From oreilly at psych.colorado.edu Thu May 5 02:58:39 2005 From: oreilly at psych.colorado.edu (Randall C. O'Reilly) Date: Thu, 5 May 2005 00:58:39 -0600 Subject: Connectionists: Re: Request: PDP++ software usage reports In-Reply-To: <200503312110.59449.oreilly@psych.colorado.edu> References: <200503312110.59449.oreilly@psych.colorado.edu> Message-ID: <200505050058.39882.oreilly@psych.colorado.edu> I apologize for a second email, but I neglected to mention that the deadline is May 15th, and we would appreciate this information by May 9th (this coming Monday) if possible. Also, please include any in-press or submitted papers. Thanks again! - Randy On Thursday 31 March 2005 09:10 pm, Randall C. O'Reilly wrote: > We are planning to write a grant proposal to support major enhancements to > the PDP++ neural network simulation software, and need to collect some data > on publications, teaching, and other usage of this software. > > If you have used PDP++ for simulations published in any form, please email > me the reference(s) to these publications (APA format preferred, but any > format will do). > > If you have used PDP++ for teaching, please send the name of the course, > years taught, number of students, etc. (any information would be > appreciated, the more the better). > > If you have used PDP++ for other purposes (e.g., business, forecasting, > etc) please send any relevant information. > > Finally, if you have any feedback on the software for things that we should > improve in the future, we would like to hear it. We have already begun the > revisions and have a fairly detailed plan, which we will be announcing > within a few weeks on the pdp-discuss email list, so your feedback would be > most beneficial if it could be given in the context of these plans, but if > you would rather just send feedback now, that would also be appreciated. > > To subscribe to the pdp-discuss email list, see the PDP++ website at: > > http://psych.colorado.edu/~oreilly/PDP++/PDP++.html *or* > http://www.cnbc.cmu.edu/Resources/PDP++/PDP++.html > > Thanks! > > - Randy From popescu at prosun.first.fraunhofer.de Wed May 4 13:41:00 2005 From: popescu at prosun.first.fraunhofer.de (Florin Popescu) Date: Wed, 04 May 2005 19:41:00 +0200 Subject: Connectionists: Postdoctoral position and doctoral position at the Fraunhofer Institute FIRST, Berlin. Message-ID: <6.2.0.14.0.20050504181359.03f1b3b8@mailhost> The Fraunhofer-Institute for Computer Architecture and Software Technology FIRST in Berlin is searching for a Postdoc as Research Associate (m/f) The EU-funded BRAIN2ROBOT project will adapt the leading technology developed at the Berlin Brain Computer Interface Laboratory (www.bbci.de) and the Intelligent Data Analysis Department at Fraunhofer Institute FIRST (www.first.fraunhofer.de) to a full arm robotic exoskeleton that will be controlled by EEG activity and aim to restore reaching function in quadriplegic patients. The position is for 3.5 years, starting near or before July 1 2005. For details of a doctoral position (Ph. D. studentship) related to this project, see: http://www.fraunhofer.de/fhg/EN/jobs/Wissenschaft.jsp (FIRST-113-05-004). The post-doctoral candidate will be expected to work on the neuro-physiological aspects of the envisioned research, which allows for basic science studies in motor control and brain function, as a complement to the main objective of arm function restoration. The expected qualifications are a strong background of independent-minded research as evidenced by a strong publication record, experience with on-line or off-line EEG analysis, and prior work in a clinical research environment. Further helpful experience would be scientific programming (e.g. MATLAB) and knowledge of machine learning, neural networks and/or related computer science topics. The eligibility requirements, set forth by European Union regulations on Marie Curie EXT Grants and therefore inflexible, are 4-10 years of research experience, counting doctoral research. It is acceptable that the candidate has not yet received his/her Ph. D. but will do so imminently. This degree is expected to be in physiology, biomedicine, or closely related areas. The working language of the laboratory is English. The monthly salary is ca. 3250 Euro (before taxes and social security). Preference will be given to nationals of EU member states (other than Germany) and nationals of EU associated states. International candidates will also receive mobility and travel allowances of up to approx. 9300 Euro per annum depending on current residency and family status. Please send your CV, cover letter and a sample of published work to (referring to job number FIRST-113-05-003): Fraunhofer-Gesellschaft Zentrale-Hauptabteilung Personal Frau Rabel Kekul?str. 7, 12489 Berlin For further information contact: Florin Popescu, Ph.D. Email: florin.popescu at first.fraunhofer.de From b.graham at cs.stir.ac.uk Fri May 6 12:43:56 2005 From: b.graham at cs.stir.ac.uk (Bruce Philip Graham) Date: Fri, 6 May 2005 17:43:56 +0100 (BST) Subject: Connectionists: 2005 Edinburgh Neuroinformatics Simulation Tools Summer School Message-ID: <2166.139.153.254.219.1115397836.squirrel@www.cs.stir.ac.uk> 2005 EDINBURGH SUMMER SCHOOL IN NEUROINFORMATICS SIMULATION TOOLS Institute for Adaptive and Neural Computation University of Edinburgh. August 22-26, 2005 * Application deadline: 6th June 2005 * This summer school in Neuroinformatics Simulation Tools is a five day intensive course which will provide a practical introduction to using neuroscience simulation tools including NEURON and Catacomb for computational modelling of neural systems. The course will be held in the Institute for Adaptive and Neural Computation in the centre of Edinburgh and will include talks from invited speakers as well as practical hands-on experience using the latest simulation tools. The course is aimed at PhD students, postdocs and faculty in neuroscience and related disciplines wishing to learn how to apply computational modelling techniques to their research problems. Bursaries are available for PhD students to cover accommodation costs. For more details, and an online application form visit:- http://www.anc.ed.ac.uk/school -- Dr Bruce Graham, Lecturer (b.graham at cs.stir.ac.uk) Dept. of Computing Science and Mathematics, University of Stirling, Stirling FK9 4LA phone: +44 1786 467 432 fax: +44 1786 464 551 -- The University of Stirling is a university established in Scotland by charter at Stirling, FK9 4LA. Privileged/Confidential Information may be contained in this message. If you are not the addressee indicated in this message (or responsible for delivery of the message to such person), you may not disclose, copy or deliver this message to anyone and any action taken or omitted to be taken in reliance on it, is prohibited and may be unlawful. In such case, you should destroy this message and kindly notify the sender by reply email. Please advise immediately if you or your employer do not consent to Internet email for messages of this kind. From talibshussain at hotmail.com Fri May 6 01:04:58 2005 From: talibshussain at hotmail.com (Talib Hussain) Date: Fri, 06 May 2005 01:04:58 -0400 Subject: Connectionists: CFP - Workshop on Achieving Functional Integration of Diverse Neural Models Message-ID: *********** Call for Papers *********** Workshop on Achieving Functional Integration of Diverse Neural Models August 4, 2005 7 - 10 pm http://openmap.bbn.com/~thussain/NeuralIntegration/index.html Part of IJCNN 2005 (International Joint Conference on Neural Networks) Hilton Bonaventure Hotel Montreal, Quebec, Canada http://faculty.uwb.edu/ijcnn05/ ====================================================== IMPORTANT DATES Quick email indicating interest: As soon as possible Position statement submission: May 16, 2005 Acceptance: May 17, 2005 Camera Ready position statement: May 20, 2005 Please submit to: neuralintegration at yahoo.com ====================================================== TOPICS AND GOALS The field of neural networks presents a very rich variety of models that have been applied to many different problems. However, successful application of neural networks to large-scale problems has been a general weakness. Further, the development of complex neural systems that demonstrate significant cognitive capabilities currently seems beyond reach. There is a critical need for new ideas and techniques for leveraging existing research by integrating current models in meaningful ways, with the goal of producing functional solutions to complex problems. Once we understand how to effectively model not only the detailed processing of specific neural components, but also the rich variety of interactions that may occur between those neural components (and other non-neural ones), we may begin to realize systems that scale well and are cognitively robust. The goals of this workshop are to explore what current integrative approaches and techniques show promise, and identify potential high-payoff areas for future research. Relevant research areas may include, for example, modularity, evolutionary neural systems, hybrid systems that integrate biological processes (such as immune systems and hormonal systems) with neural models, neural growth mechanisms, neural system engineering techniques. The outcome of this workshop is the identification of a set of key research topics on functional neural integration, together with an understanding of the key technical issues, limitations and benefits of each topic. The creation of working groups to pursue these topics will be discussed. The impact of this workshop will be to stimulate new discussion on a critical topic that we as a field ignore at our own risk. New ways of approaching large-scale neural solutions must always be at the fore. The development of effective working groups will be important in generating interest and support from funding agencies and other customers to keep advancing the state-of-the-art. INTENDED AUDIENCE The intended audience for the workshop is the neural network researcher that is interested in large-scale neural models, as well as the customer that is interested in solutions to large-scale, complex problems. The former may include practitioners in modular networks, evolutionary systems, robotic control, cognition, and neurophysiology. The latter may include companies that specialized in robotics, dynamic control systems, prediction and forecasting, as well as government and military agencies. We anticipate up to 20 participants, with a mix from industry, government and academia. WORKSHOP FORMAT The format of the workshop will be three hours with three successive sessions. In the first session, up to 10 presenters will give a 10 minute position statement summarizing their view of the problem, current relevant research that they are aware of, and the key avenues of exploration that they feel will have the most payoff. These position statements will be provided in the official workshop notes. In addition, the workshop organizer will present a short summary of other position statements collected in advance or the day-of from other workshop participants. Immediately following the first session, there will be a 45 minute networking and discussion session in which participants will be encouraged to discuss ideas in small groups and capture their thoughts on paper. In the final session, there will be a mediated discussion to identify the common themes and most promising avenues that have been identified. Working groups for those avenues will be identified and roles for those groups over the next year will be discussed. As time permits, those working groups will break off to determine their roles, agenda and action items. SUBMISSION GUIDELINES The position statement will be 2 pages in length and will begin with the title, author(s)' affiliation and a concise 100 word abstract. Ideally, the abstract will be a one-line summary of the key position taken. The statement will contain three sections titled Problem Statement, Current Research and Key Avenues. * The Problem Statement will give the authors view of the key issues that need to be addressed with regard to the topic of the workshop. * The Current Research section will give brief descriptions of the most applicable, interesting and/or controversial work that the authors feel are critical first steps towards achieving functional integration. * The Key Avenues section will identify what approaches the authors feel will have the highest payoff in the near to mid term. * References should be included at the end and will not count towards the 2 page limit. If your statement is not selected for presentation, you may still be given the option to have it included in the additional workshop notes that will be distributed at the workshop. In this case, you will be required to attend the workshop, and the content of your statement will be summarized by the workshop organizer at the end of the first session. ORGANIZER Talib S. Hussain, Ph.D. BBN Technologies 10 Moulton St., Room 308 Cambridge, MA 02474 Phone: 617-873-6861 Fax: 617-873-4328 From wahba at stat.wisc.edu Fri May 6 19:04:30 2005 From: wahba at stat.wisc.edu (Grace Wahba) Date: Fri, 6 May 2005 18:04:30 -0500 Subject: Connectionists: A Framework for Kernel Regularization, TR 1107 Message-ID: <200505062304.j46N4U1R019186@juno.stat.wisc.edu> Announcing the paper: A Framework for Kernel Regularization with Application to Protein Clustering Fan Lu, Sunduz Keles, Stephen J. Wright and Grace Wahba University of Wisconsin-Madison Statistics Dept TR 1107, May 2005. available at: http://www.stat.wisc.edu/~wahba -> TRLIST or http://www.stat.wisc.edu/~wahba/ftp1/tr1107.pdf Abstract We develop and apply a novel framework which is designed to extract information in the form of a positive definite kernel matrix from possibly crude, noisy, incomplete, inconsistent dissimilarity information between pairs of objects, obtainable in a variety of contexts. Any positive definite kernel defines a consistent set of distances, and the fitted kernel provides a set of coordinates in Euclidean space which attempt to respect the information available, while controlling for complexity of the kernel. The resulting set of coordinates are highly appropriate for visualization and as input to classification and clustering algorithms. The framework is formulated in terms of a class of optimization problems which can be solved efficiently using modern convex cone programming software. The power of the method is illustrated in the context of protein clustering based on primary sequence data. An application to the globin family of proteins resulted in a readily visualizable 3D sequence space of globins, where several sub-families and sub-groupings consistent with the literature were easily identifiable. Included in the framework is an algorithm for placing new objects in the coordinate space of the training set. Keywords: Regularized Kernel Estimation, positive definite matrices, noisy dissimilarity data, modern convex cone programming, protein clustering, globin family, support vector machines, classification. From claudio at scan.berkeley.edu Mon May 9 15:11:47 2005 From: claudio at scan.berkeley.edu (Claudio Privitera) Date: Mon, 09 May 2005 12:11:47 -0700 Subject: Connectionists: Starkfest Conference on Vision and Movement in Men and Machines Message-ID: <5.2.1.1.2.20050509115708.045c6ec0@scan.berkeley.edu> Dear Members of Connectionists, just a brief note to inform you that we are still accepting registrations and paper submissions for the fourth edition of the Starkfest, the Conference on Vision and Movement in Men and Machines, planned at the School of Optometry, University of California, Berkeley, for the two days of May, Friday and Saturday the 27th and 28th. Conference topics will emphasize all those concepts that Lawrence Stark initiated or developed and they include: Oculomotor System Scanpath and related Visual Theories Sensorimotor Control Man-Machine Interface Virtual Reality Robotics For more information, please check: http://scan.berkeley.edu/Starkfest/ Cordially, Conference chairs: Dr. Claudio Privitera School of Optometry, University of California, Berkeley Dr. John Semmlow Biomedical Eng., Rutgers, State University of New Jersey From eliassi at cs.wisc.edu Tue May 10 03:23:46 2005 From: eliassi at cs.wisc.edu (Tina Eliassi-Rad) Date: Tue, 10 May 2005 02:23:46 -0500 (CDT) Subject: Connectionists: Graduate Summer School at UCLA's Institute for Pure and Applied Mathematics Message-ID: Institute for Pure & Applied Mathematics (IPAM) University of California, Los Angeles Graduate Summer School: Intelligent Extraction of Information from Graphs and High Dimensional Data July 11-29, 2005 http://www.ipam.ucla.edu/programs/gss2005/ In recent years, there has been a rapidly increasing demand for targeted analysis of large data streams and large networks. One of the main goals has been identification of key features: face recognition in video streams and voice recognition in audio streams are two examples. Another goal has been inference of relationships: pattern discovery in large databases and determination of key links in social networks. At the same time, a number of scientific disciplines have come together to develop a theory for the analysis of high-dimensional data, as well as for the analysis of dynamic processes on massive graphs. The new techniques and new mathematics coming out of this line of research are ideally suited to a wide range of applications. Applications and connections to real challenges will be drawn from: data fusion, automated feature extraction, face and shape recognition, spectral and hyperspectral image analysis, relational data mining, link analysis and discovery, graph mining, social and transactional networks, robust network design (making networks hard to break), optimal epidemic intervention (making networks easy to break), and hidden state inference (where are targets based on indirect measurements?). The summer school is intended for graduate students and postdocs, as well as more senior researchers interested in focusing their efforts on these mathematical challenges and crucial applications. The program is organized as follows. Week 1: High-dimensional data, relational data and kernel methods. Week 2: Image analysis and machine learning. Week 3: Streaming data and networks. We anticipate that some participants will be interested in attending the entire program while others will want to stay for only one or two of the week-long sessions. Speakers James Abello (Rutgers University) Uri Alon (Weizmann Institute) Tom Asaki (Los Alamos National Laboratory) Erik Bollt (Clarkson University) Leon Bottou (NEC) Robert Burleson (Lawrence Livermore National Laboratory) Frdric Cao (IRISA) Rick Chartrand (Los Alamos National Laboratory) Ronald Coifman (Yale University) John Conroy (Institute for Defense Analysis) Terence Critchlow (Lawrence Livermore National Laboratory) George Cybenko (Dartmouth University) David Donoho (Stanford University) Tina Eliassi-Rad (Lawrence Livermore National Laboratory) Christos Faloutsos (Carnegie Mellon University) Leslie Greengard (New York University/Courant Institute of Mathematical Sciences) Dennis Healy (DARPA) Martial Hebert (Carnegie Mellon University) David Heckerman (Microsoft Research) Piotr Indyk (Massachusetts Institute of Technology) Peter Jones (Yale University) Michael Jordan (University of California at Berkeley) Ron Kimmel (Technion, Haifa, Israel) Daphne Koller (Stanford University) John Lafferty (Carnegie Mellon University) Yann LeCun (New York University) Gilad Lerman (University of Minnesota) Mehryar Mohri (New York University) Andrew Moore (Carnegie Mellon University) Jean-Michel Morel (Ecole Normale Suprieure, Cachan, France) Robert Nowak (University of Wisconsin) Bruno Olshausen (University of California at Davis) Stanley Osher (IPAM) Carey Priebe (Johns Hopkins University) Prabhakar Raghavan (Verity, Inc. and Stanford University) Ronald Resmini (NGA) Guillermo Sapiro (University of Minnesota) Lawrence Saul (University of Pennsylvania) Edward Scheinerman (Johns Hopkins University) Larry Schultz (Los Alamos National Laboratory) Ingo Steinwart (Los Alamos National Laboratory) William Szewczyk (NCSC) Demetri Terzopoulos (New York University) James Theiler (Los Alamos National Laboratory) Godfried Toussaint (McGill University) Richard Tsai (Princeton University) Kevin Vixie (Los Alamos National Laboratory) Grace Wahba (University of Wisconsin) From tobias at chaos.gwdg.de Tue May 10 10:58:29 2005 From: tobias at chaos.gwdg.de (Tobias Niemann) Date: Tue, 10 May 2005 16:58:29 +0200 Subject: Connectionists: Bernstein Fellow for Computational Neuroscience - Postdoctoral Research Positions Message-ID: <4280CC15.8080601@chaos.gwdg.de> BCCN G?TTINGEN - Bernstein Center for Computational Neuroscience Bernstein Fellow for Computational Neuroscience Applications are invited for up to three Postdoctoral Research Positions in Computational Neuroscience at the recently established Bernstein Center for Computational Neuroscience (BCCN) in G?ttingen, Germany. G?ttingen is a center of neuroscience in Europe hosting numerous internationally recognized neuroscience research institutions, including three Max Planck Institutes, the European Neuroscience Institute, the German Primate Research Center, and G?ttingen University's Centers for Systems Neuroscience (ZNV) and for the Molecular Physiology of the Brain (CMPB). The BCCN integrates theoretical and experimental research groups from these institutions to foster interdisciplinary research in computational neuroscience specifically supporting close collaboration between theorists and experimental researchers. We are looking for strong research personalities, who are experienced in the field of Computational Neuroscience and/or related disciplines such as theoretical physics, mathematics, or computer science and with commitment to a research career in neuroscience. Prior biological or neuroscience training is welcome but not required. The Bernstein Fellow will have the opportunity to collaborate with other members of the BCCN or establish an own research program which complements the activities of the BCCN. Initially the positions are limited to two years and may be extended to up to five years. Applications are welcome from now on until the positions are filled. Please submit your application preferably in one single PDF-document, including cover letter, CV, list of publications, research proposal/interests, names of three possible referees, relevant certificates, and copies of three of your most important publications to: jobs at bccn-goettingen.de (Subject: Bernstein Fellow) For more information please refer to http://www.bccn-goettingen.de While e-mail is preferred, applications may also be submitted in hardcopy to the following address: Prof. Dr. Theo Geisel Subject: Bernstein Fellow Bernstein Center for Computational Neuroscience (BCCN) G?ttingen Max-Planck-Institute for Dynamics and Self-Organization Bunsenstrasse 10 D - 37073 G?ttingen, Germany http://www.bccn-goettingen.de The BCCN is an equal opportunity employer. From B.Kappen at science.ru.nl Thu May 12 11:28:29 2005 From: B.Kappen at science.ru.nl (Bert Kappen) Date: Thu, 12 May 2005 17:28:29 +0200 (CEST) Subject: Connectionists: paper available on efficient stochastic control Message-ID: Dear all, I would like to announce the following paper, that can be downloaded from arxiv.org/physics/0505066 Path integrals and symmetry breaking for optimal control theory H.J. Kappen This paper considers linear-quadratic control of a non-linear dynamical system subject to arbitrary cost. I show that for this class of stochastic control problems the non-linear Hamilton-Jacobi-Bellman equation can be transformed into a linear equation. The transformation is similar to the transformation used to relate the classical Hamilton-Jacobi equation to the Schr\"odinger equation. As a result of the linearity, the usual backward computation can be replaced by a forward diffusion process, that can be computed by stochastic integration or by the evaluation of a path integral. It is shown, how in the deterministic limit the PMP formalism is recovered. The significance of the path integral approach is that it forms the basis for a number of efficient computational methods, such as MC sampling, the Laplace approximation and the variational approximation. We show the effectiveness of the first two methods in number of examples. Examples are given that show the qualitative difference between stochastic and deterministic control and the occurrence of symmetry breaking as a function of the noise. Bert Kappen SNN Radboud University Nijmegen URL: www.snn.kun.nl/~bert The Netherlands tel: +31 24 3614241 fax: +31 24 3541435 B.Kappen at science.ru.nl From niall.griffith at ul.ie Mon May 16 06:56:31 2005 From: niall.griffith at ul.ie (Niall Griffith) Date: Mon, 16 May 2005 11:56:31 +0100 Subject: Connectionists: PhD opportunities in NN and GA modelling of musical instruments and timbre Message-ID: Please Excuse Multiple Postings -------------- Synthesising Consistent Instrument and Voice Sounds using Physically Informed Spectral Models, Neural Networks and Evolutionary Learning. 2 PhD studentships are available to start as soon as possible at the University of Limerick, Ireland for the above project. The studentships cover fees and a monthly stipend (tax-free) of 11,700 Euro for a duration of 3 years. Applicants must be EU nationals, and have some background in either one or all of Evolutionary Computation, Artificial Neural Networks or Music. The project involves three main strands. The strands being 1) DSP & Hidden Markov Models, 2) Evolutionary Learning, and 3) Cognitive and Neural Modelling. The open positions are in areas 2 and 3 above. Applicants are encouraged to forward their CV's and a statement of their research interests and background to either: niall.griffith at ul.ie OR michael.oneill at ul.ie Closing date for applications is 10 June 2005. From F.AlmeidaCosta at sussex.ac.uk Tue May 17 02:15:19 2005 From: F.AlmeidaCosta at sussex.ac.uk (Fernando Almeida e Costa) Date: Tue, 17 May 2005 07:15:19 +0100 Subject: Connectionists: Workshop at Ecal deadline extension Message-ID: ------------------------------------------------------------- THE SUBMISSION DEADLINE FOR THE WORKSHOP *Active Agents and Their Environments as Dynamical Systems* TO BE HELD AT ECAL 2005 HAS BEEN EXTENDED TO: TUESDAY 31ST MAY 2005. ------------------------------------------------------------- ********************************************************************* ...........................Call for papers........................... ......................Workshop @ ECAL 2005....................... .......Active Agents and Their Environments as Dynamical Systems..... .................www.ecal2005.org/workshops.html..................... ............Organized by the activate.d reading group................ ......................University of Sussex........................... ********************************************************************* ECAL2005, in September, will host a workshop on "Active agents and their environments as dynamical systems" organised by the activate.d reading group from the University of Sussex. We are seeking papers within the broad range of the so called dynamical systems approach to life and cognition, from both technical and conceptual/philosophical perspectives. Papers from the workshop will be published in a special issue of the Journal of Adaptive Behavior. You may find detailed information about the workshop in our webpage at www.informatics.sussex.ac.uk/activate.d/workshop at ecal2005 or through the workshop webpage at www.ecal2005.org/workshops.html ******************** PROGRAMME COMMITTEE ******************** Randall Beer, Case Western University. Peter Cariani, Tufts Medical School. Edwin de Jong, Universiteit Utrecht. Ezequiel Di Paolo, University of Sussex. Dario Floreano, Ecole Polytechnique Federale de Lausanne. Inman Harvey, University of Sussex. Phil Husbands, University of Sussex. Takashi Ikegami, University of Tokyo. Scott Kelso, Florida Atlantic University. Luis Mateus Rocha, Indiana University. Tom Ziemke, University of Skovde. ***************** IMPORTANT DATES ***************** EXTENDED submission deadline: 31st of May Review results: 15th of June Corrected papers due: 22nd of June Papers must be emailed in pdf format to one of the organisers (see addresses below) and will be reviewed by at least two independent reviewers, in compliance with the host conference rules. The work to be submitted may include (but is not limited to) topics such as: * Embodied cognition (the exploitation by a cognitive agent, qua cognitive, of all its physical properties). * Evolution of intrinsic and extrinsic morphologies in artificial agents. * Robotics within the framework of the DSaLC (Dynamical Systems approach to Life and Cognition). * Cognition as brain/body/environment interaction. * Online learning as dynamics occurring at different time scales. * Synthesis of dynamical systems models which exhibit adaptive behaviour. * Self-organisation, selection and neutrality in the evolution of dynamical systems. * Agency, homeostasis and autopoiesis. * The present dangers of the (conscious and unconscious) use of GOFAI principles within a DSaLC framework. * Dynamical systems tools for understanding adaptive behaviour. * Behavioural dynamics of interest to cognitive science (e.g. chaotic itinerancy, globally coupled chaotic systems). * Dynamical systems architectures (i.e. neural networks, cellular automata, other models) and their behavioural dynamics. * Models of dynamical systems coupling. Papers should be sent to either one of the workshop organisers: Fernando Almeida e Costa Eduardo Izquierdo-Torres F.AlmeidaCosta at sussex.ac.uk E.J.Izquierdo-Torres at sussex.ac.uk You may find more information about the activate.d reading group at www.informatics.sussex.ac.uk/activate.d From B.Torben-nielsen at CS.unimaas.nl Wed May 18 10:54:41 2005 From: B.Torben-nielsen at CS.unimaas.nl (Torben-nielsen B (CS)) Date: Wed, 18 May 2005 16:54:41 +0200 Subject: Connectionists: Postdoc position available at the Universiteit Maastricht Message-ID: Dear all, At the Insitute for Knowledge and Agent Technology (IKAT), Universiteit Maastricht we have an open postdoc position (f/m, 38 hours a week). Tasks: Learning situated agents to adapt to novel environments by (1) exploiting sensorimotor contingencies, (2) learning techniques for situated adaptive learning, and (3) moving from low-level towards high-level conceptual learning or reasoning. Requirements: IKAT is looking for a bright and enthusiastic Postdoc with interest, skills, and experience in (neural or statistical) learning techniques and various agent architectures. Working experience in the field of robotics is desired. We offer: Temporary appointment for specified period: 48 months. Estimated maximum salary per month ? 3.453,- gross in accordance with scale 10. More information for applicants:Prof.dr. E.O. Postma or Prof.dr. H.J. van den Herik, tel.: 043-3883477, e-mail: postma at cs.unimaas.nl or herik at cs.unimaas.nl Kind regards, Ben Torben-Nielsen From P.Monaghan at psych.york.ac.uk Wed May 18 06:05:35 2005 From: P.Monaghan at psych.york.ac.uk (Padraic Monaghan) Date: Wed, 18 May 2005 11:05:35 +0100 Subject: Connectionists: PhD position in computational modelling of language Message-ID: <428B136F.1030801@psych.york.ac.uk> Marie Curie Early Stage Research Fellow (PhD Position) - Department of Psychology, University of York, UK Applications are invited for a 36-month, fixed-term Early Stage Researcher position to conduct a PhD in the area of computational modelling of language processing with particular emphasis on research into hemispheric specialisation for reading. Dr Padraic Monaghan and Professor Andy Ellis will supervise the post, which is funded by the European Community's Marie Curie scheme as part of the Research Training Network in Language and Brain (http://www.ynic.york.ac.uk/rtn-lab). You will meet the eligibility criteria regarding nationality (according to fellowship rules, applicants must be of non-British nationality and must not have resided in the UK for more than 12 months in the last three years) and will have or be expecting to gain a good first degree in Psychology, Linguistics, Computer Science, or a related discipline. Starting salary minimum 19,460 per annum. This post is available from 1 October 2005. Informal enquiries can be made to Padraic Monaghan (pjm21 at york.ac.uk). The Department of Psychology at the University of York has consistently received the highest possible ratings for its teaching and research, with cutting-edge facilities for experimental, imaging, and computational research. York is also a gorgeous place to live. For details of applying, please go to: http://www.york.ac.uk/univ/mis/cfm/vacancies/vac_detail.cfm?vacno=DR05219 -- Padraic Monaghan Department of Psychology, University of York, York, YO10 5DD, UK direct line: +44 (0)1904 432885; fax: +44 (0)1904 433181 http://www-users.york.ac.uk/~pjm21 From eneher at gwdg.de Thu May 19 03:42:08 2005 From: eneher at gwdg.de (Erwin Neher) Date: Thu, 19 May 2005 09:42:08 +0200 Subject: Connectionists: Job offer Message-ID: Post doctoral position in Goettingen The Department of Membrane Biophysics at the Max Planck Institute for Biophysical Chemistry in cooperation with the Julius Bernstein Center for Computational Neuroscience Goettingen offers a Position (BAT IIa) for a project in Computational Neurobiology The project aims at modeling of various forms of dynamic neuronal networks implementing ?realistic? short-term plasticity. Particularly, the specific properties of short-term facilitation and depression, as observed in the Calyx of Held are to be modeled. The task is to explore, how variations around the experimentally observed dynamics influence network properties, such as the number and classes of attractors, the response to transient stimulation, and various aspects of information processing, rhythm generation, cortical gain control and temporal filtering. In addition, we would like to model how the particular form of short-term depression, which is observed in our experimental system (the Calyx of Held; Forsythe, 1994; Trommersh?user et al., 2003), influences signal processing in the auditory pathway, of which the Calyx of Held is part. The Max Planck Institute for biophysical Chemistry adheres to the principle of equal opportunity employment and strongly encourages applications from qualified women. Preference will be given to disabled applicants with the same qualification and skills. Please address applications to: Prof. Dr. Erwin Neher Membranbiophysik Max-Planck-Institut f?r biophysikalische Chemie Am Fassberg 11 37077 Goettingen email: eneher at gwdg.de http://www.mpibpc.gwdg.de/abteilungen/140/core.html From Manuel.Davy at ec-lille.fr Fri May 20 02:55:05 2005 From: Manuel.Davy at ec-lille.fr (Davy Manuel) Date: Fri, 20 May 2005 08:55:05 +0200 Subject: Connectionists: Post-doc position at CNRS, Lille, France Message-ID: <428D89C9.2020806@ec-lille.fr> Post-Doctoral Position Title: Speech processing using kernel methods Context and Topic Performance of state-of-the-art speech recognition systems has greatly improved over the last years. However, these systems do not fully take advantage of today's computer computation and memory capabilities. Kernel learning methods, such as Support Vector Machines, have recently undegone a huge development, and already give excellent results in fields such as image processing, when compared to other more cassical approaches. The aim of this post-doc is to apply and develop kernel techniques so as to improve the performance of speech recogintion systems. Place: The position is based in the Laboratoire d'Automatique, de G?nie Informatique et Signal (LAGIS) in Lille (North of France). The LAGIS Laboratory is one of the major CNRS laboratories in Signal Processing and Automatic Control in the North of France. The position is also connected to the France Telecom Research Center situated in Lannion (Brittany, France). Duration: The position is for one year, and it may start as soon as possible Scientific supervision: This research work will be supervised by Dr Manuel Davy (CNRS researcher, Lille) (web page) and Dr Lionel Delphin-Poulat (France Telecom Researcher, Lannion) Informations and applications: Additional informations can be obtained from Dr Manuel Davy (Manuel dot davy at ec dash lille dott fr) and from Dr Lionel Delphin-Poulat (lionel ddott delphinpoulat at francetelecom dott com) - change 'dot', 'dash' and 'at' to obvious corresponding symbols. Applications should be emailed to Dr Manuel Davy (including CV and two reference letters) From niebur at jhu.edu Thu May 19 13:35:02 2005 From: niebur at jhu.edu (niebur@jhu.edu) Date: Thu, 19 May 2005 13:35:02 -0400 Subject: Connectionists: Programmer/analyst position in neuroscience lab at Johns Hopkins Message-ID: <200505191735.j4JHZ2f10943@russell.mindbrain> Computer programmer / Analyst in neuroscience research project Primary Duties and responsibilities: Programming in C and C++. Paradox (objectPAL), MatLab, ODBC, AutoCAD, LabWindows CVI. Primary duties are to design and develop a real- time data acquisition system for PC's that can run under Qnx or Windows NT. The programmer should be familiar with real-time NT extensions, Qnx and ideally be familiar with neurophysiological research. The programmer must be able to generate visual displays, control hardware. The programmer is also responsible for system management including evaluating, maintaining software and hardware in the lab. Machines and equipment used: Pentium PC, Digital and analog interface= boards. Minimum requirements: Education: BA/BS - biology/neuroscience or computer science or related field. Special Skills/Knowledge: C language, C++ , Dos/ Windows 95/NT, Matlab. Related work experience: Experience with real time programming desired. Additional information: 1-3 years programming experience desired. Candidates must be highly motivated and be able to work independently. The position is in the Zanvyl Krieger Mind/Brain Institute of Johns Hopkins University in Baltimore, Maryland and provides an opportunity to be an integral part of leading edge neuroscience research. Excellent benefits including tuition remission. Hopkins is an equal opportunity employer. Please contact: Steven Hsiao Krieger Mind/Brain Institute Johns Hopkins University Tel: 410-516-6409 Fax: 410-516-8648 E-mail: Steven.Hsiao at jhu.edu -- Dr. Ernst Niebur Krieger Mind/Brain Institute Assoc. Prof. of Neuroscience Johns Hopkins University niebur at jhu.edu http://cnslab.mb.jhu.edu 3400 N. Charles Street (410)516-8643, -8640 (secr), -8648 (fax), -3357 (lab) Baltimore, MD 21218 From terry at salk.edu Fri May 20 01:28:37 2005 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 19 May 2005 22:28:37 -0700 (PDT) Subject: Connectionists: NEURAL COMPUTATION 17:7 In-Reply-To: <200504281700.j3SH0Y872819@kepler.snl.salk.edu> Message-ID: <200505200528.j4K5SbO59466@kepler.snl.salk.edu> Neural Computation - Contents - Volume 17, Number 7 - July 1, 2005 NOTE Catagorization of Neural Excitability using Threshold Models A. Tonnelier LETTERS Theory of the Snowflake Plot and Its Relations to Higher-Order Analysis Methods Gabriela Czanner, Sonja Grun and Satish Iyengar Asymptotic Theory of Information-Theoretic Experimental Design Liam Paninski Maximum Likelihood Set for Estimating a Probability Mass Function Bruno M. Jedynak and Sanjeev Khudanpur Estimating Entropy Rates with Bayesian Confidence Intervals Matthew B. Kennel, Jonathon Shlens, Henry D. I. Abarbanel, and E. J. Chichilnisky Spike Timing Precision and Neural Error Correction: Local Behavior Michael Stiber A New Approach to Spatial Covariance Modeling of Functional Brain Imaging Data: Ordinal Trend Analysis Christian Habeck, John W. Krakauer, Claude Ghez, Harold A. Sackeim, David Eidelberg, Yaakov Stern, and James R. Moeller Investigating the Fault Tolerance of Neural Networks Elko B. Tchernev, Rory G. Mulvaney and Dhananjay S. Phatak Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review Henrik Jacobsson ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2005 - VOLUME 17 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $143 $90 $96.30 Institution $680 $727.60 $734 $612 $654.84 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From mail at jan-peters.net Sat May 21 15:53:27 2005 From: mail at jan-peters.net (Jan Peters) Date: Sat, 21 May 2005 12:53:27 -0700 Subject: Connectionists: [Call for Participation] Learning for Locomotion Workshop Message-ID: <36c633085cc5a60ca98ee655e7c47289@jan-peters.net> ======================================================= Call for Participation Robotics 2005 - Workshop: Learning for Locomotion Cambridge, MA, USA --- June 11, 2005 ======================================================= Quick Facts Organizers: Jan Peters, Russ Tedrake, Stefan Schaal Conference: Robotics - Science and Systems 2005 Date: June 11, 2005 Room: To be announced Location: MIT, Cambridge, MA, USA Website: http://www-clmc.usc.edu/~jrpeters/workshop.html Alternate Website: http://www.jan-peters.net/Research/LearningForLocomotion Abstract Over the last few decades, there has been an impressive amount of published work on legged locomotion, including bipedal walking, running, hopping, stand-ups, summersaults and much more. However, despite all this progress, legged locomotion research has largely been driven by researchers using human insight and creativity in order to generate locomotion control algorithms. In order to improve the robustness, energy efficiency, and natural appearance of legged locomotion, there may be a significant advantage to using machine learning methods to synthesize new controllers and to avoid tedious parameter tuning. For instance, it could be advantageous to learn dynamics models, kinematic models, impact models, for model-based control techniques. Imitation learning could be employed for the teaching of gaits patterns, and reinforcement learning could help tuning parameters of the control policies in order to improve the performance with respect to given cost functions. In this context, we would like to bring together researchers from both the legged locomotion and machine learning in order to discuss which locomotion problems require learning, and to identify the machine learning methods that can be used to solve them. Goal In order to better understand the application of machine learning techniques to locomotion, our goal is to bring together researchers who represent many different approaches to biped locomotion control with their peers in machine learning for control. We hope to discuss future research directions for principled machine learning approaches to biped locomotion. The workshop will address topics such as: * Which unsolved biped locomotion problems can be solved using learning? * Can walking be broken down into components upon which machine learning methods are applicable? * What models (e.g., forward, inverse, impact) would be desirable for controlling locomotion? * Can machine learning methods help solve the gait generation and foot-placement problems? * Can human learning of locomotion yield insights for both robotics and machine learning? * Which machine learning algorithms are suitable for online implementation on the robot, and which problems can be solved in simulation? * What cost functions should be used to describe "optimal" walking, and what experiments should be done to test our controllers? Furthermore, we intend to kick-off the Legged Robot Control Competition. Program The tentative program and list of speakers can be found at the Workshops Website ( http://www-clmc.usc.edu/~jrpeters/workshop.html ) or the alternative website ( http://www.jan-peters.net/Research/LearningForLocomotion ). Organizers The workshop is organized by Jan Peters, Russ Tedrake and Stefan Schaal, from the Departments of Computer Science and Neuroscience, University of Southern California, Los Angeles, CA, USA and from the Brain and Cognitive Sciences Department at the Massachusetts Institute of Technology, Cambridge, MA, USA. Location and More Information The most up-to-date information about Robotics - Science and Systems 2005 can be found on the Robotics 2005 website ( http://www.robotics-conference.org ). From cmbishop at microsoft.com Wed May 25 09:36:33 2005 From: cmbishop at microsoft.com (Christopher Bishop) Date: Wed, 25 May 2005 14:36:33 +0100 Subject: Connectionists: Postdoctoral Research Fellowship, Darwin College and Microsoft Research, Cambridge U.K. Message-ID: <6C6555DF5D075A4EA6D27706F4EC597502AA324E@EUR-MSG-10.europe.corp.microsoft.com> Postdoctoral Research Fellowship in Adaptive Computing DARWIN COLLEGE CAMBRIDGE Microsoft Research Fellowship The Governing Body of Darwin College Cambridge and Microsoft Research jointly invite applications for a stipendiary Research Fellowship supporting research in the field of adaptive computing (including topics such as pattern recognition, probabilistic inference, machine learning and computer vision). Applicants should hold a PhD or should be expecting to have submitted their thesis prior to commencement of the Fellowship. The Fellowship will be tenable for two years commencing 1 January 2006 or on a date to be agreed. The successful candidate will work at the Microsoft Research Laboratory in Cambridge in the Machine Learning and Perception group. Information about the laboratory and about the group is available from http://research.microsoft.com/cambridge/. Further details about the College are available from the College website http://www.dar.cam.ac.uk. The closing date for applications is 13 June 2005. Eligibility Men and women graduates of any university are eligible to apply, irrespective of age, provided they have a doctorate or an equivalent qualification, or expect to have submitted their thesis before taking up the Fellowship. Duties The successful candidate will engage in research full-time at the Microsoft Research Laboratory in Cambridge. The Fellow will be a member of the Governing Body of Darwin College and will be subject to the Statutes and Ordinances of the College which may be seen on request to the Bursar. The Statutes include the obligation to reside in or near Cambridge for at least two-thirds of each University term, but the Governing Body will normally excuse absences made necessary by the nature of the research undertaken. Stipend and Emoluments The stipend will be dependent upon age and experience. Membership of the Universities' Superannuation Scheme is optional. In addition the Fellow will be able to take seven meals per week at the College table free of charge and additional meals at his or her own expense. Guests may be invited to all meals (within the limits of available accommodation), ten of them free of charge within any quarter of the year. College accommodation will be provided, subject to availability, or an accommodation allowance will be paid in lieu. In addition to a salary the Fellowship provides funding for conference participation. Applications Applications (in Word, PDF or txt format only) should be by emailed to cambpdoc at microsoft.com with the subject line 'Darwin Microsoft Fellowship'. They should arrive by 13 June 2005 and should include (1) a curriculum vitae, (2) an account, in not more than 1000 words, of the proposed research, including a brief statement of the aims and background to it, (3) the names and addresses of three referees (including telephone, fax and email co-ordinates), WHO SHOULD BE ASKED TO EMAIL REFERENCES IMMEDIATELY DIRECT TO THE ABOVE EMAIL ADDRESS, and (4) a list of published or unpublished work that would be available for submission if requested. Short-listed candidates may be asked to make themselves available for interview at Darwin College on a date to be arranged. Election will be made as soon as possible thereafter. Travelling expenses for interviewees will be covered. - The College follows an equal opportunities policy - From frank.ritter at psu.edu Tue May 24 23:48:06 2005 From: frank.ritter at psu.edu (Frank Ritter) Date: Tue, 24 May 2005 23:48:06 -0400 Subject: Connectionists: CogModeling notes: ICCM 2006 / CogSci06 tutorials / ONR Position Message-ID: [please forward this as/if appropriate] This is based on the International Cognitive Modeling Conference mailing list, which I maintain. I've added myself to your list in order to send this to you. I send the messages out by hand using some Emacs functions. The first announcement is the one that is driving this email, the announcement of ICCM 2006. I don't anticipate much more traffic though, until the next ICCM in Trieste in 2006 has its paper call to go out for formally in the autumn. I forward messages about twice a year. cheers, Frank 1. 2006 International Conference on Cognitive Modeling Thursday, 4 April 2006 to 8 April 2006, in Trieste, Italy http://iccm2006.units.it/ 2. Tutorial program at 2005 Cognitive Science Conference, Wed 20 July 2005: ACT-R/Chrest/COGENT/Event-related Brain Potentials/LSA http://homepages.inf.ed.ac.uk/keller/cogsci05/program_tutorials.html (registration also up today!) 3. Cognitive modeling/human factors/HCI position at Office of Naval Research Closing date, 1 June 2005 http://chart.donhr.navy.mil/JobSearch/jobdetail.asp?strView=0&vid=60910 *************************************************** 1. 2006 International Conf. on Cognitive Modeling Thursday, 4 April 2006 to 8 April 2006, in Trieste, Italy http://iccm2006.units.it/ or contact iccm2006 at units.it. This continues the series of ICCM conferences. The last conference was at Pittsburgh. http://simon.lrdc.pitt.edu/~iccm/ This conference will build on that one's success. Paper submissions (6 pages) provisionally due November 20th, 2005. *************************************************** 2. Tutorial Program at Cognitive Science 2005, 20 July 2005 http://homepages.inf.ed.ac.uk/keller/cogsci05/program_tutorials.html Tutorials will present tutorial material, that is, provide results that are established and will do so in an interactive format. They tend to involve an introduction to technical skills or methods. This year the set of tutorials is focused on a range of cognitive architectures for modeling and teaching higher-level cognition, and on a method for gathering data. They will include substantial review of material. The level of presentation assumes that the attendees have at least a first degree in a cognate area. There is a student rate, and such students must bring their ID to show at registration. Attendance at the tutorials does not require conference registration, but tutorial registration does not provide conference entrance. There are five tutorials this year (one with two parts). They are likely to cost about $63 (about 35 pounds or 50 Euros) for each half-day tutorial and 30e ($38) for students. Payment can be made using the registration site on the conference page, or can be paid for on the day (if space is available, which is likely). The program includes handouts, and a tea and a coffee break (including biscuits). There will be a meeting of the tutorial committee and tutors after the tutorials, location to be announced at the tutorials. TOPICS MORNING Peter Lane and Fernand Gobet: CHREST Tutorial: Simulations of Human Learning Richard Cooper: An introduction to the COGENT Cognitive Modelling Environment Matthias Schlesewsky and Ina Bornkessel: Event-Related Brain Potentials in Language (Part 1: Introduction) Afternoon Niels Taatgen and Hedderik van Rijn: ACT-R Tutorial Benoit Lemaire and Guy Denhiere: Latent Semantic Analysis Matthias Schlesewsky and Ina Bornkessel: Event-Related Brain Potentials in Language (Part 2: Advanced Topics) *************************************************** 3. Cognitive modeling/human factors/HCI position at Office of Naval Research http://chart.donhr.navy.mil/JobSearch/jobdetail.asp?strView=0&vid=60910 Contact Susan Chipman (below) for more details. Program Officer, Human Factors (Industrial engineer) The Office of Naval Research is seeking a qualified individual to manage sponsored basic/applied research, and advanced development program and projects in the broad area of human factors engineering. The sponsored efforts are conducted at US universities and industry or Federal Labs. This is a civil service position at the GS-14/15 level ($88k-135k) depending on individual qualifications. The position requires knowledge and experience in the fundamental theories, concepts, and current state-of-the art research and/or technology development in the areas of human systems integration, human factors engineering, and industrial engineering including but not limited to, human decision making, organizational design and architectures, models for human-computer interaction, including computational models of human cognitive processing. For information on qualifications and how to apply, see the job announcements at our web site http://www.onr.navy.mil/hr. Susan writes: The quality of the people who end up in these positions is extremely important to the research community as well as to the Navy. The person in this position will have the opportunity to shape research programs and investments for many years to come. Program officers at ONR have real power of decision in funding. In addition, a less visible aspect of their role is developing ideas, mega-proposals one might say, and obtaining funding for them. Despite the use of the term, "engineer", I am sure that cognitive scientists [and I would suggest, HCI] with many different formal degrees would be able to get this position, as long as they have appropriate expertise. The government never has absolute degree requirements. Application of cognitive modeling to human systems integration is of particular interest. for more information, contact: Susan F. Chipman, Ph.D. ONR Code 342 800 N. Quincy Street Arlington, VA 22217-5660 phone: 703-696-4318 fax: 703-696-1212 *************************************************** -30- (END) From cindy at bu.edu Fri May 27 10:38:20 2005 From: cindy at bu.edu (Cynthia Bradford) Date: Fri, 27 May 2005 10:38:20 -0400 Subject: Connectionists: Neural Networks 18(4) 2005: Special Issue on Emotion and Brain Message-ID: <200505271438.j4REcKVN013923@kenmore.bu.edu> NEURAL NETWORKS 18(4) Contents - Volume 18, Number 4 - 2005 Special Issue on "Emotion and Brain: Understanding Emotions and Modelling their Recognition", J.G. Taylor, K. Scherer, and R. Cowie (editors) ------------------------------------------------------------------ Introduction to the Special Issue J.G. Taylor, K. Scherer, and R. Cowie A systems approach to appraisal mechanisms in emotion David Sander, Didier Grandjean, and Klaus R. Scherer The interaction of attention and emotion John G. Taylor and Nickolaos Fragopanagos Beyond emotion archetypes: Databases for emotion modelling using neural networks Roddy Cowie, Ellen Douglas-Cowie, and Cate Cox Emotion recognition in human-computer interaction N. Fragopanagos and J.G. Taylor Challenges in real-life emotion annotation and machine learning based detection Laurence Devillers, Laurence Vidrascu, and Lori Lamel Emotion recognition through facial expression analysis based on a neurofuzzy network Spiros V. Ioannou, Amaryllis T. Raouzaiou, Vasilis A. Tzouvaras, Theofilos P. Mailis, Kostas C. Karpouzis, and Stefanos D. Kollias ASR for emotional speech: Clarifying the issues and enhancing performance T. Athanaselis, S. Bakamidis, I. Dologlou, R. Cowie, E. Douglas-Cowie, and C. Cox Emotion understanding from the perspective of autonomous robot research Lola Canamero ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 (regular) SEK 660 Y 13,000 Neural Networks (plus Y 2,000 enrollment fee) $20 (student) SEK 460 Y 11,000 (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- membership without $30 SEK 200 not available Neural Networks to non-student (subscribe through another society) Y 5,000 student (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- Name: ______________________________________________________ Title: ______________________________________________________ Address: ______________________________________________________ Phone: ______________________________________________________ Fax: ______________________________________________________ Email: ______________________________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number _______________________________ expiration date _____________________________ INNS Membership 2810 Crossroads Drive, Suite 3800 Madison WI 53718 USA 608 443 2461, ext. 138 (phone) 608 443 2474 (fax) srees at reesgroupinc.com http://www.inns.org ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership JNNS Secretariat c/o Fuzzy Logic Systems Institute 680-41 Kawazu, Iizuka Fukuoka 820-0067 Japan 81 948 24 2771 (phone) 81 948 24 3002 (fax) jnns at flsi.cird.or.jp http://www.jnns.org/ ---------------------------------------------------------------------------- From masulli at disi.unige.it Fri May 27 06:50:00 2005 From: masulli at disi.unige.it (Francesco Masulli) Date: Fri, 27 May 2005 12:50:00 +0200 Subject: Connectionists: SECOND AND LAST CALL CFP: CIBB 2005 - paper submission deadline 30 May 2005 Message-ID: <200505271250.00963.masulli@disi.unige.it> SECOND AND LAST CALL FOR PAPERS CIBB 2005 Second International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics Crema, ITALY -- September 15-17, 2005 Meeting Website: http://cibb05.disi.unige.it/ CIBB 2005 addresses a cutting edge area of application of Neural Networks, Fuzzy Logic and Evolutionary Computation methods. Technical areas include, but are not limited to: - Data and methods for prognosis - Data and methods for diagnosis - Integration of clinical and genetic data - Proteomics - Pharmacogenetics CIBB 2005 is jointly organized by - BIOPATTERNS, European Network of Excellence on Computational Intelligence for Biopattern analysis in Support of eHealthcare - INNS, International Neural Network Society - SIREN, Italian Neural Networks Society CIBB 2005 will took place at Dipartimento di Tecnologie dell'Informazione Universita' degli Studi di Milano via Bramante 65, I-26013 Crema, ITALY in connection with WILF 2005 - Sixth International Workshop on Fuzzy Logic and Applications (http://dsa.uniparthenope.it/wilf2005/) All accepted papers submitted by registered participants to WILF 2005 will be included in the proceedings book of WILF 2005, that will be published by an international Publisher. Important Dates Submission deadline: 30 May 2005 Notification of acceptance: 30 June 2005 Camera ready papers due: 15 July 2005 Meeting: 15-17 September 2005 Submission of papers: Papers must not be longer than 6 pages, including a cover sheet stating: (1) Paper title; (2) Keywords; (3) Authors names and affiliations; (4) Corresponding author's name and contact details, including telephone/fax numbers and e-mail address. For electronic submission refer to the CIBB 2005 web site http://cibb05.disi.unige.it/. Chairs Francesco Masulli University of Pisa (Italy) Antonina Starita University of Pisa (Italy) Roberto Tagliaferri University of Salerno (Italy) International Program Committee Giovanni Cuda, University of Catanzaro, Italy Alexandru Floares, Oncological Institute Cluj-Napoca, Romania Jon Garibaldi, University of Nottingham, UK Nik Kasabov, Auckland University of Technology, NZ Natalio Krasnogor, University of Nottingham, UK Evangelia Micheli-Tzanakou, Rutgers University, NJ - USA Sushmita Mitra, Indian Statistical Institute Kolkata, India Alberto Paccanaro,Yale University, CT, USA David Alejandro Pelta, University of Granada, Spain Udo Seiffert, Leibniz Institute, Gatersleben, Germany L?onard Studer, ABMI SA, Dorigny Lausanne, Switzerland Anna Tramontano, University of Rome "La Sapienza", Italy - From stefan.wermter at sunderland.ac.uk Wed May 25 12:30:02 2005 From: stefan.wermter at sunderland.ac.uk (Stefan Wermter) Date: Wed, 25 May 2005 17:30:02 +0100 Subject: Connectionists: Stipend funding available for MSc Intelligent Systems Message-ID: <4294A80A.3010708@sunderland.ac.uk> Stipends available for MSc Intelligent Systems ----------------------------------------------- We are pleased to announce that for eligible EU students we have obtained funding to offer a bursary for our MSc Intelligent Systems in October 2005 of about 8.000 EURO (about 5500 pounds) as fee waiver and stipend. ***Please forward to students who may be interested.*** The School of Computing and Technology, University of Sunderland is delighted to announce the launch of its MSc Intelligent Systems programme for October 2005. Building on the School's leading edge research in intelligent systems this masters programme will be funded via the ESF scheme (see below). Intelligent Systems is an exciting field of study for science and industry since the currently existing computing systems have often not yet reached the various aspects of human performance. "Intelligent Systems" is a term to describe software systems and methods, which simulate aspects of intelligent behaviour. The intention is to learn from nature and human performance in order to build more powerful computing systems. The aim is to learn from cognitive science, neuroscience, biology, engineering, and linguistics for building more powerful computational system architectures. In this programme a wide variety of novel and exciting techniques will be taught including neural networks, intelligent robotics, machine learning, natural language processing, vision, evolutionary genetic computing, data mining, fuzzy methods, and hybrid intelligent architectures. Funding of about 5500 pounds (about 8.000 Euro) for eligible EU students ------------------------------ The Bursary Scheme applies to this Masters programme commencing October 2005 and we have obtained funding through the European Social Fund (ESF). ESF support enables the University to waive the normal tuition fee and provide a bursary of 50 per week for 45 weeks for eligible EU students, together up to about 5500 pounds or about 8000 Euro. For further information in the first instance please see: http://www.his.sunderland.ac.uk/Teaching_frame.html http://osiris.sund.ac.uk/webedit/allweb/courses/progmode.php?prog=G550A&mode=FT&mode2=&dmode=C http://www.his.sunderland.ac.uk/teaching/sund_is_app.pdf For information on applications and start dates contact: gillian.potts at sunderland.ac.uk Tel: 0191 515 2758 For academic information about the programme contact: alfredo.moscardini at sunderland.ac.uk Please forward to interested students. Stefan *************************************** Stefan Wermter Professor for Intelligent Systems Centre for Hybrid Intelligent Systems School of Computing and Technology University of Sunderland St Peters Way Sunderland SR6 0DD United Kingdom phone: +44 191 515 3279 fax: +44 191 515 3553 email: stefan.wermter at sunderland.ac.uk http://www.his.sunderland.ac.uk/~cs0stw/ http://www.his.sunderland.ac.uk/ **************************************** From b.graham at cs.stir.ac.uk Mon May 30 10:14:48 2005 From: b.graham at cs.stir.ac.uk (Bruce Philip Graham) Date: Mon, 30 May 2005 15:14:48 +0100 (BST) Subject: Connectionists: FINAL CALL: Neuroinformatics Simulation Tools Summer School In-Reply-To: <4336.139.153.254.219.1115141677.squirrel@www.cs.stir.ac.uk> References: <4336.139.153.254.219.1115141677.squirrel@www.cs.stir.ac.uk> Message-ID: <1181.213.78.103.162.1117462488.squirrel@www.cs.stir.ac.uk> Dear all, Please note that the application deadline for our summer school is only ONE WEEK away (6th June)! > 2005 EDINBURGH SUMMER SCHOOL IN NEUROINFORMATICS > > SIMULATION TOOLS > > Institute for Adaptive and Neural Computation > University of Edinburgh. > > August 22-26, 2005 > * Application deadline: 6th June 2005 * > > This summer school in Neuroinformatics Simulation Tools is a > five day intensive course which will provide a practical > introduction > to using neuroscience simulation tools including NEURON and Catacomb > for computational modelling of neural systems. > > The course will be held in the Institute for Adaptive and Neural > Computation in the centre of Edinburgh and will include talks from > invited speakers as well as practical hands-on experience using the > latest simulation tools. > > The course is aimed at PhD students, postdocs and faculty in > neuroscience and related disciplines wishing to learn how to apply > computational modelling techniques to their research problems. > > Bursaries are available for PhD students to cover accommodation > costs. > > For more details, and an online application form visit:- > http://www.anc.ed.ac.uk/school > > -- Dr Bruce Graham, Lecturer (b.graham at cs.stir.ac.uk) Dept. of Computing Science and Mathematics, University of Stirling, Stirling FK9 4LA phone: +44 1786 467 432 fax: +44 1786 464 551 -- The University of Stirling is a university established in Scotland by charter at Stirling, FK9 4LA. Privileged/Confidential Information may be contained in this message. If you are not the addressee indicated in this message (or responsible for delivery of the message to such person), you may not disclose, copy or deliver this message to anyone and any action taken or omitted to be taken in reliance on it, is prohibited and may be unlawful. In such case, you should destroy this message and kindly notify the sender by reply email. Please advise immediately if you or your employer do not consent to Internet email for messages of this kind. From zoubin at gatsby.ucl.ac.uk Sun May 29 22:34:50 2005 From: zoubin at gatsby.ucl.ac.uk (Zoubin Ghahramani) Date: Mon, 30 May 2005 03:34:50 +0100 Subject: Connectionists: AISTATS 2005 full proceedings available online Message-ID: <17050.31690.795936.893269@pitts.gatsby.ucl.ac.uk> The full proceedings of the 2005 AI and Statistics Workshop are now available online, both as individual papers and as a single pdf file. Please see: http://www.gatsby.ucl.ac.uk/aistats/proceedings.htm A bibtex file of all papers in the proceedings is also available at this site. Sincerely, Zoubin Ghahramani and Robert Cowell co-chairs From oreilly at psych.colorado.edu Thu May 5 02:58:39 2005 From: oreilly at psych.colorado.edu (Randall C. O'Reilly) Date: Thu, 5 May 2005 00:58:39 -0600 Subject: Connectionists: Re: Request: PDP++ software usage reports In-Reply-To: <200503312110.59449.oreilly@psych.colorado.edu> References: <200503312110.59449.oreilly@psych.colorado.edu> Message-ID: <200505050058.39882.oreilly@psych.colorado.edu> I apologize for a second email, but I neglected to mention that the deadline is May 15th, and we would appreciate this information by May 9th (this coming Monday) if possible. Also, please include any in-press or submitted papers. Thanks again! - Randy On Thursday 31 March 2005 09:10 pm, Randall C. O'Reilly wrote: > We are planning to write a grant proposal to support major enhancements to > the PDP++ neural network simulation software, and need to collect some data > on publications, teaching, and other usage of this software. > > If you have used PDP++ for simulations published in any form, please email > me the reference(s) to these publications (APA format preferred, but any > format will do). > > If you have used PDP++ for teaching, please send the name of the course, > years taught, number of students, etc. (any information would be > appreciated, the more the better). > > If you have used PDP++ for other purposes (e.g., business, forecasting, > etc) please send any relevant information. > > Finally, if you have any feedback on the software for things that we should > improve in the future, we would like to hear it. We have already begun the > revisions and have a fairly detailed plan, which we will be announcing > within a few weeks on the pdp-discuss email list, so your feedback would be > most beneficial if it could be given in the context of these plans, but if > you would rather just send feedback now, that would also be appreciated. > > To subscribe to the pdp-discuss email list, see the PDP++ website at: > > http://psych.colorado.edu/~oreilly/PDP++/PDP++.html *or* > http://www.cnbc.cmu.edu/Resources/PDP++/PDP++.html > > Thanks! > > - Randy From popescu at prosun.first.fraunhofer.de Wed May 4 13:41:00 2005 From: popescu at prosun.first.fraunhofer.de (Florin Popescu) Date: Wed, 04 May 2005 19:41:00 +0200 Subject: Connectionists: Postdoctoral position and doctoral position at the Fraunhofer Institute FIRST, Berlin. Message-ID: <6.2.0.14.0.20050504181359.03f1b3b8@mailhost> The Fraunhofer-Institute for Computer Architecture and Software Technology FIRST in Berlin is searching for a Postdoc as Research Associate (m/f) The EU-funded BRAIN2ROBOT project will adapt the leading technology developed at the Berlin Brain Computer Interface Laboratory (www.bbci.de) and the Intelligent Data Analysis Department at Fraunhofer Institute FIRST (www.first.fraunhofer.de) to a full arm robotic exoskeleton that will be controlled by EEG activity and aim to restore reaching function in quadriplegic patients. The position is for 3.5 years, starting near or before July 1 2005. For details of a doctoral position (Ph. D. studentship) related to this project, see: http://www.fraunhofer.de/fhg/EN/jobs/Wissenschaft.jsp (FIRST-113-05-004). The post-doctoral candidate will be expected to work on the neuro-physiological aspects of the envisioned research, which allows for basic science studies in motor control and brain function, as a complement to the main objective of arm function restoration. The expected qualifications are a strong background of independent-minded research as evidenced by a strong publication record, experience with on-line or off-line EEG analysis, and prior work in a clinical research environment. Further helpful experience would be scientific programming (e.g. MATLAB) and knowledge of machine learning, neural networks and/or related computer science topics. The eligibility requirements, set forth by European Union regulations on Marie Curie EXT Grants and therefore inflexible, are 4-10 years of research experience, counting doctoral research. It is acceptable that the candidate has not yet received his/her Ph. D. but will do so imminently. This degree is expected to be in physiology, biomedicine, or closely related areas. The working language of the laboratory is English. The monthly salary is ca. 3250 Euro (before taxes and social security). Preference will be given to nationals of EU member states (other than Germany) and nationals of EU associated states. International candidates will also receive mobility and travel allowances of up to approx. 9300 Euro per annum depending on current residency and family status. Please send your CV, cover letter and a sample of published work to (referring to job number FIRST-113-05-003): Fraunhofer-Gesellschaft Zentrale-Hauptabteilung Personal Frau Rabel Kekul?str. 7, 12489 Berlin For further information contact: Florin Popescu, Ph.D. Email: florin.popescu at first.fraunhofer.de From b.graham at cs.stir.ac.uk Fri May 6 12:43:56 2005 From: b.graham at cs.stir.ac.uk (Bruce Philip Graham) Date: Fri, 6 May 2005 17:43:56 +0100 (BST) Subject: Connectionists: 2005 Edinburgh Neuroinformatics Simulation Tools Summer School Message-ID: <2166.139.153.254.219.1115397836.squirrel@www.cs.stir.ac.uk> 2005 EDINBURGH SUMMER SCHOOL IN NEUROINFORMATICS SIMULATION TOOLS Institute for Adaptive and Neural Computation University of Edinburgh. August 22-26, 2005 * Application deadline: 6th June 2005 * This summer school in Neuroinformatics Simulation Tools is a five day intensive course which will provide a practical introduction to using neuroscience simulation tools including NEURON and Catacomb for computational modelling of neural systems. The course will be held in the Institute for Adaptive and Neural Computation in the centre of Edinburgh and will include talks from invited speakers as well as practical hands-on experience using the latest simulation tools. The course is aimed at PhD students, postdocs and faculty in neuroscience and related disciplines wishing to learn how to apply computational modelling techniques to their research problems. Bursaries are available for PhD students to cover accommodation costs. For more details, and an online application form visit:- http://www.anc.ed.ac.uk/school -- Dr Bruce Graham, Lecturer (b.graham at cs.stir.ac.uk) Dept. of Computing Science and Mathematics, University of Stirling, Stirling FK9 4LA phone: +44 1786 467 432 fax: +44 1786 464 551 -- The University of Stirling is a university established in Scotland by charter at Stirling, FK9 4LA. Privileged/Confidential Information may be contained in this message. If you are not the addressee indicated in this message (or responsible for delivery of the message to such person), you may not disclose, copy or deliver this message to anyone and any action taken or omitted to be taken in reliance on it, is prohibited and may be unlawful. In such case, you should destroy this message and kindly notify the sender by reply email. Please advise immediately if you or your employer do not consent to Internet email for messages of this kind. From talibshussain at hotmail.com Fri May 6 01:04:58 2005 From: talibshussain at hotmail.com (Talib Hussain) Date: Fri, 06 May 2005 01:04:58 -0400 Subject: Connectionists: CFP - Workshop on Achieving Functional Integration of Diverse Neural Models Message-ID: *********** Call for Papers *********** Workshop on Achieving Functional Integration of Diverse Neural Models August 4, 2005 7 - 10 pm http://openmap.bbn.com/~thussain/NeuralIntegration/index.html Part of IJCNN 2005 (International Joint Conference on Neural Networks) Hilton Bonaventure Hotel Montreal, Quebec, Canada http://faculty.uwb.edu/ijcnn05/ ====================================================== IMPORTANT DATES Quick email indicating interest: As soon as possible Position statement submission: May 16, 2005 Acceptance: May 17, 2005 Camera Ready position statement: May 20, 2005 Please submit to: neuralintegration at yahoo.com ====================================================== TOPICS AND GOALS The field of neural networks presents a very rich variety of models that have been applied to many different problems. However, successful application of neural networks to large-scale problems has been a general weakness. Further, the development of complex neural systems that demonstrate significant cognitive capabilities currently seems beyond reach. There is a critical need for new ideas and techniques for leveraging existing research by integrating current models in meaningful ways, with the goal of producing functional solutions to complex problems. Once we understand how to effectively model not only the detailed processing of specific neural components, but also the rich variety of interactions that may occur between those neural components (and other non-neural ones), we may begin to realize systems that scale well and are cognitively robust. The goals of this workshop are to explore what current integrative approaches and techniques show promise, and identify potential high-payoff areas for future research. Relevant research areas may include, for example, modularity, evolutionary neural systems, hybrid systems that integrate biological processes (such as immune systems and hormonal systems) with neural models, neural growth mechanisms, neural system engineering techniques. The outcome of this workshop is the identification of a set of key research topics on functional neural integration, together with an understanding of the key technical issues, limitations and benefits of each topic. The creation of working groups to pursue these topics will be discussed. The impact of this workshop will be to stimulate new discussion on a critical topic that we as a field ignore at our own risk. New ways of approaching large-scale neural solutions must always be at the fore. The development of effective working groups will be important in generating interest and support from funding agencies and other customers to keep advancing the state-of-the-art. INTENDED AUDIENCE The intended audience for the workshop is the neural network researcher that is interested in large-scale neural models, as well as the customer that is interested in solutions to large-scale, complex problems. The former may include practitioners in modular networks, evolutionary systems, robotic control, cognition, and neurophysiology. The latter may include companies that specialized in robotics, dynamic control systems, prediction and forecasting, as well as government and military agencies. We anticipate up to 20 participants, with a mix from industry, government and academia. WORKSHOP FORMAT The format of the workshop will be three hours with three successive sessions. In the first session, up to 10 presenters will give a 10 minute position statement summarizing their view of the problem, current relevant research that they are aware of, and the key avenues of exploration that they feel will have the most payoff. These position statements will be provided in the official workshop notes. In addition, the workshop organizer will present a short summary of other position statements collected in advance or the day-of from other workshop participants. Immediately following the first session, there will be a 45 minute networking and discussion session in which participants will be encouraged to discuss ideas in small groups and capture their thoughts on paper. In the final session, there will be a mediated discussion to identify the common themes and most promising avenues that have been identified. Working groups for those avenues will be identified and roles for those groups over the next year will be discussed. As time permits, those working groups will break off to determine their roles, agenda and action items. SUBMISSION GUIDELINES The position statement will be 2 pages in length and will begin with the title, author(s)' affiliation and a concise 100 word abstract. Ideally, the abstract will be a one-line summary of the key position taken. The statement will contain three sections titled Problem Statement, Current Research and Key Avenues. * The Problem Statement will give the authors view of the key issues that need to be addressed with regard to the topic of the workshop. * The Current Research section will give brief descriptions of the most applicable, interesting and/or controversial work that the authors feel are critical first steps towards achieving functional integration. * The Key Avenues section will identify what approaches the authors feel will have the highest payoff in the near to mid term. * References should be included at the end and will not count towards the 2 page limit. If your statement is not selected for presentation, you may still be given the option to have it included in the additional workshop notes that will be distributed at the workshop. In this case, you will be required to attend the workshop, and the content of your statement will be summarized by the workshop organizer at the end of the first session. ORGANIZER Talib S. Hussain, Ph.D. BBN Technologies 10 Moulton St., Room 308 Cambridge, MA 02474 Phone: 617-873-6861 Fax: 617-873-4328 From wahba at stat.wisc.edu Fri May 6 19:04:30 2005 From: wahba at stat.wisc.edu (Grace Wahba) Date: Fri, 6 May 2005 18:04:30 -0500 Subject: Connectionists: A Framework for Kernel Regularization, TR 1107 Message-ID: <200505062304.j46N4U1R019186@juno.stat.wisc.edu> Announcing the paper: A Framework for Kernel Regularization with Application to Protein Clustering Fan Lu, Sunduz Keles, Stephen J. Wright and Grace Wahba University of Wisconsin-Madison Statistics Dept TR 1107, May 2005. available at: http://www.stat.wisc.edu/~wahba -> TRLIST or http://www.stat.wisc.edu/~wahba/ftp1/tr1107.pdf Abstract We develop and apply a novel framework which is designed to extract information in the form of a positive definite kernel matrix from possibly crude, noisy, incomplete, inconsistent dissimilarity information between pairs of objects, obtainable in a variety of contexts. Any positive definite kernel defines a consistent set of distances, and the fitted kernel provides a set of coordinates in Euclidean space which attempt to respect the information available, while controlling for complexity of the kernel. The resulting set of coordinates are highly appropriate for visualization and as input to classification and clustering algorithms. The framework is formulated in terms of a class of optimization problems which can be solved efficiently using modern convex cone programming software. The power of the method is illustrated in the context of protein clustering based on primary sequence data. An application to the globin family of proteins resulted in a readily visualizable 3D sequence space of globins, where several sub-families and sub-groupings consistent with the literature were easily identifiable. Included in the framework is an algorithm for placing new objects in the coordinate space of the training set. Keywords: Regularized Kernel Estimation, positive definite matrices, noisy dissimilarity data, modern convex cone programming, protein clustering, globin family, support vector machines, classification. From claudio at scan.berkeley.edu Mon May 9 15:11:47 2005 From: claudio at scan.berkeley.edu (Claudio Privitera) Date: Mon, 09 May 2005 12:11:47 -0700 Subject: Connectionists: Starkfest Conference on Vision and Movement in Men and Machines Message-ID: <5.2.1.1.2.20050509115708.045c6ec0@scan.berkeley.edu> Dear Members of Connectionists, just a brief note to inform you that we are still accepting registrations and paper submissions for the fourth edition of the Starkfest, the Conference on Vision and Movement in Men and Machines, planned at the School of Optometry, University of California, Berkeley, for the two days of May, Friday and Saturday the 27th and 28th. Conference topics will emphasize all those concepts that Lawrence Stark initiated or developed and they include: Oculomotor System Scanpath and related Visual Theories Sensorimotor Control Man-Machine Interface Virtual Reality Robotics For more information, please check: http://scan.berkeley.edu/Starkfest/ Cordially, Conference chairs: Dr. Claudio Privitera School of Optometry, University of California, Berkeley Dr. John Semmlow Biomedical Eng., Rutgers, State University of New Jersey From eliassi at cs.wisc.edu Tue May 10 03:23:46 2005 From: eliassi at cs.wisc.edu (Tina Eliassi-Rad) Date: Tue, 10 May 2005 02:23:46 -0500 (CDT) Subject: Connectionists: Graduate Summer School at UCLA's Institute for Pure and Applied Mathematics Message-ID: Institute for Pure & Applied Mathematics (IPAM) University of California, Los Angeles Graduate Summer School: Intelligent Extraction of Information from Graphs and High Dimensional Data July 11-29, 2005 http://www.ipam.ucla.edu/programs/gss2005/ In recent years, there has been a rapidly increasing demand for targeted analysis of large data streams and large networks. One of the main goals has been identification of key features: face recognition in video streams and voice recognition in audio streams are two examples. Another goal has been inference of relationships: pattern discovery in large databases and determination of key links in social networks. At the same time, a number of scientific disciplines have come together to develop a theory for the analysis of high-dimensional data, as well as for the analysis of dynamic processes on massive graphs. The new techniques and new mathematics coming out of this line of research are ideally suited to a wide range of applications. Applications and connections to real challenges will be drawn from: data fusion, automated feature extraction, face and shape recognition, spectral and hyperspectral image analysis, relational data mining, link analysis and discovery, graph mining, social and transactional networks, robust network design (making networks hard to break), optimal epidemic intervention (making networks easy to break), and hidden state inference (where are targets based on indirect measurements?). The summer school is intended for graduate students and postdocs, as well as more senior researchers interested in focusing their efforts on these mathematical challenges and crucial applications. The program is organized as follows. Week 1: High-dimensional data, relational data and kernel methods. Week 2: Image analysis and machine learning. Week 3: Streaming data and networks. We anticipate that some participants will be interested in attending the entire program while others will want to stay for only one or two of the week-long sessions. Speakers James Abello (Rutgers University) Uri Alon (Weizmann Institute) Tom Asaki (Los Alamos National Laboratory) Erik Bollt (Clarkson University) Leon Bottou (NEC) Robert Burleson (Lawrence Livermore National Laboratory) Frdric Cao (IRISA) Rick Chartrand (Los Alamos National Laboratory) Ronald Coifman (Yale University) John Conroy (Institute for Defense Analysis) Terence Critchlow (Lawrence Livermore National Laboratory) George Cybenko (Dartmouth University) David Donoho (Stanford University) Tina Eliassi-Rad (Lawrence Livermore National Laboratory) Christos Faloutsos (Carnegie Mellon University) Leslie Greengard (New York University/Courant Institute of Mathematical Sciences) Dennis Healy (DARPA) Martial Hebert (Carnegie Mellon University) David Heckerman (Microsoft Research) Piotr Indyk (Massachusetts Institute of Technology) Peter Jones (Yale University) Michael Jordan (University of California at Berkeley) Ron Kimmel (Technion, Haifa, Israel) Daphne Koller (Stanford University) John Lafferty (Carnegie Mellon University) Yann LeCun (New York University) Gilad Lerman (University of Minnesota) Mehryar Mohri (New York University) Andrew Moore (Carnegie Mellon University) Jean-Michel Morel (Ecole Normale Suprieure, Cachan, France) Robert Nowak (University of Wisconsin) Bruno Olshausen (University of California at Davis) Stanley Osher (IPAM) Carey Priebe (Johns Hopkins University) Prabhakar Raghavan (Verity, Inc. and Stanford University) Ronald Resmini (NGA) Guillermo Sapiro (University of Minnesota) Lawrence Saul (University of Pennsylvania) Edward Scheinerman (Johns Hopkins University) Larry Schultz (Los Alamos National Laboratory) Ingo Steinwart (Los Alamos National Laboratory) William Szewczyk (NCSC) Demetri Terzopoulos (New York University) James Theiler (Los Alamos National Laboratory) Godfried Toussaint (McGill University) Richard Tsai (Princeton University) Kevin Vixie (Los Alamos National Laboratory) Grace Wahba (University of Wisconsin) From tobias at chaos.gwdg.de Tue May 10 10:58:29 2005 From: tobias at chaos.gwdg.de (Tobias Niemann) Date: Tue, 10 May 2005 16:58:29 +0200 Subject: Connectionists: Bernstein Fellow for Computational Neuroscience - Postdoctoral Research Positions Message-ID: <4280CC15.8080601@chaos.gwdg.de> BCCN G?TTINGEN - Bernstein Center for Computational Neuroscience Bernstein Fellow for Computational Neuroscience Applications are invited for up to three Postdoctoral Research Positions in Computational Neuroscience at the recently established Bernstein Center for Computational Neuroscience (BCCN) in G?ttingen, Germany. G?ttingen is a center of neuroscience in Europe hosting numerous internationally recognized neuroscience research institutions, including three Max Planck Institutes, the European Neuroscience Institute, the German Primate Research Center, and G?ttingen University's Centers for Systems Neuroscience (ZNV) and for the Molecular Physiology of the Brain (CMPB). The BCCN integrates theoretical and experimental research groups from these institutions to foster interdisciplinary research in computational neuroscience specifically supporting close collaboration between theorists and experimental researchers. We are looking for strong research personalities, who are experienced in the field of Computational Neuroscience and/or related disciplines such as theoretical physics, mathematics, or computer science and with commitment to a research career in neuroscience. Prior biological or neuroscience training is welcome but not required. The Bernstein Fellow will have the opportunity to collaborate with other members of the BCCN or establish an own research program which complements the activities of the BCCN. Initially the positions are limited to two years and may be extended to up to five years. Applications are welcome from now on until the positions are filled. Please submit your application preferably in one single PDF-document, including cover letter, CV, list of publications, research proposal/interests, names of three possible referees, relevant certificates, and copies of three of your most important publications to: jobs at bccn-goettingen.de (Subject: Bernstein Fellow) For more information please refer to http://www.bccn-goettingen.de While e-mail is preferred, applications may also be submitted in hardcopy to the following address: Prof. Dr. Theo Geisel Subject: Bernstein Fellow Bernstein Center for Computational Neuroscience (BCCN) G?ttingen Max-Planck-Institute for Dynamics and Self-Organization Bunsenstrasse 10 D - 37073 G?ttingen, Germany http://www.bccn-goettingen.de The BCCN is an equal opportunity employer. From B.Kappen at science.ru.nl Thu May 12 11:28:29 2005 From: B.Kappen at science.ru.nl (Bert Kappen) Date: Thu, 12 May 2005 17:28:29 +0200 (CEST) Subject: Connectionists: paper available on efficient stochastic control Message-ID: Dear all, I would like to announce the following paper, that can be downloaded from arxiv.org/physics/0505066 Path integrals and symmetry breaking for optimal control theory H.J. Kappen This paper considers linear-quadratic control of a non-linear dynamical system subject to arbitrary cost. I show that for this class of stochastic control problems the non-linear Hamilton-Jacobi-Bellman equation can be transformed into a linear equation. The transformation is similar to the transformation used to relate the classical Hamilton-Jacobi equation to the Schr\"odinger equation. As a result of the linearity, the usual backward computation can be replaced by a forward diffusion process, that can be computed by stochastic integration or by the evaluation of a path integral. It is shown, how in the deterministic limit the PMP formalism is recovered. The significance of the path integral approach is that it forms the basis for a number of efficient computational methods, such as MC sampling, the Laplace approximation and the variational approximation. We show the effectiveness of the first two methods in number of examples. Examples are given that show the qualitative difference between stochastic and deterministic control and the occurrence of symmetry breaking as a function of the noise. Bert Kappen SNN Radboud University Nijmegen URL: www.snn.kun.nl/~bert The Netherlands tel: +31 24 3614241 fax: +31 24 3541435 B.Kappen at science.ru.nl From niall.griffith at ul.ie Mon May 16 06:56:31 2005 From: niall.griffith at ul.ie (Niall Griffith) Date: Mon, 16 May 2005 11:56:31 +0100 Subject: Connectionists: PhD opportunities in NN and GA modelling of musical instruments and timbre Message-ID: Please Excuse Multiple Postings -------------- Synthesising Consistent Instrument and Voice Sounds using Physically Informed Spectral Models, Neural Networks and Evolutionary Learning. 2 PhD studentships are available to start as soon as possible at the University of Limerick, Ireland for the above project. The studentships cover fees and a monthly stipend (tax-free) of 11,700 Euro for a duration of 3 years. Applicants must be EU nationals, and have some background in either one or all of Evolutionary Computation, Artificial Neural Networks or Music. The project involves three main strands. The strands being 1) DSP & Hidden Markov Models, 2) Evolutionary Learning, and 3) Cognitive and Neural Modelling. The open positions are in areas 2 and 3 above. Applicants are encouraged to forward their CV's and a statement of their research interests and background to either: niall.griffith at ul.ie OR michael.oneill at ul.ie Closing date for applications is 10 June 2005. From F.AlmeidaCosta at sussex.ac.uk Tue May 17 02:15:19 2005 From: F.AlmeidaCosta at sussex.ac.uk (Fernando Almeida e Costa) Date: Tue, 17 May 2005 07:15:19 +0100 Subject: Connectionists: Workshop at Ecal deadline extension Message-ID: ------------------------------------------------------------- THE SUBMISSION DEADLINE FOR THE WORKSHOP *Active Agents and Their Environments as Dynamical Systems* TO BE HELD AT ECAL 2005 HAS BEEN EXTENDED TO: TUESDAY 31ST MAY 2005. ------------------------------------------------------------- ********************************************************************* ...........................Call for papers........................... ......................Workshop @ ECAL 2005....................... .......Active Agents and Their Environments as Dynamical Systems..... .................www.ecal2005.org/workshops.html..................... ............Organized by the activate.d reading group................ ......................University of Sussex........................... ********************************************************************* ECAL2005, in September, will host a workshop on "Active agents and their environments as dynamical systems" organised by the activate.d reading group from the University of Sussex. We are seeking papers within the broad range of the so called dynamical systems approach to life and cognition, from both technical and conceptual/philosophical perspectives. Papers from the workshop will be published in a special issue of the Journal of Adaptive Behavior. You may find detailed information about the workshop in our webpage at www.informatics.sussex.ac.uk/activate.d/workshop at ecal2005 or through the workshop webpage at www.ecal2005.org/workshops.html ******************** PROGRAMME COMMITTEE ******************** Randall Beer, Case Western University. Peter Cariani, Tufts Medical School. Edwin de Jong, Universiteit Utrecht. Ezequiel Di Paolo, University of Sussex. Dario Floreano, Ecole Polytechnique Federale de Lausanne. Inman Harvey, University of Sussex. Phil Husbands, University of Sussex. Takashi Ikegami, University of Tokyo. Scott Kelso, Florida Atlantic University. Luis Mateus Rocha, Indiana University. Tom Ziemke, University of Skovde. ***************** IMPORTANT DATES ***************** EXTENDED submission deadline: 31st of May Review results: 15th of June Corrected papers due: 22nd of June Papers must be emailed in pdf format to one of the organisers (see addresses below) and will be reviewed by at least two independent reviewers, in compliance with the host conference rules. The work to be submitted may include (but is not limited to) topics such as: * Embodied cognition (the exploitation by a cognitive agent, qua cognitive, of all its physical properties). * Evolution of intrinsic and extrinsic morphologies in artificial agents. * Robotics within the framework of the DSaLC (Dynamical Systems approach to Life and Cognition). * Cognition as brain/body/environment interaction. * Online learning as dynamics occurring at different time scales. * Synthesis of dynamical systems models which exhibit adaptive behaviour. * Self-organisation, selection and neutrality in the evolution of dynamical systems. * Agency, homeostasis and autopoiesis. * The present dangers of the (conscious and unconscious) use of GOFAI principles within a DSaLC framework. * Dynamical systems tools for understanding adaptive behaviour. * Behavioural dynamics of interest to cognitive science (e.g. chaotic itinerancy, globally coupled chaotic systems). * Dynamical systems architectures (i.e. neural networks, cellular automata, other models) and their behavioural dynamics. * Models of dynamical systems coupling. Papers should be sent to either one of the workshop organisers: Fernando Almeida e Costa Eduardo Izquierdo-Torres F.AlmeidaCosta at sussex.ac.uk E.J.Izquierdo-Torres at sussex.ac.uk You may find more information about the activate.d reading group at www.informatics.sussex.ac.uk/activate.d From B.Torben-nielsen at CS.unimaas.nl Wed May 18 10:54:41 2005 From: B.Torben-nielsen at CS.unimaas.nl (Torben-nielsen B (CS)) Date: Wed, 18 May 2005 16:54:41 +0200 Subject: Connectionists: Postdoc position available at the Universiteit Maastricht Message-ID: Dear all, At the Insitute for Knowledge and Agent Technology (IKAT), Universiteit Maastricht we have an open postdoc position (f/m, 38 hours a week). Tasks: Learning situated agents to adapt to novel environments by (1) exploiting sensorimotor contingencies, (2) learning techniques for situated adaptive learning, and (3) moving from low-level towards high-level conceptual learning or reasoning. Requirements: IKAT is looking for a bright and enthusiastic Postdoc with interest, skills, and experience in (neural or statistical) learning techniques and various agent architectures. Working experience in the field of robotics is desired. We offer: Temporary appointment for specified period: 48 months. Estimated maximum salary per month ? 3.453,- gross in accordance with scale 10. More information for applicants:Prof.dr. E.O. Postma or Prof.dr. H.J. van den Herik, tel.: 043-3883477, e-mail: postma at cs.unimaas.nl or herik at cs.unimaas.nl Kind regards, Ben Torben-Nielsen From P.Monaghan at psych.york.ac.uk Wed May 18 06:05:35 2005 From: P.Monaghan at psych.york.ac.uk (Padraic Monaghan) Date: Wed, 18 May 2005 11:05:35 +0100 Subject: Connectionists: PhD position in computational modelling of language Message-ID: <428B136F.1030801@psych.york.ac.uk> Marie Curie Early Stage Research Fellow (PhD Position) - Department of Psychology, University of York, UK Applications are invited for a 36-month, fixed-term Early Stage Researcher position to conduct a PhD in the area of computational modelling of language processing with particular emphasis on research into hemispheric specialisation for reading. Dr Padraic Monaghan and Professor Andy Ellis will supervise the post, which is funded by the European Community's Marie Curie scheme as part of the Research Training Network in Language and Brain (http://www.ynic.york.ac.uk/rtn-lab). You will meet the eligibility criteria regarding nationality (according to fellowship rules, applicants must be of non-British nationality and must not have resided in the UK for more than 12 months in the last three years) and will have or be expecting to gain a good first degree in Psychology, Linguistics, Computer Science, or a related discipline. Starting salary minimum 19,460 per annum. This post is available from 1 October 2005. Informal enquiries can be made to Padraic Monaghan (pjm21 at york.ac.uk). The Department of Psychology at the University of York has consistently received the highest possible ratings for its teaching and research, with cutting-edge facilities for experimental, imaging, and computational research. York is also a gorgeous place to live. For details of applying, please go to: http://www.york.ac.uk/univ/mis/cfm/vacancies/vac_detail.cfm?vacno=DR05219 -- Padraic Monaghan Department of Psychology, University of York, York, YO10 5DD, UK direct line: +44 (0)1904 432885; fax: +44 (0)1904 433181 http://www-users.york.ac.uk/~pjm21 From eneher at gwdg.de Thu May 19 03:42:08 2005 From: eneher at gwdg.de (Erwin Neher) Date: Thu, 19 May 2005 09:42:08 +0200 Subject: Connectionists: Job offer Message-ID: Post doctoral position in Goettingen The Department of Membrane Biophysics at the Max Planck Institute for Biophysical Chemistry in cooperation with the Julius Bernstein Center for Computational Neuroscience Goettingen offers a Position (BAT IIa) for a project in Computational Neurobiology The project aims at modeling of various forms of dynamic neuronal networks implementing ?realistic? short-term plasticity. Particularly, the specific properties of short-term facilitation and depression, as observed in the Calyx of Held are to be modeled. The task is to explore, how variations around the experimentally observed dynamics influence network properties, such as the number and classes of attractors, the response to transient stimulation, and various aspects of information processing, rhythm generation, cortical gain control and temporal filtering. In addition, we would like to model how the particular form of short-term depression, which is observed in our experimental system (the Calyx of Held; Forsythe, 1994; Trommersh?user et al., 2003), influences signal processing in the auditory pathway, of which the Calyx of Held is part. The Max Planck Institute for biophysical Chemistry adheres to the principle of equal opportunity employment and strongly encourages applications from qualified women. Preference will be given to disabled applicants with the same qualification and skills. Please address applications to: Prof. Dr. Erwin Neher Membranbiophysik Max-Planck-Institut f?r biophysikalische Chemie Am Fassberg 11 37077 Goettingen email: eneher at gwdg.de http://www.mpibpc.gwdg.de/abteilungen/140/core.html From Manuel.Davy at ec-lille.fr Fri May 20 02:55:05 2005 From: Manuel.Davy at ec-lille.fr (Davy Manuel) Date: Fri, 20 May 2005 08:55:05 +0200 Subject: Connectionists: Post-doc position at CNRS, Lille, France Message-ID: <428D89C9.2020806@ec-lille.fr> Post-Doctoral Position Title: Speech processing using kernel methods Context and Topic Performance of state-of-the-art speech recognition systems has greatly improved over the last years. However, these systems do not fully take advantage of today's computer computation and memory capabilities. Kernel learning methods, such as Support Vector Machines, have recently undegone a huge development, and already give excellent results in fields such as image processing, when compared to other more cassical approaches. The aim of this post-doc is to apply and develop kernel techniques so as to improve the performance of speech recogintion systems. Place: The position is based in the Laboratoire d'Automatique, de G?nie Informatique et Signal (LAGIS) in Lille (North of France). The LAGIS Laboratory is one of the major CNRS laboratories in Signal Processing and Automatic Control in the North of France. The position is also connected to the France Telecom Research Center situated in Lannion (Brittany, France). Duration: The position is for one year, and it may start as soon as possible Scientific supervision: This research work will be supervised by Dr Manuel Davy (CNRS researcher, Lille) (web page) and Dr Lionel Delphin-Poulat (France Telecom Researcher, Lannion) Informations and applications: Additional informations can be obtained from Dr Manuel Davy (Manuel dot davy at ec dash lille dott fr) and from Dr Lionel Delphin-Poulat (lionel ddott delphinpoulat at francetelecom dott com) - change 'dot', 'dash' and 'at' to obvious corresponding symbols. Applications should be emailed to Dr Manuel Davy (including CV and two reference letters) From niebur at jhu.edu Thu May 19 13:35:02 2005 From: niebur at jhu.edu (niebur@jhu.edu) Date: Thu, 19 May 2005 13:35:02 -0400 Subject: Connectionists: Programmer/analyst position in neuroscience lab at Johns Hopkins Message-ID: <200505191735.j4JHZ2f10943@russell.mindbrain> Computer programmer / Analyst in neuroscience research project Primary Duties and responsibilities: Programming in C and C++. Paradox (objectPAL), MatLab, ODBC, AutoCAD, LabWindows CVI. Primary duties are to design and develop a real- time data acquisition system for PC's that can run under Qnx or Windows NT. The programmer should be familiar with real-time NT extensions, Qnx and ideally be familiar with neurophysiological research. The programmer must be able to generate visual displays, control hardware. The programmer is also responsible for system management including evaluating, maintaining software and hardware in the lab. Machines and equipment used: Pentium PC, Digital and analog interface= boards. Minimum requirements: Education: BA/BS - biology/neuroscience or computer science or related field. Special Skills/Knowledge: C language, C++ , Dos/ Windows 95/NT, Matlab. Related work experience: Experience with real time programming desired. Additional information: 1-3 years programming experience desired. Candidates must be highly motivated and be able to work independently. The position is in the Zanvyl Krieger Mind/Brain Institute of Johns Hopkins University in Baltimore, Maryland and provides an opportunity to be an integral part of leading edge neuroscience research. Excellent benefits including tuition remission. Hopkins is an equal opportunity employer. Please contact: Steven Hsiao Krieger Mind/Brain Institute Johns Hopkins University Tel: 410-516-6409 Fax: 410-516-8648 E-mail: Steven.Hsiao at jhu.edu -- Dr. Ernst Niebur Krieger Mind/Brain Institute Assoc. Prof. of Neuroscience Johns Hopkins University niebur at jhu.edu http://cnslab.mb.jhu.edu 3400 N. Charles Street (410)516-8643, -8640 (secr), -8648 (fax), -3357 (lab) Baltimore, MD 21218 From terry at salk.edu Fri May 20 01:28:37 2005 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 19 May 2005 22:28:37 -0700 (PDT) Subject: Connectionists: NEURAL COMPUTATION 17:7 In-Reply-To: <200504281700.j3SH0Y872819@kepler.snl.salk.edu> Message-ID: <200505200528.j4K5SbO59466@kepler.snl.salk.edu> Neural Computation - Contents - Volume 17, Number 7 - July 1, 2005 NOTE Catagorization of Neural Excitability using Threshold Models A. Tonnelier LETTERS Theory of the Snowflake Plot and Its Relations to Higher-Order Analysis Methods Gabriela Czanner, Sonja Grun and Satish Iyengar Asymptotic Theory of Information-Theoretic Experimental Design Liam Paninski Maximum Likelihood Set for Estimating a Probability Mass Function Bruno M. Jedynak and Sanjeev Khudanpur Estimating Entropy Rates with Bayesian Confidence Intervals Matthew B. Kennel, Jonathon Shlens, Henry D. I. Abarbanel, and E. J. Chichilnisky Spike Timing Precision and Neural Error Correction: Local Behavior Michael Stiber A New Approach to Spatial Covariance Modeling of Functional Brain Imaging Data: Ordinal Trend Analysis Christian Habeck, John W. Krakauer, Claude Ghez, Harold A. Sackeim, David Eidelberg, Yaakov Stern, and James R. Moeller Investigating the Fault Tolerance of Neural Networks Elko B. Tchernev, Rory G. Mulvaney and Dhananjay S. Phatak Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review Henrik Jacobsson ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2005 - VOLUME 17 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $143 $90 $96.30 Institution $680 $727.60 $734 $612 $654.84 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From mail at jan-peters.net Sat May 21 15:53:27 2005 From: mail at jan-peters.net (Jan Peters) Date: Sat, 21 May 2005 12:53:27 -0700 Subject: Connectionists: [Call for Participation] Learning for Locomotion Workshop Message-ID: <36c633085cc5a60ca98ee655e7c47289@jan-peters.net> ======================================================= Call for Participation Robotics 2005 - Workshop: Learning for Locomotion Cambridge, MA, USA --- June 11, 2005 ======================================================= Quick Facts Organizers: Jan Peters, Russ Tedrake, Stefan Schaal Conference: Robotics - Science and Systems 2005 Date: June 11, 2005 Room: To be announced Location: MIT, Cambridge, MA, USA Website: http://www-clmc.usc.edu/~jrpeters/workshop.html Alternate Website: http://www.jan-peters.net/Research/LearningForLocomotion Abstract Over the last few decades, there has been an impressive amount of published work on legged locomotion, including bipedal walking, running, hopping, stand-ups, summersaults and much more. However, despite all this progress, legged locomotion research has largely been driven by researchers using human insight and creativity in order to generate locomotion control algorithms. In order to improve the robustness, energy efficiency, and natural appearance of legged locomotion, there may be a significant advantage to using machine learning methods to synthesize new controllers and to avoid tedious parameter tuning. For instance, it could be advantageous to learn dynamics models, kinematic models, impact models, for model-based control techniques. Imitation learning could be employed for the teaching of gaits patterns, and reinforcement learning could help tuning parameters of the control policies in order to improve the performance with respect to given cost functions. In this context, we would like to bring together researchers from both the legged locomotion and machine learning in order to discuss which locomotion problems require learning, and to identify the machine learning methods that can be used to solve them. Goal In order to better understand the application of machine learning techniques to locomotion, our goal is to bring together researchers who represent many different approaches to biped locomotion control with their peers in machine learning for control. We hope to discuss future research directions for principled machine learning approaches to biped locomotion. The workshop will address topics such as: * Which unsolved biped locomotion problems can be solved using learning? * Can walking be broken down into components upon which machine learning methods are applicable? * What models (e.g., forward, inverse, impact) would be desirable for controlling locomotion? * Can machine learning methods help solve the gait generation and foot-placement problems? * Can human learning of locomotion yield insights for both robotics and machine learning? * Which machine learning algorithms are suitable for online implementation on the robot, and which problems can be solved in simulation? * What cost functions should be used to describe "optimal" walking, and what experiments should be done to test our controllers? Furthermore, we intend to kick-off the Legged Robot Control Competition. Program The tentative program and list of speakers can be found at the Workshops Website ( http://www-clmc.usc.edu/~jrpeters/workshop.html ) or the alternative website ( http://www.jan-peters.net/Research/LearningForLocomotion ). Organizers The workshop is organized by Jan Peters, Russ Tedrake and Stefan Schaal, from the Departments of Computer Science and Neuroscience, University of Southern California, Los Angeles, CA, USA and from the Brain and Cognitive Sciences Department at the Massachusetts Institute of Technology, Cambridge, MA, USA. Location and More Information The most up-to-date information about Robotics - Science and Systems 2005 can be found on the Robotics 2005 website ( http://www.robotics-conference.org ). From cmbishop at microsoft.com Wed May 25 09:36:33 2005 From: cmbishop at microsoft.com (Christopher Bishop) Date: Wed, 25 May 2005 14:36:33 +0100 Subject: Connectionists: Postdoctoral Research Fellowship, Darwin College and Microsoft Research, Cambridge U.K. Message-ID: <6C6555DF5D075A4EA6D27706F4EC597502AA324E@EUR-MSG-10.europe.corp.microsoft.com> Postdoctoral Research Fellowship in Adaptive Computing DARWIN COLLEGE CAMBRIDGE Microsoft Research Fellowship The Governing Body of Darwin College Cambridge and Microsoft Research jointly invite applications for a stipendiary Research Fellowship supporting research in the field of adaptive computing (including topics such as pattern recognition, probabilistic inference, machine learning and computer vision). Applicants should hold a PhD or should be expecting to have submitted their thesis prior to commencement of the Fellowship. The Fellowship will be tenable for two years commencing 1 January 2006 or on a date to be agreed. The successful candidate will work at the Microsoft Research Laboratory in Cambridge in the Machine Learning and Perception group. Information about the laboratory and about the group is available from http://research.microsoft.com/cambridge/. Further details about the College are available from the College website http://www.dar.cam.ac.uk. The closing date for applications is 13 June 2005. Eligibility Men and women graduates of any university are eligible to apply, irrespective of age, provided they have a doctorate or an equivalent qualification, or expect to have submitted their thesis before taking up the Fellowship. Duties The successful candidate will engage in research full-time at the Microsoft Research Laboratory in Cambridge. The Fellow will be a member of the Governing Body of Darwin College and will be subject to the Statutes and Ordinances of the College which may be seen on request to the Bursar. The Statutes include the obligation to reside in or near Cambridge for at least two-thirds of each University term, but the Governing Body will normally excuse absences made necessary by the nature of the research undertaken. Stipend and Emoluments The stipend will be dependent upon age and experience. Membership of the Universities' Superannuation Scheme is optional. In addition the Fellow will be able to take seven meals per week at the College table free of charge and additional meals at his or her own expense. Guests may be invited to all meals (within the limits of available accommodation), ten of them free of charge within any quarter of the year. College accommodation will be provided, subject to availability, or an accommodation allowance will be paid in lieu. In addition to a salary the Fellowship provides funding for conference participation. Applications Applications (in Word, PDF or txt format only) should be by emailed to cambpdoc at microsoft.com with the subject line 'Darwin Microsoft Fellowship'. They should arrive by 13 June 2005 and should include (1) a curriculum vitae, (2) an account, in not more than 1000 words, of the proposed research, including a brief statement of the aims and background to it, (3) the names and addresses of three referees (including telephone, fax and email co-ordinates), WHO SHOULD BE ASKED TO EMAIL REFERENCES IMMEDIATELY DIRECT TO THE ABOVE EMAIL ADDRESS, and (4) a list of published or unpublished work that would be available for submission if requested. Short-listed candidates may be asked to make themselves available for interview at Darwin College on a date to be arranged. Election will be made as soon as possible thereafter. Travelling expenses for interviewees will be covered. - The College follows an equal opportunities policy - From frank.ritter at psu.edu Tue May 24 23:48:06 2005 From: frank.ritter at psu.edu (Frank Ritter) Date: Tue, 24 May 2005 23:48:06 -0400 Subject: Connectionists: CogModeling notes: ICCM 2006 / CogSci06 tutorials / ONR Position Message-ID: [please forward this as/if appropriate] This is based on the International Cognitive Modeling Conference mailing list, which I maintain. I've added myself to your list in order to send this to you. I send the messages out by hand using some Emacs functions. The first announcement is the one that is driving this email, the announcement of ICCM 2006. I don't anticipate much more traffic though, until the next ICCM in Trieste in 2006 has its paper call to go out for formally in the autumn. I forward messages about twice a year. cheers, Frank 1. 2006 International Conference on Cognitive Modeling Thursday, 4 April 2006 to 8 April 2006, in Trieste, Italy http://iccm2006.units.it/ 2. Tutorial program at 2005 Cognitive Science Conference, Wed 20 July 2005: ACT-R/Chrest/COGENT/Event-related Brain Potentials/LSA http://homepages.inf.ed.ac.uk/keller/cogsci05/program_tutorials.html (registration also up today!) 3. Cognitive modeling/human factors/HCI position at Office of Naval Research Closing date, 1 June 2005 http://chart.donhr.navy.mil/JobSearch/jobdetail.asp?strView=0&vid=60910 *************************************************** 1. 2006 International Conf. on Cognitive Modeling Thursday, 4 April 2006 to 8 April 2006, in Trieste, Italy http://iccm2006.units.it/ or contact iccm2006 at units.it. This continues the series of ICCM conferences. The last conference was at Pittsburgh. http://simon.lrdc.pitt.edu/~iccm/ This conference will build on that one's success. Paper submissions (6 pages) provisionally due November 20th, 2005. *************************************************** 2. Tutorial Program at Cognitive Science 2005, 20 July 2005 http://homepages.inf.ed.ac.uk/keller/cogsci05/program_tutorials.html Tutorials will present tutorial material, that is, provide results that are established and will do so in an interactive format. They tend to involve an introduction to technical skills or methods. This year the set of tutorials is focused on a range of cognitive architectures for modeling and teaching higher-level cognition, and on a method for gathering data. They will include substantial review of material. The level of presentation assumes that the attendees have at least a first degree in a cognate area. There is a student rate, and such students must bring their ID to show at registration. Attendance at the tutorials does not require conference registration, but tutorial registration does not provide conference entrance. There are five tutorials this year (one with two parts). They are likely to cost about $63 (about 35 pounds or 50 Euros) for each half-day tutorial and 30e ($38) for students. Payment can be made using the registration site on the conference page, or can be paid for on the day (if space is available, which is likely). The program includes handouts, and a tea and a coffee break (including biscuits). There will be a meeting of the tutorial committee and tutors after the tutorials, location to be announced at the tutorials. TOPICS MORNING Peter Lane and Fernand Gobet: CHREST Tutorial: Simulations of Human Learning Richard Cooper: An introduction to the COGENT Cognitive Modelling Environment Matthias Schlesewsky and Ina Bornkessel: Event-Related Brain Potentials in Language (Part 1: Introduction) Afternoon Niels Taatgen and Hedderik van Rijn: ACT-R Tutorial Benoit Lemaire and Guy Denhiere: Latent Semantic Analysis Matthias Schlesewsky and Ina Bornkessel: Event-Related Brain Potentials in Language (Part 2: Advanced Topics) *************************************************** 3. Cognitive modeling/human factors/HCI position at Office of Naval Research http://chart.donhr.navy.mil/JobSearch/jobdetail.asp?strView=0&vid=60910 Contact Susan Chipman (below) for more details. Program Officer, Human Factors (Industrial engineer) The Office of Naval Research is seeking a qualified individual to manage sponsored basic/applied research, and advanced development program and projects in the broad area of human factors engineering. The sponsored efforts are conducted at US universities and industry or Federal Labs. This is a civil service position at the GS-14/15 level ($88k-135k) depending on individual qualifications. The position requires knowledge and experience in the fundamental theories, concepts, and current state-of-the art research and/or technology development in the areas of human systems integration, human factors engineering, and industrial engineering including but not limited to, human decision making, organizational design and architectures, models for human-computer interaction, including computational models of human cognitive processing. For information on qualifications and how to apply, see the job announcements at our web site http://www.onr.navy.mil/hr. Susan writes: The quality of the people who end up in these positions is extremely important to the research community as well as to the Navy. The person in this position will have the opportunity to shape research programs and investments for many years to come. Program officers at ONR have real power of decision in funding. In addition, a less visible aspect of their role is developing ideas, mega-proposals one might say, and obtaining funding for them. Despite the use of the term, "engineer", I am sure that cognitive scientists [and I would suggest, HCI] with many different formal degrees would be able to get this position, as long as they have appropriate expertise. The government never has absolute degree requirements. Application of cognitive modeling to human systems integration is of particular interest. for more information, contact: Susan F. Chipman, Ph.D. ONR Code 342 800 N. Quincy Street Arlington, VA 22217-5660 phone: 703-696-4318 fax: 703-696-1212 *************************************************** -30- (END) From cindy at bu.edu Fri May 27 10:38:20 2005 From: cindy at bu.edu (Cynthia Bradford) Date: Fri, 27 May 2005 10:38:20 -0400 Subject: Connectionists: Neural Networks 18(4) 2005: Special Issue on Emotion and Brain Message-ID: <200505271438.j4REcKVN013923@kenmore.bu.edu> NEURAL NETWORKS 18(4) Contents - Volume 18, Number 4 - 2005 Special Issue on "Emotion and Brain: Understanding Emotions and Modelling their Recognition", J.G. Taylor, K. Scherer, and R. Cowie (editors) ------------------------------------------------------------------ Introduction to the Special Issue J.G. Taylor, K. Scherer, and R. Cowie A systems approach to appraisal mechanisms in emotion David Sander, Didier Grandjean, and Klaus R. Scherer The interaction of attention and emotion John G. Taylor and Nickolaos Fragopanagos Beyond emotion archetypes: Databases for emotion modelling using neural networks Roddy Cowie, Ellen Douglas-Cowie, and Cate Cox Emotion recognition in human-computer interaction N. Fragopanagos and J.G. Taylor Challenges in real-life emotion annotation and machine learning based detection Laurence Devillers, Laurence Vidrascu, and Lori Lamel Emotion recognition through facial expression analysis based on a neurofuzzy network Spiros V. Ioannou, Amaryllis T. Raouzaiou, Vasilis A. Tzouvaras, Theofilos P. Mailis, Kostas C. Karpouzis, and Stefanos D. Kollias ASR for emotional speech: Clarifying the issues and enhancing performance T. Athanaselis, S. Bakamidis, I. Dologlou, R. Cowie, E. Douglas-Cowie, and C. Cox Emotion understanding from the perspective of autonomous robot research Lola Canamero ------------------------------------------------------------------ Electronic access: www.elsevier.com/locate/neunet/. Individuals can look up instructions, aims & scope, see news, tables of contents, etc. Those who are at institutions which subscribe to Neural Networks get access to full article text as part of the institutional subscription. Sample copies can be requested for free and back issues can be ordered through the Elsevier customer support offices: nlinfo-f at elsevier.nl usinfo-f at elsevier.com or info at elsevier.co.jp ------------------------------ INNS/ENNS/JNNS Membership includes a subscription to Neural Networks: The International (INNS), European (ENNS), and Japanese (JNNS) Neural Network Societies are associations of scientists, engineers, students, and others seeking to learn about and advance the understanding of the modeling of behavioral and brain processes, and the application of neural modeling concepts to technological problems. Membership in any of the societies includes a subscription to Neural Networks, the official journal of the societies. Application forms should be sent to all the societies you want to apply to (for example, one as a member with subscription and the other one or two as a member without subscription). The JNNS does not accept credit cards or checks; to apply to the JNNS, send in the application form and wait for instructions about remitting payment. The ENNS accepts bank orders in Swedish Crowns (SEK) or credit cards. The INNS does not invoice for payment. ---------------------------------------------------------------------------- Membership Type INNS ENNS JNNS ---------------------------------------------------------------------------- membership with $80 (regular) SEK 660 Y 13,000 Neural Networks (plus Y 2,000 enrollment fee) $20 (student) SEK 460 Y 11,000 (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- membership without $30 SEK 200 not available Neural Networks to non-student (subscribe through another society) Y 5,000 student (plus Y 2,000 enrollment fee) ---------------------------------------------------------------------------- Name: ______________________________________________________ Title: ______________________________________________________ Address: ______________________________________________________ Phone: ______________________________________________________ Fax: ______________________________________________________ Email: ______________________________________________________ Payment: [ ] Check or money order enclosed, payable to INNS or ENNS OR [ ] Charge my VISA or MasterCard card number _______________________________ expiration date _____________________________ INNS Membership 2810 Crossroads Drive, Suite 3800 Madison WI 53718 USA 608 443 2461, ext. 138 (phone) 608 443 2474 (fax) srees at reesgroupinc.com http://www.inns.org ENNS Membership University of Skovde P.O. Box 408 531 28 Skovde Sweden 46 500 44 83 37 (phone) 46 500 44 83 99 (fax) enns at ida.his.se http://www.his.se/ida/enns JNNS Membership JNNS Secretariat c/o Fuzzy Logic Systems Institute 680-41 Kawazu, Iizuka Fukuoka 820-0067 Japan 81 948 24 2771 (phone) 81 948 24 3002 (fax) jnns at flsi.cird.or.jp http://www.jnns.org/ ---------------------------------------------------------------------------- From masulli at disi.unige.it Fri May 27 06:50:00 2005 From: masulli at disi.unige.it (Francesco Masulli) Date: Fri, 27 May 2005 12:50:00 +0200 Subject: Connectionists: SECOND AND LAST CALL CFP: CIBB 2005 - paper submission deadline 30 May 2005 Message-ID: <200505271250.00963.masulli@disi.unige.it> SECOND AND LAST CALL FOR PAPERS CIBB 2005 Second International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics Crema, ITALY -- September 15-17, 2005 Meeting Website: http://cibb05.disi.unige.it/ CIBB 2005 addresses a cutting edge area of application of Neural Networks, Fuzzy Logic and Evolutionary Computation methods. Technical areas include, but are not limited to: - Data and methods for prognosis - Data and methods for diagnosis - Integration of clinical and genetic data - Proteomics - Pharmacogenetics CIBB 2005 is jointly organized by - BIOPATTERNS, European Network of Excellence on Computational Intelligence for Biopattern analysis in Support of eHealthcare - INNS, International Neural Network Society - SIREN, Italian Neural Networks Society CIBB 2005 will took place at Dipartimento di Tecnologie dell'Informazione Universita' degli Studi di Milano via Bramante 65, I-26013 Crema, ITALY in connection with WILF 2005 - Sixth International Workshop on Fuzzy Logic and Applications (http://dsa.uniparthenope.it/wilf2005/) All accepted papers submitted by registered participants to WILF 2005 will be included in the proceedings book of WILF 2005, that will be published by an international Publisher. Important Dates Submission deadline: 30 May 2005 Notification of acceptance: 30 June 2005 Camera ready papers due: 15 July 2005 Meeting: 15-17 September 2005 Submission of papers: Papers must not be longer than 6 pages, including a cover sheet stating: (1) Paper title; (2) Keywords; (3) Authors names and affiliations; (4) Corresponding author's name and contact details, including telephone/fax numbers and e-mail address. For electronic submission refer to the CIBB 2005 web site http://cibb05.disi.unige.it/. Chairs Francesco Masulli University of Pisa (Italy) Antonina Starita University of Pisa (Italy) Roberto Tagliaferri University of Salerno (Italy) International Program Committee Giovanni Cuda, University of Catanzaro, Italy Alexandru Floares, Oncological Institute Cluj-Napoca, Romania Jon Garibaldi, University of Nottingham, UK Nik Kasabov, Auckland University of Technology, NZ Natalio Krasnogor, University of Nottingham, UK Evangelia Micheli-Tzanakou, Rutgers University, NJ - USA Sushmita Mitra, Indian Statistical Institute Kolkata, India Alberto Paccanaro,Yale University, CT, USA David Alejandro Pelta, University of Granada, Spain Udo Seiffert, Leibniz Institute, Gatersleben, Germany L?onard Studer, ABMI SA, Dorigny Lausanne, Switzerland Anna Tramontano, University of Rome "La Sapienza", Italy - From stefan.wermter at sunderland.ac.uk Wed May 25 12:30:02 2005 From: stefan.wermter at sunderland.ac.uk (Stefan Wermter) Date: Wed, 25 May 2005 17:30:02 +0100 Subject: Connectionists: Stipend funding available for MSc Intelligent Systems Message-ID: <4294A80A.3010708@sunderland.ac.uk> Stipends available for MSc Intelligent Systems ----------------------------------------------- We are pleased to announce that for eligible EU students we have obtained funding to offer a bursary for our MSc Intelligent Systems in October 2005 of about 8.000 EURO (about 5500 pounds) as fee waiver and stipend. ***Please forward to students who may be interested.*** The School of Computing and Technology, University of Sunderland is delighted to announce the launch of its MSc Intelligent Systems programme for October 2005. Building on the School's leading edge research in intelligent systems this masters programme will be funded via the ESF scheme (see below). Intelligent Systems is an exciting field of study for science and industry since the currently existing computing systems have often not yet reached the various aspects of human performance. "Intelligent Systems" is a term to describe software systems and methods, which simulate aspects of intelligent behaviour. The intention is to learn from nature and human performance in order to build more powerful computing systems. The aim is to learn from cognitive science, neuroscience, biology, engineering, and linguistics for building more powerful computational system architectures. In this programme a wide variety of novel and exciting techniques will be taught including neural networks, intelligent robotics, machine learning, natural language processing, vision, evolutionary genetic computing, data mining, fuzzy methods, and hybrid intelligent architectures. Funding of about 5500 pounds (about 8.000 Euro) for eligible EU students ------------------------------ The Bursary Scheme applies to this Masters programme commencing October 2005 and we have obtained funding through the European Social Fund (ESF). ESF support enables the University to waive the normal tuition fee and provide a bursary of 50 per week for 45 weeks for eligible EU students, together up to about 5500 pounds or about 8000 Euro. For further information in the first instance please see: http://www.his.sunderland.ac.uk/Teaching_frame.html http://osiris.sund.ac.uk/webedit/allweb/courses/progmode.php?prog=G550A&mode=FT&mode2=&dmode=C http://www.his.sunderland.ac.uk/teaching/sund_is_app.pdf For information on applications and start dates contact: gillian.potts at sunderland.ac.uk Tel: 0191 515 2758 For academic information about the programme contact: alfredo.moscardini at sunderland.ac.uk Please forward to interested students. Stefan *************************************** Stefan Wermter Professor for Intelligent Systems Centre for Hybrid Intelligent Systems School of Computing and Technology University of Sunderland St Peters Way Sunderland SR6 0DD United Kingdom phone: +44 191 515 3279 fax: +44 191 515 3553 email: stefan.wermter at sunderland.ac.uk http://www.his.sunderland.ac.uk/~cs0stw/ http://www.his.sunderland.ac.uk/ **************************************** From b.graham at cs.stir.ac.uk Mon May 30 10:14:48 2005 From: b.graham at cs.stir.ac.uk (Bruce Philip Graham) Date: Mon, 30 May 2005 15:14:48 +0100 (BST) Subject: Connectionists: FINAL CALL: Neuroinformatics Simulation Tools Summer School In-Reply-To: <4336.139.153.254.219.1115141677.squirrel@www.cs.stir.ac.uk> References: <4336.139.153.254.219.1115141677.squirrel@www.cs.stir.ac.uk> Message-ID: <1181.213.78.103.162.1117462488.squirrel@www.cs.stir.ac.uk> Dear all, Please note that the application deadline for our summer school is only ONE WEEK away (6th June)! > 2005 EDINBURGH SUMMER SCHOOL IN NEUROINFORMATICS > > SIMULATION TOOLS > > Institute for Adaptive and Neural Computation > University of Edinburgh. > > August 22-26, 2005 > * Application deadline: 6th June 2005 * > > This summer school in Neuroinformatics Simulation Tools is a > five day intensive course which will provide a practical > introduction > to using neuroscience simulation tools including NEURON and Catacomb > for computational modelling of neural systems. > > The course will be held in the Institute for Adaptive and Neural > Computation in the centre of Edinburgh and will include talks from > invited speakers as well as practical hands-on experience using the > latest simulation tools. > > The course is aimed at PhD students, postdocs and faculty in > neuroscience and related disciplines wishing to learn how to apply > computational modelling techniques to their research problems. > > Bursaries are available for PhD students to cover accommodation > costs. > > For more details, and an online application form visit:- > http://www.anc.ed.ac.uk/school > > -- Dr Bruce Graham, Lecturer (b.graham at cs.stir.ac.uk) Dept. of Computing Science and Mathematics, University of Stirling, Stirling FK9 4LA phone: +44 1786 467 432 fax: +44 1786 464 551 -- The University of Stirling is a university established in Scotland by charter at Stirling, FK9 4LA. Privileged/Confidential Information may be contained in this message. If you are not the addressee indicated in this message (or responsible for delivery of the message to such person), you may not disclose, copy or deliver this message to anyone and any action taken or omitted to be taken in reliance on it, is prohibited and may be unlawful. In such case, you should destroy this message and kindly notify the sender by reply email. Please advise immediately if you or your employer do not consent to Internet email for messages of this kind. From zoubin at gatsby.ucl.ac.uk Sun May 29 22:34:50 2005 From: zoubin at gatsby.ucl.ac.uk (Zoubin Ghahramani) Date: Mon, 30 May 2005 03:34:50 +0100 Subject: Connectionists: AISTATS 2005 full proceedings available online Message-ID: <17050.31690.795936.893269@pitts.gatsby.ucl.ac.uk> The full proceedings of the 2005 AI and Statistics Workshop are now available online, both as individual papers and as a single pdf file. Please see: http://www.gatsby.ucl.ac.uk/aistats/proceedings.htm A bibtex file of all papers in the proceedings is also available at this site. Sincerely, Zoubin Ghahramani and Robert Cowell co-chairs