fields will be strongly encouraged. The deadline for submissions is March 26, 2006. More details on paper submission and conference registration will be coming soon. Sponsored by the Brazilian Computer Society (SBC) Co-Sponsored by SIG/INNS/Brazil Special Interest Group of the International Neural Networks Society in Brazil Organized by the University of S?o Paulo (USP), Brazil Submissions: We welcome papers describing original works on (but it is not limited to): 1. Applications: finances, data mining, neurocontrol, time series analysis, bioinformatics; 2. Architectures: cellular NNs, hardware and software implementations, new models, weightless models; 3. Cognitive Sciences: adaptive behavior, natural language, mental processes; 4. Computational Intelligence: evolutionary systems, fuzzy systems, hybrid systems; 5. Learning: algorithms, evolutionary and fuzzy techniques, reinforcement learning; 6. Neurobiological Systems: bio-inspired systems, biologically plausible networks, vision; 7. Neuro-control: robotics, dynamic systems, adaptive control; 8. Neuro-symbolic processing: hybrid approaches, logical inference, rule extraction, structured knowledge; 9. Pattern Recognition: signal processing, artificial/computational vision; 10. Theory: radial basis functions, Bayesian systems, function approximation, computability, learnability, computational complexity. Submission Guidelines: Paper registration and submissions to SBRN 2006 will be handled using the JEMS system, which will be open for registration and submission from February 14th, 2006, 00:00 BRST. The address is: https://submissoes.sbc.org.br/home.cgi?c=280 Submission is a three-step process. In a first step authors are required to register as new authors with JEMS (note that only 1 registration is needed if you submit more than 1 paper). After registration as author the login data will be sent to the specified email address. This data can be used to access the system. In a second step authors have to register their paper (click the submit paper button in JEMS). There are two different tracks to submit a paper. In the first one (SBRN 2006), the paper is only submitted to SBRN. In the second one (SBRN or WCI), a paper which is not accepted to SBRN is automatically submitted to the Workshop on Computational Intelligence (WCI). Once the chosen track is selected, the authors are asked in this step to specify the name of the authors, the paper title, its topics and the paper category (regular, student): these categories are exactly the same, except for the fact that the first author is a student or not. The system will then assign a tracking ID to each submission which is sent to the contact author. The deadline for paper registration is March 26th., 23:55 BRST. The third step consists on uploading the paper. This step can be done jointly with the registering step. For those authors who prefer to upload their papers after registering, the tracking ID must be used. The deadline for paper uploading is March 26th, 23:55 BRST. We will *only* accept files either in pdf or in ps format. Please do not try to upload doc or rtf files, they will be rejected by the system. Note also that contrary to earlier years we only accept electronic submissions through JEMS. Please do not send papers directly to the PC-chairs. Submissions sent by regular courrier or by email will *not* be considered. Style guide Papers must be written in English and should be no longer than 6 pages (style of the IEEE Computer Society - http://www.computer.org/cspress/instruct.htm), including all tables, figures, and references. Formatting instructions, LaTeX macros and MSWord templates are available at . Submissions violating the formatting guidelines will be *excluded* from the reviewing process. Deadlines: Submission: 26 March 2006 Acceptance: 24 May 2006 Camera-ready: 12 June 2006 General Chair: Antonio Carlos Roque da Silva Filho (FFCLRP/USP Ribeir?o Preto) antonior at neuron.ffclrp.usp.br Program Chair: Anne Mag?ly de Paula Canuto (UFRN/DIMAp, Brazil) anne at dimap.ufrn.br Steering Committee Allan K. Barros (Universidade Federal do Maranh?o) Alu?zio Ara?jo (Universidade Federal de Pernambuco) Gerson Zaverucha (Universidade Federal do Rio de Janeiro) Teresa B. Ludermir (Universidade Federal de Pernambuco) Program Committee Adriao D. Doria Neto (UFRN, Brazil) Alejandro Ceccatto (Univ. of Rosario, Argentina) Allan K. Barros (UFMA, Brazil) Aluizio Araujo (UFPE, Brazil) Amanda Sharkey (Univ. of Shefield, UK) Andre C. P. L. F. de Carvalho (USP-S?o Carlos, Brazil) Anne Magaly de Paula Canuto (UFRN, Brazil) Antonio C. R. da Silva Filho (USP, Brazil) Antonio de P. Braga (UFMG, Brazil) Artur Garcez (City University, UK) Carlos H. C. Ribeiro (ITA, Brazil) Edson Costa B.C. Filho (UFPE, Brazil) Felipe Franca (UFRJ, Brazil) Fernando A. Gomide (UNICAMP, Brazil) Gerson Zaverucha (UFRJ, Brazil) Guilherme A. Barreto (UFC, Brazil) Harold Szu (George Washington Univ., USA) Herman M. Gomes (UFCG, Brazil) Igor Aleksander (Imperial College, UK) Jose Principe (Univ. of Florida, USA) Ludmila Kuncheva (University of Wales, UK) Marcilio C. P. de Souto (UFRN, Brazil) Marios Polycarpou (University of Cyprus, Cyprus) Marley M. B. R. Vellasco (PUC ? RJ, Brazil) Michael Fairhurst (Univ. of Kent, UK) Nikola Kasabov (University of Otago, New Zeland) Phillipe De Wilde (Heriot Watt University, UK) Teresa B. Ludermir (UFPE, Brazil) Zhao Liang (USP, Brazil) _______________________________________________ Sbc-l mailing list Sbc-l at inf.ufrgs.br https://listas.inf.ufrgs.br/mailman/listinfo/sbc-l ------- End of Forwarded Message ------- -- Open WebMail Project (http://openwebmail.org) Debian Project (http://www.debian.org) From lendasse at james.hut.fi Sun Mar 12 15:42:25 2006 From: lendasse at james.hut.fi (Amaury Lendasse) Date: Sun, 12 Mar 2006 22:42:25 +0200 Subject: Connectionists: Call for Papers: ICANN 2006 Special Session Message-ID: <20060312204203.9E9966C069@james.hut.fi> Call for Papers: ICANN 2006 Special Session: Title: Feature selection and dimension reduction for regression Abstract: Nowadays, many machine learning problems involved the use of a large number of features. This might be the case, for example, in DNA and biomedical data analysis, in image processing, financial data mining, chemometrics, etc. In other cases, the number of features may be smaller, but of the same order of magnitude as the number of samples. In both cases, regression tasks are faced to the curse of dimensionality: overfitting easily appears, and in some cases the regression problem can become ill-posed (or not identifiable). The challenge is then to reduce the number of features, in order to improve the regression efficiency. Interpretability is often a major concern too, as a large number of features usually prevents any understanding of the underlying relationship. Feature selection and dimension reduction includes two different ways of reducing the number inputs of the regression model. First, inputs can be selected among the original features; this is usually referred to as feature selection or input selection. Second, inputs can be built from the original features, by combining them in a linear or nonlinear way; this leads to dimension reduction (sometimes referred to as variable selection). The goal of feature selection and dimension reduction is twofold. First, reducing the number of input variables fights the curse of dimensionality, giving the possibility of increasing the regression generalization performances. Second, a reduced set of variables is of utmost importance in real applications as it allows an easier interpretation of the relationship between features and outputs. The aim of this session is to present original developments in feature selection and dimension reduction. Contributions are invited in the following areas: - new algorithms and methods; - comparisons between techniques, including the assessment of the compromise between generalization properties and computational load; -applicability of the proposed methods in real-world problems, including small sample and high dimension constraints. It is suggested (but not mandatory) to illustrate and compare the proposed methods by using one of or both the following regression datasets: Housing (Boston), available from the UCI Machine Learning Repository (http://www.ics.uci.edu/~mlearn/MLSummary.html), and Orange juice spectra, available from the UCL Machine Learning Group website (http://www.ucl.ac.be/mlg/index.php?page=DataBases). Practical details: - ICANN?06 website: http://icann2006.org/chapter1/index.html - 30 Mars: End of submission of papers to special sessions - Proceedings of ICANN will be published in Springer's "Lecture Notes in Computer Science" series. Paper length is restricted to a maximum of 10 pages, including figures. Organized by: Amaury Lendasse, Helsinki University of Technology, Adaptive Informatics Research Centre, Finland. Michel Verleysen, Universit? catholique de Louvain, Machine Learning group, Belgium. From giovanni.pezzulo at istc.cnr.it Mon Mar 13 10:54:14 2006 From: giovanni.pezzulo at istc.cnr.it (Giovanni Pezzulo) Date: Mon, 13 Mar 2006 16:54:14 +0100 Subject: Connectionists: CFP: ABiALS Workshop 2006 Message-ID: <01f301c646b6$60b16af0$4d419296@GIOVANNI> (We apologize if you receive more than one copy of this message) ########################################################################### 1st C A L L F O R P A P E R S ABiALS Workshop 2006 Anticipatory Behavior in Adaptive Learning Systems ########################################################################### SEPTEMBER 30, 2006 ROME, ITALY http://www-illigal.ge.uiuc.edu/ABiALS to be held during the ninth international conference on the SIMULATION of ADAPTIVE BEHAVIOR (SAB 2006) http://www.sab06.org ABiALS is an interdisciplinary workshop investigating the influence of anticipations on behavior and learning. ABiALS is designed to help investigate how anticipations can influence, initiate, and guide behavior and learning as well as how anticipatory influences can be implemented in an adaptive learning system. Submission deadline: Wednesday, 15. JUNE 2006 Anticipatory behavior is a mechanism, or a behavior, that does not only depend on the past and present but also on predictions, expectations, or beliefs about the future. ___________________________________________________________________________ OBJECTIVES: After two previous successful gatherings during SAB 2002, resulting in the Springer-Verlag LNCS 2684 State-of-the-Art survey named after the workshop, and SAB2004, ABiALS 2006 will continue to explore anticipatory influences on behavior and learning. The aim of ABiALS 2006 is to join researchers in their understanding and development of anticipatory mechanisms in adaptive behavior. It is aimed for an interdisciplinary gathering that combines the expertise of researchers from various disciplines including neuroscience, cognitive psychology, machine learning, artificial intelligence, control, and vision research to shed further light on the concept of anticipation. Essentially, it will be discussed how knowledge about the future can influence actual behavioral mechanisms, including influences on attention, action decision making and control, as well as (behavioral and model) learning. ___________________________________________________________________________ KEY INTERESTS: Anticipatory mechanisms for model learning ? Adaptive, predictive model learning ? Adaptive, predictive filtering ? Anticipatory attention ? Surprise for model learning ? Hierarchical, predictive model architectures ? Timing in predictive models Model-predictive, adaptive control architectures ? Inverse models and goal-oriented control ? Hierarchical structures in adaptive, model-predictive control ? Surprise in control ? Delayed feedback, forward models, and multiply timed control Anticipatory, adaptive systems / agents ? Integration of anticipatory adaptive processes in adaptive systems ? Anticipatory decision making ? Anticipatory behavior in multiagent systems ? Interactions of anticipations, motivations, and emotions ? Anticipations in BDI architectures ? Curiosity and epistemic actions Distinctions of anticipatory mechanisms: ? Benefits and drawbacks of different anticipatory mechanisms ? Distinction to reactive mechanisms ? Emergence of anticipatory mechanisms in evolution ? Anticipatory mechanisms in constructivist, interactive frameworks Anticipatory mechanisms in animals and humans ? Behavioral and cognitive anticipatory mechanisms in animals and humans ? Anticipatory mechanisms in neuroscience ? Anticipatory mechanisms in cognitive/experimental psychology ___________________________________________________________________________ SUBMISSION: Submissions for the workshop should address one of the interests listed above. The workshop is not limited to one particular type of anticipatory learning system or a particular representation of anticipations. The workshop will be generally targeted towards short presentations and extended discussions. The advantages and disadvantages of different anticipatory mechanisms and representations will be discussed in detail. Several discussion sessions on the topics in question will put the presentations in a broader perspective. Papers should be submitted electronically to one of the organizers via email in pdf or ps format. Electronic submission is strongly encouraged. If you cannot submit your contribution electronically, please contact one of the organizers. Submitted papers should have a maximal length of ten pages in 10pt, one-column format. Please use the LNCS Springer-Verlag style as specified at http://www.springeronline.com/comp/lncs/authors.html (LATEX utilities can be found in the file llncs2e.zip). Papers will be reviewed for acceptance by the program committee and the organizers. Submission deadline is the 15th of JUNE 2006. Dependent on the quality and number of contributions we will publish Post Workshop proceedings as either a Springer LNAI volume or a special issue of a journal. For more information please refer to http://www-illigal.ge.uiuc.edu/ABiALS/ ___________________________________________________________________________ ___________________________________________________________________________ IMPORTANT DATES: 15. June 2006: Deadline for Submissions 30. September 2006: ABiALS Workshop 2006 ___________________________________________________________________________ PROGRAM COMMITTEE: Christian Balkenius Cognitive Science, Lund University, Sweden Edoardo Datteri Department of Philosophy, University of Pisa, Italy Pier Luca Lanzi Dipartimento di Elettronica e Informazione, Politecnico di Milano, Italy Ralf Moeller Computer Engineering Group, Faculty of Technology, Bielefeld University, Germany Tony Prescott Department of Psychology, The University of Sheffield, UK Jesse Reichler Department of Computer Science, University of Illinois at Urbana-Champaign, IL Alexander Riegler CLEA, Vrije Universiteit Brussels, Belgium Deb Roy Cognitive Machines Group, MIT Media Laboratory, Cambridge, MA Samarth Swarup Department of Computer Science, University of Illinois at Urbana-Champaign, IL Stewart W. Wilson Prediction Dynamics, Concord, MA ___________________________________________________________________________ ORGANIZERS: Martin V. Butz, Department of Cognitive Psychology University of Wuerzburg, Germany butz at psychologie.uni-wuerzburg.de http://www-illigal.ge.uiuc.edu/~butz Olivier Sigaud AnimatLab, University Paris VI, Paris, France olivier.sigaud at lip6.fr http://animatlab.lip6.fr/Sigaud Gianluca Baldassarre Istituto di Scienze e Tecnologie della Cognizione Consiglio Nazionale delle Ricerche (ISTC-CNR) Roma, Italy gianluca.baldassarre at istc.cnr.it http://gral.istc.cnr.it/baldassarre/ Giovanni Pezzulo Istituto di Scienze e Tecnologie della Cognizione Consiglio Nazionale delle Ricerche (ISTC-CNR) Roma, Italy giovanni.pezzulo at istc.cnr.it http://www.istc.cnr.it/createhtml.php?nbr=1 From deneve at isc.cnrs.fr Wed Mar 15 18:16:20 2006 From: deneve at isc.cnrs.fr (Sophie Deneve) Date: Thu, 16 Mar 2006 00:16:20 +0100 Subject: Connectionists: (no subject) Message-ID: <5.1.1.6.0.20060316000843.0386f7a0@pop.isc.cnrs.fr> A "Ma?tre de conf?rence" position is available at the Ecole Normale Sup?rieure in Paris, France. The Ecole Normale Sup?rieure is one of the top school/research institution in France, forming elite students to multidisciplinary studies in the domain of (among others) physics, mathematics, and biology. This is permanent research position involving 145 hours of teaching per year. The candidate should have a background and good publications in the domain of computational/theoretical neuroscience. The research will be done in collaboration with the newly created Group of Neural Theory. Faculty includes Misha Tsodyks, Jean Pierre Nadal, Boris Gutkin, Sophie Deneve, and Rava Da Silveira. Candidates should contact AS SOON AS POSSIBLE Boris Gutkin (boris.gutkin at ens.fr) and Sophie Deneve (deneve at isc.cnrs.fr). Please attach a CV to your email. The applications are due on the 30th of March, and we should be contacted before the 26th. We apologize for the short delay. From andrew.coward at anu.edu.au Tue Mar 14 19:50:46 2006 From: andrew.coward at anu.edu.au (Andrew Coward) Date: Wed, 15 Mar 2006 00:50:46 -0000 Subject: Connectionists: Physiologically Realistic Cognitive Modelling: New Book Message-ID: (Apologies if you receive this announcement more than once) A recently published book, ?A System Architecture Approach to the Brain: from Neurons to Consciousness? (ISBN 1-59454-433-6), applies some developments in systems theory to demonstrate that detailed modelling of higher cognitive processes in terms of neurophysiology requires some very specific architectural approaches. The book demonstrates theoretical arguments that any learning system that is subject to a range of practical considerations will be constrained within a set of architectural bounds called the recommendation architecture. The theoretical arguments have been developed by analogy with the ways in which practical considerations constrain the architectures of extremely complex electronic control systems, although there is minimal direct resemblance between such architectures and those of learning systems. The practical considerations are (1) the need to perform a large number of behavioural features with relatively limited physical resources for information recording, information processing and internal information communication; (2) the need to add and modify features without side effects on other features; (3) the need to protect the many different meanings of information generated by one part of the system and utilized for different purposes by each of a number of other parts of the system; (4) the need to maintain the association between results obtained by different parts of the system from a set of system inputs arriving at the same time; (5) the need to limit the volume of information required to specify the system construction process; (6) the need to limit the complexity of the construction process; and (7) the need to recover from construction errors and subsequent physical failures or damage. The system theory demonstrates that if such needs are strong, there are some remarkably specific constraints on the system architecture. There are constraints on how functionality is separated into modules and components, on device information models, on the ways in which devices are organized and connected within and between modules and components, and on the ways in which information can be recorded and processed. One key constraint is a requirement for a separation between a clustering subsystem which defines and detects conditions within the information available to the system, and several competition subsystems which receive some of the conditions and interpret each condition as a recommendation in favour of a range of different behaviours, each with a different weight. These competition subsystems determine the current total recommendation weights of all behaviours across all current conditions and implement the most strongly recommended behaviour. Consequence feedback following a behaviour can set or change recommendation weights but cannot change condition definitions. Furthermore, once a condition has been defined in clustering, there are tight restrictions on subsequent changes. The limited ability to change condition definitions is one primary difference from traditional neural networks. The book describes the strong resemblances between the structures and processes predicted for a system within the recommendation architecture bounds and the physiological structures and processes of the mammal brain. The ways in which the recommendation architecture approach makes it possible to understand experimental results for a wide range of cognitive processes in terms of physiology are described. Electronic implementations of systems within the recommendation architecture bounds are described that confirm the resemblances with biological brains. L. Andrew Coward Research Fellow Department of Computer Science Australian National University Canberra ACT 0200 Australia andrew.coward at anu.edu.au tel +61 02 6125 5694 mob +62 0431 529 197 http://cs.anu.edu.au/~Andrew.Coward/ Book Website: http://www.novapublishers.com/catalog/product_info.php? cPath=23_128&products_id=2652 From retienne at jhu.edu Tue Mar 14 01:59:19 2006 From: retienne at jhu.edu (Ralph Etienne-Cummings) Date: Tue, 14 Mar 2006 01:59:19 -0500 Subject: Connectionists: Reminder: Neuromorphic Engineering Workshop 2006 In-Reply-To: <41F7C734.8060205@jhu.edu> References: <41F7C734.8060205@jhu.edu> Message-ID: <441669C7.5070609@jhu.edu> Reminder: Please forgive us if you get this announcement more than once: ======================================================================== Neuromorphic Engineering Workshop Call for Applications Sunday, June 25 - Saturday, July 15, 2006 Telluride, Colorado ------------------------------------------------------------------------------------------------------------ Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Ralph ETIENNE-CUMMINGS (Johns Hopkins University) Paul HASLER (Georgia Institute of Technology) Timmer HORIUCHI (University of Maryland) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Christof KOCH (California Institute of Technology)- Past Organization Board Member Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) Andre van SCHAIK(University of Sydney) ------------------------------------------------------------------------------------------------------------- We invite applications for a three week summer workshop that will be held in Telluride, Colorado from Sunday, June 25 to Saturday, July 15, 2006. The application deadline is Friday, March 24, and application instructions are described at the bottom of this document. The 2005 Workshop and Summer School on Neuromorphic Engineering is sponsored by the National Science Foundation, Institute of Neuromorphic Engineering, Wow Wee Toys, Airforce Research Office, Eglin Airforce Research Lab, Nova Sensors, Institute for NeuroInfomatics - ETHZ, Geogia Institute of Technology, University of Maryland - College Park, Johns Hopkins University, The Salk Institute, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology. Last year's workshop was an exciting event and a great success. We strongly encourage interested parties to browse through the previous workshop web pages at: http://ine-web.org/workshops/past-workshops GOALS: Carver Mead introduced the term "Neuromorphic Engineering" for a new field based on the design and fabrication of artificial neural systems, such as vision systems, head-eye systems, and roving robots, whose architecture and design principles are based on those of biological nervous systems. The goal of this workshop is to bring together young investigators and more established researchers from academia with their counterparts in industry and national laboratories, working on both neurobiological as well as engineering aspects of sensory systems and sensory-motor integration. The focus of the workshop will be on active participation, with demonstration systems and hands on experience for all participants. Neuromorphic engineering has a wide range of applications from nonlinear adaptive control of complex systems to the design of smart sensors. Many of the fundamental principles in this field, such as the use of learning methods and the design of parallel hardware (with an emphasis on analog and asynchronous digital VLSI), are inspired by biological systems. However, existing applications are modest and the challenge of scaling up from small artificial neural networks and designing completely autonomous systems at the levels achieved by biological systems lies ahead. The assumption underlying this three week workshop is that the next generation of neuromorphic systems would benefit from closer attention to the principles found through experimental and theoretical studies of real biological nervous systems as whole systems. FORMAT: The three week summer workshop will include background lectures on systems neuroscience (in particular learning, oculo-motor and other motor systems and attention), practical tutorials on analog VLSI design, small mobile robots (Koalas, Kheperas, LEGO robots), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, the majority of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control * central pattern generator and locomotion * robotics * multichip communication * analog VLSI * learning * neuroprosthetic systems The active perception project group will emphasize vision and human sensory-motor coordination. Issues to be covered will include spatial localization and constancy, attention, motor planning, eye movements, and the use of visual motion information for motor control. The central pattern generator group will focus on small walking and undulating robots. It will look at characteristics and sources of parts for building robots, play with working examples of legged and segmented robots, and discuss CPG's and theories of nonlinear oscillators for locomotion. It will also explore the use of simple analog VLSI sensors for autonomous robots. The robotics group will use rovers and working digital vision boards as well as other possible sensors to investigate issues of sensorimotor integration, navigation and learning. The audition group aims to develop biologically plausible algorithms and aVLSI implementations of specific auditory tasks such as source localization and tracking, and sound pattern recognition. Projects will be integrated with visual and motor tasks in the context of a robot platform. The multichip communication project group will use existing interchip communication interfaces to program small networks of artificial neurons to exhibit particular behaviors such as amplification, oscillation, and associative memory. Issues in multichip communicationwill be discussed. LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350miles). Great Lakes Aviation and America West Express airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do not rent a car. Bring hiking boots, warm clothes, rain gear, and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around mid April 2006. Participants are expected to pay a $800.00 workshop fee at that time in order to reserve a place in the workshop. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. Travel reimbursement of up to $500 for US domestic travel and up to $800 for overseas travel will be possible if financial help is needed (please specify on the application). HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e.postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage women and minority candidates to apply. The application website is: http://ine-web.org/telluride-conference-2006/apply/ Application will include: * First name, Last name, Affiliation, valid e-mail address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Two letters of recommendation (to be sent by references directly to "Alice W. Mobaidin" ). The application deadline is Friday, March 24, 2006. Applicants will be notified by e-mail by the end of April. From M.Casey at surrey.ac.uk Thu Mar 16 08:26:56 2006 From: M.Casey at surrey.ac.uk (M.Casey@surrey.ac.uk) Date: Thu, 16 Mar 2006 13:26:56 -0000 Subject: Connectionists: International Workshop on Biologically Inspired Information Fusion Message-ID: ======================================================================== ==================== International Workshop on Biologically Inspired Information Fusion Call for Contributions Tuesday 22 August - Wednesday 23 August 2006, University of Surrey, Guildford, UK. http://www.soc.surrey.ac.uk/ias/workshops/biif/ ======================================================================== ==================== We invite contributions to an international workshop on biologically inspired information fusion. The workshop is designed to bring together complementary researchers in the broad areas of computer science, engineering, psychology and biology who have an interest in the multi-disciplinary aspects of information fusion. The programme consists of tutorials from discipline leaders, discussions, and research student poster and oral presentations. Contributions are being sought for the discussion sessions and research student presentations from all of the target disciplines: computer science, engineering, psychology and biology. ======================================================================== ==================== Natural and Artificial Multi-sensory Processing The ability to process, interpret and act upon sensory information is perhaps one of the most remarkable aspects of human and animal cognition. Our sensory systems process large volumes of information at different scales in short periods of time, far out-performing current artificial systems, which struggle to usefully process just a single modality of information. For example, whereas speech recognition systems have achieved real-time continuous operation, artificial systems, designed for vision or olfaction are far less advanced, yet the combination of different information sources, or senses, may help overcome some of the processing limitations. This disparity between natural and artificial cognitive systems has been recognised in the recent UK Foresight Cognitive Systems Review, which suggests that our understanding of both natural and artificial systems of sensory processing can be achieved through collaboration between life and physical scientists. About the Workshop The workshop is sponsored by the University of Surrey's Institute of Advanced Studies. The aim is to promote collaboration between disciplines to develop an understanding of how to build adaptive information fusion systems by improving our knowledge from both natural and artificial systems research. The programme is designed to facilitate a cross-discipline understanding of multi-sensory fusion, with discussions on key topics and future directions, and presentation of current ideas. This is to be achieved through tutorials from leaders in each of the target disciplines, brainstorming and debate sessions lead by relevant researchers, and both oral and poster presentations from research students. Example topics include, but are not limited to: Sensory and multi-sensory processing: neurobiology, behaviour, computational modelling and artificial sensors - Vision, audition, olfaction, taste, touch - Attention: pre-attention or task-driven attention - Emotional bias on senses - Artificial sensors Information fusion and multi-modal systems: - Computer vision, speech processing, gesture recognition - Sensor fusion - Multiple regressor or classifier systems - Biometrics, human-computer interaction, intelligent systems - Bio-logically inspired robotics ======================================================================== ==================== Discussions Topics for the discussion sessions should aim to promote new or controversial ideas, perhaps posing unanswered questions related to the workshop. These should be in the form of abstracts (maximum 500 words) stating the key topic of discussion and highlighting possible solutions and current points of view. Proposals for debates, where two participants offer their point of view prior to discussion, should be clearly highlighted. All contributions will be peer reviewed by the workshop programme committee. Those with accepted topics will be invited to give a 10 minute presentation of their idea. For sessions focused around a debate, both participants will be invited to present their ideas in a 10 minute slot each, prior to discussion. An open brainstorming session will then follow for 50 minutes with a focus on initially evaluating the proposed idea or giving thoughts on unanswered questions. Notes and outcomes of these sessions will be recorded. Abstracts should be submitted via e-mail to biif2006 at surrey.ac.uk by the deadline. ======================================================================== ==================== Student Presentations Papers are invited from research students only to promote discussion of new ideas and to foster training and development of new researchers. All papers will be peer reviewed by the workshop programme committee to assess originality, significance, quality and clarity. Those students with accepted papers will be invited to either present a poster or to give a 20 minute oral presentation. Papers should not exceed 6 pages in length, including references, tables, figures and appendices, and should follow the LNCS format, details of which can be found at http://www.springer.com/sgw/cda/frontpage/0,11855,3-164-2-72376-0,00.htm l. Papers should be submitted via e-mail to biif2006 at surrey.ac.uk by the deadline. ======================================================================== ==================== Enquiries regarding abstract and paper submission should be directed to biif2006 at surrey.ac.uk. Abstracts and papers will be available to workshop attendees via the website and printed proceedings. After the workshop, participants will be invited to submit papers based upon their work to two journal special issues (journals to be confirmed). These will contain a mixture of review/discussion articles and presentations of current research work. ======================================================================== ==================== Important Dates 15 May 2006 Deadline for submitting papers and discussion topics 19 June 2006 Notification of acceptance 17 July 2006 Camera ready papers 22-23 August 2006 Workshop at the University of Surrey Guests looking for accommodation on campus (the cheapest in Guildford) are advised to register by the 15th May 2006. Otherwise, registration is open up until the workshop. For papers to be presented at the workshop, all guests must be registered by the 17th July 2006 to secure a place on the programme. Further information can be obtained from: - Website: http://www.soc.surrey.ac.uk/ias/workshops/biif/ - Enquiries about paper submission: biif2006 at surrey.ac.uk - General and administrative enquiries: Mrs Gautier O'Shea, S.Gautier at surrey.ac.uk; Mrs Heather Norman, H.Norman at surrey.ac.uk - Dr Matthew Casey, M.Casey at surrey.ac.uk; tel. +44 (0)1483 689635 - Dr Paul Sowden, P.Sowden at surrey.ac.uk - Dr Hujun Yin, Hujun.Yin at manchester.ac.uk - Dr Tony Browne, A.Browne at surrey.ac.uk From terry at salk.edu Mon Mar 20 16:58:06 2006 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 20 Mar 2006 13:58:06 -0800 Subject: Connectionists: NEURAL COMPUTATION 18:4 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 18, Number 4 - April 1, 2006 Note An Invariance Property of Kernel Predictors Sebastiano Stramaglia and Nicola Ancona Letters Modeling Sensorimotor Learning with Linear Dynamical Systems Sen Cheng and Philip N. Sabes Changing Roles of Temporal Representation of the Odorant During the Oscillatory Response in the Olfactory Bulb S. Kim, B. Singer. M. Zochowski Computation of the Phase Response Curve: A Direct Numerical Approach W. Govaerts and B. Sautois Multiperiodicity and Exponential Attractivity Evoked by Periodic External Inputs in Delayed Cellular Neural Networks Zhigang Zeng and Jun Wang Smooth Gradient Representations as an Unifying Account of Chevreul's Illusion, Mach Bands and a Variant of the Ehrenstein Disk Matthias S. Keil Memory Capacity for Sequences in a Recurrent Network with Biological Constraints Christian Leibold and Richard Kempter Kernel Fisher Discriminants for Outlier Detection Volker Roth Feature Scaling for Kernel Fisher Discriminant Analysis by Leave-One-Out Cross Validation Liefeng Bo, Ling Wang and Licheng Jiao Class Incremental Generazlied Discriminant Analysis Wenming Zheng ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2006 - VOLUME 18 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $154 $90 $96.30 Institution $730 $781.10 $784 $657 $702.99 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From kamps at in.tum.de Mon Mar 20 11:27:20 2006 From: kamps at in.tum.de (Marc de Kamps) Date: Mon, 20 Mar 2006 17:27:20 +0100 Subject: Connectionists: First Workshop on Topics of the nEUro-IT.net Roadmap Message-ID: <000401c64c3b$2a24bcf0$383c9f83@atknoll3> First Workshop on Topics of the nEUro-IT.net Roadmap Antwerp, 21/22 April 2006 Location: to be announced Scope nEUro-IT.net is about to present the new version of the Roadmap. The Roadmap is a document which summarizes the state-of-the-art in nEUro-IT topics, and which tries to recognize future developments in this field. The Roadmap will serve as input for new calls in FP7. In order to promote the Roadmap, we will organize a workshop around theme's in the Roadmap. This workshop will take place in Antwerp on 21/22 April. Topics are: 1. Bio-inspired and evolvable hardware 2. Brain-Machine interfacing 3. Peripheral Processing On the 21st the three workshops will take place in parallel, on the 22nd there will be a plenary session. The talks here address a general audience and allow people who have been participating in one of the workshops on the 21st to get a flavour from the other workshops. Officers from Future and Emerging Technology (FET) will be present at the meeting and briefly comment the preparations for FP7. They are also available for informal contacts during the meeting. Participation is free, but a registration is required. Please send an email to kamps at in.tum.de Programme webpage: http://www.neuro-it.net/NeuroIT/Activities/Roadmapworkshop Key note speakers include (ordered by workshop): Tetsuya Higuchi (AIST, Japan), Pauline Haddow (NTNU, Norway), Gianluca Tempesti (EPFL Switzerland), Andy Tyrrell (Univerity of York, UK), Gianluca Tempesti (EPFL Switzerland), Jim Torresen(University of Oslo, Norway), Adrian Stoica Erik De Schutter, Ad Aertsen (Bernstein Center, University of Freiburg, Germany), Paolo Dario (Polo Sant'Anna Valdera, Italy), Miguel Nicolelis (Duke University, USA and Brain Mind Institute, Lausanne, Switzerland), Eilon Vaadia (Hebrew University, Jerusalem, Israel) Stefaan Peeters,Gijs Krijnen (Universiteit Twente), George Jeronimidis (Reading University), Herbert Peremans (Universiteit Antwerpen), Leo van Hemmen (Technische Universit?t M?nchen), Annemie Van Der Linden (Universiteit Antwerpen), Heike Scheuerpflug (Forschungszentrum J?lich) Scope of the workshops is described in greater detail below: ---------------------------------------------------------------------------- -------------------------------------------------------- 1. Bio-inspired and evolvable hardware Evolvable hardware techniques enable self-reconfigurability and adaptability of programmable devices and thus have the potential to significantly increase the functionality of deployed hardware systems. Evolvable hardware is expected to have a major impact on deployable systems for space missions and defence applications that need to survive and perform at optimal functionality during long duration in unknown, harsh and/or changing environments. Evolvable hardware is also expected to greatly enrich the area of commercial applications in which adaptive information processing is needed; such applications range from human-oriented hardware interfaces and internet adaptive hardware to automotive applications. Evolvable hardware is an emerging field that applies evolution to automate design and adaptation of physical structures such as electronic systems, antennas, MEMS and robots. The aim of this workshop is to bring together leading researchers from the evolvable hardware community, representatives of the automated design and programmable/reconfigurable hardware communities, technology developers, and end-users from the aerospace, military and commercial sectors. Presentations will consider some of the following issues important now and in the future : 1. Design of large evolvable systems 2. Hardware design 3. Increased reliability using evolvable hardware 4. Analogue evolvable hardware and its applications 5. Real-world applications of evolvable hardware 6. Future evolvable systems 2. Brain Machine Interfaces: moving beyond limb control Recent progress in fundamental neurophysiological research has made a popular subject of science fiction movies seem possible: direct interfacing of the human brain with computers and machines to create the cyborg. Indeed in 2004 the first implant of an electrode array was performed in the brain of a quadriplegic patient, allowing control of external devices including a robot arm. This rapid development of a new field called neuroprosthetics has been made possible by the development of better electrodes and of fast signal processing techniques. This allowed chronic implantation of large arrays of recording electrodes in rodents and monkeys. The major breakthrough, however, was the discovery of a high level of plasticity of the neural coding in the mammalian brain, allowing it to adapt its signals to communication over a limited number of channels. This has led to an explosion of application of brain machine interfacing (BMI) to control of cursors on a computer screen or artificial upper limbs in monkeys and recently also in patients. But if we want to progress towards making cyborg-like applications, the vision of the Brain Interface project should be more ambitious than just simple motor control tasks such as using an artificial arm. This will require interfacing of sensory input to the brain and interfacing to cognitive tasks like memory. To achieve such goals the BMI needs to be developed further and we will need a much better understanding of the underlying brain plasticity and brain coding mechanisms. While research oriented towards neuroprosthetic application needs to be done in monkeys to prepare for human implementation, most of the visionary research proposed here can first be done in cheaper rodents, as was the case for the original BMI studies. This workshop will discuss both the current state of the field, where the USA is clearly leading, and achievable goals for FP7 including the development of awake animal models where the brain interacts with the environment only through BMI techniques. 3. Peripheral Processing Sensory systems based on arrays of hairs occur widely in nature and function in diverse sensing scenarios, for instance in air (cerci, external sensing hairs in arthropods), in water (lateral line, neuromasts in fish) and in a fluid-filled compartment coupled to air through impedance matching devices and beamforming baffles (mammalian auditory apparatus). These mechanosensor-systems are amongst the most sensitive sensors known. This suggests that hair-based sensing organs, supported by appropriate neuronal representation and processing, are a model system particularly well-suited for studying the extraction of significant information from noisy environments. Organisms and their environments form tightly coupled interacting systems in which all components: environmental characteristics and dynamics, sensory and physical morphology, peripheral and central neural processing and behavioural patterns, play a significant role. Hence, the analysis of hair-based sensing organs will need to be carried out at three levels simultaneously: the morphology and mechanics, the neuronal processing, and the behavioural strategies of the model-systems. We emphasize peripheral processing because we believe that knowledge of the transformations and processes performed by peripheral systems is essential for true understanding of the organisation and operation of central neuronal processing, as peripheral systems provide the input to central ones. In this workshop we want to bring together everybody interested in identifying the common principles underlying the widespread use in nature of arrays of mechanical sensory cells for the extraction of significant information as well as in making those principles available for design of engineered systems. From brefeld at informatik.hu-berlin.de Mon Mar 20 06:08:32 2006 From: brefeld at informatik.hu-berlin.de (Ulf Brefeld) Date: Mon, 20 Mar 2006 12:08:32 +0100 Subject: Connectionists: CFP: ICML Workshop on Learning in Structured Output Spaces Message-ID: <441E8D30.5080107@informatik.hu-berlin.de> -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: cfp-new.txt Url: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20060320/2485646c/cfp-new.txt From oreilly at psych.colorado.edu Tue Mar 21 00:17:34 2006 From: oreilly at psych.colorado.edu (Randall C. O'Reilly) Date: Mon, 20 Mar 2006 22:17:34 -0700 Subject: Connectionists: Computational Cognitive Neuroscience: Call for Symposium Proposals In-Reply-To: <200507142326.20216.oreilly@psych.colorado.edu> References: <200507142326.20216.oreilly@psych.colorado.edu> Message-ID: <200603202217.34527.oreilly@psych.colorado.edu> ~ Call for Symposium Proposals ~ 2ND ANNUAL CONFERENCE ON COMPUTATIONAL COGNITIVE NEUROSCIENCE www.ccnconference.org To be held in conjunction with the 2006 PSYCHONOMIC SOCIETY CONFERENCE, November 16-19, 2006 at the Hilton Americas hotel in Houston, TX. The inaugural CCNC 2005 meeting held prior to Society for Neuroscience (SFN) in Washington, DC was a great success, with approximately 250 attendees, 60 presented posters, and strongly positive reviews. In subsequent years, it will be held on a rotating basis with other meetings, such as (tentative list): CNS (Cognitive Neuroscience Society), HBM (Organization for Human Brain Mapping), CogSci (Cognitive Science Society), (SFN) Society for Neuroscience, NIPS (Neural Information Processing Systems), and COSYNE (Computational and Systems Neuroscience). ____________________________________________________________________________ * DEADLINE FOR SUBMISSION OF SYMPOSIUM PROPOSALS: May 1, 2006 * DEADLINE FOR SUBMISSION OF ABSTRACTS: TBA * CONFERENCE DATES: Wed-Thu November 15 & 16, 2006 * This year's featured Keynote Speakers (confirmed): Mike Kahana, University of Pennsylvania Mark Seidenberg, University of Wisconsin Madison Each 2 hour symposium should be discussion oriented and include a mixture of modelers and non-modelers, all focused on a common theme or issue. At least half of the talks should focus on specific results from implemented models. A moderator acts as overall organizer/coordinator, and may also participate as one of 4-5 discussants. Each discussant should present a brief 20-30 minute talk, followed by plenty of time for discussion/Q & A. No particular proposal format is required. A 1-2 page description, including potential participants, is sufficient. Send by email (plain text preferred) to the Executive Organizer: Thomas Hazy . Questions regarding potential proposals are welcomed. ____________________________________________________________________________ 2006 Planning Committee: Suzanna Becker, McMaster University Jonathan Cohen, Princeton University Yuko Munakata, University of Colorado, Boulder David Noelle, Vanderbilt University Randall O'Reilly, University of Colorado, Boulder Maximilian Riesenhuber, Georgetown University Medical Center Executive Organizer: Thomas Hazy, University of Colorado, Boulder For more information and to sign up for the mailing list visit: www.ccnconference.org From Yaochu.Jin at honda-ri.de Tue Mar 21 09:40:28 2006 From: Yaochu.Jin at honda-ri.de (Yaochu.Jin@honda-ri.de) Date: Tue, 21 Mar 2006 15:40:28 +0100 Subject: Connectionists: Book announcement "Multi-Objective Machine Learning" Message-ID: Multi-Objective Machine Learning Series: Studies in Computational Intelligence, Vol. 16 Jin, Yaochu (Ed.) Springer 2006, XIII, 660 p. 255 illus., Hardcover ISBN: 3-540-30676-5 Table of Contents Part I Multi-Objective Clustering, Feature Extraction and Feature Selection 1. Multiobjective feature selection using rough set M. Banerjee, S. Mitra, and A. Anand 2. Multi-objective clustering and cluster validation J. Handl and J. Knowles 3. Feature selection for ensembles using the MOO approach L.S. Oliveira, M. Morita, and R. Sabourin 4. Feature extraction using multi-objective genetic programming Y. Zhang and P.I. Rockett Part II Multi-Objective Learning for Accuracy Improvement 5. Regression error characteristic optimization using multi-objective optimization J. E. Fieldsend 6. Regularization for parameter identifcation using multi-objective optimization T. Furukawa, C. Lee, J.G. Michpoulos 7. Multi-objective algorithms for nrural network learning A. Braga, R. Takahashi, M. Costa, R. de A. Teixeira 8. Generating support vector machine using multi-objective optimization and goal programming H. Nakayama, Y. Yun 9. Multi-objective optimization of support vector machines T. Suttorp and C. Igel 10. Multi-objecitve evolutionary algorithms for radial basis function neural network design G. G. Yen 11. Min imizing structural risk on decision tree classification D.-E. Kim 12. Multi-objective learning classifier systems E. Bernado-Mansilla, X. Llora, I. Traus Part III Multi-Objective Learning for Interpretability Improvement 13. Simultaneous generation of accurate and interpretable neural network classifiers Y. Jin, B. Sendhoff, E. Koerner 14. GA-based Pareto optimization for rule extraction from neural networks U. Markowska-Kaczmar, K. Mularczyk 15. Agent based multi-objective approach to generating interpretable fuzzy systems H. Wang, S. Kwong, Y. Jin, C.-H. Tsang 16. Multi-objective evolutionary algorithms for temporal linguistic rule extraction G.G. Yen 17. Multiple objective learning for constructing interpretable TS fuzzy model S.M. Zhou, J.Q. Gan Part IV Multi-Objective Ensemble Generation 18. Pareto-optimal approaches to neuro-ensemble learning H. Abbass 19. Trade-off between diversity and accuracy in ensemble generation A. Chandra, H. Chen, X. Yao 20. Cooperative coevolution of neural networks and ensemble of neural networks N. Garcia-Pedrajas 21. Multi-objective structure selection for RBF networks and its application to nonlinear system identification T. Hatanaka, N. Kondo, K. Uosaki 22. Fuzzy ensemble design through multi-objective fuzzy rule selection H. Ishibuchi, Y. Nojima Part V Applications of Multi_objective Machine Learning 23. Multi-objective optimization for receiver operating characterics analysis R.M. Everson, J.E. Fieldsend 24. Multi-objective design of neuro-fuzzy controllers for robot behavior coordination N. Kubota 25. Fuzzy tuning for docking maneuver Controller of an automated guided vehicle J.M. Lucas, H. Martinez, F. Jimenez 26. A multi-objective genetic algorithm for learning linguistic persistent queries in text retrieval environments M. Luque, O. Cordon, E. Herrera-Viedma 27. Multi-objective neural network optimization for visual object detection S. Roth, A. gepperth, C. Igel Index From d.mareschal at bbk.ac.uk Wed Mar 22 04:52:43 2006 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Wed, 22 Mar 2006 09:52:43 +0000 Subject: Connectionists: PhD in Neurocomputational models of early learning Message-ID: Dear all, Please circulate the following information as appropriate. Many thanks, Denis Mareschal ------------------------------------------ A funded 3 year Phd position is available for outstanding candidates wishing to complete a project investigating the the neurocomputational mechanisms of perceptual learning memory in early infancy. A suitable candidate would have a background in neuroscience, psychology, AI or related fields. Fellows will be hosted at the Centre for Brain and Cognitive Development (CBCD), within the School of Psychology, Birkbeck University of London. Details of the Centre's and affiliated lab's activities can be found at http://www.cbcd.bbk.ac.uk/cbcd.html. The CBCD has the mission to investigate relations between postnatal brain development and changes in perceptual, cognitive, and linguistic abilities from birth through childhood and late adulthood. Research in intrinsically multidisciplinary and involves behavioural testing, ERP, fMRI, NIRS, and computational neural network modelling with typically and atypically developing children as well as adult patient populations. Successful applicants cannot have resided more than 1 year within the last 3 in the UK. Ordinarily, applications will only be considered from citizens or long-term residents of the EU or affiliated states who are not citizens or residents of the UK. Other eligibility requirements may apply. Minimum English language standards apply for all PhD candidates to the University of London. Successful candidate will be expected to have sufficient written English skill to undertake the writing of a long document in English. Equal Opportunity Birkbeck is an equal opportunity employer. We particularly encourage application from women and recognise the differing life patterns of men and women in the work and trainings sectors. Qualifications The fellowships are open to truly outstanding candidates who must have achieved at least a level of training that would enable them to qualify for entry into a PhD programme in their home country. As the PhD must be completed within the 3 years of the fellowships we anticipate that successful candidate will have already obtained a substantial amount of training in relevant research methods. Conditions of employment Successful candidates will be employed as research assistants within the school of Psychology, Birkbeck University of London. Their salary will be the sterling equivalent of approximately ?32k per annum plus a minimum of ?6k Mobility Allowance per annum. They will also receive an annual payment as a Travel Allowance, and ?2k as a Career Exploratory Allowance paid upon completion of the first 12 months of your appointment. All payments are determined by personal circumstance, details of actual salary and allowances can be obtained upon request Application procedures Interested applicants should consult the relevant web pages of the CBCD and affiliated Labs first to assess whether their research interests and experience match those of relevant possible supervisors. Applications will then be made through the School of Psychology MPhil/PhD Programme (http://www.psyc.bbk.ac.uk/courses/phd_research/). Application forms can be obtained from Ms. Mina Daniels (s.daniels at bbk.ac.uk) or they can be downloaded directly form the Birkbeck web pages by following the links on (http://www.bbk.ac.uk/for/prospective/full-time/research). When applying, candidates should make it clear on their application form that they wish to be considered for a Marie Curie Studentship. Applications should be submitted not later than March 31st 2006. A small short list of candidates drawn form those received by this date will be invited to London for interviews approximately 4 to 6 weeks following this date. However, we will continue to consider applications until all 6 positions have been filled. We will announce when the position have been filled on the CBCD web pages cited above. Informal enquires can be made to Dr. Denis Mareschal (d.mareschal at bbk.ac.uk). Procedural or administrative enquires regarding the application procedures or conditions of employment should be made to he Marie Curie Administrator Ms Katherine Jones (k.jones at bbk.ac.uk) -- ================================================= Dr. Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 (0)20 7631-6582/6226 reception: 6207 fax +44 (0)20 7631-6312 http://www.psyc.bbk.ac.uk/people/academic/mareschal_d/ ================================================= From zhaoping at gatsby.ucl.ac.uk Wed Mar 22 13:18:02 2006 From: zhaoping at gatsby.ucl.ac.uk (Dr Zhaoping Li) Date: Wed, 22 Mar 2006 18:18:02 +0000 (GMT) Subject: Connectionists: Papers available on visual input sampling and information theory Message-ID: Two papers are available for download: Lewis A. and Zhaoping L. (2006) Are cone sensitivities determined by natural color statistics? Journal of vision, 6(3):285-302. download from http://journalofvision.org/6/3/8/ Lewis A. Garcia R. and Zhaoping L. (2003) The distribution of visual objects on the retina: connecting eye movements and cone distributions Journal of Vision 3(11), p. 893-905. Download from http://www.journalofvision.org/3/11/21/ Related papers available at http://www.gatsby.ucl.ac.uk/~zhaoping/visualcoding.html From ted.carnevale at yale.edu Wed Mar 22 13:51:27 2006 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Wed, 22 Mar 2006 13:51:27 -0500 Subject: Connectionists: Parallel network simulations at the NEURON Simulator Meeting Message-ID: <44219CAF.3040005@yale.edu> The registration deadline (April 21) for the 2006 NEURON Simulator Meeting is rapidly approaching! For more information see http://www.utexas.edu/neuroscience/NEURON2006/nsm2006.html One of the featured speakers is Michael Hines, who will present a tutorial and run a workshop on using NEURON to implement network models that are distributed over multiple processors. Tutorial Title: Parallel network simulations with NEURON Abstract: Parallel network management services (i.e. the ability to create and execute network models that are distributed over multiple processors) are now available when NEURON is configured with the --with-mpi option. We have run extensive tests using published network models of conductance based neurons, on parallel hardware with dozens to thousands of CPUs. These tests demonstrate speedup that is linear with the number of CPUs, or even superlinear (due to larger effective high speed memory cache), until there are so many CPUs that each one is solving fewer than ~100 equations. Workshop Title: Implementing parallel network simulations with NEURON Abstract: This workshop is devoted to teaching how to transform serial network NEURON models into a parallel program. Transformation turns out to be fairly straightforward if the network model was originally developed from a synapse-centric or target cell viewpoint. In other words, since a NetCon that connects to a target cell exists only on the CPU where the target cell exists, it is easier if one organizes the code around the question "who projects to me?" than from the source cell perspective "to whom do I project?". The discussion will cover important practical and theoretical considerations, including the following: --mpi installation and building NEURON on Beowulf clusters and other multiprocessor systems --how to handle random connections and random spike inputs in a way that preserves double precision quantitative identity regardless of number of CPUs and how cells are distributed among the CPUs --how to measure performance From marcilio at dimap.ufrn.br Thu Mar 23 09:25:13 2006 From: marcilio at dimap.ufrn.br (Marcilio Carlos P. de Souto) Date: Thu, 23 Mar 2006 11:25:13 -0300 Subject: Connectionists: SBRN 2006: Deadline extension In-Reply-To: <20060323131202.M15909@dimap.ufrn.br> References: <20060323131202.M15909@dimap.ufrn.br> Message-ID: <20060323142454.M24171@dimap.ufrn.br> ********************************************************************** SBRN'2006 - IX BRAZILIAN SYMPOSIUM ON NEURAL NETWORKS Ribeirao Preto, October 23-26, 2006 http://www.icmc.usp.br/iarn2006/sbrn.php ********************************************************************** Due to several requests for a deadline extension, the new deadlines are: Registration: April 02, 2006, 23: 55 BRST (Extended Deadline) Submission: April 02, 2006, 23:55 BRST (Extended Deadline) Acceptance: May 24, 2006 Camera-ready: June 12, 2006 Program Chair: Anne Mag?ly de Paula Canuto (UFRN/DIMAp, Brazil) anne at dimap.ufrn.br _______________________________________________ Sbc-l mailing list Sbc-l at inf.ufrgs.br https://listas.inf.ufrgs.br/mailman/listinfo/sbc-l ------- End of Forwarded Message ------- -- Open WebMail Project (http://openwebmail.org) Debian Project (http://www.debian.org) From kfm at androidscience.com Wed Mar 22 09:55:57 2006 From: kfm at androidscience.com (Karl F. MacDorman) Date: Wed, 22 Mar 2006 09:55:57 -0500 Subject: Connectionists: External Symbol Grounding Workshop 2006 Message-ID: <002201c64dc0$bb7ae1d0$650fa8c0@anon> Call for papers External Symbol Grounding Workshop 2006 3 and 4 July 2006, University of Plymouth, Plymouth, United Kingdom http://www.tech.plym.ac.uk/SoCCE/ESG2006/ The External Symbol Grounding Workshop 2006 (ESG2006) is an international workshop for research on grounding external signs and symbols. Specifically, we wish to invite contributions viewing language and cognition as linking what goes on in the head with causal processes that are intersubjective, multimodal, affect-laden, and organised by historically rooted customs and artefacts. We aim to bring together linguists, psychologists, ethologists and social biologists, social and cognitive neuroscientists, philosophers, computer scientists, and roboticists for an intense two days of presenting and discussing (potentially incompatible) views. The purpose of the workshop is not so much to present completed work as to find new ways of tackling a complex issue and to launch collaboration among participants to that end. Since the workshop focuses on how symbol grounding can be reconsidered when language is viewed as a dynamical process rooted in both culture and biology, research related to robotic or computer modelling of symbol grounding, psychological and linguistic viewpoints on cognitive development and semiotic dynamics are of great interest. We have invited a range of speakers who will bring their specialised expertise to bear on the issue of external symbol grounding, and we are looking for additional researchers who would like to contribute to this exciting new initiative. ESG2006 is the successor to the first Distributed Language Group?s Conference on Cognitive Dynamics and the Language Sciences, held at Sidney Sussex College, Cambridge on 9-11 September 2005. Special issue Participants will be invited to submit papers to Interaction Studies for the special issue on external symbol grounding to be published in 2007. Papers will be selected based on an independent peer review. Important dates Deadline for submission of two-page abstract (or paper): 15 April 2006 Notification of acceptance: 1 May 2006 Workshop: 3 and 4 July 2006 Submission instructions Authors are invited to submit a two page abstract for presentation at the workshop. Alternatively, they may submit papers that are not to exceed 12 pages. Submitted abstracts and papers will be refereed and selected for half-hour oral presentations on the basis of quality and relevance to issues surrounding the external grounding of signs and signals. Accepted papers will be included in the proceedings and will be made accessible through the web. Copies of the proceedings will be available at the workshop. Authors are strongly encouraged to submit their papers electronically (MS Word or PDF preferred). Please email your submission to ESG2006 at plymouth.ac.uk. If you cannot send your submission through email, please send a hardcopy to Stephen J. Cowley School of Psychology University of Hertfordshire College Lane AL10 9AB Hatfield United Kingdom The deadline for submission is 15 April 2006. Confirmed speakers Michael Anderson (University of Maryland, MD, USA) Angelo Cangelosi (University of Plymouth) Stephen Cowley (University of Hertfordshire) Stevan Harnad (Universit? du Qu?bec ? Montr?al, provisional) Karl MacDorman (Indiana University, IN, USA) David Spurrett (University of KwaZulu-Natal, South Africa) Paul Thibault (Agder University College, Kristiansand, Norway) Paul Vogt (University of Tilburg, The Netherlands) From dancoisne at bccn.uni-freiburg.de Fri Mar 24 03:48:43 2006 From: dancoisne at bccn.uni-freiburg.de (Florence Dancoisne) Date: Fri, 24 Mar 2006 09:48:43 +0100 Subject: Connectionists: Announcement for the Advanced Course in Computational Neuroscience 2006 Message-ID: <4423B26B.9090203@bccn.uni-freiburg.de> *ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE* *(A PENS NEUROSCIENCE SCHOOL)* *August 7th -- September 1st 2006, ARCACHON, FRANCE* *DIRECTORS: *Ad Aertsen (BCCN Freiburg, Germany) Peter Dayan (UCL London, UK) Nicolas Brunel (CNRS, Paris, France) Israel Nelken, (Hebrew University Jerusalem, Israel) *LOCAL ORGANIZER*: Gwendal Le Masson (INSERM Bordeaux, France) The Advanced Course in Computational Neuroscience is for advanced graduate students and postdoctoral fellows who are interested in learning the essentials of the field. We seek students of any nationality from a variety of disciplines, including neuroscience, physics, electrical engineering, computer science, mathematics and psychology. Students are expected to have a keen interest and basic background in neurobiology as well as some computer experience. The course has two complementary parts. Mornings are devoted to lectures given by distinguished international faculty on topics across the breadth of experimental and computational neuroscience. During the rest of the day, students are given practical training in the art and practice of neural modelling, largely through the medium of their individual choice of model systems. The first week of the course introduces students to essential neurobiological concepts and to the most important techniques in modelling single cells, networks and neural systems. Students learn how to solve their research problems using software packages such as MATLAB, NEST, NEURON, XPP, etc. During the following three weeks the lectures cover specific brain areas and functions. Topics range from modelling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the brain. The course ends with project presentations by the students. A maximum of 30 students will be accepted. There will be a minimum fee of EUR 500 per student (depending on the course's funding) covering costs for lodging, meals and other course expenses. Also depending on funding, there will be a limited number of tuition fee waivers and travel stipends available for students who need financial help for attending the course. We specifically encourage applications from researchers who work in the developing world. These students will be selected following the normal submission procedure. Applications, including a description of the target project must be submitted electronically (see below) and should be accompanied by the names and email details of two referees who have agreed to furnish references. Applications will be assessed by a committee, with selection being based on the following criteria: the scientific quality of the candidate (CV) and of the project, the recommendation letters, and evidence that the course affords substantial benefit to the candidate's training. More information and application forms can be obtained from: http://www.neuroinf.org/courses/EUCOURSE/EU06 * Please apply electronically using a web browser.* Contact address: - mail: Florence Dancoisne, Bernstein Center for Computational Neuroscience Freiburg Albert-Ludwigs-Universit?t Freiburg Hansastrasse 9A 79104 Freiburg, Germany - e-mail: dancoisne at bccn.uni-freiburg.de From andreas at cs.ntua.gr Fri Mar 24 06:17:35 2006 From: andreas at cs.ntua.gr (andreas) Date: Fri, 24 Mar 2006 13:17:35 +0200 Subject: Connectionists: ICANN 2006 Final Call for Papers Message-ID: <200603241117.k2OBHfQX016835@theseas.softlab.ece.ntua.gr> Final Call for Papers ****** One week to deadline ****** International Conference on Artificial Neural Networks (ICANN 06) ****** The deadline for submission of papers (abstract + full paper) to regular sessions has been extended to 31 March 2006 ***** 10-14 September 2006 Holiday Inn Hotel, Athens, Greece ********Conference Framework******** The 16th International Conference on Artificial Neural Networks, ICANN 2006, will be held from September 10 to September 14, 2006, at the Holiday Inn Hotel, Athens Greece. ICANN is an annual conference organized by the European Neural Network Society in cooperation with the International Neural Network Society, Japanese Neural Network Society, and the IEEE Computational Intelligence Society, and is a premier European event in all topics related to neural networks. ICANN 2006 (www.icann2006.org) welcomes contributions on the theory, algorithms, applications and implementations in the following broad areas: -Computational neuroscience; -Connectionist cognitive science; -Data analysis and pattern recognition; -Graphical networks models, Bayesian networks; -Hardware implementations and embedded systems; -Neural and hybrid architectures and learning algorithms; -Neural control, reinforcement learning and robotics applications; -Neuroinformatics; -Neural dynamics and complex systems; -Real world applications; -Robotics, control, planning; -Signal and time series processing; -Self-organization; -Vision and image processing; -Web semantics; -Intelligent Multimedia and the Semantic Web. Ideas and nominations for interesting tutorials, special sessions, workshops and experts willing to organize various session tracks are called for. Most active experts will be included in the scientific committee of the conference. Proceedings of ICANN will be published in Springer's "Lecture Notes in Computer Science". Paper length is restricted to a maximum of 10 pages, including figures. ********Deadlines and Conference dates******** 06.01 Submission page opens 31.03 End of submission of papers (abstract+full paper) to regular sessions 31.03 End of submission of papers to special sessions 30.04 Acceptance/rejection notification 15.06 Deadline for camera ready papers 01.07 Deadline for early registration 10.09 Tutorials - first day of the conference 11-13.09 Main part of the conference 14.09 Workshops For further information and/or contacts, send inquiries to Prof. Stefanos Kollias (stefanos at cs.ntua.gr) Prof Andreas Stafylopatis (andreas at cs.ntua.gr) School of Electrical & Computer Engineering National Technical University of Athens 9, Heroon Polytechniou str., 157 80 Zografou, Athens, Greece. General Chair Stefanos Kollias, National Technical University of Athens (NTUA), Greece Co-Chair Andreas Stafylopatis, NTUA, Greece Program Chair Wlodzislaw Duch, Torum, PL & Singapore; ENNS President-elect Erkki Oja, Helsinki, FI; ENNS President Honorary Chair John G. Taylor, Kings College, London, UK; ENNS Past President ********International Program Committee******** -Hojjat Adeli, Ohio State University, USA -Peter Andras, U. Newcastle, UK -Marios Angelides, Brunel University, UK -Panos Antsaklis, U. N. Dame, USA -Bruno Apolloni, University of Milan, IT -Nikolaos Bourbakis, Wright State Univ., USA -Peter Erdi, Univ. Budapest, HU & Kalamazoo -Georg Dorffner, Univ. Wien, AT -Jose Derronsoro, Universidad Autonoma de Madrid, ES -Christophe Garcia, France T?l?com -Erol Gelenbe, Imperial College London, UK -Stan Gielen, Univ. Nijmegen, NL -Janusz Kacprzyk, Warsaw, PL -Nikola Kasabov, Kedri, AUT, NZ -Okyay Kaynak, Bogazici Univ., TR -Chris Koutsougeras, Tulane University, USA -Thomas Martinetz, Luebeck, DE -Evangelia Micheli-Tzanakou, Rutgers University, USA -Lars Niklasson, Sk?vde, SE -Andreas Nuernberger, University of Magdenburg, DE -Marios Polycarpou, Univ. of Cyprus, CY -Demetris Psaltis, Caltech, USA -Branimir Reljin, University of Belgrade, YU -Olli Simula, Espoo, FI -Alessandro Sperduti, U.Padova, IT -Lefteris Tsoukalas, Purdue Uni, USA -Michel Verleysen, Louvain-la-Neuve, BE -Alessandro Villa, U. Grenoble, FR ********Local Organizing Committee******** -Yannis Avrithis, NTUA -Christos Douligeris, Piraeus Univ -George Dounias, Aegean Univ -Kostas Karpouzis, ICCS-NTUA -Aris Likas, Univ. of Ioannina -Kostas Margaritis, Univ. Macedonia -Basil Mertzios, DUTH and ATIT -Stavros Perantonis, NCSR, Athens -Yannis Pitas, AUTH, Salonica -Costas Pattichis, Univ. of Cyprus -Apostolos Paul Refenes, Athens University Economics & Business -Christos Schizas, Univ. of Cyprus -Thanos Skodras, Univ. of Patras -Kostas Spyropoulos, NCSR, Athens -Giorgos Stamou, ICCS-NTUA -Sergios Theodoridis, UoA -Spyros Tzafestas, NTUA -Mihalis Zervakis, TUC, Crete From dgw at MIT.EDU Fri Mar 24 14:58:57 2006 From: dgw at MIT.EDU (David Weininger) Date: Fri, 24 Mar 2006 14:58:57 -0500 Subject: Connectionists: Book announcement - De Jong Message-ID: <6.2.3.4.2.20060324145811.044a2a80@po14.mit.edu> Hi all: I thought readers of Connectionists might be interested in this book. For more information, please visit http://mitpress.mit.edu/promotions/books/SP20060262041944 Thanks! Best, David Evolutionary Computation A Unified Approach Kenneth A. De Jong Evolutionary computation, the use of evolutionary systems as computational processes for solving complex problems, is a tool used by computer scientists and engineers who want to harness the power of evolution to build useful new artifacts, by biologists interested in developing and testing better models of natural evolutionary systems, and by artificial life scientists for designing and implementing new artificial evolutionary worlds. In this clear and comprehensive introduction to the field, Kenneth De Jong presents an integrated view of the state of the art in evolutionary computation. Although other books have described such particular areas of the field as genetic algorithms, genetic programming, evolution strategies, and evolutionary programming, Evolutionary Computation is noteworthy for considering these systems as specific instances of a more general class of evolutionary algorithms. This useful overview of a fragmented field is suitable for classroom use or as a reference for computer scientists and engineers. Kenneth A. De Jong is Professor of Computer Science, Head of the Evolutionary Computation Laboratory, and Associate Director of the Krasnow Institute at George Mason University. He is the founding editor of the journal Evolutionary Computation (MIT Press). 7 x 9, 250 pp., XX illus., cloth ISBN 0-262-04194-4, A Bradford Book David Weininger Associate Publicist MIT Press 55 Hayward Street Cambridge, MA 02142-1315 617.253.2079 617.253.1709 fax dgw at mit.edu Check out the new MIT Press Log http://mitpress.mit.edu/presslog From ale at sissa.it Fri Mar 31 05:14:21 2006 From: ale at sissa.it (Alessandro Treves) Date: Fri, 31 Mar 2006 12:14:21 +0200 Subject: Connectionists: EBBS Call for Symposia: Trieste, Sept 16-19, 2007 Message-ID: <1143800061.442d00fd178f1@webmail.sissa.it> European Brain and Behaviour Society - CALL for SYMPOSIA for the 39th Annual General Meeting, Trieste, September 16-19, 2007 The EBBS meeting is open to all scientists from around the world interested in how the brain produces behaviour, from integrative, cognitive, systems, computational neuroscience - and beyond. Based on previous meetings, we expect ca. 500 participants, many of whom will be new to EBBS meetings. The program includes 6 invited plenary speakers, 14 symposia with 4 talks each, and hundreds of posters presented over extended daily sessions. SISSA, the International School for Advanced Studies of Trieste, Italy and ICTP, the Abdus Salam International Centre for Theoretical Physics, will host the meeting at their attractive campus next to the Miramar castle and it park, 8 km north of Trieste along the coast. You will reach it every morning from hotels at the seafront downtown, by bus, by train, or by boat (or windsurf). Symposia are selected by the program committee among those proposed by you, whether you are an EBBS member or not, by the June 15, 2006 DEADLINE. All 4 half-hour speakers in a symposium are waived the registration fee. Moshe Abeles, Jocelyne Bachevalier, Barry Everitt, Pierre Maquet and Faraneh Vargha-Khadem will give plenary lectures, and Susumu Tonegawa will give an opening Nobel lecture on Sat evening, Sept 15. The rest depends on you. Do contribute to the success of the meeting by taking a few easy steps: * Insert the website http://www.sissa.it/~ale/EBBS2007/ among your browser?s favorites * Forbid your dear ones from getting married or falling ill on September 15-19, 2007 * Submit your top-quality proposals to our Call for Symposia by the deadline of June 15, 2006 * Produce over the next year-and-a-half the best science of your life, and present it in Trieste Welcome to Miramar! -- Alessandro Treves SISSA - Cognitive Neuroscience, now downtown in via Stock 2/2, V fl BUT NOTE, POSTAL ADDRESS: SISSA, via Beirut 2, 34014 Trieste, Italy tel:39-040-3787623 fax:39-040-3787615 http://www.sissa.it/~ale/ ---------------------------------------------------------------- SISSA Webmail https://webmail.sissa.it/ Powered by Horde http://www.horde.org/ From BerndPorr at f2s.com Thu Mar 30 16:28:18 2006 From: BerndPorr at f2s.com (Bernd Porr) Date: Thu, 30 Mar 2006 22:28:18 +0100 Subject: Connectionists: Paper: Towards Closed Loop Information Message-ID: <442C4D72.9000102@f2s.com> I'm pleased to inform you that a paper about closed loop information is available online: http://www.univie.ac.at/constructivism/journal/1.2/ in the journal Constructivist Foundations: Towards Closed Loop Information: Predictive Information Bernd Porr, Alice Egerton and Florentin W?rg?tter Motivation: Classical definitions of information, such as the Shannon information, are designed for open loop systems because they define information on a channel which has an input and an output. The main motivation of this paper is to present a closed loop information measure which is compatible with constructivist thinking. Design: Our information measure for a closed loop system reflects how additional sensor inputs are utilised to establish additional sensor-motor loops during learning. Our information measure is based on the assumption that it is not optimal to stay reactive and that it is beneficial to become proactive through increased learning about the environment. Consequently our information measure gauges the utilisation of new sensor inputs to generate anticipatory actions. We call this information measure "predictive information" (PI). Findings: Our PI is zero if the organism uses only its reflex reactions. It grows when the organism is able to use other sensor inputs to preempt reflex reactions and is able to replace reflexes by anticipatory reactions. This has been demonstrated with a real robot that had to learn to avoid obstacles. Conclusion: PI is a new measure which is able to quantify anticipatory learning and, in contrast to the Shannon information, is calculated only at the inputs of an agent. This information measure has been successfully applied to a simple robot task but its application is neither limited to a certain task nor to a certain learning rule. Keywords: Closed loop system, information measure, differential Hebbian learning, reactive vs proactive systems . About the journal: Constructivist Foundations (CF) is an independent academic peer-reviewed e-journal without commercial interests. Its aim is to promote scientific foundations and applications of constructivist sciences, to weed out pseudoscientific claims and to base constructivist sciences on sound scientific foundations, which do not equal the scientific method with objectivist claims. The journal is concerned with the interdisciplinary study of all forms of constructivist sciences, especially radical constructivism, cybersemiotics, enactive cognitive science, epistemic structuring of experience, second order cybernetics, the theory of autopoietic systems, etc. -------------------- Apologies for mutiple postings. Regards /Bernd Porr -- www: http://www.berndporr.me.uk/ http://www.linux-usb-daq.co.uk/ Mobile: +44 (0)7840 340069 Work: +44 (0)141 330 5237 University of Glasgow Department of Electronics & Electrical Engineering Room 519, Rankine Building, Oakfield Avenue, Glasgow, G12 8LT From carl at tuebingen.mpg.de Wed Mar 29 08:40:15 2006 From: carl at tuebingen.mpg.de (Carl Edward Rasmussen) Date: Wed, 29 Mar 2006 15:40:15 +0200 (CEST) Subject: Connectionists: Matlab code for Gaussian process prediction Message-ID: We would like to announce the availability of matlab code implementing the main algorithms from our recent book "Gaussian Processes for Machine Learning" from MIT Press. The code is available via: http://www.GaussianProcess.org/gpml The programs implement regression and classification. Standard regression as well as some sparse approximations are provided. Binary classification is implemented using both the Laplace approximation and the Expectation Propagation algorithm. The code supports a variety of different covariance functions and learning of hyperparamters using the marginal likelihood. Demo scripts are provided to illustrate the use of the functions. Carl Edward Rasmussen & Chris Williams From king at cse.cuhk.edu.hk Fri Mar 31 04:47:28 2006 From: king at cse.cuhk.edu.hk (Irwin King) Date: Fri, 31 Mar 2006 17:47:28 +0800 Subject: Connectionists: CFP: ICONIP2006 Call For Papers & Call For Proposals Message-ID: ******************************************************************** Upon the requests from numerous authors, the Organizing Committee of ICONIP2006 has decided to extend the deadline for papers and Special Session proposals to April 21, 2006. In addition to the multi-volume proceedings published by Springer's Lecture Notes in Computer Science (LNCS), the following journals will have special issues featuring selected papers from ICONIP2006: * Neurocomputing * Journal of Intelligent Information Systems * Pattern Analysis and Applications * International Journal of Pattern Recognition and Artificial Intelligence * Neural Information Processing-Letters & Reviews ******************************************************************** I C O N I P 2 0 0 6 D E A D L I N E E X T E N D E D CALL FOR PAPERS AND PROPOSALS 13th International Conference on Neural Information Processing (ICONIP2006) Hong Kong Convention and Exhibition Centre, Hong Kong October 3-6, 2006 http://www.iconip2006.org/ http://iconip2006.cse.cuhk.edu.hk/ Paper Submission Site https://conference.cse.cuhk.edu.hk/iconip2006/login.php ******************************************************************** The Thirteenth International Conference on Neural Information Processing (ICONIP2006) sponsored by the Asia Pacific Neural Network Assembly (APNNA) and organized by The Chinese University of Hong Kong, will be held in Hong Kong on October 3-6, 2006. You are invited to visit this vibrant and dynamic metropolitan to share the progress and research in neural computation, statistical processing, machine learning, and other related topics. ICONIP2006 will include plenary speakers, invited talks, tutorials, special sessions, as well as highly selected oral and poster presentations of refereed papers. In addition, conference social events along with other local attractions will promote interactions among conference delegates. ******************************************************************** Important Dates Paper submission deadline (extended): April 21, 2006 Special session proposal (extended): April 21, 2006 Tutorial proposal May 20, 2006 Workshop proposal June 10, 2006 Notification of acceptance: June 1, 2006 Final paper submission: July 1, 2006 ******************************************************************** Awards & Grants Best Paper Awards and Best Student Paper Awards will be given at ICONIP2006 based on the reviews and presentations at the conference. Travel grants will also be given to a number of selected student registrants at the conference. ******************************************************************** Proposals Submission For paper submission: https://conference.cse.cuhk.edu.hk/iconip2006/login.php For those who are interested in Speical Sessions, please find the related materials from the link below: http://iconip2006.cse.cuhk.edu.hk/callforproposals/CFPSS For those who are interested in Tutorial Proposoals, please find the related materials from the link below: http://iconip2006.cse.cuhk.edu.hk/callforproposals/CFPTuto For those who are interested in Workshop Proposoals, please find the related materials from the link below: http://iconip2006.cse.cuhk.edu.hk/callforproposals/CFPworkshop ******************************************************************** Paper Submission Authors are invited to submit research and application papers representing original, previously unpublished work to ICONIP2006. Submissions are solicited in all areas of neural information processing, including (but not limited to) the following: Neural Network Theory & Models -Mathematics of neural networks; -Advanced learning algorithms/models; -Neurodynamics; -Stability and convergence analysis; -Feedforward neural networks; -Recurrent neural networks; -Evolving neural networks; -Self-organizing networks; -Reinforcement learning; -PCA and ICA; -EM algorithm and mixture models; -Ensemble learning; -Kernel methods and support vector machine Computational Neuroscience and Cognitive Science -Models of neurons; -Simulation of neurons, networks, and systems; -Neuroinformatics; -Cognitive learning and memory; -Attention and consciousness; -Language; -Emotion and motivation; -Perceptual systems Neural Network Applications -Vision and image processing; -Pattern recognition; -Auditory processing; -Speech processing/recognition; -Robotics and control; -Biometric and security; -Time-series prediction; -Financial engineering; -Telecommunication; -Manufacturing systems; -Bioinformatics; -Data mining/Web mining; -Multimedia and information processing Hybrid Systems and Hardware -Fuzzy neural systems; -Hybrid systems; -Genetic algorithms; -Evolutionary programming; -Reconfigurable systems; -Hardware implementation Web links to supplementary materials (e.g., software, audio, video, etc.) in the manuscripts are encouraged. However, the manuscript must be self-contained and reviewers will not be required to review the supplementary materials. Accepted papers will be published in Lecture Notes in Computer Science (LNCS) by Springer-Verlag. In addition, selected papers from ICONIP2006 will be published with expansion after further review in speical issues of Neurocomputing, Journal of Intelligent Information Systems, Pattern Analysis and Applications, International Journal of Pattern Recognition and Artificial Intelligence, and Neural Information Processing-Letters & Reviews. ******************************************************************** Paper Format Submissions must not exceed 10 pages in length in the Acrobat PDF format, including figures, tables, references, and appendices, using a font no smaller than 10 point. The final version of accepted papers may be up to 12 pages with extra page charges. All submissions must strictly follow the LNCS style, which is available at: under "Information for LNCS Authors". Submissions violating these requirements will not be considered. ******************************************************************** Honorary Co-Chairs ------------------ Lei Xu Shun-ichi Amari General Co-Chairs ----------------- Jun Wang Laiwan Chan Advisory Board -------------- Walter J. Freeman; Toshio Fukuda; Kunihiko Fukushima; Tom Gedeon; Zhen-ya He; Nik Kasabov; Okyay Kaynak; Anthony Kuh; Sun-Yuan Kung; Soo-Young Lee; Chin-Teng Lin; Erkki Oja; Nikhil R. Pal; Marios M. Polycarpou; Shiro Usui; Benjamin W. Wah; Lipo Wang; Shoujue Wang; Paul J. Werbos; You-Shou Wu; Donald C. Wunsch II; Xin Yao; Yixin Zhong; Jacek M. Zurada Program Committee ----------------- Irwin King DeLiang Wang Shigeo Abe; Peter Andras; Sabri Arik; Ke Chen; Liang Chen; Zheru Chi; Sung-Bae Cho; Sungzoon Cho; Andrzej Cichocki; Chuangyin Dang; Takeshi Furuhashi; Artur d'Avila Garcez; Daniel W.C. Ho; Sanqing Hu; Guang-Bin Huang; Kaizhu Huang; James Tin-Yau Kwok; James Lam; Minho Lee; Xun Liang; Xiaofeng Liao; Chih-Jen Lin; Xiuwen Liu; Wenlian Lu; Jinwen Ma; Sushmita Mitra; Paul S. Pang; Jagath Rajapakse; Michael Small; Michael Stiber; P. N. Suganthan; Fuchun Sun; Ron Sun; Johan A.K. Suykens; Norikazu Takahashi; Michel Verleysen; Si Wu; Hujun Yin; Gerson Zaverucha Organizing Committee -------------------- Man-Wai Mak (Organizing Chair) Kai-Pui Lam (Finance and Registration Chair) James Kwok (Workshop and Tutorial Chair) Frank H. Leung (Publications and Special Sessions Co-Chairs) Jianwei Zhang (Publications and Special Sessions Co-Chairs) Chris C. Yang (Publicity Co-Chairs) Jeffrey Xu Yu (Publicity Co-Chairs) Derong Liu (Publicity Co-Chairs) Wlodzislaw Duch (Publicity Co-Chairs) Andrew Chi-Sing Leung (Local Arrangements Co-Chairs) Eric Yu (Local Arrangements Co-Chairs) ******************************************************************** Confirmed Plenary Speakers Shun-ichi Amari, RIKEN Brain Science Institute, Japan More to come ... ******************************************************************** Enquiry and Information For general questions, please contact: ICONIP2006 Secretariat Dept. of Computer Science & Engineering The Chinese University of Hong Kong Shatin, NT, Hong Kong http://www.iconip2006.org/ E-mail: iconip06 at cse.cuhk.edu.hk Phone: +852 2609 8444 Fax: +852 2603 5420 For questions related to technical programs, please contact: Irwin King: king at cse.cuhk.edu.hk For questions related to workshops and tutorials, please contact: James Kwok: jamesk at cs.ust.hk For questions related to special sessions, please contact: Frank H. Leung: enfrank at inet.polyu.edu.hk For questions related to organization, please contact: Manwai Mak: enmwmak at polyu.edu.hk From juergen at idsia.ch Fri Mar 31 03:17:15 2006 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Fri, 31 Mar 2006 10:17:15 +0200 Subject: Connectionists: source code of Optimal Ordered Problem Solver Message-ID: Due to frequent requests, source code for the experiments described in "Optimal Ordered Problem Solver. Machine Learning 54, 211-254, 2004" was released under the terms of the GNU public license: http://www.idsia.ch/~juergen/oops.html -Juergen From p.husbands at sussex.ac.uk Fri Mar 31 08:12:58 2006 From: p.husbands at sussex.ac.uk (Phil Husbands) Date: Fri, 31 Mar 2006 14:12:58 +0100 Subject: Connectionists: Funded PhD places at Sussex University Message-ID: Funded PhD places are available in the department of Informatics, University of Sussex. Studentships are available in various areas of Computer Science, AI and Cognitive Science including adaptive systems, bioinformatics, computational neuroscience and machine learning. For further details, including how to apply, see Funded places are also available on our MSc in Evolutionary and Adaptive Systems. From tt at cs.dal.ca Thu Mar 30 08:06:42 2006 From: tt at cs.dal.ca (Thomas Trappenberg) Date: Thu, 30 Mar 2006 09:06:42 -0400 Subject: Connectionists: Faculty positions in Computer Science at Dalhousie University, Canada Message-ID: <20060330130642.C8070B00B@mail.cs.dal.ca> Colleagues, I would like to bring to your attention that we have openings for outstanding researchers at the Faculty of Computer Science at Dalhousie University in Halifax, Canada. Halifax is a wonderful city to live in and Dalhousie University is a major University in Atlantic Canada with active research programs in Computer Science, Neuroscience and Cognitive Science (among others). The openings are for prestigious Canada Research Chairs, either at a junior level (Ph.D. < 7 years), or outstanding senior level. See http://www.cs.dal.ca/news/news-1282.shtml or contact me if you have any questions. Regards, Thomas Trappenberg Faculty of Computer Science Dalhousie University 6050 University Avenue Halifax, NS B3H 1W5 Canada From ted.carnevale at yale.edu Wed Mar 1 18:12:19 2006 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Wed, 01 Mar 2006 18:12:19 -0500 Subject: Connectionists: 2006 NEURON Simulator Meeting Message-ID: <44062A53.4050203@yale.edu> What: the 2006 NEURON Simulator Meeting When: 9 AM Friday - Noon Sunday, May 5-7, 2006 Where: The University of Texas at Austin Registration is now open for the 2006 NEURON Simulator Meeting. The purpose of this meeting is to bring together people who are interested in using computational modeling in neuroscience research and education--especially current users of NEURON, and others who are interested in using it--in order to: * share knowledge about technical aspects of computational modeling * keep informed about the latest advances and "best practices" in the use of NEURON * encourage participation in NEURON's development * stimulate communication and collaboration This conference will alternate between single track sessions for presentations and discussions on topics of general interest, and multiple track breakout sessions for smaller group interactions. We invite proposals for talks, symposia, tutorials, and workshops (see "Proposals Invited" below). Registration is limited to 50 individuals on a first-come, first serve basis. For more information see http://www.utexas.edu/neuroscience/NEURON2006/nsm2006.html Proposals Invited We invite participants to propose and be responsible for talks, symposia, tutorials, or workshops. See http://www.utexas.edu/neuroscience/NEURON2006/nsm2006.html for more information. --Ted From g.goodhill at imb.uq.edu.au Wed Mar 1 22:00:06 2006 From: g.goodhill at imb.uq.edu.au (Geoffrey Goodhill) Date: Thu, 02 Mar 2006 13:00:06 +1000 Subject: Connectionists: Submit to Network via Manuscript Central Message-ID: <44065FB6.4030400@imb.uq.edu.au> Dear Connectionists, I am delighted to announce that the journal "Network: Computation in Neural Systems" is being relaunched by its new publishers, Taylor & Francis. As part of this the journal now has an online manuscript submission site based on Manuscript Central, which can be found at http://mc.manuscriptcentral.com/ncns This is linked from the journal's new homepage at http://www.tandf.co.uk/journals/titles/0954898X.asp Below is the Editorial that will appear in the March 2006 issue introducing the new Network. Among other things it outlines some new categories of papers Network will now consider. The new contact address for the Editorial Office is ncns at uq.edu.au. HOWEVER, during the transition period, please continue to send resubmissions of existing manuscripts and any related correspondence to net at tandf.co.uk as before. Regards, Geoffrey Goodhill Editor-in-Chief, Network: Computation in Neural Systems --------------------------------------------------------------- EDITORIAL: WELCOME TO THE NEW NETWORK Computational approaches are now accepted as useful, important, and sometimes even indispensible in most areas of neuroscience. It has become common to see papers in primarily experimental journals "garnished" by a modelling component. However, sometimes such journals are not equipped to do justice to the many details that are required to fully evaluate a mathematical/computational model. The role of Network is to present models in neuroscience which one can trust have been rigorously evaulated not just for their relevance to biology, but also for their mathematical and computational correctness, novelty, and elegance. It provides an indispensible port of call for both experimentalists and theoreticians who are eager to keep abreast of the latest developments in this fast-moving field. In July 2005 I was honoured to step into the large shoes of the previous Editor-in-Chief, David Willshaw. David's history is almost the modern history of computational neuroscience. He was there "battling", as they say in Australia, when theoretical approaches in some areas were often considered not just dispensible but downright dangerous. However he persevered and ultimately triumphed, establishing many of the basic theoretical foundations for areas including associative memory and topographic maps. Since 1998 he has devoted a huge amount of his time to the success of Network, for which I for one am extremely grateful. I now have the great pleasure of introducing you to a new era of Network. Taylor & Francis, the journal's new publishers, have made a considerable investment in relaunching the journal with a new design and a new online submission system based on Manuscript Central. To the already impressively staffed Editorial Board we have newly recruited two eminent senior neuroscientists (Chuck Stevens and Mu-ming Poo), and two new rising stars (Max Riesenhuber and Nick Brunel). We have also introduced a number of new categories of articles we will consider for publication. In addition to regular Articles, Network has a distinguished tradition of disseminating more lengthy Reviews. Besides continuing with these, we will now regularly publish Editorials, Viewpoints, and Historical Perspectives. Editorials will usually be contributed by a member of the Editorial Board, and will provide a "bully pulpit" for these leaders in the field to discuss issues they feel are of importance to the future of computational neuroscience. Viewpoints allow a more personal view of an area than is appropriate for a Review, and will often be opinionated and controversial. Occasional Historical Perspectives will briefly outline people and/or events that have been crucial in the past development of computational neuroscience, but which are perhaps not as well known or understood by neuroscientists at large as they should be. Usually Reviews, Viewpoints and Historical Perspectives will be invited by the Editorial Office. However unsolicted proposals will also be considered, which should consist in the first instance of a 1-page summary sent to ncns at uq.edu.au. Since becoming Editor-in-Chief I have been extremely impressed by both the commitment and enthusiasm of the Editorial Board, and the very thoughtful and thorough evaluations generously provided by many of our reviewers. I offer my most heartfelt thanks to everyone who contributes their valuable time to protecting and developing the scientific quality of the papers we publish. Besides taking on the job of Editor I recently moved my own lab to the University of Queensland, and my new responsibilities to Network seem ideally served by my joint appointment between the School of Physical Sciences and the new Queensland Brain Institute. I am looking forward with relish and excitement to the development of Network, and of computational neuroscience more generally, in the years to come. Geoffrey Goodhill, Editor-in-Chief University of Queensland, Australia From g.goodhill at imb.uq.edu.au Wed Mar 1 22:03:34 2006 From: g.goodhill at imb.uq.edu.au (Geoffrey Goodhill) Date: Thu, 02 Mar 2006 13:03:34 +1000 Subject: Connectionists: Workshop on Mathematical and Computational Neuroscience Message-ID: <44066086.9080406@imb.uq.edu.au> Dear Connectionists, The Queensland Brain Institute, the Australian Mathematical Sciences Institute, and Network: Computation in Neural Systems invite you to attend the following event: INAUGURAL QUEENSLAND BRAIN INSTITUTE WORKSHOP ON MATHEMATICAL AND COMPUTATIONAL NEUROSCIENCE August 13-14th, 2006. Hillstone St Lucia (www.hillstonestlucia.com.au) Brisbane, Australia. Speakers include: Shun-ichi Amari (Riken) Peter Dayan (University College London) Zhaoping Li (University College London) Mandyam Srinivasan (Australian National University) Peter Robinson (University of Sydney) Anthony Burkitt (Bionic Ear Institute, Melbourne) Kevin Burrage (University of Queensland) Geoffrey Goodhill (University of Queensland) Registration: AU$100 (Students AU$80). Abstract submissions are invited from registered participants for poster presentation. Submission deadline June 1st 2006. For further details please see http://public.qbi.uq.edu.au/cnw Some travel support is available from the Australian Mathematical Sciences Institute for participants from AMSI member organizations. See the above website for more details. Regards, Geoffrey J Goodhill, PhD Associate Professor Queensland Brain Institute, School of Physical Sciences & Institute for Molecular Bioscience University of Queensland St Lucia, QLD 4072, Australia Phone: +61 7 3346 2612 Fax: +61 7 3346 8836 Email: g.goodhill at uq.edu.au http://cns.qbi.uq.edu.au Editor-in-Chief, Network: Computation in Neural Systems From bower at uthscsa.edu Fri Mar 3 17:51:45 2006 From: bower at uthscsa.edu (james Bower) Date: Fri, 03 Mar 2006 16:51:45 -0600 Subject: Connectionists: Liaison Positions in Computational Biology in San Antonio, Texas Message-ID: The University of Texas San Antonio, and the University of Texas Health Science Center in San Antonio, have recently raised several million dollars to establish a facility in computational biology to engage in collaborative research with bench biologists within both institutions. Computational biology in this case is broadly defined, ranging from data-mining and gene sequence analysis to the construction of large scale realistic models of biological systems. The facility, for example, is the home of the GENESIS simulation project (http://www.genesis-sim.org/GENESIS/). The facility already includes staff and faculty who are expert in the technical aspects of computational biology. The Liaison positions offered here (see official announcement below), are intended to add core competence in biological experimentation and interpretation. The primary role of each of the three liaisons will be to serve as the interface between the facility and a number of different individual research laboratories. The ideal candidate is likely someone with a broad experience and interest in biology, who has successfully performed both experimental and computational science. These positions should be of particular interest to comparative studies. Liaisons will be non-tenure track faculty, with the ability to write and manage their own grants, and participate fully as professionals in research collaborations. San Antonio Currently, healthcare and biotechnology industries lead the San Antonio economy with an estimated annual economic impact of over $13 billion while maintaining 100,000 jobs. San Antonio itself is a wonderful place to live with a deep cultural heritage and particularly family friendly. The mean cost of housing is one of the lowest in the United States. Official Job Posting Instructor(s) for Bioinformatics/Computational Biology We are seeking to fill three research faculty positions with the title of Instructor who will be associated with a new Bioinformatics/Computational Biology Core Facility serving both UTHSCSA and UTSA. The primary responsibility of each position will be to foster the development and application of applied computational methodologies within existing individual laboratories and research programs at either or both institutions. Accordingly, each individual can be expected to work with several different laboratories on experimental design, development of analysis plans, and identification of training needs in computational techniques. In doing so, the individuals hired will also work closely with and be supported by the Core Facility's technical staff and associated supervising faculty. Instructor may also be involved in writing grant proposals, general training and instruction, and will play an integral role in planning the further development and extension of the core facility. Minimum requirements for this position are a doctoral degree in a biologically-related scientific discipline and a demonstrated proficiency in experimental design and laboratory technique. Candidates must also be able to demonstrate core competency in computational methods and analytical procedures. These positions are available on either a full- or part-time basis. Currently, the Center for Epidemiology and Biostatistics has 10 doctoral-level faculty and supports several large research programs such as the UTHSCSA/UTSA Bioinformatics/Computational Biology Program, the Children's Cancer Research Institute, the San Antonio Cancer Institute, and the Frederic C. Barter General Clinical Research Center. These programs span basic, translational, clinical and population-based research. Applicants should send current curriculum vitae, a description of research plans, and three letters of reference to: Brad H. Pollock, M.P.H., Ph.D. Professor & Director Center for Epidemiology and Biostatistics The University of Texas Health Science Center at San Antonio MC 7933 7703 Floyd Curl Drive San Antonio, TX 78229-3900 (210) 562-9020 or bpollock at uthscsa.edu All faculty appointments are designated as security sensitive positions. UTHSCSA is an Equal Employment Opportunity/Affirmative Action Employer. -- James M. Bower Ph.D. Research Imaging Center University of Texas Health Science Center at San Antonio 7703 Floyd Curl Drive San Antonio, TX 78284-6240 Cajal Neuroscience Center University of Texas San Antonio Phone: 210 567 8080 Fax: 210 567 8152 From fschwenker at neuro.informatik.uni-ulm.de Thu Mar 2 11:16:18 2006 From: fschwenker at neuro.informatik.uni-ulm.de (Friedhelm Schwenker) Date: Thu, 02 Mar 2006 17:16:18 +0100 Subject: Connectionists: ANNPR 2006 Final CFP and extended deadline Message-ID: <44071A52.6000604@neuro.informatik.uni-ulm.de> [ Apologies for multiple postings ] ************************************************************* !! EXTENDED PAPER SUBMISSION DEADLINE: MARCH 30, 2006 !! ************************************************************* FINAL CALL FOR PAPERS ANNPR 2006 2nd IAPR TC3 International Workshop on Artificial Neural Networks in Pattern Recognition August 31 - September 2 2006 University of Ulm, Reisensburg Castle (Germany) (http://www.informatik.uni-ulm.de/ni/ANNPR06) The workshop proceedings will be published by Springer Verlag (LNAI). Aim of the workshop: ANNPR 2006 follows the success of the first workshop ANNPR 2003 held at the University of Florence, Italy, in September 2003. This 2nd ANNPR workshop will act as a major forum for international researchers and practitioners working in all areas of neural network based pattern recognition to present and discuss the latest research, results, and ideas in these areas. The TC3 "Neural Networks & Computational Intelligence" is one of the 20 technical committees of the International Association on Pattern Recognition (IAPR). The scope of this TC is on all kinds of Computational Intelligence approaches, including artificial neural networks, fuzzy systems, evolutionary computing, with focus on pattern recognition applications. Papers are solicited dealing with neural networks and pattern recognition which emphasize methodological issues arising in applications. They should be related but not limited to the following topics. Methodological issues: - Supervised learning. - Unsupervised learning. - Combination of supervized and unsupervized learning. - Feedforward networks and kernel machines - Recurrent and competitive neural networks. - Hierarchical modular architectures and hybrid systems. - Combination of neural networks and Hidden Markov models. - Multiple classifier systems and ensemble methods. Applications in Pattern Recognition - Image processing and segmentation. - Sensorfusion and multimodal processing. - Feature extraction, dimension reduction. - Clustering and vector quantisation. - Speech and speaker recognition. - Data, text, and web mining. - Bioinformatics. --------------------------------------------------------------------------- Original and unpublished contributions are solicited which include regular papers and extended abstracts. Potential participants should submit a paper describing their work in one of the areas described above. Each regular paper must be accompanied by an abstract summarizing the contribution it makes to the field. Maximum paper length for regular papers is 12 pages in LNCS format. Extended abstracts can have at most four pages. Submission of a paper constitutes a commitment that, if accepted, one or more authors will attend and participate in the workshop. The workshop proceedings will be published in the Springer LNAI series. Electronic submission in camera-ready format is required. Papers must be sent to: Friedhelm Schwenker, Department of Neural Information Processing, University of Ulm (Email: friedhelm.schwenker at uni-ulm.de) --------------------------------------------------------------------------- Important Dates: Paper submission: March 30, 2006 Notification of acceptance: May 15, 2006 Camera ready copies: May 30, 2006 --------------------------------------------------------------------------- Further information: Contact Simone Marinai or Friedhelm Schwenker (Email: annpr2006 at uni-ulm.de) or visit the Workshop web page (http://www.informatik.uni-ulm.de/ni/ANNPR06/). --------------------------------------------------------------------------- General Chair Simone Marinai (University of Florence, Italy) Program Chair Friedhelm Schwenker (University of Ulm, Germany) Program Committee (confirmed members): Shigeo Abe (Kobe University, Japan) Herve Bourlard (IDIAP, Martigny, Switzerland) Horst Bunke (University of Bern, Switzerland) Neamat El Gayar(Cairo University, Egypt) Patrick Gallinari (University Pierre et Marie Curie, Paris, France) Marco Gori (University of Siena, Italy) Barbara Hammer (Technical University of Clausthal, Germany) Tom Heskes (University of Nijmegen, The Netherlands) Jose Manuel Inesta (University of Alicante, Spain) Rudolph Kruse (Otto-von-Guericke University of Magdeburg, Germany) Cheng-Lin Liu (Chinese Academy of Sciences, China) Marco Maggini (University of Siena, Italy) Erkki Oja (Helsinky University of Technology, Finland) Guenther Palm (University of Ulm, Germany) Marcello Pelillo (University Ca Foscari, Venezia, Italy) Raul Rojas (Freie University of Berlin, Germany) Fabio Roli (University of Cagliari, Italy) Ah Chung Tsoi (University of Wollongong, Australia) Michel Verleysen (Catholic University of Louvain, Belgium) Stefan Wermter (University of Sunderland, UK) ----------------------------------------------------- -- ---------------------------------------------------------------------- Dr. Friedhelm Schwenker University of Ulm | email: fschwenker at neuro.informatik.uni-ulm.de Department of Neural | fax: +49-731-50-24156 Information Processing | phone: +49-731-50-24159 D-89069 Ulm (Germany) | www: http://www.informatik.uni-ulm.de/ni/mitarbeiter/FSchwenker.html ---------------------------------------------------------------------- From jose.millan at jrc.it Thu Mar 2 12:09:04 2006 From: jose.millan at jrc.it (jose.millan@jrc.it) Date: Thu, 2 Mar 2006 18:09:04 +0100 Subject: Connectionists: Open position for Senior Researcher in Machine Learning at IDIAP Research Inst Message-ID: <4401D1930000023D@cheetah-1.jrc.it> The IDIAP Research Institute (www.idiap.ch) is currently seeking one talented senior researcher in machine learning with a proven record of high level research and project management, and whose interests are aligned with our existing strengths in speech processing, computer vision, biometric authentication, and multimedia data mining. A candidate with these strengths will be expected to play a leading role in the research, teaching ans strategic development of the Institute. Most of IDIAP's research ativities take place in the framework of National long term research initiatives such as the National Centre of Competence in Research (NCCR) on "Interactive Multimodal Information Management" (IM2, see www.im2.ch) or large European projects such as "Augmented Multi-party Interaction" (AMI, see www.amiproject.org). Specific Knowledge/Skills: * PhD in electrical engineering, computer science, signal processing, mathematics, statistics, or relevant discipline with a minimum of 5 years (post-PhD) experience. * Strong record of research and innovation in the area of pattern recognition and machine learning (incl. HMM, ANN,SVM, kernel approaches, Gaussian processes). * Significant experience in software development, including C/C++. * Experience with large real world audio and video data sets is desirable. * Experience in project management and supervision of researchers, including PhD students. * Good organizational and communication skills, both written and oral. * Ability to interact well with international, multi-disciplinary, R&D teams. Initiated in 1991, and supported by the Swiss Federal Government, the State of Valais, and the City of Martigny, IDIAP (www.idiap.ch) is an independent, nonprofit research institute located in Martigny (at the edge of the Swiss Alps), and is affiliated with EPFL (Ecole Polytechnique Federale de Lausanne) and the University of Geneva. See http://www.idiap.ch/pages/press/faq.pdf for more information and FAQs. IDIAP is building a culturally diverse research community and strongly encourages applications from female and minority candidates. Prospective candidates should apply with a cover letter, CV, statement of research interests and accomplishments, and names and email addresses of 3 references. Please sent these to jobs at idiap.ch, with a clear reference in subject header to "senior position in machine learning"). More information can also be obtained by contacting Prof. Herve Bourlard (bourlard at idiap.ch), Director of IDIAP. Start dates are flexible, but applications received by June 30, 2006, will receive full consideration. See http://www.idiap.ch/jobs.php for other positions available at IDIAP. -- Prof. Herv? Bourlard Director, IDIAP Research Institute, www.idiap.ch Professor, Swiss Federal Institute of Technology at Lausanne (EPFL), www.epfl.ch P.O. Box 592 Rue du Simplon, 4 CH-1920 Martigny, Switzerland Tel: +41-27-721.77.20 Mobile: +41-79-436.00.35 Fax: +41-27-721.77.12 Email: bourlard at idiap.ch http://www.idiap.ch/~bourlard From haeusler at igi.tu-graz.ac.at Fri Mar 3 05:44:16 2006 From: haeusler at igi.tu-graz.ac.at (Stefan Haeusler) Date: Fri, 03 Mar 2006 11:44:16 +0100 Subject: Connectionists: paper by Haeusler and Maass on detailed cortical microcircuit models Message-ID: <44081E00.9080105@igi.tu-graz.ac.at> The paper "A statistical analysis of information processing properties of lamina-specific cortical microcircuit models" by Stefan Haeusler, and Wolfgang Maass (to appear in Cerebral Cortex, 2006) is now available at http://cercor.oxfordjournals.org/cgi/reprint/bhj132 ABSTRACT: A major challenge for computational neuroscience is to understand the computational function of lamina-specific synaptic connection patterns in stereotypical cortical microcircuits. Previous work on this problem had focused on hypothesized specific computational roles of individual layers and connections between layers, and had tested these hypotheses through simulations of abstract neural network models. We approach this problem by studying instead the dynamical system defined by more realistic cortical microcircuit models as a whole, and by investigating the in fluence which its laminar structure has on the transmission and fusion of information within this dynamical system. The circuit models that we examine consist of Hodgkin-Huxley neurons with dynamic synapses, based on detailed data from [Thomson et al., 2002, Markram et al., 1998] and [Gupta et al., 2000]. We investigate to what extent this cortical microcircuit template supports the accumulation and fusion of information contained in generic spike inputs into layer 4 and layers 2/3, and how well it makes this information accessible to projection neurons in layers 2/3 and layer 5. We exhibit specific computational advantages of such data-based lamina-specific cortical microcircuit model by comparing its performance with various types of control models that have the same components and the same global statistics of neurons and synaptic connections, but are missing the lamina-specific structure of real cortical microcircuits. We conclude that computer simulations of detailed lamina-specific cortical microcircuit models provide new insight into computational consequences of anatomical and physiological data. Stefan Haeusler From derdogmus at ieee.org Wed Mar 1 14:39:45 2006 From: derdogmus at ieee.org (Deniz Erdogmus) Date: Wed, 01 Mar 2006 11:39:45 -0800 Subject: Connectionists: MLSP 2006 Data Analysis Competition extended deadline March 31st Message-ID: <4405F881.4000601@ieee.org> Dear Colleagues, I would like to bring to your attention the MLSP 2006 Data Analysis Competition announced at the following website: http://mlsp2006.conwiz.dk/index.php?id=18 The extended submission deadline for the competition is March 31st. If you have already submitted your entries, please feel free to send in revisions. The competition involves three separate problems that will be evaluated independently: 1) Large-scale, ill-conditioned, small-sample ICA 2) fMRI image processing 3) MEG denoising The winners in each category will be invited to submit papers to the Machine Learning for Signal Processing Workshop, as well as a follow-up journal special issue. Regards, Deniz -- 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.csee.ogi.edu/~deniz derdogmus at ieee.org From kampis at axelero.hu Sun Mar 5 12:10:33 2006 From: kampis at axelero.hu (Kampis) Date: Sun, 5 Mar 2006 18:10:33 +0100 Subject: Connectionists: Reminder: Budapest Semester in Cognitive Science 2006 Message-ID: <00a501c64077$bbd93ce0$0e01a8c0@kampis> [Sorry for cross-posting -- please forward to students] -------------------------------------------------------------- This is a reminder about the Budapest Semester in Cognitive Science (or BSCS, http://hps.elte.hu/BSCS) and its Call for Students for 2006. # We have a modified deadline of *May 15, 2006*. # Enclosed pls find a NEW poster (for high res., visit Web site). # Application procedure as seen on the Web site. Courses and teachers in 2006 include: Cognitive Neuroscience Professor John Bickle, UC (USA) Dynamic Brain Modeling Professor Peter Erdi, KCollege (USA) Consciousness Professor Olga Markic, U Ljubljana (Slovenia) Phil. of Mind Professor Lilia Gurova, NBU (Bulgaria) Cognitive Psychology Professor Giselher Guttmann, U Vienna (Austria) and also from Hungary: Foundations of Cogsci Professor George Kampis, ELTE Cognitive Linguistics Professor Laszlo Komlosi, PTE Phil. of Language Professor Gabor Forrai, ME Neural Networks Dr. Fulop Bazso, KFKI BSCS is a one-semester study abroad program run by the Hungarian Foundation in Cognitive Science (www.makog.hu). We welcome US and international students. Fellowships available in proven need. Send all inquiries to jhegedus at kzoo.edu (US Coordinator) or to George Kampis General Director gk at hps.elte.hu http://hps.elte.hu/~kampis From d.cornford at aston.ac.uk Mon Mar 6 04:24:21 2006 From: d.cornford at aston.ac.uk (Dan Cornford) Date: Mon, 06 Mar 2006 09:24:21 +0000 Subject: Connectionists: Research Jobs: Postdoc and PhD's in variational Bayesian inference for large dynamic models Message-ID: <440BFFC5.5090000@aston.ac.uk> POSTDOC: 3 years, 5 months We are looking for an outstanding postdoctoral research fellow to work on the VISDEM project, a collaboration between Aston, Southampton, Surrey Universities and the Met Office. The VISDEM project will look at the creation of novel frameworks for data assimilation (combining partial differential euqation based model with observations, i.e. better Kalman filtering / smoothing for non-linear systems) and will extend recently developed methods from statistical physics and machine learning to large stochastic dynamic systems. Working with Dr Dan Cornford, and a project student at Aston, you will take the theoretical developments from the Southampton team, led by Professor Manfred Opper and Professor John Shaw-Taylor, and apply these to a range of realistic stochastic dynamic models which have similar properties to real atmospheric models. In particular you will assist in creating a novel variational Bayesian approach to inference within realistic stochastic dynamic models. You will develop novel computational methods for space-time Gaussian processes, and also apply these to real systems, including the case with state dependent (multiplicative) model error. You will also work on the development of the hyper-parameter estimation for unknowns such as the variance of the forcing noise that arises from model error. The project is ambitious and exciting; we have a strong team and are looking for an experienced and highly motivated researcher to take the project forward. Applicants should have excellent mathematical and computational skills and be able to communicate effectively. A background in theoretical physics, mathematics, machine learning or equivalent is required. The post holder is expected to start on or before the 1 August 2006. The post is fixed term for 3 years 5 months. A little more information can be found on the rather temporary: http://www.ncrg.aston.ac.uk/~cornfosd/VISDEM/ web page, but for detailed information on the project please email me at d.cornford at aston.ac.uk Application forms etc can be found at: http://www.aston.ac.uk/staff/hr/recruitment/academicresearch/R0637-advert.jsp PHD's: 3.5 years, one at enhanced stipend. There are also a range of funded PhD studentships available within the NCRG at Aston, including a studentship on the VISDEM project which will be looking at the evaluation of the variational Bayesian methods in comparison with state of the art approaches to data assimilation in large stochastic dynamic models. A related MUCM (Managing Uncertainty in Complex Models) PhD studentship is also available on an enhanced stipend, which will look at issues of dimension reduction in large complex models, particularly focussing on the input dimension. Details of the PhD studentships can be found at: http://www.ncrg.aston.ac.uk/studentships/ Any questions feel free to email me, cheers Dan -- Dr Dan Cornford tel: +44 (0)121 204 3451 Lecturer in Computer Science email: d.cornford at aston.ac.uk NCRG, Aston University Birmigham B4 7ET, UK From tom.ziemke at his.se Mon Mar 6 08:24:18 2006 From: tom.ziemke at his.se (Tom Ziemke) Date: Mon, 06 Mar 2006 14:24:18 +0100 Subject: Connectionists: Two postdoc positions in cognitive/emotional robotics Message-ID: <440C3802.5020001@his.se> Applications are invited for two postdoc positions in cognitive/ emotional robotics at the University of Skovde, Sweden. These positions are part of a four-year European research project on bio-inspired cognitive/emotional robotics (www.his.se/icea, Jan 2006 - Dec 2009). The primary aim of the ICEA project is to develop a cognitive systems architecture integrating cognitive, emotional and bioregulatory (self-maintenance) mechanisms, based on the architecture and physiology of the mammalian brain. The two postdoc positions are focused on developing robot/neural net models of (1) the role of anticipation, representation and emotion in agent-environment interaction, (2) the interaction between cognitive and emotional mechanisms. The application deadlines are March 20 and April 18, respectively. For further information and detailed application instructions see: * position 1 (deadline March 20): - http://www.career.edu/index.php?post_id=1081 - http://www.his.se/templates/vanligwebbsida1.aspx?id=24698 * position 2 (deadline April 18): - http://www.career.edu/index.php?post_id=1105 - http://www.his.se/templates/vanligwebbsida1.aspx?id=24811 Starting date (both cases): spring/summer 2006 (as soon as possible). Informal inquiries can be directed to Tom Ziemke (tom.ziemke at his.se). From ken at neurotheory.columbia.edu Mon Mar 6 13:53:04 2006 From: ken at neurotheory.columbia.edu (Ken Miller) Date: Mon, 6 Mar 2006 13:53:04 -0500 Subject: Connectionists: Theoretical Neuroscience Faculty Recruitment, Columbia University Message-ID: <17420.34064.73173.682828@neurotheory.columbia.edu> Theoretical Neuroscience Faculty Recruitment The Center for Theoretical Neuroscience at Columbia University (http://www.neurotheory.columbia.edu) is recruiting for a faculty position in theoretical and computational neuroscience. Candidates who apply mathematical analysis and computer simulation to topics in neuroscience at levels ranging from cellular to systems and cognitive are urged to apply. We encourage applications for a tenure-track Assistant Professor position, but will also consider applications from more senior investigators for tenured positions. The Center for Theoretical Neuroscience is a highly interactive group of faculty (4 full-time and 1 part-time, at this point), postdoctoral researchers and graduate students who also interact extensively with experimentalists within Columbia's well-known program in neurobiology and behavior as well as with members of the scientific departments at the Morningside Heights campus. These interactions will be augmented in the upcoming years by the new Columbia Neuroscience Initiative, which is hiring a significant number of new faculty in the area of circuit-level neuroscience. Applications for this position are requested by March 31, 2006. A CV, cover letter including statement of interests, and three letters of reference under separate cover should be emailed to Andrew Fink, andrew at neurotheory.columbia.edu. In addition, please mail a hard copy of these documents to: Theoretical Neuroscience Search c/o: Andrew Fink Columbia University College of Physicians and Surgeons Kolb Research Annex 1051 Riverside Drive New York, NY 10032-2695 Columbia University takes affirmative action to ensure equal opportunity. From casutton at cs.umass.edu Tue Mar 7 20:45:05 2006 From: casutton at cs.umass.edu (Charles Sutton) Date: Tue, 7 Mar 2006 20:45:05 -0500 Subject: Connectionists: Announcing new tutorial on conditional random fields Message-ID: Andrew McCallum and I have written a new tutorial on conditional random fields: An Introduction to Conditional Random Fields for Relational Learning. Charles Sutton and Andrew McCallum. In Introduction to Statistical Relational Learning. Edited by Lise Getoor and Ben Taskar. To appear. http://www.cs.umass.edu/~casutton/publications/crf-tutorial.pdf It describes linear-chain CRFs, CRFs over general graphs, learning with latent variables, and many implementation concerns that arise when applying CRFs in practice. It also presents a case study of applying a loopy CRF to a practical natural language problem. Best wishes, Charles From terry at salk.edu Sun Mar 5 22:45:57 2006 From: terry at salk.edu (Terry Sejnowski) Date: Sun, 05 Mar 2006 19:45:57 -0800 Subject: Connectionists: NETtalk tape Message-ID: In response to many requests for a NETtalk demonstration tape for teaching, there is an MP3 file of NETalk for download at: http://www.cnl.salk.edu/ParallelNetsPronounce/index.php PDF files for the NETtalk paper and all of my publications are also available at: http://papers.cnl.salk.edu/ These include: Ackley, D. H.; Hinton, G. E.; Sejnowski, T. J.; A Learning Algorithm for Boltzmann Machines, Cognitive Science, 9, 147-169, 1985 Steriade, M.; McCormick, D. A.; Sejnowski, T. J.; Thalamocortical Oscillations in the Sleeping and Aroused Brain, Science, 262, 679-685, 1993 Bell, A. J.; Sejnowski, T. J.; An Information-Maximization Approach to Blind Separation and Blind Deconvolution, Neural Computation, 7, 1129-1159, 1995 Churchland, P. S.; Ramachandran, V. S.; Sejnowski, T. J.; A Critique of Pure Vision Koch, C.; Davis, J.; (Eds.), In: Large-Scale Neuronal Theories of the Brain, Cambridge, MA: MIT Press, 23-60, 1994 Mainen, Z. F.; Sejnowski, T. J.; Reliability of Spike Timing in Neocortical Neurons, Science, 268, 1503-1506, 1995 Montague, P. R.; Dayan, P.; Sejnowski, T. J.; A Framework for Mesencephalic Dopamine Systems Based on Predictive Hebbian Learning, Journal of Neuroscience, 16(5), 1936-1947, 1996 Sejnowski, T. J.; Destexhe, A.; Why Do We Sleep?, Brain Research, 886 (1-2) 208-223, 2000 Salinas, E.; Sejnowski, T. J.; Correlated Neuronal Activity and the Flow of Neural Information, Nature Reviews Neuroscience, 2, 539-550, 2001 Laughlin, S. B.; Sejnowski, T. J.; Communication in Neuronal Networks, Science, 301, 1870-1874, 2003 Coggan, J. S.; Bartol, T. M. Jr.; Esquenazi, E. I.; Stiles, J. R.; Lamont, S.; Martone, M. E.; Berg, D. K.; Ellisman, M. H.; Sejnowski, T. J.; Evidence for Ectopic Neurotransmission at a Neuronal Synapse, Science, 39, 446-451, 2005 Terry ----- From andreas at cs.ntua.gr Wed Mar 8 07:42:10 2006 From: andreas at cs.ntua.gr (andreas) Date: Wed, 8 Mar 2006 14:42:10 +0200 Subject: Connectionists: ICANN 2006 Call for papers and deadline extension Message-ID: <200603081242.k28CgDfU011583@theseas.softlab.ece.ntua.gr> Call for Papers International Conference on Artificial Neural Networks (ICANN 06) *************** The deadline for submission of papers (abstract + full paper) to regular sessions has been extended to 31 March 2006 *************** 10-14 September 2006 Holiday Inn Hotel, Athens, Greece ************Conference Framework************ The 16th International Conference on Artificial Neural Networks, ICANN 2006, will be held from September 10 to September 14, 2006, at the Holiday Inn Hotel, Athens Greece. ICANN is an annual conference organized by the European Neural Network Society in cooperation with the International Neural Network Society, Japanese Neural Network Society, and the IEEE Computational Intelligence Society, and is a premier European event in all topics related to neural networks. ICANN 2006 (www.icann2006.org) welcomes contributions on the theory, algorithms, applications and implementations in the following broad areas: ? Computational neuroscience; ? Connectionist cognitive science; ? Data analysis and pattern recognition; ? Graphical networks models, Bayesian networks; ? Hardware implementations and embedded systems; ? Neural and hybrid architectures and learning algorithms; ? Neural control, reinforcement learning and robotics applications; ? Neuroinformatics; ? Neural dynamics and complex systems; ? Real world applications; ? Robotics, control, planning; ? Signal and time series processing; ? Self-organization; ? Vision and image processing; ? Web semantics; ? Intelligent Multimedia and the Semantic Web. Ideas and nominations for interesting tutorials, special sessions, workshops and experts willing to organize various session tracks are called for. Most active experts will be included in the scientific committee of the conference. Proceedings of ICANN will be published in Springer's "Lecture Notes in Computer Science". Paper length is restricted to a maximum of 10 pages, including figures. ************Deadlines and Conference dates************ 06.01 Submission page opens 31.03 End of submission of papers (abstract+full paper) to regular sessions 31.03 End of submission of papers to special sessions 30.04 Acceptance/rejection notification 15.06 Deadline for camera ready papers 01.07 Deadline for early registration 10.09 Tutorials - first day of the conference 11-13.09 Main part of the conference 14.09 Workshops For further information and/or contacts, send inquiries to Prof. Stefanos Kollias (stefanos at cs.ntua.gr) Prof Andreas Stafylopatis (andreas at cs.ntua.gr) School of Electrical & Computer Engineering National Technical University of Athens 9, Heroon Polytechniou str., 157 80 Zografou, Athens, Greece. General Chair Stefanos Kollias, National Technical University of Athens (NTUA), Greece Co-Chair Andreas Stafylopatis, NTUA, Greece Program Chair Wlodzislaw Duch, Torum, PL & Singapore; ENNS President-elect Erkki Oja, Helsinki, FI; ENNS President Honorary Chair John G. Taylor, Kings College, London, UK; ENNS Past President ************International Program Committee************ ? Peter Andras, U. Newcastle, UK ? Panos Antsaklis, U. N. Dame, USA ? Nikolaos Bourbakis, Wright State Univ., USA ? Peter Erdi, Univ. Budapest, HU & Kalamazoo ? Georg Dorffner, Univ. Wien, AT ? Christophe Garcia, France T?l?com ? Erol Gelenbe, Imperial College London, UK ? Stan Gielen, Univ. Nijmegen, NL ? Nikola Kasabov, Kedri, AUT, NZ ? Janusz Kacprzyk, Warsaw, PL ? Okyay Kaynak, Bogazici Univ., TR ? Chris Koutsougeras, Tulane University, USA ? Thomas Martinetz, Luebeck, DE ? Evangelia Micheli-Tzanakou, Rutgers University, USA ? Lars Niklasson, Sk?vde SE ? Marios Polycarpou, Univ. of Cyprus ? Demetris Psaltis, Caltech, USA ? Olli Simula, Espoo, FI ? Alessandro Sperduti, U.Padova, IT ? Lefteris Tsoukalas, Purdue Uni, USA ? Michel Verleysen, Louvain-la-Neuve, BE ? Alessandro Villa, U. Grenoble, FR ************Local Organizing Committee************ ? Yannis Avrithis, NTUA ? Christos Douligeris, Piraeus Univ ? George Dounias, Aegean Univ ? Kostas Karpouzis, ICCS-NTUA ? Aris Likas, Univ. of Ioannina ? Kostas Margaritis, Univ. Macedonia ? Basil Mertzios,DUTH and ATIT ? Stavros Perantonis, NCSR, Athens ? Yannis Pitas, AUTH, Salonica ? Costas Pattichis, Univ. of Cyprus ? Apostolos Paul Refenes, Athens University Economics & Business ? Christos Schizas, Univ. of Cyprus ? Thanos Skodras, Univ. of Patras ? Kostas Spyropoulos, NCSR, Athens ? Giorgos Stamou, ICCS-NTUA ? Sergios Theodoridis, UoA ? Spyros Tzafestas, NTUA ? Mihalis Zervakis, TUC, Crete From netta at comp.leeds.ac.uk Fri Mar 10 05:26:38 2006 From: netta at comp.leeds.ac.uk (N Cohen) Date: Fri, 10 Mar 2006 10:26:38 +0000 (GMT) Subject: Connectionists: Junion/Senior Faculty Recruitment: University of Leeds Message-ID: Fellow connectionists, Lecturer/Senior Lecturer/Reader in Biosystems University of Leeds, UK Applications are invited for a faculty position at the School of Computing, University of Leeds, in the Biosystems area. We are particularly keen to expand and enhance activity in computational neuroscience, neurocomputation and/or bio-robotics. The successful candidate will join a vibrant Biosystems group led by Dr. Netta Cohen. The Biosystems Group in the School of Computing comprises 4 members of academic staff and 8 postgraduate students. Our research spans theoretical and computational neuroscience, invertebrate neurobiology, foundations and applications of bio-inspired computing, evolutionary dynamics, swarm intelligence, and a range of topics spanning complex adaptive behaviour in ecology, evolution, gene networks, and more. Further details on the Group's research activities can be found at http://www.comp.leeds.ac.uk/biosystems/ Full details of the post can be found at http://www.comp.leeds.ac.uk/vacancies/20060320lecturer.shtml and by following the link to "Further particulars". Closing Date: 20th March 2006 From jose.r.dorronsoro at iic.uam.es Fri Mar 10 09:51:26 2006 From: jose.r.dorronsoro at iic.uam.es (Jose Dorronsoro) Date: Fri, 10 Mar 2006 15:51:26 +0100 Subject: Connectionists: CFP: Special Session on Advances in Neural Network Learning Methods, ICANN 2006 Message-ID: <7.0.0.16.0.20060310155106.01ce1290@iic.uam.es> Special Session on Advances in Neural Network Learning Methods ICANN 2006: 16th International Conference on Artificial Neural Networks 10-14 September 2006 Holiday Inn Athens, Greece http://icann2006.org/ Call for Papers While there are several well established NN construction procedures, there is a constant research work on new ways to improve on them or to apply to NN training new procedures coming from other areas of machine learning. Moreover, there is a clear awareness among NN practitioners of the advantages that alternative procedures or paradigms may bring and a willingness to apply those most promising on new classification or regression problems arising in diverse areas, particularly those involving special difficulties, such as large sample dimension or data noise. The aim of this Special Session is to provide a wide look on the latest applications to NN training of recent advancements in machine learning. As possible topics of the session we mention: * Latest improvements on established NN learning methods. * Advances in ensemble NN methods, such as boosting, bagging and their variants. * Dimension expanding procedures, such as kernel methods. * Evolutionary computation based training. * New training paradigms from neurobiological computation. Submission procedure: Papers are to be submitted through the ICANN 2006 submission webpage, where Instructions for Authors are also available. When submitting these, please mention your interest in this special session and send also the abstract to one of the Special Session Organizers. SPECIAL SESSION ORGANIZERS Jos? Dorronsoro Departamento de Ingenier?a Inform?tica and Instituto de Ingenier?a del Conocimiento Escuela Polit?cnica Superior Universidad Aut?noma de Madrid Madrid, Spain jose.dorronsoro at uam.es Pedro Isasi Departamento de Inform?tica Escuela Polit?cnica Superior Universidad Carlos III de Madrid Madrid, Spain isasi at ia.uc3m.es Important dates: 30 March: End of submission of papers to special sessions 30 April: Acceptance/rejection notification 15 June: Deadline for camera ready papers Jos? R. Dorronsoro Escuela Polit?cnica Superior Universidad Aut?noma de Madrid 28049 Madrid Tel: 34 91 497 2329, 34 91 497 2240 Fax: 34 91 497 2334 From gwestermann at brookes.ac.uk Fri Mar 10 11:35:38 2006 From: gwestermann at brookes.ac.uk (Gert Westermann) Date: Fri, 10 Mar 2006 16:35:38 +0000 Subject: Connectionists: PhD studentship Message-ID: <4411AADA.9050400@brookes.ac.uk> Dear Connectionists, Please see below for an advert for a PhD studentship in our department. One possible area for the studentship is connectionist modelling of cognitive developmental processes. For informal enquiries regarding this area please email Gert Westermann at gwestermann at brookes.ac.uk. The closing date for applications is 19 April 2006. ---------------------------------------------------------------------- Oxford Brookes University Department of Psychology ESRC Psychology Research Studentship Applications are invited for an ESRC quota research Studentship (fees + maintenance grant), available in an area of Psychology that reinforces the Department?s research activities. As a successful applicant, you will join a well-resourced, supportive and research-active department, becoming actively involved in international quality research. Organised around Developmental Psychology and Cognitive Parapsychology's key areas of research expertise include: ? Cognitive development (home and school numeracy, development of writing skills, connectionist modelling of development, deaf children?s development) ? Cultural identity development and immigration; Learning and development in multicultural communities ? Developmental disorders in children and adults (autism, sleeping, motor coordination, dyslexia) ? Cognitive neuropsychology (bipolar disorder, visual perception in normal and clinical populations, connectionist modelling of normal and impaired cognitive processing). The Studentship will be funded for either a '+3' or ?1+3' scheme. The 1+3 award combines a Masters of Research (MRes) in Psychology followed by an MPhil/PhD. See http://ssl.brookes.ac.uk/postgraduates/resmethods-psychology-mres.htm for details of the Oxford Brookes MRes in Psychology. The Department welcomes applications from those who have (or expect to achieve in 2006) a degree (of at least 2:1, or academic equivalent) in Psychology, Education or a related cognate discipline. Applicants who have already completed a Masters programme that is ESRC recognised may alternatively apply for the ?+3' mode (to support an MPhil/PhD research post). The award is available to UK/EU students and will cover fees and a maintenance grant of ?12,300 per year. EU students will receive fees only (unless they have been resident in the UK for at least 3 years). Further guidance is available on the ESRC web site at: http://www.esrcsocietytoday.ac.uk/ESRCInfoCentre/opportunities/postgraduate/fundingopportunities/ The closing date for applications is Wednesday 19 April 2006. Interviews will be held on Friday 26 April 2006. Start date October 2006. To request an application pack, please contact Jennie Cripps, Research Support Officer, e-mail jcripps at brookes.ac.uk, tel 01865 48 3763. Further details about the Department?s research can be found at: http://www.brookes.ac.uk/schools/social/psych/research.html -- ===================================================================== Dr. Gert Westermann gwestermann at brookes.ac.uk Department of Psychology, Oxford Brookes University, Oxford OX3 0BP Tel +44 (0)1865 271 400 Fax: +44 (0)1865 48 38 87 http://www.cbcd.bbk.ac.uk/people/gert/ ===================================================================== From renaud.jolivet at epfl.ch Sat Mar 11 04:00:20 2006 From: renaud.jolivet at epfl.ch (Renaud Jolivet) Date: Sat, 11 Mar 2006 10:00:20 +0100 Subject: Connectionists: EPFL School of life sciences summer research program Message-ID: <441291A4.9030401@epfl.ch> From ahu at cs.stir.ac.uk Sun Mar 12 10:55:48 2006 From: ahu at cs.stir.ac.uk (Dr. Amir Hussain) Date: Sun, 12 Mar 2006 15:55:48 -0000 Subject: Connectionists: Final CFP: Extended Paper Submission Deadline: 25 March 2006 for the 2nd International Conference on BICS 2006, Lesvos, Greece, 10-14 Oct 2006 Message-ID: <00a001c645ed$6e4047f0$3bea0954@hec.gov> Please forward to any relevant people or lists. Thank you in advance! -- Please see the website for more details on the Conference CFP: http://www.icsc-naiso.org/conferences/bics2006/bics06-cfp.html (Click on "BICS 2006" on the left of the page for more info). Note: Due to numerous requests from authors, the paper submission deadline has been extended till: 25 March 2006 - for other important dates, please see: http://www.icsc-naiso.org/conferences/bics2006/bics06_dates.html For submitting a draft paper (4-7 pages) for peer review by the IPC, please see: http://www.x-cd.com/bics06/abstract.cfm The conference features an excellent line-up of invited plenary speakers, including: Shun-ichi Amari, RIKEN Brain Science Institute, Japan Holk Cruse, University of Bielefeld, Germany Pentti Haikonen, Nokia Research Center, Finland Timothy K Horiuchi, University of Maryland, USA John Taylor, Kings College, London, U.K. Steve Potter, Georgia Tech, USA Jacek M Zurada, University of Louisville, USA Marios Polycarpou, University of Cyprus, Cyprus And others to be confirmed. We hope to see you in the Greek Islands in October for a great conference, and we look forward to receiving your submission(s). Amir Hussain On behalf of the BICS 2006 Organizing Committee (BICS 2006 General Chairman: Igor Alexander, Imperial College, London, UK) -- Dr. Amir Hussain Chair IEEE UK & RI Industry Applications Society Chapter Department of Computing Science & Mathematics University of Stirling, Scotland, UK Tel / Fax: +44 (0)1786 467437 / 464551 Email: ahu at cs.stir.ac.uk http://www.cs.stir.ac.uk/~ahu/ From marcilio at dimap.ufrn.br Mon Mar 13 06:35:34 2006 From: marcilio at dimap.ufrn.br (Marcilio Carlos P. de Souto) Date: Mon, 13 Mar 2006 08:35:34 -0300 Subject: Connectionists: Fw: [Sbc-l] 2nd Call for paper SBRN 2006 In-Reply-To: <20060310122258.M85005@dimap.ufrn.br> References: <20060310122258.M85005@dimap.ufrn.br> Message-ID: <20060313113523.M53111@dimap.ufrn.br> --------------------------- Apologies for cross-posting --------------------------- 2nd CALL FOR PAPERS ********************************************************************** SBRN'2006 - IX BRAZILIAN SYMPOSIUM ON NEURAL NETWORKS Ribeirao Preto, October 23-26, 2006 http://www.icmc.usp.br/iarn2006/sbrn.php ********************************************************************** The biannual Brazilian Symposium on Artificial Neural Networks (SBRN) - of which this is the 9th event - is a forum dedicated to Neural Networks (NNs) and other models of computational intelligence. The emphasis of the Symposium will be on original theories and novel applications of these computational models. The Symposium welcomes paper submissions from researchers, practitioners, and students worldwide. SBRN'2006 is sponsored by the Brazilian Computer Society (SBC) and co- sponsored by SIG/INNS/Brazil Special Interest Group of the International Neural Networks Society in Brazil. It will take place October 23-26, and will be held in Ribeirao Preto. Ribeirao preto is a dynamic and sunny city, about 300 km from the city of S?o Paulo. Sao Paulo is the main gateway to Brazil with regular flights to all major cities in Brazil as well as Europe, United states, Asia, among others. SBRN'2006 will be held together with the X Ibero-American Artificial Intelligence Conference (IBERAMIA) and XVIII Brazilian Symposium on Artificial Intelligence (SBIA). All Symposia will feature keynote speeches and tutorials by world-leading researchers. SBIA has its main focus on symbolic AI. Crossfertilization of these fields will be strongly encouraged. The deadline for submissions is March 26, 2006. More details on paper submission and conference registration will be coming soon. Sponsored by the Brazilian Computer Society (SBC) Co-Sponsored by SIG/INNS/Brazil Special Interest Group of the International Neural Networks Society in Brazil Organized by the University of S?o Paulo (USP), Brazil Submissions: We welcome papers describing original works on (but it is not limited to): 1. Applications: finances, data mining, neurocontrol, time series analysis, bioinformatics; 2. Architectures: cellular NNs, hardware and software implementations, new models, weightless models; 3. Cognitive Sciences: adaptive behavior, natural language, mental processes; 4. Computational Intelligence: evolutionary systems, fuzzy systems, hybrid systems; 5. Learning: algorithms, evolutionary and fuzzy techniques, reinforcement learning; 6. Neurobiological Systems: bio-inspired systems, biologically plausible networks, vision; 7. Neuro-control: robotics, dynamic systems, adaptive control; 8. Neuro-symbolic processing: hybrid approaches, logical inference, rule extraction, structured knowledge; 9. Pattern Recognition: signal processing, artificial/computational vision; 10. Theory: radial basis functions, Bayesian systems, function approximation, computability, learnability, computational complexity. Submission Guidelines: Paper registration and submissions to SBRN 2006 will be handled using the JEMS system, which will be open for registration and submission from February 14th, 2006, 00:00 BRST. The address is: https://submissoes.sbc.org.br/home.cgi?c=280 Submission is a three-step process. In a first step authors are required to register as new authors with JEMS (note that only 1 registration is needed if you submit more than 1 paper). After registration as author the login data will be sent to the specified email address. This data can be used to access the system. In a second step authors have to register their paper (click the submit paper button in JEMS). There are two different tracks to submit a paper. In the first one (SBRN 2006), the paper is only submitted to SBRN. In the second one (SBRN or WCI), a paper which is not accepted to SBRN is automatically submitted to the Workshop on Computational Intelligence (WCI). Once the chosen track is selected, the authors are asked in this step to specify the name of the authors, the paper title, its topics and the paper category (regular, student): these categories are exactly the same, except for the fact that the first author is a student or not. The system will then assign a tracking ID to each submission which is sent to the contact author. The deadline for paper registration is March 26th., 23:55 BRST. The third step consists on uploading the paper. This step can be done jointly with the registering step. For those authors who prefer to upload their papers after registering, the tracking ID must be used. The deadline for paper uploading is March 26th, 23:55 BRST. We will *only* accept files either in pdf or in ps format. Please do not try to upload doc or rtf files, they will be rejected by the system. Note also that contrary to earlier years we only accept electronic submissions through JEMS. Please do not send papers directly to the PC-chairs. Submissions sent by regular courrier or by email will *not* be considered. Style guide Papers must be written in English and should be no longer than 6 pages (style of the IEEE Computer Society - http://www.computer.org/cspress/instruct.htm), including all tables, figures, and references. Formatting instructions, LaTeX macros and MSWord templates are available at . Submissions violating the formatting guidelines will be *excluded* from the reviewing process. Deadlines: Submission: 26 March 2006 Acceptance: 24 May 2006 Camera-ready: 12 June 2006 General Chair: Antonio Carlos Roque da Silva Filho (FFCLRP/USP Ribeir?o Preto) antonior at neuron.ffclrp.usp.br Program Chair: Anne Mag?ly de Paula Canuto (UFRN/DIMAp, Brazil) anne at dimap.ufrn.br Steering Committee Allan K. Barros (Universidade Federal do Maranh?o) Alu?zio Ara?jo (Universidade Federal de Pernambuco) Gerson Zaverucha (Universidade Federal do Rio de Janeiro) Teresa B. Ludermir (Universidade Federal de Pernambuco) Program Committee Adriao D. Doria Neto (UFRN, Brazil) Alejandro Ceccatto (Univ. of Rosario, Argentina) Allan K. Barros (UFMA, Brazil) Aluizio Araujo (UFPE, Brazil) Amanda Sharkey (Univ. of Shefield, UK) Andre C. P. L. F. de Carvalho (USP-S?o Carlos, Brazil) Anne Magaly de Paula Canuto (UFRN, Brazil) Antonio C. R. da Silva Filho (USP, Brazil) Antonio de P. Braga (UFMG, Brazil) Artur Garcez (City University, UK) Carlos H. C. Ribeiro (ITA, Brazil) Edson Costa B.C. Filho (UFPE, Brazil) Felipe Franca (UFRJ, Brazil) Fernando A. Gomide (UNICAMP, Brazil) Gerson Zaverucha (UFRJ, Brazil) Guilherme A. Barreto (UFC, Brazil) Harold Szu (George Washington Univ., USA) Herman M. Gomes (UFCG, Brazil) Igor Aleksander (Imperial College, UK) Jose Principe (Univ. of Florida, USA) Ludmila Kuncheva (University of Wales, UK) Marcilio C. P. de Souto (UFRN, Brazil) Marios Polycarpou (University of Cyprus, Cyprus) Marley M. B. R. Vellasco (PUC ? RJ, Brazil) Michael Fairhurst (Univ. of Kent, UK) Nikola Kasabov (University of Otago, New Zeland) Phillipe De Wilde (Heriot Watt University, UK) Teresa B. Ludermir (UFPE, Brazil) Zhao Liang (USP, Brazil) _______________________________________________ Sbc-l mailing list Sbc-l at inf.ufrgs.br https://listas.inf.ufrgs.br/mailman/listinfo/sbc-l ------- End of Forwarded Message ------- -- Open WebMail Project (http://openwebmail.org) Debian Project (http://www.debian.org) From lendasse at james.hut.fi Sun Mar 12 15:42:25 2006 From: lendasse at james.hut.fi (Amaury Lendasse) Date: Sun, 12 Mar 2006 22:42:25 +0200 Subject: Connectionists: Call for Papers: ICANN 2006 Special Session Message-ID: <20060312204203.9E9966C069@james.hut.fi> Call for Papers: ICANN 2006 Special Session: Title: Feature selection and dimension reduction for regression Abstract: Nowadays, many machine learning problems involved the use of a large number of features. This might be the case, for example, in DNA and biomedical data analysis, in image processing, financial data mining, chemometrics, etc. In other cases, the number of features may be smaller, but of the same order of magnitude as the number of samples. In both cases, regression tasks are faced to the curse of dimensionality: overfitting easily appears, and in some cases the regression problem can become ill-posed (or not identifiable). The challenge is then to reduce the number of features, in order to improve the regression efficiency. Interpretability is often a major concern too, as a large number of features usually prevents any understanding of the underlying relationship. Feature selection and dimension reduction includes two different ways of reducing the number inputs of the regression model. First, inputs can be selected among the original features; this is usually referred to as feature selection or input selection. Second, inputs can be built from the original features, by combining them in a linear or nonlinear way; this leads to dimension reduction (sometimes referred to as variable selection). The goal of feature selection and dimension reduction is twofold. First, reducing the number of input variables fights the curse of dimensionality, giving the possibility of increasing the regression generalization performances. Second, a reduced set of variables is of utmost importance in real applications as it allows an easier interpretation of the relationship between features and outputs. The aim of this session is to present original developments in feature selection and dimension reduction. Contributions are invited in the following areas: - new algorithms and methods; - comparisons between techniques, including the assessment of the compromise between generalization properties and computational load; -applicability of the proposed methods in real-world problems, including small sample and high dimension constraints. It is suggested (but not mandatory) to illustrate and compare the proposed methods by using one of or both the following regression datasets: Housing (Boston), available from the UCI Machine Learning Repository (http://www.ics.uci.edu/~mlearn/MLSummary.html), and Orange juice spectra, available from the UCL Machine Learning Group website (http://www.ucl.ac.be/mlg/index.php?page=DataBases). Practical details: - ICANN?06 website: http://icann2006.org/chapter1/index.html - 30 Mars: End of submission of papers to special sessions - Proceedings of ICANN will be published in Springer's "Lecture Notes in Computer Science" series. Paper length is restricted to a maximum of 10 pages, including figures. Organized by: Amaury Lendasse, Helsinki University of Technology, Adaptive Informatics Research Centre, Finland. Michel Verleysen, Universit? catholique de Louvain, Machine Learning group, Belgium. From giovanni.pezzulo at istc.cnr.it Mon Mar 13 10:54:14 2006 From: giovanni.pezzulo at istc.cnr.it (Giovanni Pezzulo) Date: Mon, 13 Mar 2006 16:54:14 +0100 Subject: Connectionists: CFP: ABiALS Workshop 2006 Message-ID: <01f301c646b6$60b16af0$4d419296@GIOVANNI> (We apologize if you receive more than one copy of this message) ########################################################################### 1st C A L L F O R P A P E R S ABiALS Workshop 2006 Anticipatory Behavior in Adaptive Learning Systems ########################################################################### SEPTEMBER 30, 2006 ROME, ITALY http://www-illigal.ge.uiuc.edu/ABiALS to be held during the ninth international conference on the SIMULATION of ADAPTIVE BEHAVIOR (SAB 2006) http://www.sab06.org ABiALS is an interdisciplinary workshop investigating the influence of anticipations on behavior and learning. ABiALS is designed to help investigate how anticipations can influence, initiate, and guide behavior and learning as well as how anticipatory influences can be implemented in an adaptive learning system. Submission deadline: Wednesday, 15. JUNE 2006 Anticipatory behavior is a mechanism, or a behavior, that does not only depend on the past and present but also on predictions, expectations, or beliefs about the future. ___________________________________________________________________________ OBJECTIVES: After two previous successful gatherings during SAB 2002, resulting in the Springer-Verlag LNCS 2684 State-of-the-Art survey named after the workshop, and SAB2004, ABiALS 2006 will continue to explore anticipatory influences on behavior and learning. The aim of ABiALS 2006 is to join researchers in their understanding and development of anticipatory mechanisms in adaptive behavior. It is aimed for an interdisciplinary gathering that combines the expertise of researchers from various disciplines including neuroscience, cognitive psychology, machine learning, artificial intelligence, control, and vision research to shed further light on the concept of anticipation. Essentially, it will be discussed how knowledge about the future can influence actual behavioral mechanisms, including influences on attention, action decision making and control, as well as (behavioral and model) learning. ___________________________________________________________________________ KEY INTERESTS: Anticipatory mechanisms for model learning ? Adaptive, predictive model learning ? Adaptive, predictive filtering ? Anticipatory attention ? Surprise for model learning ? Hierarchical, predictive model architectures ? Timing in predictive models Model-predictive, adaptive control architectures ? Inverse models and goal-oriented control ? Hierarchical structures in adaptive, model-predictive control ? Surprise in control ? Delayed feedback, forward models, and multiply timed control Anticipatory, adaptive systems / agents ? Integration of anticipatory adaptive processes in adaptive systems ? Anticipatory decision making ? Anticipatory behavior in multiagent systems ? Interactions of anticipations, motivations, and emotions ? Anticipations in BDI architectures ? Curiosity and epistemic actions Distinctions of anticipatory mechanisms: ? Benefits and drawbacks of different anticipatory mechanisms ? Distinction to reactive mechanisms ? Emergence of anticipatory mechanisms in evolution ? Anticipatory mechanisms in constructivist, interactive frameworks Anticipatory mechanisms in animals and humans ? Behavioral and cognitive anticipatory mechanisms in animals and humans ? Anticipatory mechanisms in neuroscience ? Anticipatory mechanisms in cognitive/experimental psychology ___________________________________________________________________________ SUBMISSION: Submissions for the workshop should address one of the interests listed above. The workshop is not limited to one particular type of anticipatory learning system or a particular representation of anticipations. The workshop will be generally targeted towards short presentations and extended discussions. The advantages and disadvantages of different anticipatory mechanisms and representations will be discussed in detail. Several discussion sessions on the topics in question will put the presentations in a broader perspective. Papers should be submitted electronically to one of the organizers via email in pdf or ps format. Electronic submission is strongly encouraged. If you cannot submit your contribution electronically, please contact one of the organizers. Submitted papers should have a maximal length of ten pages in 10pt, one-column format. Please use the LNCS Springer-Verlag style as specified at http://www.springeronline.com/comp/lncs/authors.html (LATEX utilities can be found in the file llncs2e.zip). Papers will be reviewed for acceptance by the program committee and the organizers. Submission deadline is the 15th of JUNE 2006. Dependent on the quality and number of contributions we will publish Post Workshop proceedings as either a Springer LNAI volume or a special issue of a journal. For more information please refer to http://www-illigal.ge.uiuc.edu/ABiALS/ ___________________________________________________________________________ ___________________________________________________________________________ IMPORTANT DATES: 15. June 2006: Deadline for Submissions 30. September 2006: ABiALS Workshop 2006 ___________________________________________________________________________ PROGRAM COMMITTEE: Christian Balkenius Cognitive Science, Lund University, Sweden Edoardo Datteri Department of Philosophy, University of Pisa, Italy Pier Luca Lanzi Dipartimento di Elettronica e Informazione, Politecnico di Milano, Italy Ralf Moeller Computer Engineering Group, Faculty of Technology, Bielefeld University, Germany Tony Prescott Department of Psychology, The University of Sheffield, UK Jesse Reichler Department of Computer Science, University of Illinois at Urbana-Champaign, IL Alexander Riegler CLEA, Vrije Universiteit Brussels, Belgium Deb Roy Cognitive Machines Group, MIT Media Laboratory, Cambridge, MA Samarth Swarup Department of Computer Science, University of Illinois at Urbana-Champaign, IL Stewart W. Wilson Prediction Dynamics, Concord, MA ___________________________________________________________________________ ORGANIZERS: Martin V. Butz, Department of Cognitive Psychology University of Wuerzburg, Germany butz at psychologie.uni-wuerzburg.de http://www-illigal.ge.uiuc.edu/~butz Olivier Sigaud AnimatLab, University Paris VI, Paris, France olivier.sigaud at lip6.fr http://animatlab.lip6.fr/Sigaud Gianluca Baldassarre Istituto di Scienze e Tecnologie della Cognizione Consiglio Nazionale delle Ricerche (ISTC-CNR) Roma, Italy gianluca.baldassarre at istc.cnr.it http://gral.istc.cnr.it/baldassarre/ Giovanni Pezzulo Istituto di Scienze e Tecnologie della Cognizione Consiglio Nazionale delle Ricerche (ISTC-CNR) Roma, Italy giovanni.pezzulo at istc.cnr.it http://www.istc.cnr.it/createhtml.php?nbr=1 From deneve at isc.cnrs.fr Wed Mar 15 18:16:20 2006 From: deneve at isc.cnrs.fr (Sophie Deneve) Date: Thu, 16 Mar 2006 00:16:20 +0100 Subject: Connectionists: (no subject) Message-ID: <5.1.1.6.0.20060316000843.0386f7a0@pop.isc.cnrs.fr> A "Ma?tre de conf?rence" position is available at the Ecole Normale Sup?rieure in Paris, France. The Ecole Normale Sup?rieure is one of the top school/research institution in France, forming elite students to multidisciplinary studies in the domain of (among others) physics, mathematics, and biology. This is permanent research position involving 145 hours of teaching per year. The candidate should have a background and good publications in the domain of computational/theoretical neuroscience. The research will be done in collaboration with the newly created Group of Neural Theory. Faculty includes Misha Tsodyks, Jean Pierre Nadal, Boris Gutkin, Sophie Deneve, and Rava Da Silveira. Candidates should contact AS SOON AS POSSIBLE Boris Gutkin (boris.gutkin at ens.fr) and Sophie Deneve (deneve at isc.cnrs.fr). Please attach a CV to your email. The applications are due on the 30th of March, and we should be contacted before the 26th. We apologize for the short delay. From andrew.coward at anu.edu.au Tue Mar 14 19:50:46 2006 From: andrew.coward at anu.edu.au (Andrew Coward) Date: Wed, 15 Mar 2006 00:50:46 -0000 Subject: Connectionists: Physiologically Realistic Cognitive Modelling: New Book Message-ID: (Apologies if you receive this announcement more than once) A recently published book, ?A System Architecture Approach to the Brain: from Neurons to Consciousness? (ISBN 1-59454-433-6), applies some developments in systems theory to demonstrate that detailed modelling of higher cognitive processes in terms of neurophysiology requires some very specific architectural approaches. The book demonstrates theoretical arguments that any learning system that is subject to a range of practical considerations will be constrained within a set of architectural bounds called the recommendation architecture. The theoretical arguments have been developed by analogy with the ways in which practical considerations constrain the architectures of extremely complex electronic control systems, although there is minimal direct resemblance between such architectures and those of learning systems. The practical considerations are (1) the need to perform a large number of behavioural features with relatively limited physical resources for information recording, information processing and internal information communication; (2) the need to add and modify features without side effects on other features; (3) the need to protect the many different meanings of information generated by one part of the system and utilized for different purposes by each of a number of other parts of the system; (4) the need to maintain the association between results obtained by different parts of the system from a set of system inputs arriving at the same time; (5) the need to limit the volume of information required to specify the system construction process; (6) the need to limit the complexity of the construction process; and (7) the need to recover from construction errors and subsequent physical failures or damage. The system theory demonstrates that if such needs are strong, there are some remarkably specific constraints on the system architecture. There are constraints on how functionality is separated into modules and components, on device information models, on the ways in which devices are organized and connected within and between modules and components, and on the ways in which information can be recorded and processed. One key constraint is a requirement for a separation between a clustering subsystem which defines and detects conditions within the information available to the system, and several competition subsystems which receive some of the conditions and interpret each condition as a recommendation in favour of a range of different behaviours, each with a different weight. These competition subsystems determine the current total recommendation weights of all behaviours across all current conditions and implement the most strongly recommended behaviour. Consequence feedback following a behaviour can set or change recommendation weights but cannot change condition definitions. Furthermore, once a condition has been defined in clustering, there are tight restrictions on subsequent changes. The limited ability to change condition definitions is one primary difference from traditional neural networks. The book describes the strong resemblances between the structures and processes predicted for a system within the recommendation architecture bounds and the physiological structures and processes of the mammal brain. The ways in which the recommendation architecture approach makes it possible to understand experimental results for a wide range of cognitive processes in terms of physiology are described. Electronic implementations of systems within the recommendation architecture bounds are described that confirm the resemblances with biological brains. L. Andrew Coward Research Fellow Department of Computer Science Australian National University Canberra ACT 0200 Australia andrew.coward at anu.edu.au tel +61 02 6125 5694 mob +62 0431 529 197 http://cs.anu.edu.au/~Andrew.Coward/ Book Website: http://www.novapublishers.com/catalog/product_info.php? cPath=23_128&products_id=2652 From retienne at jhu.edu Tue Mar 14 01:59:19 2006 From: retienne at jhu.edu (Ralph Etienne-Cummings) Date: Tue, 14 Mar 2006 01:59:19 -0500 Subject: Connectionists: Reminder: Neuromorphic Engineering Workshop 2006 In-Reply-To: <41F7C734.8060205@jhu.edu> References: <41F7C734.8060205@jhu.edu> Message-ID: <441669C7.5070609@jhu.edu> Reminder: Please forgive us if you get this announcement more than once: ======================================================================== Neuromorphic Engineering Workshop Call for Applications Sunday, June 25 - Saturday, July 15, 2006 Telluride, Colorado ------------------------------------------------------------------------------------------------------------ Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Ralph ETIENNE-CUMMINGS (Johns Hopkins University) Paul HASLER (Georgia Institute of Technology) Timmer HORIUCHI (University of Maryland) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Christof KOCH (California Institute of Technology)- Past Organization Board Member Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) Andre van SCHAIK(University of Sydney) ------------------------------------------------------------------------------------------------------------- We invite applications for a three week summer workshop that will be held in Telluride, Colorado from Sunday, June 25 to Saturday, July 15, 2006. The application deadline is Friday, March 24, and application instructions are described at the bottom of this document. The 2005 Workshop and Summer School on Neuromorphic Engineering is sponsored by the National Science Foundation, Institute of Neuromorphic Engineering, Wow Wee Toys, Airforce Research Office, Eglin Airforce Research Lab, Nova Sensors, Institute for NeuroInfomatics - ETHZ, Geogia Institute of Technology, University of Maryland - College Park, Johns Hopkins University, The Salk Institute, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology. Last year's workshop was an exciting event and a great success. We strongly encourage interested parties to browse through the previous workshop web pages at: http://ine-web.org/workshops/past-workshops GOALS: Carver Mead introduced the term "Neuromorphic Engineering" for a new field based on the design and fabrication of artificial neural systems, such as vision systems, head-eye systems, and roving robots, whose architecture and design principles are based on those of biological nervous systems. The goal of this workshop is to bring together young investigators and more established researchers from academia with their counterparts in industry and national laboratories, working on both neurobiological as well as engineering aspects of sensory systems and sensory-motor integration. The focus of the workshop will be on active participation, with demonstration systems and hands on experience for all participants. Neuromorphic engineering has a wide range of applications from nonlinear adaptive control of complex systems to the design of smart sensors. Many of the fundamental principles in this field, such as the use of learning methods and the design of parallel hardware (with an emphasis on analog and asynchronous digital VLSI), are inspired by biological systems. However, existing applications are modest and the challenge of scaling up from small artificial neural networks and designing completely autonomous systems at the levels achieved by biological systems lies ahead. The assumption underlying this three week workshop is that the next generation of neuromorphic systems would benefit from closer attention to the principles found through experimental and theoretical studies of real biological nervous systems as whole systems. FORMAT: The three week summer workshop will include background lectures on systems neuroscience (in particular learning, oculo-motor and other motor systems and attention), practical tutorials on analog VLSI design, small mobile robots (Koalas, Kheperas, LEGO robots), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, the majority of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control * central pattern generator and locomotion * robotics * multichip communication * analog VLSI * learning * neuroprosthetic systems The active perception project group will emphasize vision and human sensory-motor coordination. Issues to be covered will include spatial localization and constancy, attention, motor planning, eye movements, and the use of visual motion information for motor control. The central pattern generator group will focus on small walking and undulating robots. It will look at characteristics and sources of parts for building robots, play with working examples of legged and segmented robots, and discuss CPG's and theories of nonlinear oscillators for locomotion. It will also explore the use of simple analog VLSI sensors for autonomous robots. The robotics group will use rovers and working digital vision boards as well as other possible sensors to investigate issues of sensorimotor integration, navigation and learning. The audition group aims to develop biologically plausible algorithms and aVLSI implementations of specific auditory tasks such as source localization and tracking, and sound pattern recognition. Projects will be integrated with visual and motor tasks in the context of a robot platform. The multichip communication project group will use existing interchip communication interfaces to program small networks of artificial neurons to exhibit particular behaviors such as amplification, oscillation, and associative memory. Issues in multichip communicationwill be discussed. LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350miles). Great Lakes Aviation and America West Express airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do not rent a car. Bring hiking boots, warm clothes, rain gear, and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around mid April 2006. Participants are expected to pay a $800.00 workshop fee at that time in order to reserve a place in the workshop. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. Travel reimbursement of up to $500 for US domestic travel and up to $800 for overseas travel will be possible if financial help is needed (please specify on the application). HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e.postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage women and minority candidates to apply. The application website is: http://ine-web.org/telluride-conference-2006/apply/ Application will include: * First name, Last name, Affiliation, valid e-mail address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Two letters of recommendation (to be sent by references directly to "Alice W. Mobaidin" ). The application deadline is Friday, March 24, 2006. Applicants will be notified by e-mail by the end of April. From M.Casey at surrey.ac.uk Thu Mar 16 08:26:56 2006 From: M.Casey at surrey.ac.uk (M.Casey@surrey.ac.uk) Date: Thu, 16 Mar 2006 13:26:56 -0000 Subject: Connectionists: International Workshop on Biologically Inspired Information Fusion Message-ID: ======================================================================== ==================== International Workshop on Biologically Inspired Information Fusion Call for Contributions Tuesday 22 August - Wednesday 23 August 2006, University of Surrey, Guildford, UK. http://www.soc.surrey.ac.uk/ias/workshops/biif/ ======================================================================== ==================== We invite contributions to an international workshop on biologically inspired information fusion. The workshop is designed to bring together complementary researchers in the broad areas of computer science, engineering, psychology and biology who have an interest in the multi-disciplinary aspects of information fusion. The programme consists of tutorials from discipline leaders, discussions, and research student poster and oral presentations. Contributions are being sought for the discussion sessions and research student presentations from all of the target disciplines: computer science, engineering, psychology and biology. ======================================================================== ==================== Natural and Artificial Multi-sensory Processing The ability to process, interpret and act upon sensory information is perhaps one of the most remarkable aspects of human and animal cognition. Our sensory systems process large volumes of information at different scales in short periods of time, far out-performing current artificial systems, which struggle to usefully process just a single modality of information. For example, whereas speech recognition systems have achieved real-time continuous operation, artificial systems, designed for vision or olfaction are far less advanced, yet the combination of different information sources, or senses, may help overcome some of the processing limitations. This disparity between natural and artificial cognitive systems has been recognised in the recent UK Foresight Cognitive Systems Review, which suggests that our understanding of both natural and artificial systems of sensory processing can be achieved through collaboration between life and physical scientists. About the Workshop The workshop is sponsored by the University of Surrey's Institute of Advanced Studies. The aim is to promote collaboration between disciplines to develop an understanding of how to build adaptive information fusion systems by improving our knowledge from both natural and artificial systems research. The programme is designed to facilitate a cross-discipline understanding of multi-sensory fusion, with discussions on key topics and future directions, and presentation of current ideas. This is to be achieved through tutorials from leaders in each of the target disciplines, brainstorming and debate sessions lead by relevant researchers, and both oral and poster presentations from research students. Example topics include, but are not limited to: Sensory and multi-sensory processing: neurobiology, behaviour, computational modelling and artificial sensors - Vision, audition, olfaction, taste, touch - Attention: pre-attention or task-driven attention - Emotional bias on senses - Artificial sensors Information fusion and multi-modal systems: - Computer vision, speech processing, gesture recognition - Sensor fusion - Multiple regressor or classifier systems - Biometrics, human-computer interaction, intelligent systems - Bio-logically inspired robotics ======================================================================== ==================== Discussions Topics for the discussion sessions should aim to promote new or controversial ideas, perhaps posing unanswered questions related to the workshop. These should be in the form of abstracts (maximum 500 words) stating the key topic of discussion and highlighting possible solutions and current points of view. Proposals for debates, where two participants offer their point of view prior to discussion, should be clearly highlighted. All contributions will be peer reviewed by the workshop programme committee. Those with accepted topics will be invited to give a 10 minute presentation of their idea. For sessions focused around a debate, both participants will be invited to present their ideas in a 10 minute slot each, prior to discussion. An open brainstorming session will then follow for 50 minutes with a focus on initially evaluating the proposed idea or giving thoughts on unanswered questions. Notes and outcomes of these sessions will be recorded. Abstracts should be submitted via e-mail to biif2006 at surrey.ac.uk by the deadline. ======================================================================== ==================== Student Presentations Papers are invited from research students only to promote discussion of new ideas and to foster training and development of new researchers. All papers will be peer reviewed by the workshop programme committee to assess originality, significance, quality and clarity. Those students with accepted papers will be invited to either present a poster or to give a 20 minute oral presentation. Papers should not exceed 6 pages in length, including references, tables, figures and appendices, and should follow the LNCS format, details of which can be found at http://www.springer.com/sgw/cda/frontpage/0,11855,3-164-2-72376-0,00.htm l. Papers should be submitted via e-mail to biif2006 at surrey.ac.uk by the deadline. ======================================================================== ==================== Enquiries regarding abstract and paper submission should be directed to biif2006 at surrey.ac.uk. Abstracts and papers will be available to workshop attendees via the website and printed proceedings. After the workshop, participants will be invited to submit papers based upon their work to two journal special issues (journals to be confirmed). These will contain a mixture of review/discussion articles and presentations of current research work. ======================================================================== ==================== Important Dates 15 May 2006 Deadline for submitting papers and discussion topics 19 June 2006 Notification of acceptance 17 July 2006 Camera ready papers 22-23 August 2006 Workshop at the University of Surrey Guests looking for accommodation on campus (the cheapest in Guildford) are advised to register by the 15th May 2006. Otherwise, registration is open up until the workshop. For papers to be presented at the workshop, all guests must be registered by the 17th July 2006 to secure a place on the programme. Further information can be obtained from: - Website: http://www.soc.surrey.ac.uk/ias/workshops/biif/ - Enquiries about paper submission: biif2006 at surrey.ac.uk - General and administrative enquiries: Mrs Gautier O'Shea, S.Gautier at surrey.ac.uk; Mrs Heather Norman, H.Norman at surrey.ac.uk - Dr Matthew Casey, M.Casey at surrey.ac.uk; tel. +44 (0)1483 689635 - Dr Paul Sowden, P.Sowden at surrey.ac.uk - Dr Hujun Yin, Hujun.Yin at manchester.ac.uk - Dr Tony Browne, A.Browne at surrey.ac.uk From terry at salk.edu Mon Mar 20 16:58:06 2006 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 20 Mar 2006 13:58:06 -0800 Subject: Connectionists: NEURAL COMPUTATION 18:4 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 18, Number 4 - April 1, 2006 Note An Invariance Property of Kernel Predictors Sebastiano Stramaglia and Nicola Ancona Letters Modeling Sensorimotor Learning with Linear Dynamical Systems Sen Cheng and Philip N. Sabes Changing Roles of Temporal Representation of the Odorant During the Oscillatory Response in the Olfactory Bulb S. Kim, B. Singer. M. Zochowski Computation of the Phase Response Curve: A Direct Numerical Approach W. Govaerts and B. Sautois Multiperiodicity and Exponential Attractivity Evoked by Periodic External Inputs in Delayed Cellular Neural Networks Zhigang Zeng and Jun Wang Smooth Gradient Representations as an Unifying Account of Chevreul's Illusion, Mach Bands and a Variant of the Ehrenstein Disk Matthias S. Keil Memory Capacity for Sequences in a Recurrent Network with Biological Constraints Christian Leibold and Richard Kempter Kernel Fisher Discriminants for Outlier Detection Volker Roth Feature Scaling for Kernel Fisher Discriminant Analysis by Leave-One-Out Cross Validation Liefeng Bo, Ling Wang and Licheng Jiao Class Incremental Generazlied Discriminant Analysis Wenming Zheng ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2006 - VOLUME 18 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $154 $90 $96.30 Institution $730 $781.10 $784 $657 $702.99 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From kamps at in.tum.de Mon Mar 20 11:27:20 2006 From: kamps at in.tum.de (Marc de Kamps) Date: Mon, 20 Mar 2006 17:27:20 +0100 Subject: Connectionists: First Workshop on Topics of the nEUro-IT.net Roadmap Message-ID: <000401c64c3b$2a24bcf0$383c9f83@atknoll3> First Workshop on Topics of the nEUro-IT.net Roadmap Antwerp, 21/22 April 2006 Location: to be announced Scope nEUro-IT.net is about to present the new version of the Roadmap. The Roadmap is a document which summarizes the state-of-the-art in nEUro-IT topics, and which tries to recognize future developments in this field. The Roadmap will serve as input for new calls in FP7. In order to promote the Roadmap, we will organize a workshop around theme's in the Roadmap. This workshop will take place in Antwerp on 21/22 April. Topics are: 1. Bio-inspired and evolvable hardware 2. Brain-Machine interfacing 3. Peripheral Processing On the 21st the three workshops will take place in parallel, on the 22nd there will be a plenary session. The talks here address a general audience and allow people who have been participating in one of the workshops on the 21st to get a flavour from the other workshops. Officers from Future and Emerging Technology (FET) will be present at the meeting and briefly comment the preparations for FP7. They are also available for informal contacts during the meeting. Participation is free, but a registration is required. Please send an email to kamps at in.tum.de Programme webpage: http://www.neuro-it.net/NeuroIT/Activities/Roadmapworkshop Key note speakers include (ordered by workshop): Tetsuya Higuchi (AIST, Japan), Pauline Haddow (NTNU, Norway), Gianluca Tempesti (EPFL Switzerland), Andy Tyrrell (Univerity of York, UK), Gianluca Tempesti (EPFL Switzerland), Jim Torresen(University of Oslo, Norway), Adrian Stoica Erik De Schutter, Ad Aertsen (Bernstein Center, University of Freiburg, Germany), Paolo Dario (Polo Sant'Anna Valdera, Italy), Miguel Nicolelis (Duke University, USA and Brain Mind Institute, Lausanne, Switzerland), Eilon Vaadia (Hebrew University, Jerusalem, Israel) Stefaan Peeters,Gijs Krijnen (Universiteit Twente), George Jeronimidis (Reading University), Herbert Peremans (Universiteit Antwerpen), Leo van Hemmen (Technische Universit?t M?nchen), Annemie Van Der Linden (Universiteit Antwerpen), Heike Scheuerpflug (Forschungszentrum J?lich) Scope of the workshops is described in greater detail below: ---------------------------------------------------------------------------- -------------------------------------------------------- 1. Bio-inspired and evolvable hardware Evolvable hardware techniques enable self-reconfigurability and adaptability of programmable devices and thus have the potential to significantly increase the functionality of deployed hardware systems. Evolvable hardware is expected to have a major impact on deployable systems for space missions and defence applications that need to survive and perform at optimal functionality during long duration in unknown, harsh and/or changing environments. Evolvable hardware is also expected to greatly enrich the area of commercial applications in which adaptive information processing is needed; such applications range from human-oriented hardware interfaces and internet adaptive hardware to automotive applications. Evolvable hardware is an emerging field that applies evolution to automate design and adaptation of physical structures such as electronic systems, antennas, MEMS and robots. The aim of this workshop is to bring together leading researchers from the evolvable hardware community, representatives of the automated design and programmable/reconfigurable hardware communities, technology developers, and end-users from the aerospace, military and commercial sectors. Presentations will consider some of the following issues important now and in the future : 1. Design of large evolvable systems 2. Hardware design 3. Increased reliability using evolvable hardware 4. Analogue evolvable hardware and its applications 5. Real-world applications of evolvable hardware 6. Future evolvable systems 2. Brain Machine Interfaces: moving beyond limb control Recent progress in fundamental neurophysiological research has made a popular subject of science fiction movies seem possible: direct interfacing of the human brain with computers and machines to create the cyborg. Indeed in 2004 the first implant of an electrode array was performed in the brain of a quadriplegic patient, allowing control of external devices including a robot arm. This rapid development of a new field called neuroprosthetics has been made possible by the development of better electrodes and of fast signal processing techniques. This allowed chronic implantation of large arrays of recording electrodes in rodents and monkeys. The major breakthrough, however, was the discovery of a high level of plasticity of the neural coding in the mammalian brain, allowing it to adapt its signals to communication over a limited number of channels. This has led to an explosion of application of brain machine interfacing (BMI) to control of cursors on a computer screen or artificial upper limbs in monkeys and recently also in patients. But if we want to progress towards making cyborg-like applications, the vision of the Brain Interface project should be more ambitious than just simple motor control tasks such as using an artificial arm. This will require interfacing of sensory input to the brain and interfacing to cognitive tasks like memory. To achieve such goals the BMI needs to be developed further and we will need a much better understanding of the underlying brain plasticity and brain coding mechanisms. While research oriented towards neuroprosthetic application needs to be done in monkeys to prepare for human implementation, most of the visionary research proposed here can first be done in cheaper rodents, as was the case for the original BMI studies. This workshop will discuss both the current state of the field, where the USA is clearly leading, and achievable goals for FP7 including the development of awake animal models where the brain interacts with the environment only through BMI techniques. 3. Peripheral Processing Sensory systems based on arrays of hairs occur widely in nature and function in diverse sensing scenarios, for instance in air (cerci, external sensing hairs in arthropods), in water (lateral line, neuromasts in fish) and in a fluid-filled compartment coupled to air through impedance matching devices and beamforming baffles (mammalian auditory apparatus). These mechanosensor-systems are amongst the most sensitive sensors known. This suggests that hair-based sensing organs, supported by appropriate neuronal representation and processing, are a model system particularly well-suited for studying the extraction of significant information from noisy environments. Organisms and their environments form tightly coupled interacting systems in which all components: environmental characteristics and dynamics, sensory and physical morphology, peripheral and central neural processing and behavioural patterns, play a significant role. Hence, the analysis of hair-based sensing organs will need to be carried out at three levels simultaneously: the morphology and mechanics, the neuronal processing, and the behavioural strategies of the model-systems. We emphasize peripheral processing because we believe that knowledge of the transformations and processes performed by peripheral systems is essential for true understanding of the organisation and operation of central neuronal processing, as peripheral systems provide the input to central ones. In this workshop we want to bring together everybody interested in identifying the common principles underlying the widespread use in nature of arrays of mechanical sensory cells for the extraction of significant information as well as in making those principles available for design of engineered systems. From brefeld at informatik.hu-berlin.de Mon Mar 20 06:08:32 2006 From: brefeld at informatik.hu-berlin.de (Ulf Brefeld) Date: Mon, 20 Mar 2006 12:08:32 +0100 Subject: Connectionists: CFP: ICML Workshop on Learning in Structured Output Spaces Message-ID: <441E8D30.5080107@informatik.hu-berlin.de> -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: cfp-new.txt Url: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20060320/2485646c/cfp-new-0001.txt From oreilly at psych.colorado.edu Tue Mar 21 00:17:34 2006 From: oreilly at psych.colorado.edu (Randall C. O'Reilly) Date: Mon, 20 Mar 2006 22:17:34 -0700 Subject: Connectionists: Computational Cognitive Neuroscience: Call for Symposium Proposals In-Reply-To: <200507142326.20216.oreilly@psych.colorado.edu> References: <200507142326.20216.oreilly@psych.colorado.edu> Message-ID: <200603202217.34527.oreilly@psych.colorado.edu> ~ Call for Symposium Proposals ~ 2ND ANNUAL CONFERENCE ON COMPUTATIONAL COGNITIVE NEUROSCIENCE www.ccnconference.org To be held in conjunction with the 2006 PSYCHONOMIC SOCIETY CONFERENCE, November 16-19, 2006 at the Hilton Americas hotel in Houston, TX. The inaugural CCNC 2005 meeting held prior to Society for Neuroscience (SFN) in Washington, DC was a great success, with approximately 250 attendees, 60 presented posters, and strongly positive reviews. In subsequent years, it will be held on a rotating basis with other meetings, such as (tentative list): CNS (Cognitive Neuroscience Society), HBM (Organization for Human Brain Mapping), CogSci (Cognitive Science Society), (SFN) Society for Neuroscience, NIPS (Neural Information Processing Systems), and COSYNE (Computational and Systems Neuroscience). ____________________________________________________________________________ * DEADLINE FOR SUBMISSION OF SYMPOSIUM PROPOSALS: May 1, 2006 * DEADLINE FOR SUBMISSION OF ABSTRACTS: TBA * CONFERENCE DATES: Wed-Thu November 15 & 16, 2006 * This year's featured Keynote Speakers (confirmed): Mike Kahana, University of Pennsylvania Mark Seidenberg, University of Wisconsin Madison Each 2 hour symposium should be discussion oriented and include a mixture of modelers and non-modelers, all focused on a common theme or issue. At least half of the talks should focus on specific results from implemented models. A moderator acts as overall organizer/coordinator, and may also participate as one of 4-5 discussants. Each discussant should present a brief 20-30 minute talk, followed by plenty of time for discussion/Q & A. No particular proposal format is required. A 1-2 page description, including potential participants, is sufficient. Send by email (plain text preferred) to the Executive Organizer: Thomas Hazy . Questions regarding potential proposals are welcomed. ____________________________________________________________________________ 2006 Planning Committee: Suzanna Becker, McMaster University Jonathan Cohen, Princeton University Yuko Munakata, University of Colorado, Boulder David Noelle, Vanderbilt University Randall O'Reilly, University of Colorado, Boulder Maximilian Riesenhuber, Georgetown University Medical Center Executive Organizer: Thomas Hazy, University of Colorado, Boulder For more information and to sign up for the mailing list visit: www.ccnconference.org From Yaochu.Jin at honda-ri.de Tue Mar 21 09:40:28 2006 From: Yaochu.Jin at honda-ri.de (Yaochu.Jin@honda-ri.de) Date: Tue, 21 Mar 2006 15:40:28 +0100 Subject: Connectionists: Book announcement "Multi-Objective Machine Learning" Message-ID: Multi-Objective Machine Learning Series: Studies in Computational Intelligence, Vol. 16 Jin, Yaochu (Ed.) Springer 2006, XIII, 660 p. 255 illus., Hardcover ISBN: 3-540-30676-5 Table of Contents Part I Multi-Objective Clustering, Feature Extraction and Feature Selection 1. Multiobjective feature selection using rough set M. Banerjee, S. Mitra, and A. Anand 2. Multi-objective clustering and cluster validation J. Handl and J. Knowles 3. Feature selection for ensembles using the MOO approach L.S. Oliveira, M. Morita, and R. Sabourin 4. Feature extraction using multi-objective genetic programming Y. Zhang and P.I. Rockett Part II Multi-Objective Learning for Accuracy Improvement 5. Regression error characteristic optimization using multi-objective optimization J. E. Fieldsend 6. Regularization for parameter identifcation using multi-objective optimization T. Furukawa, C. Lee, J.G. Michpoulos 7. Multi-objective algorithms for nrural network learning A. Braga, R. Takahashi, M. Costa, R. de A. Teixeira 8. Generating support vector machine using multi-objective optimization and goal programming H. Nakayama, Y. Yun 9. Multi-objective optimization of support vector machines T. Suttorp and C. Igel 10. Multi-objecitve evolutionary algorithms for radial basis function neural network design G. G. Yen 11. Min imizing structural risk on decision tree classification D.-E. Kim 12. Multi-objective learning classifier systems E. Bernado-Mansilla, X. Llora, I. Traus Part III Multi-Objective Learning for Interpretability Improvement 13. Simultaneous generation of accurate and interpretable neural network classifiers Y. Jin, B. Sendhoff, E. Koerner 14. GA-based Pareto optimization for rule extraction from neural networks U. Markowska-Kaczmar, K. Mularczyk 15. Agent based multi-objective approach to generating interpretable fuzzy systems H. Wang, S. Kwong, Y. Jin, C.-H. Tsang 16. Multi-objective evolutionary algorithms for temporal linguistic rule extraction G.G. Yen 17. Multiple objective learning for constructing interpretable TS fuzzy model S.M. Zhou, J.Q. Gan Part IV Multi-Objective Ensemble Generation 18. Pareto-optimal approaches to neuro-ensemble learning H. Abbass 19. Trade-off between diversity and accuracy in ensemble generation A. Chandra, H. Chen, X. Yao 20. Cooperative coevolution of neural networks and ensemble of neural networks N. Garcia-Pedrajas 21. Multi-objective structure selection for RBF networks and its application to nonlinear system identification T. Hatanaka, N. Kondo, K. Uosaki 22. Fuzzy ensemble design through multi-objective fuzzy rule selection H. Ishibuchi, Y. Nojima Part V Applications of Multi_objective Machine Learning 23. Multi-objective optimization for receiver operating characterics analysis R.M. Everson, J.E. Fieldsend 24. Multi-objective design of neuro-fuzzy controllers for robot behavior coordination N. Kubota 25. Fuzzy tuning for docking maneuver Controller of an automated guided vehicle J.M. Lucas, H. Martinez, F. Jimenez 26. A multi-objective genetic algorithm for learning linguistic persistent queries in text retrieval environments M. Luque, O. Cordon, E. Herrera-Viedma 27. Multi-objective neural network optimization for visual object detection S. Roth, A. gepperth, C. Igel Index From d.mareschal at bbk.ac.uk Wed Mar 22 04:52:43 2006 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Wed, 22 Mar 2006 09:52:43 +0000 Subject: Connectionists: PhD in Neurocomputational models of early learning Message-ID: Dear all, Please circulate the following information as appropriate. Many thanks, Denis Mareschal ------------------------------------------ A funded 3 year Phd position is available for outstanding candidates wishing to complete a project investigating the the neurocomputational mechanisms of perceptual learning memory in early infancy. A suitable candidate would have a background in neuroscience, psychology, AI or related fields. Fellows will be hosted at the Centre for Brain and Cognitive Development (CBCD), within the School of Psychology, Birkbeck University of London. Details of the Centre's and affiliated lab's activities can be found at http://www.cbcd.bbk.ac.uk/cbcd.html. The CBCD has the mission to investigate relations between postnatal brain development and changes in perceptual, cognitive, and linguistic abilities from birth through childhood and late adulthood. Research in intrinsically multidisciplinary and involves behavioural testing, ERP, fMRI, NIRS, and computational neural network modelling with typically and atypically developing children as well as adult patient populations. Successful applicants cannot have resided more than 1 year within the last 3 in the UK. Ordinarily, applications will only be considered from citizens or long-term residents of the EU or affiliated states who are not citizens or residents of the UK. Other eligibility requirements may apply. Minimum English language standards apply for all PhD candidates to the University of London. Successful candidate will be expected to have sufficient written English skill to undertake the writing of a long document in English. Equal Opportunity Birkbeck is an equal opportunity employer. We particularly encourage application from women and recognise the differing life patterns of men and women in the work and trainings sectors. Qualifications The fellowships are open to truly outstanding candidates who must have achieved at least a level of training that would enable them to qualify for entry into a PhD programme in their home country. As the PhD must be completed within the 3 years of the fellowships we anticipate that successful candidate will have already obtained a substantial amount of training in relevant research methods. Conditions of employment Successful candidates will be employed as research assistants within the school of Psychology, Birkbeck University of London. Their salary will be the sterling equivalent of approximately ?32k per annum plus a minimum of ?6k Mobility Allowance per annum. They will also receive an annual payment as a Travel Allowance, and ?2k as a Career Exploratory Allowance paid upon completion of the first 12 months of your appointment. All payments are determined by personal circumstance, details of actual salary and allowances can be obtained upon request Application procedures Interested applicants should consult the relevant web pages of the CBCD and affiliated Labs first to assess whether their research interests and experience match those of relevant possible supervisors. Applications will then be made through the School of Psychology MPhil/PhD Programme (http://www.psyc.bbk.ac.uk/courses/phd_research/). Application forms can be obtained from Ms. Mina Daniels (s.daniels at bbk.ac.uk) or they can be downloaded directly form the Birkbeck web pages by following the links on (http://www.bbk.ac.uk/for/prospective/full-time/research). When applying, candidates should make it clear on their application form that they wish to be considered for a Marie Curie Studentship. Applications should be submitted not later than March 31st 2006. A small short list of candidates drawn form those received by this date will be invited to London for interviews approximately 4 to 6 weeks following this date. However, we will continue to consider applications until all 6 positions have been filled. We will announce when the position have been filled on the CBCD web pages cited above. Informal enquires can be made to Dr. Denis Mareschal (d.mareschal at bbk.ac.uk). Procedural or administrative enquires regarding the application procedures or conditions of employment should be made to he Marie Curie Administrator Ms Katherine Jones (k.jones at bbk.ac.uk) -- ================================================= Dr. Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 (0)20 7631-6582/6226 reception: 6207 fax +44 (0)20 7631-6312 http://www.psyc.bbk.ac.uk/people/academic/mareschal_d/ ================================================= From zhaoping at gatsby.ucl.ac.uk Wed Mar 22 13:18:02 2006 From: zhaoping at gatsby.ucl.ac.uk (Dr Zhaoping Li) Date: Wed, 22 Mar 2006 18:18:02 +0000 (GMT) Subject: Connectionists: Papers available on visual input sampling and information theory Message-ID: Two papers are available for download: Lewis A. and Zhaoping L. (2006) Are cone sensitivities determined by natural color statistics? Journal of vision, 6(3):285-302. download from http://journalofvision.org/6/3/8/ Lewis A. Garcia R. and Zhaoping L. (2003) The distribution of visual objects on the retina: connecting eye movements and cone distributions Journal of Vision 3(11), p. 893-905. Download from http://www.journalofvision.org/3/11/21/ Related papers available at http://www.gatsby.ucl.ac.uk/~zhaoping/visualcoding.html From ted.carnevale at yale.edu Wed Mar 22 13:51:27 2006 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Wed, 22 Mar 2006 13:51:27 -0500 Subject: Connectionists: Parallel network simulations at the NEURON Simulator Meeting Message-ID: <44219CAF.3040005@yale.edu> The registration deadline (April 21) for the 2006 NEURON Simulator Meeting is rapidly approaching! For more information see http://www.utexas.edu/neuroscience/NEURON2006/nsm2006.html One of the featured speakers is Michael Hines, who will present a tutorial and run a workshop on using NEURON to implement network models that are distributed over multiple processors. Tutorial Title: Parallel network simulations with NEURON Abstract: Parallel network management services (i.e. the ability to create and execute network models that are distributed over multiple processors) are now available when NEURON is configured with the --with-mpi option. We have run extensive tests using published network models of conductance based neurons, on parallel hardware with dozens to thousands of CPUs. These tests demonstrate speedup that is linear with the number of CPUs, or even superlinear (due to larger effective high speed memory cache), until there are so many CPUs that each one is solving fewer than ~100 equations. Workshop Title: Implementing parallel network simulations with NEURON Abstract: This workshop is devoted to teaching how to transform serial network NEURON models into a parallel program. Transformation turns out to be fairly straightforward if the network model was originally developed from a synapse-centric or target cell viewpoint. In other words, since a NetCon that connects to a target cell exists only on the CPU where the target cell exists, it is easier if one organizes the code around the question "who projects to me?" than from the source cell perspective "to whom do I project?". The discussion will cover important practical and theoretical considerations, including the following: --mpi installation and building NEURON on Beowulf clusters and other multiprocessor systems --how to handle random connections and random spike inputs in a way that preserves double precision quantitative identity regardless of number of CPUs and how cells are distributed among the CPUs --how to measure performance From marcilio at dimap.ufrn.br Thu Mar 23 09:25:13 2006 From: marcilio at dimap.ufrn.br (Marcilio Carlos P. de Souto) Date: Thu, 23 Mar 2006 11:25:13 -0300 Subject: Connectionists: SBRN 2006: Deadline extension In-Reply-To: <20060323131202.M15909@dimap.ufrn.br> References: <20060323131202.M15909@dimap.ufrn.br> Message-ID: <20060323142454.M24171@dimap.ufrn.br> ********************************************************************** SBRN'2006 - IX BRAZILIAN SYMPOSIUM ON NEURAL NETWORKS Ribeirao Preto, October 23-26, 2006 http://www.icmc.usp.br/iarn2006/sbrn.php ********************************************************************** Due to several requests for a deadline extension, the new deadlines are: Registration: April 02, 2006, 23: 55 BRST (Extended Deadline) Submission: April 02, 2006, 23:55 BRST (Extended Deadline) Acceptance: May 24, 2006 Camera-ready: June 12, 2006 Program Chair: Anne Mag?ly de Paula Canuto (UFRN/DIMAp, Brazil) anne at dimap.ufrn.br _______________________________________________ Sbc-l mailing list Sbc-l at inf.ufrgs.br https://listas.inf.ufrgs.br/mailman/listinfo/sbc-l ------- End of Forwarded Message ------- -- Open WebMail Project (http://openwebmail.org) Debian Project (http://www.debian.org) From kfm at androidscience.com Wed Mar 22 09:55:57 2006 From: kfm at androidscience.com (Karl F. MacDorman) Date: Wed, 22 Mar 2006 09:55:57 -0500 Subject: Connectionists: External Symbol Grounding Workshop 2006 Message-ID: <002201c64dc0$bb7ae1d0$650fa8c0@anon> Call for papers External Symbol Grounding Workshop 2006 3 and 4 July 2006, University of Plymouth, Plymouth, United Kingdom http://www.tech.plym.ac.uk/SoCCE/ESG2006/ The External Symbol Grounding Workshop 2006 (ESG2006) is an international workshop for research on grounding external signs and symbols. Specifically, we wish to invite contributions viewing language and cognition as linking what goes on in the head with causal processes that are intersubjective, multimodal, affect-laden, and organised by historically rooted customs and artefacts. We aim to bring together linguists, psychologists, ethologists and social biologists, social and cognitive neuroscientists, philosophers, computer scientists, and roboticists for an intense two days of presenting and discussing (potentially incompatible) views. The purpose of the workshop is not so much to present completed work as to find new ways of tackling a complex issue and to launch collaboration among participants to that end. Since the workshop focuses on how symbol grounding can be reconsidered when language is viewed as a dynamical process rooted in both culture and biology, research related to robotic or computer modelling of symbol grounding, psychological and linguistic viewpoints on cognitive development and semiotic dynamics are of great interest. We have invited a range of speakers who will bring their specialised expertise to bear on the issue of external symbol grounding, and we are looking for additional researchers who would like to contribute to this exciting new initiative. ESG2006 is the successor to the first Distributed Language Group?s Conference on Cognitive Dynamics and the Language Sciences, held at Sidney Sussex College, Cambridge on 9-11 September 2005. Special issue Participants will be invited to submit papers to Interaction Studies for the special issue on external symbol grounding to be published in 2007. Papers will be selected based on an independent peer review. Important dates Deadline for submission of two-page abstract (or paper): 15 April 2006 Notification of acceptance: 1 May 2006 Workshop: 3 and 4 July 2006 Submission instructions Authors are invited to submit a two page abstract for presentation at the workshop. Alternatively, they may submit papers that are not to exceed 12 pages. Submitted abstracts and papers will be refereed and selected for half-hour oral presentations on the basis of quality and relevance to issues surrounding the external grounding of signs and signals. Accepted papers will be included in the proceedings and will be made accessible through the web. Copies of the proceedings will be available at the workshop. Authors are strongly encouraged to submit their papers electronically (MS Word or PDF preferred). Please email your submission to ESG2006 at plymouth.ac.uk. If you cannot send your submission through email, please send a hardcopy to Stephen J. Cowley School of Psychology University of Hertfordshire College Lane AL10 9AB Hatfield United Kingdom The deadline for submission is 15 April 2006. Confirmed speakers Michael Anderson (University of Maryland, MD, USA) Angelo Cangelosi (University of Plymouth) Stephen Cowley (University of Hertfordshire) Stevan Harnad (Universit? du Qu?bec ? Montr?al, provisional) Karl MacDorman (Indiana University, IN, USA) David Spurrett (University of KwaZulu-Natal, South Africa) Paul Thibault (Agder University College, Kristiansand, Norway) Paul Vogt (University of Tilburg, The Netherlands) From dancoisne at bccn.uni-freiburg.de Fri Mar 24 03:48:43 2006 From: dancoisne at bccn.uni-freiburg.de (Florence Dancoisne) Date: Fri, 24 Mar 2006 09:48:43 +0100 Subject: Connectionists: Announcement for the Advanced Course in Computational Neuroscience 2006 Message-ID: <4423B26B.9090203@bccn.uni-freiburg.de> *ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE* *(A PENS NEUROSCIENCE SCHOOL)* *August 7th -- September 1st 2006, ARCACHON, FRANCE* *DIRECTORS: *Ad Aertsen (BCCN Freiburg, Germany) Peter Dayan (UCL London, UK) Nicolas Brunel (CNRS, Paris, France) Israel Nelken, (Hebrew University Jerusalem, Israel) *LOCAL ORGANIZER*: Gwendal Le Masson (INSERM Bordeaux, France) The Advanced Course in Computational Neuroscience is for advanced graduate students and postdoctoral fellows who are interested in learning the essentials of the field. We seek students of any nationality from a variety of disciplines, including neuroscience, physics, electrical engineering, computer science, mathematics and psychology. Students are expected to have a keen interest and basic background in neurobiology as well as some computer experience. The course has two complementary parts. Mornings are devoted to lectures given by distinguished international faculty on topics across the breadth of experimental and computational neuroscience. During the rest of the day, students are given practical training in the art and practice of neural modelling, largely through the medium of their individual choice of model systems. The first week of the course introduces students to essential neurobiological concepts and to the most important techniques in modelling single cells, networks and neural systems. Students learn how to solve their research problems using software packages such as MATLAB, NEST, NEURON, XPP, etc. During the following three weeks the lectures cover specific brain areas and functions. Topics range from modelling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the brain. The course ends with project presentations by the students. A maximum of 30 students will be accepted. There will be a minimum fee of EUR 500 per student (depending on the course's funding) covering costs for lodging, meals and other course expenses. Also depending on funding, there will be a limited number of tuition fee waivers and travel stipends available for students who need financial help for attending the course. We specifically encourage applications from researchers who work in the developing world. These students will be selected following the normal submission procedure. Applications, including a description of the target project must be submitted electronically (see below) and should be accompanied by the names and email details of two referees who have agreed to furnish references. Applications will be assessed by a committee, with selection being based on the following criteria: the scientific quality of the candidate (CV) and of the project, the recommendation letters, and evidence that the course affords substantial benefit to the candidate's training. More information and application forms can be obtained from: http://www.neuroinf.org/courses/EUCOURSE/EU06 * Please apply electronically using a web browser.* Contact address: - mail: Florence Dancoisne, Bernstein Center for Computational Neuroscience Freiburg Albert-Ludwigs-Universit?t Freiburg Hansastrasse 9A 79104 Freiburg, Germany - e-mail: dancoisne at bccn.uni-freiburg.de From andreas at cs.ntua.gr Fri Mar 24 06:17:35 2006 From: andreas at cs.ntua.gr (andreas) Date: Fri, 24 Mar 2006 13:17:35 +0200 Subject: Connectionists: ICANN 2006 Final Call for Papers Message-ID: <200603241117.k2OBHfQX016835@theseas.softlab.ece.ntua.gr> Final Call for Papers ****** One week to deadline ****** International Conference on Artificial Neural Networks (ICANN 06) ****** The deadline for submission of papers (abstract + full paper) to regular sessions has been extended to 31 March 2006 ***** 10-14 September 2006 Holiday Inn Hotel, Athens, Greece ********Conference Framework******** The 16th International Conference on Artificial Neural Networks, ICANN 2006, will be held from September 10 to September 14, 2006, at the Holiday Inn Hotel, Athens Greece. ICANN is an annual conference organized by the European Neural Network Society in cooperation with the International Neural Network Society, Japanese Neural Network Society, and the IEEE Computational Intelligence Society, and is a premier European event in all topics related to neural networks. ICANN 2006 (www.icann2006.org) welcomes contributions on the theory, algorithms, applications and implementations in the following broad areas: -Computational neuroscience; -Connectionist cognitive science; -Data analysis and pattern recognition; -Graphical networks models, Bayesian networks; -Hardware implementations and embedded systems; -Neural and hybrid architectures and learning algorithms; -Neural control, reinforcement learning and robotics applications; -Neuroinformatics; -Neural dynamics and complex systems; -Real world applications; -Robotics, control, planning; -Signal and time series processing; -Self-organization; -Vision and image processing; -Web semantics; -Intelligent Multimedia and the Semantic Web. Ideas and nominations for interesting tutorials, special sessions, workshops and experts willing to organize various session tracks are called for. Most active experts will be included in the scientific committee of the conference. Proceedings of ICANN will be published in Springer's "Lecture Notes in Computer Science". Paper length is restricted to a maximum of 10 pages, including figures. ********Deadlines and Conference dates******** 06.01 Submission page opens 31.03 End of submission of papers (abstract+full paper) to regular sessions 31.03 End of submission of papers to special sessions 30.04 Acceptance/rejection notification 15.06 Deadline for camera ready papers 01.07 Deadline for early registration 10.09 Tutorials - first day of the conference 11-13.09 Main part of the conference 14.09 Workshops For further information and/or contacts, send inquiries to Prof. Stefanos Kollias (stefanos at cs.ntua.gr) Prof Andreas Stafylopatis (andreas at cs.ntua.gr) School of Electrical & Computer Engineering National Technical University of Athens 9, Heroon Polytechniou str., 157 80 Zografou, Athens, Greece. General Chair Stefanos Kollias, National Technical University of Athens (NTUA), Greece Co-Chair Andreas Stafylopatis, NTUA, Greece Program Chair Wlodzislaw Duch, Torum, PL & Singapore; ENNS President-elect Erkki Oja, Helsinki, FI; ENNS President Honorary Chair John G. Taylor, Kings College, London, UK; ENNS Past President ********International Program Committee******** -Hojjat Adeli, Ohio State University, USA -Peter Andras, U. Newcastle, UK -Marios Angelides, Brunel University, UK -Panos Antsaklis, U. N. Dame, USA -Bruno Apolloni, University of Milan, IT -Nikolaos Bourbakis, Wright State Univ., USA -Peter Erdi, Univ. Budapest, HU & Kalamazoo -Georg Dorffner, Univ. Wien, AT -Jose Derronsoro, Universidad Autonoma de Madrid, ES -Christophe Garcia, France T?l?com -Erol Gelenbe, Imperial College London, UK -Stan Gielen, Univ. Nijmegen, NL -Janusz Kacprzyk, Warsaw, PL -Nikola Kasabov, Kedri, AUT, NZ -Okyay Kaynak, Bogazici Univ., TR -Chris Koutsougeras, Tulane University, USA -Thomas Martinetz, Luebeck, DE -Evangelia Micheli-Tzanakou, Rutgers University, USA -Lars Niklasson, Sk?vde, SE -Andreas Nuernberger, University of Magdenburg, DE -Marios Polycarpou, Univ. of Cyprus, CY -Demetris Psaltis, Caltech, USA -Branimir Reljin, University of Belgrade, YU -Olli Simula, Espoo, FI -Alessandro Sperduti, U.Padova, IT -Lefteris Tsoukalas, Purdue Uni, USA -Michel Verleysen, Louvain-la-Neuve, BE -Alessandro Villa, U. Grenoble, FR ********Local Organizing Committee******** -Yannis Avrithis, NTUA -Christos Douligeris, Piraeus Univ -George Dounias, Aegean Univ -Kostas Karpouzis, ICCS-NTUA -Aris Likas, Univ. of Ioannina -Kostas Margaritis, Univ. Macedonia -Basil Mertzios, DUTH and ATIT -Stavros Perantonis, NCSR, Athens -Yannis Pitas, AUTH, Salonica -Costas Pattichis, Univ. of Cyprus -Apostolos Paul Refenes, Athens University Economics & Business -Christos Schizas, Univ. of Cyprus -Thanos Skodras, Univ. of Patras -Kostas Spyropoulos, NCSR, Athens -Giorgos Stamou, ICCS-NTUA -Sergios Theodoridis, UoA -Spyros Tzafestas, NTUA -Mihalis Zervakis, TUC, Crete From dgw at MIT.EDU Fri Mar 24 14:58:57 2006 From: dgw at MIT.EDU (David Weininger) Date: Fri, 24 Mar 2006 14:58:57 -0500 Subject: Connectionists: Book announcement - De Jong Message-ID: <6.2.3.4.2.20060324145811.044a2a80@po14.mit.edu> Hi all: I thought readers of Connectionists might be interested in this book. For more information, please visit http://mitpress.mit.edu/promotions/books/SP20060262041944 Thanks! Best, David Evolutionary Computation A Unified Approach Kenneth A. De Jong Evolutionary computation, the use of evolutionary systems as computational processes for solving complex problems, is a tool used by computer scientists and engineers who want to harness the power of evolution to build useful new artifacts, by biologists interested in developing and testing better models of natural evolutionary systems, and by artificial life scientists for designing and implementing new artificial evolutionary worlds. In this clear and comprehensive introduction to the field, Kenneth De Jong presents an integrated view of the state of the art in evolutionary computation. Although other books have described such particular areas of the field as genetic algorithms, genetic programming, evolution strategies, and evolutionary programming, Evolutionary Computation is noteworthy for considering these systems as specific instances of a more general class of evolutionary algorithms. This useful overview of a fragmented field is suitable for classroom use or as a reference for computer scientists and engineers. Kenneth A. De Jong is Professor of Computer Science, Head of the Evolutionary Computation Laboratory, and Associate Director of the Krasnow Institute at George Mason University. He is the founding editor of the journal Evolutionary Computation (MIT Press). 7 x 9, 250 pp., XX illus., cloth ISBN 0-262-04194-4, A Bradford Book David Weininger Associate Publicist MIT Press 55 Hayward Street Cambridge, MA 02142-1315 617.253.2079 617.253.1709 fax dgw at mit.edu Check out the new MIT Press Log http://mitpress.mit.edu/presslog From ale at sissa.it Fri Mar 31 05:14:21 2006 From: ale at sissa.it (Alessandro Treves) Date: Fri, 31 Mar 2006 12:14:21 +0200 Subject: Connectionists: EBBS Call for Symposia: Trieste, Sept 16-19, 2007 Message-ID: <1143800061.442d00fd178f1@webmail.sissa.it> European Brain and Behaviour Society - CALL for SYMPOSIA for the 39th Annual General Meeting, Trieste, September 16-19, 2007 The EBBS meeting is open to all scientists from around the world interested in how the brain produces behaviour, from integrative, cognitive, systems, computational neuroscience - and beyond. Based on previous meetings, we expect ca. 500 participants, many of whom will be new to EBBS meetings. The program includes 6 invited plenary speakers, 14 symposia with 4 talks each, and hundreds of posters presented over extended daily sessions. SISSA, the International School for Advanced Studies of Trieste, Italy and ICTP, the Abdus Salam International Centre for Theoretical Physics, will host the meeting at their attractive campus next to the Miramar castle and it park, 8 km north of Trieste along the coast. You will reach it every morning from hotels at the seafront downtown, by bus, by train, or by boat (or windsurf). Symposia are selected by the program committee among those proposed by you, whether you are an EBBS member or not, by the June 15, 2006 DEADLINE. All 4 half-hour speakers in a symposium are waived the registration fee. Moshe Abeles, Jocelyne Bachevalier, Barry Everitt, Pierre Maquet and Faraneh Vargha-Khadem will give plenary lectures, and Susumu Tonegawa will give an opening Nobel lecture on Sat evening, Sept 15. The rest depends on you. Do contribute to the success of the meeting by taking a few easy steps: * Insert the website http://www.sissa.it/~ale/EBBS2007/ among your browser?s favorites * Forbid your dear ones from getting married or falling ill on September 15-19, 2007 * Submit your top-quality proposals to our Call for Symposia by the deadline of June 15, 2006 * Produce over the next year-and-a-half the best science of your life, and present it in Trieste Welcome to Miramar! -- Alessandro Treves SISSA - Cognitive Neuroscience, now downtown in via Stock 2/2, V fl BUT NOTE, POSTAL ADDRESS: SISSA, via Beirut 2, 34014 Trieste, Italy tel:39-040-3787623 fax:39-040-3787615 http://www.sissa.it/~ale/ ---------------------------------------------------------------- SISSA Webmail https://webmail.sissa.it/ Powered by Horde http://www.horde.org/ From BerndPorr at f2s.com Thu Mar 30 16:28:18 2006 From: BerndPorr at f2s.com (Bernd Porr) Date: Thu, 30 Mar 2006 22:28:18 +0100 Subject: Connectionists: Paper: Towards Closed Loop Information Message-ID: <442C4D72.9000102@f2s.com> I'm pleased to inform you that a paper about closed loop information is available online: http://www.univie.ac.at/constructivism/journal/1.2/ in the journal Constructivist Foundations: Towards Closed Loop Information: Predictive Information Bernd Porr, Alice Egerton and Florentin W?rg?tter Motivation: Classical definitions of information, such as the Shannon information, are designed for open loop systems because they define information on a channel which has an input and an output. The main motivation of this paper is to present a closed loop information measure which is compatible with constructivist thinking. Design: Our information measure for a closed loop system reflects how additional sensor inputs are utilised to establish additional sensor-motor loops during learning. Our information measure is based on the assumption that it is not optimal to stay reactive and that it is beneficial to become proactive through increased learning about the environment. Consequently our information measure gauges the utilisation of new sensor inputs to generate anticipatory actions. We call this information measure "predictive information" (PI). Findings: Our PI is zero if the organism uses only its reflex reactions. It grows when the organism is able to use other sensor inputs to preempt reflex reactions and is able to replace reflexes by anticipatory reactions. This has been demonstrated with a real robot that had to learn to avoid obstacles. Conclusion: PI is a new measure which is able to quantify anticipatory learning and, in contrast to the Shannon information, is calculated only at the inputs of an agent. This information measure has been successfully applied to a simple robot task but its application is neither limited to a certain task nor to a certain learning rule. Keywords: Closed loop system, information measure, differential Hebbian learning, reactive vs proactive systems . About the journal: Constructivist Foundations (CF) is an independent academic peer-reviewed e-journal without commercial interests. Its aim is to promote scientific foundations and applications of constructivist sciences, to weed out pseudoscientific claims and to base constructivist sciences on sound scientific foundations, which do not equal the scientific method with objectivist claims. The journal is concerned with the interdisciplinary study of all forms of constructivist sciences, especially radical constructivism, cybersemiotics, enactive cognitive science, epistemic structuring of experience, second order cybernetics, the theory of autopoietic systems, etc. -------------------- Apologies for mutiple postings. Regards /Bernd Porr -- www: http://www.berndporr.me.uk/ http://www.linux-usb-daq.co.uk/ Mobile: +44 (0)7840 340069 Work: +44 (0)141 330 5237 University of Glasgow Department of Electronics & Electrical Engineering Room 519, Rankine Building, Oakfield Avenue, Glasgow, G12 8LT From carl at tuebingen.mpg.de Wed Mar 29 08:40:15 2006 From: carl at tuebingen.mpg.de (Carl Edward Rasmussen) Date: Wed, 29 Mar 2006 15:40:15 +0200 (CEST) Subject: Connectionists: Matlab code for Gaussian process prediction Message-ID: We would like to announce the availability of matlab code implementing the main algorithms from our recent book "Gaussian Processes for Machine Learning" from MIT Press. The code is available via: http://www.GaussianProcess.org/gpml The programs implement regression and classification. Standard regression as well as some sparse approximations are provided. Binary classification is implemented using both the Laplace approximation and the Expectation Propagation algorithm. The code supports a variety of different covariance functions and learning of hyperparamters using the marginal likelihood. Demo scripts are provided to illustrate the use of the functions. Carl Edward Rasmussen & Chris Williams From king at cse.cuhk.edu.hk Fri Mar 31 04:47:28 2006 From: king at cse.cuhk.edu.hk (Irwin King) Date: Fri, 31 Mar 2006 17:47:28 +0800 Subject: Connectionists: CFP: ICONIP2006 Call For Papers & Call For Proposals Message-ID: ******************************************************************** Upon the requests from numerous authors, the Organizing Committee of ICONIP2006 has decided to extend the deadline for papers and Special Session proposals to April 21, 2006. In addition to the multi-volume proceedings published by Springer's Lecture Notes in Computer Science (LNCS), the following journals will have special issues featuring selected papers from ICONIP2006: * Neurocomputing * Journal of Intelligent Information Systems * Pattern Analysis and Applications * International Journal of Pattern Recognition and Artificial Intelligence * Neural Information Processing-Letters & Reviews ******************************************************************** I C O N I P 2 0 0 6 D E A D L I N E E X T E N D E D CALL FOR PAPERS AND PROPOSALS 13th International Conference on Neural Information Processing (ICONIP2006) Hong Kong Convention and Exhibition Centre, Hong Kong October 3-6, 2006 http://www.iconip2006.org/ http://iconip2006.cse.cuhk.edu.hk/ Paper Submission Site https://conference.cse.cuhk.edu.hk/iconip2006/login.php ******************************************************************** The Thirteenth International Conference on Neural Information Processing (ICONIP2006) sponsored by the Asia Pacific Neural Network Assembly (APNNA) and organized by The Chinese University of Hong Kong, will be held in Hong Kong on October 3-6, 2006. You are invited to visit this vibrant and dynamic metropolitan to share the progress and research in neural computation, statistical processing, machine learning, and other related topics. ICONIP2006 will include plenary speakers, invited talks, tutorials, special sessions, as well as highly selected oral and poster presentations of refereed papers. In addition, conference social events along with other local attractions will promote interactions among conference delegates. ******************************************************************** Important Dates Paper submission deadline (extended): April 21, 2006 Special session proposal (extended): April 21, 2006 Tutorial proposal May 20, 2006 Workshop proposal June 10, 2006 Notification of acceptance: June 1, 2006 Final paper submission: July 1, 2006 ******************************************************************** Awards & Grants Best Paper Awards and Best Student Paper Awards will be given at ICONIP2006 based on the reviews and presentations at the conference. Travel grants will also be given to a number of selected student registrants at the conference. ******************************************************************** Proposals Submission For paper submission: https://conference.cse.cuhk.edu.hk/iconip2006/login.php For those who are interested in Speical Sessions, please find the related materials from the link below: http://iconip2006.cse.cuhk.edu.hk/callforproposals/CFPSS For those who are interested in Tutorial Proposoals, please find the related materials from the link below: http://iconip2006.cse.cuhk.edu.hk/callforproposals/CFPTuto For those who are interested in Workshop Proposoals, please find the related materials from the link below: http://iconip2006.cse.cuhk.edu.hk/callforproposals/CFPworkshop ******************************************************************** Paper Submission Authors are invited to submit research and application papers representing original, previously unpublished work to ICONIP2006. Submissions are solicited in all areas of neural information processing, including (but not limited to) the following: Neural Network Theory & Models -Mathematics of neural networks; -Advanced learning algorithms/models; -Neurodynamics; -Stability and convergence analysis; -Feedforward neural networks; -Recurrent neural networks; -Evolving neural networks; -Self-organizing networks; -Reinforcement learning; -PCA and ICA; -EM algorithm and mixture models; -Ensemble learning; -Kernel methods and support vector machine Computational Neuroscience and Cognitive Science -Models of neurons; -Simulation of neurons, networks, and systems; -Neuroinformatics; -Cognitive learning and memory; -Attention and consciousness; -Language; -Emotion and motivation; -Perceptual systems Neural Network Applications -Vision and image processing; -Pattern recognition; -Auditory processing; -Speech processing/recognition; -Robotics and control; -Biometric and security; -Time-series prediction; -Financial engineering; -Telecommunication; -Manufacturing systems; -Bioinformatics; -Data mining/Web mining; -Multimedia and information processing Hybrid Systems and Hardware -Fuzzy neural systems; -Hybrid systems; -Genetic algorithms; -Evolutionary programming; -Reconfigurable systems; -Hardware implementation Web links to supplementary materials (e.g., software, audio, video, etc.) in the manuscripts are encouraged. However, the manuscript must be self-contained and reviewers will not be required to review the supplementary materials. Accepted papers will be published in Lecture Notes in Computer Science (LNCS) by Springer-Verlag. In addition, selected papers from ICONIP2006 will be published with expansion after further review in speical issues of Neurocomputing, Journal of Intelligent Information Systems, Pattern Analysis and Applications, International Journal of Pattern Recognition and Artificial Intelligence, and Neural Information Processing-Letters & Reviews. ******************************************************************** Paper Format Submissions must not exceed 10 pages in length in the Acrobat PDF format, including figures, tables, references, and appendices, using a font no smaller than 10 point. The final version of accepted papers may be up to 12 pages with extra page charges. All submissions must strictly follow the LNCS style, which is available at: under "Information for LNCS Authors". Submissions violating these requirements will not be considered. ******************************************************************** Honorary Co-Chairs ------------------ Lei Xu Shun-ichi Amari General Co-Chairs ----------------- Jun Wang Laiwan Chan Advisory Board -------------- Walter J. Freeman; Toshio Fukuda; Kunihiko Fukushima; Tom Gedeon; Zhen-ya He; Nik Kasabov; Okyay Kaynak; Anthony Kuh; Sun-Yuan Kung; Soo-Young Lee; Chin-Teng Lin; Erkki Oja; Nikhil R. Pal; Marios M. Polycarpou; Shiro Usui; Benjamin W. Wah; Lipo Wang; Shoujue Wang; Paul J. Werbos; You-Shou Wu; Donald C. Wunsch II; Xin Yao; Yixin Zhong; Jacek M. Zurada Program Committee ----------------- Irwin King DeLiang Wang Shigeo Abe; Peter Andras; Sabri Arik; Ke Chen; Liang Chen; Zheru Chi; Sung-Bae Cho; Sungzoon Cho; Andrzej Cichocki; Chuangyin Dang; Takeshi Furuhashi; Artur d'Avila Garcez; Daniel W.C. Ho; Sanqing Hu; Guang-Bin Huang; Kaizhu Huang; James Tin-Yau Kwok; James Lam; Minho Lee; Xun Liang; Xiaofeng Liao; Chih-Jen Lin; Xiuwen Liu; Wenlian Lu; Jinwen Ma; Sushmita Mitra; Paul S. Pang; Jagath Rajapakse; Michael Small; Michael Stiber; P. N. Suganthan; Fuchun Sun; Ron Sun; Johan A.K. Suykens; Norikazu Takahashi; Michel Verleysen; Si Wu; Hujun Yin; Gerson Zaverucha Organizing Committee -------------------- Man-Wai Mak (Organizing Chair) Kai-Pui Lam (Finance and Registration Chair) James Kwok (Workshop and Tutorial Chair) Frank H. Leung (Publications and Special Sessions Co-Chairs) Jianwei Zhang (Publications and Special Sessions Co-Chairs) Chris C. Yang (Publicity Co-Chairs) Jeffrey Xu Yu (Publicity Co-Chairs) Derong Liu (Publicity Co-Chairs) Wlodzislaw Duch (Publicity Co-Chairs) Andrew Chi-Sing Leung (Local Arrangements Co-Chairs) Eric Yu (Local Arrangements Co-Chairs) ******************************************************************** Confirmed Plenary Speakers Shun-ichi Amari, RIKEN Brain Science Institute, Japan More to come ... ******************************************************************** Enquiry and Information For general questions, please contact: ICONIP2006 Secretariat Dept. of Computer Science & Engineering The Chinese University of Hong Kong Shatin, NT, Hong Kong http://www.iconip2006.org/ E-mail: iconip06 at cse.cuhk.edu.hk Phone: +852 2609 8444 Fax: +852 2603 5420 For questions related to technical programs, please contact: Irwin King: king at cse.cuhk.edu.hk For questions related to workshops and tutorials, please contact: James Kwok: jamesk at cs.ust.hk For questions related to special sessions, please contact: Frank H. Leung: enfrank at inet.polyu.edu.hk For questions related to organization, please contact: Manwai Mak: enmwmak at polyu.edu.hk From juergen at idsia.ch Fri Mar 31 03:17:15 2006 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Fri, 31 Mar 2006 10:17:15 +0200 Subject: Connectionists: source code of Optimal Ordered Problem Solver Message-ID: Due to frequent requests, source code for the experiments described in "Optimal Ordered Problem Solver. Machine Learning 54, 211-254, 2004" was released under the terms of the GNU public license: http://www.idsia.ch/~juergen/oops.html -Juergen From p.husbands at sussex.ac.uk Fri Mar 31 08:12:58 2006 From: p.husbands at sussex.ac.uk (Phil Husbands) Date: Fri, 31 Mar 2006 14:12:58 +0100 Subject: Connectionists: Funded PhD places at Sussex University Message-ID: Funded PhD places are available in the department of Informatics, University of Sussex. Studentships are available in various areas of Computer Science, AI and Cognitive Science including adaptive systems, bioinformatics, computational neuroscience and machine learning. For further details, including how to apply, see Funded places are also available on our MSc in Evolutionary and Adaptive Systems. From tt at cs.dal.ca Thu Mar 30 08:06:42 2006 From: tt at cs.dal.ca (Thomas Trappenberg) Date: Thu, 30 Mar 2006 09:06:42 -0400 Subject: Connectionists: Faculty positions in Computer Science at Dalhousie University, Canada Message-ID: <20060330130642.C8070B00B@mail.cs.dal.ca> Colleagues, I would like to bring to your attention that we have openings for outstanding researchers at the Faculty of Computer Science at Dalhousie University in Halifax, Canada. Halifax is a wonderful city to live in and Dalhousie University is a major University in Atlantic Canada with active research programs in Computer Science, Neuroscience and Cognitive Science (among others). The openings are for prestigious Canada Research Chairs, either at a junior level (Ph.D. < 7 years), or outstanding senior level. See http://www.cs.dal.ca/news/news-1282.shtml or contact me if you have any questions. Regards, Thomas Trappenberg Faculty of Computer Science Dalhousie University 6050 University Avenue Halifax, NS B3H 1W5 Canada