From triesch at fias.uni-frankfurt.de Wed Nov 1 17:23:53 2006 From: triesch at fias.uni-frankfurt.de (Jochen Triesch) Date: Wed, 1 Nov 2006 23:23:53 +0100 (CET) Subject: Connectionists: Faculty Positions at UC San Diego: Human Development Message-ID: <10468.84.58.36.198.1162419833.squirrel@fias.uni-frankfurt.de> FACULTY POSITIONS DEPARTMENT OF COGNITIVE SCIENCE UNIVERSITY OF CALIFORNIA, SAN DIEGO The Department of Cognitive Science at the University of California at San Diego has two faculty positions for outstanding developmental researchers. The Cognitive Science department at UCSD (http:// www.cogsci.ucsd.edu/) was the first of its kind in the world, and, as part of an exceptional scientific community, it remains a dominant influence in the field it helped to create. The department is truly interdisciplinary, with a faculty whose interests span anthropology, computer science, human development, linguistics, neuroscience, philosophy, and psychology. 1. Assistant Professor (tenure-track): The department is looking for a top-caliber junior researcher in any area(s) of cognitive science, with a focus on problems of human development. Applicants must have a Ph.D. (or ABD). A broad interdisciplinary perspective will be highly valued. Experience with multiple methodologies is preferred. 2. Associate or Full Professor (with tenure): The department is looking for an outstanding senior researcher in any area(s) of cognitive science, with a focus on problems of human development. The position will also include the Directorship of the UCSD Center for Human Development (http://chd.ucsd.edu/). The Center for Human Development is an interdisciplinary research unit with close ties to Cognitive Science, Psychology, and other departments at UCSD. Its principal mission is to foster strong cross-disciplinary approaches to the study of human development, broadly defined. Applicants with a track record of exemplary research with an impact in multiple disciplines are preferred. Salary for each position will be commensurate with the experience of the successful applicant and based on the UC pay scale. Both positions begin July 1, 2007. Women and minorities are encouraged to apply. Applicants are invited to provide comments about their leadership activities and contributions to diversity in education and scholarship. The University of California, San Diego is an affirmative action/equal opportunity employer with a strong institutional commitment to excellence through diversity. Review of applications will begin January 15, 2007 and will continue until each position is filled. Candidates should submit, via our online application, a letter of intent describing their background and interests, a current curriculum vita, reprints of up to four representative publications, and a list of at least three references (names, titles, addresses, and email addresses). To apply, see ?Faculty Positions? at http:// www.cogsci.ucsd.edu/. From smyth at ics.uci.edu Wed Nov 1 20:20:17 2006 From: smyth at ics.uci.edu (Padhraic Smyth) Date: Wed, 1 Nov 2006 17:20:17 -0800 Subject: Connectionists: Two Tenure-Track Faculty Positions at UC Irvine Message-ID: <9d909ca60611011720j7873396dk40ad42f65333168e@mail.gmail.com> FACULTY POSITIONS AT THE UNIVERSITY OF CALIFORNIA, IRVINE The Department of Computer Science at the University of California, Irvine is currently inviting applications for two open tenure-track faculty positions. Areas of particular emphasis include machine learning, text analysis, and computer vision. The Department has a very active graduate program in machine learning and AI with faculty such as Max Welling, Padhraic Smyth, Don Patterson, Eric Mjolsness, Ramesh Jain, Rick Lathrop, Rina Dechter, and Pierre Baldi. The Department also has four additional open faculty positions in the area of bioinformatics (in addition to the two positions mentioned above). There are strong collaborations with faculty in departments such as Cognitive Science (e.g., Mark Steyvers) and Statistics (e.g., David van Dyk, Gang Liang, and Hal Stern), as well as multiple interdisciplinary opportunities on campus with other departments, in particular through campus-wide research centers. These include the Institute for Genomics and Bioinformatics, the California Institute for Telecommunications and Information Technology (Calit2), the Institute for Mathematical Behavioral Sciences, and the newly-formed Center for Machine Learning and Data Mining. In early 2007 the Department will be moving to the newly-constructed Bren Hall, housing the Computer Science, Informatics, and Statistics departments. The UC Irvine campus is one of the youngest UC campuses and has been targeted for significant growth by the University of California. UC Irvine has received three Nobel prizes in the past 10 years. The campus is located three miles from the ocean in sunny Southern California with an excellent year-round Mediterranean climate. The area surrounding campus offers numerous outdoor and cultural opportunities and the public school system in Irvine is one of the highest-ranked in the nation. Full application details can be found at: http://www.ics.uci.edu/employment/employ_faculty.php#cs_prof From skoenig at usc.edu Fri Nov 3 11:57:15 2006 From: skoenig at usc.edu (Sven Koenig) Date: Fri, 3 Nov 2006 08:57:15 -0800 (PST) Subject: Connectionists: AAAI-07 Nectar CFP Message-ID: The following CFP is interesting for "connectionists" who would like to make significant results that they have recently presented in NIPS and related conferences to the artificial intelligence community. We are looking for truly outstanding results that are of interest to the artificial intelligence community and will likely be highly influential. Cheers, Sven and Elaine ------------------------------------------------------------ AAAI-07 will again include the Nectar track, whose goal is to make the most significant AI results presented in sister conferences in the last two years available to a broad AI audience. The Nectar (new scientific and technical advances in research) track will consist of papers that are based on important results that have already been published in the proceedings of at least one major specialized conference in 2005 and 2006, as either a single paper or a series of papers. Examples of such conferences include AAMAS, AIIDE, ALIFE, ACL, CEC, CogSci, CP, FUZZ-IEEE, GECCO, ICAPS, ICCBR, ICML, ICRA, IEEE CEC, IJCNN, IROS, ISWC, IUI, KCAP, KR, NIPS, RSS, SAT, UAI and WCCI. Examples of conferences in related fields with relevance to AI are ALife, CIKM, COLT, KDD, PODS, ICDTSIGIR, SIGMOD, VLDB, and WWW. Papers that report on the application of AI techniques in other fields, for example bioinformatics, may also serve as the basis for Nectar papers. Authors of application papers, however, are advised that they may find the conference on innovative applications of AI (IAAI) a more appropriate venue for reaching the AI community since those papers can be longer and thus provide a clearer application setting in which to describe the work. Papers that have appeared in either AAAI or IJCAI cannot serve as the basis for Nectar papers since they have already been presented to the entire AI community. One important goal of the track is to offer young researchers the opportunity to learn about areas with which they may not already be familiar. Another goal is to encourage the sort of cross-disciplinary AI work that has historically been supported by AAAI. We solicit short submissions of up to four pages. Each submission should focus on a major result that has already been published in one or more venues as described above. A Nectar paper needs to clarify the relationship of the paper to any other AAAI-07 submissions by the authors and cannot overlap with them substantially. The Nectar paper should cite the previous publication(s) and will typically devote no more than one or two pages to summarizing the core results. The remainder of the paper should be devoted to putting the results, as well as the problem they solve, into a context that is meaningful to a wide AI audience. AAAI Nectar track papers will be presented as short talks or posters at AAAI-07. The papers will also be published in the conference proceedings. Submitted papers will be reviewed according to: (1) significance of the result to the broad goals of AI, (2) potential for the result to influence work in other areas of AI, and (3) clarity of the presentation to a wide AI audience. Although papers will describe previously published results, the paper itself must be original. Authors of accepted papers will be required to transfer copyright. Papers must be received by February 27, 2007. Decisions on the acceptance of papers will be made by March 29, 2007. For more information, as it becomes available, please see www.aaai.org/Conferences/AAAI/aaai07.php and www.aaai.org/Conferences/AAAI/2007/aaai07nectarcall.php Elaine Rich (University of Texas at Austin), Cochair Sven Koenig (University of Southern California), Cochair --- Sven Koenig University of Southern California Computer Science Department Henry Salvatori Computer Center (SAL) 312 941 W 37th Street Los Angeles, CA 90089-0781, USA Tel: 213-740-6491 Fax: 213-740-7285 Email: skoenig at usc.edu WWW: idm-lab.org (= www-rcf.usc.edu/~skoenig/) From moore at santafe.edu Fri Nov 3 17:56:24 2006 From: moore at santafe.edu (Cristopher Moore) Date: Fri, 3 Nov 2006 15:56:24 -0700 Subject: Connectionists: postdocs at the Santa Fe Institute Message-ID: <2A98CA5C-2921-4F5F-AF86-82E16722E11E@santafe.edu> The Santa Fe Institute is seeking applications for postdoctoral researchers. The deadline to apply is November 15, 2006. Below is a link to a flyer. Cristopher Moore, Associate Professor Computer Science / Physics and Astronomy University of New Mexico External Professor, Santa Fe Institute From ahirose at ee.t.u-tokyo.ac.jp Mon Nov 6 04:46:36 2006 From: ahirose at ee.t.u-tokyo.ac.jp (Akira Hirose) Date: Mon, 06 Nov 2006 18:46:36 +0900 Subject: Connectionists: New book: Complex-Valued Neural Networks In-Reply-To: <437D87DE.5060600@ee.t.u-tokyo.ac.jp> References: <4379B2EB.1060107@eis.t.u-tokyo.ac.jp> <437D8697.5070800@ee.t.u-tokyo.ac.jp> <437D87DE.5060600@ee.t.u-tokyo.ac.jp> Message-ID: <454F047C.6050200@ee.t.u-tokyo.ac.jp> ===== New Book ===== Complex-Valued Neural Networks Akira Hirose 2006, 176 p., 70 illus., 3 in colour, Hardcover ISBN-10: 3-540-33456-4 ISBN-13: 978-3-540-33456-9 Full details, including sample chapter, at: http://www.springer.com/east/home/default?SGWID=5-40356-22-165284615-0 About this book ========================== This book is the first monograph ever on complex-valued neural networks, which lends itself to graduate and undergraduate courses in electrical engineering, informatics, control engineering, mechanics, robotics, bioengineering, and other relevant fields. It is useful for those beginning their studies, for instance, adaptive signal processing for highly functional sensing and imaging, control in unknown and changing environment, brainlike information processing, robotics inspired by human neural systems, and interdisciplinary studies to realize comfortable society. It is also helpful to those who carry out research and development regarding new products and services at companies. The author wrote this book hoping in particular that it provides the readers with meaningful hints to make good use of neural networks in fully practical applications. The book emphasizes basic ideas and ways of thinking. Why do we need to consider neural networks that deal with complex numbers? What advantages do the complex-valued neural networks have? What is the origin of the advantages? In what areas do they develop principal applications? This book answers these questions by describing details and examples, which will inspire the readers with new ideas. Table of contents ========================== Part I Basic Ideas and Fundamentals: Why are complex-valued neural networks inevitable? - Complex-valued neural networks fertilize electronics. - Neural networks: The characteristic viewpoints. - Complex-valued neural networks: Distinctive features. - Constructions and dynamics of neural networks. Part II Applications: How wide are the application fields? - Land-surface classification with unevenness and reflectance taken into consideration. - Adaptive radar system to visualize antipersonnel plastic landmines. - Removal of phase singular points to create digital elevation map. - Lightwave associative memory that memorizes and recalls information depending on optical-carrier frequency. - Adaptive optical-phase equalizer. - Developmental learning with behavioral-mode tuning by carrier-frequency modulation. - Pitch-asynchronous overlap-add waveform-concatenation speech synthesis by optimizing phase spectrum in frequency domain. ================================================ From erik at tnb.ua.ac.be Mon Nov 6 13:13:51 2006 From: erik at tnb.ua.ac.be (Erik De Schutter) Date: Mon, 6 Nov 2006 19:13:51 +0100 Subject: Connectionists: Postdoc and PhD positions in computational neuroscience in Okinawa Message-ID: <3A1B347A-D06C-4111-AD25-8DC0B44B1CB4@tnb.ua.ac.be> I am starting a new Computational Neuroscience unit at the Okinawa Institute of Science and Technology, Japan in 2007. We have several openings for postdocs, PhD students and software engineers in the following topics: - molecular modeling of synaptic plasticity - cellular modeling of Purkinje cells - modeling of channel and synaptic homeostasis - development of software to model neuron growth PhD candidates can have diverse backgrounds, postdoc candidates should have experience in computational neuroscience. Proficiency in spoken and written English is required. For more information on the work in the unit see http:// www.tnb.ua.ac.be and recent publications: M. Berends, R. Maex and E. De Schutter: The effect of NMDA receptors on gain modulation. Neural Computation 17: 2531-2547 (2005). E. De Schutter, ?. Ekeberg, J. Hellgren Kotaleski, P. Achard, A. Lansner: Biophysically detailed modelling of microcircuits and beyond. Trends in Neurosciences 28: 562-569 (2005). S.M.G. Solinas, R. Maex and E. De Schutter: Dendritic amplification of inhibitory postsynaptic potentials in a model Purkinje cell. European Journal of Neuroscience 23: 1207-1218 (2006). P. Achard and E. De Schutter: Complex parameter landscape for a complex neuron model. PLoS Computational Biology 2: e94, 794-804 (2006). F. Santamaria, S. Wils, E. De Schutter and G.J. Augustine: Anomalous diffusion in Purkinje cell dendrites caused by dendritic spines. Neuron in press (2006). We offer attractive financial and working conditions in an English language environment. Duration of initial appointments will depend on previous experience, appointments can last up to 5 years. More information about the Okinawa Institute of Science and Technology is available at http://www.oist.jp/ Send curriculum vitae, summary of research interests, and the names of three referees to Prof. Erik De Schutter at erik at tnb.ua.ac.be From latallah at doc.ic.ac.uk Sat Nov 4 12:55:16 2006 From: latallah at doc.ic.ac.uk (Louis Atallah) Date: Sat, 4 Nov 2006 17:55:16 +0000 Subject: Connectionists: RA in Pervasive Sensing at Imperial College Message-ID: <20061104175516.un5883xuokcs44s0@tern.doc.ic.ac.uk> Dear all, We are looking for a Research Assistant/Associate to work in the Body Sensors Networks group focusing on pervasive computing. Experience in any of the following areas will be preferred: * Multi-sensor fusion, pattern recognition, data mining and knowledge discovery * Machine learning and decision support * Embedded systems, wireless sensor networks and automatic systems * Large-scale real-time databases The posts are for a fixed term of 36 months. Research Assistant applicants should have a distinction-level Masters degree (or equivalent) in computer science, electrical engineering or medical physics. Research Associate applicants should have a PhD (or equivalent) in computer science, electrical engineering or medical physics. Preference will be given to applicants with a proven research record in relevant areas. Applications should include a College application form, which can be obtained from: http://www.imperial.ac.uk/employment/academicform.htm. Please quote reference: BSN RA. A 1-2 page research statement should be provided outlining interesting research issues relating to one or more of the above posts and why your expertise is relevant. Applications must include a full CV, stating the names and addresses of two referees and should be sent to: Hannah Wells Department of Computing, Imperial College London, South Kensington Campus, London, SW7 2AZ UK e-mail: h.wells at imperial.ac.uk fax: +44 (0)20 7584 8354 For additional information on the project, please contact Hanna Wells (h.wells at imperial.ac.uk). Closing Date: 18 November 2006 regards, Louis Dr Louis Atallah Body Sensors Networks Group Department of Computing Imperial College London From stefan.wermter at sunderland.ac.uk Tue Nov 7 09:11:31 2006 From: stefan.wermter at sunderland.ac.uk (Stefan Wermter) Date: Tue, 07 Nov 2006 14:11:31 +0000 Subject: Connectionists: Jobs: Research Associate / Research Assistant: neural communication Message-ID: <45509413.4070502@sunderland.ac.uk> Research Associate in communication and neural networks (NESTCOM project) Ref: CTR020/1277 Fixed term from 1st January 2007 to 31st December 2008 Part time ? 18.5 hours per week ?19,920 to ?20,808 per annum, pro rata subject to contract ----------------------------------------------------------------- Research Assistant in communication and neural networks (NESTCOM project) Ref: CTR021/1276 Fixed term from 1st January 2007 to 31st December 2008 Part time ? 18.5 hours per week ?13,802 to ?18,673 per annum, pro rata subject to contract ------------------------------------------------------------------ Our focus in this project NESTCOM is to develop a scientific roadmap for ?what it means to communicate?. This project is coordinated at the Centre for Hybrid Intelligent Systems at the University of Sunderland ( www.his.sunderland.ac.uk ). A wealth of new knowledge has been produced by recent NEST (New and Emerging Science and Technology) projects in the EU exploring verbal and visual communication. In this project we will explore the characteristics of human communication and their relationships to computational neural networks and mirror neurons. One particular focus will be on language processing. In support of the NEST initiative we will produce an interdisciplinary roadmap which should lead to a better understanding of the neural, computational and social aspects of communication. 1. The *Research Associate* will assist to coordinate the interdisciplinary project NESTCOM and road map development for ?NESTCOM what it means to communicate?. You will be educated to PhD level or possess substantial research experience. A higher degree, or equivalent qualification and extensive experience in computing is essential, as is knowledge of natural language processing, neural networks or non-verbal visual communication. Knowledge of mirror neuron theory is desirable. 2. The *Research Assistant* will support the interdisciplinary project NESTCOM by supporting the analysis of NEST project research results, support workshop and meeting organisation as well as dissemination and website development. An honours degree, or equivalent qualification, in a computing discipline, or related subject is essential, as is knowledge of natural language processing, neural networks or non-verbal visual communication. This post will offer an ideal opportunity for a person who wishes to gain experience with international projects and combine it with a part-time PhD programme, e.g. in natural language processing, neural networks, or a learning language robot head. For informal discussions please contact Prof. Stefan Wermter ( stefan.wermter at sunderland.ac.uk ) Interviews for this post will be held on Wednesday 6th December 2006. Application forms and Role Profiles can be obtained by contacting Human Resources on 0191 515 2057 or www.sunderland.ac.uk/jobs Closing Date: **29th November 2006*** *************************************** Professor Stefan Wermter Chair for Intelligent Systems School of Computing and Technology University of Sunderland St Peters Way Sunderland SR6 0DD United Kingdom phone: +44 191 515 3279 fax: +44 191 515 3553 email: stefan.wermter AT sunderland.ac.uk http://www.his.sunderland.ac.uk/~cs0stw/ http://www.his.sunderland.ac.uk/ **************************************** -- University of Sunderland - life-changing: see our new TV advert at http://www.lifechangingsunderland.com or http://www.sunderland.ac.uk From liam at stat.columbia.edu Tue Nov 7 16:41:49 2006 From: liam at stat.columbia.edu (liam@stat.columbia.edu) Date: Tue, 7 Nov 2006 16:41:49 -0500 (EST) Subject: Connectionists: Postdoctoral positions in retinal population coding Message-ID: Apologies for the cross-posting. Full-time postdoctoral positions are available for collaborative research in computational modeling of the neural coding properties of populations of cells in primate retina. This is a three-way collaboration between the laboratories of Liam Paninski (http://www.stat.columbia.edu/~liam/), Eero Simoncelli (http://www.cns.nyu.edu/~lcv/), and E.J. Chichilnisky (http://www.snl-e.salk.edu/). Examples of previous related publications include: - Prediction and decoding of retinal responses with a probabilistic spiking model J W Pillow, L Paninski, V J Uzell, E P Simoncelli, and EJ Chichilnisky. Journal of Neuroscience, 25(47):11003-11013, 23 Nov 2005. http://www.cns.nyu.edu/~lcv/ABSTRACTS/pillow05-abstract.html - Statistical models for neural encoding, decoding, and optimal stimulus design L Paninski, J W Pillow, and J Lewi. To appear in Computational Neuroscience: Progress in Brain Research, eds. P Cisek, T Drew and J Kalaska. http://www.stat.columbia.edu/~liam/research/abstracts/pbr-abs.html Requirements: The work is highly interdisciplinary, and applicants must have strong mathematical and computational skills. Preferred educational background is a PhD in Electrical Engineering, Statistics, Physics, or Applied Mathematics. Previous experience with signal/image processing, statistical modeling, machine learning, and/or computational neuroscience is highly desirable. Environment: The computational aspects of the work will be carried out in two locations: - the Paninski group at Columbia University, based in the Statistics department (http://www.stat.columbia.edu/) and the Center for Theoretical Neuroscience (http://www.neurotheory.columbia.edu/) - the Simoncelli group at New York University, based in the Center for Neural Science (http://www.cns.nyu.edu/), with connections to the Courant Institute of Mathematical Sciences (http://www.cims.nyu.edu/). Appointments: Initial appointments are for one year, and are renewable. Salaries will be covered by an NIH grant for Collaborative Research in Computational Neuroscience, and will be set based on experience and skills. Applicants should send email to Eero Simoncelli and/or Liam Paninski (email addresses on web pages given above) providing: - a one-page description of research interests and goals - a resume of educational and research experience, including publications - names of at least two people that could provide letters of reference All materials should be in Acrobat (pdf) or plain text (no MS Word documents, please), and may be included as a URL, or as an email attachment. From awhite at cs.ualberta.ca Tue Nov 7 17:55:36 2006 From: awhite at cs.ualberta.ca (Adam White) Date: Tue, 7 Nov 2006 15:55:36 -0700 Subject: Connectionists: NIPS RL Competition -- Update Message-ID: NIPS*06 Workshop - Whistler, BC, December 9, 2006 "First Annual Reinforcement Learning Competition" ====================================================== ---------------------------- UPDATE ---------------------------- The competition server is now active!! Registered teams may now connect remotely and enter their agents into competition. To register your team email: awhite at cs.ualberta.ca An update to the competition software has also been released. ------------------------ Important Dates ------------------------ Official start of competition: October 26, 2006 Competition end: December 3, 2006 Submission deadline for Solution descriptions: December 5, 2006 ---------------------------------- Organization Committee ---------------------------------- Adam White, University of Alberta, Alberta, Canada Richard S. Sutton, University of Alberta, Alberta, Canada Michael L. Littman, Rutgers University, New Jersey, USA Doina Precup, Mcgill University , Montreal, Canada Peter Stone, University of Texas, Austin, Texas, USA ------------------------------------------------ Technical Organization Committee ------------------------------------------------ Andrew Butcher, University of Alberta, Alberta, Canada From btanner at cs.ualberta.ca Mon Nov 6 17:59:15 2006 From: btanner at cs.ualberta.ca (Brian Tanner) Date: Mon, 6 Nov 2006 15:59:15 -0700 Subject: Connectionists: Extended Call for Participation : NIPS Workshop on Grounding Perception, Knowledge and Cognition in Sensori-Motor Experience Message-ID: UPDATES: The organizers of the workshop have extended the deadline for poster submission until Sunday, November 12th, 2006. We have also confirmed all five invited speakers. Call for Participation ====================== NIPS 2006 Workshop on Grounding Perception, Knowledge and Cognition in Sensori-Motor Experience Whistler Resort & Spa and the Whistler Hilton Resort & Spa, BC, CANADA http://rlai.cs.ualberta.ca/RLAI/prw2006.html Workshop Overview ------------------------------------- Understanding how world knowledge can be grounded in sensori-motor experience has been a long-standing goal of philosophy, psychology, and artificial intelligence. So far this goal has remained distant, but recent progress in machine learning, cognitive science, neuroscience, engineering, and other fields seems to bring nearer the possibility of addressing it productively. The objective of this workshop is to provide cross-fertilization of ideas between diverse research communities interested in this subject. This workshop will serve as a meeting point for researchers from these various disciplines to share their perspectives and insights on the issue of representing knowledge in terms of sensori- motor experience. The workshop will focus on research topics such as: * The role of prediction in biological and neurological systems * Identifying relevant sensory information, both across sensors and time (sensor bootstrapping) * Representations spanning multiple spatio-temporal scales * Signals to symbols, symbol grounding * General issues of grounded knowledge representations: formats, capabilities, affordances, and limitations * Reasoning and planning in terms of grounded knowledge * Active perception guided by sensory-motor experience * Construction of perceptual or motor control primitives * Grounded state representations (PSRs, OOMs, etc) * Dynamical / environmental models grounded in sensory-motor experience * Learning algorithms for intelligent agents * Learning in infants, going from sensory data to representations The workshop will be comprised of invited talks by 5-6 of the top people from a variety of disciplines related to experience based knowledge representations. The speakers will share their area- specific knowledge and understanding of these issues with the workshop attendees. Several discussion sessions will give an opportunity for all workshop participants to discuss ideas. The workshop will conclude with a poster session populated with work submitted by the community at large. A central goal is to bring together the perspectives of different communities. We invite participants from any area, including machine learning, cognitive science, computational neuroscience, developmental robotics, and philosophy. Confirmed Speakers ------------------------------------- Dr. Richard Sutton Richard S. Sutton is professor and iCORE chair of computing science at the University of Alberta. He is a fellow of the American Association for Artificial Intelligence and co-author of the textbook Reinforcement Learning: An Introduction from MIT Press. Before joining the University of Alberta in 2003, he worked in industry at AT&T and GTE Labs, and in academia at the University of Massachusetts. He received a PhD in computer science from the University of Massachusetts in 1984 and a BA in psychology from Stanford University in 1978. Rich's research interests center on the learning problems facing a decision-maker interacting with its environment, which he sees as central to artificial intelligence. He is also interested in animal learning psychology, in connectionist networks, and generally in systems that continually improve their representations and models of the world. Dr. Deb Roy Deb Roy is an associate professor of media arts and sciences at the Massachusetts Institute of Technology, where he heads the Media Lab's Cognitive Machines research group. In 2003 he was appointed AT&T Career Development Professor. Roy has published over 50 peer-reviewed papers in the areas of artificial intelligence, cognitive modeling, data mining, robotics, and human-machine interface design. He has served as guest editor for the journal Artificial Intelligence, and as an associate of the journal Behavioral and Brain Sciences. Roy collaborates closely with industry in the areas of data visualization, data mining, and the design of human-machine collaborative systems. He holds a BASc in computer engineering from University of Waterloo, Canada, and MS and PhD degrees in media arts and sciences from MIT. Dr. Mark H. Bickhard Mark H. Bickhard received his B.S. in Mathematics, M.S. in Statistics, and Ph. D. in Human Development, all from the University of Chicago. He taught at the University of Texas at Austin for eighteen years before joining Lehigh University in 1990 as Henry R. Luce Professor in Cognitive Robotics and the Philosophy of Knowledge. He is affiliated with the Departments of Psychology, Philosophy, Biology, Counseling, and Computer Science, and is Director of the Institute for Interactivist Studies and of the Complex Systems Research Group. He was Director of Cognitive Science from 1992 thru 2003. His work focuses on the nature and development of persons, as biological, psychological, and social beings. This work has generated an integrated organization of models encompassing the whole person, ranging from the nature of biological function through perception, cognition, processes of and constraints on development, rationality, emotions, reflexive consciousness, language, psychopathology, and the relationships between the emergence of social reality and the social ontology of persons. Dr. Rajesh Rao Rajesh Rao is an associate professor in the Computer Science and Engineering department at the University of Washington, where he heads the Laboratory for Neural Systems. He received his PhD from the University of Rochester and was a Sloan Postdoctoral Fellow at the Salk Institute for Biological Studies before joining the University of Washington. His research spans the areas of computational neuroscience, humanoid robotics, and brain-computer interfaces. He is the recipient of a David and Lucile Packard Fellowship, an Alfred P. Sloan Fellowship for junior faculty, an ONR Young Investigator Award, and an NSF Career award. He is the co-editor of two books: Probabilistic Models of the Brain (2002) and Bayesian Brain (2007). Dr. Bernard Balleine Bernard Balleine is Professor in the Department of Psychology and Associate Director of the Brain Research Institute, UCLA. He received his BA from the University of Sydney, Australia and his PhD from the University of Cambridge, UK where he was subsequently elected a Research Fellow of Jesus College. His research focuses on the motivational, cognitive and neural determinants of goal-directed action as a part of the larger goal of establishing the fundamental distinctions between reflexive, volitional and habitual actions. Call for Participation ------------------------------------- Participation in the form of a poster will be by invitation from the program committee based on a small written submission, either a short paper or extended abstract on your relevant work (this may be work that has been previously published elsewhere). We encourage submissions from all disciplines that are related to the topic of the workshop. The poster session is expected to reflect the wide variety of interesting ideas surrounding our topic. * Submission Deadline: November 12, 2006 <-- *UPDATED* * Acceptance Notification: November 10, 2006 <-- Notification stands for already existing submissions. New submitters will be notified ASAP. * Workshop date: December 8, 2006 All submissions should be emailed to grounded.workshop at gmail.com Agenda and Venue ------------------------------------- This will be a one-day workshop held on December 8, 2006 in Whistler, British Columbia, Canada as part of the NIPS conference. The schedule can be found on the workshop website. Organizers / Contact Information ------------------------------------- * Brian Tanner (University of Alberta) Co-Chair * Michael James (Toyota Research) Co-Chair * David Wingate (University of Michigan) Co-Chair * Satinder Singh (University of Michigan) * Rich Sutton (University of Alberta) Please direct all questions and submissions to grounded.workshop at gmail.com The official workshop website is: http://rlai.cs.ualberta.ca/RLAI/ prw2006.html Related Past Events This workshop is in the same spirit as recent workshops including: * 2006 Barbados workshop Predictive State Representations * 2005 Barbados workshop Predictive State Representations * 2004 ICML Workshop Predictive Representations of World Knowledge * 2001 AAAI Spring Symposium Learning Grounded Representations From isabelle at clopinet.com Tue Nov 7 01:09:50 2006 From: isabelle at clopinet.com (Isabelle Guyon) Date: Mon, 06 Nov 2006 22:09:50 -0800 Subject: Connectionists: $1000 easily won in a model selection game Message-ID: <4550232E.4020500@clopinet.com> Dear colleagues, The MODEL SELECTION GAME is well under way! Compete with 15 other entrants and win one of two $500 cash awards. http://clopinet.com/isabelle/Projects/NIPS2006/ The best contributors will be present there results at the NIPS workshop on Multi-level Inference. They will be encouraged to submit a paper to the new special topic of JMLR on model selection. http://clopinet.com/isabelle/Projects/modelselect/call-for-papers.html Isabelle Guyon From pmt6sbc at maths.leeds.ac.uk Tue Nov 7 06:58:12 2006 From: pmt6sbc at maths.leeds.ac.uk (S B Cooper) Date: Tue, 7 Nov 2006 11:58:12 +0000 (GMT) Subject: Connectionists: Connectionism, Turing, and the Big Picture Message-ID: In 2001, Cristof Teuscher's timely book from Springer on "Turing's Connectionism: An Investigation of Neural Network Architectures" reminded us that neural networks and basic computability theoretic research have together had a fruitful history. The new network and conference series 'Computability in Europe' (its eurocentric title betraying its origins in a bid for EU funding) is built around the growing richness and diversity of computability theoretic research, and seeks to revitalise the Alan Turing approach of setting this in a broad and basic context. CiE 2007 - for details see its webpage: http://www.amsta.leeds.ac.uk/~pmt6sbc/cie07.html encourages the participation of connectionist and other computability related researchers who value novel interactions, and who like to place their "normal science" (to quote Thomas Kuhn) in a broader context. Best wishes, Barry Cooper Coordinator, CiE ____________________________________________________________________________ S Barry Cooper Tel: UK: (0113) 343 5165, Int: +44 113 343 5165 School of Mathematics Fax: UK: (0113) 343 5090, Int: +44 113 343 5090 University of Leeds Email: pmt6sbc at leeds.ac.uk, Mobile: 07952 198826 Leeds LS2 9JT Home tel: (0113) 278 2586, Int: +44 113 278 2586 U.K. WWW: http://www.amsta.leeds.ac.uk/~pmt6sbc ____________________________________________________________________________ From triesch at fias.uni-frankfurt.de Wed Nov 8 11:56:51 2006 From: triesch at fias.uni-frankfurt.de (Prof. Jochen Triesch) Date: Wed, 08 Nov 2006 17:56:51 +0100 Subject: Connectionists: Several Post-doc and PhD positions at FIAS Message-ID: <45520C53.6070106@fias.uni-frankfurt.de> There are openings for 2 Post-docs and 3 PhD students in Jochen Triesch's new group at the Frankfurt Institute for Advanced Studies (FIAS, http://fias.uni-frankfurt.de/). FIAS is a new and quickly expanding center for theoretical research in the natural sciences. Its focus lies on the study of complex, self-organizing systems. FIAS is located in the new "Science City" Frankfurt-Riedberg in Frankfurt am Main, Germany. Our group's research areas include: - Neural Computation / Computational Neuroscience - Vision (Computer, Robot, and Human Vision) - Computational Models of Cognitive Development. For recent publications see: http://fias.uni-frankfurt.de/~triesch/ Some of the positions are in the context of a recently awarded project entitled "PLICON - plasticity and learning in cortical networks" funded by the European Union. We will develop models of the interaction of different forms of neural plasticity at the neuron, network, and system levels. In particular, the project aims to study sensory coding, perceptual learning and inference, and sensori-motor learning. Frankfurt has a vibrant neuroscience community and close ties exist with other groups in Frankfurt including the Max Planck Institute for Brain Research: http://www.mpih-frankfurt.mpg.de. Our group has several collaborations with labs in the US and Europe. Candidates for the PhD positions should have an excellent Masters degree (or equivalent) in a quantitative discipline (physics, mathematics, computer science, electrical engineering, or related fields) and a keen interest in several of the lab's research areas. Proficiency in spoken and written English is required. The post-doctoral positions will be initially for two years with the possibility of extension. A competitive stipend will be offered. Application materials should include: - resume (including date of birth, degrees, awards, publications, ...), - statement of research interests (1-2 pages), - 2-3 reference letters, The positions are available immideately and will remain open until filled. Reviewing of applications starts immediately. If possible, please send materials electronically to: triesch at fias.uni-frankfurt.de and stephanie.mueller at fias.uni-frankfurt.de -- Jochen Triesch, Fellow Frankfurt Institute for Advanced Studies http://fias.uni-frankfurt.de/~triesch/ triesch at fias.uni-frankfurt.de From mholee at MIT.EDU Thu Nov 9 17:31:25 2006 From: mholee at MIT.EDU (Min Ho Lee) Date: Fri, 10 Nov 2006 07:31:25 +0900 Subject: Connectionists: CFP : Special Issue on "Artificial Brain and Emotion and Learning" for Neural Information Processing-Letters and Reviews (NIP-LR) Message-ID: <200611092231.kA9MVRnj015204@outgoing-legacy.mit.edu> CALL FOR PAPERS Special Issue on "Artificial Brain and Emotion and Learning" for Neural Information Processing-Letters and Reviews (NIP-LR) As announced earlier at the International Symposium on Artificial Brain with Emotion Learning (ISABEL2006; Seoul, Korea), Neural Information Processing-Letters and Reviews (NIP-LR) is preparing a special issue on "Artificial Brain with Emotion and Learning." Although artificial neural networks are based on information processing mechanisms in our brain, there still exists a big gap between the biological neural networks and artificial neural networks. The more intelligence we would like to incorporate into artificial intelligent systems, the more biologically-inspired models and hardware are required. Fortunately the cognitive neuroscience has been developed enormously during the last decade, and engineers now have more to learn from the science. In this special issue, we invite contributions on artificial brain with emotion and learning with more human-like traits for real world applications. The suggested topics include, but are not limited to: Models of auditory pathway Models of visual pathway Models of cognition, learning, and inference Models of attention, emotion, and consciousness Models of autonomous behavior Hardware implementation of bio-inspired models Engineering applications of bio-inspired models For more information on the special issue for NIP-LR see: http://www.nip-lr.info Submission instruction: Papers should be emailed as a PDF attachment to Rhee Man Kil rmkil at kaist.ac.kr and Minho Lee mholee at knu.ac.kr, the guest editors. Important dates: December 15, 2006: Submission Deadline January 15, 2007: Deadline for the Reviews January 30, 2007: Notification of Acceptance/Rejection. February 15, 2007: Publication for the special issue Copyright: Authors will maintain all rights to their papers, and may subsequently publish extended versions of their papers in other journals. Rhee Man Kil Division of Applied Mathematics KAIST rmkil at kaist.ac.kr, 82-42-869-2736 Minho Lee School of EE and CS Kyungpook National Univeristy, Korea mholee at knu.ac.kr, 82-53-950-6436 Dept. of Brain and Cognitive Science MIT, USA mholee at mit.edu, 617-324-5340 From fsommer at berkeley.edu Thu Nov 9 16:22:12 2006 From: fsommer at berkeley.edu (Fritz Sommer) Date: Thu, 9 Nov 2006 13:22:12 -0800 Subject: Connectionists: Neural circuit for sparse coding using optimized matching pursuit References: Message-ID: A new paper is available that describes a neural network for sparse coding of visual input principled on optimized matching pursuit: Title: A network that uses few active neurones to code visual input predicts the diverse shapes of cortical receptive fields by M. Rehn and F. T. Sommer Abstract: Computational models of primary visual cortex have demonstrated that principles of efficient coding and neuronal sparseness can explain the emergence of neurones with localised oriented receptive fields. Yet, existing models have failed to predict the diverse shapes of receptive fields that occur in nature. The existing models used a particular ?soft? form of sparseness that limits average neuronal activity. Here we study models of efficient coding in a broader context by comparing soft and ?hard? forms of neuronal sparseness. As a result of our analyses, we propose a novel network model for visual cortex. The model forms efficient visual representations in which the number of active neurones, rather than mean neuronal activity, is limited. This form of hard sparseness also economises cortical resources like synaptic memory and metabolic energy. Furthermore, our model accurately predicts the distribution of receptive field shapes found in the primary visual cortex of cat and monkey. If your institution has access to Journal of Computational Neuroscience, you may view your paper at: http://dx.doi.org/10.1007/ s10827-006-0003-9 Otherwise the preprint can be downloaded: http://redwood.berkeley.edu/ ~fsommer/papers/rehnsommer06pre-jcn.pdf ------------------------------------------------------------------------ ---------------------------------------------- A related recent paper in Neurocomputing explores connections between sparse sensory coding and sparse associative memory: Title: Storing and restoring visual input with collaborative rank coding and associative memory. by M. Rehn and F. T. Sommer Abstract: Associative memory in cortical circuits has been held as a major mechanism for content-addressable memory. Hebbian synapses implement associative memory efficiently when storing sparse binary activity patterns. However, in models of sensory processing, representations are graded and not binary. Thus, it has been an unresolved question how sensory computation could exploit cortical associative memory. Here we propose a way how sensory processing could benefit from memory in cortical circuitry. We describe a new collaborative method of rank coding for converting graded stimuli, such as natural images, into sequences of synchronous spike volleys. Such sequences of sparse binary patterns can be efficiently processed in associative memory of the Willshaw type. We evaluate storage capacity and noise tolerance of the proposed system and demonstrate its use in cleanup and fill-in for noisy or occluded visual input. The preprint can be downloaded: http://redwood.berkeley.edu/~fsommer/ papers/rehnsommer06neurocomp.pdf ------------------------------------------------------------------------ ------------------------------------------------ Best, Fritz Sommer Redwood Center for Theoretical Neuroscience University of California, Berkeley http://redwood.berkeley.edu/wiki/Fritz_Sommer From cabestan at eel.upc.edu Sun Nov 12 17:34:35 2006 From: cabestan at eel.upc.edu (Joan Cabestany) Date: Sun, 12 Nov 2006 23:34:35 +0100 Subject: Connectionists: IWANN2007 CFP and Special Sessions Message-ID: Dear colleague, Let us focus your interest on 9th International Work-Conference on Artificial Neural Networks (IWANN2007), to be held next June 20-22, 2007 in San Sebastian (Spain). You are cordially invited to participate by submitting a paper and/or organizing a special session. Please, find extended information concerning special sessions at the page: http://www.iwann-conference.org/2007/special.html The proceedings will include all the accepted communications of registered authors to the conference (tutorials, oral and posters). As in previous editions of IWANN, we are preparing the publication of the proceedings with Springer-Verlag on Lecture Notes on Computer Science (LNCS) series, and the book will be available on-site. It is also foreseen the publication of an extended version of selected papers in a special issue of the Neurocomputing journal (Elsevier). Special sessions organizers will have the autonomy in promoting their sessions, appointing the possible additional reviewers for the session papers (possible including the organizer him/herself), chairing their respective sessions and proposing their co-organizer and/or co-chair. Besides, the session organizers will get a reduction of 30% in the registration fees. You can obtain and freely print a copy of a more detailed Call For Papers at: http://www.iwann-conference.org/2007/pdf/call_for_papers_iwann2007.pdf Do not hesitate to access the conference web site : http://www.iwann-conference.org/2007or to contact us by e-mail for further questions or suggestions at: iwann2007pc at dte.uma.es We hope this conference could be of your interest. Cordially yours Joan Cabestany Alberto Prieto Francisco Sandoval Co-Chairmen of IWANN2007 Conference Very important dates: * Submission of Special Sessions Proposals: November 26, 2006 * Submission of regular papers: February 4, 2007 * Early registration: March 25, 2007 * Conference dates: June 20 to 22, 2007 ---------------------------------------------------------------------------- ------- Joan Cabestany - Professor Electronic Engineering Dept. UPC - Technical University of Catalunya Jordi Girona, 1-3 Building C4 08034 BARCELONA - Spain Phone: + 34 93 401 6742/ + 34 609 766001 E-mail: cabestan at eel.upc.edu Web: http://csse.upc.es ---------------------------------------------------------------------------- ------- From bower at uthscsa.edu Mon Nov 13 18:16:40 2006 From: bower at uthscsa.edu (james Bower) Date: Mon, 13 Nov 2006 17:16:40 -0600 Subject: Connectionists: Computational Biology in San Antonio Texas Message-ID: Computational Biology in San Antonio, Texas The University of Texas San Antonio and the University of Texas Health Science Center San Antonio announces several faculty positions in Computational Biology. These positions reflect the growing multi-disciplinary base for computational studies of Biological Systems in San Antonio, which is also one of the nicest and most affordable places to live in the United States. The diversity of research interests at these two institutions also puts us in a unique position to address "two body problems". These positions are also all related to a major new joint multi-disciplinary bio-informatics and computational biology initiative involving the University of Texas Health Science Center, and the University of Texas San Antonio (http://www.cbi.utsa.edu/about). Based in a new computational biology facility, the initiative provides both technical staff as well as substantial computational resources to establish and nurture collaborations between biologists and quantitative scientists in projects ranging from biological data analysis to system modeling and simulation. This facility is also now the home for the GENESIS simulation project (http://www.genesis-sim.org/GENESIS/). The computational core was recently declared an International Center of Excellence for Biological Modeling and Simulation by SUN Microsystems. The Computational Biology Facility is also linked to several state-of-the-art core facilities including a new two-photon microscopy center directed by Dr. Charles Wilson, numerous molecular and cellular core facilities, a state-of-the-art behavioral core facility currently under construction, and the Research Imaging Center in San Antonio (http://ric.uthscsa.edu/) directed by Dr. Peter Fox, which has just received a 9 million dollar award to significantly expand its capacity for animal imaging. Please feel free to contact Dr. James Bower (bower at uthscsa.edu) for further information on computational biology in San Antonio, or directly contact each search committee as described below. Positions Currently Available: ASSISTANT ASSOCIATE PROFESSOR OF SYSTEMS NEUROSCIENCE. The Department of Biology at UTSA seeks applicants at the Assistant / Associate tenure track positions in systems neuroscience. We are in particular searching for candidates with a record of accomplishment in the study of central pattern generators, especially in invertebrate systems; neuronal control of movement; structure / function studies of ion channels; and/or dynamical changes in neuronal structure whether during development or in adults. Preference will be given to candidates linking experimental and model-based studies. See complete job description below. Contact information: biofacultyad at utsa.edu Associate / Full Professor in Proteomics The Department of Biology at UTSA seeks applicants at the Associate / Full tenure track level in Proteomics. This faculty member will provide leadership in an already funded new Proteomics Core Facility at UTSA. This facility is linked to the computational Biology Facility which provides an array of support services. Contact information: PROT at utsa.edu ASSISTANT / ASSOCIATE / FULL PROFESSOR IN BIOINFORMATICS. The Department of Computer Science at The University of Texas at San Antonio invites applications for a tenure/tenure-track position in bioinformatics or computational biology. Computational biology in the context of this search is defined very broadly, including not only work related to molecular processes, but also systems level studies including modeling and simulation. See complete job description below. Contact information: bioinfosearch at cs.utsa.edu Additional information can be obtained from: http://www.cs.utsa.edu/jobs/csjobs/bi_facsearch2006.html ASSISTANT / ASSOCIATE / FULL PROFESSOR IN BIOINFORMATICS/ BiOSTATISTICS The Department of Epidemiology and Biostatistics at the University of Texas Health Science Center at San Antonio, is seeking to full a tenure/tenure track position in bioinformatics and biostatistics. This position is related to a major new joint multi-disciplinary bioinformatics and computational biology initiative involving the University of Texas Health Science Center, and the University of Texas San Antonio (http://www.cbi.utsa.edu/about). Based in a new computational biology facility, the initiative provides both technical staff as well as substantial computational resources to establish and nurture collaborations between biologists and quantitative scientists in projects ranging from biological data analysis to system modeling and simulation. See complete job description below. ----------------------------------------------------------------------------------------------------------- The University of Texas at San Antonio Assistant / Associate Professor- Neuroscience The Department of Biology at the University of Texas San Antonio invites applications for a tenure-track position at the rank of Assistant/Associate Professor. Candidates must have a M.D., or Ph.D. or the equivalent in biology or a related discipline, and for appointments as an Assistant Professor, at least 2 years of postdoctoral experience. We are in particular searching for candidates with a record of accomplishment in the study of central pattern generators, especially in invertebrate systems; neuronal control of movement; structure / function studies of ion channels; and/or dynamical changes in neuronal structure whether during development or in adults. Preference will be given to candidates linking experimental and model-based studies. The successful applicant is expected to establish and maintain an extramurally funded research program, and contribute to undergraduate teaching and graduate supervision. In addition to an attractive start up package and laboratory space, the candidate will also have support from two recently established core facilities, one in computational biology (http://www.cbi.utsa.edu) and one with extensive support for imaging studies, including two photon microscopy. The successful candidate will also join a growing group of researchers in Neuroscience at UTSA with an emphasis on experimentally-based computational studies. Candidates please forward via email (biofacultyad at utsa.edu) or U.S. Post (Dr. James M. Bower, Chairman Search Committee, Department of Biology, UTSA, One UTSA Circle, San Antonio, TX 78249-0662) a current curriculum vita, two or three representative publications, and a brief summary of future research interests and teaching experience. Include contact information (including email addresses) of three references. Applicants who are not U. S. citizens must state their current visa and residency status. UTSA is an Affirmative Action/Equal Opportunity employer. Women and minorities are encouraged to apply. For full consideration, applications should be received by December 15, 2006, but will be accepted until the position is filled. For further information contact the chairman of the search committee, Dr. James M. Bower (bower at uthscsa.edu). ----------------------------------------------------------------------------------------------------------- THE UNIVERSITY OF TEXAS AT SAN ANTONIO ASSOCIATE or FULL PROFESSOR PROTEOMICS The University of Texas at San Antonio (UTSA) is accepting applications for a tenured Associate Professor or Full Professor position, starting Fall 2007. The appointment will be in the broad area of proteomics. The required qualifications are: an established program of research in proteomics, excellence in teaching, experience in directing doctoral dissertations, and a record of success in obtaining external funding. Responsibilities include leadership in developing the new UTSA Proteomics Core Facility, teaching, supervising research students at all levels, and maintaining an externally funded research program. UTSA, the second largest component university of The University of Texas System, has an enrollment in excess of 28,000 students. The Biology Department has 47 tenured/tenure-track faculty members, approximately 3,000 undergraduate majors, 150 graduate students in two M.S. programs (Biology, Biotechnology), and 50 doctoral students in two Ph.D. programs (Neurobiology, Cell and Molecular Biology). The Department of Chemistry has 15 tenured/tenure-track faculty members, approximately 145 Undergraduate majors, 12 graduate and 11 doctoral students. Review of submitted applications will begin immediately and will continue until the position is filled. Applicants who are not U.S. citizens must state their current visa and residency status. Applicants must submit a letter of application, a dated current curriculum vitae, a description of current research and research plans, a statement of teaching philosophy, and the names, postal addresses, and e-mail addresses of three individuals who can provide recommendation letters. Application materials should be sent to: Proteomics Search Committee, 1.620 BSE, The University of Texas at San Antonio, One UTSA Circle, San Antonio, Texas 78249-0661, or electronically to PROT at utsa.edu. Applications will be treated as confidential. Budget approval for position is pending. UTSA is an Affirmative Action/Equal Opportunity employer. Women, minorities, veterans, and individuals with disabilities are encouraged to apply. ----------------------------------------------------------------------------------------------------------- THE UNIVERSITY OF TEXAS AT SAN ANTONIO Faculty Position in Bioinformatics The Department of Computer Science at The University of Texas at San Antonio invites applications for a tenure/tenure-track position in bioinformatics or computational biology, starting in the fall of 2007. Computational biology in the context of this search is defined very broadly, including not only work related to molecular processes, but also systems level studies including modeling and simulation. The rank of the position may be at the assistant, associate or full professor level depending on applicant qualifications. Required qualifications: Candidates must have a Ph.D. or the equivalent in computer science or a related discipline. Candidates must also have a record of research accomplishment in bioinformatics or computational biology with a research focus that is both strongly computational and biological. Responsibilities: The successful applicant is expected to establish and maintain an extramurally funded research program, and contribute to undergraduate and graduate teaching and curriculum development in computer science. The successful applicant will join an interactive group of researchers in computer science, biology and statistics at UTSA and the nearby UT Health Science Center and participate in the development of new interdisciplinary degree programs in bioinformatics and computational biology. This position offers the opportunity to join an outstanding and expanding group of scientists in a highly interactive, interdisciplinary research environment supported by state-of-the-art research facilities. Attractive startup packages and access to a variety of shared facilities are available including a Bioinformatics/Computational Core Facility, an Imaging Core Facility, a Proteomics Core Facility, and a Genomics Core Facility which are being collocated in a new $85M building housing biological sciences and engineering. The Department of Computer Science currently has 24 faculty members and offers B.S., M.S., and Ph.D. degrees supporting a dynamic and growing program with over 500 undergraduate and 100 graduate students. (See http://www.cs.utsa.edu for additional information on the Department of Computer Science and its faculty.) The University is the largest public university in south Texas serving over 28,000 students. The city of San Antonio has a population of over one million and is known for its rich Hispanic culture, historic attractions, affordable housing, and excellent medical facilities. Substantial computer and biotechnology industry is located in San Antonio and Austin, located 75 miles away. Nearby higher education and research institutions include UT Health Science Center and Southwest Research Institute. Applicants must submit a signed letter of application that includes an indication of the level of position for which they are applying. Applications must also include a complete dated curriculum vitae (including employment chronology, publications and grants), a statement of research interests, and the names, addresses (postal and e-mail), and telephone numbers of at least three references. Applicants who are not U.S. citizens must state their current Visa and residency status. Screening will begin immediately, and will continue until the position is filled (pending budget approval). The University of Texas at San Antonio is an Affirmative Action/Equal Opportunity Employer. Women, minorities, veterans, and individuals with disabilities are encouraged to apply. Applications may be faxed, emailed, or mailed to: Chair of Bioinformatics Faculty Search Committee Department of Computer Science The University of Texas at San Antonio One UTSA Circle San Antonio, TX 78249-1644 bioinfosearch at cs.utsa.edu FAX: 210-458-4437 ----------------------------------------------------------------------------------------------------------- UNIVERSITY OF TEXAS HEALTH SCIENCE CENTER - SAN ANTONIO Faculty Position in Bioinformatics Candidates are invited to apply for a faculty position in the Department of Epidemiology and Biostatistics at the University of Texas Health Science Center at San Antonio (http://deb.uthscsa.edu/index.html) in the area of bioinformatics. A tenure-track position is available at the rank of assistant/associate/full professor level in biostatistics/bioinformatics. This position is related to a major new joint multi-disciplinary bioinformatics and computational biology initiative involving the University of Texas Health Science Center, and the University of Texas San Antonio (http://www.cbi.utsa.edu/about). Based in a new computational biology facility, the initiative provides both technical staff as well as substantial computational resources to establish and nurture collaborations between biologists and quantitative scientists in projects ranging from biological data analysis to system modeling and simulation. Duties include conducting methodological and applied statistical research in bioinformatics. As the initiative also includes a substantial effort at the level of undergraduate and graduate education, duties will also include curriculum development and teaching. Candidates will be expected to participate in the development of interdisciplinary programs and grant initiatives in bioinformatics, and collaborative investigations with investigators in medical, translational and basic science application areas; e.g., microarray analyses, data mining, gene networks, etc. Requirements are that applicants hold a PhD or equivalent in biostatistics, mathematical statistics, bioinformatics, or a closely related discipline. Candidates at the assistant professor level need to have at least one year of postdoctoral training and research in bioinformatics. For an associate/full professor, we seek candidates with nationally recognized scholarly accomplishments in bioinformatics, including methodological and collaborative research. A background of extramural funding is valued, as is experience in teaching and graduate mentorship. The selected candidate is expected to strengthen the translational research ties between the Department of Epidemiology and Biostatistics and the Children's Cancer Research Institute, the San Antonio Cancer Institute, the Research Imaging Center and the Barshop Institute for Longevity and Aging Studies as well as participate in the University of Texas Health Science Center at San Antonio - University of Texas San Antonio Bioinformatics / Computational Biology Program, and the newly established Department of Defense funded National Center for Targeted Therapeutics. Applicants should submit curriculum vitae, at least three letters of reference, and a letter describing their background, research interests, and relevant experience to: Brad Pollock, MPH, PhD Department of Epidemiology and Biostatistics University of Texas Health Science Center at San Antonio 7703 Floyd Curl, MC 7933 San Antonio, Texas 78229 Applications will be considered until the position is filled. The University of Texas Health Science Center at San Antonio is an Equal Employment Opportunity/Affirmative Action Employer. All faculty appointments are designated as security sensitive positions. -- 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 CONFIDENTIAL NOTICE: The contents of this email and any attachments to it may be privileged or contain privileged and confidential information. This information is only for the viewing or use of the intended recipient. If you have received this e-mail in error or are not the intended recipient, you are hereby notified that any disclosure, copying, distribution or use of, or the taking of any action in reliance upon, any of the information contained in this e-mail, or any of the attachments to this e-mail, is strictly prohibited and that this e-mail and all of the attachments to this e-mail, if any, must be immediately returned to the sender or destroyed and, in either case, this e-mail and all attachments to this e-mail must be immediately deleted from your computer without making any copies hereof and any and all hard copies made must be destroyed. If you have received this e-mail in error, please notify the sender by e-mail immediately. From feldman at ICSI.Berkeley.EDU Tue Nov 14 12:48:40 2006 From: feldman at ICSI.Berkeley.EDU (Jerome Feldman) Date: Tue, 14 Nov 2006 09:48:40 -0800 Subject: Connectionists: M2M book errata Message-ID: <455A0178.1010707@icsi.berkeley.edu> Friends, My MIT Press book is about to go to the second (small) printing. Please send me any errors that you have noticed. The currently known corrections and updates are at: www.m2mbook.org/updates/ Thanks, Jerry From dayan at gatsby.ucl.ac.uk Thu Nov 16 02:20:59 2006 From: dayan at gatsby.ucl.ac.uk (Peter Dayan) Date: Thu, 16 Nov 2006 07:20:59 +0000 Subject: Connectionists: Gatsby faculty recruitment Message-ID: <20061116072059.GA13915@crick.gatsby.ucl.ac.uk> The Gatsby Computational Neuroscience Unit at UCL is looking to recruit a junior or senior level faculty in machine learning or statistics. We are especially interested in candidates whose work in these fields integrates well with the Unit's focus on probabilistic inference and learning, or its wider interests in the brain. Along with the statistical machine learning focus at Gatsby, led by Yee Whye Teh, UCL offers a rich environment across the breadth of the field. Activities in these areas are anchored by the new Centre for Computational Statistics and Machine Learning which is directed by John Shawe-Taylor, involving the departments of Computer Science (Mark Herbster; Massimiliano Pontil), Statistics (Phil Dawid; Trevor Sweeting) and Gatsby itself. The Gatsby Unit was set up at UCL in 1998 as a research institute devoted to computational neuroscience and machine learning. We have core funding for five faculty, eight postdocs and around twelve PhD students. PIs can raise additional funds through grants. We have no undergraduate programme, so only teaching and supervision of graduate-level Gatsby students is required. We have close ties with the Departments of Anatomy, Computer Science, Psychology, Physiology and Statistics at UCL and with groups in Engineering and Physics (Zoubin Ghahramani, David MacKay) at Cambridge and beyond. We are located in a leafy haven in Queen Square, London. Applications, consisting of a CV, a statement of research interests and accomplishments and full contact details for three academic referees should be sent to Alexandra Boss by email: alexandra 'at' gatsby.ucl.ac.uk, or post: Gatsby Unit, UCL, Alexandra House, 17 Queen Square, London WC1N 3AR, UK. Applicants are asked to provide standardised monitoring information by completing and returning the forms available at: www.gatsby.ucl.ac.uk/vacancies/Applications_by_CV.pdf Applications must arrive no later than 5th January 2007. For further information, please see www.gatsby.ucl.ac.uk; for informal enquiries, please contact Yee Whye Teh at ywteh 'at' gatsby.ucl.ac.uk We particularly welcome applications from women and ethnic minorities. From macl at isr.ist.utl.pt Thu Nov 16 03:36:19 2006 From: macl at isr.ist.utl.pt (Manuel Cabido Lopes) Date: Thu, 16 Nov 2006 10:36:19 +0200 (EET) Subject: Connectionists: International Symposium on Imitation in Animals and Artifacts Message-ID: <54003.130.188.8.12.1163666179.squirrel@omni.isr.ist.utl.pt> CALL FOR PARTICIPATION 4th International Symposium on Imitation in Animals and Artifacts at the AISB'07 Convention in Newcastle upon Tyne, UK April 2nd-5th 2007 http://vislab.isr.ist.utl.pt/aisb07_imitation/ ABSTRACT: Imitation facilitates transmitting culture practices and ideas from generation to generation, enabling humans, animals, and now robots, to learn skills others have already mastered. By avoiding the lengthy period of trial-and-error to accomplish new tasks, imitation is thus a very efficient learning method, and also a very intuitive way to program robots by teaching. Imitation is unique among other social learning mechanisms in that it requires the observer to understand the action being performed, and then to relate it to its equivalent motor representations. It also requires the integration of information from sensory, motor, and brain systems, whose underlying mechanisms are not well-understood yet. Explaining the imitative abilities of humans and other animals has proved to be a complex subject. Indeed, it is highly non-trivial even to say exactly what it means for two behaviours to be the "same". The mechanisms of imitation and social learning are not well-understood, and the connections to social interaction, communication, development, and learning are deep, as recent research from various disciplines has started to uncover. Comparison of imitation in animals and artifacts reveals that easy tasks for machines can be hard tasks for animals and vice-versa. However, computational complexity issues do not explain, by themselves, the existence or not of imitation behaviours in animals, and the integration of higher level cognitive capabilities like agent?s goals, intentions and emotions, may play a fundamental role in explaining these differences. This interdisciplinary workshop will bring together researchers from neuroscience, brain imaging, animal psychology, computer science and robotics to examine the latest advances to imitation, aiming to further advance our understanding of the underlying mechanisms. AREAS OF INTEREST (not limited to): * Cognitive Development and Imitation * Neurobiological Foundations of Imitation * Social interaction and Imitation * Language acquisition * Imitation, Intentionality and Communication * Imitation in Animals * Learning by Imitation to bootstrap the acquisition of skills & knowledge * The Role of Imitation in the Development of Social Cognition * Robot Imitation * Computational mechanisms of imitation * Joint-attention and perspective taking * Cultural transmission of skills * Teaching and scaffolding of behaviours * Imitation and motivation Chairs: Jos? Santos-Victor (IST, PT) Manuel Lopes (IST, PT) Alexandre Bernardino (IST, PT) Steering Committee: Yiannis Demiris (IC, UK) Chrystopher L. Nehaniv (Herts, UK) Kerstin Dautenhahn (Herts, UK) Program Committee: Alexandre Bernardino, (IST, Portugal) Andrew Meltzoff, (U. Washington, USA) Aris Alissandraiks, (Hertfordshire, UK) Aude Billard, (EPFL, CH) Bart Jansen, (VUB, Belgium) Brian Scassellati, (Yale, USA) Chana Akins, (Kentucky, USA) C. L. Nehaniv, (Hertfordshire, UK) Fr?d?ric Kaplan, (Sony CSL, FR) Francisco Lacerda, (Stockholm, Sweden) Giorgio Metta, (Genova, IT) Harold Bekkering, (Nijmegen, NL) Heiko Wersing, (Honda R.I., Germany) Irene Pepperberg, (Harvard, USA) Jacqueline Nadel, (CNRS, France) Jochen J. Steil, (Bielefeld, Germany) Joanna Bryson, (Bath, UK) Jos? Santos-Victor, (IST, Portugal) K. Dautenhahn, (Hertfordshire, UK) Ludwig Huber, (Vienna, Austria) Manuel Lopes, (IST, Portugal) Max Lungarella, (Tokyo, JP) Monica Nicolescu, (Nevada, USA) Nicola McGuigan, (St. Andrews, Scotland) Rui Prada, (IST, Portugal) Thomas R. Zentall, (Kentucky, USA) Tony Belpaeme, (Plymouth, UK) Yukie Nagai, (Bielefeld, Germany) Yiannis Demiris, (Imperial College UK) Special Dates: Dec 15 Paper submissions Feb 05 Notification Feb 22 Camera ready copies April 02-05 AISB'07 Workshop website: http://vislab.isr.ist.utl.pt/aisb07_imitation/ Conference website: http://www.aisb.org.uk/convention/aisb07/ -- =============================================================== Manuel Lopes Instituto Superior Tecnico macl at isr.ist.utl.pt Instituto de Sistemas e Robotica www.isr.ist.utl.pt/~macl Av. Rovisco Pais, 1 1049-001 Lisboa, PORTUGAL +351218418291 (fax) ================================================================ From wduch at is.umk.pl Fri Nov 17 07:23:03 2006 From: wduch at is.umk.pl (Wlodzislaw Duch) Date: Fri, 17 Nov 2006 13:23:03 +0100 Subject: Connectionists: 3 papers on challenges for Computational Intelligence Message-ID: <002d01c70a43$221bc3c0$6400a8c0@duchnote> Dear Colleagues, defining what is Computational Intelligence and how is it related to AI and other branches of science is quite controversial, but such a chapter was hard to avoid in the forthcoming book "Challenges for Computational Intelligence". At this address: http://www.fizyka.umk.pl/publications/kmk/06-CIdef.html you can find the abstract and link to the paper: W. Duch, What is Computational Intelligence and where is it going? In: W. Duch and J. Mandziuk, Challenges for Computational Intelligence. Springer "Studies in Computational Intelligence" Series, 2007, pp. xxx-yyy (12 pp) The second paper has also been written as a chapter for the same book: W. Duch, Towards comprehensive foundations of computational intelligence. http://www.fizyka.umk.pl/publications/kmk/06-CI-foundations.html In the third paper I have introduced the concept of k-separability to characterize non-separable problems, redefine the goal of learning and find simplest models that solve difficult learning problems, such as problems arising when the structure of the data involves non-trivial logic. W. Duch, K-separability. Lecture Notes in Computer Science 4131 (2006) 188-197. http://www.fizyka.umk.pl/publications/kmk/06-ksep.html As usually I shall be grateful for your comments. Enjoy, Wlodek Duch ______________________________________________________ School of Computer Engineering, Nanyang Technological University, Singapore; Dept. of Informatics, Nicolaus Copernicus University, Torun, Poland; Google: Duch From rsun at rpi.edu Sat Nov 18 09:52:23 2006 From: rsun at rpi.edu (Professor Ron Sun) Date: Sat, 18 Nov 2006 09:52:23 -0500 Subject: Connectionists: new book available ---- Cognition and Multi-Agent Interaction: From Cognitive Modeling to Social Simulation Message-ID: new book available ---- Cognition and Multi-Agent Interaction: From Cognitive Modeling to Social Simulation Edited by Ron Sun Published by Cambridge University Press http://www.cambridge.org/us/catalogue/catalogue.asp? isbn=0521839645 This book explores the intersection between cognitive sciences and social sciences. In particular, it explores the intersection between individual cognitive modeling and modeling of multi-agent interaction (social stimulation). The two contributing fields --individual cognitive modeling (especially cognitive architectures) and modeling of multi-agent interaction (including social simulation and, to some extent, multi-agent systems) -- have seen significant growth in recent years. However, the interaction of these two fields has not been sufficiently developed. We believe that the interaction of the two may be more significant than either alone, leading to better understanding of both individual cognition and sociocultural processes. It is possible that an integrative field of study in cognitive and social sciences is emerging and we are laying the foundation for it. ? explore a heretofore largely unexplored area ? written by leading researchers in various disciplines ? provide provocative new insights into relevant issues and solid research ? intended for researchers and students in cognitive, behavioral, and social sciences but may also be read by interested laypersons ----------------------------- Contents Part I. Introduction: 1. Prolegomena to integrating cognitive modeling and social simulation. Ron Sun; Part II. Overviews of Cognitive Architectures: 2. Modeling paradigms in ACT-R. Niel Taatgen, Christian Lebiere and John Anderson; 3. Considering Soar as an agent architecture. Robert Wray and Randolph M. Jones; 4. The CLARION cognitive architecture: extending cognitive modeling to social simulation. Ron Sun; Part III. Modeling and Simulating Cognitive and Social Processes: 5. Cognitive architectures, game playing, and human evolution. Robert West, Christian Lebiere, and Dan Bothell; 6. Simulating a simple case of organizational decision making. Isaac Naveh and Ron Sun; 7. Cognitive modeling of social behaviors. William J. Clancey, Maarten Sierhuis, Bruce Damer, and Boris Brodsky; 8. Cognitive agents interacting in real and virtual worlds. Brad Best and Christian Lebiere; 9. Modeling social emotions and social attributions. Jonathan Gratch, Wenji Mao, and Stacy Marcella; 10. Communicating and collaborating with robotic agents. J. Gregory Trafton, Alan C. Schultz, Nicholas L. Cassimatis, et al; 11. Behavior-based methods for modeling and structuring control of social robots. Dylan Shell and Maja Mataric; 12. Evolution of a teamwork model. Nathan Schurr, Steven Okamoto, Rajiv T. Matheswaran, and Milind Tambe; 13. Sociality in embodied neural agents. Domenico Parisi and Stefano Nolfi; 14. Cognitive architecture and contents for social structures and interactions. Cristiano Castelfranchi; Part IV. A Symposium: 15. Cognitive science and good social science. Scott Moss; 16. Collective cognition and emergence in multi-agent systems. Pietro Panzarasa and Nick Jennings; 17. Social judgement in multi-agent systems. Tom Burns and Ewa Roszkowska; 18. Including human variability in a cognitive architecture to improve team simulation. Frank Ritter and Emma Norling; 19. When does social simulation need cognitive models? Nigel Gilbert. -------------------------------- To order, please go to: http://www.cambridge.org/us/catalogue/catalogue.asp?isbn=0521839645 or http://www.cambridge.org/uk/catalogue/catalogue.asp?isbn=0521839645 ======================================================== Professor Ron Sun Cognitive Science Department Rensselaer Polytechnic Institute 110 Eighth Street, Carnegie 302A Troy, NY 12180, USA phone: 518-276-3409 fax: 518-276-3017 email: rsun at rpi.edu web: http://www.cogsci.rpi.edu/~rsun ======================================================= From daniela.pelz at bccn-berlin.de Mon Nov 20 03:24:31 2006 From: daniela.pelz at bccn-berlin.de (Daniela Pelz) Date: Mon, 20 Nov 2006 09:24:31 +0100 Subject: Connectionists: Master and PhD Program Computational Neuroscience Message-ID: <4561663F.4060709@bccn-berlin.de> Dear Connectionists, attached please find the announcement of a Master and a PhD program in Computational Neuroscience. Sincerely yours, Daniela Pelz -- Dr. Daniela Pelz Teaching Coordinator Bernstein Center for Computational Neuroscience Institute f. Biology, Humboldt University Invalidenstr. 42 10115 Berlin phone: (030) 2093-9110 fax: (030) 2093-8801 =============================================================================================== International Master of Science or PhD in Computational Neuroscience Bernstein Center for Computational Neuroscience Berlin, Germany The Berlin University of Technology, the Charit? Medical School and the Humboldt University of Berlin solicit applications for an international Master and PhD program in Computational Neuroscience within the Bernstein Center for Computational Neuroscience Berlin (http://www.bccn-berlin.de). The Master program is full-time for four semesters, and started in October 2006. The PhD program is full-time for three years, and will start in October 2007. Course language is English. There are no tuition fees. Application deadline for both programs is March 1^st 2007. Courses start in October 2007. Objectice of the MSc and PhD Program Computational neuroscience uses a multidisciplinary approach for understanding the functioning brain. It combines experiments with data analysis and computer simulations on the basis of well-defined theoretical concepts, and makes a scientific language available that can be used across disciplines and levels for neurobiology, cognitive science, and information technology. Computational Neuroscience may thus help to solve long-standing research questions, contribute to better prevention and treatment strategies for neural disorders, lead to unified concepts about biological processes, advance information technologies and human-machine interactions and, last but not least, provide new insight for designing efficient strategies for teaching and learning. Both the MSc and the PhD program emphasize a broad, interdisciplinary education with strong interactions between experiment and theory. The programs? faculty is drawn from the Bernstein Center for Computational Neuroscience, which represents university departments ranging from biology and medicine to physics and computer science at the three major universities in Berlin. > Language of Instruction: English > Duration of MSc Program: 2 years > Duration of PhD Program: 3 years > Application deadline: March 1st > Beginning of Programs: Mid October Final degrees: > MSc Computational Neuroscience > PhD from the department of the student?s principal thesis advisor and a certificate from the Berlin Graduate School for Computational Neuroscience Structure of the MSc Program (starting in 2006) The 2-year-Master program is organized in modules, each consisting of one or more courses. The courses comprise lectures, tutorials, exercises, seminars, experimental laboratories, and research projects. For each module students are assessed through oral or written exams and receive the corresponding number of European Credit Points (CP, one CP roughly corresponds to 30 hours of student work.). Students are expected to earn 60 CP per year. In the first two semesters, students are individually brought to a high level of competence in the basic fields of the program. The third semester is devoted to lab rotations. Every student will participate in research projects in three different laboratories affiliated with the Bernstein Center. Each of the three projects lasts for approximately two months (3x9 CP). The projects will be tailored to give intensive hands-on experience to the students. They will carry out individual research projects, and will be supervised by a senior researcher. The three projects include at least one theoretical and one experimental project. Additionally, students will take an obligatory course on ethical issues and societal implications of brain research. The fourth semester is primarily devoted to thesis research (20 CP), and complemented by courses on advanced topics (10 CP). The Master thesis is concluded by an oral presentation (defense). Structure of the PhD Program (starting in 2007) The 3-year PhD program has a strong focus on thesis research and is complemented by course work (30 CP). Course work will cover advanced topics freely chosen from the curriculum of the Bernstein Center such as methodological courses or international summer schools (15 CP). Another 15 CP will be earned by participating in ?soft-skill? courses, in a weekly PhD student seminar, poster or oral contributions at symposia and international conferences and the like. The PhD thesis is evaluated by three reviewers and is defended in an oral presentation. Application Master Program: Bachelor degree or equivalent required PhD program: Master degree or equivalent required Entry degrees have to be awarded by an internationally recognized university-level institution, typically in the areas of natural sciences, engineering, or mathematics. Students who graduated in other subjects have to document sufficient mathematical knowledge in linear algebra, analysis, probability theory and statistics. also to be included: > TOEFL test or equivalent certificate of proficiency in English (non-native speakers only) > a letter describing why you want to study computational neuroscience at the Berlin Graduate School > CV including activities and experiences relevant for the studies > copies of certificates and transcript of records of previous studies > two letters of recommendation > a completed matriculation form > a GRE general test pdf dowload and further information at www.computation-neuroscience-berlin.de/admission Details of the admission requirements and procedures are currently in the legislative process of the state of Berlin and may be subject to change. Bernstein Center for Computational Neuroscience The Bernstein Center for Computational Neuroscience Berlin integrates research and teaching activities at the Charit?-Universit?tsmedizin Berlin, Freie Universit?t Berlin, Humboldt-Universit?t zu Berlin, Berlin University of Technology, Fraunhofer FIRST, the Max-Delbrueck-Center and the Wissenschaftskolleg zu Berlin. Teaching and Training follow a ?one day, one location? principle. http:// www.bccn-berlin.de For further information please contact daniela.pelz at bccn-berlin.de From t.heskes at science.ru.nl Mon Nov 20 10:29:05 2006 From: t.heskes at science.ru.nl (Tom Heskes) Date: Mon, 20 Nov 2006 16:29:05 +0100 Subject: Connectionists: Neurocomputing volume 70 (issues 1-3) Message-ID: <4561C9C1.1090307@science.ru.nl> Neurocomputing volume 70 (issues 1-3) ------- SPECIAL PAPERS (7th Brazilian Symposium on Neural Networks edited by A.F.R. Ara?jo and A. de Carvalho) The Brazilian Symposium on Neural Networks (SBRN?04) Alu?zio F.R. Ara?jo and Andr? de Carvalho A computational model of the primary auditory cortex exhibiting plasticity in the frequency representation Marilene de Pinho, Marcelo Mazza and Ant?nio C. Roque Using non-linear even functions for error minimization in adaptive filters Allan Kardec Barros, Jose Principe, Yoshinori Takeuchi and Noboru Ohnishi Reinforcement learning of a simple control task using the spike response model Murilo Saraiva de Queiroz, Roberto Coelho de Berr?do and Ant?nio de P?dua Braga Influence zones: A strategy to enhance reinforcement learning Arthur Pl?nio de S. Braga and Alu?zio F.R. Ara?jo The best currently known class of dynamically equivalent cellular automata rules for density classification Pedro P.B. de Oliveira, Jos? C. Bortot and Gina M.B. Oliveira Use of gene dependent mutation probability in evolutionary neural networks for non-stationary problems Renato Tin?s and Andr? C.P.L.F. de Carvalho Determination of multiple direction of arrival in antennas arrays with radial basis functions Osmar de Ara?jo Dourado J?nior, Adri?o Duarte D?ria Neto and Wilson da Mata Improving self-organization of document collections by semantic mapping Renato Fernandes Corr?a and Teresa Bernarda Ludermir Combining an evolutionary algorithm with data mining to solve a single-vehicle routing problem H.G. Santos, L.S. Ochi, E.H. Marinho and L.M.A. Drummond ------- REGULAR PAPERS Detecting novelties in time series through neural networks forecasting with robust confidence intervals Adriano L.I. Oliveira and Silvio R.L. Meira Developing parallel sequential minimal optimization for fast training support vector machine L.J. Cao, S.S. Keerthi, C.J. Ong, P. Uvaraj, X.J. Fu and H.P. Lee Neural network approach to contingency screening and ranking in power systems K. Shanti Swarup and G. Sudhakar Neural computation using discrete and continuous Hopfield networks for power system economic dispatch and unit commitment K. Shanti Swarup and P.V. Simi Concurrent genetic optimization for joint design of source and channel codes Chien-Min Ou, Wen-Jyi Hwang, Wen-Wei Hu and Tsung-Yan Lo Wavelet-based nonlinear multiscale decomposition model for electricity load forecasting D. Benaouda, F. Murtagh, J.-L. Starck and O. Renaud A novel mixture of experts model based on cooperative coevolution Minh Ha Nguyen, Hussein A. Abbass and Robert I. Mckay Dynamics of periodic Cohen?Grossberg neural networks with varying delays Zhaohui Yuan, Lifen Yuan and Lihong Huang A meta-learning approach to automatic kernel selection for support vector machines Shawkat Ali and Kate A. Smith-Miles Ensemble classifiers based on correlation analysis for DNA microarray classification Kyung-Joong Kim and Sung-Bae Cho Inhibitory control of spike timing precision M. Ambard and D. Martinez Balanced parameterization of multichannel blind deconvolutive systems: A continuous time realization Liangsuo Ma and Ah Chung Tsoi Linear stability and Hopf bifurcation in a three-unit neural network with two delays Shaofen Zou, Lihong Huang and Yuming Chen A modified infomax algorithm for blind signal separation Hyung-Min Park, Sang-Hoon Oh and Soo-Young Lee Self-generation RBFNs using evolutional PSO learning Hsuan-Ming Feng Simulation of neural population dynamics with a refractory density approach and a conductance-based threshold neuron model Anton V. Chizhov, Lyle J. Graham and Andrey A. Turbin Quantitative measure of complexity of the dynamic event-related EEG data Xiao-mei Pei, Chong-xun Zheng, Wei-xing He and Jin Xu On the global robust asymptotic stability of BAM neural networks with time-varying delays Xuyang Lou and Baotong Cui Melt index prediction by neural networks based on independent component analysis and multi-scale analysis Jian Shi, Xinggao Liu and Youxian Sun Neural network control of flexible-link manipulators using sliding mode Yuangang Tang, Fuchun Sun and Zengqi Sun Adaptive neuro-fuzzy inference system to compute quasi-TEM characteristic parameters of microshield lines with practical cavity sidewall profiles Elif Derya ?beyli and I.nan G?ler Feature selection and classification using flexible neural tree Yuehui Chen, Ajith Abraham and Bo Yang On global exponential stability of generalized stochastic neural networks with mixed time-delays Yurong Liu, Zidong Wang and Xiaohui Liu NeuGen: A tool for the generation of realistic morphology of cortical neurons and neural networks in 3D J.P. Eberhard, A. Wanner and G. Wittum Global exponential stability of periodic neural networks with time-varying delays Haijun Jiang and Jinde Cao Generalization ability of Boolean functions implemented in feedforward neural networks Leonardo Franco Convergence analysis of Xu's LMSER learning algorithm via deterministic discrete time system method Jian Cheng Lv, Zhang Yi and K.K. Tan Interpretation of perceptron weights as constructed time series for EEG classification Dik Kin Wong, E. Timothy Uy, Marcos Perreau Guimaraes, Wayne Yang and Patrick Suppes Extracting rules from multilayer perceptrons in classification problems: A clustering-based approach Eduardo R. Hruschka and Nelson F.F. Ebecken Inversion-based nonlinear adaptation of noisy acoustic parameters for a neural/HMM speech recognizer Edmondo Trentin and Marco Gori Short-term ANN load forecasting from limited data using generalization learning strategies Zeke S.H. Chan, H.W. Ngan, A.B. Rad, A.K. David and N. Kasabov Non-flat function estimation with a multi-scale support vector regression Danian Zheng, Jiaxin Wang and Yannan Zhao Multiple recurrent neural networks for stable adaptive control Wen Yu A fast modified constructive-covering algorithm for binary multi-layer neural networks Di Wang and Narendra. S. Chaudhari Sparse support vector regression based on orthogonal forward selection for the generalised kernel model X.X. Wang, S. Chen, D. Lowe and C.J. Harris The regularized LVQ1 algorithm Sergio Bermejo Extreme learning machine: Theory and applications Guang-Bin Huang, Qin-Yu Zhu and Chee-Kheong Siew Inverse training scheme for MS_CMAC neural network to handle random training data Jiun-Chi Jan, Chih-Ming Chen and Liang-Hao Hsiao A set of nonlinear equations and inequalities arising in robotics and its online solution via a primal neural network Yunong Zhang An efficient hidden layer training method for the multilayer perceptron Changhua Yu, Michael T. Manry, Jiang Li and Pramod Lakshmi Narasimha Dynamical behaviors of Cohen?Grossberg neural networks with delays and reaction?diffusion terms Hongyong Zhao and Kunlun Wang A new training and pruning algorithm based on node dependence and Jacobian rank deficiency Jinhua Xu and Daniel W.C. Ho Mold temperature control of a rubber injection-molding machine by TSK-type recurrent neural fuzzy network Chia-Feng Juang, Shui-Tien Huang and Fun-Bin Duh Modified gradient algorithm for total least square filtering Xiangyu Kong, Chongzhao Han and Ruixuan Wei PIRANHA: Policy iteration for recurrent artificial neural networks with hidden activities Istv?n Szita and Andr?s Lo"rincz ------- BRIEF PAPERS A novel full structure optimization algorithm for radial basis probabilistic neural networks Ji-Xiang Du, De-Shuang Huang, Guo-Jun Zhang and Zeng-Fu Wang Three-dimensional surface registration: A neural network strategy Heng Liu, Jingqi Yan and David Zhang Stability analysis of an unsupervised neural network with feedforward and feedback dynamics A. Meyer-Baese and S. Pilyugin ------- JOURNAL SITE: http://www.elsevier.com/locate/neucom SCIENCE DIRECT: http://www.sciencedirect.com/science/issue/5660-2006-999299998-636228 From lendasse at james.hut.fi Sun Nov 19 15:43:27 2006 From: lendasse at james.hut.fi (Amaury Lendasse) Date: Sun, 19 Nov 2006 22:43:27 +0200 Subject: Connectionists: ESTSP'07: Deadline has been extended Message-ID: **We apologize for possible duplicates of this message, sent to distributions lists only** Due to a number of requests, we have extended the submission deadline. Submission of papers: 29 November 2006 (instead of 22 November) ESTSP 2007 07 - 09 February 2007 The first European Symposium on Time Series Prediction (TSP) is a new event in the fields of Neural Networks, Statistics and Econometrics. It will be held in Espoo (Helsinki), one of the most innovative towns in Europe. Contributions are welcome. Webpage: http://www.estsp2007.org/ DEADLINES Submission of papers: 29 November 2006 (instead of 22 November) Notification of acceptance: 15 December 2006 ESTSP conference: 07 - 09 February 2007 PREDICTION COMPETITION A new prediction competition is organized. The goal of the competition is the long-term prediction of a new benchmark. The dataset will be available on October 1st. The competition deadline is on November 29nd, same date as the paper submission deadline. The schedule of the competition will favor fast methods. PROCEEDINGS AND JOURNAL SPECIAL ISSUE The proceedings will include all communications presented to the conference, and will be available on-site. Extended versions of selected papers will be published in the Neurocomputing journal (Elsevier). LOCATION The ESTSP 2007 conference will be held at the Helsinki University of Technology in Dipoli conference center. Helsinki University of Technology is one of the top universities in Finland for both education and research. The ESTSP 2007 is organized by the Adaptive Informatics Research Centre from the Laboratory of Computer and Information Science (CIS) of HUT. Espoo, a high-tech metropolis, surrounded by nature is a lively and buzzling city in the greater Helsinki region. The conference will be organized in a conference center located near the university at a walking distance from the Radisson SAS Hotel of Espoo. Conference location: Dipoli Conference Center Otakaari 24 FI-02150 ESPOO, FINLAND CONTACT AND CONFERENCE SECRETARIAT All questions concerning ESTSP'2007 may be sent by e-mail (preferred) to estsp2007( at )estsp2007.org. Contact address: Dr. Amaury Lendasse Helsinki University of Technology Laboratory of Computer and Information Science P.O. Box 5400 FI-02015 HUT FINLAND fax +358-9-451 3277 http://www.estsp2007.org/ From bilmes at ee.washington.edu Mon Nov 20 19:21:54 2006 From: bilmes at ee.washington.edu (Jeff Bilmes) Date: Mon, 20 Nov 2006 16:21:54 -0800 Subject: Connectionists: Post-doctoral position at University of Washington, Seattle Message-ID: <456246A2.8000006@ee.washington.edu> Post-doctoral position at University of Washington, Seattle The Department of Computer Science & Engineering at the University of Washington, Seattle is offering a one year postdoctoral research position in the areas of machine learning, probabilistic reasoning, and time series learning with application to activity recognition. The starting date could be as early as December 1st, 2006. This position is funded by a DARPA program in which we develop techniques for automatically generating high-level summaries of human activities based on data collected by wearable sensors. There are a variety of exciting research opportunities in this context, including unsupervised discovery of activities, learning to extract high-level information from various types of sensors, adaptation and transfer learning on sequences, boosted neural networks, multi-modal information fusion and particularly neural approaches to this problem, and efficient reasoning about unknown numbers of objects. Some related papers: http://www.cs.washington.edu/robotics/abstracts/gps-msb-uai-06.abstract.html http://www.cs.washington.edu/robotics/abstracts/places-ijrr-07.abstract.html http://www.cs.washington.edu/robotics/abstracts/veb-ijcai-07.abstract.html The University of Washington is an affirmative action, equal opportunity employer. The University is dedicated to the goal of building a culturally diverse and pluralistic faculty, and research staff committed to teaching and working in a multicultural environment and strongly encourages applications from women, minorities, individuals with disabilities, and covered veterans. Please reply by sending email to Jeff Bilmes or Dieter Fox . From esann at dice.ucl.ac.be Tue Nov 21 10:52:59 2006 From: esann at dice.ucl.ac.be (esann) Date: Tue, 21 Nov 2006 16:52:59 +0100 Subject: Connectionists: deadline extension: ESANN'2007 European Symposium on Artificial Neural Networks Message-ID: <01d401c70d85$1f0f3410$4c1bd6c2@maxwell.local> Due to numerous requests, and also to the unavailability of the submission system during a few days recently, the deadline to submit papers to the ESANN'2007 conference has been extended to December 8, 2006. Note that this extended deadline is strict: no further extension will be allowed. The e-mail below is a reminder of the call for papers. Looking forward to seeing you at ESANN'2007, The organizing committee. ===================================================== ESANN'2007 15th European Symposium on Artificial Neural Networks Advances in Computational Intelligence and Learning Bruges (Belgium) - April 25-26-27, 2007 Announcement and call for papers ===================================================== The call for papers for the ESANN'2007 conference is now available on the Web: http://www.dice.ucl.ac.be/esann For those of you who maintain WWW pages including lists of related ANN sites: we would appreciate if you could add the above URL to your list; thank you very much! We make all possible efforts to avoid sending multiple copies of this call for papers; however we apologize if you receive this e-mail twice, despite our precautions. You will find below a short version of this call for papers, without the instructions to authors (available on the Web). ESANN'2007 is organized in collaboration with the UCL (Universite catholique de Louvain, Louvain-la-Neuve) and the KULeuven (Katholiek Universiteit Leuven). The conference is technically co-sponsored by the International Neural Networks Society, the European Neural Networks Society, the IEEE Computational Intelligence Society, the IEEE Region 8, the IEEE Benelux Section (sponsors to be confirmed). Scope and topics ---------------- Since its first happening in 1993, the European Symposium on Artificial Neural Networks has become the reference for researchers on fundamentals and theoretical aspects of artificial neural networks, computational intelligence, learning and related topics. Each year, around 100 specialists attend ESANN, in order to present their latest results and comprehensive surveys, and to discuss the future developments in this field. The ESANN'2007 conference will follow this tradition, while adapting its scope to the new developments in the field. Artificial neural networks are viewed as a branch, or subdomain, of machine learning, statistical information processing and computational intelligence. Mathematical foundations, algorithms and tools, and applications are covered. The following is a non-exhaustive list of machine learning, computational intelligence and artificial neural networks topics covered during the ESANN conferences: THEORY and MODELS Statistical and mathematical aspects of learning Feedforward models Kernel machines Graphical models, EM and Bayesian learning Vector quantization and self-organizing maps Recurrent networks and dynamical systems Blind signal processing Ensemble learning Nonlinear projection and data visualization Fuzzy neural networks Evolutionary computation Bio-inspired systems INFORMATION PROCESSING and APPLICATIONS Data mining Signal processing and modeling Approximation and identification Classification and clustering Feature extraction and dimension reduction Time series forecasting Multimodal interfaces and multichannel processing Adaptive control Vision and sensory systems Biometry Bioinformatics Brain-computer interfaces Neuroinformatics Papers will be presented orally (single track) and in poster sessions; all posters will be complemented by a short oral presentation during a plenary session. It is important to mention that the topics of a paper decide if it better fits into an oral or a poster session, not its quality. The selection of posters will be identical to oral presentations, and both will be printed in the same way in the proceedings. Nevertheless, authors must indicate their preference for oral or poster presentation when submitting their paper. Special sessions ---------------- Special sessions will be organized by renowned scientists in their respective fields. Papers submitted to these sessions are reviewed according to the same rules as submissions to regular sessions. They must also follow the same format, instructions, deadlines and submission procedure. The special sessions organized during ESANN'2007 are: 1) Fuzzy and Probabilistic Methods in Neural Networks and Machine Learning B. Hammer, Clausthal Univ. Tech. (Germany), T. Villmann, Univ. Leipzig (Germany) 2) Reinforcement Learning V. Heidrich-Meisner, Ruhr-Univ. Bochum, M. Lauer, Univ. Osnabr?ck, C. Igel, Ruhr-Univ. Bochum, M. Riedmiller, Univ. Karlsruhe (Germany) 3) Convex Optimization for the Design of Learning Machines K. Pelckmans, J.A.K. Suykens, Katholieke Univ. Leuven (Belgium) 4) Learning causality P. F. Verdes, Heidelberg Acad. of Sciences (Germany), K. Hlavackova-Schindler, Austrian Acad. of Sciences (Austria) 5) Reservoir Computing D. Verstraeten, B. Schrauwen, Univ. Gent (Belgium) Location -------- The conference will be held in Bruges (also called "Venice of the North"), one of the most beautiful medieval towns in Europe. Bruges can be reached by train from Brussels in less than one hour (frequent trains). The town of Bruges is world-wide known, and famous for its architectural style, its canals, and its pleasant atmosphere. The conference will be organized in a hotel located near the centre (walking distance) of the town. There is no obligation for the participants to stay in this hotel. Hotels of all levels of comfort and price are available in Bruges; there is a possibility to book a room in the hotel of the conference at a preferential rate through the conference secretariat. A list of other smaller hotels is also available. The conference will be held at the Novotel hotel, Katelijnestraat 65B, 8000 Brugge, Belgium. Proceedings and journal special issue ------------------------------------- The proceedings will include all communications presented to the conference (tutorials, oral and posters), and will be available on-site. Extended versions of selected papers will be published in the Neurocomputing journal (Elsevier). Call for contributions ---------------------- Prospective authors are invited to submit their contributions before December 1, 2006. The electronic submission procedure is described on the ESANN portal http://www.dice.ucl.ac.be/esann/. Authors must also commit themselves that they will register to the conference and present the paper in case of acceptation of their submission (one paper per registrant). Authors of accepted papers will have to register before February 28, 2007; they will benefit from the advance registration fee. The ESANN conference applies a strict policy about the presentation of accepted papers during the conference: authors of accepted papers who do not show up at the conference will be blacklisted for future ESANN conferences, and the lists will be communicated to other conference organizers. Deadlines --------- Submission of papers December 1, 2006 Notification of acceptance January 26, 2007 Symposium April 25-27, 2007 Conference secretariat ---------------------- ESANN'2007 d-side conference services phone: + 32 2 730 06 11 24 av. L. Mommaerts Fax: + 32 2 730 06 00 B - 1140 Evere (Belgium) E-mail: esann at dice.ucl.ac.be http://www.dice.ucl.ac.be/esann Steering and local committee ---------------------------- Fran?ois Blayo Ipseite (CH) Gianluca Bontempi Univ. Libre Bruxelles (B) Marie Cottrell Univ. Paris I (F) Jeanny H?rault INPG Grenoble (F) Mia Loccufier Univ. Gent (B) Bernard Manderick Vrije Univ. Brussel (B) Jean-Pierre Peters FUNDP Namur (B) Joos Vandewalle KUL Leuven (B) Michel Verleysen UCL Louvain-la-Neuve (B) Scientific committee (to be confirmed) -------------------- Cecilio Angulo Univ. Polit. de Catalunya (E) Miguel Atencia Univ. Malaga (E) Pierre Bessi?re CNRS (F) Herv? Bourlard IDIAP Martigny (CH) Joan Cabestany Univ. Polit. de Catalunya (E) St?phane Canu Inst. Nat. Sciences App. (F) Valentina Colla Scuola Sup. Sant'Anna Pisa (I) Holk Cruse Universit?t Bielefeld (D) Eric de Bodt Univ. Lille II (F) & UCL Louvain-la-Neuve (B) Dante Del Corso Politecnico di Torino (I) Georg Dorffner University of Vienna (A) Wlodek Duch Nicholas Copernicus Univ. (PL) Marc Duranton Philips Semiconductors (USA) Richard Duro Univ. Coruna (E) Andr? Elisseef IBM Research (CH) Deniz Erdogmus Oregon Health & Science University (USA) Anibal Figueiras-Vidal Univ. Carlos III Madrid (E) Simone Fiori Univ. Perugia (I) Jean-Claude Fort Universit? Nancy I (F) Leonardo Franco Univ. Malaga (E) Colin Fyfe Univ. Paisley (UK) Stan Gielen Univ. of Nijmegen (NL) Mirta Gordon IMAG Grenoble (F) Marco Gori Univ. Siena (I) Bernard Gosselin Fac. Polytech. Mons (B) Manuel Grana UPV San Sebastian (E) Anne Gu?rin-Dugu? INPG Grenoble (F) Barbara Hammer Univ. of Osn?bruck (D) Martin Hasler EPFL Lausanne (CH) Tom Heskes Univ. Nijmegen (NL) Christian Igel Ruhr-Univ. Bochum (D) Jose Jerez Univ. Malaga (E) Gonzalo Joya Univ. Malaga (E) Christian Jutten INPG Grenoble (F) Juha Karhunen Helsinki Univ. of Tech. (FIN) Stefanos Kollias National Tech. Univ. Athens (GR) Jouko Lampinen Helsinki Univ. of Tech. (FIN) Petr Lansky Acad. of Science of the Czech Rep. (CZ) Beatrice Lazzerini Univ. Pisa (I) Erzsebet Merenyi Rice Univ. (USA) Jean-Pierre Nadal Ecole Normale Sup?rieure Paris (F) Erkki Oja Helsinki Univ. of Technology (FIN) Arlindo Oliveira INESC-ID (P) Gilles Pag?s Univ. Paris 6 (F) Thomas Parisini Univ. Trieste (I) H?l?ne Paugam-Moisy Universit? Lumi?re Lyon 2 (F) Alberto Prieto Universitad de Granada (E) Didier Puzenat Univ. Antilles-Guyane (F) Leonardo Reyneri Politecnico di Torino (I) Jean-Pierre Rospars INRA Versailles (F) Fabrice Rossi INRIA (F) Francisco Sandoval Univ.Malaga (E) Jose Santos Reyes Univ. Coruna (E) Craig Saunders Univ.Southampton (UK) Udo Seiffert IPK Gatersleben (D) Bernard Sendhoff Honda Research Institute Europe (D) Peter Sollich King's College (UK) Jochen Steil Univ. Bielefeld (D) John Stonham Brunel University (UK) Johan Suykens K. U. Leuven (B) John Taylor King?s College London (UK) Claude Touzet Univ. Provence (F) Marc Van Hulle KUL Leuven (B) Thomas Villmann Univ. Leipzig (D) Axel Wism?ller Ludwig-Maximilians-Univ. M?nchen (D) Bart Wyns Univ.Gent (B) Michalis Zervakis Technical Univ. Crete (GR) ======================================================== ESANN - European Symposium on Artificial Neural Networks http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews,... Michel Verleysen Univ. Cath. de Louvain - Machine Learning Group 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at dice.ucl.ac.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at dice.ucl.ac.be ======================================================== From g.goodhill at imb.uq.edu.au Tue Nov 21 23:59:52 2006 From: g.goodhill at imb.uq.edu.au (Geoffrey Goodhill) Date: Wed, 22 Nov 2006 14:59:52 +1000 Subject: Connectionists: Postdoc position available Message-ID: <4563D948.1040604@imb.uq.edu.au> POSTDOCTORAL POSITION IN BAYESIAN MODELLING OF AXON GUIDANCE A postdoctoral position is now available in my lab at the Queensland Brain Institute (http://www.qbi.uq.edu.au), funded by a 3-year grant from the Australian National Health & Medical Research Council. The goal of this project is to understand growth cone chemotaxis using a combination of theoretical and experimental techniques. Theoretically we are particularly interested in Bayesian approaches. The experiments are based on timelapse imaging of mouse dorsal root ganglion growth cones in 3D gels using the only Zeiss LSM-5-Live line-scanning confocal microscope in the southern hemisphere, currently located in my lab. Molecular gradients are created in the gels using a novel technology we have recently developed (Nat. Neurosci., 7:678-682, 2004). While the primary responsibility of the current position is theoretical modelling, a strong interest in the experimental aspects of the work would be an advantage. This project is a collaboration with Peter Dayan (UCL) and Linda Richards (University of Queensland). The Queensland Brain Institute was established in 2003 at the University of Queensland (UQ) with the aim of discovering the fundamental mechanisms regulating brain function, particularly those controlling the formation of new nerve connections and the generation of new nerve cells. From late 2007 it will be housed in a new AU$64M, 7000sqm building. According to http://www.thes.co.uk/worldrankings the University of Queensland is one of the top 50 universities in the world. It provides an excellent environment for interdisciplinary research, and is currently investing AU$200M in the general area of Biotechnology. UQ is in Brisbane, the capital of Queensland, a cosmopolitan city of 1.7 million people with excellent facilities, a vibrant cultural environment, and a subtropical climate. Queensland is also home to attractions such as tropical rainforests, the Great Barrier Reef, and some very large crocodiles, though fortunately these don't live anywhere near Brisbane. If you are interested please send a CV, statement of interest and contact information for 3 referees to g.goodhill at uq.edu.au. Informal enquiries are also welcome. 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 http://www.tandf.co.uk/journals/titles/0954898X.asp From doug.aberdeen at anu.edu.au Tue Nov 21 01:46:41 2006 From: doug.aberdeen at anu.edu.au (Douglas Aberdeen) Date: Tue, 21 Nov 2006 17:46:41 +1100 Subject: Connectionists: RL/Planning post-doc or researcher positions with National ICT Australia Message-ID: <455F3E1B-4AF2-4F58-9F7C-34B70B65BEEF@anu.edu.au> * Research Positions in Reinforcement Learning, Australia * Appliction deadline: December 15 (come talk to us at NIPS). National ICT Australia (NICTA), Canberra Lab, have open post-doc, researcher, and senior researcher positions in the area of reinforcement learning (RL). These positions have been created to expand the current RL group within NICTAs Statistical Machine Learning Program (http://sml.nicta.com.au/), headed by Dr Alex Smola. The current RL group consists of Dr Douglas Aberdeen, Dr Olivier Buffet, plus a research engineer and students. The RL group currently has an interest in the use of RL methods for decision-theoretic planning, and thus has a strong relationship with NICTAs co-located planning group headed by Sylvie Thiebaux and Jussi Rintanen. The rest of the Statistical Machine Learning group has interests in kernel methods, optimisation, graphical models, bio-informatics and document analysis. NICTA is Australia's premier ICT (Information Communication Technology) research institute with approximately 300 researchers across the country, conducting a diverse range of technology research. The Statistical Machine Learning group is based in Canberra and conducts research in cooperation with the Australian National University (ANU). The ANU is consistently ranked in the top 10 universities in the Asia/Pacific region, and top 50 in the world. These are pure research positions, however a small amount of teaching through the ANU is encouraged. The duties of the position also include the supervision of research students, and participation in other Program activities. NICTA provides generous resources for travel, supporting visitors, and other activities such as commercialisation of research. Post-doc/researcher positions are typically 3 year fixed term. Senior researcher positions are typically ongoing. Applicants should indicate their preference for these positions. Salary will be commensurate with the background of the applicant, but are approximately in the range of $65,000 to $110,000 Australian dollars per year before tax. Formal applications should be made online at http://nicta.com.au/jobs.html, however please email questions or expressions-of-interest to doug.aberdeen at anu.edu.au. The closing date for applications is December 15, for positions to be taken up by April 2007 or earlier. -- Dr Douglas Aberdeen Senior Researcher Statistical Machine Learning National ICT Australia Limited Locked Bag 8001 Canberra ACT 2601 Tel. +61 2 6125 8647 Fax. +61 2 6125 8645 Email. doug.aberdeen at anu.edu.au Web. http://sml.nicta.com.au/~daa The imagination driving Australia's ICT future. To receive the latest NICTA information register at http:// nicta.com.au/registration.cfm From steve at cns.bu.edu Sat Nov 25 11:22:57 2006 From: steve at cns.bu.edu (Stephen Grossberg) Date: Sat, 25 Nov 2006 11:22:57 -0500 Subject: Connectionists: from hippocampal grid cells to place cells Message-ID: The following article is now available at http://www.cns.bu.edu/Profiles/Grossberg: Gorchetchnikov, A. and Grossberg, S. (2006). Space, time, and learning in the hippocampus: How fine spatial and temporal scales are expanded into population codes for behavioral control. Neural Networks, in press. ABSTRACT: The hippocampus participates in multiple functions, including spatial navigation, adaptive timing, and declarative (notably, episodic) memory. How does it carry out these particular functions? The present article proposes that hippocampal spatial and temporal processing are carried out by parallel circuits within entorhinal cortex, dentate gyrus, and CA3 that are variations of the same circuit design. In particular, interactions between these brain regions transform fine spatial and temporal scales into population codes that are capable of representing the much larger spatial and temporal scales that are needed to control adaptive behaviors. Previous models of adaptively timed learning propose how a spectrum of cells tuned to brief but different delays are combined and modulated by learning to create a population code for controlling goal-oriented behaviors that span hundreds of milliseconds or even seconds. Here it is proposed how projections from entorhinal grid cells can undergo a similar learning process to create hippocampal place cells that can cover a space of many meters that are needed to control navigational behaviors. The suggested homology between spatial and temporal processing may clarify how spatial and temporal information may be integrated into an episodic memory. The model proposes how a path integration process activates a spatial map of grid cells. Path integration has a limited spatial capacity, and must be reset periodically, leading to the observed grid cell periodicity. Integration-to-map transformations have been proposed to exist in other brain systems. These include cortical mechanisms for numerical representation in the parietal cortex. As in the grid-to-place cell spatial expansion, the analog representation of number is extended by additional mechanisms to represent much larger numbers. The model also suggests how visual landmarks may influence grid cell activities via feedback projections from hippocampal place cells to the entorhinal cortex. Keywords: spatial navigation, adaptively timed learning, grid cells, place cells, entorhinal cortex, dentate gyrus, hippocampus, CA3. From zhaoping at gatsby.ucl.ac.uk Sat Nov 25 16:19:36 2006 From: zhaoping at gatsby.ucl.ac.uk (Dr Zhaoping Li) Date: Sat, 25 Nov 2006 21:19:36 +0000 (GMT) Subject: Connectionists: Postdoc position available in London, UK Message-ID: A postdoc position is available in University College London to study visual perception under contextual influences. The post holder should be somebody who is skilled computationally and interested in collaborating/communicating with experimentalists, or somebody skilled in visual psychophysics experiments and interested in collaborating with theorists. He or she will be working work Drs. Li Zhaoping ( www.gatsby.ucl.ac.uk/~zhaoping ) and Peter Dayan (www.gatsby.ucl.ac.uk/~dayan) whose labs carry out both theoretical and experimental projects. The project will also involve interactions/collaborations with Drs. Joshua Solomon and Michael Morgan in City University in London. Candidates should send a C.V. and names of three references to Li Zhaoping (z.li at ucl.ac.uk ) and Peter Dayan (dayan at gatsby.ucl.ac.uk) The starting dates are negotiable, and salary will be commensurate with qualifications and experience. There is also an experimental postdoc position available on the same grant with Joshua Solomon and Michael Morgan and interested parties should contact them (http://www.visionscience.com/pipermail/visionlist/2006/001871.html) . From C.Campbell at bristol.ac.uk Mon Nov 27 08:08:40 2006 From: C.Campbell at bristol.ac.uk (ICG Campbell, Engineering Mathematics) Date: Mon, 27 Nov 2006 13:08:40 -0000 Subject: Connectionists: PhD studentship and other positions available Message-ID: <9789626.1164632920@ems-iggs.enm.bris.ac.uk> PhD studentship and other positions available. Computational Intelligence Group, Bristol University We have a PhD studenthip available in the area of machine learning, bioinformatics and cancer informatics. For details about the research area, stipend and application process see: http://www.jobs.ac.uk/jobfiles/VA276.html The closing date is: *** 3rd January 2007 ***. Two other positions are currently being advertised: 1. A 12 month visitor position (machine learning and bioinformatics). Since funding is a residual from an EU grant, for the support of younger researchers, applicants should be within 10 years of graduating with a PhD. Contact: Dr. Colin Campbell (c.campbell at bris.ac.uk) 2. A 3 year EPSRC supported postdoctoral position. Details are available at: http://www.jobs.ac.uk/jobfiles/JK801.html Note that the closing date for the last position is soon: *** 30th November 2006 *** Colin Campbell Bristol University c.campbell at bris.ac.uk From py at csl.sony.fr Tue Nov 28 10:02:24 2006 From: py at csl.sony.fr (Pierre-Yves Oudeyer) Date: Tue, 28 Nov 2006 16:02:24 +0100 Subject: Connectionists: [book] Self-Organization in the Evolution of Speech Message-ID: <456C4F80.3000305@csl.sony.fr> Dear colleagues, I am pleased to announce you the publication of my book : Oudeyer, P-Y. (2006) Self-Organization in the Evolution of Speech , Studies in the Evolution of Language, Oxford University Press. (Translation by James R. Hurford). Keywords: self-organization, cultural and biological evolution, phonetics, sensori-motor coupling, neural networks, agent-based modeling This book studies the interactions between self-organization and natural selection in the origins of combinatorial speech sounds. In particular, it aims to show how concepts coming from complex systems sciences and how computational modeling tools involving neural networks and agents can help formulate new theories about the origins of culturally shared speech codes. It also includes detailed discussions about the epistemological foundations of computational modeling in human sciences. More information, including a sample chapter, is available on the web page: http://www.csl.sony.fr/~py/book.htm Best regards, Pierre-Yves Oudeyer Sony CSL Paris http://www.csl.sony.fr/~py From Dave_Touretzky at cs.cmu.edu Tue Nov 28 11:15:57 2006 From: Dave_Touretzky at cs.cmu.edu (Dave_Touretzky@cs.cmu.edu) Date: Tue, 28 Nov 2006 11:15:57 -0500 Subject: Connectionists: new Ph.D. program in Neural Computation Message-ID: <32088.1164730557@ammon.boltz.cs.cmu.edu> New Graduate Program in Neural Computation at Carnegie Mellon University and the University of Pittsburgh In recognition of the increased demand for computationally-oriented researchers, Carnegie Mellon University, in collaboration with the University of Pittsburgh, has begun a Ph.D. program in computational neuroscience. As neuroscientists have applied new technologies to acquire and analyze large data sets, and have developed new models for understanding increasingly complicated neurobiological systems, quantitative methods have become centrally important to their effort. The new program takes advantage of the unusually large and highly collaborative group of faculty and students in neuroscience in the Pittsburgh community. Details about program curriculum, training faculty, and contact information are available at: http://www.cnbc.cmu.edu/GradTrain/pnc_index.shtml The deadline for applications is February 1, 2007. From l.wiskott at biologie.hu-berlin.de Thu Nov 30 09:41:47 2006 From: l.wiskott at biologie.hu-berlin.de (Laurenz Wiskott) Date: Thu, 30 Nov 2006 15:41:47 +0100 Subject: Connectionists: Open Position for a PhD-Student in the Berlin NeuroImaging Center Message-ID: <17774.60843.754350.379426@huxley.biologie.hu-berlin.de> (sent in behalf of Dr. Stephan A. Brandt) ________________________________________________________________________ Open Position for a PhD-Student in the Berlin NeuroImaging Center http://www.berlin-neuroimaging-center.de/open_positions ______________________________________________________________________ Institute: Department of Neurology, Charit,Ai(B Charit,Ai(Bplatz 1 D-10117 Berlin, Germany The Berlin NeuroImaging Center (BNIC) is a young and dynamic lab that implements interdisciplinary innovative research pertinent to various themes of neuroscience. Research group: The position is directly related to the project $B!H(Badaptive attention mechanisms in conflict processing$B!I(B. The position is available in the Vision and Motor Systems Research Group led by PD Dr. Stephan A. Brandt and is funded by the Deutsche Forschungsgemeinschaft (DFG) in collaboration with the Institute of Psychology of the Humboldt University, the Freie University of Berlin and the Max Planck Institute for Human Development in the DFG funded Forschergruppe $B!H(Bconflicts as signals in cognitive systems$B!I(B. http://www.berlin-neuroimagingenter.de/groups/vision Research topics: The goal of this project is to implement and investigate dynamic causal models (DCM) of brain areas involved in attentional mechanisms during conflict processing. The model will be developed in collaboration with the Institute for Theoretical Biology and Bernstein Center for Computational Neuroscience Berlin (Dr. Laurenz Wiskott & Prof. Dr. John-Dylan Haynes). http://www.bccn-berlin.de/ Teaching: None. Time: The position will be available as of December 2006. The starting date is negotiable. The appointment will be for 1 + 2 years. Requirements: Candidates should provide proof of education in physics, mathematics, computer science, electrical engineering or other related field. Strong mathematical and programming skills as well as the ability to communicate and work well in a team are considered mandatory. Candidates with the above named prerequisites who have familiar with dynamic causal modelling are also encouraged to apply. Salary: Salary will be ,A=(B or ,A>(B BAT IIa depending on qualifications, experience, age and family status. BAT is the regular salary scale for public employees in Germany. Inquiries: Informal inquiries can be addressed to PD Dr. Stephan A. Brandt stephan.brandt at charite.de Application: Formal applications, CV and two letters of recommendation should be sent to PD Dr. Stephan A. Brandt at the address given above. Please send only copies and not original documents, since the applications will not be returned. You can also send applications via email, but please ensure that they are complete and in a convenient format. Handicapped applicants with corresponding qualifications will be considered preferentially. To increase the proportion of female scientists, applications of qualified females are especially welcome. Deadline: None. Application will be accepted until the position is filled, as will be indicated on the web-page http://www.berlin-neuroimaging-center.de/open_positions. ========================================================================== From maass at igi.tugraz.at Wed Nov 29 03:37:28 2006 From: maass at igi.tugraz.at (Wolfgang Maass) Date: Wed, 29 Nov 2006 09:37:28 +0100 Subject: Connectionists: Program of Workshop on ESNs and LSMs Message-ID: <456D46C8.2040708@igi.tugraz.at> The program of the NIPS Workshop on Echo State Networks and Liquid State Machines on Dec. 9 at Whistler, Ca, is now posted on http://www.esn-lsm.tugraz.at/index.php/Main_Page This is simultaneously a workshop of the European PASCAL Network http://www.pascal-network.org/ -Wolfgang Maass -- Prof. Dr. Wolfgang Maass Institut fuer Grundlagen der Informationsverarbeitung Technische Universitaet Graz Inffeldgasse 16b , A-8010 Graz, Austria Tel.: ++43/316/873-5811 Fax ++43/316/873-5805 http://www.igi.tugraz.at/maass/Welcome.html From sham at gatsby.ucl.ac.uk Wed Nov 29 11:24:13 2006 From: sham at gatsby.ucl.ac.uk (Sham Kakade) Date: Wed, 29 Nov 2006 16:24:13 +0000 (GMT) Subject: Connectionists: TTI-Chicago is admitting PhD Students Message-ID: TTI-Chicago is a Ph.D. granting computer science institute located on the University of Chicago campus emphasizing machine learning, theory (algorithms and complexity), and programming languages. The Ph.D. program is small with more than one faculty per student. Although TTI-Chicago is an independent degree granting institution, TTI-Chicago students have full access to University of Chicago courses, faculty, library facilities and other amenities. TTI-Chicago is currently welcoming student applications for admission in September of 2007. Successful applicants will receive full tuition and a living stipend. Please ask your machine learning, theory, or programming language professors about TTI-Chicago. TTI-C's web site can be found at: http://www.tti-c.org Application instructions can be found at http://www.tti-c.org/apps/student/app_instructions_phd.pdf and an electronic application form (with no application fee) can be found at http://www.tti-c.org/apps/student/student.htm From risc at idf.ext.jussieu.fr Thu Nov 30 07:36:06 2006 From: risc at idf.ext.jussieu.fr (RISC) Date: Thu, 30 Nov 2006 13:36:06 +0100 Subject: Connectionists: Research scientist: Invitation for applications from researchers Message-ID: <669ab209a368d7981b3ed4cac63151dc@idf.ext.jussieu.fr> De: Michel Denis Research scientist: Invitation for applications from researchers in the field of "Virtual Reality and Cognition" LIMSI, a multidisciplinary research unit within the French National Center for Scientific Research (CNRS) located on the Orsay campus of the University of Paris-Sud (France), is currently developing research on "Virtual Reality and Cognition". The development of an immersive Virtual Reality (VR) system, with funding from the CNRS and the Ile-de-France Region, is part of a broader project in which the cognitive sciences will play a major role. LIMSI has embarked on a virtual and augmented reality project that will involve both designing multimodal immersive interaction methods and using these technologies in various fields of application. LIMSI also intends to develop the potential applications of VR in setting up scientific interactions between engineering and the cognitive sciences. This project has two main purposes: (a) to ensure that the development of the VR interfaces at LIMSI benefits from expertise in cognitive ergonomics; (b) to ensure that in the specific areas studied at LIMSI, VR can be used to investigate cognitive functions in people interacting with these systems. LIMSI already includes specialists in cognitive psychology, and this will facilitate this further line of development. The objective of LIMSI is to invest new types of competence in this project so that it can successfully carry out the mission with which it has been entrusted by the CNRS. The suitable candidate for this development project will be a specialist in psychology and/or cognitive ergonomics, or possibly the cognitive neurosciences, and who intends to submit an application during the next round of CNRS recruitments (December 2006/January 2007). Applications will be welcome from scientists embarking on a career in research, as well as experienced researchers. LIMSI will welcome preliminary informal enquiries from potential candidates. If you are interested please contact LIMSI as soon as possible. Enquiries and preliminary applications should be addressed to one of the following: - Patrick Le Qu?r?, Director of LIMSI (plq at limsi.fr). Tel.: +33 1 69 85 80 85. - Philippe Tarroux, Deputy Director (tarroux at limsi.fr). Tel.: +33 1 69 85 80 86. ------- Message redirig? par le relais d'information sur les sciences de la cognition (RISC) sans virus http://www.risc.cnrs.fr From n.yousif at imperial.ac.uk Thu Nov 30 08:25:57 2006 From: n.yousif at imperial.ac.uk (Yousif, Nada) Date: Thu, 30 Nov 2006 13:25:57 -0000 Subject: Connectionists: DBS symposium announcement Message-ID: <08384600730B8A43A157D18D20A9E4660FCC04@icex5.ic.ac.uk> Apologies if received more than once. ************************************************************************ ********************************************** ************************************************************************ ********************************************** FIRST ANNOUNCEMENT ************************************************************************ ********************************************** ************************************************************************ ********************************************** Theory and Neuroinformatics in Research Related to Deep Brain Stimulation 15-16 March 2007 Imperial College London Deep Brain Stimulation (DBS) is an increasingly used therapeutic procedure which is used to treat a series of neurological and psychiatric related disorders. DBS modulates brain activity via the implanted depth electrodes by conducting electrical pulses. However, the success of the procedure is not only dependent on the precision of electrode implantation, but the parameters of the electric pulses also need to be tuned for each patient. We are organising an international symposium where researchers from different backgrounds (mathematics, computer science, neurobiology, neurological medicine) will be able to meet in person, identify the direction of future research, and discuss possible collaborative projects in the DBS field. For further information please see the conference website: http://www1.imperial.ac.uk/medicine/about/divisions/neuro/news/informati cs07/