From t.heskes at science.ru.nl Tue Nov 1 10:00:58 2005 From: t.heskes at science.ru.nl (Tom Heskes) Date: Tue, 01 Nov 2005 16:00:58 +0100 Subject: Connectionists: Neurocomputing volume 69 Message-ID: <4367832A.3030409@science.ru.nl> Neurocomputing Volume 69 (November 2005) ------- SPECIAL PAPERS (Neural Networks in Signal Processing edited by Marc M. van Hulle and Jan Larsen) Neural Networks in Signal Processing (editorial) Marc M. Van Hulle and Jan Larsen Loss functions to combine learning and decision in multiclass problems Alicia Guerrero-Curieses, Roc?o Alaiz-Rodr?guez and Jes?s Cid-Sueiro Discriminative clustering Samuel Kaski, Janne Sinkkonen and Arto Klami Support Vector Regression for the simultaneous learning of a multivariate function and its derivatives Marcelino L?zaro, Ignacio Santamar?a, Fernando P?rez-Cruz and Antonio Art?s-Rodr?guez Algebraic geometry and stochastic complexity of hidden Markov models Keisuke Yamazaki and Sumio Watanabe Novel approximations for inference in nonlinear dynamical systems using expectation propagation Alexander Ypma and Tom Heskes The differogram: Non-parametric noise variance estimation and its use for model selection Kristiaan Pelckmans, Jos De Brabanter, Johan A.K. Suykens and Bart De Moor Variational inference for Student-t models: Robust Bayesian interpolation and generalised component analysis Michael E. Tipping and Neil D. Lawrence Computationally efficient sequential learning algorithms for direct link resource-allocating networks Vijanth S. Asirvadam, Se?n F. McLoone and George W. Irwin Fast error whitening algorithms for system identification and control with noisy data Yadunandana N. Rao, Deniz Erdogmus, Geetha Y. Rao and Jose C. Principe Bidirectional associative memory with learning capability using simultaneous perturbation Yutaka Maeda and Masatoshi Wakamura A general solution to blind inverse problems for sparse input signals ? David Luengo, Ignacio Santamar?a and Luis Vielva ------- LETTERS Class-information-incorporated principal component analysis Songcan Chen and Tingkai Sun (2D)^2 PCA: Two-directional two-dimensional PCA for efficient face representation and recognition Daoqiang Zhang and Zhi-Hua Zhou Chaos and transient chaos in simple Hopfield neural networks Xiao-Song Yang and Quan Yuan Multihashing, human authentication featuring biometrics data and tokenized random number: A case study FVC2004 Dario Maio and Loris Nanni View-independent person identification from human gait Zonghua Zhang and Nikolaus F Troje Hyperplanes for predicting protein?protein interactions Loris Nanni A fixed-point nonlinear PCA algorithm for blind source separation ? Xiaolong Zhu, Jimin Ye and Xianda Zhang Using batch algorithm for kernel blind source separation Zhan-Li Sun, De-Shuang Huang, Chun-Hou Zheng and Li Shang ------- JOURNAL SITE: http://www.elsevier.com/locate/neucom SCIENCE DIRECT: http://www.sciencedirect.com/science/issue/5660-2005-999309998-609282 From Luc.Berthouze at aist.go.jp Tue Nov 1 20:11:54 2005 From: Luc.Berthouze at aist.go.jp (Luc Berthouze) Date: Wed, 2 Nov 2005 10:11:54 +0900 Subject: Connectionists: Call for papers - Workshop on Motor development (Bristol, UK, 3-6 April 2006) Message-ID: Call for Papers: Motor Development http://www.neurosci.aist.go.jp/~berthouz/MotDev.html April 5th-6th 2006 A symposium part of the AISB 2006 conference University of Bristol, Bristol, England Call for Papers The motor activity of an organism is one of its primary means of interacting with, and operating on, its environment. As such, its development is key to its cognitive development and, indeed, developmental psychology has shown both processes to be tightly coupled. In embodied robotics and cognitive modeling, however, these processes have been mostly treated in isolation with systems either evolving higher cognitive processes, or acquiring new motor skills. The motivation of this symposium is that understanding, and simulating, the mechanisms underlying motor development is necessary to implement an ecologically-balanced development of the system. This interdisciplinary symposium aims to bring together researchers from neuroscience, developmental psychology, computer science and robotics to examine the latest advances in the area, and delineate new strategies. Submissions We invite abstracts on any subject within the area of motor development. Areas of interest include but are not limited to: - Motor development in animals and humans: studies, models and theories - Motor development in robots: issues, models, experiments or simulations - Evolutionary developmental biology and motor development - Critical periods of motor development - Pathologies of motor development - Interplay between motor and cognitive development - Degree of freedom problem - U-shape development - Emergence of new skills - Role of caregiver in skill acquisition Accepted abstracts will be presented orally on the day and appear in the published workshop proceedings. Extended abstracts of between 1 and 2 pages should be submitted as PDF files to Luc.Berthouze at aist.go.jp by 13th January 2006. Selected papers will be invited for publication in a special issue of a journal. Further details will be available soon. Organiser Luc Berthouze, AIST Neuroscience Research Institute, Japan Programme Committee (confirmed members) Luc Berthouze, AIST Neuroscience Research Institute, Japan Yiannis Demiris, Imperial College, UK Eugene Goldfield, Children's Hospital Boston, USA Giorgio Metta, Genoa University, Italy Claes Van Hofsten, Uppsala University, Sweden Important dates Submissions of papers by : 13 Jan 06 Notification of decision: 01 Feb 06 Camera ready copies by: 20 Feb 06 Up-to-date information at: http://www.neurosci.aist.go.jp/~berthouz/ MotDev.html ------------------- Dr. Luc Berthouze, Senior Research Scientist, Neuroscience Research Institute (AIST 2) Umezono 1-1-1, Tsukuba 305-8568, Japan Tel: +81-298-61-5369 Fax: +81-298-61-5841 Email: Luc.Berthouze at aist.go.jp From chengsoon.ong at tuebingen.mpg.de Wed Nov 2 05:21:55 2005 From: chengsoon.ong at tuebingen.mpg.de (Cheng Soon Ong) Date: Wed, 2 Nov 2005 11:21:55 +0100 Subject: Connectionists: Machine Learning Tools Satellite Workshop (4 Dec 2005) Message-ID: <172FB4A4-022B-4D32-99AC-D162C49D1B22@tuebingen.mpg.de> Machine Learning Tools Satellite Workshop A satellite workshop on machine learning tools, collocated with NIPS, held in Vancouver(B.C.) on December 4, 2005. (website) http://lineal.developer.nicta.com.au/support/workshops/ (mirror) http://www.fml.mpg.de/MLPython Workshop Description The aim of this meeting is to discuss the requirements and design of an open source machine learning toolbox. Recently, there has been a collaborative effort among NICTA Canberra, MPI Tuebingen, Fraunhofer Berlin, Fraunhofer Darmstadt, and INSA de Rouen to develop such a toolkit codenamed LINEAL and ELEFANT. This set of tools uses Python as an interface language and currently uses PETSc as a numerical back end. The workshop is for the collaborators to investigate the different strategies for developing the toolbox. We would appreciate an email to SVN Vishwanathan at (SVN -dot- Vishwanathan -at- nicta.com.au) if you are interested in attending the meeting. From mdorigo at ulb.ac.be Wed Nov 2 14:23:47 2005 From: mdorigo at ulb.ac.be (Marco DORIGO) Date: Wed, 2 Nov 2005 20:23:47 +0100 Subject: Connectionists: ANTS 2006 Call for Papers Message-ID: *** Apologies if you have received this CFP more than once *** ANTS 2006 Fifth International Workshop on Ant Colony Optimization and Swarm Intelligence September 4-7, 2006. Brussels, Belgium Call for papers prepared on October 31, 2005 Short version ANTS 2006 solicits contributions dealing with any aspect of swarm intelligence including ant colony optimization, particle swarm optimization, and swarm robotics. More details and up-to-date information at http://iridia.ulb.ac.be/ants2006 Workshop proceedings will be published by Springer in the LNCS series. Important Dates =============== Title and abstract deadline Mar 12, 2006 Submission deadline Mar 19, 2006 Notification of acceptance May 21, 2006 Camera ready copy June 4, 2006 ANTS 2006 Workshop Committee ============================ General Chairs Marco Dorigo, IRIDIA, ULB, Brussels, Belgium Luca M. Gambardella, IDSIA, USI-SUPSI, Manno, Switzerland Technical Program Chairs Alcherio Martinoli, EPFL, Lausanne, Switzerland Riccardo Poli, University of Essex, UK Thomas Stuetzle, IRIDIA, ULB, Brussels, Belgium Publication Chair Mauro Birattari, IRIDIA, ULB, Brussels, Belgium Sponsors ======== AntOptima http://www.antoptima.com Comp2Sys, Marie Curie Early Stage Training Site http://iridia.ulb.ac.be/comp2sys French Community of Belgium (through the research project ANTS) http://www.cfwb.be IEEE Computational Intelligence Society (as a technical co-sponsor) http://www.ieee-cis.org -- ========================================================================== Marco Dorigo, Ph.D. mdorigo@(no.spam)ulb.ac.be Directeur de Recherches du FNRS http://iridia.ulb.ac.be/~mdorigo/ IRIDIA CP 194/6 Universite' Libre de Bruxelles Tel +32 (0)2 6503169 Avenue Franklin Roosevelt 50 GSM +32 478 301233 1050 Bruxelles Fax +32 (0)2 6502715 Belgium Sec +32 (0)2 6502729 ========================================================================== From anderson at CS.ColoState.EDU Thu Nov 3 14:41:43 2005 From: anderson at CS.ColoState.EDU (Chuck Anderson) Date: Thu, 03 Nov 2005 12:41:43 -0700 Subject: Connectionists: tenure-track faculty position in Dept. of Computer Science at Colorado State University Message-ID: <436A67F7.9060300@cs.colostate.edu> Tenure-Track Faculty Position Department of Computer Science Colorado State University Position Description RESPONSIBILITIES The candidate is expected to teach undergraduate and graduate courses in computer science, advise undergraduate and graduate students, perform research, and make a service contribution to the department, the university, and professional community. QUALIFICATIONS A successful candidate must: - Have earned a doctorate in computer science, computer engineering, or a related field. - Have the potential for excellence in research and teaching. - Have a research perspective that is consistent with the department's emphasis on collaborative and interdisciplinary research. - Have a research specialty that is consistent with the department's needs and interests. Candidates for appointments above the level of assistant professor must demonstrate a strong connection to ongoing department research. EMPLOYMENT CONDITIONS This nine-month, full-time position will carry a salary commensurate with qualifications. This appointment will be preferably made at the level of assistant professor. The department has 18 tenure-track faculty, 150 M.S. and Ph.D. students, and 275 undergraduate majors. Areas of research emphasis include artificial intelligence (bioinformatics, computer vision, evolutionary computation, machine learning, planning), software engineering (formal methods, program comprehension, reliability, testing), networks, parallel and distributed computing (embedded systems, reconfigurable architectures), and security. Colorado State University with an enrollment of 25,000 students is located in Fort Collins, Colorado, an attractive community of over 134,000 people, at the base of the Front Range of the Rocky Mountains, 65 miles north of Denver. The northern Front Range offers a wide range of outdoor recreational activities. More information about the department, its research programs, and applying for this position can be obtained from the department's home page at http://www.cs.colostate.edu From malchiodi at dsi.unimi.it Thu Nov 3 10:39:26 2005 From: malchiodi at dsi.unimi.it (Dario Malchiodi) Date: Thu, 3 Nov 2005 16:39:26 +0100 Subject: Connectionists: ICHSA workshop: new paradigms for hybrid learning systems Message-ID: <03D43245-4C80-11DA-BE0E-0003939B3D3E@dsi.unimi.it> ????????? Sorry, if you received this message more than once. ???? Feel free to distribute it to those who might be interested. ################################################################ CALL FOR CONTRIBUTIONS WORKSHOP ON NEW PARADIGMS FOR HYBRID LEARNING SYSTEMS http://laren.dsi.unimi.it/new_paradigm within the International Conference on Hybrid Systems and Applications (ICHSA 2006) May 24th 2006, The University of Louisiana, Lafayette, LA, USA http://cos.fit.edu/math/ichsa/ Submission deadline: February 15th 2006 ################################################################ Organizers: ------------ * Bruno Apolloni, University of Milano http://laren.dsi.unimi.it/apolloni * Zong Sha, Chinese Institute of electronics,Beijing, China zsha at public.bat.net.cn, z.sha at ieee.org * Dario Malchiodi, University of Milano http://homes.dsi.unimi.it/~malchiod Besides the common dichotomy between subsymbolic learning systems such as neural networks and symbolic systems such as decision trees, and their various forms of hybridization, new algorithms are raising for learning, sharing features of both symbolic and subsymbolic paradigms. Of classification algorithms like SVM or feature extraction algorithms like ICA you cannot say to be completely symbolic since the kernels/non gaussianity measures selection must be drawn by data in a non direct way -- guessed in any way -- while the goal they optimize is an explicit function of the parameters they aim to learn. In very broad terms the object of this special session is to gather various approaches to learning, where the distinction between what comes from axiomatic theories and what is left to the ability of the learner and his heuristics is untenable. Rather we may distinguish between different strategies with which the users organize past data in order to face their continuation. Contributions: -------------- As it is, the scope of this special session is open to the contribution of researchers in many fields, ranging from statistics to granular computing, neural networks, evolutionary computation, computational learning and so on. A definite preference is for non conventional approaches, provided a clear rationale and either formal proofs or stringent numerical results are supplied. We expect extended abstracts six to eight pages long without special format. Authors of the accepted contributions will be invited to submit a paper in the format requested by the conference proceedings? editor. Please submit extended abstracts to new_paradigms at dsi.unimi.it within February 15th 2006. Important dates: ------------------- February 15th 2006 Submission deadline March 15th 2006 Notification of acceptance April 15th 2006 Camera ready papers deadline May 22nd 2006 Conference From biehl at physik.uni-wuerzburg.de Fri Nov 4 03:16:58 2005 From: biehl at physik.uni-wuerzburg.de (Michael Biehl) Date: Fri, 4 Nov 2005 09:16:58 +0100 (CET) Subject: Connectionists: PhD position available, Groningen/NL Message-ID: PhD position available A Ph.D. fellowship for non-Dutch citizens is available in field of Machine Learning at the University of Groningen, Department of Computing Science. The fellowship is for a period of four years and amounts to (currently) 1340 Euros (tax free) per month. The aim of the project is two-fold: (a) to gain a better theoretical understanding of prototype based learning in systems with many degrees of freedom (b) the design and application of optimized or novel training algorithms in the context of real world problems (e.g. medical images or data). The focus will be on prototype-based techniques of unsupervised Vector Quantization, Neural Gas algorithms and Self-organizing Maps, as well as on supervised algorithms for Learning Vector Quantization (LVQ). Candidates should have a strong interest in theory and mathematics. A background in theoretical physics (statistical mechanics) would be a big plus, but is not required. Before applying, please check out publications and try to get an impression of our on-going research. Brief descriptions of our projects and preprints are available from http://www.cs.rug.nl/~biehl Please feel free to contact me (see below) if you have further questions about the post and the project. Interested candidates should send their application (through e-mail in pdf-format or hardcopies by mail) to Dr. Michael Biehl University of Groningen Dept. of Mathematics and Computing Science Blauwborgje 3 9747 AC Groningen The Netherlands m.biehl at rug.nl From gcc at cmp.uea.ac.uk Fri Nov 4 09:06:54 2005 From: gcc at cmp.uea.ac.uk (gcc@cmp.uea.ac.uk) Date: Fri, 4 Nov 2005 09:06:54 GB Subject: Connectionists: Predictive Uncertainty Competition for IJCNN-2006 Message-ID: <200511040906.jA496sGB026955@s5.cmp.uea.ac.uk> Dear Connectionists, there will be a second competition at IJCNN-2006 (http://www.wcci2006.org/) involving "predictive uncertainty in environmental modelling", with a special session devoted to papers describing the best methods. The aim is to create regression models that provide an estimate of the uncertainty of their predictions, e.g. error-bars, with models being evaluated according to the negative log-likelihood on the test data. This is particularly important for environmental problems, which are typically rather noise, often have non-Gaussian noise processes and the uncertainty in predictions is useful in estimating the impacts of e.g. increased rainfall on flooding. The competition has the same format as the Pascal Predictive Uncertainty Challenge (http://predict.kyb.tuebingen.mpg.de/), so those competing in the regression section of that exercise will have models they can deploy immediately. The competition web site is at http://theoval.cmp.uea.ac.uk/~gcc/competition/ Please do not hesitate to contact me if you have any questions or comments. best regards Gavin Cawley School of Computing Sciences University of East Anglia Norwich NR4 7TJ, U.K. From doya at irp.oist.jp Mon Nov 7 13:37:42 2005 From: doya at irp.oist.jp (Kenji Doya) Date: Tue, 8 Nov 2005 03:37:42 +0900 Subject: Connectionists: Postdoctoral Fellow and Investigator Positions, OIST In-Reply-To: <5.1.1.6.0.20051005153429.031869f0@pop.isc.cnrs.fr> References: <5.1.1.6.0.20051005153429.031869f0@pop.isc.cnrs.fr> Message-ID: <46e32594f98e94a7f9fb00aebfc2d66c@irp.oist.jp> We are building a new graduate institute in Okinawa, a southern island known for its beautiful ocean and rich traditional culture. We are seeking postdocs and junior faculty who are interested in interdisciplinary research and starting up a totally new university. My group is working on reinforcement learning and Bayesian algorithms, rodent experiments on decision and neuromodulation, and 'cyber rodent' experiments on learning and evolution. If you are interested in this opportunity, please apply by the following. Best wishes, Kenji Doya **** Okinawa Institute of Science and Technology Postdoctoral Fellows & Investigators The Okinawa Institute of Science and Technology, a new International Graduate University in Okinawa, has established a Research Initiative with a number of Research Groups. We are seeking postdoctoral fellows in the areas of Molecular Cell Biology, Molecular Cellular Neuroscience, Computational and Experimental Neurobiology to join the following groups: Neural Computation: Dr. K. Doya Experimental studies of Learning and Memory: Dr. S. Endo G0-cell: Yeast Cell Cycle: Dr. M. Yanagida Molecular Neuroscience: Dr. S. Brenner, Dr. I. Maruyama, Dr. T. Naito In addition, we have several openings for investigators with independent research projects in these areas. Applicants for Postdoctoral fellowships should send their CV's, a description of their area of research interest, and the names of two references. Applicants for Investigator positions should, in addition, provide a brief outline (1000 words) of the research that they would like to carry out and the resources required for it. Successful candidates will be invited to present more detailed proposals. The research groups are at present housed in well-equipped temporary laboratories and a major construction program for the new University is underway. Post doctoral fellows will be appointed for two years in the first instance with the possibility of renewal. Investigators will receive renewable 5-year appointment as well as the resources required for their research. Further details about the Institute can be viewed on our website (www.oist.jp) which also has the last research report. Please send your resumes by e-mail, fax, or postal mail to: Human Resources Department Okinawa Institute of Science and Technology 12-22 Suzaki, Uruma-shi, Okinawa 904-2234, Japan. e-mail: careers at irp.oist.jp fax: +81-98-934-844 ---- Kenji Doya Initial Research Project, Okinawa Institute of Science and Technology 12-22 Suzaki, Uruma, Okinawa 904-2234, Japan Phone:+81-98-921-3843; Fax:+81-98-921-3873 http://www.irp.oist.jp/nc From girolami at dcs.gla.ac.uk Tue Nov 8 09:45:03 2005 From: girolami at dcs.gla.ac.uk (Mark Girolami) Date: Tue, 8 Nov 2005 14:45:03 -0000 Subject: Connectionists: PhD Studentship in Machine Learning Available Message-ID: A fully funded, industry sponsored, three year PhD studentship (fees & stipend) is now available, with immediate start, within the Department of Computing Science at the University of Glasgow which is internationally recognised for its research and was rated 5 in the 2001 Research Assessment Exercise. The proposed PhD will investigate how advanced Machine Learning and Statistical Pattern Recognition methods may assist in the self-service environment, particularly using diverse heterogeneous data to make optimal decisions. Recent theoretical and applied work in Machine Learning and the application of Bayesian Inference in Machine Learning (particularly involving kernel methods such as Support Vector Machines, Gaussian Processes and Relevance Vector Machines) has attempted to address the problem of combining heterogeneous data to provide an improved prediction or classification decision. It is anticipated that the student will investigate the role that Machine Learning and Statistical Pattern Recognition can play in providing possible solutions to this particular problem. This is an outstanding opportunity to work on a research project with direct links to industrial issues and work with an international IT company. Appropriate academic backgrounds include Engineering, Physics, Mathematics, Statistics and Computing Science. Interested applicants should contact Dr Mark Girolami (girolami at dcs.gla.ac.uk) in the first instance for further information regarding this studentship. Mark Girolami PhD Bioinformatics Research Centre Department of Computing Science A416, Fourth Floor, Davidson Building University of Glasgow Glasgow G12 8QQ Scotland UK Tel : +44 (0)141 330 8628 Fax: +44 (0)141 330 8627 email : girolami at dcs.gla.ac.uk http://www.dcs.gla.ac.uk/~girolami/ From erik at tnb.ua.ac.be Thu Nov 10 08:55:43 2005 From: erik at tnb.ua.ac.be (Erik De Schutter) Date: Thu, 10 Nov 2005 14:55:43 +0100 Subject: Connectionists: Neuro-IT Cerebellar Modeling Workshop Fellowships Message-ID: <28B642D4-874F-4872-8BA5-C2E640A435C7@tnb.ua.ac.be> A limited number of 200 euro student fellowships to cover accommodation costs will be available for the two-day cerebellar modeling workshop at the University of Antwerp, Belgium on December 5-6, 2005. Interested master or PhD students coming from outside of Belgium (maximum one for a research group) can apply for a fellowship when registering for the workshop. Invited speakers include N. Brunel (Paris, France, G. Chauvet (Angers, France), E. d'Angelo (Pavia, Italy), C. Darlot (Paris, France), P. Dean (Sheffield, UK), E. De Schutter (Antwerp, Belgium), C. De Zeeuw (Rotterdam, Netherlands), M. Hausser (London, UK), R. Maex (Antwerp, Belgium), A. Silver (London, UK), P. Verschure (Zurich, Switzerland), Y. Yarom (Jerusalem, Israel). Full program and (free) registration can be found at http:// www.neuroinf.org/workshop/neuroit05/ From dayan at gatsby.ucl.ac.uk Fri Nov 4 04:25:57 2005 From: dayan at gatsby.ucl.ac.uk (Peter Dayan) Date: Fri, 4 Nov 2005 09:25:57 +0000 Subject: Connectionists: Gatsby faculty recruitment Message-ID: <20051104092557.GA21636@flies.gatsby.ucl.ac.uk> The Gatsby Computational Neuroscience Unit at UCL is looking to recruit one or more faculty at senior and/or junior levels in machine learning, statistics or control theory. We are especially interested in candidates whose work in these fields integrates well with the Unit's focus on inference and learning in the brain, and with the wider research environment at UCL. The Computer Science Department at UCL is in conjunction recruiting for a senior faculty position to act as a Director for a proposed UCL Centre for Computational Statistics and Machine Learning, reflecting the substantial cross-campus links in this area. 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 (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 2006. Unless otherwise requested applicants will also be considered by the Computer Science Department. Appointment at a senior level is subject to the normal senior appointments process at UCL. For further information, please see www.gatsby.ucl.ac.uk; for informal enquiries, please contact Peter Dayan at dayan 'at' gatsby.ucl.ac.uk Information about the Department of Computer Science and their recruitment is at http://www.cs.ucl.ac.uk and http://www.cs.ucl.ac.uk/vacancies From choe at cs.tamu.edu Wed Nov 9 01:43:01 2005 From: choe at cs.tamu.edu (Yoonsuck Choe) Date: Wed, 9 Nov 2005 00:43:01 -0600 (CST) Subject: Connectionists: CFP: NIP-LR Special Issue on Bio-Inspired Models and Hardware Message-ID: [We apologize in advance in case you get this annoucement from multiple sources. Please redistribute as you see fit. Thanks!] /////////////////////////////////////////////////////////////////////// /// Call for Papers for a Special Issue of /// /// Neural Information Processing-Letters and Reviews /// /// on Bio-Inspired Models and Hardware /// /////////////////////////////////////////////////////////////////////// As announced earlier at the International Workshop on Biologically Inspired Models and Hardware (BIMH2005, http://www.bimh2005.org), a post-conference workshop at IJCNN2005 (Montreal, Canada), Neural Information Processing-Letters and Reviews (NIP-LR) is preparing a special issue on biologically-inspired models and hardware for human-like intelligent functions. Although artificial neural networks are inspired by information processing mechanisms in the brain, there still exists a big gap between biological neural networks and their artificial counterpart. To have more intelligent characteristics incorporated into artificial neural systems, we need to rely more on biologically inspired models and hardware. In this special issue of NIP-LR, we invite contributions on biologically plausible hardware systems and models with more human-like intelligent characteristics that can help deal with real-world problems. Relevant topics for this special issue include, but are not limited to: o Models of the auditory pathway o Models of the visual pathway o Models of cognition, learning, and inference o Models of attention, emotion, and consciousness o Models of autonomous behavior o Hardware implementation of bio-inspired models o Engineering applications of bio-inspired models For more information on the special issue for NIP-LR, please visit: http://www.nip-lr.info Submission instruction: Papers should be emailed as a PDF attachment to the guest editors Yoonsuck Choe (choe at tamu.edu) and Minho Lee (mholee at knu.ac.kr). Important dates: December 15, 2005: Submission Deadline February 15, 2006: Deadline for the Reviews February 28, 2006: Notification of Acceptance/Rejection. March 2006: Publication, as a combined February-March Issue. Copyright: Authors will maintain all rights to their papers, and may subsequently publish extended versions of their papers in other journals. Yoonsuck Choe, Assistant Professor Minho Lee, Associate Professor Texas A&M University, USA Kyungpook National University, Korea choe at tamu.edu, 1-979-845-5466 mholee at knu.ac.kr, 82-53-950-6436 From Gunnar.Raetsch at tuebingen.mpg.de Thu Nov 10 09:51:04 2005 From: Gunnar.Raetsch at tuebingen.mpg.de (=?ISO-8859-1?Q?Gunnar_R=E4tsch?=) Date: Thu, 10 Nov 2005 15:51:04 +0100 Subject: Connectionists: =?iso-8859-1?q?2_Group_Leader_positions_at_the_Fr?= =?iso-8859-1?q?iedrich_Miescher_Laboratory_in_T=FCbingen_?= Message-ID: <072F5710-2438-443B-9411-2E6AE6DD1500@tuebingen.mpg.de> The Max Planck Society invites applications for 2 Independent Junior Group Leader positions at the Friedrich Miescher Laboratory in T?bingen, Germany The Friedrich Miescher Laboratory (FML) in T?bingen has openings for two Independent Junior Group Leaders (W2; equivalent to associate professor level without tenure). The FML is an institution of the Max Planck Society hosting four Independent Junior Research Groups, which work in different disciplines related to the broad spectrum of research represented in the Biomedical Section of the Max Planck Society. The groups share equipment and jointly manage the organization of the laboratory. These special conditions and the close interaction between the groups make for a very active and lively research atmosphere. For more information see http://www.fml.tuebingen.mpg.de. The FML is part of the Max Planck Campus in T?bingen (http://www.tuebingen.mpg.de), which also hosts the Max Planck Institutes for Developmental Biology and Biological Cybernetics. While there is no restriction on the research area, there is the expectation that the successful candidates will interact synergistically with other groups and departments on the campus. Current fields of research include cell biology, biochemistry and structural biology, developmental genetics, evolutionary biology, computational biology, as well as machine learning, neuroscience, and psychophysics. Moreover, the University of T?bingen is a highly active center for biomedical research and there are many opportunities for interaction. Funding includes one Postdoc position, one PhD scholarship and one Technical Assistant position, as well as running costs and a competitive startup package. The exact conditions will depend on the field of research and experience. The group leader position and funding is guaranteed for five years with the possibility of extension. The Max Planck Society is an equal opportunity employer and wishes to increase the share of women in areas in which they are underrepresented. Application requirements are detailed on http://www.snwg.mpg.de. The deadline for application is December 20, 2005. Further information can be obtained from Gunnar R?tsch http://www.fml.tuebingen.mpg.de/ raetsch Friedrich Miescher Laboratory Gunnar.Raetsch at tuebingen.mpg.de Max Planck Society Tel: (+49) 7071 601 820 Spemannstra?e 39, 72076 T?bingen, Germany Fax: (+49) 7071 601 455 From pascal.fua at epfl.ch Mon Nov 7 22:29:32 2005 From: pascal.fua at epfl.ch (Pascal Fua) Date: Tue, 08 Nov 2005 04:29:32 +0100 Subject: Connectionists: Open faculty positions at EPFL Message-ID: <43701B9C.7060706@epfl.ch> Hello, EPFL has open faculty positions in Computer Science and is looking for candidates with an interest in machine learning. See full text of the add below from the http://professeurs.epfl.ch/Jahia/site/professeurs/op/preview/pid/57801?matrix=1127201488194 web site. Would it be possible to post it on your site? Regards Pascal Faculty Positions in Computer Science The School of Computer and Communication Sciences at EPFL invites applications for faculty positions in computer science. We are primarily seeking candidates for tenure-track assistant professor positions, but suitably qualified candidates for senior positions will also be considered. Successful candidates will develop an independent and creative research program, participate in both undergraduate and graduate teaching, and supervise PhD students. Candidates from all areas of computer science will be considered, but preference will be given to candidates with interests in algorithms, graphics-related areas, machine learning, design methodologies for integrated systems, and foundations and applications of verification. Significant start-up resources and research infrastructure will be available. We offer internationally competitive salaries and benefits. To apply, please follow the application procedure at http://icrecruiting.epfl.ch. The following documents are requested in PDF format: curriculum vitae, including publication list, brief statements of research and teaching interests, names and addresses (including e-mail) of 3 references for junior positions, and 6 for senior positions. Screening will start on January 15, 2006. Further questions can be addressed to: Professor Willy Zwaenepoel Dean School of Computer and Communication Sciences EPFL CH-1015 Lausanne, Switzerland recruiting.ic at epfl.ch For additional information on EPFL, please consult http://www.epfl.ch EPFL is an equal opportunity employer. -- -------------------------------------------------------------------- Prof. P. Fua (Pascal.Fua at epfl.ch) Tel: 41/21-693-7519 FAX: 41/21-693-7520 Url: http://cvlab.epfl.ch/~fua/ -------------------------------------------------------------------- From moodylab at icsi.berkeley.edu Thu Nov 10 18:02:47 2005 From: moodylab at icsi.berkeley.edu (John Moody) Date: Thu, 10 Nov 2005 15:02:47 -0800 Subject: Connectionists: Program: Machine Learning in Finance Message-ID: <10b7069b0511101502m7dbafa16p7b937a025c6f7ba4@mail.gmail.com> MACHINE LEARNING IN FINANCE Westin Resort, Whistler, BC December 9, 2005 WORKSHOP PROGRAM: The program for Machine Learning in Finance is now available. For program, hotel and registration information, please see: http://www.icsi.berkeley.edu/~moody/MLFinance2005.htm WORKSHOP DESCRIPTION: Machine learning (ML) and related methods have produced some of the financial industry's most consistently profitable proprietary trading strategies during the past 20 years. With markets, trade execution and financial decision making becoming more automated and competitive, practitioners increasingly recognize the need for ML. This workshop brings together researchers from machine learning, academic finance and the financial industry to discuss problems in finance where ML may provide an edge. ML themes include reinforcement learning, optimization methods, recurrent and state space models, on-line algorithms, evolutionary computing, kernel methods, bayesian estimation, wavelets, neural nets, SVMs, boosting and multi-agent simulation. Financial topics include high frequency data, trading strategies, execution models, forecasting, volatility, extreme events, credit risk, portfolio management, yield curve estimation, option pricing, and selection of indicators, models and equilibria. From b.graham at cs.stir.ac.uk Fri Nov 11 03:53:25 2005 From: b.graham at cs.stir.ac.uk (b.graham@cs.stir.ac.uk) Date: Fri, 11 Nov 2005 08:53:25 -0000 (GMT) Subject: Connectionists: Postdoc in computational neuroscience Message-ID: <1055.213.78.119.123.1131699205.squirrel@www.cs.stir.ac.uk> Dear all, The following postdoc position in computational neuroscience is now available in my laboratory at the University of Stirling in Scotland. Bruce Graham ----------------------------------------------------------------- SITUATION VACANT DEPARTMENT OF COMPUTING SCIENCE AND MATHEMATICS UNIVERSITY OF STIRLING, SCOTLAND, U.K. RESEARCH ASSISTANT (?20,044 - ?30,002p.a.) Research Assistant post to work on a BBSRC funded project concerning ?Changes in information transmission at an auditory synapse in the binaural pathway during short-term synaptic modulation?. The information required for sound source localization is carried in the firing times of neurones in brain stem auditory nuclei. These neurones exhibit synaptic and cellular specializations that contribute to precisely timed electrical signalling. The project will investigate the information transmission characteristics of the glutamatergic calyx of Held synapse in the mammalian MNTB using a combination of mathematical modelling, computer simulation and physiological experiments. This post, to be held in the laboratory of Dr Bruce Graham at the University of Stirling, involves carrying out the modelling and computer simulation work. This will be based on data from physiological experiments being carried out by another RA funded by this BBSRC award, in the laboratory of Prof. Ian Forsythe at the University of Leicester. There are travel funds for research visits between the two laboratories. The overall objective is to determine whether multiple forms of short term synaptic modulation interact to alter, and perhaps optimise, information transmission through this pathway in response to behaviourally-relevant sound stimuli, tuning it to aid in sound source localization. This project is an exciting opportunity for a mathematician / computer scientist to gain experience of neuroscience. You will have a PhD in Mathematics / Computing Science or be shortly about to complete such a PhD. You will be familiar with numerical mathematics, information theory, and dynamic and stochastic systems. You should also have proven computer programming ability in a high-level language such as Java or C++. Knowledge of MATLAB and the NEURON simulation package would be highly beneficial. You should have a willingness to learn sufficient neuroscience to understand the system being studied. Depending on experience, up to a 20 month appointment will be made on the Research Staff Salary Scale at point 6: a maximum of ?22,289 p.a. The successful candidate will be expected to take up the position by the beginning of January 2006, or as soon as possible thereafter. Informal enquiries may be made to Dr Bruce Graham: Tel: 01786 467432, Fax: 01786 464551 or e-mail b.graham at cs.stir.ac.uk, from whom further details of the project can be obtained. Further Particulars are available from the HR Services Office, University of Stirling, Stirling, FK9 4LA. Tel: (01786) 467028, Fax: (01786) 466155, e-mail hr-services at stir.ac.uk Closing date for applications: Monday 28th November 2005 Reference No. 11643/4134 www.hr-services.stir.ac.uk AN EQUAL OPPORTUNITIES EMPLOYER -- Dr Bruce Graham, Reader (b.graham at cs.stir.ac.uk) Dept. of Computing Science and Mathematics, University of Stirling, Stirling FK9 4LA phone: +44 1786 467 432 fax: +44 1786 464 551 -- The University of Stirling is a university established in Scotland by charter at Stirling, FK9 4LA. Privileged/Confidential Information may be contained in this message. If you are not the addressee indicated in this message (or responsible for delivery of the message to such person), you may not disclose, copy or deliver this message to anyone and any action taken or omitted to be taken in reliance on it, is prohibited and may be unlawful. In such case, you should destroy this message and kindly notify the sender by reply email. Please advise immediately if you or your employer do not consent to Internet email for messages of this kind. From baolshausen at berkeley.edu Fri Nov 11 12:16:26 2005 From: baolshausen at berkeley.edu (Bruno Olshausen) Date: Fri, 11 Nov 2005 12:16:26 -0500 Subject: Connectionists: Tenure-track position - UC Berkeley Message-ID: <4374D1EA.7040906@berkeley.edu> The Helen Wills Neuroscience Institute together with the Department of Physics at UC Berkeley intend to make a joint tenure-track appointment, effective July 1, 2006. The search is broadly defined and could range from experimental biophysics to theoretical approaches. The full details may be obtained from: http://neuroscience.berkeley.edu/job_openings.php Berkeley has a strong neuroscience program, and with the recent establishment of the Redwood Center for Theoretical Neuroscience (http://redwood.berkeley.edu) it also now has a strong contingent pursuing theoretical and computational approaches. Note the application deadline is soon: ** November 23, 2005 ** -- Bruno A. Olshausen Director, Redwood Center for Theoretical Neuroscience and Associate Professor, Helen Wills Neuroscience Institute and School of Optometry, UC Berkeley 132 Barker Hall, #3190, Berkeley, CA 94720-3190 (510) 643-1472 / 4952 (fax) http://redwood.berkeley.edu From ahirose at ee.t.u-tokyo.ac.jp Fri Nov 18 02:50:54 2005 From: ahirose at ee.t.u-tokyo.ac.jp (Akira Hirose) Date: Fri, 18 Nov 2005 16:50:54 +0900 Subject: Connectionists: CFP: WCCI'06-IJCNN'06 Special Session on Complex-Valued Neural Networks In-Reply-To: <437D8697.5070800@ee.t.u-tokyo.ac.jp> References: <4379B2EB.1060107@eis.t.u-tokyo.ac.jp> <437D8697.5070800@ee.t.u-tokyo.ac.jp> Message-ID: <437D87DE.5060600@ee.t.u-tokyo.ac.jp> Call For Papers: WCCI-IJCNN 2006 Special Session on Complex-Valued Neural Networks Organized by Akira Hirose URL: http://www.eis.t.u-tokyo.ac.jp/ ============================================== Scope: The complex-valued neural networks (CVNNs) have been widening the scope of applications not only in electronics and informatics, but also in social systems. The fields are, namely, optoelectronics, imaging, remote sensing, quantum neural devices and systems, intelligent transport systems, and so on. One of the most important characteristics of the CVNNs is the proper treatment of complex-amplitude information, e.g., the treatment of wave-related / rotation-related phenomena such as electromagnetism, lightwaves, quantum waves, oscillatory phenomena even including traffic signal control, and color image processing based on adaptive signal rotation in the RGB space. Recently there were several CVNN Special Sessions (SSs) in, for example, KES 2001-2003, ICONIP 2002 Singapore, ICANN/ICONIP 2003 Istanbul, and ICONIP 2004 Calcutta, where we had large audience and enjoyed heated and encouraging discussions successfully. The series indicates the increasing importance of this new area. Now we hold a SS in the WCCI for a wider audience, including fuzzy and evolutionary researchers, to develop further investigations both in theoretical and application fields. We will present the latest results and considerations, and discuss prospective possibilities of the CVNNs. Papers that are, or might be, related to the CVNNs are widely solicited. Topics include, but are not limited to: * Complex-Valued Neuron Dynamics * Complex-Valued Associative Memories * Chaos in Complex Domain * Spatiotemporal CVNN Processing * CVNN-based Two-dimensional Information Transform * CVNN-based Periodic Information Processing * Fourier Domain CVNN Processing * Phase-Sensitive Radar Signal Processing * Coherent Optoelectronic Applications * Speech, Sonic and Ultrasonic Applications * Adaptive Quantum Devices * Quantum Computation and Quantum Neural Networks * CVNNs in Color Image Processing * CVNNs in Traffic Control * CVNNs in Robotics * Quaternion and Clifford Networks ============================================= From zhaoping at gatsby.ucl.ac.uk Sun Nov 20 16:38:13 2005 From: zhaoping at gatsby.ucl.ac.uk (Dr Zhaoping Li) Date: Sun, 20 Nov 2005 21:38:13 +0000 (GMT) Subject: Connectionists: Postdoc job in vision in London UK Message-ID: Applications are invited for the post of Postdoctoral Research Fellow to work with Dr. Li Zhaoping (http://www.gatsby.ucl.ac.uk/~zhaoping) in the area of neuroscience, particularly on biological vision, using theoretical and/or psychophysical investigation tools. The candidate should have good experience in theoretical/modeling areas or in visual psychophysical area. Interest and capability to engage in research activities in both areas would be preferable although not essential. The research fellow is expected to contribute to the research environment of the laboratory and should have the capability to work well in a team. The post is available Jan 2006. Salary is on the RA1A scale (£25,622-£32,442 including London allowance) and will depend upon qualifications and experience. Applications (email or hard copy ) by cover letter, CV and Personal Information form (the latter available at http://www.psychol.ucl.ac.uk/info/Personal_Information.doc) to: John Draper Departmental Administrator Department of Psychology UCL Gower Street London WC1E 6BT j.draper at ucl.ac.uk If applying by email please submit all requested information in one .pdf file names by your surname eg Smith.pdf. Further information concerning the post are on the web at http://www.psychol.ucl.ac.uk/info/psychophysics_li.htm while interested candidates can also contact Li Zhaoping, z.li at ucl.ac.uk 44 20 7679 1174 The closing date for the applications is Friday 2nd December 2005. --- sorry for the late posting, but please apply ASAP if interested, and we will continue to accept applications before the position is offered. From derdogmus at ieee.org Tue Nov 15 16:19:13 2005 From: derdogmus at ieee.org (Deniz Erdogmus) Date: Tue, 15 Nov 2005 13:19:13 -0800 Subject: Connectionists: CFP: Neurocomputing Special Issue on Advances in Blind Signal Processing Message-ID: <437A50D1.20905@ieee.org> Dear Connectionists, Please take note of this special issue that aims to bring together the latest results in BSP. The CFP preprint can be downloaded at the following address: http://www.csee.ogi.edu/~deniz/NEUCOM_CFP.pdf Best, Deniz Erdogmus From esann at dice.ucl.ac.be Sun Nov 20 15:23:21 2005 From: esann at dice.ucl.ac.be (esann) Date: Sun, 20 Nov 2005 21:23:21 +0100 Subject: Connectionists: extended deadline: ESANN'2006 European Symposium on Artificial Neural Networks Message-ID: <005401c5ee10$40fda7e0$43ed6882@maxwell.local> Due to numerous requests, the deadline to submit papers to the ESANN'2006 conference has been extended to December 6, 2005. 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'2006, The organizing committee. ===================================================== ESANN'2006 14th European Symposium on Artificial Neural Networks 14th European Symposium on Artificial Neural Networks Advances in Computational Intelligence and Learning Bruges (Belgium) - April 26-27-28, 2006 Announcement and call for papers ===================================================== Technically co-sponsored by the International Neural Networks Society, the European Neural Networks Society, the IEEE Computational Intelligence Society (to be confirmed), the IEEE Region 8, the IEEE Benelux Section. The call for papers for the ESANN'2006 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'2006 is organized in collaboration with the UCL (Universite catholique de Louvain, Louvain-la-Neuve) and the KULeuven (Katholiek Universiteit Leuven). 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'2006 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 organised 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 organised during ESANN'2006 are: 1) Semi-blind approaches for source separation and independent component analysis M. Babaie-Zadeh, Sharif Univ. Tech. (Iran), C. Jutten, CNRS ? Univ. J. Fourier ? INPG (France) 2) Visualization methods for data mining F. Rossi, INRIA Rocquencourt (France) 3) Neural Networks and Machine Learning in Bioinformatics - Theory and Applications B. Hammer, Clausthal Univ. Tech. (Germany), S. Kaski, Helsinki Univ. Tech. (Finland), U. Seiffert, IPK Gatersleben (Germany), T. Villmann, Univ. Leipzig (Germany) 4) Online Learning in Cognitive Robotics J.J. Steil, Univ. Bielefeld, H. Wersing, Honda Research Institute Europe (Germany) 5) Man-Machine-Interfaces - Processing of nervous signals M. Bogdan, Univ. T?bingen (Germany) 6) Nonlinear dynamics N. Crook, T. olde Scheper, Oxford Brookes University (UK) 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 November 28, 2005. 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, 2006; 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 November 28, 2005 Notification of acceptance January 27, 2006 Symposium April 26-28, 2006 Conference secretariat ---------------------- ESANN'2006 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 Pr?figure (F) Gianluca Bontempi Univ.Libre Bruxelles (B) Marie Cottrell Univ. Paris I (F) Jeanny H?rault INPG Grenoble (F) Bernard Manderick Vrije Univ. Brussel (B) Eric Noldus Univ. Gent (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) Peter Bartlett Univ.California, Berkeley (USA) 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 Technology (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) Mia Loccufier Univ. Gent (B) Erzsebet Merenyi Rice Univ. (USA) Jos? Mira UNED (E) 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) David Saad Aston Univ. (UK) 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) Michael Tipping Microsoft Research (Cambridge) (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) 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 girolami at dcs.gla.ac.uk Thu Nov 17 09:22:26 2005 From: girolami at dcs.gla.ac.uk (Mark Girolami) Date: Thu, 17 Nov 2005 14:22:26 -0000 Subject: Connectionists: Gaussian Process Classification Paper Available Message-ID: The following paper may be of interest to those working on devising efficient methods of approximate Bayesian inference for classification over multiple classes with Gaussian Processes. Title: Variational Bayesian Multinomial Probit Regression with Gaussian Process Priors. Authors: Mark Girolami and Simon Rogers, Department of Computing Science, University of Glasgow Abstract It is well known in the statistics literature that augmenting binary and polychotomous response models with Gaussian latent variables enables exact Bayesian analysis via Gibbs sampling from the parameter posterior. By adopting such a data augmentation strategy, dispensing with priors over regression coefficients in favour of Gaussian Process (GP) priors over functions, and employing variational approximations to the full posterior we obtain efficient computational methods for Gaussian Process classification in the multi-class setting. The model augmentation with additional latent variables ensures full a posteriori class coupling whilst retaining the simple a priori independent GP covariance structure from which sparse approximations, such as multi-class Informative Vector Machines (IVM), emerge in a very natural and straightforward manner. This is the first time that a fully Variational Bayesian treatment for multi-class GP classification has been developed without having to resort to additional explicit approximations to the non-Gaussian likelihood term. Empirical comparisons with exact analysis via MCMC and Laplace approximations illustrate the utility of the variational approximation as a computationally economic alternative to full MCMC and it is shown to be more accurate than the Laplace approximation. Available from: http://www.dcs.gla.ac.uk/people/personal/girolami/pubs_2005/VBGP/index.h tm To Appear Neural Computation, MIT Press From jeffyoshimi at yahoo.com Sun Nov 20 18:26:28 2005 From: jeffyoshimi at yahoo.com (Jeffrey Yoshimi) Date: Sun, 20 Nov 2005 15:26:28 -0800 Subject: Connectionists: Faculty Position at UC Merced Message-ID: <8A322C9F-71E2-4B49-8BA5-8FC86733EDF8@yahoo.com> All: UC Merced is currently hiring an Assistant Professor of Cognitive Science and Engineering. See: http://jobs.ucmerced.edu/view_academic_position.faces?positionId=300 It's an exciting place to be. UC Merced is the tenth campus of the University of California System, and the first new UC to be built in about 40 years. We just opened this year and are building a whole host of interdisciplinary programs, including cognitive science, from the ground up. Merced is 2 hours from the San Francisco Bay Area and 1.5 hours from Yosemite. Cheers! Jeff Yoshimi Assistant Professor and Founding Faculty University of California, Merced From neil at dcs.shef.ac.uk Fri Nov 18 06:29:26 2005 From: neil at dcs.shef.ac.uk (Neil Lawrence) Date: Fri, 18 Nov 2005 11:29:26 +0000 Subject: Connectionists: Postdoctoral position in Modelling Human Motion Message-ID: <437DBB16.9050404@dcs.shef.ac.uk> The following postdoc position in probabilistic modelling of human motion data is available at the University of Sheffield in the Department of Computer Science. Job Title: Postdoctoral Research Associate Job Location: Department of Computer Science University of Sheffield, U.K. Job Ref No: PR2250 Closing Date: 22nd December, 2005 Salary: 22,774 - 28,850 per annum Project Summary The focus of the work will be on the construction of probabilistic models for modelling human motion capture data. The project is a collaboration between Professor Philip Torr of Oxford Brookes University and Dr Neil Lawrence of Sheffield University. Applicants should have, or should be about to receive a PhD in a related area (e.g. machine learning, graphics, vision). The post is for a period of up to one year. The position is funded as a pump-priming project by the PASCAL European Network of Excellence. It is expected, as part of the project, that a submission for extended funding will be made through the EU or UK research councils with the successful applicant as a named research associate. Neil Lawrence will be available at NIPS to conduct informal interviews for interested candidates. Please e-mail neil at dcs.shef.ac.uk if you would like to discuss the position there. More details of the position are available at http://www.dcs.shef.ac.uk/~neil/postdoc1105.html From A.Cangelosi at plymouth.ac.uk Mon Nov 21 05:24:09 2005 From: A.Cangelosi at plymouth.ac.uk (Angelo Cangelosi) Date: Mon, 21 Nov 2005 10:24:09 -0000 Subject: Connectionists: Connection Science Special Issue on "The Emergence of Language: Neural Network and Adaptive Agent Models" Message-ID: <64997DB783F0FD4EB5550AD0D550E2290501DCA7@03-CSEXCH.uopnet.plymouth.ac.uk> Hello, Can you please forward this email to the Connectionist mailing lists? Thanks, Angelo Connection Science Journal Special Issue on "The Emergence of Language: Neural and Adaptive Agent Models" Volume 17, Issue 3-4, 2005 http://journalsonline.tandf.co.uk/(222bwz45frr1jz55wm1xfv45)/app/home/issue.asp?referrer=parent&backto=journal,1,34;linkingpublicationresults,1:100630,1 This special issue has two main aims. The first is to provide an up-to-date account of recent modeling studies of the emergence of language. This is achieved through the inclusion of papers reporting on the latest advances in robotics and computer simulation experiments on language emergence. This special issue includes papers on robotics and embodied systems (Nolfi, Yu, Dominey), adaptive multi-agent systems (Bartlett & Kazakov, Oudeyer, Kaplan) and connectionist simulations (Kuehn and Cruse, Mirolli & Parisi, van der Velde). The second aim is to identify the key research directions for the future. This is mainly achieved in the two invited papers by Brian MacWhinney and Luc Steels, in addition to specific research issues discussed in individual papers. TABLE OF CONTENT Editorial: The emergence of language: neural and adaptive agent models Angelo Cangelosi The emergence of linguistic form in time Brian MacWhinney The emergence and evolution of linguistic structure: from lexical to grammatical communication systems Luc Steels Emergence of communication in embodied agents: co-adapting communicative and non-communicative behaviours Stefano Nolfi Simple models of distributed co-ordination Fr?d?ric Kaplan The origins of syntax: from navigation to language Mark Bartlett and Dimitar Kazakov Emergence of grammatical constructions: evidence from simulation and grounded agent experiments Peter Ford Dominey How can we explain the emergence of a language that benefits the hearer but not the speaker? Marco Mirolli and Domenico Parisi The self-organization of combinatoriality and phonotactics in vocalization systems Pierre-yves Oudeyer Static mental representations in recurrent neural networks for the control of dynamic behavioural sequences Simone K?hn and Holk Cruse Modelling language development and evolution with the benefit of hindsight Frank Van Der Velde The emergence of links between lexical acquisition and object categorization: a computational study Chen Yu ---------------- Angelo Cangelosi, PhD ---------------- Reader in Artificial Intelligence and Cognition Adaptive Behaviour and Cognition Research Group School of Computing, Communications & Electronics University of Plymouth Portland Square Building (A316) Plymouth PL4 8AA (UK) E-mail: acangelosi at plymouth.ac.uk http://www.tech.plym.ac.uk/soc/staff/angelo (tel) +44 1752 232559 (fax) +44 1752 232540 From vgkabs at philippos.teikav.edu.gr Mon Nov 21 06:44:44 2005 From: vgkabs at philippos.teikav.edu.gr (Kaburlasos Vassilis) Date: Mon, 21 Nov 2005 13:44:44 +0200 Subject: Connectionists: Call For Papers: WCCI 2006 Special Session on "Computational Intelligence Based on Lattice Theory" Message-ID: <014b01c5ee90$f7b6f0b0$755e82c3@industrialwin.teikav.edu.gr> CALL FOR PAPERS 2006 IEEE Congress on Computational Intelligence (WCCI 2006) Vancouver, Canada, 16-21 July 2006 http://www.wcci2006.org/ FUZZ-IEEE approved special session on "Computational Intelligence Based on Lattice Theory" Organized by Vassilis G. Kaburlasos (Technological Educational Institution of Kavala), Gerhard X. Ritter (University of Florida), Michael Georgiopoulos (University of Central Florida) URL: http://iiu.teikav.edu.gr/users/vgkabs/WCCI2006.htm ============================================== Scope: Rooted in neural computing the employment of lattice theory emerges lately in computational intelligence with the potential to cross-fertilize several domains including, as well, fuzzy systems, machine learning, probabilistic reasoning, etc. Genetic algorithms are often employed for tuning performance. Lattice theory has already been used to improve analysis and design of popular neurocomputing paradigms. For instance, granular extensions of both Carpenter's fuzzy adaptive resonance theory (ART) and Kohonen's self-organizing maps (SOM) have been presented in the literature based on lattice theory. Lattice algebra is also employed in several computational intelligence domains. Another promising application for lattice theory is fuzzy inference systems. Furthermore, a "principled design" of a model based on disparate types of data (e.g. vectors of numbers, images, text structures, logical relations, concepts, (fuzzy) sets and graphs) can be pursued using lattice theory. Hence, lattice theory emerges as a sound foundation for unifying rigorously diversity in computational intelligence. This special session is meant as a forum for researchers with interests in computational intelligence applications of lattice theory. The objective is to present high-quality, state-of-the-art research results. An array of novel mathematical tools, design practices and real world applications will be presented. Emphasis is on system modeling, knowledge representation, data mining, and industrial/environmental applications. Topics of interest include but are not limited to . Lattice algebra neural networks . Fuzzy lattice neurocomputing . Fuzzy adaptive resonance theory . Fuzzy mathematical morphology . Fuzzy implications . Fuzzy similarity measures . Fuzzy system modeling . Probabilistic reasoning . Granular computing . Data mining . Lattice-interval/hyperbox learning . Disparate data fusion . Semantic Web . Knowledge representation . Formal concept analysis . Category theory ============================================= From popescu at prosun.first.fraunhofer.de Mon Nov 21 09:21:23 2005 From: popescu at prosun.first.fraunhofer.de (Florin Popescu) Date: Mon, 21 Nov 2005 15:21:23 +0100 Subject: Connectionists: post-doc position at Fraunhofer Institute FIRST Berlin Message-ID: <6.2.3.4.0.20051121151826.02eb9628@mailhost> The Fraunhofer-Institute FIRST in Berlin is searching for a Postdoc as Research Associate (m/f) A three-year fellowship is available for a researcher with 4-10 years research experience starting January 2005. The EC-funded BRAIN2ROBOT project will adapt the brain computer interface technology developed at the Berlin Brain Computer Interface (BBCI) Laboratory at Fraunhofer-FIRST-IDA (http://ida.first.fraunhofer.de, www.bbci.de) to restore reaching function in quadriplegic patients. The Marie Curie Excellence Team consists of 4 researchers, but work will be done in close collaboration with other IDA group members. The main focus of this fellowship would be to adapt and possibly improve the BBCI interface to the control of a robot, while producing innovative and tangible research. The candidate will be expected to have a strong computer science background, with competence in time series analysis, pattern recognition, machine learning, dynamical systems and complexity. Strong programming skills and theoretical skills grounded in mathematics are a must. A strong plus would be direct experience with electrophysiological signal analysis and neurophysiology. The working language of the laboratory is English. The yearly salary is ca. 3850Euro/month (before taxes and social security). Preference will be given to nationals of EU member states (other than Germany) and nationals of EU associated states. International candidates will also receive mobility and travel allowances of up to approx. 9300 Euro per annum depending on current residency and family status. Please send your CV, cover letter and a sample of published work to (in your letter or email, refer to job number FIRST-113-05-003): Fraunhofer-Gesellschaft Zentrale-Hauptabteilung Personal Frau Rabel Kekulstr. 7, 12489 Berlin To apply via email contact: Florin Popescu, Ph.D. Email: florin.popescu at first.fraunhofer.de Speculative submissions will not be considered. From rao at cs.washington.edu Tue Nov 22 14:45:18 2005 From: rao at cs.washington.edu (Rajesh Rao) Date: Tue, 22 Nov 2005 11:45:18 -0800 Subject: Connectionists: Preprint: Bayesian inference and attention in the visual cortex In-Reply-To: References: Message-ID: <4383754E.2000605@brain.cs.washington.edu> The following paper is available for download: http://www.cs.washington.edu/homes/rao/nreport_bayes_atten05.pdf Bayesian Inference and Attentional Modulation in the Visual Cortex Neuroreport 16(16), 1843-1848, 2005 The responses of neurons in cortical areas V2 and V4 can be significantly modulated by attention to particular locations within an input image. We show that such effects emerge naturally when perception is viewed as a probabilistic inference process governed by Bayesian principles and implemented in hierarchical cortical networks. We show that the proposed model can explain a rich variety of attention-related responses in cortical area V4 including multiplicative modulation of tuning curves, restoration of neural responses in the presence of distracting stimuli, and influence of attention on neighboring unattended locations. Our results suggest a new interpretation of attention as a cortical mechanism for reducing perceptual uncertainty by combining top-down task-relevant information with bottom-up sensory inputs in a probabilistic manner. -- Rajesh P. N. Rao Dept of Computer Science and Engineering Univ of Washington Seattle, WA 98195-2350 http://cs.washington.edu/homes/rao/ Lab Website: http://neural.cs.washington.edu From soeren.lorenz at uni-bielefeld.de Thu Nov 24 04:24:34 2005 From: soeren.lorenz at uni-bielefeld.de (Soeren Lorenz) Date: Thu, 24 Nov 2005 10:24:34 +0100 Subject: Connectionists: Special Issue on Realistic Neural Modeling (OA eJournal Brains, Minds, and Media) Message-ID: <438586D2.3060309@uni-bielefeld.de> (Apologies for multiple postings) ________________________ SPECIAL ISSUE ON REALISTIC NEURAL MODELING Brains, Minds & Media - open access eJournal http://www.brains-minds-media.org ________________________ Now available, free online access: Special Issue on Realistic Neural Modeling - Wam-Bamm '05 Tutorials. Guest Editors: James M. Bower and David Beeman http://www.brains-minds-media.org/current THE ISSUE This special issue provides article versions of eight tutorials presented at the 1st Conference of the World Association of Modelers: Biologically Accurate Modeling Meeting (WAM-BAMM '05), held in San Antonio, Texas, in March 2005. The issue is introduced by the viewpoint "Looking for Newton: Realistic Modeling in Modern Biology" by James M. Bower. GENERAL The issue deals with methods and practical implications of biologically accurate modeling and offers introductory and advanced tutorials mainly based on the tools GENESIS and NEURON. Some contributions provide supplementary material, such as GENESIS source code, detailed modeling and user instructions or visualisations. TOPICS Part of the articles covers questions of realistic modeling ranging from a general introduction to modeling of single cells, calcium concentrations, biochemical pathways, and synaptic input patterns. The other articles are concerned with tools and techniques, like how to use GENESIS and P-GENESIS for modeling, recent developments in NEURON and the role of XML for model specifications in neuroscience. TABLE OF CONTENTS *Looking for Newton: Realistic Modeling in Modern Biology by James M. Bower *Introduction to Realistic Neural Modeling by David Beeman *GENESIS Modeling Tutorial (Wam-Bamm'05 Edition) by David Beeman *Recent Developments in NEURON by Michael Hines and Nicholas T. Carnevale *Realistic Single Cell Modeling - from Experiment to Simulation by Dieter Jaeger *Modeling Calcium Concentration and Biochemical Reactions by Kim T. Blackwell *Simulating in vivo-like Synaptic Input Patterns in Multicompartmental Models by Jeremy Edgerton *Using P-GENESIS for Parallel Simulation of GENESIS Models - a Brief Overview by Greg Hood *XML for Model Specification in Neuroscience - an Introduction and Workshop Summary by Sharon Crook, David Beeman, Padraig Gleeson and Fred Howell ----------------------------- CONTINUOUS CALL FOR SUBMISSION 'Brains, Minds & Media' is an open access eJournal and publishes peer-reviewed articles and media from research and education in the neural and cognitive sciences (http://www.brains-minds-media.org/aims). Future accepted contributions will be published consecutively and integrated ex post into volumes or (special) issues. You are invited to submit contributions to 'Brains, Minds & Media'. More information about manuscript submissions can be found at http://www.brains-minds-media.org/guidelines. Please send your submission to editors at brains-minds-media.org. ----------------------------- If you have any questions, please contact info at brains-minds-media.org. Thank you! Soeren Lorenz (editorial co-ordinator) soeren.lorenz at uni-bielefeld.de From terry at salk.edu Thu Nov 24 00:06:05 2005 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 23 Nov 2005 21:06:05 -0800 Subject: Connectionists: NEURAL COMPUTATION 18:1 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 18, Number 1 - January 1, 2006 NOTE Mixture Models Based on Neural Network Averaging Walter W. Focke LETTERS Sensory Memory for Odors is Encoded in Spontaneous Correlated Activity Between Olfactory Glomeruli Roberto F. Galan, Marcel Weidert, Randolf Menzel, Andreas V. M. Herz and C. Giovanni Galizia The Optimal Synapse for Sparse, Binary Signals in the Rod Pathway Paul T. Clark and Mark C. W. van Rossum Simultaneous Rate-Synchrony Codes in Population of Spiking Neurons Naoki Masuda Spontaneous Dynamics of Asymmetric Random Recurrent Spiking Neural Networks Hedi Soula, Guillaume Beslon, and Olivier Mazet Bayesian Population Decoding of Motor Cortical Activity Using a Kalman Filter Wei Wu, Yun Gao, Elie Bienenstock, John P. Donoghue and Michael J. Black Facial Attractiveness: Beauty and the Machine Yael Eisenthal, Gideon Dror and Eytan Ruppin Classification of Faces in Man and Machine Arnulf B. A. Graf, Felix A. Wichmann, Heinrich H. Buelthoff and Bernhard Schoelkopf Exploring Latent Structure of Mixture ICA Models by the Minimum Beta-Divergence Method Md. Nurul Haque Mollah, Mihoko Minami and Shinto Eguchi An Adaptive Method for Subband Decompostion ICA Kun Zhang and Lai-Wan Chan On Consistency of Bayesian Inference with Mixtures of Logistic Regression Yang Ge and Wenxin Jiang ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2006 - VOLUME 18 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $154 $90 $96.30 Institution $730 $781.10 $784 $657 $702.99 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From jonas at buchli.org Fri Nov 25 10:38:29 2005 From: jonas at buchli.org (Jonas Buchli) Date: Fri, 25 Nov 2005 16:38:29 +0100 Subject: Connectionists: CfP: EPFL-LATSIS Symposium 2006 - Dynamical Principles for Neuroscience and Intelligent Biomimetic Devices Message-ID: <1132933109.10486.66.camel@moria.buchli.org> Dear Connectionists, Please find below the call for poster abstracts of a conference which might be of interest for many of you. Best regards Jonas Buchli ----------------------------------------------------------------------- <> EPFL-LATSIS Symposium 2006 Call for Poster abstracts ==================================================== We invite the submission of poster abstracts for the EPFL-LATSIS Symposium 2006 Dynamical Principles for Neuroscience and Intelligent Biomimetic Devices http://latsis2006.epfl.ch March, 8-10, 2006 Ecole Polytechnique F?d?rale de Lausanne (EPFL), Switzerland Aim of the Conference --------------------- The goal of the conference is to bring together scientists and engineers interested in understanding the dynamical properties of the nervous system, and in taking inspiration from those properties for the design of prosthetic and robotic devices. The conference is interdisciplinary in nature, and aims at bringing together researchers working on similar topics and phenomena but from different backgrounds. The conference is made possible thanks to the generous support of the Latsis Foundation. The presentations will consists of a series of invited talks (see below) and of poster presentations (with short poster spotlights). For more background on the aim of the conference, please visit http://latsis2006.epfl.ch Important Dates --------------- Deadline of abstract submission: January 27, 2006 Notification of acceptance: February 6, 2006 Conference dates: March 8-10, 2006 Abstract submission ------------------- Please send a two-page abstract (including figures and references as needed) to jonas.buchli -at- epfl.ch . Note that we will not have a full peer review process, the number of posters that we can accept is however limited. Thus, we will accept the contributions depending on relevance to the conference topics, quality, and available place. Once accepted, presenters will have the opportunity to present their work with a poster, as well as a short poster spotlight (a 2-minute presentation) in the conference theatre. Templates as well as additional information on the format of abstracts and posters is available on the following website: http://latsis2006.epfl.ch/page14710.html Proceedings ----------- The poster abstracts will be published in a booklet with ISBN number distributed at the conference. Speakers -------- Dynamics of brain function and behavior * Avis Cohen (University of Maryland) * Sten Grillner (Karolinska Institutet, Stockholm) * Serge Rossignol (Universit? de Montr?al) * Carmen Sandi (EPFL) * Allen Selverston (UC San Diego) Nonlinear Dynamics and neural computation * Bard Ermentrout (University of Pittsburgh) * Wulfram Gerstner (EPFL) * Martin Hasler (EPFL) * Wolfgang Maass (TU Graz) * Misha Rabinovich (UC San Diego) * Misha Tsodyks (Weizmann Institute of Science) Neuroprosthetics * Maria Chiara Carrozza (Scuola Superiore Sant'Anna, Pisa) * Miguel Nicolelis (EPFL/Duke University) * Philippe Renaud (EPFL) * Andrew Schwartz (University of Pittsburgh) Hybrid circuits and electronic neurons * Thierry Bal (Unic / CNRS) * Rodney Douglas (ETHZ, Zurich) * Peter Fromherz (Max-Planck-Institute for Biochemistry, Martinsried) * Gwendal Le Masson (University of Bordeaux) Biomimetic Robotics and Control * Jean-Louis Deneubourg (Univ. libre de Bruxelles) * Auke Jan Ijspeert (EPFL) * Yasuo Kuniyoshi (University of Tokyo) * Jean-Jacques Slotine (MIT) * Barbara Webb (University of Edinburgh) Organizing Committee -------------------- Main organizer: Auke Ijspeert, EPFL Co-organizers: Aude Billard, EPFL Dario Floreano, EPFL Wulfram Gerstner, EPFL Martin Hasler, EPFL Henry Markram, EPFL Misha Rabinovich, UCSD Al Selverston, UCSD Local chair: Jonas Buchli, EPFL Email contacts: Auke.Ijspeert -at- epfl.ch and Jonas.Buchli -at- epfl.ch -- ----------------------------------------------------------------- Jonas Buchli Research Assistant Biologically Inspired Robotics Group School of Computer and Communication Sciences EPFL, Swiss Federal Institute of Technology, Lausanne CH 1015 Lausanne, Switzerland jonas at buchli.org http://birg.epfl.ch ++41 21 693 67 14 ----------------------------------------------------------------- From ihaya at kcn.res.kutc.kansai-u.ac.jp Thu Nov 24 06:11:56 2005 From: ihaya at kcn.res.kutc.kansai-u.ac.jp (Isao Hayashi) Date: Thu, 24 Nov 2005 20:11:56 +0900 (JST) Subject: Connectionists: CFP: WCCI'06 Special Session on Biologically Motivated Systems In-Reply-To: <437D87DE.5060600@ee.t.u-tokyo.ac.jp> Message-ID: <20051124.201156.846960977.ihaya@kcn.res.kutc.kansai-u.ac.jp> Call For Papers: WCCI 2006 Special Session on Biologically Motivated Systems - Fuzzy Brain and Fuzzy Evolution Organized by I.Hayashi, T.Nakashima, and T.Murata ======================================================================== IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) July 16-21, 2006 Sheraton Vancouver Wall Centre, Vancouver, BC, Canada http://www.wcci2006.org/ ======================================================================== Session: Biologically Motivated Systems - Fuzzy Brain and Fuzzy Evolution Session Organizer: I.Hayashi (ihaya at kcn.res.kutc.kansai-u.ac.jp) T.Nakashima (email: nakashi at cs.osakafu-u.ac.jp) T.Murata (murata at res.kutc.kansai-u.ac.jp) Paper Submission : January 31, 2006 Scope of the Organized Session: The main aim of this session is to introduce a new approach in brain physiology, cognitive psychology, vision, blonomy, genetic sciences, and psychological genetics, relating neuro-fuzzy and genetic fuzzy systems: these issues are germane to a wide modeling of biologically motivated systems, not just to computer vision and engineering systems. The session covers modeling of brain system and vision system, experiments of visual psychology, visual neural networks, neuro-fuzzy system, genetic fuzzy systems, A-Life, etc. ======================================================================== --- Isao Hayashi,Dr.Eng. Professor Faculty of Informatics Kansai University 2-1-1, Ryozenji-cho, Takatsuki, Osaka 569-1095, Japan telephone +81-72-690-2448 m.phone +81-90-6677-6259 facsimile +81-72-690-2491 e.mail ihaya at kcn.res.kutc.kansai-u.ac.jp URL http://www.hannan-u.ac.jp/kcn/ *********************************************************************** From alaakso at indiana.edu Mon Nov 28 10:09:43 2005 From: alaakso at indiana.edu (Aarre Laakso) Date: Mon, 28 Nov 2005 10:09:43 -0500 Subject: Connectionists: CFP: Dynamics and Psychology Message-ID: <438B1DB7.2010304@indiana.edu> ************** APOLOGIES FOR MULTIPLE POSTINGS ******************* CALL FOR PAPERS *New Ideas in Psychology* Published by Elsevier Science B.V. ISSN 0732-118X, URL: A Special Issue on 'Dynamics and Psychology' GUEST EDITORS Paco Calvo (U. Murcia, Spain) Aarre Laakso (Indiana University, USA) Toni Gomila (U. Illes Balears, Spain) Paper Submission Deadline: September 30th, 2006 New Ideas in Psychology is calling papers for a special issue entitled 'Dynamics and Psychology'. The purpose of this special issue is to bring together some of the leading views on dynamicism as it relates to psychological phenomena. Although the primary focus is on conceptual ideas regarding the status of dynamicism from the standpoint of Developmental Psychology, Cognitive Science, Artificial Intelligence, Philosophy, and related fields, empirical work is also welcome insofar as it bears explicitly upon theoretical debate. New Ideas in Psychology invites original contributions for the forthcoming special issue on Dynamics and Psychology from a broad scope of areas. Some key research issues and topics relevant to this special issue include: *Brain and cognitive function *Categorical perception *Dynamic computer simulations *Dynamic field approach *Dynamic systems theory and developmental theory *Dynamics of control of processing *Dynamics of social interaction *Emergence *Intermodality *Language development *Mental representation *Motor development *Neurobiological constraints *Perceptual learning *Self-organization of behavior *Sensory-motor and perception-action loops *Temporality SUBMISSION INSTRUCTIONS AND DEADLINE Manuscripts, following the New Ideas in Psychology guidelines () should be emailed to Paco Calvo (fjcalvo at um.es) by September 30th, 2006. INVITED CONTRIBUTORS The special issue will include invited papers by: Dante Chialvo (Northwestern University Medical School, Chicago) Eliana Colunga (Colorado, Boulder) and Linda Smith (Indiana University) Aarre Laakso (Indiana University) John Spencer (University of Iowa) RELATED AND SAMPLE ARTICLES *Bechtel, W. (1998) "Representations and cognitive explanations: assessing the dynamicist's challenge in cognitive science", Cognitive Science, 22, 295-318. *Beer, R. D. (1995) "A dynamical systems perspective on agent-environment interaction", Artificial Intelligence, 72, 173-215. *Clark, A. (1997) "The dynamical challenge", Cognitive Science, 21, 461-481. *Erlhagen, W. & Schner, G. (2002) "Dynamic field theory of movement preparation", Psychological Review, 109, 545-572. *Nuez, R. & Freeman, W.J. (1999) Reclaiming cognition: the primacy of action, intention and emotion. Imprint Academic. *Prinz, J. J., & Barsalou, L. W. (2000) "Steering a course for embodied representation", In E. Dietrich & A. B. *Markman (Eds.), Cognitive dynamics: Conceptual and representational change in humans and machines (pp. 51-77). Mahwah, NJ: Lawrence Erlbaum Associates. *Spencer, J.P. & Schner, G. (2003) "Bridging the representational gap in the dynamic systems approach to development", Developmental Science, 6, 392-412. *Sporns, O., Chialvo, D., Kaiser, M. & Hilgetag, C. (2004) "Organization, development and function of complex brain networks", Trends in Cognitive Sciences, 9, 418-425. *Thelen, E., Schner, G., Scheier, C. & Smith, L. (2001) "The dynamics of embodiment: A field theory of infant perseverative reaching", Behavioral and Brain Sciences, 24, 1-86. *Townsend, J. T., & Busemeyer, J. (1995) "Dynamic representation of decision making", In R. F. Port & T. Van Gelder (Eds.), Mind as motion. Cambridge, MA: MIT Press. *Turvey, M. T., & Carello, C. (1995) "Some dynamical themes in perception and action" In R. F. Port & T. Van *Gelder (Eds.), Mind as motion. Cambridge, MA: MIT Press. *van Gelder, T. (1998) "The dynamical hypothesis in Cognitive Science", Behavioral and Brain Sciences, 21, 615-665. GUEST EDITORS Paco Calvo Departamento de Filosofa Universidad de Murcia E-30100 Murcia - SPAIN e-mail: fjcalvo at um.es Aarre Laakso Department of Psychology Indiana University 1101 East 10th Street Bloomington, IN 47405 e-mail: alaakso at indiana.edu Toni Gomila Department of Psychology University of the Balearic Islands E-07122 Palma de Mallorca - SPAIN e-mail: toni.gomila at uib.es From bisant at umbc.edu Mon Nov 28 18:29:10 2005 From: bisant at umbc.edu (D Bisant) Date: Mon, 28 Nov 2005 18:29:10 -0500 Subject: Connectionists: Function Approximation Message-ID: <438B92C6.9080301@umbc.edu> A presenter at Supercomputing 2005 claimed that a number of classification methods used in datamining, such as decision trees and nearest neighbor, have been extended and perform well on function approximation applications. Are any of you familiar with the application of these methods to function approximation or interpolation? Regards, David Bisant The Laboratory for Physical Sciences From justin at cnel.ufl.edu Mon Nov 28 07:55:55 2005 From: justin at cnel.ufl.edu (Justin Sanchez) Date: Mon, 28 Nov 2005 07:55:55 -0500 Subject: Connectionists: Graduate Assistant (PhD) Position Available: Brain-Machine Interfaces Message-ID: <001001c5f41b$247726d0$7832b29f@Tranquility> Graduate Assistant (PhD) Position Available: Brain-Machine Interfaces The Neuroprosthetics Research Group (NRG) is searching for a highly-motivated Ph.D. student to participate in a National Science Foundation funded project for developing novel Brain-Machine Interfaces (BMI). The candidate will be expected to be competent in electrophysiological methods and signal processing (time series analysis). The student's research will bridge in vivo BMI experimental paradigms with the analysis of functional neural ensemble recordings. The position is available starting January 2006. If interested, please send via email a CV, a summary of skills and experiences, and the names/contact of two references to: Justin Sanchez, Ph.D. Email: jcs77 at ufl.edu Justin C. Sanchez, Ph.D. Department of Pediatrics, Division of Neurology McKnight Brain Institute, L2-140 PH: 1-352-392-4827 FAX: 1-352-392-2515 Neuroprosthetics Research Group University of Florida Gainesville, FL 32611 WWW: http://nrg.mbi.ufl.edu/ From ken at neurotheory.columbia.edu Wed Nov 30 14:25:21 2005 From: ken at neurotheory.columbia.edu (Ken Miller) Date: Wed, 30 Nov 2005 14:25:21 -0500 Subject: Connectionists: Columbia University Postdoctoral/Graduate Fellowships in Theoretical Neuroscience Message-ID: <17293.64673.455127.571337@neurotheory.columbia.edu> FULL INFO: http://www.neurotheory.columbia.edu PLEASE DO NOT USE 'REPLY'; FOR MORE INFO USE ABOVE WEB SITE The Center for Theoretical Neuroscience at Columbia University in New York City is accepting applications for graduate students and postdoctoral fellows. The faculty include: Larry Abbott, Co-Director http://neurotheory.columbia.edu/~larry Ken Miller, Co-Director http://neurotheory.columbia.edu/~ken Liam Paninski http://www.stat.columbia.edu/~liam Ning Qian http://brahms.cpmc.columbia.edu/ Stefano Fusi (Senior Research Associate) http://www.cns.unibe.ch/~fusi/ Bill Bialek (Visiting one day per week) http://www.princeton.edu/~wbialek/wbialek.html Columbia has a strong research program in experimental neurobiology (http://cpmcnet.columbia.edu/dept/neurobeh/nb_phd_res_area.html) and in computational biology (http://www.c2b2.columbia.edu/). The Center is a highly interactive environment for bringing theoretical approaches to Neuroscience. For postdoctoral fellowships, applicants should have a strong background and education in theoretical neuroscience or biology or in a quantitative field such as mathematics, theoretical or experimental physics, engineering, or computer science, and commitment to a future research career in neuroscience. Prior biological or neuroscience training is not required. TO APPLY, please send a curriculum vitae, a statement of previous research and research goals, up to three relevant publications, and have three letters of recommendation sent, to the address below. Applications are due by Jan. 30, 2006. For graduate fellowships, apply to an existing Ph.D. program at Columbia (details on our web site). Separately, notify us that you wish to be considered for a fellowship in Theoretical Neuroscience by sending email, to the address below, with a letter explaining which program you've applied to, why you intend to pursue Theoretical Neuroscience in your graduate work, and what background you bring to it. Please also include a copy of your application materials, and ask your referees to send us copies of their letters. Note that the priority application deadline for most programs is either Jan. 3 or (for engineering) Dec. 15. Application materials may be sent by email to Andrew Fink, andrew at neurotheory.columbia.edu; please include your name and "postdoctoral fellowship, CTN" or "graduate fellowship, CTN" in the subject line. Alternatively materials may be sent by surface mail (address on our web site). From wahba at stat.wisc.edu Tue Nov 29 16:18:47 2005 From: wahba at stat.wisc.edu (Grace Wahba) Date: Tue, 29 Nov 2005 15:18:47 -0600 Subject: Connectionists: Job opening in the Statistics Dept at Madison Message-ID: <200511292118.jATLIlNI006910@juno.stat.wisc.edu> The Statistics Department at the University of Wisconsin-Madison has an opening for a tenure track assistant professor starting fall 2006. There are several faculty members interested in classification and machine learning in the Statistics Department and many scattered throughout the campus in CS, Math, ECE and elsewhere. Madison is one of the great research universities and there are are many opportunities for collaboration. Madison is also a great place to live and (personally speaking) if you are interested in bicycling, sailing (we are on four lakes) and other outdoor activities it is a terrific place, along with cultural opportunities which are outstanding for a medium sized city. A job description can be found at http://www.stat.wisc.edu/Employent/ (please send job-related correspondance to the address there, not to me, thanks) regards Grace (More about Mad City at http://www.ci.madison.wi.us/) From sethu.vijayakumar at ed.ac.uk Tue Nov 29 05:06:18 2005 From: sethu.vijayakumar at ed.ac.uk (Sethu Vijayakumar) Date: Tue, 29 Nov 2005 10:06:18 +0000 Subject: Connectionists: Postdoctoral Fellowship in Machine Learning and Robotics in Edinburgh, UK. Message-ID: <438C281A.3090100@ed.ac.uk> Applications are invited for a Postdoctoral Research fellow in the area of Machine Learning and Robotics as part of an EU-IST FP6 funded four year project "SENSOPAC - Sensorimotor structuring of Perception and Action". The post is available from Jan. 2006 for a maximum of 48 months and located in the School of Informatic at the University of Edinburgh. Salary is on the RA1A scale (GBP 20,044 to GBP 30,002) and will depend upon qualifications and experience. The postdoctoral fellow will be responsible for developing statistical machine learning techniques for automatically extracting sensorimotor contingences from dynamic and kinematic movement data (collected from robots and human experiments) and using this to learn latent model representations of various contexts and tasks. This will involve basic research in the fields of high dimensional, online nonparametric regression, Bayesian model selection and latent model learning as well as applied areas of adaptive motor control and robotics. Candidates are expected to have a PhD in the area of machine learning and/or adaptive motor control and strong mathematical skills in the area of optimization, algebra and probability theory in addition to strong programming skills in C, C++, MATLAB or equivalent. Some experience with real world robotic systems and motor control is a plus. More details of the job and the research group can be found at: http://www.ipab.inf.ed.ac.uk/slmc/index.html Online applications are encouraged at: http://www.jobs.ed.ac.uk/vacancies/index.cfm?fuseaction=vacancies.detail&vacancy_ref=3005309 Application Deadline: December 20, 2005 Informal enquiries may be addressed to: Dr. Sethu Vijayakumar (sethu.vijayakumar [at] ed.ac.uk) Dr. Marc Toussaint (mtoussai [at] inf.ed.ac.uk) will be available at NIPS for an informal discussion/interview. (Please advertise in your department using the attached flyer) (We will continue to accept applications till the post is filled) -- ------------------------------------------------------------------ Sethu Vijayakumar, Ph.D. Assistant Professor(UK Lecturer) Director, IPAB, School of Informatics, The University of Edinburgh 2107F JCMB, The Kings Buildings, Edinburgh EH9 3JZ, United Kingdom URL: http://homepages.inf.ed.ac.uk/svijayak Ph: +44(0)131 651 3444 SLMC Research Group URL: http://www.ipab.informatics.ed.ac.uk/slmc ------------------------------------------------------------------ Adjunct Assistant Professor, Department of Computer Science, University of Southern California ------------------------------------------------------------------ From B.Kappen at science.ru.nl Wed Nov 30 03:36:58 2005 From: B.Kappen at science.ru.nl (Bert Kappen) Date: Wed, 30 Nov 2005 09:36:58 +0100 (CET) Subject: Connectionists: JSTAT special issue on approximate inference Message-ID: Dear all, Last January, we have organized an interface meeting in Switzerland between researchers in the field of machine learning and statistical physics. The topic of common interest was approximate inference and in particular message passing methods. The meeting was very interesting for both sides. Clearly, machine learning benefits from statistical physics methods, but also the reverse is true, in particular where it concerns the development of robust algorithms and challenging applications. The IOP Journal of Statistical Mechanics has published a focus issue on the meeting, which you will find at http://www.iop.org/EJ/journal/-page=extra.focus2/jstat Bert Kappen, Manfred Opper, Riccardo Zecchina and Ruedi Stoop Bert Kappen SNN Radboud University Nijmegen URL: www.snn.kun.nl/~bert The Netherlands tel: +31 24 3614241 fax: +31 24 3541435 B.Kappen at science.ru.nl From t.heskes at science.ru.nl Tue Nov 1 10:00:58 2005 From: t.heskes at science.ru.nl (Tom Heskes) Date: Tue, 01 Nov 2005 16:00:58 +0100 Subject: Connectionists: Neurocomputing volume 69 Message-ID: <4367832A.3030409@science.ru.nl> Neurocomputing Volume 69 (November 2005) ------- SPECIAL PAPERS (Neural Networks in Signal Processing edited by Marc M. van Hulle and Jan Larsen) Neural Networks in Signal Processing (editorial) Marc M. Van Hulle and Jan Larsen Loss functions to combine learning and decision in multiclass problems Alicia Guerrero-Curieses, Roc?o Alaiz-Rodr?guez and Jes?s Cid-Sueiro Discriminative clustering Samuel Kaski, Janne Sinkkonen and Arto Klami Support Vector Regression for the simultaneous learning of a multivariate function and its derivatives Marcelino L?zaro, Ignacio Santamar?a, Fernando P?rez-Cruz and Antonio Art?s-Rodr?guez Algebraic geometry and stochastic complexity of hidden Markov models Keisuke Yamazaki and Sumio Watanabe Novel approximations for inference in nonlinear dynamical systems using expectation propagation Alexander Ypma and Tom Heskes The differogram: Non-parametric noise variance estimation and its use for model selection Kristiaan Pelckmans, Jos De Brabanter, Johan A.K. Suykens and Bart De Moor Variational inference for Student-t models: Robust Bayesian interpolation and generalised component analysis Michael E. Tipping and Neil D. Lawrence Computationally efficient sequential learning algorithms for direct link resource-allocating networks Vijanth S. Asirvadam, Se?n F. McLoone and George W. Irwin Fast error whitening algorithms for system identification and control with noisy data Yadunandana N. Rao, Deniz Erdogmus, Geetha Y. Rao and Jose C. Principe Bidirectional associative memory with learning capability using simultaneous perturbation Yutaka Maeda and Masatoshi Wakamura A general solution to blind inverse problems for sparse input signals ? David Luengo, Ignacio Santamar?a and Luis Vielva ------- LETTERS Class-information-incorporated principal component analysis Songcan Chen and Tingkai Sun (2D)^2 PCA: Two-directional two-dimensional PCA for efficient face representation and recognition Daoqiang Zhang and Zhi-Hua Zhou Chaos and transient chaos in simple Hopfield neural networks Xiao-Song Yang and Quan Yuan Multihashing, human authentication featuring biometrics data and tokenized random number: A case study FVC2004 Dario Maio and Loris Nanni View-independent person identification from human gait Zonghua Zhang and Nikolaus F Troje Hyperplanes for predicting protein?protein interactions Loris Nanni A fixed-point nonlinear PCA algorithm for blind source separation ? Xiaolong Zhu, Jimin Ye and Xianda Zhang Using batch algorithm for kernel blind source separation Zhan-Li Sun, De-Shuang Huang, Chun-Hou Zheng and Li Shang ------- JOURNAL SITE: http://www.elsevier.com/locate/neucom SCIENCE DIRECT: http://www.sciencedirect.com/science/issue/5660-2005-999309998-609282 From Luc.Berthouze at aist.go.jp Tue Nov 1 20:11:54 2005 From: Luc.Berthouze at aist.go.jp (Luc Berthouze) Date: Wed, 2 Nov 2005 10:11:54 +0900 Subject: Connectionists: Call for papers - Workshop on Motor development (Bristol, UK, 3-6 April 2006) Message-ID: Call for Papers: Motor Development http://www.neurosci.aist.go.jp/~berthouz/MotDev.html April 5th-6th 2006 A symposium part of the AISB 2006 conference University of Bristol, Bristol, England Call for Papers The motor activity of an organism is one of its primary means of interacting with, and operating on, its environment. As such, its development is key to its cognitive development and, indeed, developmental psychology has shown both processes to be tightly coupled. In embodied robotics and cognitive modeling, however, these processes have been mostly treated in isolation with systems either evolving higher cognitive processes, or acquiring new motor skills. The motivation of this symposium is that understanding, and simulating, the mechanisms underlying motor development is necessary to implement an ecologically-balanced development of the system. This interdisciplinary symposium aims to bring together researchers from neuroscience, developmental psychology, computer science and robotics to examine the latest advances in the area, and delineate new strategies. Submissions We invite abstracts on any subject within the area of motor development. Areas of interest include but are not limited to: - Motor development in animals and humans: studies, models and theories - Motor development in robots: issues, models, experiments or simulations - Evolutionary developmental biology and motor development - Critical periods of motor development - Pathologies of motor development - Interplay between motor and cognitive development - Degree of freedom problem - U-shape development - Emergence of new skills - Role of caregiver in skill acquisition Accepted abstracts will be presented orally on the day and appear in the published workshop proceedings. Extended abstracts of between 1 and 2 pages should be submitted as PDF files to Luc.Berthouze at aist.go.jp by 13th January 2006. Selected papers will be invited for publication in a special issue of a journal. Further details will be available soon. Organiser Luc Berthouze, AIST Neuroscience Research Institute, Japan Programme Committee (confirmed members) Luc Berthouze, AIST Neuroscience Research Institute, Japan Yiannis Demiris, Imperial College, UK Eugene Goldfield, Children's Hospital Boston, USA Giorgio Metta, Genoa University, Italy Claes Van Hofsten, Uppsala University, Sweden Important dates Submissions of papers by : 13 Jan 06 Notification of decision: 01 Feb 06 Camera ready copies by: 20 Feb 06 Up-to-date information at: http://www.neurosci.aist.go.jp/~berthouz/ MotDev.html ------------------- Dr. Luc Berthouze, Senior Research Scientist, Neuroscience Research Institute (AIST 2) Umezono 1-1-1, Tsukuba 305-8568, Japan Tel: +81-298-61-5369 Fax: +81-298-61-5841 Email: Luc.Berthouze at aist.go.jp From chengsoon.ong at tuebingen.mpg.de Wed Nov 2 05:21:55 2005 From: chengsoon.ong at tuebingen.mpg.de (Cheng Soon Ong) Date: Wed, 2 Nov 2005 11:21:55 +0100 Subject: Connectionists: Machine Learning Tools Satellite Workshop (4 Dec 2005) Message-ID: <172FB4A4-022B-4D32-99AC-D162C49D1B22@tuebingen.mpg.de> Machine Learning Tools Satellite Workshop A satellite workshop on machine learning tools, collocated with NIPS, held in Vancouver(B.C.) on December 4, 2005. (website) http://lineal.developer.nicta.com.au/support/workshops/ (mirror) http://www.fml.mpg.de/MLPython Workshop Description The aim of this meeting is to discuss the requirements and design of an open source machine learning toolbox. Recently, there has been a collaborative effort among NICTA Canberra, MPI Tuebingen, Fraunhofer Berlin, Fraunhofer Darmstadt, and INSA de Rouen to develop such a toolkit codenamed LINEAL and ELEFANT. This set of tools uses Python as an interface language and currently uses PETSc as a numerical back end. The workshop is for the collaborators to investigate the different strategies for developing the toolbox. We would appreciate an email to SVN Vishwanathan at (SVN -dot- Vishwanathan -at- nicta.com.au) if you are interested in attending the meeting. From mdorigo at ulb.ac.be Wed Nov 2 14:23:47 2005 From: mdorigo at ulb.ac.be (Marco DORIGO) Date: Wed, 2 Nov 2005 20:23:47 +0100 Subject: Connectionists: ANTS 2006 Call for Papers Message-ID: *** Apologies if you have received this CFP more than once *** ANTS 2006 Fifth International Workshop on Ant Colony Optimization and Swarm Intelligence September 4-7, 2006. Brussels, Belgium Call for papers prepared on October 31, 2005 Short version ANTS 2006 solicits contributions dealing with any aspect of swarm intelligence including ant colony optimization, particle swarm optimization, and swarm robotics. More details and up-to-date information at http://iridia.ulb.ac.be/ants2006 Workshop proceedings will be published by Springer in the LNCS series. Important Dates =============== Title and abstract deadline Mar 12, 2006 Submission deadline Mar 19, 2006 Notification of acceptance May 21, 2006 Camera ready copy June 4, 2006 ANTS 2006 Workshop Committee ============================ General Chairs Marco Dorigo, IRIDIA, ULB, Brussels, Belgium Luca M. Gambardella, IDSIA, USI-SUPSI, Manno, Switzerland Technical Program Chairs Alcherio Martinoli, EPFL, Lausanne, Switzerland Riccardo Poli, University of Essex, UK Thomas Stuetzle, IRIDIA, ULB, Brussels, Belgium Publication Chair Mauro Birattari, IRIDIA, ULB, Brussels, Belgium Sponsors ======== AntOptima http://www.antoptima.com Comp2Sys, Marie Curie Early Stage Training Site http://iridia.ulb.ac.be/comp2sys French Community of Belgium (through the research project ANTS) http://www.cfwb.be IEEE Computational Intelligence Society (as a technical co-sponsor) http://www.ieee-cis.org -- ========================================================================== Marco Dorigo, Ph.D. mdorigo@(no.spam)ulb.ac.be Directeur de Recherches du FNRS http://iridia.ulb.ac.be/~mdorigo/ IRIDIA CP 194/6 Universite' Libre de Bruxelles Tel +32 (0)2 6503169 Avenue Franklin Roosevelt 50 GSM +32 478 301233 1050 Bruxelles Fax +32 (0)2 6502715 Belgium Sec +32 (0)2 6502729 ========================================================================== From anderson at CS.ColoState.EDU Thu Nov 3 14:41:43 2005 From: anderson at CS.ColoState.EDU (Chuck Anderson) Date: Thu, 03 Nov 2005 12:41:43 -0700 Subject: Connectionists: tenure-track faculty position in Dept. of Computer Science at Colorado State University Message-ID: <436A67F7.9060300@cs.colostate.edu> Tenure-Track Faculty Position Department of Computer Science Colorado State University Position Description RESPONSIBILITIES The candidate is expected to teach undergraduate and graduate courses in computer science, advise undergraduate and graduate students, perform research, and make a service contribution to the department, the university, and professional community. QUALIFICATIONS A successful candidate must: - Have earned a doctorate in computer science, computer engineering, or a related field. - Have the potential for excellence in research and teaching. - Have a research perspective that is consistent with the department's emphasis on collaborative and interdisciplinary research. - Have a research specialty that is consistent with the department's needs and interests. Candidates for appointments above the level of assistant professor must demonstrate a strong connection to ongoing department research. EMPLOYMENT CONDITIONS This nine-month, full-time position will carry a salary commensurate with qualifications. This appointment will be preferably made at the level of assistant professor. The department has 18 tenure-track faculty, 150 M.S. and Ph.D. students, and 275 undergraduate majors. Areas of research emphasis include artificial intelligence (bioinformatics, computer vision, evolutionary computation, machine learning, planning), software engineering (formal methods, program comprehension, reliability, testing), networks, parallel and distributed computing (embedded systems, reconfigurable architectures), and security. Colorado State University with an enrollment of 25,000 students is located in Fort Collins, Colorado, an attractive community of over 134,000 people, at the base of the Front Range of the Rocky Mountains, 65 miles north of Denver. The northern Front Range offers a wide range of outdoor recreational activities. More information about the department, its research programs, and applying for this position can be obtained from the department's home page at http://www.cs.colostate.edu From malchiodi at dsi.unimi.it Thu Nov 3 10:39:26 2005 From: malchiodi at dsi.unimi.it (Dario Malchiodi) Date: Thu, 3 Nov 2005 16:39:26 +0100 Subject: Connectionists: ICHSA workshop: new paradigms for hybrid learning systems Message-ID: <03D43245-4C80-11DA-BE0E-0003939B3D3E@dsi.unimi.it> ????????? Sorry, if you received this message more than once. ???? Feel free to distribute it to those who might be interested. ################################################################ CALL FOR CONTRIBUTIONS WORKSHOP ON NEW PARADIGMS FOR HYBRID LEARNING SYSTEMS http://laren.dsi.unimi.it/new_paradigm within the International Conference on Hybrid Systems and Applications (ICHSA 2006) May 24th 2006, The University of Louisiana, Lafayette, LA, USA http://cos.fit.edu/math/ichsa/ Submission deadline: February 15th 2006 ################################################################ Organizers: ------------ * Bruno Apolloni, University of Milano http://laren.dsi.unimi.it/apolloni * Zong Sha, Chinese Institute of electronics,Beijing, China zsha at public.bat.net.cn, z.sha at ieee.org * Dario Malchiodi, University of Milano http://homes.dsi.unimi.it/~malchiod Besides the common dichotomy between subsymbolic learning systems such as neural networks and symbolic systems such as decision trees, and their various forms of hybridization, new algorithms are raising for learning, sharing features of both symbolic and subsymbolic paradigms. Of classification algorithms like SVM or feature extraction algorithms like ICA you cannot say to be completely symbolic since the kernels/non gaussianity measures selection must be drawn by data in a non direct way -- guessed in any way -- while the goal they optimize is an explicit function of the parameters they aim to learn. In very broad terms the object of this special session is to gather various approaches to learning, where the distinction between what comes from axiomatic theories and what is left to the ability of the learner and his heuristics is untenable. Rather we may distinguish between different strategies with which the users organize past data in order to face their continuation. Contributions: -------------- As it is, the scope of this special session is open to the contribution of researchers in many fields, ranging from statistics to granular computing, neural networks, evolutionary computation, computational learning and so on. A definite preference is for non conventional approaches, provided a clear rationale and either formal proofs or stringent numerical results are supplied. We expect extended abstracts six to eight pages long without special format. Authors of the accepted contributions will be invited to submit a paper in the format requested by the conference proceedings? editor. Please submit extended abstracts to new_paradigms at dsi.unimi.it within February 15th 2006. Important dates: ------------------- February 15th 2006 Submission deadline March 15th 2006 Notification of acceptance April 15th 2006 Camera ready papers deadline May 22nd 2006 Conference From biehl at physik.uni-wuerzburg.de Fri Nov 4 03:16:58 2005 From: biehl at physik.uni-wuerzburg.de (Michael Biehl) Date: Fri, 4 Nov 2005 09:16:58 +0100 (CET) Subject: Connectionists: PhD position available, Groningen/NL Message-ID: PhD position available A Ph.D. fellowship for non-Dutch citizens is available in field of Machine Learning at the University of Groningen, Department of Computing Science. The fellowship is for a period of four years and amounts to (currently) 1340 Euros (tax free) per month. The aim of the project is two-fold: (a) to gain a better theoretical understanding of prototype based learning in systems with many degrees of freedom (b) the design and application of optimized or novel training algorithms in the context of real world problems (e.g. medical images or data). The focus will be on prototype-based techniques of unsupervised Vector Quantization, Neural Gas algorithms and Self-organizing Maps, as well as on supervised algorithms for Learning Vector Quantization (LVQ). Candidates should have a strong interest in theory and mathematics. A background in theoretical physics (statistical mechanics) would be a big plus, but is not required. Before applying, please check out publications and try to get an impression of our on-going research. Brief descriptions of our projects and preprints are available from http://www.cs.rug.nl/~biehl Please feel free to contact me (see below) if you have further questions about the post and the project. Interested candidates should send their application (through e-mail in pdf-format or hardcopies by mail) to Dr. Michael Biehl University of Groningen Dept. of Mathematics and Computing Science Blauwborgje 3 9747 AC Groningen The Netherlands m.biehl at rug.nl From gcc at cmp.uea.ac.uk Fri Nov 4 09:06:54 2005 From: gcc at cmp.uea.ac.uk (gcc@cmp.uea.ac.uk) Date: Fri, 4 Nov 2005 09:06:54 GB Subject: Connectionists: Predictive Uncertainty Competition for IJCNN-2006 Message-ID: <200511040906.jA496sGB026955@s5.cmp.uea.ac.uk> Dear Connectionists, there will be a second competition at IJCNN-2006 (http://www.wcci2006.org/) involving "predictive uncertainty in environmental modelling", with a special session devoted to papers describing the best methods. The aim is to create regression models that provide an estimate of the uncertainty of their predictions, e.g. error-bars, with models being evaluated according to the negative log-likelihood on the test data. This is particularly important for environmental problems, which are typically rather noise, often have non-Gaussian noise processes and the uncertainty in predictions is useful in estimating the impacts of e.g. increased rainfall on flooding. The competition has the same format as the Pascal Predictive Uncertainty Challenge (http://predict.kyb.tuebingen.mpg.de/), so those competing in the regression section of that exercise will have models they can deploy immediately. The competition web site is at http://theoval.cmp.uea.ac.uk/~gcc/competition/ Please do not hesitate to contact me if you have any questions or comments. best regards Gavin Cawley School of Computing Sciences University of East Anglia Norwich NR4 7TJ, U.K. From doya at irp.oist.jp Mon Nov 7 13:37:42 2005 From: doya at irp.oist.jp (Kenji Doya) Date: Tue, 8 Nov 2005 03:37:42 +0900 Subject: Connectionists: Postdoctoral Fellow and Investigator Positions, OIST In-Reply-To: <5.1.1.6.0.20051005153429.031869f0@pop.isc.cnrs.fr> References: <5.1.1.6.0.20051005153429.031869f0@pop.isc.cnrs.fr> Message-ID: <46e32594f98e94a7f9fb00aebfc2d66c@irp.oist.jp> We are building a new graduate institute in Okinawa, a southern island known for its beautiful ocean and rich traditional culture. We are seeking postdocs and junior faculty who are interested in interdisciplinary research and starting up a totally new university. My group is working on reinforcement learning and Bayesian algorithms, rodent experiments on decision and neuromodulation, and 'cyber rodent' experiments on learning and evolution. If you are interested in this opportunity, please apply by the following. Best wishes, Kenji Doya **** Okinawa Institute of Science and Technology Postdoctoral Fellows & Investigators The Okinawa Institute of Science and Technology, a new International Graduate University in Okinawa, has established a Research Initiative with a number of Research Groups. We are seeking postdoctoral fellows in the areas of Molecular Cell Biology, Molecular Cellular Neuroscience, Computational and Experimental Neurobiology to join the following groups: Neural Computation: Dr. K. Doya Experimental studies of Learning and Memory: Dr. S. Endo G0-cell: Yeast Cell Cycle: Dr. M. Yanagida Molecular Neuroscience: Dr. S. Brenner, Dr. I. Maruyama, Dr. T. Naito In addition, we have several openings for investigators with independent research projects in these areas. Applicants for Postdoctoral fellowships should send their CV's, a description of their area of research interest, and the names of two references. Applicants for Investigator positions should, in addition, provide a brief outline (1000 words) of the research that they would like to carry out and the resources required for it. Successful candidates will be invited to present more detailed proposals. The research groups are at present housed in well-equipped temporary laboratories and a major construction program for the new University is underway. Post doctoral fellows will be appointed for two years in the first instance with the possibility of renewal. Investigators will receive renewable 5-year appointment as well as the resources required for their research. Further details about the Institute can be viewed on our website (www.oist.jp) which also has the last research report. Please send your resumes by e-mail, fax, or postal mail to: Human Resources Department Okinawa Institute of Science and Technology 12-22 Suzaki, Uruma-shi, Okinawa 904-2234, Japan. e-mail: careers at irp.oist.jp fax: +81-98-934-844 ---- Kenji Doya Initial Research Project, Okinawa Institute of Science and Technology 12-22 Suzaki, Uruma, Okinawa 904-2234, Japan Phone:+81-98-921-3843; Fax:+81-98-921-3873 http://www.irp.oist.jp/nc From girolami at dcs.gla.ac.uk Tue Nov 8 09:45:03 2005 From: girolami at dcs.gla.ac.uk (Mark Girolami) Date: Tue, 8 Nov 2005 14:45:03 -0000 Subject: Connectionists: PhD Studentship in Machine Learning Available Message-ID: A fully funded, industry sponsored, three year PhD studentship (fees & stipend) is now available, with immediate start, within the Department of Computing Science at the University of Glasgow which is internationally recognised for its research and was rated 5 in the 2001 Research Assessment Exercise. The proposed PhD will investigate how advanced Machine Learning and Statistical Pattern Recognition methods may assist in the self-service environment, particularly using diverse heterogeneous data to make optimal decisions. Recent theoretical and applied work in Machine Learning and the application of Bayesian Inference in Machine Learning (particularly involving kernel methods such as Support Vector Machines, Gaussian Processes and Relevance Vector Machines) has attempted to address the problem of combining heterogeneous data to provide an improved prediction or classification decision. It is anticipated that the student will investigate the role that Machine Learning and Statistical Pattern Recognition can play in providing possible solutions to this particular problem. This is an outstanding opportunity to work on a research project with direct links to industrial issues and work with an international IT company. Appropriate academic backgrounds include Engineering, Physics, Mathematics, Statistics and Computing Science. Interested applicants should contact Dr Mark Girolami (girolami at dcs.gla.ac.uk) in the first instance for further information regarding this studentship. Mark Girolami PhD Bioinformatics Research Centre Department of Computing Science A416, Fourth Floor, Davidson Building University of Glasgow Glasgow G12 8QQ Scotland UK Tel : +44 (0)141 330 8628 Fax: +44 (0)141 330 8627 email : girolami at dcs.gla.ac.uk http://www.dcs.gla.ac.uk/~girolami/ From erik at tnb.ua.ac.be Thu Nov 10 08:55:43 2005 From: erik at tnb.ua.ac.be (Erik De Schutter) Date: Thu, 10 Nov 2005 14:55:43 +0100 Subject: Connectionists: Neuro-IT Cerebellar Modeling Workshop Fellowships Message-ID: <28B642D4-874F-4872-8BA5-C2E640A435C7@tnb.ua.ac.be> A limited number of 200 euro student fellowships to cover accommodation costs will be available for the two-day cerebellar modeling workshop at the University of Antwerp, Belgium on December 5-6, 2005. Interested master or PhD students coming from outside of Belgium (maximum one for a research group) can apply for a fellowship when registering for the workshop. Invited speakers include N. Brunel (Paris, France, G. Chauvet (Angers, France), E. d'Angelo (Pavia, Italy), C. Darlot (Paris, France), P. Dean (Sheffield, UK), E. De Schutter (Antwerp, Belgium), C. De Zeeuw (Rotterdam, Netherlands), M. Hausser (London, UK), R. Maex (Antwerp, Belgium), A. Silver (London, UK), P. Verschure (Zurich, Switzerland), Y. Yarom (Jerusalem, Israel). Full program and (free) registration can be found at http:// www.neuroinf.org/workshop/neuroit05/ From dayan at gatsby.ucl.ac.uk Fri Nov 4 04:25:57 2005 From: dayan at gatsby.ucl.ac.uk (Peter Dayan) Date: Fri, 4 Nov 2005 09:25:57 +0000 Subject: Connectionists: Gatsby faculty recruitment Message-ID: <20051104092557.GA21636@flies.gatsby.ucl.ac.uk> The Gatsby Computational Neuroscience Unit at UCL is looking to recruit one or more faculty at senior and/or junior levels in machine learning, statistics or control theory. We are especially interested in candidates whose work in these fields integrates well with the Unit's focus on inference and learning in the brain, and with the wider research environment at UCL. The Computer Science Department at UCL is in conjunction recruiting for a senior faculty position to act as a Director for a proposed UCL Centre for Computational Statistics and Machine Learning, reflecting the substantial cross-campus links in this area. 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 (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 2006. Unless otherwise requested applicants will also be considered by the Computer Science Department. Appointment at a senior level is subject to the normal senior appointments process at UCL. For further information, please see www.gatsby.ucl.ac.uk; for informal enquiries, please contact Peter Dayan at dayan 'at' gatsby.ucl.ac.uk Information about the Department of Computer Science and their recruitment is at http://www.cs.ucl.ac.uk and http://www.cs.ucl.ac.uk/vacancies From choe at cs.tamu.edu Wed Nov 9 01:43:01 2005 From: choe at cs.tamu.edu (Yoonsuck Choe) Date: Wed, 9 Nov 2005 00:43:01 -0600 (CST) Subject: Connectionists: CFP: NIP-LR Special Issue on Bio-Inspired Models and Hardware Message-ID: [We apologize in advance in case you get this annoucement from multiple sources. Please redistribute as you see fit. Thanks!] /////////////////////////////////////////////////////////////////////// /// Call for Papers for a Special Issue of /// /// Neural Information Processing-Letters and Reviews /// /// on Bio-Inspired Models and Hardware /// /////////////////////////////////////////////////////////////////////// As announced earlier at the International Workshop on Biologically Inspired Models and Hardware (BIMH2005, http://www.bimh2005.org), a post-conference workshop at IJCNN2005 (Montreal, Canada), Neural Information Processing-Letters and Reviews (NIP-LR) is preparing a special issue on biologically-inspired models and hardware for human-like intelligent functions. Although artificial neural networks are inspired by information processing mechanisms in the brain, there still exists a big gap between biological neural networks and their artificial counterpart. To have more intelligent characteristics incorporated into artificial neural systems, we need to rely more on biologically inspired models and hardware. In this special issue of NIP-LR, we invite contributions on biologically plausible hardware systems and models with more human-like intelligent characteristics that can help deal with real-world problems. Relevant topics for this special issue include, but are not limited to: o Models of the auditory pathway o Models of the visual pathway o Models of cognition, learning, and inference o Models of attention, emotion, and consciousness o Models of autonomous behavior o Hardware implementation of bio-inspired models o Engineering applications of bio-inspired models For more information on the special issue for NIP-LR, please visit: http://www.nip-lr.info Submission instruction: Papers should be emailed as a PDF attachment to the guest editors Yoonsuck Choe (choe at tamu.edu) and Minho Lee (mholee at knu.ac.kr). Important dates: December 15, 2005: Submission Deadline February 15, 2006: Deadline for the Reviews February 28, 2006: Notification of Acceptance/Rejection. March 2006: Publication, as a combined February-March Issue. Copyright: Authors will maintain all rights to their papers, and may subsequently publish extended versions of their papers in other journals. Yoonsuck Choe, Assistant Professor Minho Lee, Associate Professor Texas A&M University, USA Kyungpook National University, Korea choe at tamu.edu, 1-979-845-5466 mholee at knu.ac.kr, 82-53-950-6436 From Gunnar.Raetsch at tuebingen.mpg.de Thu Nov 10 09:51:04 2005 From: Gunnar.Raetsch at tuebingen.mpg.de (=?ISO-8859-1?Q?Gunnar_R=E4tsch?=) Date: Thu, 10 Nov 2005 15:51:04 +0100 Subject: Connectionists: =?iso-8859-1?q?2_Group_Leader_positions_at_the_Fr?= =?iso-8859-1?q?iedrich_Miescher_Laboratory_in_T=FCbingen_?= Message-ID: <072F5710-2438-443B-9411-2E6AE6DD1500@tuebingen.mpg.de> The Max Planck Society invites applications for 2 Independent Junior Group Leader positions at the Friedrich Miescher Laboratory in T?bingen, Germany The Friedrich Miescher Laboratory (FML) in T?bingen has openings for two Independent Junior Group Leaders (W2; equivalent to associate professor level without tenure). The FML is an institution of the Max Planck Society hosting four Independent Junior Research Groups, which work in different disciplines related to the broad spectrum of research represented in the Biomedical Section of the Max Planck Society. The groups share equipment and jointly manage the organization of the laboratory. These special conditions and the close interaction between the groups make for a very active and lively research atmosphere. For more information see http://www.fml.tuebingen.mpg.de. The FML is part of the Max Planck Campus in T?bingen (http://www.tuebingen.mpg.de), which also hosts the Max Planck Institutes for Developmental Biology and Biological Cybernetics. While there is no restriction on the research area, there is the expectation that the successful candidates will interact synergistically with other groups and departments on the campus. Current fields of research include cell biology, biochemistry and structural biology, developmental genetics, evolutionary biology, computational biology, as well as machine learning, neuroscience, and psychophysics. Moreover, the University of T?bingen is a highly active center for biomedical research and there are many opportunities for interaction. Funding includes one Postdoc position, one PhD scholarship and one Technical Assistant position, as well as running costs and a competitive startup package. The exact conditions will depend on the field of research and experience. The group leader position and funding is guaranteed for five years with the possibility of extension. The Max Planck Society is an equal opportunity employer and wishes to increase the share of women in areas in which they are underrepresented. Application requirements are detailed on http://www.snwg.mpg.de. The deadline for application is December 20, 2005. Further information can be obtained from Gunnar R?tsch http://www.fml.tuebingen.mpg.de/ raetsch Friedrich Miescher Laboratory Gunnar.Raetsch at tuebingen.mpg.de Max Planck Society Tel: (+49) 7071 601 820 Spemannstra?e 39, 72076 T?bingen, Germany Fax: (+49) 7071 601 455 From pascal.fua at epfl.ch Mon Nov 7 22:29:32 2005 From: pascal.fua at epfl.ch (Pascal Fua) Date: Tue, 08 Nov 2005 04:29:32 +0100 Subject: Connectionists: Open faculty positions at EPFL Message-ID: <43701B9C.7060706@epfl.ch> Hello, EPFL has open faculty positions in Computer Science and is looking for candidates with an interest in machine learning. See full text of the add below from the http://professeurs.epfl.ch/Jahia/site/professeurs/op/preview/pid/57801?matrix=1127201488194 web site. Would it be possible to post it on your site? Regards Pascal Faculty Positions in Computer Science The School of Computer and Communication Sciences at EPFL invites applications for faculty positions in computer science. We are primarily seeking candidates for tenure-track assistant professor positions, but suitably qualified candidates for senior positions will also be considered. Successful candidates will develop an independent and creative research program, participate in both undergraduate and graduate teaching, and supervise PhD students. Candidates from all areas of computer science will be considered, but preference will be given to candidates with interests in algorithms, graphics-related areas, machine learning, design methodologies for integrated systems, and foundations and applications of verification. Significant start-up resources and research infrastructure will be available. We offer internationally competitive salaries and benefits. To apply, please follow the application procedure at http://icrecruiting.epfl.ch. The following documents are requested in PDF format: curriculum vitae, including publication list, brief statements of research and teaching interests, names and addresses (including e-mail) of 3 references for junior positions, and 6 for senior positions. Screening will start on January 15, 2006. Further questions can be addressed to: Professor Willy Zwaenepoel Dean School of Computer and Communication Sciences EPFL CH-1015 Lausanne, Switzerland recruiting.ic at epfl.ch For additional information on EPFL, please consult http://www.epfl.ch EPFL is an equal opportunity employer. -- -------------------------------------------------------------------- Prof. P. Fua (Pascal.Fua at epfl.ch) Tel: 41/21-693-7519 FAX: 41/21-693-7520 Url: http://cvlab.epfl.ch/~fua/ -------------------------------------------------------------------- From moodylab at icsi.berkeley.edu Thu Nov 10 18:02:47 2005 From: moodylab at icsi.berkeley.edu (John Moody) Date: Thu, 10 Nov 2005 15:02:47 -0800 Subject: Connectionists: Program: Machine Learning in Finance Message-ID: <10b7069b0511101502m7dbafa16p7b937a025c6f7ba4@mail.gmail.com> MACHINE LEARNING IN FINANCE Westin Resort, Whistler, BC December 9, 2005 WORKSHOP PROGRAM: The program for Machine Learning in Finance is now available. For program, hotel and registration information, please see: http://www.icsi.berkeley.edu/~moody/MLFinance2005.htm WORKSHOP DESCRIPTION: Machine learning (ML) and related methods have produced some of the financial industry's most consistently profitable proprietary trading strategies during the past 20 years. With markets, trade execution and financial decision making becoming more automated and competitive, practitioners increasingly recognize the need for ML. This workshop brings together researchers from machine learning, academic finance and the financial industry to discuss problems in finance where ML may provide an edge. ML themes include reinforcement learning, optimization methods, recurrent and state space models, on-line algorithms, evolutionary computing, kernel methods, bayesian estimation, wavelets, neural nets, SVMs, boosting and multi-agent simulation. Financial topics include high frequency data, trading strategies, execution models, forecasting, volatility, extreme events, credit risk, portfolio management, yield curve estimation, option pricing, and selection of indicators, models and equilibria. From b.graham at cs.stir.ac.uk Fri Nov 11 03:53:25 2005 From: b.graham at cs.stir.ac.uk (b.graham@cs.stir.ac.uk) Date: Fri, 11 Nov 2005 08:53:25 -0000 (GMT) Subject: Connectionists: Postdoc in computational neuroscience Message-ID: <1055.213.78.119.123.1131699205.squirrel@www.cs.stir.ac.uk> Dear all, The following postdoc position in computational neuroscience is now available in my laboratory at the University of Stirling in Scotland. Bruce Graham ----------------------------------------------------------------- SITUATION VACANT DEPARTMENT OF COMPUTING SCIENCE AND MATHEMATICS UNIVERSITY OF STIRLING, SCOTLAND, U.K. RESEARCH ASSISTANT (?20,044 - ?30,002p.a.) Research Assistant post to work on a BBSRC funded project concerning ?Changes in information transmission at an auditory synapse in the binaural pathway during short-term synaptic modulation?. The information required for sound source localization is carried in the firing times of neurones in brain stem auditory nuclei. These neurones exhibit synaptic and cellular specializations that contribute to precisely timed electrical signalling. The project will investigate the information transmission characteristics of the glutamatergic calyx of Held synapse in the mammalian MNTB using a combination of mathematical modelling, computer simulation and physiological experiments. This post, to be held in the laboratory of Dr Bruce Graham at the University of Stirling, involves carrying out the modelling and computer simulation work. This will be based on data from physiological experiments being carried out by another RA funded by this BBSRC award, in the laboratory of Prof. Ian Forsythe at the University of Leicester. There are travel funds for research visits between the two laboratories. The overall objective is to determine whether multiple forms of short term synaptic modulation interact to alter, and perhaps optimise, information transmission through this pathway in response to behaviourally-relevant sound stimuli, tuning it to aid in sound source localization. This project is an exciting opportunity for a mathematician / computer scientist to gain experience of neuroscience. You will have a PhD in Mathematics / Computing Science or be shortly about to complete such a PhD. You will be familiar with numerical mathematics, information theory, and dynamic and stochastic systems. You should also have proven computer programming ability in a high-level language such as Java or C++. Knowledge of MATLAB and the NEURON simulation package would be highly beneficial. You should have a willingness to learn sufficient neuroscience to understand the system being studied. Depending on experience, up to a 20 month appointment will be made on the Research Staff Salary Scale at point 6: a maximum of ?22,289 p.a. The successful candidate will be expected to take up the position by the beginning of January 2006, or as soon as possible thereafter. Informal enquiries may be made to Dr Bruce Graham: Tel: 01786 467432, Fax: 01786 464551 or e-mail b.graham at cs.stir.ac.uk, from whom further details of the project can be obtained. Further Particulars are available from the HR Services Office, University of Stirling, Stirling, FK9 4LA. Tel: (01786) 467028, Fax: (01786) 466155, e-mail hr-services at stir.ac.uk Closing date for applications: Monday 28th November 2005 Reference No. 11643/4134 www.hr-services.stir.ac.uk AN EQUAL OPPORTUNITIES EMPLOYER -- Dr Bruce Graham, Reader (b.graham at cs.stir.ac.uk) Dept. of Computing Science and Mathematics, University of Stirling, Stirling FK9 4LA phone: +44 1786 467 432 fax: +44 1786 464 551 -- The University of Stirling is a university established in Scotland by charter at Stirling, FK9 4LA. Privileged/Confidential Information may be contained in this message. If you are not the addressee indicated in this message (or responsible for delivery of the message to such person), you may not disclose, copy or deliver this message to anyone and any action taken or omitted to be taken in reliance on it, is prohibited and may be unlawful. In such case, you should destroy this message and kindly notify the sender by reply email. Please advise immediately if you or your employer do not consent to Internet email for messages of this kind. From baolshausen at berkeley.edu Fri Nov 11 12:16:26 2005 From: baolshausen at berkeley.edu (Bruno Olshausen) Date: Fri, 11 Nov 2005 12:16:26 -0500 Subject: Connectionists: Tenure-track position - UC Berkeley Message-ID: <4374D1EA.7040906@berkeley.edu> The Helen Wills Neuroscience Institute together with the Department of Physics at UC Berkeley intend to make a joint tenure-track appointment, effective July 1, 2006. The search is broadly defined and could range from experimental biophysics to theoretical approaches. The full details may be obtained from: http://neuroscience.berkeley.edu/job_openings.php Berkeley has a strong neuroscience program, and with the recent establishment of the Redwood Center for Theoretical Neuroscience (http://redwood.berkeley.edu) it also now has a strong contingent pursuing theoretical and computational approaches. Note the application deadline is soon: ** November 23, 2005 ** -- Bruno A. Olshausen Director, Redwood Center for Theoretical Neuroscience and Associate Professor, Helen Wills Neuroscience Institute and School of Optometry, UC Berkeley 132 Barker Hall, #3190, Berkeley, CA 94720-3190 (510) 643-1472 / 4952 (fax) http://redwood.berkeley.edu From ahirose at ee.t.u-tokyo.ac.jp Fri Nov 18 02:50:54 2005 From: ahirose at ee.t.u-tokyo.ac.jp (Akira Hirose) Date: Fri, 18 Nov 2005 16:50:54 +0900 Subject: Connectionists: CFP: WCCI'06-IJCNN'06 Special Session on Complex-Valued Neural Networks In-Reply-To: <437D8697.5070800@ee.t.u-tokyo.ac.jp> References: <4379B2EB.1060107@eis.t.u-tokyo.ac.jp> <437D8697.5070800@ee.t.u-tokyo.ac.jp> Message-ID: <437D87DE.5060600@ee.t.u-tokyo.ac.jp> Call For Papers: WCCI-IJCNN 2006 Special Session on Complex-Valued Neural Networks Organized by Akira Hirose URL: http://www.eis.t.u-tokyo.ac.jp/ ============================================== Scope: The complex-valued neural networks (CVNNs) have been widening the scope of applications not only in electronics and informatics, but also in social systems. The fields are, namely, optoelectronics, imaging, remote sensing, quantum neural devices and systems, intelligent transport systems, and so on. One of the most important characteristics of the CVNNs is the proper treatment of complex-amplitude information, e.g., the treatment of wave-related / rotation-related phenomena such as electromagnetism, lightwaves, quantum waves, oscillatory phenomena even including traffic signal control, and color image processing based on adaptive signal rotation in the RGB space. Recently there were several CVNN Special Sessions (SSs) in, for example, KES 2001-2003, ICONIP 2002 Singapore, ICANN/ICONIP 2003 Istanbul, and ICONIP 2004 Calcutta, where we had large audience and enjoyed heated and encouraging discussions successfully. The series indicates the increasing importance of this new area. Now we hold a SS in the WCCI for a wider audience, including fuzzy and evolutionary researchers, to develop further investigations both in theoretical and application fields. We will present the latest results and considerations, and discuss prospective possibilities of the CVNNs. Papers that are, or might be, related to the CVNNs are widely solicited. Topics include, but are not limited to: * Complex-Valued Neuron Dynamics * Complex-Valued Associative Memories * Chaos in Complex Domain * Spatiotemporal CVNN Processing * CVNN-based Two-dimensional Information Transform * CVNN-based Periodic Information Processing * Fourier Domain CVNN Processing * Phase-Sensitive Radar Signal Processing * Coherent Optoelectronic Applications * Speech, Sonic and Ultrasonic Applications * Adaptive Quantum Devices * Quantum Computation and Quantum Neural Networks * CVNNs in Color Image Processing * CVNNs in Traffic Control * CVNNs in Robotics * Quaternion and Clifford Networks ============================================= From zhaoping at gatsby.ucl.ac.uk Sun Nov 20 16:38:13 2005 From: zhaoping at gatsby.ucl.ac.uk (Dr Zhaoping Li) Date: Sun, 20 Nov 2005 21:38:13 +0000 (GMT) Subject: Connectionists: Postdoc job in vision in London UK Message-ID: Applications are invited for the post of Postdoctoral Research Fellow to work with Dr. Li Zhaoping (http://www.gatsby.ucl.ac.uk/~zhaoping) in the area of neuroscience, particularly on biological vision, using theoretical and/or psychophysical investigation tools. The candidate should have good experience in theoretical/modeling areas or in visual psychophysical area. Interest and capability to engage in research activities in both areas would be preferable although not essential. The research fellow is expected to contribute to the research environment of the laboratory and should have the capability to work well in a team. The post is available Jan 2006. Salary is on the RA1A scale (£25,622-£32,442 including London allowance) and will depend upon qualifications and experience. Applications (email or hard copy ) by cover letter, CV and Personal Information form (the latter available at http://www.psychol.ucl.ac.uk/info/Personal_Information.doc) to: John Draper Departmental Administrator Department of Psychology UCL Gower Street London WC1E 6BT j.draper at ucl.ac.uk If applying by email please submit all requested information in one .pdf file names by your surname eg Smith.pdf. Further information concerning the post are on the web at http://www.psychol.ucl.ac.uk/info/psychophysics_li.htm while interested candidates can also contact Li Zhaoping, z.li at ucl.ac.uk 44 20 7679 1174 The closing date for the applications is Friday 2nd December 2005. --- sorry for the late posting, but please apply ASAP if interested, and we will continue to accept applications before the position is offered. From derdogmus at ieee.org Tue Nov 15 16:19:13 2005 From: derdogmus at ieee.org (Deniz Erdogmus) Date: Tue, 15 Nov 2005 13:19:13 -0800 Subject: Connectionists: CFP: Neurocomputing Special Issue on Advances in Blind Signal Processing Message-ID: <437A50D1.20905@ieee.org> Dear Connectionists, Please take note of this special issue that aims to bring together the latest results in BSP. The CFP preprint can be downloaded at the following address: http://www.csee.ogi.edu/~deniz/NEUCOM_CFP.pdf Best, Deniz Erdogmus From esann at dice.ucl.ac.be Sun Nov 20 15:23:21 2005 From: esann at dice.ucl.ac.be (esann) Date: Sun, 20 Nov 2005 21:23:21 +0100 Subject: Connectionists: extended deadline: ESANN'2006 European Symposium on Artificial Neural Networks Message-ID: <005401c5ee10$40fda7e0$43ed6882@maxwell.local> Due to numerous requests, the deadline to submit papers to the ESANN'2006 conference has been extended to December 6, 2005. 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'2006, The organizing committee. ===================================================== ESANN'2006 14th European Symposium on Artificial Neural Networks 14th European Symposium on Artificial Neural Networks Advances in Computational Intelligence and Learning Bruges (Belgium) - April 26-27-28, 2006 Announcement and call for papers ===================================================== Technically co-sponsored by the International Neural Networks Society, the European Neural Networks Society, the IEEE Computational Intelligence Society (to be confirmed), the IEEE Region 8, the IEEE Benelux Section. The call for papers for the ESANN'2006 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'2006 is organized in collaboration with the UCL (Universite catholique de Louvain, Louvain-la-Neuve) and the KULeuven (Katholiek Universiteit Leuven). 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'2006 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 organised 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 organised during ESANN'2006 are: 1) Semi-blind approaches for source separation and independent component analysis M. Babaie-Zadeh, Sharif Univ. Tech. (Iran), C. Jutten, CNRS ? Univ. J. Fourier ? INPG (France) 2) Visualization methods for data mining F. Rossi, INRIA Rocquencourt (France) 3) Neural Networks and Machine Learning in Bioinformatics - Theory and Applications B. Hammer, Clausthal Univ. Tech. (Germany), S. Kaski, Helsinki Univ. Tech. (Finland), U. Seiffert, IPK Gatersleben (Germany), T. Villmann, Univ. Leipzig (Germany) 4) Online Learning in Cognitive Robotics J.J. Steil, Univ. Bielefeld, H. Wersing, Honda Research Institute Europe (Germany) 5) Man-Machine-Interfaces - Processing of nervous signals M. Bogdan, Univ. T?bingen (Germany) 6) Nonlinear dynamics N. Crook, T. olde Scheper, Oxford Brookes University (UK) 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 November 28, 2005. 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, 2006; 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 November 28, 2005 Notification of acceptance January 27, 2006 Symposium April 26-28, 2006 Conference secretariat ---------------------- ESANN'2006 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 Pr?figure (F) Gianluca Bontempi Univ.Libre Bruxelles (B) Marie Cottrell Univ. Paris I (F) Jeanny H?rault INPG Grenoble (F) Bernard Manderick Vrije Univ. Brussel (B) Eric Noldus Univ. Gent (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) Peter Bartlett Univ.California, Berkeley (USA) 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 Technology (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) Mia Loccufier Univ. Gent (B) Erzsebet Merenyi Rice Univ. (USA) Jos? Mira UNED (E) 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) David Saad Aston Univ. (UK) 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) Michael Tipping Microsoft Research (Cambridge) (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) 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 girolami at dcs.gla.ac.uk Thu Nov 17 09:22:26 2005 From: girolami at dcs.gla.ac.uk (Mark Girolami) Date: Thu, 17 Nov 2005 14:22:26 -0000 Subject: Connectionists: Gaussian Process Classification Paper Available Message-ID: The following paper may be of interest to those working on devising efficient methods of approximate Bayesian inference for classification over multiple classes with Gaussian Processes. Title: Variational Bayesian Multinomial Probit Regression with Gaussian Process Priors. Authors: Mark Girolami and Simon Rogers, Department of Computing Science, University of Glasgow Abstract It is well known in the statistics literature that augmenting binary and polychotomous response models with Gaussian latent variables enables exact Bayesian analysis via Gibbs sampling from the parameter posterior. By adopting such a data augmentation strategy, dispensing with priors over regression coefficients in favour of Gaussian Process (GP) priors over functions, and employing variational approximations to the full posterior we obtain efficient computational methods for Gaussian Process classification in the multi-class setting. The model augmentation with additional latent variables ensures full a posteriori class coupling whilst retaining the simple a priori independent GP covariance structure from which sparse approximations, such as multi-class Informative Vector Machines (IVM), emerge in a very natural and straightforward manner. This is the first time that a fully Variational Bayesian treatment for multi-class GP classification has been developed without having to resort to additional explicit approximations to the non-Gaussian likelihood term. Empirical comparisons with exact analysis via MCMC and Laplace approximations illustrate the utility of the variational approximation as a computationally economic alternative to full MCMC and it is shown to be more accurate than the Laplace approximation. Available from: http://www.dcs.gla.ac.uk/people/personal/girolami/pubs_2005/VBGP/index.h tm To Appear Neural Computation, MIT Press From jeffyoshimi at yahoo.com Sun Nov 20 18:26:28 2005 From: jeffyoshimi at yahoo.com (Jeffrey Yoshimi) Date: Sun, 20 Nov 2005 15:26:28 -0800 Subject: Connectionists: Faculty Position at UC Merced Message-ID: <8A322C9F-71E2-4B49-8BA5-8FC86733EDF8@yahoo.com> All: UC Merced is currently hiring an Assistant Professor of Cognitive Science and Engineering. See: http://jobs.ucmerced.edu/view_academic_position.faces?positionId=300 It's an exciting place to be. UC Merced is the tenth campus of the University of California System, and the first new UC to be built in about 40 years. We just opened this year and are building a whole host of interdisciplinary programs, including cognitive science, from the ground up. Merced is 2 hours from the San Francisco Bay Area and 1.5 hours from Yosemite. Cheers! Jeff Yoshimi Assistant Professor and Founding Faculty University of California, Merced From neil at dcs.shef.ac.uk Fri Nov 18 06:29:26 2005 From: neil at dcs.shef.ac.uk (Neil Lawrence) Date: Fri, 18 Nov 2005 11:29:26 +0000 Subject: Connectionists: Postdoctoral position in Modelling Human Motion Message-ID: <437DBB16.9050404@dcs.shef.ac.uk> The following postdoc position in probabilistic modelling of human motion data is available at the University of Sheffield in the Department of Computer Science. Job Title: Postdoctoral Research Associate Job Location: Department of Computer Science University of Sheffield, U.K. Job Ref No: PR2250 Closing Date: 22nd December, 2005 Salary: 22,774 - 28,850 per annum Project Summary The focus of the work will be on the construction of probabilistic models for modelling human motion capture data. The project is a collaboration between Professor Philip Torr of Oxford Brookes University and Dr Neil Lawrence of Sheffield University. Applicants should have, or should be about to receive a PhD in a related area (e.g. machine learning, graphics, vision). The post is for a period of up to one year. The position is funded as a pump-priming project by the PASCAL European Network of Excellence. It is expected, as part of the project, that a submission for extended funding will be made through the EU or UK research councils with the successful applicant as a named research associate. Neil Lawrence will be available at NIPS to conduct informal interviews for interested candidates. Please e-mail neil at dcs.shef.ac.uk if you would like to discuss the position there. More details of the position are available at http://www.dcs.shef.ac.uk/~neil/postdoc1105.html From A.Cangelosi at plymouth.ac.uk Mon Nov 21 05:24:09 2005 From: A.Cangelosi at plymouth.ac.uk (Angelo Cangelosi) Date: Mon, 21 Nov 2005 10:24:09 -0000 Subject: Connectionists: Connection Science Special Issue on "The Emergence of Language: Neural Network and Adaptive Agent Models" Message-ID: <64997DB783F0FD4EB5550AD0D550E2290501DCA7@03-CSEXCH.uopnet.plymouth.ac.uk> Hello, Can you please forward this email to the Connectionist mailing lists? Thanks, Angelo Connection Science Journal Special Issue on "The Emergence of Language: Neural and Adaptive Agent Models" Volume 17, Issue 3-4, 2005 http://journalsonline.tandf.co.uk/(222bwz45frr1jz55wm1xfv45)/app/home/issue.asp?referrer=parent&backto=journal,1,34;linkingpublicationresults,1:100630,1 This special issue has two main aims. The first is to provide an up-to-date account of recent modeling studies of the emergence of language. This is achieved through the inclusion of papers reporting on the latest advances in robotics and computer simulation experiments on language emergence. This special issue includes papers on robotics and embodied systems (Nolfi, Yu, Dominey), adaptive multi-agent systems (Bartlett & Kazakov, Oudeyer, Kaplan) and connectionist simulations (Kuehn and Cruse, Mirolli & Parisi, van der Velde). The second aim is to identify the key research directions for the future. This is mainly achieved in the two invited papers by Brian MacWhinney and Luc Steels, in addition to specific research issues discussed in individual papers. TABLE OF CONTENT Editorial: The emergence of language: neural and adaptive agent models Angelo Cangelosi The emergence of linguistic form in time Brian MacWhinney The emergence and evolution of linguistic structure: from lexical to grammatical communication systems Luc Steels Emergence of communication in embodied agents: co-adapting communicative and non-communicative behaviours Stefano Nolfi Simple models of distributed co-ordination Fr?d?ric Kaplan The origins of syntax: from navigation to language Mark Bartlett and Dimitar Kazakov Emergence of grammatical constructions: evidence from simulation and grounded agent experiments Peter Ford Dominey How can we explain the emergence of a language that benefits the hearer but not the speaker? Marco Mirolli and Domenico Parisi The self-organization of combinatoriality and phonotactics in vocalization systems Pierre-yves Oudeyer Static mental representations in recurrent neural networks for the control of dynamic behavioural sequences Simone K?hn and Holk Cruse Modelling language development and evolution with the benefit of hindsight Frank Van Der Velde The emergence of links between lexical acquisition and object categorization: a computational study Chen Yu ---------------- Angelo Cangelosi, PhD ---------------- Reader in Artificial Intelligence and Cognition Adaptive Behaviour and Cognition Research Group School of Computing, Communications & Electronics University of Plymouth Portland Square Building (A316) Plymouth PL4 8AA (UK) E-mail: acangelosi at plymouth.ac.uk http://www.tech.plym.ac.uk/soc/staff/angelo (tel) +44 1752 232559 (fax) +44 1752 232540 From vgkabs at philippos.teikav.edu.gr Mon Nov 21 06:44:44 2005 From: vgkabs at philippos.teikav.edu.gr (Kaburlasos Vassilis) Date: Mon, 21 Nov 2005 13:44:44 +0200 Subject: Connectionists: Call For Papers: WCCI 2006 Special Session on "Computational Intelligence Based on Lattice Theory" Message-ID: <014b01c5ee90$f7b6f0b0$755e82c3@industrialwin.teikav.edu.gr> CALL FOR PAPERS 2006 IEEE Congress on Computational Intelligence (WCCI 2006) Vancouver, Canada, 16-21 July 2006 http://www.wcci2006.org/ FUZZ-IEEE approved special session on "Computational Intelligence Based on Lattice Theory" Organized by Vassilis G. Kaburlasos (Technological Educational Institution of Kavala), Gerhard X. Ritter (University of Florida), Michael Georgiopoulos (University of Central Florida) URL: http://iiu.teikav.edu.gr/users/vgkabs/WCCI2006.htm ============================================== Scope: Rooted in neural computing the employment of lattice theory emerges lately in computational intelligence with the potential to cross-fertilize several domains including, as well, fuzzy systems, machine learning, probabilistic reasoning, etc. Genetic algorithms are often employed for tuning performance. Lattice theory has already been used to improve analysis and design of popular neurocomputing paradigms. For instance, granular extensions of both Carpenter's fuzzy adaptive resonance theory (ART) and Kohonen's self-organizing maps (SOM) have been presented in the literature based on lattice theory. Lattice algebra is also employed in several computational intelligence domains. Another promising application for lattice theory is fuzzy inference systems. Furthermore, a "principled design" of a model based on disparate types of data (e.g. vectors of numbers, images, text structures, logical relations, concepts, (fuzzy) sets and graphs) can be pursued using lattice theory. Hence, lattice theory emerges as a sound foundation for unifying rigorously diversity in computational intelligence. This special session is meant as a forum for researchers with interests in computational intelligence applications of lattice theory. The objective is to present high-quality, state-of-the-art research results. An array of novel mathematical tools, design practices and real world applications will be presented. Emphasis is on system modeling, knowledge representation, data mining, and industrial/environmental applications. Topics of interest include but are not limited to . Lattice algebra neural networks . Fuzzy lattice neurocomputing . Fuzzy adaptive resonance theory . Fuzzy mathematical morphology . Fuzzy implications . Fuzzy similarity measures . Fuzzy system modeling . Probabilistic reasoning . Granular computing . Data mining . Lattice-interval/hyperbox learning . Disparate data fusion . Semantic Web . Knowledge representation . Formal concept analysis . Category theory ============================================= From popescu at prosun.first.fraunhofer.de Mon Nov 21 09:21:23 2005 From: popescu at prosun.first.fraunhofer.de (Florin Popescu) Date: Mon, 21 Nov 2005 15:21:23 +0100 Subject: Connectionists: post-doc position at Fraunhofer Institute FIRST Berlin Message-ID: <6.2.3.4.0.20051121151826.02eb9628@mailhost> The Fraunhofer-Institute FIRST in Berlin is searching for a Postdoc as Research Associate (m/f) A three-year fellowship is available for a researcher with 4-10 years research experience starting January 2005. The EC-funded BRAIN2ROBOT project will adapt the brain computer interface technology developed at the Berlin Brain Computer Interface (BBCI) Laboratory at Fraunhofer-FIRST-IDA (http://ida.first.fraunhofer.de, www.bbci.de) to restore reaching function in quadriplegic patients. The Marie Curie Excellence Team consists of 4 researchers, but work will be done in close collaboration with other IDA group members. The main focus of this fellowship would be to adapt and possibly improve the BBCI interface to the control of a robot, while producing innovative and tangible research. The candidate will be expected to have a strong computer science background, with competence in time series analysis, pattern recognition, machine learning, dynamical systems and complexity. Strong programming skills and theoretical skills grounded in mathematics are a must. A strong plus would be direct experience with electrophysiological signal analysis and neurophysiology. The working language of the laboratory is English. The yearly salary is ca. 3850Euro/month (before taxes and social security). Preference will be given to nationals of EU member states (other than Germany) and nationals of EU associated states. International candidates will also receive mobility and travel allowances of up to approx. 9300 Euro per annum depending on current residency and family status. Please send your CV, cover letter and a sample of published work to (in your letter or email, refer to job number FIRST-113-05-003): Fraunhofer-Gesellschaft Zentrale-Hauptabteilung Personal Frau Rabel Kekulstr. 7, 12489 Berlin To apply via email contact: Florin Popescu, Ph.D. Email: florin.popescu at first.fraunhofer.de Speculative submissions will not be considered. From rao at cs.washington.edu Tue Nov 22 14:45:18 2005 From: rao at cs.washington.edu (Rajesh Rao) Date: Tue, 22 Nov 2005 11:45:18 -0800 Subject: Connectionists: Preprint: Bayesian inference and attention in the visual cortex In-Reply-To: References: Message-ID: <4383754E.2000605@brain.cs.washington.edu> The following paper is available for download: http://www.cs.washington.edu/homes/rao/nreport_bayes_atten05.pdf Bayesian Inference and Attentional Modulation in the Visual Cortex Neuroreport 16(16), 1843-1848, 2005 The responses of neurons in cortical areas V2 and V4 can be significantly modulated by attention to particular locations within an input image. We show that such effects emerge naturally when perception is viewed as a probabilistic inference process governed by Bayesian principles and implemented in hierarchical cortical networks. We show that the proposed model can explain a rich variety of attention-related responses in cortical area V4 including multiplicative modulation of tuning curves, restoration of neural responses in the presence of distracting stimuli, and influence of attention on neighboring unattended locations. Our results suggest a new interpretation of attention as a cortical mechanism for reducing perceptual uncertainty by combining top-down task-relevant information with bottom-up sensory inputs in a probabilistic manner. -- Rajesh P. N. Rao Dept of Computer Science and Engineering Univ of Washington Seattle, WA 98195-2350 http://cs.washington.edu/homes/rao/ Lab Website: http://neural.cs.washington.edu From soeren.lorenz at uni-bielefeld.de Thu Nov 24 04:24:34 2005 From: soeren.lorenz at uni-bielefeld.de (Soeren Lorenz) Date: Thu, 24 Nov 2005 10:24:34 +0100 Subject: Connectionists: Special Issue on Realistic Neural Modeling (OA eJournal Brains, Minds, and Media) Message-ID: <438586D2.3060309@uni-bielefeld.de> (Apologies for multiple postings) ________________________ SPECIAL ISSUE ON REALISTIC NEURAL MODELING Brains, Minds & Media - open access eJournal http://www.brains-minds-media.org ________________________ Now available, free online access: Special Issue on Realistic Neural Modeling - Wam-Bamm '05 Tutorials. Guest Editors: James M. Bower and David Beeman http://www.brains-minds-media.org/current THE ISSUE This special issue provides article versions of eight tutorials presented at the 1st Conference of the World Association of Modelers: Biologically Accurate Modeling Meeting (WAM-BAMM '05), held in San Antonio, Texas, in March 2005. The issue is introduced by the viewpoint "Looking for Newton: Realistic Modeling in Modern Biology" by James M. Bower. GENERAL The issue deals with methods and practical implications of biologically accurate modeling and offers introductory and advanced tutorials mainly based on the tools GENESIS and NEURON. Some contributions provide supplementary material, such as GENESIS source code, detailed modeling and user instructions or visualisations. TOPICS Part of the articles covers questions of realistic modeling ranging from a general introduction to modeling of single cells, calcium concentrations, biochemical pathways, and synaptic input patterns. The other articles are concerned with tools and techniques, like how to use GENESIS and P-GENESIS for modeling, recent developments in NEURON and the role of XML for model specifications in neuroscience. TABLE OF CONTENTS *Looking for Newton: Realistic Modeling in Modern Biology by James M. Bower *Introduction to Realistic Neural Modeling by David Beeman *GENESIS Modeling Tutorial (Wam-Bamm'05 Edition) by David Beeman *Recent Developments in NEURON by Michael Hines and Nicholas T. Carnevale *Realistic Single Cell Modeling - from Experiment to Simulation by Dieter Jaeger *Modeling Calcium Concentration and Biochemical Reactions by Kim T. Blackwell *Simulating in vivo-like Synaptic Input Patterns in Multicompartmental Models by Jeremy Edgerton *Using P-GENESIS for Parallel Simulation of GENESIS Models - a Brief Overview by Greg Hood *XML for Model Specification in Neuroscience - an Introduction and Workshop Summary by Sharon Crook, David Beeman, Padraig Gleeson and Fred Howell ----------------------------- CONTINUOUS CALL FOR SUBMISSION 'Brains, Minds & Media' is an open access eJournal and publishes peer-reviewed articles and media from research and education in the neural and cognitive sciences (http://www.brains-minds-media.org/aims). Future accepted contributions will be published consecutively and integrated ex post into volumes or (special) issues. You are invited to submit contributions to 'Brains, Minds & Media'. More information about manuscript submissions can be found at http://www.brains-minds-media.org/guidelines. Please send your submission to editors at brains-minds-media.org. ----------------------------- If you have any questions, please contact info at brains-minds-media.org. Thank you! Soeren Lorenz (editorial co-ordinator) soeren.lorenz at uni-bielefeld.de From terry at salk.edu Thu Nov 24 00:06:05 2005 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 23 Nov 2005 21:06:05 -0800 Subject: Connectionists: NEURAL COMPUTATION 18:1 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 18, Number 1 - January 1, 2006 NOTE Mixture Models Based on Neural Network Averaging Walter W. Focke LETTERS Sensory Memory for Odors is Encoded in Spontaneous Correlated Activity Between Olfactory Glomeruli Roberto F. Galan, Marcel Weidert, Randolf Menzel, Andreas V. M. Herz and C. Giovanni Galizia The Optimal Synapse for Sparse, Binary Signals in the Rod Pathway Paul T. Clark and Mark C. W. van Rossum Simultaneous Rate-Synchrony Codes in Population of Spiking Neurons Naoki Masuda Spontaneous Dynamics of Asymmetric Random Recurrent Spiking Neural Networks Hedi Soula, Guillaume Beslon, and Olivier Mazet Bayesian Population Decoding of Motor Cortical Activity Using a Kalman Filter Wei Wu, Yun Gao, Elie Bienenstock, John P. Donoghue and Michael J. Black Facial Attractiveness: Beauty and the Machine Yael Eisenthal, Gideon Dror and Eytan Ruppin Classification of Faces in Man and Machine Arnulf B. A. Graf, Felix A. Wichmann, Heinrich H. Buelthoff and Bernhard Schoelkopf Exploring Latent Structure of Mixture ICA Models by the Minimum Beta-Divergence Method Md. Nurul Haque Mollah, Mihoko Minami and Shinto Eguchi An Adaptive Method for Subband Decompostion ICA Kun Zhang and Lai-Wan Chan On Consistency of Bayesian Inference with Mixtures of Logistic Regression Yang Ge and Wenxin Jiang ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2006 - VOLUME 18 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $154 $90 $96.30 Institution $730 $781.10 $784 $657 $702.99 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From jonas at buchli.org Fri Nov 25 10:38:29 2005 From: jonas at buchli.org (Jonas Buchli) Date: Fri, 25 Nov 2005 16:38:29 +0100 Subject: Connectionists: CfP: EPFL-LATSIS Symposium 2006 - Dynamical Principles for Neuroscience and Intelligent Biomimetic Devices Message-ID: <1132933109.10486.66.camel@moria.buchli.org> Dear Connectionists, Please find below the call for poster abstracts of a conference which might be of interest for many of you. Best regards Jonas Buchli ----------------------------------------------------------------------- <> EPFL-LATSIS Symposium 2006 Call for Poster abstracts ==================================================== We invite the submission of poster abstracts for the EPFL-LATSIS Symposium 2006 Dynamical Principles for Neuroscience and Intelligent Biomimetic Devices http://latsis2006.epfl.ch March, 8-10, 2006 Ecole Polytechnique F?d?rale de Lausanne (EPFL), Switzerland Aim of the Conference --------------------- The goal of the conference is to bring together scientists and engineers interested in understanding the dynamical properties of the nervous system, and in taking inspiration from those properties for the design of prosthetic and robotic devices. The conference is interdisciplinary in nature, and aims at bringing together researchers working on similar topics and phenomena but from different backgrounds. The conference is made possible thanks to the generous support of the Latsis Foundation. The presentations will consists of a series of invited talks (see below) and of poster presentations (with short poster spotlights). For more background on the aim of the conference, please visit http://latsis2006.epfl.ch Important Dates --------------- Deadline of abstract submission: January 27, 2006 Notification of acceptance: February 6, 2006 Conference dates: March 8-10, 2006 Abstract submission ------------------- Please send a two-page abstract (including figures and references as needed) to jonas.buchli -at- epfl.ch . Note that we will not have a full peer review process, the number of posters that we can accept is however limited. Thus, we will accept the contributions depending on relevance to the conference topics, quality, and available place. Once accepted, presenters will have the opportunity to present their work with a poster, as well as a short poster spotlight (a 2-minute presentation) in the conference theatre. Templates as well as additional information on the format of abstracts and posters is available on the following website: http://latsis2006.epfl.ch/page14710.html Proceedings ----------- The poster abstracts will be published in a booklet with ISBN number distributed at the conference. Speakers -------- Dynamics of brain function and behavior * Avis Cohen (University of Maryland) * Sten Grillner (Karolinska Institutet, Stockholm) * Serge Rossignol (Universit? de Montr?al) * Carmen Sandi (EPFL) * Allen Selverston (UC San Diego) Nonlinear Dynamics and neural computation * Bard Ermentrout (University of Pittsburgh) * Wulfram Gerstner (EPFL) * Martin Hasler (EPFL) * Wolfgang Maass (TU Graz) * Misha Rabinovich (UC San Diego) * Misha Tsodyks (Weizmann Institute of Science) Neuroprosthetics * Maria Chiara Carrozza (Scuola Superiore Sant'Anna, Pisa) * Miguel Nicolelis (EPFL/Duke University) * Philippe Renaud (EPFL) * Andrew Schwartz (University of Pittsburgh) Hybrid circuits and electronic neurons * Thierry Bal (Unic / CNRS) * Rodney Douglas (ETHZ, Zurich) * Peter Fromherz (Max-Planck-Institute for Biochemistry, Martinsried) * Gwendal Le Masson (University of Bordeaux) Biomimetic Robotics and Control * Jean-Louis Deneubourg (Univ. libre de Bruxelles) * Auke Jan Ijspeert (EPFL) * Yasuo Kuniyoshi (University of Tokyo) * Jean-Jacques Slotine (MIT) * Barbara Webb (University of Edinburgh) Organizing Committee -------------------- Main organizer: Auke Ijspeert, EPFL Co-organizers: Aude Billard, EPFL Dario Floreano, EPFL Wulfram Gerstner, EPFL Martin Hasler, EPFL Henry Markram, EPFL Misha Rabinovich, UCSD Al Selverston, UCSD Local chair: Jonas Buchli, EPFL Email contacts: Auke.Ijspeert -at- epfl.ch and Jonas.Buchli -at- epfl.ch -- ----------------------------------------------------------------- Jonas Buchli Research Assistant Biologically Inspired Robotics Group School of Computer and Communication Sciences EPFL, Swiss Federal Institute of Technology, Lausanne CH 1015 Lausanne, Switzerland jonas at buchli.org http://birg.epfl.ch ++41 21 693 67 14 ----------------------------------------------------------------- From ihaya at kcn.res.kutc.kansai-u.ac.jp Thu Nov 24 06:11:56 2005 From: ihaya at kcn.res.kutc.kansai-u.ac.jp (Isao Hayashi) Date: Thu, 24 Nov 2005 20:11:56 +0900 (JST) Subject: Connectionists: CFP: WCCI'06 Special Session on Biologically Motivated Systems In-Reply-To: <437D87DE.5060600@ee.t.u-tokyo.ac.jp> Message-ID: <20051124.201156.846960977.ihaya@kcn.res.kutc.kansai-u.ac.jp> Call For Papers: WCCI 2006 Special Session on Biologically Motivated Systems - Fuzzy Brain and Fuzzy Evolution Organized by I.Hayashi, T.Nakashima, and T.Murata ======================================================================== IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) July 16-21, 2006 Sheraton Vancouver Wall Centre, Vancouver, BC, Canada http://www.wcci2006.org/ ======================================================================== Session: Biologically Motivated Systems - Fuzzy Brain and Fuzzy Evolution Session Organizer: I.Hayashi (ihaya at kcn.res.kutc.kansai-u.ac.jp) T.Nakashima (email: nakashi at cs.osakafu-u.ac.jp) T.Murata (murata at res.kutc.kansai-u.ac.jp) Paper Submission : January 31, 2006 Scope of the Organized Session: The main aim of this session is to introduce a new approach in brain physiology, cognitive psychology, vision, blonomy, genetic sciences, and psychological genetics, relating neuro-fuzzy and genetic fuzzy systems: these issues are germane to a wide modeling of biologically motivated systems, not just to computer vision and engineering systems. The session covers modeling of brain system and vision system, experiments of visual psychology, visual neural networks, neuro-fuzzy system, genetic fuzzy systems, A-Life, etc. ======================================================================== --- Isao Hayashi,Dr.Eng. Professor Faculty of Informatics Kansai University 2-1-1, Ryozenji-cho, Takatsuki, Osaka 569-1095, Japan telephone +81-72-690-2448 m.phone +81-90-6677-6259 facsimile +81-72-690-2491 e.mail ihaya at kcn.res.kutc.kansai-u.ac.jp URL http://www.hannan-u.ac.jp/kcn/ *********************************************************************** From alaakso at indiana.edu Mon Nov 28 10:09:43 2005 From: alaakso at indiana.edu (Aarre Laakso) Date: Mon, 28 Nov 2005 10:09:43 -0500 Subject: Connectionists: CFP: Dynamics and Psychology Message-ID: <438B1DB7.2010304@indiana.edu> ************** APOLOGIES FOR MULTIPLE POSTINGS ******************* CALL FOR PAPERS *New Ideas in Psychology* Published by Elsevier Science B.V. ISSN 0732-118X, URL: A Special Issue on 'Dynamics and Psychology' GUEST EDITORS Paco Calvo (U. Murcia, Spain) Aarre Laakso (Indiana University, USA) Toni Gomila (U. Illes Balears, Spain) Paper Submission Deadline: September 30th, 2006 New Ideas in Psychology is calling papers for a special issue entitled 'Dynamics and Psychology'. The purpose of this special issue is to bring together some of the leading views on dynamicism as it relates to psychological phenomena. Although the primary focus is on conceptual ideas regarding the status of dynamicism from the standpoint of Developmental Psychology, Cognitive Science, Artificial Intelligence, Philosophy, and related fields, empirical work is also welcome insofar as it bears explicitly upon theoretical debate. New Ideas in Psychology invites original contributions for the forthcoming special issue on Dynamics and Psychology from a broad scope of areas. Some key research issues and topics relevant to this special issue include: *Brain and cognitive function *Categorical perception *Dynamic computer simulations *Dynamic field approach *Dynamic systems theory and developmental theory *Dynamics of control of processing *Dynamics of social interaction *Emergence *Intermodality *Language development *Mental representation *Motor development *Neurobiological constraints *Perceptual learning *Self-organization of behavior *Sensory-motor and perception-action loops *Temporality SUBMISSION INSTRUCTIONS AND DEADLINE Manuscripts, following the New Ideas in Psychology guidelines () should be emailed to Paco Calvo (fjcalvo at um.es) by September 30th, 2006. INVITED CONTRIBUTORS The special issue will include invited papers by: Dante Chialvo (Northwestern University Medical School, Chicago) Eliana Colunga (Colorado, Boulder) and Linda Smith (Indiana University) Aarre Laakso (Indiana University) John Spencer (University of Iowa) RELATED AND SAMPLE ARTICLES *Bechtel, W. (1998) "Representations and cognitive explanations: assessing the dynamicist's challenge in cognitive science", Cognitive Science, 22, 295-318. *Beer, R. D. (1995) "A dynamical systems perspective on agent-environment interaction", Artificial Intelligence, 72, 173-215. *Clark, A. (1997) "The dynamical challenge", Cognitive Science, 21, 461-481. *Erlhagen, W. & Schner, G. (2002) "Dynamic field theory of movement preparation", Psychological Review, 109, 545-572. *Nuez, R. & Freeman, W.J. (1999) Reclaiming cognition: the primacy of action, intention and emotion. Imprint Academic. *Prinz, J. J., & Barsalou, L. W. (2000) "Steering a course for embodied representation", In E. Dietrich & A. B. *Markman (Eds.), Cognitive dynamics: Conceptual and representational change in humans and machines (pp. 51-77). Mahwah, NJ: Lawrence Erlbaum Associates. *Spencer, J.P. & Schner, G. (2003) "Bridging the representational gap in the dynamic systems approach to development", Developmental Science, 6, 392-412. *Sporns, O., Chialvo, D., Kaiser, M. & Hilgetag, C. (2004) "Organization, development and function of complex brain networks", Trends in Cognitive Sciences, 9, 418-425. *Thelen, E., Schner, G., Scheier, C. & Smith, L. (2001) "The dynamics of embodiment: A field theory of infant perseverative reaching", Behavioral and Brain Sciences, 24, 1-86. *Townsend, J. T., & Busemeyer, J. (1995) "Dynamic representation of decision making", In R. F. Port & T. Van Gelder (Eds.), Mind as motion. Cambridge, MA: MIT Press. *Turvey, M. T., & Carello, C. (1995) "Some dynamical themes in perception and action" In R. F. Port & T. Van *Gelder (Eds.), Mind as motion. Cambridge, MA: MIT Press. *van Gelder, T. (1998) "The dynamical hypothesis in Cognitive Science", Behavioral and Brain Sciences, 21, 615-665. GUEST EDITORS Paco Calvo Departamento de Filosofa Universidad de Murcia E-30100 Murcia - SPAIN e-mail: fjcalvo at um.es Aarre Laakso Department of Psychology Indiana University 1101 East 10th Street Bloomington, IN 47405 e-mail: alaakso at indiana.edu Toni Gomila Department of Psychology University of the Balearic Islands E-07122 Palma de Mallorca - SPAIN e-mail: toni.gomila at uib.es From bisant at umbc.edu Mon Nov 28 18:29:10 2005 From: bisant at umbc.edu (D Bisant) Date: Mon, 28 Nov 2005 18:29:10 -0500 Subject: Connectionists: Function Approximation Message-ID: <438B92C6.9080301@umbc.edu> A presenter at Supercomputing 2005 claimed that a number of classification methods used in datamining, such as decision trees and nearest neighbor, have been extended and perform well on function approximation applications. Are any of you familiar with the application of these methods to function approximation or interpolation? Regards, David Bisant The Laboratory for Physical Sciences From justin at cnel.ufl.edu Mon Nov 28 07:55:55 2005 From: justin at cnel.ufl.edu (Justin Sanchez) Date: Mon, 28 Nov 2005 07:55:55 -0500 Subject: Connectionists: Graduate Assistant (PhD) Position Available: Brain-Machine Interfaces Message-ID: <001001c5f41b$247726d0$7832b29f@Tranquility> Graduate Assistant (PhD) Position Available: Brain-Machine Interfaces The Neuroprosthetics Research Group (NRG) is searching for a highly-motivated Ph.D. student to participate in a National Science Foundation funded project for developing novel Brain-Machine Interfaces (BMI). The candidate will be expected to be competent in electrophysiological methods and signal processing (time series analysis). The student's research will bridge in vivo BMI experimental paradigms with the analysis of functional neural ensemble recordings. The position is available starting January 2006. If interested, please send via email a CV, a summary of skills and experiences, and the names/contact of two references to: Justin Sanchez, Ph.D. Email: jcs77 at ufl.edu Justin C. Sanchez, Ph.D. Department of Pediatrics, Division of Neurology McKnight Brain Institute, L2-140 PH: 1-352-392-4827 FAX: 1-352-392-2515 Neuroprosthetics Research Group University of Florida Gainesville, FL 32611 WWW: http://nrg.mbi.ufl.edu/ From ken at neurotheory.columbia.edu Wed Nov 30 14:25:21 2005 From: ken at neurotheory.columbia.edu (Ken Miller) Date: Wed, 30 Nov 2005 14:25:21 -0500 Subject: Connectionists: Columbia University Postdoctoral/Graduate Fellowships in Theoretical Neuroscience Message-ID: <17293.64673.455127.571337@neurotheory.columbia.edu> FULL INFO: http://www.neurotheory.columbia.edu PLEASE DO NOT USE 'REPLY'; FOR MORE INFO USE ABOVE WEB SITE The Center for Theoretical Neuroscience at Columbia University in New York City is accepting applications for graduate students and postdoctoral fellows. The faculty include: Larry Abbott, Co-Director http://neurotheory.columbia.edu/~larry Ken Miller, Co-Director http://neurotheory.columbia.edu/~ken Liam Paninski http://www.stat.columbia.edu/~liam Ning Qian http://brahms.cpmc.columbia.edu/ Stefano Fusi (Senior Research Associate) http://www.cns.unibe.ch/~fusi/ Bill Bialek (Visiting one day per week) http://www.princeton.edu/~wbialek/wbialek.html Columbia has a strong research program in experimental neurobiology (http://cpmcnet.columbia.edu/dept/neurobeh/nb_phd_res_area.html) and in computational biology (http://www.c2b2.columbia.edu/). The Center is a highly interactive environment for bringing theoretical approaches to Neuroscience. For postdoctoral fellowships, applicants should have a strong background and education in theoretical neuroscience or biology or in a quantitative field such as mathematics, theoretical or experimental physics, engineering, or computer science, and commitment to a future research career in neuroscience. Prior biological or neuroscience training is not required. TO APPLY, please send a curriculum vitae, a statement of previous research and research goals, up to three relevant publications, and have three letters of recommendation sent, to the address below. Applications are due by Jan. 30, 2006. For graduate fellowships, apply to an existing Ph.D. program at Columbia (details on our web site). Separately, notify us that you wish to be considered for a fellowship in Theoretical Neuroscience by sending email, to the address below, with a letter explaining which program you've applied to, why you intend to pursue Theoretical Neuroscience in your graduate work, and what background you bring to it. Please also include a copy of your application materials, and ask your referees to send us copies of their letters. Note that the priority application deadline for most programs is either Jan. 3 or (for engineering) Dec. 15. Application materials may be sent by email to Andrew Fink, andrew at neurotheory.columbia.edu; please include your name and "postdoctoral fellowship, CTN" or "graduate fellowship, CTN" in the subject line. Alternatively materials may be sent by surface mail (address on our web site). From wahba at stat.wisc.edu Tue Nov 29 16:18:47 2005 From: wahba at stat.wisc.edu (Grace Wahba) Date: Tue, 29 Nov 2005 15:18:47 -0600 Subject: Connectionists: Job opening in the Statistics Dept at Madison Message-ID: <200511292118.jATLIlNI006910@juno.stat.wisc.edu> The Statistics Department at the University of Wisconsin-Madison has an opening for a tenure track assistant professor starting fall 2006. There are several faculty members interested in classification and machine learning in the Statistics Department and many scattered throughout the campus in CS, Math, ECE and elsewhere. Madison is one of the great research universities and there are are many opportunities for collaboration. Madison is also a great place to live and (personally speaking) if you are interested in bicycling, sailing (we are on four lakes) and other outdoor activities it is a terrific place, along with cultural opportunities which are outstanding for a medium sized city. A job description can be found at http://www.stat.wisc.edu/Employent/ (please send job-related correspondance to the address there, not to me, thanks) regards Grace (More about Mad City at http://www.ci.madison.wi.us/) From sethu.vijayakumar at ed.ac.uk Tue Nov 29 05:06:18 2005 From: sethu.vijayakumar at ed.ac.uk (Sethu Vijayakumar) Date: Tue, 29 Nov 2005 10:06:18 +0000 Subject: Connectionists: Postdoctoral Fellowship in Machine Learning and Robotics in Edinburgh, UK. Message-ID: <438C281A.3090100@ed.ac.uk> Applications are invited for a Postdoctoral Research fellow in the area of Machine Learning and Robotics as part of an EU-IST FP6 funded four year project "SENSOPAC - Sensorimotor structuring of Perception and Action". The post is available from Jan. 2006 for a maximum of 48 months and located in the School of Informatic at the University of Edinburgh. Salary is on the RA1A scale (GBP 20,044 to GBP 30,002) and will depend upon qualifications and experience. The postdoctoral fellow will be responsible for developing statistical machine learning techniques for automatically extracting sensorimotor contingences from dynamic and kinematic movement data (collected from robots and human experiments) and using this to learn latent model representations of various contexts and tasks. This will involve basic research in the fields of high dimensional, online nonparametric regression, Bayesian model selection and latent model learning as well as applied areas of adaptive motor control and robotics. Candidates are expected to have a PhD in the area of machine learning and/or adaptive motor control and strong mathematical skills in the area of optimization, algebra and probability theory in addition to strong programming skills in C, C++, MATLAB or equivalent. Some experience with real world robotic systems and motor control is a plus. More details of the job and the research group can be found at: http://www.ipab.inf.ed.ac.uk/slmc/index.html Online applications are encouraged at: http://www.jobs.ed.ac.uk/vacancies/index.cfm?fuseaction=vacancies.detail&vacancy_ref=3005309 Application Deadline: December 20, 2005 Informal enquiries may be addressed to: Dr. Sethu Vijayakumar (sethu.vijayakumar [at] ed.ac.uk) Dr. Marc Toussaint (mtoussai [at] inf.ed.ac.uk) will be available at NIPS for an informal discussion/interview. (Please advertise in your department using the attached flyer) (We will continue to accept applications till the post is filled) -- ------------------------------------------------------------------ Sethu Vijayakumar, Ph.D. Assistant Professor(UK Lecturer) Director, IPAB, School of Informatics, The University of Edinburgh 2107F JCMB, The Kings Buildings, Edinburgh EH9 3JZ, United Kingdom URL: http://homepages.inf.ed.ac.uk/svijayak Ph: +44(0)131 651 3444 SLMC Research Group URL: http://www.ipab.informatics.ed.ac.uk/slmc ------------------------------------------------------------------ Adjunct Assistant Professor, Department of Computer Science, University of Southern California ------------------------------------------------------------------ From B.Kappen at science.ru.nl Wed Nov 30 03:36:58 2005 From: B.Kappen at science.ru.nl (Bert Kappen) Date: Wed, 30 Nov 2005 09:36:58 +0100 (CET) Subject: Connectionists: JSTAT special issue on approximate inference Message-ID: Dear all, Last January, we have organized an interface meeting in Switzerland between researchers in the field of machine learning and statistical physics. The topic of common interest was approximate inference and in particular message passing methods. The meeting was very interesting for both sides. Clearly, machine learning benefits from statistical physics methods, but also the reverse is true, in particular where it concerns the development of robust algorithms and challenging applications. The IOP Journal of Statistical Mechanics has published a focus issue on the meeting, which you will find at http://www.iop.org/EJ/journal/-page=extra.focus2/jstat Bert Kappen, Manfred Opper, Riccardo Zecchina and Ruedi Stoop Bert Kappen SNN Radboud University Nijmegen URL: www.snn.kun.nl/~bert The Netherlands tel: +31 24 3614241 fax: +31 24 3541435 B.Kappen at science.ru.nl