From olivier.chapelle at tuebingen.mpg.de Fri Sep 1 09:20:00 2006 From: olivier.chapelle at tuebingen.mpg.de (Olivier Chapelle) Date: Fri, 01 Sep 2006 15:20:00 +0200 Subject: Connectionists: Papers and code about SVM training Message-ID: <44F83380.8030300@tuebingen.mpg.de> Dear colleagues, I would like to announce the availability of papers and code related to SVM training. Training an SVM in the primal ----------------------------- Abstract from http://www.kyb.mpg.de/publication.html?publ=4142: Most literature on Support Vector Machines (SVMs) concentrate on the dual optimization problem. In this paper, we would like to point out that the primal problem can also be solved efficiently, both for linear and non-linear SVMs, and that there is no reason for ignoring this possibilty. On the contrary, from the primal point of view new families of algorithms for large scale SVM training can be investigated. Additional details and Matlab code can be found at http://www.kyb.tuebingen.mpg.de/bs/people/chapelle/primal/ In particular, you will find a link to another paper explaining how to train an SVM with very few basis functions: S. S. Keerthi, O. Chapelle, D. DeCoste, Building Support Vector Machines with Reduced Classifier Complexity, JMLR 7, 2006. Learning kernel parameters -------------------------- Some code based on the work I did during my PhD is available at: http://www.kyb.tuebingen.mpg.de/bs/people/chapelle/ams/ It includes: - learning the kernel parameters of an SVM (classification) or GP (regression) by gradient descent on either the leave-one-out error, the radius/margin bound, a validation error or the marginalized likelihood. - learning a linear combination of kernels (this is a convex problem) - estimating efficiently the leave-one-out error of an SVM. Olivier Chapelle From dorr at inb.uni-luebeck.de Fri Sep 1 12:44:03 2006 From: dorr at inb.uni-luebeck.de (Michael Dorr) Date: Fri, 1 Sep 2006 18:44:03 +0200 Subject: Connectionists: PhD / Postdoc positions Message-ID: <200609011844.03505.dorr@inb.uni-luebeck.de> For an EU funded interdisciplinary project on gaze-based communication we are seeking several ? ? ?PhD students and/or Postdoctoral Researchers Project abstract ---------------- Vision is the dominant perceptual channel through which we interact with information and communication systems, but one major limitation of our visual communication capabilities is that we can attend to only a very limited number of features and events at any one time. This fact has severe consequences for visual communication, because what is effectively communicated depends to a large degree on those mechanisms in the brain that deploy our attentional resources and determine where we direct our gaze. We therefore propose that future ICT systems should use gaze guidance to help the users deploy their limited attentional resources more effectively. The same technology can be used to create augmented vision aids that improve human visual capabilities by complementing natural vision with computer- vision technology in an unobtrusive way. Position at the Institute for Neuro- and Bioinformatics, University of Luebeck, Germany (http://www.inb.uni-luebeck.de) -------------------------------------------------------- Work at INB will focus on eye-tracking, gaze-contingent displays, and eye-movement prediction. This involves high-speed image processing, tracking, and graphics, machine-learning techniques, and the mathematical modeling of visual functions. Applicants for the PhD student position should have a Master, Diploma or equivalent degree in computer science, physics, mathematics, or related areas. Applicants for the postdoctoral position should have a PhD in one of the areas listed above. All applicants should show enthusiasm for interdisciplinary research. Additionally, applicants should have a strong background in several of the?following areas: - Image Processing and Image Analysis - Computer Vision - Machine Learning - Software Development Applications, including CV and references, should be sent via email to barth at inb.uni-luebeck.de, with Cc to dorr at inb.uni-luebeck.de. The deadline for applications is midnight CEST on 15 September 2006, but later applications might be considered. Position at Abteilung Allgemeine Psychologie, Justus-Liebig-Universitaet Giessen, Germany (http://www.allpsych.uni-giessen.de/) --------------------------------------------- Applicants for the PhD student position should have a Master, Diploma or equivalent degree in psychology, biology, neuroscience, or related areas. Applicants for the postdoctoral position should have a PhD in one of the areas listed above. All applicants should show enthusiasm for interdisciplinary research. Additionally, applicants should have a strong background in at least one of the following areas: - Visual Neuroscience - Oculomotor system - Attention Some background in programming visual displays would be highly beneficial. Applications, including CV and references, should be sent via email to gegenfurtner at uni-giessen.de. The deadline for applications is midnight CEST on 15 September 2006, but later applications might be considered. A similar position is available at the Laboratory for Experimental Ophthalmology at the University of Groningen, The Netherlands. Please contact Frans Cornelissen for more details. Duration and salary ------------------- The positions last for three years and are available from 1 October 2006. Applicants should ideally be available from this date, though applicants who require a later starting date may also be considered. The salary will be based on the German public service BAT IIa payscale (from around 38,000 EUR per annum, the exact amount depending on age and marital status). From Randy.OReilly at colorado.edu Fri Sep 1 11:42:50 2006 From: Randy.OReilly at colorado.edu (Randall C. O'Reilly) Date: Fri, 1 Sep 2006 09:42:50 -0600 Subject: Connectionists: Faculty Position at University of Colorado Boulder Message-ID: <200609010942.51273.Randy.OReilly@colorado.edu> COGNITIVE PSYCHOLOGY FACULTY POSITION AT THE UNIVERSITY OF COLORADO BOULDER The Department of Psychology, University of Colorado at Boulder, invites applications for a tenure-track position in cognitive psychology beginning August 2007. The department anticipates hiring at the assistant professor level. The University of Colorado, Boulder, is committed to diversity and equality in education and employment. In that spirit, applications at all levels will be considered from those who would strengthen the department's diversity. Candidates in any area of cognitive psychology will be considered, and all approaches to cognition (e.g., experimental, individual differences, computational, developmental, cognitive neuroscience) are appropriate for the position. The successful candidate will be expected to teach at the undergraduate and graduate levels, to supervise undergraduate and graduate students in research, and to maintain an active research program. Salary is competitive and dependent upon experience. All applicants should send a curriculum vitae, a statement of research interests, a statement of undergraduate and graduate teaching interests, representative research papers, and at least three letters of recommendation to: Akira Miyake, Chair, Cognitive Search Committee, Department of Psychology, University of Colorado, 345 UCB, Boulder, CO 80309-0345. We will begin reviewing applications on November 3, 2006, and will continue to review applications until the position is filled. The University of Colorado at Boulder is committed to diversity and equality in education and employment. From ala at nada.kth.se Sun Sep 3 07:19:48 2006 From: ala at nada.kth.se (Anders Lansner) Date: Sun, 3 Sep 2006 13:19:48 +0200 Subject: Connectionists: Faculty Position in Computational Neuroscience at Stockholm Brain Institute Message-ID: <005701c6cf4a$de62bc20$6f00a8c0@nt.nada.kth.se> The newly established Stockholm Brain Institute (SBI) is seeking outstanding candidates for a Lecturer/Associate Professor position in Computational Neuroscience. The recruited candidate will join the Group for Computational Biology and Neurocomputing at KTH, and is expected to develop an active research programme, take part in organizing the use of advanced computational neuroscience techniques and tools, and provide training and expert advice to SBI groups. The deadline for application is September 25. For more information on SBI see http://www.stockholmbrain.se. The position is part financed by the Swedish Foundation for Strategic Research (SSF), see http://www.stratreseach.se. Further information is available at http://www.csc.kth.se/om/ledigajobb/lektor/index.php.en From renaud.jolivet at epfl.ch Mon Sep 4 04:28:21 2006 From: renaud.jolivet at epfl.ch (Renaud Jolivet) Date: Mon, 04 Sep 2006 10:28:21 +0200 Subject: Connectionists: Building a modeling community around neuro-glia interactions Message-ID: <44FBE3A5.10203@epfl.ch> Dear colleagues, I recently started to model neuro-glia interactions. As most of you are certainly aware of, this field is undergoing a small revolution as more and more evidences accumulate showing the active role of glial cells in plasticity, signal processing, metabolism and more. As a newcomer to this field, I would be interested to know if a community of modelers already exists structured around this topic and if not, would be willing to start building one. So, if working on this topic and interested by joining forces in a network of researchers, would you please contact me? Regards, Renaud Jolivet -- Renaud Jolivet PhD Brain Mind Institute EPFL -- http://icwww.epfl.ch/~rjolivet +41 21 693 9687 From juergen at idsia.ch Mon Sep 4 07:04:36 2006 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Mon, 4 Sep 2006 13:04:36 +0200 Subject: Connectionists: RL: postdoc & phd fellowships at the Swiss AI lab IDSIA Message-ID: <4aa458fa83ebed33bef01261f5225105@idsia.ch> We have new job openings for an outstanding postdoc and an excellent phd student. Topic: theory and practice of reinforcement learning Details: http://www.idsia.ch/~juergen/rl2007.html More jobs at IDSIA: http://www.idsia.ch/jobs?status=open Juergen Schmidhuber Codirector IDSIA, Switzerland Prof. Cognitive Robotics, TU Munich, Germany http://www.idsia.ch/~juergen/whatsnew.html From feldman at ICSI.Berkeley.EDU Sat Sep 2 12:50:03 2006 From: feldman at ICSI.Berkeley.EDU (Jerome Feldman) Date: Sat, 02 Sep 2006 09:50:03 -0700 Subject: Connectionists: M2M book site Message-ID: <44F9B63B.4040103@icsi.berkeley.edu> There is now a web site: www.m2mbook.org/ for my new book "From Molecule to Metaphor: A Neural Theory of Language" The main purpose of this site is to serve as a platform for the continuing pursuit of a Unified Cognitive Science as suggested in the book. Use the Reader Comments link to send comments at any level, from typos to alternative formulations of the driving question: How does the brain compute the mind? Selected reader comments will be displayed, possibly with a response, but this is not a blog. Jerry Feldman From Randy.OReilly at colorado.edu Sat Sep 2 11:21:14 2006 From: Randy.OReilly at colorado.edu (Randall C. O'Reilly) Date: Sat, 2 Sep 2006 09:21:14 -0600 Subject: Connectionists: CCNC 2006: Call for Fellowship Applicants Message-ID: <200609020921.14555.Randy.OReilly@colorado.edu> ~ CCNC2006 --- CALL FOR FELLOWSHIP APPLICANTS ~ The CCNC organizing committee is pleased to announce the availability of a limited number of $500 fellowship awards to early-career computational cognitive neuroscience researchers and potential researchers. Eligible candidates should be undergraduates, graduate students, or post-docs. It is anticipated that approximately five (5) stipends will be awarded. Criteria to be used in selection will include (in approximate order of weighting): * Financial need: e.g., student status, specific hardship, etc. * Membership in a group underrepresented in science: e.g., African-American, Hispanic, Native American ancestry; female gender * Distance to be traveled: Transoceanic vs. North America * Participating author: e.g., are you a sole presenter, first author, auxiliary author on a poster? Interested applicants should send an email to the conference administrator no later than Friday September 29, 2006: Thomas E. Hazy, MD thazy at colorado.edu Your email should include your career status and address all of the selection criteria listed above. Please also include the name and contact info of a faculty reference who is familiar with your career status, academic work and/or research interests and can corroborate your application if asked. An overview of CCNC2006 is provided below. ---------------------------------------------------------------------------- 2ND ANNUAL CONFERENCE ON COMPUTATIONAL COGNITIVE NEUROSCIENCE www.ccnconference.org To be held in conjunction with the 2006 PSYCHONOMIC SOCIETY CONFERENCE, November 16-19, 2006 at the Hilton Americas hotel in Houston, TX. CONFERENCE DATES: Wed-Thu November 15 & 16, 2006 The inaugural CCNC 2005 meeting held prior to Society for Neuroscience (SfN) in Washington DC was a great success with approximately 250 attendees 60 presented posters and strongly positive reviews. In future years it will continue to be held on a rotating basis with other meetings such as (tentative list): Cognitive Neuroscience Society (CNS) Organization for Human Brain Mapping (OHBM) Cognitive Science Society (CogSci) Neural Information Processing Systems (NIPS) and Computational and Systems Neuroscience (COSYNE). ____________________________________________________________________________ ~PROGRAM~ _________________________________________________________________________ * 2006 Keynote Speakers (confirmed): Mike Kahana, University of Pennsylvania Mark Seidenberg, University of Wisconsin Madison ___________________________________________________________________________ * 3 Symposia (2 hours each): 1) Face/Object Recognition: Are Faces Special, or Just a Special Case? Computational models of face and object processing Speakers: Gary Cottrell, UCSD (Moderator) Kalanit Grill-Spector, Stanford Alice O'Toole, UT Dallas Maximilian Riesenhuber, Georgetown Description: What can computational models tell us about human visual object processing? We have excellent models that explain how we may recognize objects at multiple scales and orientations, while other models explain why faces may or may not be "special," or simply a special case. The goal of this symposium is to summarize what we understand with some degree of confidence, what is still not understood, and to what degree what we understand meshes with data on human and animal visual processing, including behavioral, fMRI, neurophysiological, and neuropsychological data. 2) Semantics: Development and Brain Organization of Conceptual Knowledge: Computational and Experimental Investigations. Speakers: Jay McClelland, Stanford University (Moderator) Linda Smith, Indiana University Tim Rogers, University of Wisconsin Alex Martin, National Institute of Mental Health Description: The symposium is predicated on the assumption that there are links between conceptual structure, experience, conceptual development, and brain organization of conceptual knowledge. Jay McClelland will begin with a computational perspective on conceptual development, followed by Linda Smith with an empirical perspective. We would then switch to the subject of brain organization of conceptual knowledge, beginning with a computational perspective by Tim Rogers followed by an empirical perspective from Alex Martin. 3) Emergent Cognitive Control: Computational and Empirical Investigations Speakers: Mike Mozer, University of Colorado (Moderator) Stephen Monsell, University of Exeter Gordon Logan, Vanderbilt Matt Bottvinick, University of Pennsylvania Sue Becker, McMaster Description: Cognitive control is required whenever an individual performs novel activities, either because the task is novel or because the stimuli, responses, or task environment is unfamiliar. Aspects of cognitive control include: the deployment of visual attention, the selection of responses, and the use of working memory to subserve ongoing processing. The cognitive architecture is extremely flexible. The role of cognitive control is to reconfigure this general-purpose architecture to perform a specific task. Cognitive control is typically conceived of in terms of an active process in frontal cortex which guides and routes processing in posterior systems. Even if the process is implemented in neural hardware, it still has the flavor of a homunculus---an intelligent overseer that inhibits or otherwise biases processing in less intelligent, subservient systems. In this symposium, we wish to explore alternative perspectives on cognitive control, including perspectives that treat control as an emergent property of a complex cognitive architecture, and perspectives in which control is not an explicit active process, but rather a consequence of the sequential dynamics of experience. __________________________________________________________________________ * 12 short contributed talks featuring selected posters * Poster sessions ___________________________________________________________________________ 2006 Planning Committee: Suzanna Becker, McMaster University Jonathan Cohen, Princeton University Yuko Munakata, University of Colorado, Boulder David Noelle, Vanderbilt University Randall O'Reilly, University of Colorado, Boulder Maximilian Riesenhuber, Georgetown University Medical Center Executive Organizer: Thomas Hazy, University of Colorado, Boulder For more information and to sign up for the mailing list visit: www.ccnconference.org From Manuel.Davy at ec-lille.fr Mon Sep 4 04:48:42 2006 From: Manuel.Davy at ec-lille.fr (Davy Manuel) Date: Mon, 04 Sep 2006 10:48:42 +0200 Subject: Connectionists: Post-Doctoral position at INRIA, Lille, France Message-ID: <44FBE86A.6010309@ec-lille.fr> One year post-doctoral position in the INRIA-Sequel research group, Lille, France Scientific context : This project is at the heart of SequeL's research interest, namely 'sequential learning'. There are many situations where one collects data from which actions should be decided sequentially. For example, a mobile robot collects measurement from its environment thanks to several sensors, and must decide where to go, based on these measurements. When the robot resources (energy, sensor availability, time) are limited, the sensors must be managed so as to reduce some cost. This project will focus on this task, within the general assumption that the environment is not perfectly known, and that the sensor behavior may be known only partly. Description of the post-doc activities : The post-doctoral researcher will need to develop and implement reinforcement learning as well as particle filtering algorithms to achieve these tasks, within the general framework of Partially Observable Markov Decision Processes (POMDPs). These developments will be made in the context of a real application. The approaches that prove successful in simulations will be implemented onto real robots. Applicant's required skills The applicant needs to have a PhD with a focus on either particle filtering or reinforcement learning. Person to contact for further informations : Manuel Davy (Manuel.Davy at inria.fr) To apply for, please send a CV and a covering letter to : Chantal.birot at inria.fr and Nathalie.legoullon at inria.fr ------------------------------------------------------- Sequel's url is http://www.grappa.univ-lille3.fr/cgi-bin/twiki/view/Sequel This add may also be found at the url http://www-futurs.inria.fr/emplois/fiches_post_doc/Fiche_SequeL_Ang.html Please be aware that conditions apply, see http://www-futurs.inria.fr/emplois/Offers_for_Post.html --------------------------------------------------------- From ASAHTan at ntu.edu.sg Sun Sep 3 06:30:32 2006 From: ASAHTan at ntu.edu.sg (Tan Ah Hwee (Assoc Prof)) Date: Sun, 3 Sep 2006 18:30:32 +0800 Subject: Connectionists: Research Associate Position Message-ID: <7CD06E15ADF4104A9F2E4DC2DE678F8901DB8D4B@EXCHANGE21.staff.main.ntu.edu.sg> September 2006 Research Associate Nanyang Technological University, Singapore A research associate is open for a funded research project in the field of biologically inspired cognitive architectures. The successful candidates will join a vibrant team of postgraduate students and software engineers in developing an integrated neural architecture, with high-level cognitive capabilities. Applicants for the position must satisfy the following requirement. 1. A good MSc/BSc degree in Computer Science or a related discipline. 2. Research experience with publications in the fields of cognitive and neural systems, machine learning, and knowledge representation. 3. Good communication and writing skills. 4. Competency in software programming and application prototype development. The RA position is for a period of two years, subject to review and renewal after one year. The commencing salary for the above post will be competitive and commensurate with the candidates' qualifications and experience. To apply, please send a detailed resume, including a list of publications and referees to the following address. Email submission of application is encouraged with the subject of "Application for Research Associate". A/Prof Ah-Hwee Tan School of Computer Engineering Nanyang Technological University Nanyang Avenue, Singapore 639798 Email: asahtan at ntu.edu.sg Application will remain opened until the position is filled. Only short-listed candidates will be notified. From ASAHTan at ntu.edu.sg Tue Sep 5 09:01:42 2006 From: ASAHTan at ntu.edu.sg (Tan Ah Hwee (Assoc Prof)) Date: Tue, 5 Sep 2006 21:01:42 +0800 Subject: Connectionists: PhD Scholarships References: <7CD06E15ADF4104A9F2E4DC2DE678F8901DB8D4C@EXCHANGE21.staff.main.ntu.edu.sg> Message-ID: <7CD06E15ADF4104A9F2E4DC2DE678F8901DB8D60@EXCHANGE21.staff.main.ntu.edu.sg> September 2006 PhD Scholarships Nanyang Technological University, Singapore Research scholarships are available for postgraduate study, leading to a PhD degree, on topics in the field of cognitive and neural systems. The successful candidates will join a vibrant team of postgraduate students and research engineers conducting research and development into various aspects of the biologically inspired cognitive and neural systems. Applicants for the scholarships must satisfy the following requirement. 1. A good MSc/BSc degree in Computer Science, Computer Engineering, or a related discipline. 2. Research experience in the fields of cognitive science, neural networks, machine learning, and/or knowledge representation is a plus. 3. Good communication and writing skills. 4. Competency in programming and prototype development. The full-fee scholarships with monthly stipends will be awarded for an initial period of three years, subject to yearly review and renewal. To apply, please send a detailed resume, including publications and names of referees to the following address. Email submission of application is encouraged and should use the subject heading of "Application for Postgraduate Study". A/Prof Ah-Hwee Tan School of Computer Engineering Nanyang Technological University Nanyang Avenue, Singapore 639798 Email: asahtan at ntu.edu.sg Application will remain opened until the positions are filled. Only short-listed candidates will be notified. From fiser at brandeis.edu Tue Sep 5 22:47:01 2006 From: fiser at brandeis.edu (Jozsef Fiser) Date: Tue, 5 Sep 2006 22:47:01 -0400 Subject: Connectionists: Tenure-track position in theoretical/computational neuroscience at Brandeis Message-ID: <57900EFC-BA4D-4FC5-A63A-0839A62914B1@brandeis.edu> ****************************************************************** Brandeis University Tenure-track Position in Theoretical/Computational Neuroscience Brandeis University seeks THEORETICAL/COMPUTATIONAL NEUROSCIENTIST. Candidates should have a Ph.D. in Math, Physics, Computer Science, Engineering, Biophysics, Cognitive Science, Neuroscience, or other related discipline and postdoctoral experience relevant to modeling problems in neuroscience. We anticipate making an appointment at the Assistant Professor level, but under exceptional circumstances a more senior level appointment is possible. First priority will be given to applications received by October 30, 2006. Candidates should submit their initial information online at: http:// www.bio.brandeis.edu/facultySearch/appFormCN.php Candidates should provide a CV, list of publications, brief statements of research and teaching interests and arrange for three letters of reference to be submitted either by email to volencenter at courier.brandeis.edu or in hard copy to: Computational Neuroscience Search Committee Volen National Center for Complex Systems ? MS013 Brandeis University 415 South Street Waltham, MA 02454-9110. Brandeis University is an equal opportunity employer, committed to building a culturally diverse intellectual community and strongly encourages applications from women and minorities. ****************************************************************** From jutta.kretzberg at uni-oldenburg.de Fri Sep 8 14:33:57 2006 From: jutta.kretzberg at uni-oldenburg.de (Jutta Kretzberg) Date: Fri, 08 Sep 2006 20:33:57 +0200 Subject: Connectionists: Ph.D. Stipends "Neurosensory Science, Systems and Applications" Message-ID: <4501B795.80609@uni-oldenburg.de> Several Ph.D. stipends at the International Graduate School ?Neurosensory Science, Systems and Applications? http://medi.uni-oldenburg.de/projects/eurogk/ The international graduate training site ? financed by the German Research Foundation (DFG) and the state of lower Saxony and pursued at the Universit?t Oldenburg together with the Rijksuniversietit Groningen ? is inviting applications for several Ph.D. stipends ( - increased stipend rate, partially BAT IIa/(2) - ) in the subject areas physics/engineering (medical physics, acoustics, theory of complex systems, signal processing, neurosensory physics), biology (neurobiology, zoology and animal behaviour, animal navigation, sensory physiology), psychology (cognition research) and computer science/engineering (medical robotics). Successful candidates should have a university degree that entitles for admission to a Ph.D program in one of the subjects listed above with a grade level clearly above the average. Further prerequisites are an excellent qualification and motivation for pursuing a high-level dissertation project in an interdisciplinary and international context within one of the research groups contributing to the training site. For further conditions and amount of stipends visit http://www.dfg.de/en/research_funding/coordinated_programmes/research_training_groups/index.html Please direct your applications (including CV, list of publications, copy of university degree) to: Prof. Dr. Dr. Birger Kollmeier, Sprecher des Int. Graduiertenkollegs, Medizinische Physik, Universit?t Oldenburg, D-26111 Oldenburg, Germany e-mail: Susanne.garre at uni-oldenburg.de From renaud.jolivet at epfl.ch Fri Sep 8 15:30:51 2006 From: renaud.jolivet at epfl.ch (Renaud Jolivet) Date: Fri, 08 Sep 2006 21:30:51 +0200 Subject: Connectionists: 2 PostDoc positions in Computational Neuroscience Message-ID: <4501C4EB.7000307@epfl.ch> We are looking for several enthusiastic and highly qualified researchers interested in work on - simplified models of spiking neurons and/or - models of spike timing dependent plasticity (STDP) The Laboratory of Computational Neuroscience is part of the Brain-Mind Institute at the EPFL, and located in Lausanne on the shores of the Lake of Geneva in Switzerland. Together with the ETHZ the EPFL (Ecole Polytechnique Federale de Lausanne) ranks amongst the top universities in Europe. The EPFL has a very active research program in neuroscience with a strong component in theoretical and computational neuroscience. The ideal candidates should have a background in physics or related fields and previous experience in computational neuroscience. For more information on the work in the lab see http://diwww.epfl.ch/mantra/ Recent publications of the lab relevant for the project include - Simplified Models of Spiking Neurons R. Jolivet, A. Rauch, H.-R. Luscher and W. Gerstner (2006) Predicting spike timing of neocortical pyramidal neurons by simple threshold models, Journal of Computational Neuroscience 21:35-49 Romain Brette and Wulfram Gerstner (2005) Adaptive Exponential Integrate-and-Fire Model as an Effective Description of Neuronal Activity, J Neurophysiol, 94: 3637 - 3642 - Models of STDP J.-P. Pfister, T. Toyoizumi, D. Barber, and W. Gerstner (2006) Optimal Spike-Timing Dependent Plasticity for Precise Action Potential Firing in supervised learning Neural Computation 18:1309-1339 T. Toyoizumi, J.-P. Pfister, K. Aihara, and W. Gerstner (2005) Generalized Bienenstock-Cooper-Munro rule for spiking neurons that maximizes information transmission Proc. Natl. Acad. Sci. USA, 102:5239-5244 J.-P. Pfister and W. Gerstner (2005) Beyond Pair-Based STDP: a Phenomenological Rule for Spike Triplet and Frequency Effects. IN: Advances in Neural Information Processing Systems 18, Y. Weiss and B. Sch?lkopf and J. Platt, MIT Press, Cambridge, pp 1083--1090 ------- PostDoctoral positions are for an initial period of 2 years with a flexible starting date. Applications including - a 1 page statement of research interests - CV with publications - names and contact details of 3 referees should be sent in pdf format to Wulfram.Gerstner at epfl.ch -- Renaud Jolivet PhD Brain Mind Institute EPFL -- http://icwww.epfl.ch/~rjolivet +41 21 693 9687 From gwestermann at brookes.ac.uk Sun Sep 10 16:03:01 2006 From: gwestermann at brookes.ac.uk (Gert Westermann) Date: Sun, 10 Sep 2006 21:03:01 +0100 Subject: Connectionists: Jobs: two postdocs in connectionist modelling Message-ID: <45046F75.4020102@brookes.ac.uk> University of Oxford, Department of Experimental Psychology and Oxford Brookes University, Department of Psychology Two postdoctoral positions in connectionist modelling Oxford University and Oxford Brookes University are pleased to advertise two posts linked to the planned new Oxford Centre for Connectionist Modelling to investigate phenomena of linguistic and cognitive development and normal and impaired adult processing with computational models. Two three-year ESRC-funded post-doctoral research positions in connectionist modelling are now available to work with Dr. Gert Westermann and Prof. Kim Plunkett on models of word learning and inflection processing. Candidates for both positions should have a PhD in Psychology or a related subject, good programming skills, and experience with using connectionist neural network models in psychological modelling. Position 1: This position is mainly based in the Department of Psychology at Oxford Brookes University to work with Dr Gert Westermann on models of the development, normal and impaired adult processing of verb inflections in English and German. This project will involve developing neural network models to explore the link between brain development and cognitive development in verb inflection processing as well as adult functional brain organization. Salary is in the range of ?24,886- ?27,103. Ref: 265/15846/BC For informal enquiries about this position please contact Dr Gert Westermann, gwestermann at brookes.ac.uk Further details are available at http://www.brookes.ac.uk/vacancy/ Position 2: This position is mainly based in the Dept. of Experimental Psychology, University of Oxford, to work with Prof. Kim Plunkett on models of word learning in infancy. This project will involve developing neural network models to explore the link between brain development and cognitive development in early word learning. An important part of the research will involve identifying network architectures that are particularly well-suited to the multi-modal aspects of lexical development. Grade 7: Salary is in the range ?24,886-?30,607. For informal enquiries about this position please contact Prof Kim Plunkett, kim.plunkett at psy.ox.ac.uk Before submitting an application for this position, candidates should obtain further particulars from http://www.psy.ox.ac.uk or the Administrator (e-mail: applications at psy.ox.ac.uk or telephone 01865 271399) quoting reference CQ/06/016. The closing date for both positions is 6 October 2006. Interviews will be held in mid-October for a starting date as soon as possible thereafter. Interviews for both positions will be held together, and applicants should indicate whether they wish to be considered for one or both positions. -- ===================================================================== Dr. Gert Westermann gwestermann at brookes.ac.uk Department of Psychology, Oxford Brookes University, Oxford OX3 0BP Tel +44 (0)1865 271 400 Fax: +44 (0)1865 48 38 87 http://www.cbcd.bbk.ac.uk/people/gert/ ===================================================================== From t.heskes at science.ru.nl Tue Sep 12 09:38:50 2006 From: t.heskes at science.ru.nl (Tom Heskes) Date: Tue, 12 Sep 2006 15:38:50 +0200 Subject: Connectionists: Neurocomputing volume 69 (issues 16-18) Message-ID: <4506B86A.6000801@science.ru.nl> Neurocomputing volume 69 (issues 16-18) ------- SPECIAL PAPERS (Brain inspired cognitive systems edited by Amir Hussain, Leslie S. Smith and Igor Alexander) Brain inspired cognitive systems (BICS 2004) Amir Hussain, Leslie S. Smith and Igor Alexander Symmetry axis extraction by a neural network Kunihiko Fukushima and Masayuki Kikuchi The oscillatory dynamic link matcher for spiking-neuron-based pattern recognition Ramin Pichevar, Jean Rouat and Le Tan Thanh Tai A binary neural decision table classifier Victoria J. Hodge, Simon O?Keefe and Jim Austin Mixed-signal neuron-synapse implementation for large-scale neural network Il Song Han A novel multiple-controller incorporating a radial basis function neural network based generalized learning model Ali S. Zayed, Amir Hussain and Rudwan A. Abdullah A new biclustering technique based on crossing minimization Ahsan Abdullah and Amir Hussain Effects of NMDA and non-NMDA receptors antagonists on the dynamic behavior of cultured cortical networks L. Bonzano, M. Bove and S. Martinoia An artificial early visual model adopting spike-timing-dependent plasticity Zhijun Yang and Alan F. Murray Learning under weight constraints in networks of temporal encoding spiking neurons Q.X. Wu, T.M. McGinnity, L.P. Maguire, B. Glackin and A. Belatreche Executive attention, task selection and attention-based learning in a neurally controlled simulated robot Jason Garforth, Sue L. McHale and Anthony Meehan Spatio-temporal information coding in the cuneate nucleus J. Navarro, E. S?nchez and A. Canedo Balancing plasticity and stability of on-line learning based on hierarchical Bayesian adaptation of forgetting factors Junichiro Hirayama, Junichiro Yoshimoto and Shin Ishii Design and basic blocks of a neuromorphic VLSI analogue vision system Jordi Cosp, Jordi Madrenas and Daniel Fern?ndez Selective attention implemented with dynamic synapses and integrate-and-fire neurons Chiara Bartolozzi and Giacomo Indiveri Modelling the interaction of attention and emotion N. Fragopanagos and J.G. Taylor A model of agent consciousness and its implementation Ivan Moura Eye movement predictions on natural videos Martin B?hme, Michael Dorr, Christopher Krause, Thomas Martinetz and Erhardt Barth Understanding spike-time-dependent plasticity: A biologically motivated computational model Matthew Hartley, Neill Taylor and John Taylor ------- REGULAR PAPERS Adaptive multiple sets of CSS features for hand posture recognition Chin-Chen Chang Learning with generalized-mean neuron model R.N. Yadav, Nimit Kumar, Prem K. Kalra and Joseph John Kernel self-organising maps for classification K.W. Lau, H. Yin and S. Hubbard GOLS?Genetic orthogonal least squares algorithm for training RBF networks A.M.S. Barreto, H.J.C. Barbosa and N.F.F. Ebecken A filter bank approach to independent component analysis for convolved mixtures Hyung-Min Park, Chandra Shekhar Dhir, Sang-Hoon Oh and Soo-Young Lee A novel genetic reinforcement learning for nonlinear fuzzy control problems Cheng-Jian Lin and Yong-Ji Xu Global exponential stability of BAM neural networks with recent-history distributed delays and impulses Bingwen Liu and Lihong Huang Dynamic pruning algorithm for multilayer perceptron based neural control systems Jie Ni and Qing Song Stochastic saliency-based search model for search asymmetry with uncertain targets Takahiko Koike and Jun Saiki Deductive rules in holographic reduced representation Vladim?r Kvasni?ka and Ji?? Posp?chal Simple neuron-based adaptive controller for a nonholonomic mobile robot including actuator dynamics Tamoghna Das, I.N. Kar and S. Chaudhury Existence and exponential stability of periodic solution for BAM neural networks with periodic coefficients and delays Yanqing Liu and Wansheng Tang The effect of different basis functions on a radial basis function network for time series prediction: A comparative study C. Harpham and C.W. Dawson Parallel reinforcement learning using multiple reward signals Peter Raicevic Building meaningful representations for nonlinear modeling of 1d- and 2d-signals: applications to biomedical signals R. Dubois, B. Quenet, Y. Faisandier and G. Dreyfus Evolved neural networks based on cellular automata for sensory-motor controller Kyung-Joong Kim and Sung-Bae Cho Integrating the improved CBP model with kernel SOM Qun Dai and Songcan Chen Probabilistic PCA for t distributions J. Zhao and Q. Jiang LIRA neural classifier for handwritten digit recognition and visual controlled microassembly Ernst Kussul and Tatiana Baidyk Margin-based wrapper methods for gene identification using microarray Xue-Wen Chen ICA with Reference Wei Lu and Jagath C. Rajapakse Finding cancer subtypes in microarray data using random projections Debashis Ghosh Evolutionary system for automatically constructing and adapting radial basis function networks Daniel Manrique, Juan R?os and Alfonso Rodr?guez-Pat?n A new ARTMAP-based neural network for incremental learning Mu-Chun Su, Jonathan Lee and Kuo-Lung Hsieh Analysis of two restart algorithms Wei Lin and Tianping Chen Genetic tracker with neural network for single and multiple target tracking Ilke Turkmen, Kerim Guney and Dervis Karaboga Fast computation with neural oscillators Wei Wang and Jean-Jacques E. Slotine An image coding scheme using SMVQ and support vector machines Chin-Chen Chang and Chia-Te Liao ------- BRIEF PAPERS A deformation-invariant image-based fingerprint verification system Loris Nanni and Alessandra Lumini Phase space learning in an autonomous dynamical neural network Hiroshi Inazawa and Garrison W. Cottrell Secure hash function based on neural network Shiguo Lian, Jinsheng Sun and Zhiquan Wang A variational method for learning sparse Bayesian regression Mingjun Zhong Flexible kernels for RBF networks Andre O. Falc?o, Thibault Langlois and Andreas Wichert New fast time delay neural networks using cross correlation performed in the frequency domain Hazem M. El-Bakry Image restoration using variational PDE-based neural network Ya-Dong Wu, Qing-Xin Zhu, Shi-Xin Sun and Hong-Ying Zhang Improved extreme learning machine for function approximation by encoding a priori information Fei Han and De-Shuang Huang New LMI conditions for delay-dependent asymptotic stability of delayed Hopfield neural networks Xuyang Lou and Baotong Cui Hardware?software partitioning of real-time operating systems using Hopfield neural networks Bing Guo, Dianhui Wang, Yan Shen and Zhong Liu Combining labeled and unlabeled data with graph embedding Haitao Zhao Empirical tests on BioHashing Loris Nanni and Alessandra Lumini A novel adaptive sequential niche technique for multimodal function optimization Jun Zhang, De-Shuang Huang, Tat-Ming Lok and Michael R. Lyu An advanced multi-matcher method for on-line signature verification featuring global features and tokenised random numbers Loris Nanni Feature selection in independent component subspace for microarray data classification Chun-Hou Zheng, De-Shuang Huang and Li Shang Image binarization focusing on objects Songcan Chen and Daohong Li Non-combinatorial estimation of independent autoregressive sources Barnab?s P?czos and Andr?s L?rincz On-line estimation of the final prediction error via recursive least-squares method John Sum and Kevin Ho Prototype-based fuzzy classification with local relevance for proteomics T. Villmann, F.-M. Schleif and B. Hammer Applying genetic algorithm for classifying anomalous TCP/IP packets Taeshik Shon, Xeno Kovah and Jongsub Moon A novel ensemble of classifiers for protein fold recognition Loris Nanni Global optimal ICA and its application in MEG data analysis Lei Xie and Jun Wu Sampled FLDA for face recognition with single training image per person Hongtao Yin, Ping Fu and Shengwei Meng Reduced complexity RBF classifiers with support vector centres and dynamic decay adjustment Renzo Perfetti and Elisa Ricci A new methodology for in situ calibration of a neural network-based software sensor for S-parameter prediction in six-port reflectometers J.L. Pedre?o-Molina, M. Pinzolas and J. Monz?-Cabrera On the reduction of complexity in the architecture of fuzzy ARTMAP with dynamic decay adjustment Shing Chiang Tan, M.V.C. Rao and Chee Peng Lim Remarks on BioHashing based cancelable biometrics in verification system Andrew Teoh Beng Jin and Tee Connie ------- JOURNAL SITE: http://www.elsevier.com/locate/neucom SCIENCE DIRECT: http://www.sciencedirect.com/science/journal/09252312 From bhanu.prasad at famu.edu Wed Sep 6 09:03:28 2006 From: bhanu.prasad at famu.edu (Bhanu Prasad) Date: Wed, 6 Sep 2006 09:03:28 -0400 Subject: Connectionists: Call for book chapters Message-ID: <723175C2360BAE44A77F135E68A9E84901814818@its-exch2k3be1.FAMU.EDU> SECOND CALL FOR BOOK CHAPTER CONTRIBUTIONS SUBMISSION DEADLINE EXTENDED UNTIL OCTOBER 4 2006 (people who already submitted their abstracts need not respond to this email) Book Title: Speech, Audio, Image and Biomedical Signal Processing using Neural Networks Editors: Dr. Bhanu Prasad 1 and Dr. S. R. Mahadeva Prasanna 2 Publisher: Springer-Verlag, Germany Year of Publication: 2007 BACKGROUND AND MOTIVATION Neural networks are being used for processing speech, audio, image and biomedical signals for many years. Some of the applications in speech processing where neural networks are extensively used include speech recognition, speaker recognition, speech enhancement, speech coding and speech synthesis. In audio processing, neural networks are used for speech/music classification, audio classification and audio indexing and retrieval. Edge extraction, texture classification, face recognition, character recognition, finger print identification, image enhancement and image coding are some of the applications of neural networks in image processing. Neural networks are also used for the identification of biomedical signals, different diseases, medical image processing and ECG signal processing. The articles related to the applications of neural networks in speech, audio, image and biomedical signal processing are spread in the literature across different journals, conference proceedings and books. The objective of this book is to provide a common platform for all the researchers working in the above mentioned areas to consolidate their research findings in the form of book chapters. Review articles on the usefulness of neural networks in the above mentioned signal processing areas are also planned to be included in this book. The proposed book is aimed to serve the research community mainly in the following ways: ? The reader is equipped with the basics of signal processing like a course on digital signal processing and is interested in pursuing a research career in the application areas of signal processing. Articles on the fundamentals of speech, audio, image and biomedical signal processing and also neural networks will provide the necessary background for the beginner to start research work in these areas. ? The reader has completed first courses in one of the above mentioned signal processing areas say speech processing and neural networks and is curious to know how to use neural network models in some of the tasks like speech recognition, speaker recognition and so on. For such a reader this book will be a good starting point since information about the applications of neural networks for these tasks and also rich literature related to them will be present. ? The reader has used neural network models in one of the signal processing areas say speech processing and would like to know how they are and can be used in other signal processing areas like audio, image and biomedical signals. For such a reader this book will be a good source where applications of neural networks for processing different types of signals can be found. CALL FOR ABSTRACTS The prospective authors who are working in one or more of the above mentioned areas can email an extended abstract of 1500-2000 words describing the scope of the work that will be included in their proposed chapters. Since it is proposed to conduct a blind review of the submitted abstracts, it is strongly suggested not to reveal their identity in any form. The abstract needs to be submitted in WORD/PDF format and should contain only chapter title and text of abstract without any affiliation details. The author details including the affiliations should be included within the body of the email. Notification of acceptance/rejection will be intimated by email. MAIL YOUR ABSTRACTS TO prasanna at iitg.ernet.in and CC to srmp1944 at yahoo.co.in NEW IMPORTANT DATES Last Date for Receiving Abstract: 1st October 2006 Notification of Acceptance/Rejection: 1st November 2006 Camera Ready Version of Chapter: 1st January 2007 CONTACT INFORMATION Dr. S. R. Mahadeva Prasanna Department of Electronics and Communication Engineering Indian Institute of Technology Guwahati Guwahati-781039, Assam, India Email: prasanna at iitg.ernet.in and CC to srmp1944 at yahoo.co.in Tel:+91-361-2582513 (office) Fax:+91-361-2582542 Web: http://www.iitg.ernet.in/engfac/ece/public_html/srmp.htm _________________________________________________________________________________________________ 1 Department of Computer and Information Sciences, Florida A&M University, Tallahassee, FL 32307 USA., email: bhanupvsr at gmail.com, bhanu.prasad at famu.edu 2 Department of Electronics and Communication Engineering, Indian Institute of Technology Guwahati, Guwahati-781039, Assam, India., email: prasanna at iitg.ernet.in and CC to srmp1944 at yahoo.co.in From franco at ulisse.cib.na.cnr.it Tue Sep 12 10:53:18 2006 From: franco at ulisse.cib.na.cnr.it (FVentriglia) Date: Tue, 12 Sep 2006 16:53:18 +0200 Subject: Connectionists: BVAi2007 - International Symposium Message-ID: <7.0.1.0.0.20060912165017.01f8ac70@ulisse.cib.na.cnr.it> ********************************************************************* Subject: Announcement and Call For Papers: BVAI 2007 ********************************************************************* *** Apologies for multiple copies *** ANNOUNCEMENT and CALL FOR PAPERS 2nd International Symposium on "Brain, Vision and Artificial Intelligence" (BVAI 2007) Naples-Italy, October 10-12, 2007 BVAI 2007 is organised by researchers of the Institute of Cybernetics "E. Caianiello" of the Italian National Research Council, and will be held in Naples, Italy, 10-12 October 2007. The scientific program will include, besides eight invited talks, contributed papers that will be presented in plenary oral or poster sessions. Original and unpublished papers on BVAI 2007 main research areas and related topics are welcome. Main research areas The basic Brain: Neurobiology, Biophysics and Computational Theories Natural Vision: Visual Neuroscience, Visual Perception and Visual Cognition Artificial Vision: Pattern Recognition, Computer Vision, Biometrics Artificial Intelligence: Intelligent Systems, Robotics and Human Computer Interaction. Invited Speakers: Michael Arbib (USA) Matteo Carandini (USA) Karl Gegenfurtner (Germany) Jose' Millan (Switerland) Petr Lansky (Czech) Oliviero Stock (Italy) John K. Tsotsos (Canada) Massimo Tistarelli (Italy) Important Dates: Paper Submission 1 March 2007 Acceptance Notification 11 May 2007 Camera-ready Papers 11 June 2007 BVAI 2007 Proceedings, including all accepted contributions, will be published by Springer-Verlag in the series Lecture Notes in Computer Science (www.springer.com/lncs). In addition, two special issues of international journals are planned, which will include extended versions of selected BVAI 2007 papers. Visit the WWW BVAI 2007 Page http://bvai.cib.na.cnr.it/BVAI2007 for more details and updated information. Email Contact: bvai2007 at biocib.cib.na.cnr.it Add a bookmark to: http://bvai.cib.na.cnr.it/BVAI2007 -------------- next part -------------- No virus found in this outgoing message. Checked by AVG Free Edition. Version: 7.1.405 / Virus Database: 268.12.3/445 - Release Date: 11/09/2006 From lendasse at james.hut.fi Fri Sep 8 11:24:51 2006 From: lendasse at james.hut.fi (Amaury Lendasse) Date: Fri, 8 Sep 2006 18:24:51 +0300 Subject: Connectionists: Time Series Symposium in Finland Message-ID: <002401c6d35a$eda811d0$9aade982@itlpc54> **We apologize for possible duplicates of this message, sent to distributions lists only** Please find enclosed the Call for Papers of the European Symposium on Time Series Prediction, which will be held in Otaniemi (Espoo), Finland, 07 - 09 February 2007, www.estsp2007.org. ESTSP 2007 07 - 09 February 2007 The first European Symposium on Time Series Prediction (TSP) is a new event in the fields of Neural Networks, Statistics and Econometrics. It will be held in Espoo (Helsinki), one of the most innovative towns in Europe. Contributions are welcome. Webpage: http://www.estsp2007.org/ DEADLINES Submission of papers: 22 November 2006 Notification of acceptance: 15 December 2006 ESTSP conference: 07 - 09 February 2007 PREDICTION COMPETITION A new prediction competition is organized. The goal of the competition is the long-term prediction of a new benchmark. The dataset will be available on October 1st. The competition deadline is on November 22nd, same date as the paper submission deadline. The schedule of the competition will favor fast methods. PROCEEDINGS AND JOURNAL SPECIAL ISSUE The proceedings will include all communications presented to the conference, and will be available on-site. Extended versions of selected papers will be published in the Neurocomputing journal (Elsevier). LOCATION The ESTSP 2007 conference will be held at the Helsinki University of Technology in Dipoli conference center. Helsinki University of Technology is one of the top universities in Finland for both education and research. The ESTSP 2007 is organized by the Adaptive Informatics Research Centre from the Laboratory of Computer and Information Science (CIS) of HUT. Espoo, a high-tech metropolis, surrounded by nature is a lively and buzzling city in the greater Helsinki region. The conference will be organized in a conference center located near the university at a walking distance from the Radisson SAS Hotel of Espoo. Conference location: Dipoli Conference Center Otakaari 24 FI-02150 ESPOO, FINLAND CONTACT AND CONFERENCE SECRETARIAT All questions concerning ESTSP'2007 may be sent by e-mail (preferred) to estsp2007 at estsp2007.org. Contact address: Dr. Amaury Lendasse Helsinki University of Technology Laboratory of Computer and Information Science P.O. Box 5400 FI-02015 HUT FINLAND fax +358-9-451 3277 http://www.estsp2007.org/ From Eugene.Izhikevich at nsi.edu Tue Sep 12 20:18:38 2006 From: Eugene.Izhikevich at nsi.edu (Eugene M. Izhikevich) Date: Tue, 12 Sep 2006 17:18:38 -0700 Subject: Connectionists: Scholarpedia: Encyclopedia of Computational Intelligence Message-ID: <45074E5E.6050807@nsi.edu> All connectionists are invited to participate in the election of authors for the Encyclopedia of Computational Intelligence, which is hosted by scholarpedia.org ? the free peer-reviewed encyclopedia. Scholarpedia is a synthesis of Encyclopedia Britannica and Wikipedia. It feels and looks like Wikipedia, with the exception that (1) Each article is written by an expert. (2) Each article is anonymously peer reviewed to ensure accurate and reliable information. (3) Each article has a curator - typically its author -- who is responsible for its content. (4) Any modification of the article needs to be approved by the curator before it appears in the final, approved version. Currently, Scholarpedia hosts Encyclopedia of Computational Neuroscience, Encyclopedia of Dynamical Systems, and Encyclopedia of Computational Intelligence. All will be published in a printed form. A unique feature of Scholarpedia is that its authors are either invited by the editor-in-chief or elected by the public - you. Public election of authors ensures fairness in assigning articles to the corresponding experts in each field. You are invited to register as a ?Scholar? using the invitation key ?IEEE?. This would allow you to vote for authors, nominate people for articles, and even initiate election for new articles. Self-nominations are welcomed. Read more about Scholarpedia at http://www.scholarpedia.org. Click at http://www.scholarpedia.org/article/Encyclopedia_of_Computational_Intelligence to see the list of suggested articles for the encyclopedia. Feel free to modify it and add new topics. Most popular election: 'Spike-Timing Dependent Plasticity' (55 voters) Most nominated article: 'Dynamic Clamp' (9 candidates) Among participants of Scholarpedia are M. Abeles (Synfire Chains), J.A. Anderson (Brain-State-in-a-Box), M. Arbib (NSL), A.-L. Barabasi (Scale-Free Networks), A.G. Barto (Temporal Difference Learning), L.O. Chua (Chua Circuit), J. Conway (Game of Life), M. Dorigo (Swarm Intelligence), G.M. Edelman (Neural Darwinism), R. FitzHugh (FitzHugh-Nagumo Model), D. Floreano (Evolutionary Robotics), W.J. Freeman (Intentionality), K. Fukushima (Neocognitron), S. Grossberg (ART), H. Haken (Synergetics), R. Hecht-Nielsen (Confabulation Theory), G.E. Hinton (Boltzmann Machine), J.H. Holland (Genetic Algorithms), J.J. Hopfield (Hopfield Network), S. Kirkpatrick (Simulated Annealing), T. Kohonen (Kohonen Network), E.N. Lorenz (Butterfly Effect), B. Mandelbrot (Fractals), J.L. McClelland (PDP), V. Mountcastle (Cortical Columns), V. Piuri (Computational Intelligence), W. Schultz (Reward), T.J. Sejnowski, W. Singer (Binding by Synchrony), J. G. Taylor (Mind-Body Problem), C. von der Malsburg (Dynamic Link Architecture), C. Watkins (Q-Learning), B. Widrow (ADALINE), L. Zadeh (Fuzzy Logic), and many others. Your invitation key is 'IEEE'. Eugene M. Izhikevich, The Neurosciences Institute, San Diego, California. From d.mareschal at bbk.ac.uk Wed Sep 13 07:51:19 2006 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Wed, 13 Sep 2006 12:51:19 +0100 Subject: Connectionists: Phd in Developmental Cognitive Neuroscience Message-ID: Dear Colleagues, Please circulate to appropriate people. Best regards, Denis Mareschal -------------------- The Centre for Brain and Cognitive Development in London is looking to fill 1 a 3-year Phd position funded by the European Commission through the Marie Curie training programme. The successful candidate would be expected to carry out a PhD in any area of expertise related to the research interests of the members of the Centre. The research will focus on typical and/or atypical development and could involve learning a number of different methods including experimental infant testing, EEG, optical imaging, fMRI, computational and neural network modelling. Suitable candidates should be of outstanding academic potential and have reached a Masters level of training (4 years higher education). Further details of the Centre's research and the position (including EC residency and mobility requirements) can be found on (http://www.cbcd.bbk.ac.uk/cbcd.html). Interested candidates should address enquiries to Professor Denis Mareschal (d.mareschal at bbk.ac.uk) -- ================================================= Professor Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 (0)20 7631-6582/6226 reception: 6207 fax +44 (0)20 7631-6312 http://www.psyc.bbk.ac.uk/people/academic/mareschal_d/ ================================================= From benjamin.schrauwen at elis.ugent.be Wed Sep 13 04:08:10 2006 From: benjamin.schrauwen at elis.ugent.be (Benjamin Schrauwen) Date: Wed, 13 Sep 2006 10:08:10 +0200 Subject: Connectionists: PhD positions on Reservoir Computing In-Reply-To: References: Message-ID: <4507BC6A.6070302@elis.ugent.be> Job opening for 2 PhD positions at the ELectronics and Information Systems department, Ghent University, Belgium Liquid State Machines, Echo State Networks and Back-Propagation Decorrelation (generally termed Reservoir Computing) all use a random, fixed recurrent network of neurons as dynamic reservoir which makes a spatio-temporal pre-mapping of the input data. This pre-mapped representation is processed by simple linear techniques such as linear regression. Only this last, linear part needs to be trained. This way the good temporal processing properties of recurrent networks get combined with the ease of training of linear techniques. The method has been applied successfully to speech recognition, robotics and system modelling. The faculty of Engineering at Ghent University has possible funding available for PhD students (two four year positions) in two projects concerning research on Reservoir Computing. One concerns the application of Reservoir Computing to the detection of epileptic seizures using novel sensor techniques, the other investigates the use of nano-photonic devices instead of software-simulated neural networks as reservoirs. We offer an exciting job in a stimulating environment, with a nice amount of flexibility and academic liberty. Our research group has a thorough expertise in the research area. Applicants should have a Masters degree in Engineering, Informatics, Mathematics or Physics/Photonics. The ideal candidates should have a background or previous experience in neural networks, pattern classification or AI. For more information or to send your CV and a short motivation text, mail to "Benjamin dot Schrauwen at UGent.be". From wolpert at eng.cam.ac.uk Thu Sep 14 04:37:13 2006 From: wolpert at eng.cam.ac.uk (Daniel Wolpert) Date: Thu, 14 Sep 2006 09:37:13 +0100 Subject: Connectionists: Research Associate in Computational Sensorimotor Control Message-ID: <002901c6d7d8$fa1648b0$0d96a981@motor> UNIVERSITY OF CAMBRIDGE DEPARTMENT OF ENGINEERING Research Associate in Computational Sensorimotor Control We are currently seeking a highly motivated Research Associates (postdoctoral fellows) to join our group working on theoretical and experimental approaches to human sensorimotor control. The project is funded by an EU grant led by Professor Daniel Wolpert and involves investigating the processes involved in motor learning, sensorimotor integration and control. The successful applicants will be expected to conduct independent research involving both computational and experimental studies in humans. Candidates should have a Ph.D. in Neuroscience, Psychology, or Physical and Engineering Sciences relevant to sensorimotor control, with an academic record of scientific excellence, independent research, and a strong interest in an interdisciplinary approach to motor control. A strong mathematical, statistical, and/or computational background and experience with computers and programming (Matlab, C++, etc.) is expected. Applicants with a strong computational background relevant to neuroscience who wish to learn experimental approaches will also be considered. The appointment will be for two years initially starting November 1st, 2006 or as soon as possible thereafter. Salary is in the range ?24,161-?31,525 p.a. Further details of the posts are available on www.wolpertlab.com Informal enquiries should be addressed by email to Professor Wolpert (wolpert at eng.cam.ac.uk). Applicants are asked to submit (a) a cover letter describing their research experiences, interests, and goals, (b) a curriculum vitae, (c) the names and contact information of three individuals who can serve as references. These should be sent to Mrs. J. Milne (preferably by email jrm16 at eng.cam.ac.uk), Department of Engineering, Trumpington Street, Cambridge, CB2 1PZ, UK to arrive prior to September 29th, 2006. From laurent.perrinet at incm.cnrs-mrs.fr Thu Sep 14 10:24:41 2006 From: laurent.perrinet at incm.cnrs-mrs.fr (Laurent Perrinet) Date: Thu, 14 Sep 2006 16:24:41 +0200 Subject: Connectionists: [PostDoc] Computational Neuroscience: "Functional, Large-scale Models of Visual Motion Perception" Message-ID: Post-doctoral Position in Computational Neuroscience: "Functional, Large-scale Models of Visual Motion Perception" DyVA team, INCM (CNRS) in Marseille, France We are currently inviting applications for a postdoctoral position in computational neuroscience to study functional, large-scale models of visual motion perception. The post is for up to 3 years in the DyVA team at the INCM (CNRS) in Marseille, France and will be funded within the european FACETS consortium. The project will involve developing, designing and implementing large- scale neural networks of the primary visual areas. The goal is to bridge theoretical principles of computations, physiological data (e.g. optical imaging) and behavioral data (e.g. eye movements) to bring new understanding on the neural computations underlying the perception of motion. We are particularly interested in the dynamics of motion integration, focusing on responses to complex motion stimuli in areas V1 and V5/MT. Our theoretical approaches span from statistical inference to adaptive distributed representations to provide insights into these parallel, dynamical processes. We use state-of-the-art simulation software to validate these results thanks to our computer facilities, with the goal of transferring this technology to aVLSI chips developped within the consortium. -> More material and links at http://incm.cnrs-mrs.fr/perrinet/dynn/PostdoctoralPosition Interested candidates should send their application materials - cover letter, CV, statement of research interests and research experience (no .doc file, please) or informal enquiries to Dr. Laurent Perrinet ( mailto:Laurent.Perrinet at incm.cnrs-mrs.fr ). ---- Laurent Perrinet - INCM(UMR6193)/CNRS - http://incm.cnrs-mrs.fr/perrinet/ From lyle at biomedicale.univ-paris5.fr Mon Sep 18 05:46:41 2006 From: lyle at biomedicale.univ-paris5.fr (Lyle Graham) Date: Mon, 18 Sep 2006 11:46:41 +0200 Subject: Connectionists: Postdoctoral Position in Visual Cortical Neurophysiology - CNRS Paris Message-ID: <019601c6db07$5884f3c0$0d3e14ac@biomedicale.univparis5.fr> Postdoctoral Position in Visual Cortical Neurophysiology - CNRS Paris I am looking for an experimental postdoc for a project aimed at characterizing the functional impact of membrane channels and synaptic dynamics in visual cortical neurophysiology (see lab website at www.neurophys.biomedicale.univ-paris5.fr/~graham). This person will focus on in-vivo whole cell patch recordings in the cat and rat, including the development of several novel protocols and methods. The work will be closely allied with the analysis of the stochastic component of evoked and background activity from intracellular recordings, and of biophysically-detailed models of cortical neurons and networks. The contract will be initially for one year, with possible extension to a total of three years, and can start as early as November 2006. Experience required in either computational neuroscience, electrical engineering, applied physics, or electrophysiology. Interested candidates may send their c.v. and two letters of recommendation to lyle at biomedicale.univ-paris5.fr or to this mail address: Lyle J. Graham Laboratory of Neurophysics and Physiology, CNRS UMR 8119 Universit? Ren? Descartes 45 rue des Saint-P?res, 75006 Paris Lyle J. Graham Laboratory of Neurophysics and Physiology, CNRS UMR 8119 www.neurophys.biomedicale.univ-paris5.fr/~graham UFR Biom?dicale de l'Universit? Ren? Descartes 45 rue des Saint-P?res, 75006 Paris Tel: 33 1 42 86 20 92 (Secr?tariat: 33 1 42 86 21 38) Fax: 33 1 49 27 90 62 From nicolas.brunel at univ-paris5.fr Mon Sep 18 11:34:41 2006 From: nicolas.brunel at univ-paris5.fr (Nicolas Brunel) Date: Mon, 18 Sep 2006 17:34:41 +0200 Subject: Connectionists: Call for proposal to host the Advanced Course in Computational Neuroscience Message-ID: <450EBC91.7060706@univ-paris5.fr> The organizing committee of the "European Advanced Course in Computational Neuroscience" is looking for applications for potential sites to host the course for 3 years (2008-2010). The course is now in its eleventh year. It was held first in Crete (Greece, 1996-1998), and then in Trieste (Italy, 1999-2001) and Obidos (Portugal, 2002-2004). It is currently held in Arcachon (France, 2005-2007). Each year, around 25 lecturers and tutors teach 30 graduate students, postdocs and junior faculty; many research groups across the world have thus been nucleated and nurtured. Traditionally, the course is held in August in a European (or Associated) country. The ideal site is relatively remote and small (ie not a large institution in a big city), in order to ensure intimacy and quietness, and be an attractive location to spend part of the summer. We also need a relatively fast internet connection for the computer network. Critical to the success and smooth-running of the course is the local organizer. S/he is responsible for sorting out and arranging for local facilities, such as lodging, food, transport, rooms to hold the lectures and the computer network to a budget provided by the course. We will need a firm commitment to secure everything for a period of three years (2008-2010). Anyone interested should contact Nicolas Brunel (see address below) and will be requested to send details such as a description of the site and approximate budget including estimated costs for lodging, food, rental of computers, etc. In practice, we need: - lecture room(s), with a capacity of about 50 seats; - computer room(s), that can fit computers for about 50 people, with a fast internet connection; - affordable lodging for about 50 people for four weeks, close to the lecture/computer rooms (university accommodation could be fine) - affordable food (restaurant or other) for about 50 people, close to the lecture/computer rooms; In addition, it would be nice to have: - kitchen/dining room that students can use during the week-ends - a secretary that can handle communication with faculty/students during the months preceding the school; - a full-time systems manager for computer network for the duration of the school - possibilities of local funding. A site-visit to selected locations will take place at the beginning of 2007. Below are contact addresses and a short description of the course CONTACT Nicolas Brunel Laboratory of Neurophysics and Physiology UMR 8119 CNRS-Universite Rene Descartes 45 rue des Saints Peres 75270 Paris Cedex 06 Tel (33).1.42.86.20.58 - Fax (33).1.49.27.90.62 nicolas.brunel at univ-paris5.fr www.neurophys.biomedicale.univ-paris5.fr/~brunel SHORT DESCRIPTION OF THE COURSE The European Advanced Course in Computational Neuroscience is a high-level 4-week intensive course on the computational aspects of the central nervous system function, from the cellular to the systems level. It is usually structured in 4 thematic weeks, going from the cellular to systems level. The invited faculty are among the best scientists in their respective fields (both experimental and theoretical; see web site for past programs). The course is highly selective - we receive from 90 to 180 applications every year, from which 25 to 30 students are selected. Students are mid-term PhD or postdocs, and can be of any background (usually a mixture of experimentalists and theoreticians). The course is intended to give them a solid basis on the different aspects that are important to understand the complexity of the nervous system, as well as the different approaches that have been used in theoretical studies. Students are required to do a research project during the course, and are helped by the faculty and tutors. The selection of students is based on letters of recommendation and the advice of three independent referees. More information is available at our website: http://www.neuroinf.org/courses/EUCOURSE/EU06/courses.shtml From doug.aberdeen at anu.edu.au Tue Sep 19 02:33:58 2006 From: doug.aberdeen at anu.edu.au (Douglas Aberdeen) Date: Tue, 19 Sep 2006 16:33:58 +1000 Subject: Connectionists: Research Positions in Reinforcement Learning, Australia Message-ID: <8D873AC0-088F-4970-8C82-8D742D852986@anu.edu.au> * Research Positions in Reinforcement Learning, Australia * National ICT Australia (NICTA), Canberra Lab, have open post-doc, researcher, and senior researcher positions in the area of reinforcement learning (RL). These positions have been created to expand the current RL group within NICTAs Statistical Machine Learning Program (http://sml.nicta.com.au/), headed by Dr Alex Smola. The current RL group consists of Dr Douglas Aberdeen, Dr Olivier Buffet, plus a research engineer and students. The RL group currently has an interest in the use of RL methods for decision-theoretic planning, and thus has a strong relationship with NICTAs co-located planning group headed by Sylvie Thiebaux and Jussi Rintanen. The rest of the Statistical Machine Learning group has interests in kernel methods, optimisation, graphical models, bio-informatics and document analysis. NICTA is Australia's premier ICT (Information Communication Technology) research institute with approximately 300 researchers across the country, conducting a diverse range of technology research. The Statistical Machine Learning group is based in Canberra and conducts research in cooperation with the Australian National University (ANU). The ANU is consistently ranked in the top 10 universities in the Asia/Pacific region, and top 50 in the world. These are pure research positions, however a small amount of teaching through the ANU is encouraged. The duties of the position also include the supervision of research students, and participation in other Program activities. NICTA provides generous resources for travel, supporting visitors, and other activities such as commercialisation of research. Post-doc/researcher positions are typically 3 year fixed term. Senior researcher positions are typically ongoing. Applicants should indicate their preference for these positions. Salary will be commensurate with the background of the applicant, but are approximately in the range of $65,000 to $110,000 Australian dollars per year before tax. Formal applications should be made online at http://nicta.com.au/jobs.html, however please email questions or expressions-of-interest to doug.aberdeen at anu.edu.au. The closing date for applications is December 15, for positions to be taken up by April 2007 or earlier. -- Dr Douglas Aberdeen Senior Researcher Statistical Machine Learning National ICT Australia Limited Locked Bag 8001 Canberra ACT 2601 Tel. +61 2 6125 8647 Fax. +61 2 6125 8645 Email. doug.aberdeen at anu.edu.au Web. http://sml.nicta.com.au/~daa The imagination driving Australia's ICT future. To receive the latest NICTA information register at http:// nicta.com.au/registration.cfm From alan at cns.nyu.edu Tue Sep 19 10:17:12 2006 From: alan at cns.nyu.edu (alan stocker) Date: Tue, 19 Sep 2006 10:17:12 -0400 Subject: Connectionists: NIPS Demo Deadline - September 24 Message-ID: <450FFBE8.9030504@cns.nyu.edu> Reminder: The Deadline for NIPS Demonstration Proposals is Sunday, September 24, 2006. Demonstrators will have a chance to show their live and interactive demos in the areas of hardware technology, neuromorphic and biologically-inspired systems, robotics, and software simulations. New this year: NIPS is reserving 2-3 travel awards for students and young researchers presenting at the demonstration track. For further information see: http://www.nips.cc/Conferences/2006/Calls/Call%20For%20Demonstrations -- ________________________________________ alan a. stocker, ph.d. +1 212 992 8752 http://www.cns.nyu.edu/~alan/ ________________________________________ From Yann.Guermeur at loria.fr Tue Sep 19 17:44:30 2006 From: Yann.Guermeur at loria.fr (Yann.Guermeur@loria.fr) Date: Tue, 19 Sep 2006 23:44:30 +0200 Subject: Connectionists: Generalized VC dimensions for multi-class pattern recognition Message-ID: <1158702270.451064be0a013@www.loria.fr> Dear colleagues, I am interested in the statistical theory of large margin multi-class discriminant models, such as MLPs with several sigmoidal output units or multi-class SVMs. However, I could not find any reference on the VC theory of such models. I thus wrote the following report: "Large Margin Multi-category Discriminant Models and Scale-sensitive Psi-dimensions" https://hal.inria.fr/inria-00096091 which could be of some interest for the readers of this list. I am highly interested in feedbacks. Best regards, Yann Guermeur From nicola.cancedda at xrce.xerox.com Wed Sep 20 05:30:26 2006 From: nicola.cancedda at xrce.xerox.com (Nicola Cancedda) Date: Wed, 20 Sep 2006 11:30:26 +0200 Subject: Connectionists: Researcher in Machine Learning for Cross-Language Technologies at XRCE Message-ID: <45110A32.4050800@xrce.xerox.com> Position: Researcher in Machine Learning for Cross-Language Technologies The Cross-Language Technologies (CLT) group of the Xerox Research Centre Europe has the mission of researching and developing the most effective methods for crossing language barriers. Targeted applications include Statistical Machine Translation (SMT), multilingual terminology extraction, Cross-Language Information Retrieval (CLIR), Categorization and Clustering (CLCC). The team is part of the PASCAL European Network of Excellence, and is coordinating the SMART European project on the use of machine learning methods for translation and cross-language textual information access (starting October 1st), ensuring a strong network of academic collaboration. We are looking for a researcher with strong experience in Machine Learning to strengthen the CLT group. Responsibilities will include inventing, implementing and evaluating novel cross-language technologies, contributing to government funded and academic research projects, as well as contributing to setting and achieving the group's long-term research goals. Initially, we envisage research on: 1. Breakthrough techniques for training statistical translation and language models 2. Advanced latent-semantic representations of textual data XRCE maintains a high level of publications and patents: we expect the successful candidate to be part of these efforts. Applicants should possess a Ph. D. or equivalent in machine learning, optimization or statistics; experience in statistical machine translation is a definite plus. The successful candidate must have a serious interest in real-world applications and an inventive flair, coupled with the flexibility and initiative to pursue a dynamic array of research problems within a fast-working team. Excellent skills in algorithms and C++/C/Python/Perl/Matlab programming are required as well as good communication skills, particularly in English. To apply: Please email your CV, a covering letter and sample publications, with message subject "Cross-Language Technologies Researcher" to xrce-candidates at xrce.xerox.com and to Nicola.Cancedda at xrce.xerox.com. Xerox Research Centre Europe (XRCE) is a young, dynamic research organization, which creates innovative new business opportunities for Xerox in the digital and Internet markets. XRCE is a multicultural and multidisciplinary organization set in Grenoble, France. We have renowned expertise in machine learning, work practice studies, image processing, natural language processing and document structure. The variety of both cultures and disciplines at XRCE makes it both an interesting and stimulating environment to work in, leading to often unexpected discoveries! XRCE is part of the Xerox Innovation Group made up of 550 researchers and engineers in four world-renowned research and technology centres. The Grenoble site is set in a park in the heart of the French Alps in a stunning location only a few kilometers from the city centre. The city of Grenoble has a large scientific community made up of national research institutes (CNRS, Universities, INRIA, Minatec) and private industries. Grenoble is close to both the Swiss and Italian borders and is the ideal place for skiing, climbing, hang gliding and all types of mountain sports. From sophie.deneve at ens.fr Fri Sep 22 06:37:01 2006 From: sophie.deneve at ens.fr (sophie deneve) Date: Fri, 22 Sep 2006 12:37:01 +0200 Subject: Connectionists: Postdoctoral Position in Bayesian Motor Control at the Institute of Cognitive Sciences, Lyon Message-ID: <000201c6de33$0cdb39f0$de05a8c0@atlantique> A postdoctoral position in computational sensorimotor control is available starting in fall 2006 at the Institute for Cognitive Science, Lyon, France, to participate in a project investigating Bayesian mechanisms for sensorimotor integration and motor control. The position is funded for two years, with generous travel allowance. The project will be supervised by Pierre Baraduc and Sophie Deneve, and will focus on internal estimates of eye and arm state during movement in humans, its update by sensory feedback and its dependence on priors. This question will be addressed by combining behavioral experiments and theoretical models. Facilities include Eyelink II and Optotrak tracking devices integrated in a virtual reality system. The ideal candidate should have a Ph.D. in a relevant discipline, a strong background in mathematics, physics, computer science or engineering, as well as a real interest for neuroscience. Prior experience in psychophysics and human movement recording is preferred, but not required. Programming skills in C/C++ and Matlab are essential. The ISC is one of the leading French centers specialising in integrative approaches to understanding brain function. It gathers researchers from neuroscience, psychology, computer science and linguistics and is located on a campus strong in vision and sensorimotor control. Information request and applications (including CV, brief summary of previous research work and research goals, and the names and contact details of two professional references) should be sent to Pierre Baraduc, Institute for Cognitive Science, 67 bd Pinel, 69675 Bron, France, or electronically to pierre.baraduc at isc.cnrs.fr, with Cc to sophie.deneve at ens.fr. From rsun at rpi.edu Fri Sep 22 10:11:03 2006 From: rsun at rpi.edu (Professor Ron Sun) Date: Fri, 22 Sep 2006 10:11:03 -0400 Subject: Connectionists: IJCNN 2007 in Orlando, Florida Message-ID: <563F2BB7-F459-4C82-92CF-28C7F01B5E98@rpi.edu> IJCNN 2007 Call For Papers 2007 International Joint Conference on Neural Networks Orlando, Florida August 12-17, 2007 Celebrating 20 years of Neural Networks! http://www.ijcnn2007.org The 2007 International Joint Conference on Neural Networks (IJCNN 2007), sponsored by the International Neural Network Society and co- sponsored by the IEEE Computational Intelligence Society, is the premier event in the field of neural networks. It covers all topics in neural network theories and applications, including, but not limited to: - Neural network models and analysis - Connectionist cognitive science and cognitive modeling (language, reasoning, perception, learning, memory, consciousness, emotion, etc.) - Computational neuroscience - Neuroengineering - Cognitive robotics, developmental robotics, and neural robotics - Data analysis and pattern recognition - Signal processing and image processing - Neural control - Neuroinformatics - Hybrid neural-symbolic, neuro-fuzzy, neuro-evolutionary systems, etc. - Bayesian models and other graphical models - Kernel methods - Learning methods: supervised, unsupervised, and reinforcement - Approximate dynamic programming and neural network approaches to optimization - Neural dynamics, complex systems, and chaos - Hardware implementations of neural networks and neuromorphic engineering - Neural networks applications (expert systems, embedded systems, data mining, Multi-agent systems, financial engineering, bioinformatics, telecommunication, manufacturing, etc.) IJCNN 2007 will feature plenary speakers, special sessions, moderated panel discussions, pre-conference tutorials, post-conference workshops, regular technical sessions, poster sessions, and social functions. Prospective authors are invited to submit complete papers of no more than six (6) pages (including results, figures, tables, and references) in IEEE two-column format. Authors should submit their papers in PDF through the online submission system, which will be available at the website: http://www.ijcnn2007.org. Call for Special Sessions and Panel Discussions: The IJCNN 2007 Program Committee solicits proposals for special sessions and panel discussions within the technical scope of the conference. Special sessions and panel discussions are to be organized by experts and aimed to bring together researchers around a focused topic. Special sessions and panel discussions have become both a tradition and an important component of the IJCNN. Papers submitted for special sessions or panel discussions are to be peer-reviewed with the same criteria used for regular contributed papers. Researchers interested in organizing a special session or a panel are invited to submit a formal proposal to the Special Sessions Chair or the Panels Chair, respectively. Special session or panel proposals should include the session title, a brief description of its scope, motivation, its appeal to the attendees of this conference, organizer names and contact information, and brief CVs of the organizers. Call for Pre-Conference Tutorials and Post-Conference Workshops: IJCNN 2007 will feature a number of pre-conference tutorials and post-conference workshops covering fundamental and advanced topics in neural networks (broadly defined). Pre-conference tutorial and post-conference workshop proposals, submitted to the Tutorials Chair and Workshops Chair, respectively, are requested, and should include title, outline, motivation, appeal to the conference attendees, expected enrollment, and organizers' CVs. Important Dates: Special Session and Panel Discussion Proposals: November 31, 2006 Paper Submission: January 31, 2007 Pre-Conference Tutorial and Post-Conference Workshop Proposals: January 31, 2007 Decision Notification: March 31, 2007 Camera-Ready Submission: April 30, 2007 Further information: http://www.ijcnn2007.org General Chair: Jennie Si Arizona State University Program Chair: Ron Sun Rensselaer Polytechnic Institute ======================================================== Professor Ron Sun Cognitive Science Department Rensselaer Polytechnic Institute 110 Eighth Street, Carnegie 302A Troy, NY 12180, USA phone: 518-276-3409 fax: 518-276-3017 email: rsun at rpi.edu web: http://www.cogsci.rpi.edu/~rsun ======================================================= From jirsa at ccs.fau.edu Fri Sep 22 11:14:26 2006 From: jirsa at ccs.fau.edu (Viktor Jirsa) Date: Fri, 22 Sep 2006 11:14:26 -0400 Subject: Connectionists: PhD positions available in Theoretical Neuroscience Message-ID: <4513FDD2.6090003@ccs.fau.edu> The Theoretical Neuroscience Group (TNG) invites applications for PhD positions in Marseille, France. The research will focus on cognitive and behavioral neuroscience characterized by a close interaction of experimental and theoretical approaches. The successful candidate will join a young and vibrant interdisciplinary team composed of scientists from neuroscience, psychology and physics. PhD projects are offered in Movement Sciences, exploring the laws underlying human multi-limb coordination in complex and changing environments through experiment/computation/modeling; in Brain Connectivity, studying network structure and function with applications to non-invasive brain imaging (EEG, MEG, fMRI) through data analysis/computation/modeling. Full and partial scholarships are available up to three years, subject to yearly review and renewal. Depending on the desired research focus (theoretical/ experimental), applicants should have a Masters degree in Physics, Mathematics, Engineering, or Psychology, Biology, Neuroscience. The Marseille members of TNG are housed in the Movement & Perception Laboratory, CNRS, in Marseille (France) and have close ties with the Center for Complex Systems & Brain Sciences (CCSBS) at Florida Atlantic University, Boca Raton (USA). A key element is the emphasis on active integration across disciplines, which provides a unique training opportunity for the successful candidate. The TNG is also member of an international consortium, the Brain Network Recovery Group (Brain NRG), which represents the union of computational, cognitive and clinical neuroscience dedicated to the application of neural network theory to understanding the damaged brain. Students will benefit from various meetings of TNG, Brain NRG and CCSBS. More information on the Theoretical Neuroscience Group (TNG) is available at http://tng.ccs.fau.edu. Information on the Brain NRG project can be accessed at http://www.brainnrg.org. Review of applications will begin immediately and continue until the positions are filled. Qualified candidates should send their curriculum vitae with names of three references to Dr. Sarah Calvin (email: sarah.calvin at univmed.fr). From terry at salk.edu Fri Sep 22 14:46:28 2006 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 22 Sep 2006 11:46:28 -0700 Subject: Connectionists: NEURAL COMPUTATION November 2006 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 18, Number 11 - November 1, 2006 Note Spike Count Correlation Increases with Length of Time Interval in the Presence of Trial-to-Trial Variation Robert E. Kass and Valérie Ventura Letters The Spike-Triggered Average of the Integrate-and-Fire Cell Driven by Gaussian White Noise Liam Paninski Low-Dimensional Maps Encoding Dynamics in Entorhinal Cortex and Hippocampus Dmitri D. Pervouchine, Theoden I. Netoff, Horacio G. Rotstein, John A. White, Mark O. Cunningham, Miles A. Whittington and Nancy J. Kopell Programmable Logic Construction Kits for Hyper Real-time Neuronal Modeling Ruben Guerrero-Rivera, Abigail Morrison, Markus Diesmann and Tim C. Pearce Soft Mixer Assignment in a Hierarchical Generative Model of Natural Scene Statistics Odelia Schwartz, Terrence J. Sejnowski, and Peter Dayan The Scaling of Winner Takes All Accuracy with the Population Size Maoz Shamir An Extended EM Algorithm for Joint Feature Extraction and Classification in Brain Computer Interfaces Yuanqing Li and Cuntai Guan On the Consistency of Bayesian Variable Selection for High Dimensional Binary Regression and Classification Wenxin Jiang A Maximum Likelihood Approach to Density Estimation with Semidefinite Programming Tadayoshi Fushiki, Shingo Horiuchi and Takashi Tsuchiya Piecewise-Linear Neural Networks and their Relationship to Rule Extraction from Data Martin Holena Computation of Madalines' Sensitivity to Input and Weight Perturbations Yingfeng Wang, Xiaoqin Zeng, Daniel So Yeung and Zhihang Peng ----- 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 nicolas.brunel at univ-paris5.fr Mon Sep 25 04:35:09 2006 From: nicolas.brunel at univ-paris5.fr (Nicolas Brunel) Date: Mon, 25 Sep 2006 10:35:09 +0200 Subject: Connectionists: Postdoctoral position in theoretical neuroscience at ISI foundation, (Torino, Italy) Message-ID: <451794BD.2000606@univ-paris5.fr> Postdoctoral position in theoretical neuroscience at ISI foundation (Torino, Italy) Applications are invited for a post-doctoral position to carry out theoretical research at the interface between statistical physics and theoretical neuroscience. The position is funded initially for 2 years, with possible extensions. Applicants should have a strong background in physics, and previous research experience in computational/theoretical neuroscience. The applicant should be able to perform independent research and interact with both the statistical physics group (currently headed by Riccardo Zecchina) and the computational neuroscience group (currently headed by Nicolas Brunel). The research interests of these groups currently focus on learning and on network dynamics. Applicants should send a curriculum vitae and have two or three letters of recommendation sent by email to Nicolas Brunel (nicolas.brunel at univ-paris5.fr). The fellowship could start as early as November 2006. For more information on research activities of ISI: www.isi.it Nicolas Brunel website: www.neurophys.biomedicale.univ-paris5.fr/~brunel Riccardo Zecchina website: www.ictp.trieste.it/~zecchina From esann at dice.ucl.ac.be Mon Sep 25 14:18:34 2006 From: esann at dice.ucl.ac.be (esann) Date: Mon, 25 Sep 2006 20:18:34 +0200 Subject: Connectionists: CFP: ESANN'2007 European Symposium on Artificial Neural Networks Message-ID: <00d401c6e0cf$03cf7ee0$43ed6882@maxwell.local> ESANN'2007 15th European Symposium on Artificial Neural Networks Advances in Computational Intelligence and Learning Bruges (Belgium) - April 25-26-27, 2007 Announcement and call for papers ===================================================== The call for papers for the ESANN'2007 conference is now available on the Web: http://www.dice.ucl.ac.be/esann For those of you who maintain WWW pages including lists of related ANN sites: we would appreciate if you could add the above URL to your list; thank you very much! We make all possible efforts to avoid sending multiple copies of this call for papers; however we apologize if you receive this e-mail twice, despite our precautions. You will find below a short version of this call for papers, without the instructions to authors (available on the Web). ESANN'2007 is organized in collaboration with the UCL (Universite catholique de Louvain, Louvain-la-Neuve) and the KULeuven (Katholiek Universiteit Leuven). The conference is technically co-sponsored by the International Neural Networks Society, the European Neural Networks Society, the IEEE Computational Intelligence Society, the IEEE Region 8, the IEEE Benelux Section (sponsors to be confirmed). Scope and topics ---------------- Since its first happening in 1993, the European Symposium on Artificial Neural Networks has become the reference for researchers on fundamentals and theoretical aspects of artificial neural networks, computational intelligence, learning and related topics. Each year, around 100 specialists attend ESANN, in order to present their latest results and comprehensive surveys, and to discuss the future developments in this field. The ESANN'2007 conference will follow this tradition, while adapting its scope to the new developments in the field. Artificial neural networks are viewed as a branch, or subdomain, of machine learning, statistical information processing and computational intelligence. Mathematical foundations, algorithms and tools, and applications are covered. The following is a non-exhaustive list of machine learning, computational intelligence and artificial neural networks topics covered during the ESANN conferences: THEORY and MODELS Statistical and mathematical aspects of learning Feedforward models Kernel machines Graphical models, EM and Bayesian learning Vector quantization and self-organizing maps Recurrent networks and dynamical systems Blind signal processing Ensemble learning Nonlinear projection and data visualization Fuzzy neural networks Evolutionary computation Bio-inspired systems INFORMATION PROCESSING and APPLICATIONS Data mining Signal processing and modeling Approximation and identification Classification and clustering Feature extraction and dimension reduction Time series forecasting Multimodal interfaces and multichannel processing Adaptive control Vision and sensory systems Biometry Bioinformatics Brain-computer interfaces Neuroinformatics Papers will be presented orally (single track) and in poster sessions; all posters will be complemented by a short oral presentation during a plenary session. It is important to mention that the topics of a paper decide if it better fits into an oral or a poster session, not its quality. The selection of posters will be identical to oral presentations, and both will be printed in the same way in the proceedings. Nevertheless, authors must indicate their preference for oral or poster presentation when submitting their paper. Special sessions ---------------- Special sessions will be organized by renowned scientists in their respective fields. Papers submitted to these sessions are reviewed according to the same rules as submissions to regular sessions. They must also follow the same format, instructions, deadlines and submission procedure. The special sessions organized during ESANN'2007 are: 1) Fuzzy and Probabilistic Methods in Neural Networks and Machine Learning B. Hammer, Clausthal Univ. Tech. (Germany), T. Villmann, Univ. Leipzig (Germany) 2) Reinforcement Learning V. Heidrich-Meisner, Ruhr-Univ. Bochum, M. Lauer, Univ. Osnabr?ck, C. Igel, Ruhr-Univ. Bochum, M. Riedmiller, Univ. Karlsruhe (Germany) 3) Convex Optimization for the Design of Learning Machines K. Pelckmans, J.A.K. Suykens, Katholieke Univ. Leuven (Belgium) 4) Learning causality P. F. Verdes, Heidelberg Acad. of Sciences (Germany), K. Hlavackova-Schindler, Austrian Acad. of Sciences (Austria) 5) Reservoir Computing D. Verstraeten, B. Schrauwen, Univ. Gent (Belgium) Location -------- The conference will be held in Bruges (also called "Venice of the North"), one of the most beautiful medieval towns in Europe. Bruges can be reached by train from Brussels in less than one hour (frequent trains). The town of Bruges is world-wide known, and famous for its architectural style, its canals, and its pleasant atmosphere. The conference will be organized in a hotel located near the centre (walking distance) of the town. There is no obligation for the participants to stay in this hotel. Hotels of all levels of comfort and price are available in Bruges; there is a possibility to book a room in the hotel of the conference at a preferential rate through the conference secretariat. A list of other smaller hotels is also available. The conference will be held at the Novotel hotel, Katelijnestraat 65B, 8000 Brugge, Belgium. Proceedings and journal special issue ------------------------------------- The proceedings will include all communications presented to the conference (tutorials, oral and posters), and will be available on-site. Extended versions of selected papers will be published in the Neurocomputing journal (Elsevier). Call for contributions ---------------------- Prospective authors are invited to submit their contributions before December 1, 2006. The electronic submission procedure is described on the ESANN portal http://www.dice.ucl.ac.be/esann/. Authors must also commit themselves that they will register to the conference and present the paper in case of acceptation of their submission (one paper per registrant). Authors of accepted papers will have to register before February 28, 2007; they will benefit from the advance registration fee. The ESANN conference applies a strict policy about the presentation of accepted papers during the conference: authors of accepted papers who do not show up at the conference will be blacklisted for future ESANN conferences, and the lists will be communicated to other conference organizers. Deadlines --------- Submission of papers December 1, 2006 Notification of acceptance January 26, 2007 Symposium April 25-27, 2007 Conference secretariat ---------------------- ESANN'2007 d-side conference services phone: + 32 2 730 06 11 24 av. L. Mommaerts Fax: + 32 2 730 06 00 B - 1140 Evere (Belgium) E-mail: esann at dice.ucl.ac.be http://www.dice.ucl.ac.be/esann Steering and local committee ---------------------------- Fran?ois Blayo Ipseite (CH) Gianluca Bontempi Univ. Libre Bruxelles (B) Marie Cottrell Univ. Paris I (F) Jeanny H?rault INPG Grenoble (F) Mia Loccufier Univ. Gent (B) Bernard Manderick Vrije Univ. Brussel (B) Jean-Pierre Peters FUNDP Namur (B) Joos Vandewalle KUL Leuven (B) Michel Verleysen UCL Louvain-la-Neuve (B) Scientific committee (to be confirmed) -------------------- Cecilio Angulo Univ. Polit. de Catalunya (E) Miguel Atencia Univ. Malaga (E) Pierre Bessi?re CNRS (F) Herv? Bourlard IDIAP Martigny (CH) Joan Cabestany Univ. Polit. de Catalunya (E) St?phane Canu Inst. Nat. Sciences App. (F) Valentina Colla Scuola Sup. Sant'Anna Pisa (I) Holk Cruse Universit?t Bielefeld (D) Eric de Bodt Univ. Lille II (F) & UCL Louvain-la-Neuve (B) Dante Del Corso Politecnico di Torino (I) Georg Dorffner University of Vienna (A) Wlodek Duch Nicholas Copernicus Univ. (PL) Marc Duranton Philips Semiconductors (USA) Richard Duro Univ. Coruna (E) Andr? Elisseef IBM Research (CH) Deniz Erdogmus Oregon Health & Science University (USA) Anibal Figueiras-Vidal Univ. Carlos III Madrid (E) Simone Fiori Univ. Perugia (I) Jean-Claude Fort Universit? Nancy I (F) Leonardo Franco Univ. Malaga (E) Colin Fyfe Univ. Paisley (UK) Stan Gielen Univ. of Nijmegen (NL) Mirta Gordon IMAG Grenoble (F) Marco Gori Univ. Siena (I) Bernard Gosselin Fac. Polytech. Mons (B) Manuel Grana UPV San Sebastian (E) Anne Gu?rin-Dugu? INPG Grenoble (F) Barbara Hammer Univ. of Osn?bruck (D) Martin Hasler EPFL Lausanne (CH) Tom Heskes Univ. Nijmegen (NL) Christian Igel Ruhr-Univ. Bochum (D) Jose Jerez Univ. Malaga (E) Gonzalo Joya Univ. Malaga (E) Christian Jutten INPG Grenoble (F) Juha Karhunen Helsinki Univ. of Tech. (FIN) Stefanos Kollias National Tech. Univ. Athens (GR) Jouko Lampinen Helsinki Univ. of Tech. (FIN) Petr Lansky Acad. of Science of the Czech Rep. (CZ) Beatrice Lazzerini Univ. Pisa (I) Erzsebet Merenyi Rice Univ. (USA) Jean-Pierre Nadal Ecole Normale Sup?rieure Paris (F) Erkki Oja Helsinki Univ. of Technology (FIN) Arlindo Oliveira INESC-ID (P) Gilles Pag?s Univ. Paris 6 (F) Thomas Parisini Univ. Trieste (I) H?l?ne Paugam-Moisy Universit? Lumi?re Lyon 2 (F) Alberto Prieto Universitad de Granada (E) Didier Puzenat Univ. Antilles-Guyane (F) Leonardo Reyneri Politecnico di Torino (I) Jean-Pierre Rospars INRA Versailles (F) Fabrice Rossi INRIA (F) Francisco Sandoval Univ.Malaga (E) Jose Santos Reyes Univ. Coruna (E) Craig Saunders Univ.Southampton (UK) Udo Seiffert IPK Gatersleben (D) Bernard Sendhoff Honda Research Institute Europe (D) Peter Sollich King's College (UK) Jochen Steil Univ. Bielefeld (D) John Stonham Brunel University (UK) Johan Suykens K. U. Leuven (B) John Taylor King?s College London (UK) Claude Touzet Univ. Provence (F) Marc Van Hulle KUL Leuven (B) Thomas Villmann Univ. Leipzig (D) Axel Wism?ller Ludwig-Maximilians-Univ. M?nchen (D) Bart Wyns Univ.Gent (B) Michalis Zervakis Technical Univ. Crete (GR) ======================================================== ESANN - European Symposium on Artificial Neural Networks http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews,... Michel Verleysen Univ. Cath. de Louvain - Machine Learning Group 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at dice.ucl.ac.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at dice.ucl.ac.be ======================================================== From g.goodhill at imb.uq.edu.au Mon Sep 25 21:13:44 2006 From: g.goodhill at imb.uq.edu.au (Geoffrey Goodhill) Date: Tue, 26 Sep 2006 11:13:44 +1000 Subject: Connectionists: Positions available Message-ID: <45187EC8.9020800@imb.uq.edu.au> Dear Connectionists, Several postdoctoral and research assistant positions are now available in a multidisciplinary team at the University of Queensland in the area of computational/cognitive neuroscience. The focus of the positions includes electrophysiology, mathematical/computational modelling, robotics, neuroimaging, information systems, and software support. This project is funded by a large-scale 5-year "Thinking Systems" grant from the Australian Research Council. Details of the project, positions and Chief Investigators can be found at http://www.itee.uq.edu.au/~janetw/ThinkingSystems This page also contains more information about the formal application process. The deadline for applications is November 8th 2006, though applications will continue to be considered until the positions are filled. Informal enquires are welcome, and should be directed to Janet Wiles (wiles at itee.uq.edu.au) or Geoff Goodhill (g.goodhill at uq.edu.au). According to http://www.thes.co.uk/worldrankings the University of Queensland is one of the top 50 universities in the world. It provides an excellent environment for interdisciplinary research, and is currently investing AU$200M in the general area of Biotechnology. This includes AU$50M for a new neuroscience institute, http://www.qbi.uq.edu.au, for which a new 7000sqm building is currently under construction. UQ is in Brisbane, the capital of Queensland, a cosmopolitan city of 1.5 million people with excellent facilities, a vibrant cultural environment, and a subtropical climate. Queensland is also home to attractions such as tropical rainforests and the Great Barrier Reef. Geoffrey J Goodhill, PhD Associate Professor Queensland Brain Institute, School of Physical Sciences & Institute for Molecular Bioscience University of Queensland St Lucia, QLD 4072, Australia Phone: +61 7 3346 2612 Fax: +61 7 3346 8836 Email: g.goodhill at uq.edu.au http://cns.qbi.uq.edu.au Editor-in-Chief, Network: Computation in Neural Systems http://www.tandf.co.uk/journals/titles/0954898X.asp From bengio at idiap.ch Thu Sep 28 04:09:35 2006 From: bengio at idiap.ch (Samy Bengio) Date: Thu, 28 Sep 2006 10:09:35 +0200 (CEST) Subject: Connectionists: call for abstracts - NIPS workshop on learning to campare examples Message-ID: CALL FOR PAPERS: NIPS'06 Workshop on Learning to Compare Examples ---------------------------- http://www.idiap.ch/lce Whistler, Canada December 8-9, 2006 (submission deadline: October 26, 2006) Overview: The identification of an effective function to compare examples is essential to several machine learning problems. For instance, retrieval systems entirely depend on such a function to rank the documents with respect to their estimated similarity to the submitted query. Another example is kernel-based algorithms which heavily rely on the choice of an appropriate kernel function. In most cases, the choice of the comparison function (also called, depending on the context and its mathematical properties, distance metric, similarity measure, kernel function or matching measure) is done a-priori, relying on some knowledge/assumptions specific to the task. An alternative to this a-priori selection is to learn a suitable function relying on a set of examples and some of its desired properties. This workshop is aimed at bringing together researchers interested in such a task. Topics of interest include, but are not limited to: * algorithmic approaches for distance metric(*) learning, * comparisons of distance metric learning(*) approaches, * effect of distance metric(*) learning on retrieval/categorization models, * learning a distance(*) robust to certain transformations, * links between distance(*) learning and the ranking/categorization problem, * criteria, loss bounds for distance(*) learning, * using unlabeled data for distance(*) learning, * applications of the above to IR/categorization problems for text, vision.. (*) "distance metric" can, of course, be replaced by similarity measure, kernel or matching measure as mentioned in the abstract. Submissions: The problem of "Learning to Compare Examples" (LCE) has arisen in several application contexts, ranging from information retrieval (e.g. [6]) to face verification (e.g. [1]) and it has been addressed relying on various machine learning approaches, which include, among others, Neural Networks (e.g. [1]), Kernel Methods (e.g. [6,8]) and Boosting Approaches (e.g. [2]). Also, a large variety of learning criteria have been proposed for this task. This workshop aims at gathering the different communities that have been working on this problem, with the objective to foster collaboration and inspiration between them. In this context, contributions from researchers of these communities are solicited. Abstract Format We encourage the submissions of extended abstract. The suggested abstract length is ~3 pages (maximum 8 pages), formatted in the NIPS format. The authors of the accepted abstracts will be allocated between 20 and 40 minutes to present their work (to be determined according to submissions). In addition, the abstracts will be available to a broader audience on this web site. Submission Procedure The authors should submit their extended abstract to: lce [ @ ] idiap.ch in pdf before October 19, 2006, 23:59 Samoa Time. An email confirming the reception of the submission will be sent by the organizers. Planned Schedule Sept 28: Workshop announcement / call for abstracts Oct 26: Abstract submission deadline Nov 9: Notification of acceptance Nov 23: Final extended abstracts due Dec 8 or 9: Workshop Planned Program In addition to the peer-review presentations, two invited talks will also be given. Based on the dominant themes of the workshop submissions as well as the opinions of the PC members and the invited speakers, we plan to identify 2/3 main themes related to the workshop topics in order to group the talks and organize thematic discussions after the presentations. Questions to the Organizers Requests, suggestions and comments should be sent to: lce [ @ ] idiap.ch People Invited Speakers Yann LeCun, New York University Sam Roweis, University of Toronto Organizers Samy Bengio, IDIAP Research Institute David Grangier, IDIAP Research Institute Program Committee Samy Bengio, IDIAP Research Institute Gilles Blanchard, Fraunhofer FIRST Chris Burges, Microsoft Research David Grangier, IDIAP Research Institute Thomas Hofmann, Technical University of Darmstadt Guy Lebanon, Purdue University Thorsten Joachims, Cornell University Yoram Singer, The Hebrew University Alex Smola, National ICT Australia References 1. S. Chopra, R. Hadsell and Y. LeCun, Learning a Similarity Metric Discriminatively, with Application to Face Verification (CVPR, 2005). 2. K. Crammer, J. Keshet and Y. Singer, Kernel Design using Boosting (NIPS, 2002). 3. F. Fleuret and G. Blanchard, Pattern Recognition from One Example by Chopping (NIPS, 2005). 4. A. Globerson and S. Roweis, Metric Learning by Collapsing Classes (NIPS, 2005). 5. J. Goldberger, S. Roweis, G. Hinton, R. Salakhutdinov, Neighbourhood Component Analysis (NIPS, 2004). 6. D. R. Hardoon, S. Szedmak and J. Shawe-Taylor, Canonical Correlation Analysis: An Overview with Application to Learning Methods (Neural Comp., 2004). 7. T. Hertz, A. Bar-Hillel and D. Weinshall, Boosting Margin-Based Distance Functions for Clustering (ICML, 2004). 8. G. R. G. Lanckriet, N. Cristianini, P. Bartlett, L. El Ghaoui and M. I. Jordan, Learning the Kernel Matrix with Semidefinite Programming (JMLR, 2004). 9. G. Lebanon, Metric Learning for Text Documents (TPAMI, 2006). 10. S. Shalev-Shwartz, Y. Singer and A. Y. Ng, Online and Batch Learning of Pseudo-Metrics (ICML, 2004). 11. M. Schutz and T. Joachims, Learning a Distance Metric from Relative Comparisons (NIPS, 2003). 12. K. Q. Weinberger, J. Blitzer, and L. K. Saul, Distance Metric Learning for Large Margin Nearest Neighbor Classification (NIPS, 2005). 13. E. Xing, A. Y. Ng, M. Jordan, and S. Russell, Distance Metric Learning, with Application to Clustering with Side-Information (NIPS, 2002). Sponsors This workshop is partially sponsored by the PASCAL European Network of Excellence, in the context of the thematic on Intelligent Information Access. ---- Samy Bengio Senior Researcher in Machine Learning. IDIAP, CP 592, rue du Simplon 4, 1920 Martigny, Switzerland. tel: +41 27 721 77 39, fax: +41 27 721 77 12. mailto:bengio at idiap.ch, http://www.idiap.ch/~bengio From M.Casey at surrey.ac.uk Thu Sep 28 11:45:35 2006 From: M.Casey at surrey.ac.uk (M.Casey@surrey.ac.uk) Date: Thu, 28 Sep 2006 16:45:35 +0100 Subject: Connectionists: Biologically Inspired Information Fusion: Workshop Report Message-ID: The final report for the Workshop on Biologically Inspired Information Fusion is now available at: http://www.cs.surrey.ac.uk/people/academic/M.Casey/biif2006.html The workshop was held to bring together both life and physical scientists, focused on discussing information fusion. The aim was to promote collaboration between the disciplines to develop an understanding of how to build adaptive information fusion systems. This initial workshop was targeted at bringing the disciplines together to develop a set of research priorities for future collaboration. This was achieved through a two-day programme of tutorials, discussion sessions, student presentations and brainstorming held on the 22nd and 23rd August 2006. The report summarises the overall organisation, participation, evaluation and outcomes of the workshop. In particular, the report highlights the top three research priorities that were defined during the workshop brainstorming sessions: 1. Sensory fusion, disorder and clinical application How does sensory fusion impact on disorder and how can this be applied? In particular, can we develop machine aids in the form of implants or prosthetics to overcome or reduce the effects of disorders? For example, hearing impaired people perform sub-optimally at using visual cues to amplify auditory cues. Could a training regime be developed to enhance the operation of multi-sensory integration to overcome the sub-optimal performance on visual cues? 2. Exploiting effective biological processes for sensory integration What biological processes can be exploited by computer systems? What do biological sensory systems do well, and conversely what do computer sensory systems do well? Which biological sensory systems are optimal? Is fusion of benefit or not? Which senses dominate under which circumstances? How does memory impact on sensory integration? 3. Developing a common language for inter-disciplinary communication and collaboration In order to develop collaboration further, a common language is required to overcome terminology differences and to assist in cross-discipline training and dissemination. Follow-up activities are already planned to help build upon these identified priorities. In the first instance these are: 1. Dissemination of the workshop findings and notes. 2. Journal special issue to provide further training and dissemination, and to promote collaboration. Currently a call for papers for a special issue of the Information Fusion journal is being drafted for publication in 2007. 3. Establishment of follow-up projects. Further details, proceedings and notes are available at the website. If you have any questions or comments, please don't hesitate to get in touch. Thanks, Matthew Casey Department of Computing School of Electronics and Physical Sciences University of Surrey Guildford Surrey GU2 7XH Tel: +44 (0)1483 689635 E-mail: m.casey at surrey.ac.uk From Soeren.Sonnenburg at first.fraunhofer.de Fri Sep 29 01:50:59 2006 From: Soeren.Sonnenburg at first.fraunhofer.de (Soeren Sonnenburg) Date: Fri, 29 Sep 2006 05:50:59 +0000 Subject: Connectionists: Call for Contributions: NIPS Workshop on Machine Learning Open Source Software 2006 Message-ID: <1159509059.32073.313.camel@localhost> Workshop on Machine Learning Open Source Software 2006 ============================================================ ( http://www.fml.tuebingen.mpg.de/raetsch/workshops/MLOSS06 ) The NIPS workshop on Workshop on Machine Learning Open Source Software (MLOSS) will held in Whistler (B.C.) on the 8th or 9th of December, 2006. Important Dates --------------- * Submission Date: October 26th, 2006 * Notification of Acceptance: November 9th, 2006 * Workshop date: December 8 or 9th, 2006 Description ----------- Open source tools have recently reached a level of maturity which makes them suitable for building large-scale real-world systems. At the same time, the field of machine learning has developed a large body of powerful learning algorithms for a wide range of applications. Inspired by similar conferences in bioinformatics (BOSC) or statistics (useR), our aim is to build a forum for open source software in machine learning. The workshop's ultimate goal is to bring existing and freshly developed toolboxes and algorithmic implementations to people's attention. Program Commitee ---------------- * Jason Weston (NEC Princeton, USA) * G?khan BakIr (MPI Tuebingen, Germany) * Alexander Smola (NICTA Canberra, Australia) * Gunnar R?tsch (FML Tuebingen, Germany) * Lieven Vandenberghe (University of California LA, USA) * Chih-Jen Lin ( National Taiwan University Taipei, Taiwan) * William Stafford Noble (University of Washington, Seattle, USA) * Klaus-Robert Mueller (Fraunhofer Institute First, Germany) Call for Contributions ---------------------- The organizing committee is currently seeking abstracts for talks at MLOSS 2006. MLOSS is a great opportunity for you to tell the community about your use, development, or philosophy of open source software in machine learning. This includes (but is not limited to) numeric packages (e.g. R,octave,numpy), machine learning toolboxes and implementations of ML-algorithms. The committee will select several submitted abstracts for 20-minute talks. Accepted abstracts will be published on the web site. If you are interested in speaking at MLOSS, please send us an email at mloss at tuebingen.mpg.de before October 28th, 2006 with: * an abstract (1 page A4) * a URL for the project page, if applicable * information about the open source license used for your software or your release plans. Note: Submissions must adhere to a recognized Open Source License (cf. http://www.opensource.org/licenses/ ) and the source code must be available at the time of presentation. Planned format: --------------- The workshop will be a mixture of talks (including a mandatory demo of the software) and panel/open/hands-on discussions. Invited Speakers: ----------------- * Python with scipy - Travis Oliphant * CVXOPT - Lieven Vandenberghe * R - Kurt Hornick or John MainDonald * Torch Ronan Collobert or Samy Bengio or Johnny Marithoz Organizers: ----------- * Soeren Sonnenburg, Mikio Braun - Fraunhofer FIRST * Cheng Soon Ong - MPI for Biological Cybernetics and Friedrich Miescher Laboratory * S.V.N. Vishwanathan - National ICT Australia -- Soeren Sonnenburg - Fraunhofer FIRST Tel: +49 (30) 6392 1882 Kekulestr. 7, 12489 Berlin, Germany Fax: +49 (30) 6392 1805 From juergen at idsia.ch Fri Sep 29 15:18:00 2006 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Fri, 29 Sep 2006 21:18:00 +0200 Subject: Connectionists: Postdoc / Phd position at TU Munich Message-ID: We are seeking an outstanding researcher (Postdoc or PhD student) interested in Sequence Learning, Statistical Models, Recurrent Neural Networks, Evolino, and Support Vector Machines. We anticipate that the work will be funded through a project on Tactile Sensing. The project will involve neurobiologists and hardware experts building artificial haptic devices. Our goal is to process and analyze sequential data from artificial fingers with haptic sensors, and from neurophysiological measurements. Subgoals: to improve existing sequence learning algorithms, to recognize surfaces and objects by touching them, etc. Knowledge of German could be a plus but is not mandatory. The job will involve some interaction with experts in the UK, Sweden, and Switzerland. Possible starting date: 1 December 2006 Details: http://www.idsia.ch/~juergen/bat2006eu.html Juergen Schmidhuber TU Munich & IDSIA http://www.idsia.ch/~juergen/cogbotlab.html From Johan.Suykens at esat.kuleuven.be Fri Sep 29 07:01:06 2006 From: Johan.Suykens at esat.kuleuven.be (Johan Suykens) Date: Fri, 29 Sep 2006 13:01:06 +0200 Subject: Connectionists: PhD positions K.U. Leuven ESAT-SCD Message-ID: <451CFCF2.600@esat.kuleuven.ac.be> The research group K.U. Leuven ESAT-SCD is currently offering 3 new PhD positions (4-years of PhD study) to work in one of the following areas: - Support vector machines and kernel based learning: systematic design of kernel machines for supervised and semi-supervised learning based on convex optimization techniques and using least squares support vector machines as elementary building blocks. - Nonlinear system identification using kernel based modelling: study different model structures for system identification and time-series modelling in terms of primal and dual model representations, incorporation of prior knowledge via constraints and its relation to equivalent kernels. - Cooperative optimization processes: study methods for optimal cooperation with groups of optimization processes (e.g. coupled local minimizers, coupled simulated annealing) with respect to coupling schemes, hierarchical structure, synchronization properties and optimal convergence. The research group ESAT-SCD http://www.esat.kuleuven.be/scd/ at the university K.U. Leuven Belgium provides an excellent research environment being active in the broad area of mathematical engineering, including systems and control theory, neural networks and machine learning, nonlinear systems, signal processing, bioinformatics and biomedicine, quantum information theory and cryptography. The research will be conducted under the supervision of Prof. Johan Suykens. Interested candidates having a solid mathematical background and master degree should follow the guidelines at http://www.esat.kuleuven.be/vacancies/C3online.en.php for submitting the application and forward the application to ilse.pardon at esat.kuleuven.be (secretariat) and to johan.suykens at esat.kuleuven.be. Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm From csaba.szepesvari at ualberta.ca Mon Sep 25 01:04:50 2006 From: csaba.szepesvari at ualberta.ca (Csaba Szepesvari) Date: Sun, 24 Sep 2006 23:04:50 -0600 Subject: Connectionists: CFP: IEEE ADPRL 2007, Honolulu, Hawaii Message-ID: <45176372.1030000@ualberta.ca> Apologies for cross-posting! IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, Honolulu, Hawaii, April 1-5, 2007 Call for Contributed Papers and Special Sessions The IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning will be held as part of the Symposium Series on Computational Intelligence (SSCI). The area of Approximate Dynamic Programming and Reinforcement Learning is a fusion of a number of research areas in engineering, mathematics, artificial intelligence, operations research, and systems and control theory. 50 years after Richard Bellman's pioneering work on dynamic programming in 1957, this symposium will provide a remarkable opportunity for the academic and industrial community to address new challenges and share solutions, and define promising future research directions. The main challenge introduced by Bellman and which still remains a widely open question is the famous "curse of dimensionality". The theme of this year's symposium is "breaking the curse of dimensionality". A systems approach is required to address new problems of this challenging and promising area, and designing biologically-inspired intelligent systems may be an interesting way to address the problems. All research directions towards "breaking the curse" will be welcome! The symposium will feature plenary speeches from academia, NSF or DARPA, and industry, industrial panel sessions, funding agency panel sessions, poster sessions, and invited/special sessions. Technical topics of the symposium include but are not limited to: "Towards breaking the curse!" Parsimoneous function representation Convergence and performance bounds of ADP Complexity issues in RL and ADP Statistical learning and RL, PAC bounds for RL Monte-Carlo and quasi Monte-Carlo methods Direct policy search, actor-critic methods Adaptive feature discovery Learning rules and architectures for RL Sensitivity analysis for policy gradient estimation Neuroscience and biologically inspired control Partially observable Markov decision processes Distributed intelligent systems Multi-agent systems Multi-level multi-objective optimization Kernel methods and value function representation Applications of ADP and RL PAPER SUBMISSION Prospective authors are invited to submit complete papers of no more than eight (8) pages in IEEE two-column format, including results, figures, tables and references. Authors should submit their papers in PDF format through the online submission system, which will be available at the website http://www.ieee-ssci.org. A LaTeX style file and a Microsoft Word template are available from the IEEE web site (http://www.ieee.org/pubs/transactions/stylesheets.xml). The title page of the paper should include author name(s), affiliation, mailing address, telephone, fax, and e-mail address. Prospective authors are expected to present their papers at the symposium. IMPORTANT DATES Special session proposals deadline: October 15, 2006 Paper submission deadline: November 1, 2006 Notification of acceptance: December 1, 2006 Camera-ready copy due: January 15, 2007