From terry at salk.edu Sat Feb 1 18:50:20 2003 From: terry at salk.edu (Terry Sejnowski) Date: Sat, 1 Feb 2003 15:50:20 -0800 (PST) Subject: Telluride Workshop deadline Message-ID: <200302012350.h11NoK596876@purkinje.salk.edu> ------------------------------------------------------------------------ NEUROMORPHIC ENGINEERING WORKSHOP Sunday, JUNE 29 - Saturday, JULY 19, 2003 TELLURIDE, COLORADO http://www.ini.unizh.ch/telluride/ ------------------------------------------------------------------------ Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Timmer HORIUCHI (Johns Hopkins University) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Christof KOCH (California Institute of Technology) Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) ------------------------------------------------------------------------ We invite applications for the annual three week "Telluride Workshop and Summer School on Neuromorphic Engineering" that will be held in Telluride, Colorado from Sunday, June 29 to Saturday, July 19, 2003. The application deadline is FRIDAY, MARCH 14, and application instructions are described at the bottom of this document. Like each of these workshops that have taken place since 1994, the 2002 Workshop and Summer School on Neuromorphic Engineering, sponsored by the National Science Foundation, the Whitaker Foundation, the Office of Naval Research, the Defence Advanced Research Projects Agency, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology, was an exciting event and a great success. We strongly encourage interested parties to browse through the previous workshop web pages located at: http://www.ini.unizh.ch/telluride For a discussion of the underlying science and technology and a report on the 2001 workshop, see the September 20, 2001 issue of "The Economist": http://www.economist.com/science/tq/displayStory.cfm?Story_ID=779503 GOALS: Carver Mead introduced the term "Neuromorphic Engineering" for a new field based on the design and fabrication of artificial neural systems, such as vision systems, head-eye systems, and roving robots, whose architecture and design principles are based on those of biological nervous systems. The goal of this workshop is to bring together young investigators and more established researchers from academia with their counterparts in industry and national laboratories, working on both neurobiological as well as engineering aspects of sensory systems and sensory-motor integration. The focus of the workshop will be on active participation, with demonstration systems and hands on experience for all participants. Neuromorphic engineering has a wide range of applications from nonlinear adaptive control of complex systems to the design of smart sensors, vision, speech understanding and robotics. Many of the fundamental principles in this field, such as the use of learning methods and the design of parallel hardware (with an emphasis on analog and asynchronous digital VLSI), are inspired by biological systems. However, existing applications are modest and the challenge of scaling up from small artificial neural networks and designing completely autonomous systems at the levels achieved by biological systems lies ahead. The assumption underlying this three week workshop is that the next generation of neuromorphic systems would benefit from closer attention to the principles found through experimental and theoretical studies of real biological nervous systems as whole systems. FORMAT: The three week summer school will include background lectures on systems neuroscience (in particular learning, oculo-motor and other motor systems and attention), practical tutorials on analog VLSI design, small mobile robots (Koalas, Kheperas, LEGO robots, and biobugs), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, the majority of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control * central pattern generator * robotics * swarm robotics * multichip communication * analog VLSI * learning The active perception project group will emphasize vision and human sensory-motor coordination. Issues to be covered will include spatial localization and constancy, attention, motor planning, eye movements, and the use of visual motion information for motor control. The central pattern generator group will focus on small walking and undulating robots. It will look at characteristics and sources of parts for building robots, play with working examples of legged and segmented robots, and discuss CPG's and theories of nonlinear oscillators for locomotion. It will also explore the use of simple analog VLSI sensors for autonomous robots. The robotics group will use rovers and working digital vision boards as well as other possible sensors to investigate issues of sensorimotor integration, navigation and learning. The audition group aims to develop biologically plausible algorithms and aVLSI implementations of specific auditory tasks such as source localization and tracking, and sound pattern recognition. Projects will be integrated with visual and motor tasks in the context of a robot platform. The multichip communication project group will use existing interchip communication interfaces to program small networks of artificial neurons to exhibit particular behaviors such as amplification, oscillation, and associative memory. Issues in multichip communication will be discussed. This year we will also have *200* biobugs, kindly donated by the WowWee Toys division of Hasbro in Hong Kong. B.I.O.-Bugs, short for Bio-mechanical Integrated Organisms, are autonomous creatures, each measuring about one foot and weighing about one pound (www.wowwee.com/biobugs/biointerface.html). This will permit us to carry out experiments in collective/swarm robotics. LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350 miles). Great Lakes Aviation and America West Express airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do NOT rent a car. Bring hiking boots, warm clothes, rain gear and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around mid April 2003. Participants are expected to pay a $275.00 workshop fee at that time in order to reserve a place in the workshop. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. Travel reimbursement of up to $500 for US domestic travel and up to $800 for overseas travel will be possible if financial help is needed (Please specify on the application). HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e., postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage qualified women and minority candidates to apply. Application should include: * First name, Last name, Affiliation, valid e-mail address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Description of demonstrations that could be brought to the workshop. * Two letters of recommendation Complete applications should be sent to: Terrence Sejnowski The Salk Institute 10010 North Torrey Pines Road San Diego, CA 92037 e-mail: telluride at salk.edu FAX: (858) 587 0417 APPLICATION DEADLINE: MARCH 14, 2003 From terry at salk.edu Mon Feb 3 13:44:39 2003 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 3 Feb 2003 10:44:39 -0800 (PST) Subject: NEURAL COMPUTATION 15:3 In-Reply-To: <200301152207.h0FM7QD79176@purkinje.salk.edu> Message-ID: <200302031844.h13IidS98237@purkinje.salk.edu> Neural Computation - Contents - Volume 15, Number 3 - March 1, 2003 ARTICLE Synchronization in Networks of Excitatory and Inhibitory Neurons with Sparse, Random Connectivity Christoph Borgers and Nancy Kopell NOTES The Effects of Input Rate and Synchrony on a Coincidence Detector: Analytical Solution Shawn Mikula and Ernst Niebur A Theoretical Model of Axon Guidance By the Robo Code Geoffrey Goodhill LETTERS Spike-Driven Synaptic Dynamics Generating Working Memory States Daniel J. Amit and Gianluigi Mongillo A Stochastic Method to Predict the Consequence of Arbitrary Forms of Spike-Timing-Dependent Plasticity Hideyuki Cateau and Tomoki Fukai Permitted and Forbidden Sets in Symmetric Threshold-Linear Networks Richard H.R. Hahnloser, H. Sebastian Seung and Jean-Jacques Slotine Multistability Analysis for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions Zhang Yi, K. K. Tan and T. H. Lee Simple-Cell-Like Receptive Fields Maximize Temporal Coherence in Natural Video Jarmo Hurri and Aapo Hyvarinen Continuous-Time Symmetric Hopfield Nets Are Computationally Universal Jiri Sima and Pekka Orponen ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2003 - VOLUME 15 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $95 $101.65 $143 Institution $590 $631.30 $638 * 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 dayan at gatsby.ucl.ac.uk Mon Feb 3 11:46:21 2003 From: dayan at gatsby.ucl.ac.uk (Peter Dayan) Date: Mon, 3 Feb 2003 16:46:21 +0000 Subject: Faculty position: Gatsby Computational Neuroscience Unit Message-ID: <20030203164620.A18789@miller.gatsby.ucl.ac.uk> The Gatsby Computational Neuroscience Unit is looking to recruit a lecturer (roughly equivalent to an assistant professor). We seek someone with interests from across the range of theoretical neuroscience and machine learning that would complement and bolster our existing strengths in neural representation, neural computation, and foundational and applied aspects of learning and Bayesian statistics. There is also the opportunity to run a human psychophysics lab in the service of testing theories. Remuneration will be at a level appropriate to the international standing of the successful candidate. The Gatsby Unit was set up at University College London as a research institute devoted to computational neuroscience and machine learning. We have core funding for four faculty, five postdocs and around ten PhD students. We have no undergraduate programme, so only graduate-level teaching is required. We are located in Queen Square, London, in close proximity to the Institutes of Neurology and Cognitive Neuroscience and the Functional Imaging Lab, and also have close ties with the Departments of Anatomy, Computer Science, Psychology, Physiology and Statistics at UCL and with groups in Physics and Experimental Psychology at Cambridge and beyond. Applications, including a CV, a statement of research interests and accomplishments and full contact details for three referees should be sent by 14th March 2003 by email to Alexandra Boss at alexandra at gatsby.ucl.ac.uk, or by mail to her at Gatsby Computational Neuroscience Unit, UCL, Alexandra House, 17 Queen Square, London WC1N 3AR, UK. For further information, please see www.gatsby.ucl.ac.uk or contact Peter Dayan at dayan at gatsby.ucl.ac.uk From robbie at bcs.rochester.edu Tue Feb 4 10:51:23 2003 From: robbie at bcs.rochester.edu (Robert Jacobs) Date: Tue, 04 Feb 2003 10:51:23 -0500 Subject: 5 postdoc positions available Message-ID: <5.1.1.6.0.20030204104911.02e45d30@bcs.rochester.edu> A non-text attachment was scrubbed... Name: not available Type: multipart/alternative Size: 2765 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/00000000/d8710521/attachment.bin From canete at ctima.uma.es Tue Feb 4 06:40:39 2003 From: canete at ctima.uma.es (=?iso-8859-1?Q?Javier_Fern=E1ndez_de_Ca=F1ete?=) Date: Tue, 4 Feb 2003 12:40:39 +0100 Subject: EANN'2003. Second CALL FOR PAPERS. Message-ID: <002101c2cc42$468dc840$836dd696@isa.uma.es> Dear colleague: This is a "one month submission reminder" to all interested individuals that the deadline for submitting extended abstracts to the conference on Engineering Applications on Neural Networks 2003 (EANN'03) is February 28, 2003. This conference will be held at the beautiful "Melia Torremolinos Hotel" at Torremolinos, Costa del Sol, SPAIN, from 8 to 10 September 2003. All information regarding this conference can be found on our website at http://www.isa.uma.es/eann03 Please refer to this website for formatting and submission requirements. If you have any questions about the conference, please feel free to contact me at eann03 at ctima.uma.es Hoping to seeing you at EANN'03 With regards Javier Fernandez de Canete Prof. Javier Fernandez de Canete, Ph. D. EANN2003 Conference Secretariat E.T.S.I. Informatica Universidad de Malaga Campus de Teatinos s/n 29071 Malaga SPAIN Phone: +34-95-2132887 Fax: +34-95-2133361 e_mail: canete at ctima.uma.es From bogus@does.not.exist.com Wed Feb 5 07:34:35 2003 From: bogus@does.not.exist.com () Date: Wed, 5 Feb 2003 12:34:35 -0000 Subject: Professorship in Neuromorphic Computing Systems Message-ID: <736F0925D69F9941B3BA8AEED0F5E75C5F406B@02-CSEXCH.uopnet.plymouth.ac.uk> Please post and circulate (apologies for cross listings) Professorship in Neuromorphic Computing Systems University of Plymouth, UK The University of Plymouth is currently seeking to make new Professorial appointments in the Computing discipline within the Faculty of Technology. Outstanding candidates are sought in a number of specialist areas, and candidates whose specialist expertise is in neuromorphic computing systems, in particular in vision, audition or sensory-motor systems, are hereby invited to apply. Such candidates will be encouraged to work closely with other research groups in the Faculty, including the newly established Centre for Theoretical and Computational Neuroscience (see below for further details of this research Centre). Appointees will also be expected to contribute to the development of undergraduate and postgraduate programmes in computing within the Faculty of Technology, and to provide research leadership in their area. Candidates must have a substantial record of successful research and teaching experience, a strong publication record, and evidence of success in the acquisition of research grants. The University has also reserved certain specific Lectureships which will be associated with these positions and used to support research growth in the appointees' specialist areas. Potential applicants should initially contact, by email, Professor Mike Denham (mdenham at plymouth.ac.uk) in order to discuss their application. In this respect, it would be helpful if a brief curriculum vitae and an indication of research interests could be included with the initial email. Centre for Theoretical and Computational Neuroscience, University of Plymouth, UK This newly-established Centre specialises in the application of rigorous, quantitative approaches, including mathematical and computational modelling and psychophysics, to understanding information coding, processing, storage and transmission in the brain and its manifestation in perception and action. Areas of study include: visual and auditory perception and psychophysics; sensory-motor control, in particular oculomotor control; and mathematical and computational modelling of the cortical neural circuitry underlying perception, attention, learning and memory, and motor control. Academic staff in the Centre are: Prof Jochen Braun (vision); Dr Susan Denham (audition); Prof Chris Harris (sensory-motor control); Prof Roman Borisyuk (mathematical and computational modelling); Prof Mike Denham (mathematical and computational modelling). The Centre has a number of externally-funded research programmes and strong international links, including with the Institute of Neuroinformatics at ETH, Zurich, and the Koch laboratory at Caltech. It has a strong interest and is currently active in collaborating with researchers in the neuromorphic systems area, in particular in the implementation of the computational principles and models of neural processing it is investigating within artificial systems, in particular in vision, audition and sensory-motor systems. From mvanross at inf.ed.ac.uk Thu Feb 6 06:26:47 2003 From: mvanross at inf.ed.ac.uk (Mark van Rossum) Date: Thu, 6 Feb 2003 11:26:47 +0000 (GMT) Subject: PhD Studentships Neuroinformatics in Edinburgh UK Message-ID: 4 YEAR DOCTORAL TRAINING (PhD) IN NEUROINFORMATICS. UNIVERSITY OF EDINBURGH We invite applications for the PhD program in the newly established Edinburgh Doctoral Training Centre in Neuroinformatics. The programme is made up of 3 themes: 1) Computational and Cognitive Neurocience - analytical and computational modelling of the nervous system, visual processing, sensory coding. 2) Neuromorphic Engineering and Neural Computation - Artificial sensor perception and analysis, neuromorphic modelling, spiking computation and mixed-mode VLSI, evolutionary optimisation of physical systems, neurally inspired algorithms, neurorobotics. 3) Simulation, Analysis, Visualisation and Data Handling - software systems and computational techniques for neuroscience and neural engineering. The 4 year programme in Neuroinformatics consists of an introductory year of training in neuroscience, informatics techniques and smaller lab-based research projects, followed by 3 years of Ph.D. research study related to one of the above subjects. The programme has a strong interdiscplinary character and is ideal for students who want to apply their skills to neuroinformatics problems. Students with a strong background in computer science, electronics, mathematics, physics or engineering are particularly welcome to apply, but motivated students with other backgrounds will be considered as well. We will be accepting an average of 10 students a year. Students will be based initially in the Institute for Adaptive and Neural Computation in the School of Informatics, the UK's largest and highest-quality academic computer-science group. Edinburgh has a strong research community in all of the areas listed above and leads the UK in integrating these into a coherent programme in Neuroinformatics. Edinburgh has in the past been voted as 'best place to live in Britain', and has many exciting cultural and student activities. The stipend is set in the region of 10,000 pounds (15,000 Euros) in the first year and 13,000 pounds (20,000 Euros/Dollars) per annum in years 2-4. Full fees are paid. The studentships are available to UK students. Funding for EU students is currently unclear. Applicants who are not citizens or longstanding residents of EU countries will need to find their own funding. For full application details, and further information of areas of study at the Centre, consult the website: http://www.anc.ed.ac.uk/neuroinformatics or send email to neuroinformatics-phd at anc.ed.ac.uk Applications received by February 28th will receive priority treatment. Mark van Rossum ==== mvanross at inf.ed.ac.uk ===== http://homepages.inf.ed.ac.uk/mvanross From memory at cogs.nbu.bg Thu Feb 6 09:28:49 2003 From: memory at cogs.nbu.bg (CogSci Summer School) Date: Thu, 6 Feb 2003 16:28:49 +0200 Subject: Deadline approaching Message-ID: Advanced Interdisciplinary Workshop on Constructive Memory: Data and Models Sofia, New Bulgarian University, July 12-14, 2003 The aim of the workshop will be to challenge our current understanding of human memory by integrating data with theoretical and computational models and by bringing researchers from a variety of domains together. The workshop topics will include: * False Memory and Memory Illusions * Interaction between memory and reasoning, between memory and imagination * Autobiographical memory * Spatial Memory * Memory for Actions and Events * Memory for Faces and Objects * WM and constructive processes * Context-Sensitivity of Human Memory * Collective memory The workshop is deliberately interdisciplinary and will cover a variety of methods: * lab experiments * field studies * computer simulations * mathematical models * brain imaging * brain lesions The workshop program will consist of invited key speaker talks which will be challenged by discussants, short talks by regular participants, and numerous discussions and working groups. In parallel to the workshop an International Summer School in Cognitive Science will take place. Key talks * Jay McClelland (Carnegie Mellon University, USA) Emergence of Theory-like Knowledge from Experience: A Parallel-Distributed Processing Account * Elizabeth Loftus (University of Washington, USA) - False Memories and Other Mind Changes * Alan Baddeley (University of Bristol, UK) - Constructive Processes in Working Memory * Daniel Schacter (Harvard University, USA) - The Seven Sins of Memory: A Cognitive Neuroscience Perspective * Morris Moscovitch (University of Toronto, Canada) Remote Memory, Consolidation and Hippocampal-Neocortical Interaction: Evidence from the Laboratory and Clinic. * Robert Bjork and Elizabeth Bjork (University of California, Los Angeles, USA) - The Role of Retrieval-Induced Forgetting in the Construction and Distortion of Memories * Michael Anderson (University of Oregon, USA) - Inhibitory Processes and the Regulation of Awareness * Martin Conway (University of Durham, UK) & Amanda Barnier (University of New South Wales, Australia) - On the Accessibility of Autobiographical Memories: Shaping the Self * Johannes Engelkamp (Saarland University, Germany) - What is Special about Memory for Actions? * William Hirst (New School for Social Research, NY, USA) The Construction of a Collective Memory * Jeroen Raaijmakers (University of Amsterdam, The Netherlands) - Towards a General Theory of Human Memory * Boicho Kokinov (New Bulgarian University) - The AMBR Model of Episodic Memory Construction and Distortion: Interaction between Memory and Reasoning Call for Papers Potential participants are invited to submit papers in electronic form (MS Word or PDF format) for presentation during the workshop. The papers should be not longer than 10 single spaced pages, including tables, figures, references, and appendices and use Times New Roman Font size 10. The papers may address any of the topics described above. Interdisciplinary work is especially welcome. Priority will be given to papers that open up new issues, challenge the current understanding of human memory, present new models or data. Papers should be sent by April 1st 2003 to the following address: memory at cogs.nbu.bg Program Committee Michael Anderson (University of Oregon, USA) Alan Baddeley (University of Bristol, UK) Robert Bjork (University of California, Los Angeles, USA) Martin Conway (University of Durham, UK) Johannes Engelkamp (Saarland University, Germany) William Hirst (New School for Social Research, NY, USA) - Co-Chair Boicho Kokinov (New Bulgarian University) - Co-Chair Elizabeth Loftus (University of Washington, USA) Jay McClelland (Carnegie Mellon University, USA) Morris Moscovitch (University of Toronto, Canada) Jeroen Raaijmakers (University of Amsterdam, The Netherlands) Daniel Schacter (Harvard University, USA) For more information look at: http://www.nbu.bg/cogs/events/workshop.html Central and East European Center for Cognitive Science New Bulgarian University 21 Montevideo Str. Sofia 1618 phone: 955-75-18 e-mail: school at cogs.nbu.bg memory at cogs.nbu.bg Radostina Belcheva Administrative manager Central and East European Center for Cognitive Science Svetlana Petkova Administrative manager Central and East European Center for Cognitive Science From mm at cse.ogi.edu Thu Feb 6 14:43:48 2003 From: mm at cse.ogi.edu (Melanie Mitchell) Date: Thu, 6 Feb 2003 11:43:48 -0800 Subject: Faculty Positions at OGI School of Science and Engineering Message-ID: <15938.47860.698159.509423@sangre.cse.ogi.edu> I wanted to bring to your attention the following advertisement for faculty recruitment at OGI. Adaptive systems and machine learning is one of our specific target areas for hiring. OGI is putting significant resources into building a strong and diverse Laboratory for Adaptive Systems, and we expect to hire between two and four people in this area within the next five years. Our recent merger with the Oregon Health & Science University has opened up great opportunities for collaboration with researchers in biological and medical sciences, and our close proximity to the OHSU Neurological Sciences Institute has already resulted in collaborations between our respective faculties in the fields of neural modeling and neural computation. OGI's current adaptive systems faculty includes: Dan Hammerstrom: Biologically inspired computation, VLSI chip design, neural networks Marwan Jabri: Intelligent signal processing, biologically inspired control for robotics Todd Leen: Machine learning, local and mixture models, neurophysiological modeling Melanie Mitchell: Evolutionary computation, cognitive science, complex systems John Moody: Reinforcement learning, neural networks, time series analysis, data mining, computational finance Misha Pavel: Cognitive science, biologically inspired computation, biomedical engineering Xubo Song: Image processing, statistical pattern recognition Eric Wan: Neural networks, adaptive signal processing and control We are looking for outstanding individuals in any area of machine learning or adaptive systems to join our faculty. Please pass this on to anyone you think might be interested. --------------------------------------------------------------------------- Faculty Positions at the OGI School of Science and Engineering The Department of Computer Science and Engineering invites applications for faculty positions at all ranks. The current strengths of our department include graphics and visualization, adaptive systems and machine learning, databases and data mining, networking, programming languages, software systems, human-computer interaction, spoken language systems, software engineering, control, computer architecture, image processing, and applied formal methods and verification of both hardware and software. In addition to these areas, our target areas for hiring include bioinformatics and computational biology, security, mobile and embedded systems, real-time and reactive systems, high-performance computing, vision, robotics, and sensor fusion. While these are particular areas of interest, we will consider outstanding candidates in any area of computer science and engineering. Building on a shared commitment to excellence in graduate education and research, Oregon Graduate Institute of Science and Technology (OGI) merged with Oregon Health Sciences University (OHSU) on July 1, 2001. OGI now is the OGI School of Science and Engineering in the re-named Oregon Health & Science University (OHSU). The merger is enabling the CSE department to expand in core disciplines and establish strong interdisciplinary collaborations among researchers in information technology, health care, biomedical engineering, and environmental and biological sciences. Significant collaborations between OGI and OHSU have existed for 30 years. The typical teaching load in CSE is 2 graduate-level classes per year. Faculty receive contracts of 2-5 years duration, renewable annually with satisfactory academic performance. NSF, NIH and other federal research sponsors recognize OGI faculty appointments as being equivalent to tenured positions. OGI is located 12 miles west of Portland, Oregon, in the heart of the Silicon Forest. Portland's thriving high-tech community, extensive cultural amenities and spectacular natural surroundings combine to make the quality of life here extraordinary. To learn more about the department, OGI, OHSU and Portland, please visit www.cse.ogi.edu. To apply, send a brief description of your research interests, the names of at least three references, and a curriculum vitae with a list of publications to: Chair, Recruiting Committee Department of Computer Science and Engineering OGI School of Science and Engineering at OHSU 20000 NW Walker Road Beaverton, Oregon 97006 The email address for inquiries is: csedept at cse.ogi.edu. OGI/OHSU is an Equal Opportunity/Affirmative Action employer. We particularly welcome applications from women, minorities, and individuals with disabilities. From erik at bbf.uia.ac.be Tue Feb 4 12:40:15 2003 From: erik at bbf.uia.ac.be (Erik De Schutter) Date: Tue, 4 Feb 2003 18:40:15 +0100 Subject: CNS*03: FINAL CALL FOR PAPERS (changed deadline) Message-ID: FINAL CALL FOR PAPERS: SUBMISSION DEADLINE: February 23, 2003 midnight DEADLINE HAS BEEN EXTENDED BY ONE WEEK: We can now announce substantial travel grants for students traveling to the meeting plus reduced registration fees compared to last year. More info when the registration openslater this year. Twelfth Annual Computational Neuroscience Meeting CNS*2003 July 5 - July 9, 2003 Alicante, Spain http://www.neuroinf.org/CNS.shtml Info at cp at bbf.uia.ac.be CNS*2003 will be held in Alicante from Saturday, July 5, 2003 to Wednesday, July 9. The main meeting will be July 5 - 7 at the Hotel Meli=E1 (poster sessions) and at the CAM Cultural Center (oral presentations). The main meeting consists of 6 oral sessions (one each morning and afternoon) and 3 early evening poster sessions. Workshops will be held at the University Miguel Hern=E1ndez (Medical School Campus) July 8 - 9. New is that some workshops will be mini-symposia or tutorials, a list of currently planned workshops can be found at the website. The conference dinner will take place in the Santa B=E1rbara castle overlooking the city and the sea on Sunday, July 6. For tourist information see http://www.alicanteturismo.com, more specific practical information will be made available through the conference website. Papers can include experimental, model-based, as well as more abstract theoretical approaches to understanding neurobiological computation. We especially encourage papers that mix experimental and theoretical studies. We also accept papers that describe new technical approaches to theoretical and experimental issues in computational neuroscience or relevant software packages. The paper submission procedure is again completely electronic this year. There will not be any meeting announcement through surface mail, instead you find the meeting poster attached. PAPER SUBMISSION Papers for the meeting can be submitted ONLY through the web site at http://www.neuroinf.org/CNS.shtml Papers can be submitted either as a 1000 word summary or as a full paper (max 6 typeset pages). Full papers stand a better chance of being accepted for oral presentation. You will need to submit the paper in pdf format (if necessary Elsevier can help in converting your paper to pdf) and the 100 word abstract as text. You will also need to select two categories which describe your paper and which will guide the selection of reviewers. In addition we encourage you to also submit your paper to the Elsevier preprint server (http://www.computersciencepreprints.com). All submissions will be acknowledged by email. THE REVIEW PROCESS All submitted papers will be first reviewed by the program committee. Papers will be judged and accepted for the meeting based on the clarity with which the work is described and the biological relevance of the research. For this reason authors should be careful to make the connection to biology clear. We reject only a small fraction of the papers (~ 5%) and this usually based on absence of biological relevance (e.g. pure machine learning). We will notify authors of meeting acceptance before end of March. The second stage of review involves evaluation of submissions which requested an oral presentation by two independent referees. In addition to perceived quality as an oral presentation, the novelty of the research and the diversity and coherence of the overall program will be considered. To ensure diversity, those who have given talks in the recent past will not be selected and multiple oral presentations from the same lab will be discouraged. All accepted papers not selected for oral talks as well as papers explicitly submitted as poster presentations will be included in one of three evening poster sessions. Authors will be notified of the presentation format of their papers by begin of May. CONFERENCE PROCEEDINGS The proceedings volume is published each year as a special supplement to the journal Neurocomputing. In addition the proceedings are published in a hardbound edition by Elsevier Press. Only 200 papers will be published in the proceedings volume. If more than 200 papers are submitted (which is likely) the following rules will apply: each presenting author (who has to register for the meeting) can publish at most one paper in the proceedings book. In case of multi-author papers the same rule applies: one of the authors is considered presenting author and this person has to register at the meeting and cannot publish another paper. If more than 200 presenting authors wish to publish their papers in the proceedings volume the ranking based on the review process will be used to select the top 200 papers. Paper submissions to the conference proceedings are a process separate from the current call for papers: a new submission will need to be done in the early fall of 2003 for which authors will receive detailed instructions. For reference, papers presented at CNS*99 can be found in volumes 32-33 of Neurocomputing (2000), those of CNS*00 in volumes 38-40 (2001) and those of CNS*01 in volumes 44-46 (2002). INVITED SPEAKERS: Yang Dan (University of California Berkeley, USA) Peter Dayan (Gatsby Computational Neuroscience Unit, London, UK) Henry Markram (Brain Mind Institute Lausanne, Switzerland) ORGANIZING COMMITTEE: The CNS meeting is organized by the Computational Meeting Organization Program chair: Erik De Schutter (University of Antwerp, Belgium) Local organizer: Albert Compte (University Miguel Hern=E1ndez, Spain) Workshop organizer: Maneesh Sahani (University of California, San Francisco, USA) Government Liaison: Dennis Glanzman (NIMH/NIH, USA) and Yuan Liu (NINDS/NIH, USA) Program Committee: Upinder Bhalla (National Centre for Biological Sciences, India) Victoria Booth (New Jersey Institute of Technology, USA) Alain Destexhe (CNRS Gif-sur-Yvette, France) John Hertz (Nordita, Denmark) Bill Holmes (Ohio University, USA) Hidetoshi Ikeno (Himeji Institute of Technology, Japan) Barry Richmond (NIMH, USA) Eytan Ruppin (Tel Aviv University) Frances Skinner (University Toronto, Canada) From giacomo at ini.phys.ethz.ch Tue Feb 11 04:09:26 2003 From: giacomo at ini.phys.ethz.ch (Giacomo Indiveri) Date: Tue, 11 Feb 2003 10:09:26 +0100 Subject: Neuromorphic Engineering Workshop: SECOND CALL FOR APPLICATIONS Message-ID: <3E48BDC6.9010502@ini.phys.ethz.ch> Please post and distribute to collegues and friends http://www.ini.unizh.ch/telluride/announcement.html SECOND CALL FOR APPLICATIONS (sorry for cross-postings) ------------------------------------------------------------------------ NEUROMORPHIC ENGINEERING WORKSHOP Sunday, JUNE 29 - Saturday, JULY 19, 2003 TELLURIDE, COLORADO http://www.ini.unizh.ch/telluride/ ------------------------------------------------------------------------ Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Ralph ETIENNE-CUMMINGS (University of Maryland) Timmer HORIUCHI (University of Maryland) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Christof KOCH (California Institute of Technology) Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) ------------------------------------------------------------------------- We invite applications for the annual three week "Telluride Workshop and Summer School on Neuromorphic Engineering" that will be held in Telluride, Colorado from Sunday, June 29 to Saturday, July 19, 2003. The application deadline is FRIDAY, MARCH 14, and application instructions are described at the bottom of this document. Like each of these workshops that have taken place since 1994, the 2002 Workshop and Summer School on Neuromorphic Engineering, sponsored by the National Science Foundation, the Whitaker Foundation, the Office of Naval Research, the Defence Advanced Research Projects Agency, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology, was an exciting event and a great success. We strongly encourage interested parties to browse through the previous workshop web pages located at: http://www.ini.unizh.ch/telluride For a discussion of the underlying science and technology and a report on the 2001 workshop, see the September 20, 2001 issue of "The Economist": http://www.economist.com/science/tq/displayStory.cfm?Story_ID=779503 GOALS: Carver Mead introduced the term "Neuromorphic Engineering" for a new field based on the design and fabrication of artificial neural systems, such as vision systems, head-eye systems, and roving robots, whose architecture and design principles are based on those of biological nervous systems. The goal of this workshop is to bring together young investigators and more established researchers from academia with their counterparts in industry and national laboratories, working on both neurobiological as well as engineering aspects of sensory systems and sensory-motor integration. The focus of the workshop will be on active participation, with demonstration systems and hands on experience for all participants. Neuromorphic engineering has a wide range of applications from nonlinear adaptive control of complex systems to the design of smart sensors, vision, speech understanding and robotics. Many of the fundamental principles in this field, such as the use of learning methods and the design of parallel hardware (with an emphasis on analog and asynchronous digital VLSI), are inspired by biological systems. However, existing applications are modest and the challenge of scaling up from small artificial neural networks and designing completely autonomous systems at the levels achieved by biological systems lies ahead. The assumption underlying this three week workshop is that the next generation of neuromorphic systems would benefit from closer attention to the principles found through experimental and theoretical studies of real biological nervous systems as whole systems. FORMAT: The three week summer school will include background lectures on systems neuroscience (in particular learning, oculo-motor and other motor systems and attention), practical tutorials on analog VLSI design, small mobile robots (Koalas, Kheperas, LEGO robots, and biobugs), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, the majority of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control * central pattern generator * robotics * swarm robotics * multichip communication * analog VLSI * learning The active perception project group will emphasize vision and human sensory-motor coordination. Issues to be covered will include spatial localization and constancy, attention, motor planning, eye movements, and the use of visual motion information for motor control. The central pattern generator group will focus on small walking and undulating robots. It will look at characteristics and sources of parts for building robots, play with working examples of legged and segmented robots, and discuss CPG's and theories of nonlinear oscillators for locomotion. It will also explore the use of simple analog VLSI sensors for autonomous robots. The robotics group will use rovers and working digital vision boards as well as other possible sensors to investigate issues of sensorimotor integration, navigation and learning. The audition group aims to develop biologically plausible algorithms and aVLSI implementations of specific auditory tasks such as source localization and tracking, and sound pattern recognition. Projects will be integrated with visual and motor tasks in the context of a robot platform. The multichip communication project group will use existing interchip communication interfaces to program small networks of artificial neurons to exhibit particular behaviors such as amplification, oscillation, and associative memory. Issues in multichip communication will be discussed. This year we will also have *200* biobugs, kindly donated by the WowWee Toys division of Hasbro in Hong Kong. B.I.O.-Bugs, short for Bio-mechanical Integrated Organisms, are autonomous creatures, each measuring about one foot and weighing about one pound (www.wowwee.com/biobugs/biointerface.html). This will permit us to carry out experiments in collective/swarm robotics. LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350 miles). Great Lakes Aviation and America West Express airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do NOT rent a car. Bring hiking boots, warm clothes, rain gear and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around mid April 2003. Participants are expected to pay a $275.00 workshop fee at that time in order to reserve a place in the workshop. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. Travel reimbursement of up to $500 for US domestic travel and up to $800 for overseas travel will be possible if financial help is needed (Please specify on the application). HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e., postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage qualified women and minority candidates to apply. Application should include: * First name, Last name, Affiliation, valid e-mail address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Description of demonstrations that could be brought to the workshop. * Two letters of recommendation Complete applications should be sent to: Terrence Sejnowski The Salk Institute 10010 North Torrey Pines Road San Diego, CA 92037 e-mail: telluride at salk.edu FAX: (858) 587 0417 APPLICATION DEADLINE: MARCH 14, 2003 From Peter.Andras at newcastle.ac.uk Tue Feb 11 10:06:57 2003 From: Peter.Andras at newcastle.ac.uk (Peter Andras) Date: Tue, 11 Feb 2003 15:06:57 -0000 Subject: Postdoc job / Deadline: 24 February Message-ID: <20CC6C4061CBB04A98656ED3209B203C430533@bond.ncl.ac.uk> Research Associate, School of Computing Science, =A318,265 - =A327,339 Medical Research Council funded postdoctoral position based in the School of Computing Science, University of Newcastle, UK. A postdoctoral research associate is required to work on the development of knowledge discovery and knowledge management tools and applications for GRID-enabled neuroinformatics. The candidates should have a PhD in computer science, neuroinformatics, neuroscience, or related areas, and good knowledge and experience of objected oriented software design and development (e.g., Java, C/C++). Experience in any of the following areas is beneficial: using artificial intelligence methods (e.g., neural networks, text and data mining), working with web-databases (e.g., neuroscience databases), developing distributed systems (e.g., distributed databases). The post is for up to three years. The salary depends on experience and it is on the RA1A scale range: =A318,265 - =A327,339. For further enquiries e-mail Dr Peter Andras at peter.andras at ncl.ac.uk. Applications including an application form (download from the web-site), a CV, and names and addresses of two referees should be sent to Mrs A. Jackson, School of Computing Science, Claremont Tower, Claremont Road, Newcastle upon Tyne NE1 7RU, or by email to: Anke.Jackson at ncl.ac.uk. Closing date is 24 February 2003. Job reference: D520R Web: http://www.ncl.ac.uk/vacancies/vacancy.phtml?ref=3DD520R ----------------- Dr Peter Andras Lecturer Claremont Tower School of Computing Science University of Newcastle Newcastle upon Tyne NE1 7RU UK Tel. +44-191-2227946 Fax. +44-191-2228232 Web: www.staff.ncl.ac.uk/peter.andras From mhb0 at Lehigh.EDU Tue Feb 11 09:08:37 2003 From: mhb0 at Lehigh.EDU (Mark H. Bickhard) Date: Tue, 11 Feb 2003 09:08:37 -0500 Subject: Final CFP Message-ID: <3E4903E4.6F5A4E87@lehigh.edu> FINAL CALL FOR PAPERS Interactivist Summer Institute 2003 July 22-26, 2003 Botanical Auditorium Copenhagen, Denmark Join us in exploring the frontiers of understanding of life, mind, and cognition. There is a growing recognition - across many disciplines - that phenomena of life and mind, including cognition and representation, are emergents of far-from-equilibrium, interactive, autonomous systems. Mind and biology, mind and agent, are being re-united. The classical treatment of cognition and representation within a formalist framework of encodingist assumptions is widely recognized as a fruitless maze of blind alleys. From neurobiology to robotics, from cognitive science to philosophy of mind and language, dynamic and interactive alternatives are being explored. Dynamic systems approaches and autonomous agent research join in the effort. The interactivist model offers a theoretical approach to matters of life and mind, ranging from evolutionary- and neuro-biology - including the emergence of biological function ? through representation, perception, motivation, memory, learning and development, emotions, consciousness, language, rationality, sociality, personality and psychopathology. This work has developed interfaces with studies of central nervous system functioning, the ontology of process, autonomous agents, philosophy of science, and all areas of psychology, philosophy, and cognitive science that address the person. The conference will involve both tutorials addressing central parts and aspects of the interactive model, and papers addressing current work of relevance to this general approach. This will be our second Summer Institute; the first was in 2001 at Lehigh University, Bethlehem, PA, USA. The intention is for this Summer Institute to become a traditional biennial meeting where those sharing the core ideas of interactivism will meet and discuss their work, try to reconstruct its historical roots, put forward current research in different fields that fits the interactivist framework, and define research topics for prospective graduate students. People working in philosophy of mind, linguistics, social sciences, artificial intelligence, cognitive robotics, theoretical biology, and other fields related to the sciences of mind are invited to send their paper submission or statement of interest for participation to the organizers. http://www.lehigh.edu/~interact/isi2003/isi2003.html -- Mark H. Bickhard 17 Memorial Drive East Lehigh University Bethlehem, PA 18015 610-758-3633 mark at bickhard.name http://www.bickhard.ws/ From cindy at bu.edu Tue Feb 11 14:44:37 2003 From: cindy at bu.edu (Cynthia Bradford) Date: Tue, 11 Feb 2003 14:44:37 -0500 Subject: Neural Networks 16(2) Message-ID: <200302111944.h1BJibe04196@cns-pc75.bu.edu> NEURAL NETWORKS 16(2) Contents - Volume 16, Number 2 - 2003 ------------------------------------------------------------------ NEURAL NETWORKS LETTERS: A complex-valued nonlinear neural adaptive filter with a gradient adaptive amplitude of the activation function Andrew I. Hanna and Danilo P. Mandic CONTRIBUTED ARTICLES: ***** Neuroscience and Neuropsychology ***** Self-organizing continuous attractor networks and motor function S.M. Stringer, E.T. Rolls, T.P. Trappenberg, and I.E.T. de Araujo ***** Mathematical and Computational Analysis ***** Zonal function network frames on the sphere H.N. Mhaskar, F.J. Narcowich, and J.D. Ward On motion detection through a multi-layer neural network architecture Antonio Fernandez-Caballero, Jose Mira, Miguel A. Fernandez, and Ana E. Delgado Dual extended Kalman filtering in recurrent neural networks Chi-Sing Leung and Law-Wan Chan Kalman filters improve LSTM network performance in problems unsolvable by traditional recurrent nets Juan Antonio Perez-Ortiz, Felix A. Gers, Douglas Eck, and Jurgen Schmidhuber Intelligent optimal control with dynamic neural networks Yasar Becerikli, Ahmet Ferit Konar, and Tariq Samad Clustering ensembles of neural network models Bart Bakker and Tom Heskes ***** Engineering and Design ***** Neural network based tracking control of a flexible macro-micro manipulator system X.P. Cheng and R.V. Patel BOOK REVIEWS: Review of "Graphical models: Foundations of neural computation" (Michael I. Jordan and Terrence J. Sejnowski, editors) by Gary R. Bradski Review of "Introduction to neural and cognitive modeling: Second edition" (Daniel S. Levine, author) by Haluk Ogmen CURRENT EVENTS ------------------------------------------------------------------ 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 (regular) Y 13,000 (regular) Neural Networks (plus 2,000 enrollment fee) $20 (student) SEK 460 (student) Y 11,000 (student) (plus 2,000 enrollment fee) ----------------------------------------------------------------------------- membership without $30 SEK 200 not available to Neural Networks non-students (subscribe through another society) Y 5,000 (student) (plus 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 19 Mantua Road Mount Royal NJ 08061 USA 856 423 0162 (phone) 856 423 3420 (fax) innshq at talley.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 c/o Professor Takashi Nagano Faculty of Engineering Hosei University 3-7-2, Kajinocho, Koganei-shi Tokyo 184-8584 Japan 81 42 387 6350 (phone and fax) jnns at k.hosei.ac.jp http://jnns.inf.eng.tamagawa.ac.jp/home-j.html ----------------------------------------------------------------- From jelinek at jhu.edu Tue Feb 11 06:59:35 2003 From: jelinek at jhu.edu (Fred Jelinek) Date: Tue, 11 Feb 2003 06:59:35 -0500 Subject: NSF-supported Summer Internships Message-ID: <6284-Tue11Feb2003065935-0500-jason@cs.jhu.edu> Dear Colleague: The Center for Language and Speech Processing at the Johns Hopkins University is offering a unique summer internship opportunity, which we would like you to bring to the attention of your best students in the current junior class. Preliminary applications for these internships are due at the end of this week. This internship is unique in the sense that the selected students will participate in cutting edge research as full members alongside leading scientists from industry, academia, and the government. The exciting nature of the internship is the exposure of the undergraduate students to the emerging fields of language engineering, such as automatic speech recognition (ASR), natural language processing (NLP) and machine translation (MT). We are specifically looking to attract new talent into the field and, as such, do not require the students to have prior knowledge of language engineering technology. Please take a few moments to nominate suitable bright students for this internship. On-line applications for the program can be found at http://www.clsp.jhu.edu/ along with additional information regarding plans for the 2003 Workshop and information on past workshops. The application deadline is February 15, 2003. If you have questions, please contact us by phone (410-516-4237), e-mail (sec at clsp.jhu.edu) or via the Internet http://www.clsp.jhu.edu Sincerely, Frederick Jelinek J.S. Smith Professor and Director --------------------------------------------------------------------------- Team Project Descriptions for this Summer --------------------------------------------------------------------------- 1. Syntax for Statistical Machine Translation In recent evaluations of machine translation systems, statistical systems based on probabilistic models have outperformed classical approaches based on interpretation, transfer, and generation. Nonetheless, the output of statistical systems often contains obvious grammatical errors. This can be attributed to the fact that the syntactic well-formedness is only influenced by local n-gram language models and simple alignment models. We aim to integrate syntactic structure into statistical models to address this problem. A very convenient and promising approach for this integration is the maximum entropy framework, which allows to integrate many different knowledge sources into an overall model and to train the combination weights discriminatively. This approach will allow us to extend a baseline system easily by adding new feature functions. The workshop will start with a strong baseline -- the alignment template statistical machine translation system that obtained best results in the 2002 DARPA MT evaluations. During the workshop, we will incrementally add new features representing syntactic knowledge that deal with specific problems of the underlying baseline. We want to investigate a broad range of possible feature functions, from very simple binary features to sophisticated tree-to-tree translation models. Simple feature functions might test if a certain constituent occurs in the source and the target language parse tree. More sophisticated features will be derived from an alignment model where whole sub-trees in source and target can be aligned node by node. We also plan to investigate features based on projection of parse trees from one language onto strings of another, a useful technique when parses are available for only one of the two languages. We will extend previous tree-based alignment models by allowing partial tree alignments when the two syntactic structures are not isomorphic. We will work with the Chinese-English data from the recent evaluations, as large amounts of sentence-aligned training corpora, as well as multiple reference translations are available. This will also allow us to compare our results with the various systems participating in the evaluations. In addition, annotation is underway on a Chinese-English parallel tree-bank. We plan to evaluate the improvement of our system using both automatic metrics for comparison with reference translations (BLEU and NIST) as well as subjective evaluations of adequacy and fluency. We hope both to improve machine translation performance and advance the understanding of how linguistic representations can be integrated into statistical models of language. --------------------------------------------------------------------------- 2. Semantic Analysis Over Sparse Data The aim of the task is to verify the feasibility of a machine learning-based semantic approach to the data sparseness problem that is encountered in many areas of natural language processing such as language modeling, text classification, question answering and information extraction. The suggested approach takes advantage of several technologies for supervised and unsupervised sense disambiguation that have been developed in the last decade and of several resources that have been made available. The task is motivated by the fact that current language processing models are considerably affected by sparseness of training data, and current solutions, like class-based approaches, do not elicit appropriate information: the semantic nature and linguistic expressiveness of automatically derived word classes is unclear. Many of these limitations originate from the fact that fine-grained automatic sense disambiguation is not applicable on a large scale. The workshop will develop a weakly supervised method for sense modeling (i.e. reduction of possible word senses in corpora according to their genre) and apply it to a huge corpus in order to coarsely sense-disambiguate it. This can be viewed as an incremental step towards fine-grained sense disambiguation. The created semantic repository as well as the developed techniques will be made available as resources for future work on language modeling, semantic acquisition for text extraction, question answering, summarization, and most other natural language processing tasks. --------------------------------------------------------------------------- 3. Dialectal Chinese Speech Recognition There are eight major dialectal regions in addition to Mandarin (Northern China) in China, including Wu (Southern Jiangsu, Zhejiang, and Shanghai), Yue (Guangdong, Hong Kong, Nanning Guangxi), Min (Fujian, Shantou Guangdong, Haikou Hainan, Taipei Taiwan), Hakka (Meixian Guangdong, Hsin-chu Taiwan), Xiang (Hunan), Gan (Jiangxi), Hui (Anhui), and Jin (Shanxi). These dialects can be further divided into more than 40 sub-categories. Although the Chinese dialects share a written language and standard Chinese (Putonghua) is widely spoken in most regions, speech is still strongly influenced by the native dialects. This great linguistic diversity poses problems for automatic speech and language technology. Automatic speech recognition relies to a great extent on the consistent pronunciation and usage of words within a language. In Chinese, word usage, pronunciation, and syntax and grammar vary depending on the speaker's dialect. As a result speech recognition systems constructed to process standard Chinese (Putonghua) perform poorly for the great majority of the population. The goal of our summer project is to develop a general framework to model phonetic, lexical, and pronunciation variability in dialectal Chinese automatic speech recognition tasks. The baseline system is a standard Chinese recognizer. The goal of our research is to find suitable methods that employ dialect-related knowledge and training data (in relatively small quantities) to modify the baseline system to obtain a dialectal Chinese recognizer for the specific dialect of interest. For practical reasons during the summer, we will focus on one specific dialect, for example the Wu dialect or the Chuan dialect. However the techniques we intend to develop should be broadly applicable. Our project will build on established ASR tools and systems developed for standard Chinese. In particular, our previous studies in pronunciation modeling have established baseline Mandarin ASR systems along with their component lexicons and language model collections. However, little previous work or resources are available to support research in Chinese dialect variation for ASR. Our pre-workshop will therefore focus on further infrastructure development: * Dialectal Lexicon Construction. We will establish an electronic dialect dictionary for the chosen dialect. The lexicon will be constructed to represent both standard and dialectal pronunciations. * Dialectal Chinese Database Collection. We will set up a dialectal Chinese speech database with canonical pinyin level and dialectal pinyin level transcriptions. The database could contain two parts: read speech and spontaneous speech. For the spontaneous speech part, the generalized initial/final (GIF) level transcription should be also included. Our effort at the workshop will be to employ these materials to develop ASR system components that can be adapted from standard Chinese to the chosen dialect. Emphasis will be placed on developing techniques that work robustly with relatively small (or even no) dialect data. Research will focus primarily on acoustic phenomena, rather than syntax or grammatical variation, which we intend to pursue after establishing baseline ASR experiments. --------------------------------------------------------------------------- 4. Confidence Estimation for Natural Language Applications Significant progress has been made in natural language processing (NLP) technologies in recent years, but most still do not match human performance. Since many applications of these technologies require human-quality results, some form of manual intervention is necessary. The success of such applications therefore depends heavily on the extent to which errors can be automatically detected and signaled to a human user. In our project we will attempt to devise a generic method for NLP error detection by studying the problem of Confidence Estimation (CE) in NLP results within a Machine Learning (ML) framework. Although widely used in Automatic Speech Recognition (ASR) applications, this approach has not yet been extensively pursued in other areas of NLP. In ASR, error recovery is entirely based on confidence measures: results with a low level of confidence are rejected and the user is asked to repeat his or her statement. We argue that a large number of other NLP applications could benefit from such an approach. For instance, when post-editing MT output, a human translator could revise only those automatic translations that have a high probability of being wrong. Apart from improving user interactions, CE methods could also be used to improve the underlying technologies. For example, bootstrap learning could be based on outputs with a high confidence level, and NLP output re-scoring could depend on probabilities of correctness. Our basic approach will be to use a statistical Machine Learning (ML) framework to post-process NLP results: an additional ML layer will be trained to discriminate between correct and incorrect NLP results and compute a confidence measure (CM) that is an estimate of the probability of an output being correct. We will test this approach on a statistical MT application using a very strong baseline MT system. Specifically, we will start off with the same training corpus (Chinese-English data from recent NIST evaluations), and baseline system as the Syntax for Statistical Machine Translation team. During the workshop we will investigate a variety of confidence features and test their effects on the discriminative power of our CM using Receiver Operating Characteristic (ROC) curves. We will investigate features intended to capture the amount of overlap, or consensus, among the system's n-best translation hypotheses, features focusing on the reliability of estimates from the training corpus, ones intended to capture the inherent difficulty of the source sentence under translation, and those that exploit information from the base statistical MT system. Other themes for investigation include a comparison of different ML frameworks such as Neural Nets or Support Vector Machines, and a determination of the optimal granularity for confidence estimates (sentence-level, word-level, etc). Two methods will be used to evaluate final results. First, we will perform a re-scoring experiment where the n-best translation alternatives output by the baseline system will be re-ordered according to their confidence estimates. The results will be measured using the standard automatic evaluation metric BLEU, and should be directly comparable to those obtained by the Syntax for Statistical Machine Translation team. We expect this to lead to many insights about the differences between our approach and theirs. Another method of evaluation will be to estimate the tradeoff between final translation quality and amount of human effort invested, in a simulated post-editing scenario. --------------------------------------------------------------------------- From nat at site.uottawa.ca Tue Feb 11 19:46:59 2003 From: nat at site.uottawa.ca (Nathalie Japkowicz) Date: Tue, 11 Feb 2003 19:46:59 -0500 (EST) Subject: Workshop: Learning from Imbalanced Data Sets Message-ID: CALL FOR PAPERS ICML-KDD'2003 Workshop: Learning from Imbalanced Data Sets II Thursday, August 21, 2003 Washington, DC ------------------------------------------------------------------------ Organizers: ----------- Nitesh Chawla, Business Analytic Solutions, CIBC (chawla at csee.usf.edu) Nathalie Japkowicz, University of Ottawa (nat at site.uottawa.ca) Aleksander Kolcz, America Online, Inc. (ark at pikespeak.uccs.edu) ------------------------------------------------------------------------ Workshop Page: -------------- http://www.site.uottawa.ca/~nat/Workshop2003/workshop2003.html ------------------------------------------------------------------------ Workshop Description: --------------------- Overview: Recent years brought increased interest in applying machine learning techniques to difficult "real-world" problems, many of which are characterized by imbalanced learning data, where at least one class is under-represented relative to others. Examples include (but are not limited to): fraud/intrusion detection, risk management, medical diagnosis/monitoring, bioinformatics, text categorization and personalization of information. The problem of imbalanced data is often associated with asymmetric costs of misclassifying elements of different classes. Additionally the distribution of the test data may differ from that of the learning sample and the true misclassification costs may be unknown at learning time. The AAAI-2000 Workshop on "Learning from Imbalanced Data Sets" provided the first venue where this important problem was explicitly addressed and has been received with much interest. The related ICML-2000 Workshop on "Cost-Sensitive Learning" provided another venue for addressing the problem of asymmetric costs of different classes and features. Although much awareness of the issues related to data imbalance has been raised, many of the key problems still remain open and are in fact encountered more often, especially when applied to massive datasets. We believe that it would be of value to the machine learning community to not only examine the progress achieved in this area over the last three years but also discuss the current school of thought on research in learning from imbalanced datasets. Based on our understanding of class imbalance problem, the following topics of discussion are proposed (but not limited to): * sampling (under-, over-, progressive, active) * post-processing of learned models * accounting for class imbalance via inductive bias * one-sided learning * handling uncertainty of target distribution and misclassification costs * handling varying amounts (class dependent) of label noise Proposed Format: The workshop will open with an invited talk by Foster Provost that will introduce and overview the topic. Presentations will then be organized into several sessions corresponding roughly to the to the categories identified above. The workshop will conclude with a discussion during which a distinguished guest will comment on the presentations of the day, and open the floor for general discussion. Proposed Length: One Day during which each panel will be allocated 1 to 2 hours, depending on the number of contributions and the expected length of the discussion session. Workshop Notes: The accepted papers will be available electronically from the workhop website, and also as printed workshop notes to the attendees. Submissions: Authors are invited to submit papers on the topics outlined above or on other related issues. Submissions should not exceed 8 pages, and should be in line with the ICML style sheet. Electronic submissions, in PDF format, are prefered and should be sent to: Nitesh Chawla at chawla at morden.csee.usf.edu If electronic submissions are inconvenient, please send four hard copies of your submission to: Dr. Nitesh Chawla Business Analytic Solutions, TBRM, CIBC, BCE Place, 161 Bay Street, 11th Floor, Toronto, Ontario M5J 2S8, Canada ------------------------------------------------------------------------ Timetable: ---------- * Submission deadline: May 1, 2003 * Notification date: May 25, 2003 * Final date for camera-ready copies to organizers: June 8, 2003 ------------------------------------------------------------------------ Invited Speakers: ----------------- Foster Provost New York University, USA Others To Be Announced ------------------------------------------------------------------------ Program Committee: ------------------ Kevin Bowyer University of Notre Dame, USA Chris Drummond National Research Council, Canada Charles Elkan University of California San Diego, USA Marko Grobelnik Jozef Stefan Institute, Slovenia Larry Hall University of South Florida, USA Robert Holte University of Alberta, Canada W.Philip Kegelmeyer Sandia National Labs, USA Miroslav Kubat University of Miami, USA Aleksandar Lazarevic University of Minnesotta, USA Charles Ling University of Western Ontario, Canada Dragos Margineantu Boeing Corporation, USA Foster Provost New York University, USA Gary Weiss AT&T Labs, USA ----------------------------------------------------------------------- Nathalie Japkowicz, Ph.D. Office: SITE Building 5-029 Assistant Professor Phone: (613) 562-5800 x6693 School of Information E-mail:nat at site.uottawa.ca Technology & Engineering WWW: http://www.site.uottawa.ca/~nat University of Ottawa FAX: (613) 562-5664 Street Address: 800 King Edward Avenue, P.O. Box 450 Stn. A Ottawa, Ontario, Canada K1N 6N5 ----------------------------------------------------------------------- From bengioy at IRO.UMontreal.CA Tue Feb 11 14:17:04 2003 From: bengioy at IRO.UMontreal.CA (Yoshua Bengio) Date: Tue, 11 Feb 2003 14:17:04 -0500 Subject: date change, Montreal workshop on Advances in Machine Learning Message-ID: <20030211141704.A31458@lmlp.iro.umontreal.ca> ----- Forwarded message from Balazs Kegl ----- Due to a date conflict with a major conference, we have had to reschedule the Workshop on Advances in Machine Learning from June 2-6 to June 9-13. We apologize for the inconvenience it may cause. The paper submission deadline remains March 31. -------------------------------------------------------------------------- Call for papers Workshop on Advances in Machine Learning Montreal, Canada, June 9-13, 2003 URL: www.iro.umontreal.ca/~lisa/workshop2003.html Organizers: Yoshua Bengio, Balazs Kegl (University of Montreal) Doina Precup (McGill University) Scope: Probabilities are at the core of recent advances in the theory and practice of machine learning algorithms. The workshop will focus on three broad areas where these advances are crucial: statistical learning theory, learning algorithms, and reinforcement learning. The workshop will therefore bring together experts from each of these three important domains. Among the sub-topics that will be covered, we note: variational methods, graphical models, the curse of dimensionality, empirical methods to take advantage of theories of generalization error, and some of the applications of these new methods. On the theoretical side, in recent years a lot of effort has been devoted to explain the generalization abilities of popular learning algorithms such as voting classifiers and kernel methods. Some of these results have given rise to general principles that can guide practical classifier design. Some (non-exclusive) sub-topics in this aspect of the workshop include Rademacher and Gaussian complexities, algorithmic stability and generalization, localized complexities and results on the generalization ability of voting classifiers and kernel-based methods. On the algorithmic side, one of the emphasis of recent years has been on probabilistic models that attempt to capture the complex structure in the data, often by discovering the main lower-dimensional features that explain the data. This raises interesting and difficult questions on how to train such models, but such algorithms may have wide ranging applications in domains in which the data has interesting structure that may be explained at multiple levels, such as in vision and language. In reinforcement learning (RL), recent research has brought significant advances in some of the traditional problems, such as understanding the interplay between RL algorithms and function approximation, and extending RL beyond MDPs. At the same time, new areas of research, such as computational game theory, have developed at the interface between RL and probabilistic learning methods. In this workshop, we invite presentations on all RL topics, ranging from theoretical development to practical applications. Invited speakers: Rich Sutton, U. Massachusetts, MA, USA Andy Barto, U. Massachusetts, MA, USA (to confirm) Satinder Singh, U. Michigan, Ann Arbour, MI, USA Sridhar Mahadevan, U. Massachusetts Peter Bartlett, U. California Berkeley, CA, USA Vladimir Koltchinskii, U. New Mexico, NM, USA Yann Le Cun, NEC Research, NJ, USA Paolo Frasconi, U. Firenze, Italy Dale Schuurmans, Waterloo U., Ontario, Canada Nando de Freitas, U. British Columbia, BC, Canada Sam Roweis, U. Toronto, Ontario, Canada Geoff Hinton, U. Toronto, Ontario, Canada Important dates: March 31, Paper submission deadline April 15, Notification of paper acceptance/rejection. Submission: Papers should be submitted electronically to kegl at iro.umontreal.ca. Papers can be submitted either as a postscript or a pdf (acrobat) file. No proceedings are currently planned. Registration: The registration fees are minimal: regular registration fees are 100$CAN. Reduced rate for students from a Canadian academic institution: 50$CAN. Venue: The workshop will take place at the Centre de Recherches Mathematiques, on the campus of Universite de Montreal, in lively and beautiful Montreal, Canada. The conference will be held in the Pavillon Andre Aisenstadt, 2920 chemin de la Tour. ----- End forwarded message ----- Yoshua Bengio Full Professor / Professeur titulaire Canada Research Chair in Statistical Learning Algorithms / titulaire de la chaire de recherche du Canada en algorithmes d'apprentissage statistique D?partement d'Informatique et Recherche Op?rationnelle Universit? de Montr?al, adresse postale: C.P. 6128 Succ. Centre-Ville, Montr?al, Qu?bec, Canada H3C 3J7 adresse civique: 2920 Chemin de la Tour, Montr?al, Qu?bec, Canada H3T 1J8, #2194 Tel: 514-343-6804. Fax: 514-343-5834. Bureau 3339. http://www.iro.umontreal.ca/~bengioy http://www.iro.umontreal.ca/~lisa From silvia at sa.infn.it Tue Feb 11 17:37:43 2003 From: silvia at sa.infn.it (Silvia Scarpetta) Date: Tue, 11 Feb 2003 23:37:43 +0100 Subject: Announcement of Erice School on Cortical Dynamics 31 Oct - 6 Nov 2003 Message-ID: <3E497B37.5070502@sa.infn.it> *International School on Neural Nets "E.R. Caianiello"* JOINTLY ORGANIZED BY IIASS International Institute for Advanced Scientific Studies and EMFCSC Ettore Majorana Foundation and Center for Scientific Culture *8th Course:** Computational Neuroscience: Cortical Dynamics * *31 Oct.- 6 Nov. 2003 * *Ettore Majorana Centre* * *Erice (Sicily) ITALY homepage: http://www.sa.infn.it/NeuralGroup/CorticalDynamicsSchool2003/ *Directors of the Course:* Maria Marinaro (Dept. of Physics "E.R. Caianiello", Univ. of Salerno, Italy) Peter Erdi (Kalamazoo College, USA & _KFKI Res. Inst. Part. and Nucl. Phys. Hung. Acad. Sci._ Hungary ) *Lecturers:* *Luigi Agnati *- Dept. of Neuroscience Karolinka Inst.,Sweden & Modena Univ. Italy *Peter Dayan * - Gatsby Computational Neuroscience Unit, UCL, UK - abstract _*Peter Erdi *_ - CCSS Kalamazoo College USA & KFKI Hung. Accad.of Science Hungary - Codirector - abstract *Bruce P Graham* - Dept of Computer Science and Mathematics, Univ. of Stirling UK- abstract *John Hertz* - Nordita, DK - abstract *Zhaoping Li* - Univ. College of London, UK - abstract *Ronen Segev * - School of Physics and Astronomy, Tel Aviv University, Israel - abstract *Ivan Soltesz* - Dept. of Anatomy and Neurobiology, Univ. of California, USA - abstract *Misha Tsodyks* - Dept. of Neurobiology Weizmann Institute of Science, Israel *Ichiro Tsuda* - Dept. of Mathematics, Hokkaido University, Japan -abstract *Alessandro Treves* - Sissa, Cognitive Neuroscience, Trieste, It - abstract **Scientific Program ** /Recently the amount of experimental data available to computational neuroscience community grows steadily, //due to the development of new experimental technique.//The data obtained with these modern techniques allows a degree of comparison with modeling results that so far was not possible. At the same time new and stronger theoretical ideas are being developed from all over the world, borrowing ideas and tools from different fields of science, such as physics and mathematics. / /The goal of the school is to present an up-to-date description of the experimental and theoretical results and of the current efforts to investigate processing, transmission and imprinting of information in the brain, focusing on cortical area. Cortical areas play a key role in important functions like those related to the memory. A systematic description of cortical rhythms and cortical neural plasticity will be given, from its structural basis to its functional significance. / /The school is devoted to students with different scientific background (physics, mathematics, biology, neuroscience, etc.) who wish to learn recent developments in computational neuroscience and cortical dynamics. The basic concepts will be introduced, with emphasis on the underlying //physical concepts//, //common principles and connections between experimental data and biophysically-based as well abstract models. Then cortical dynamics will be investigated, focusing on recent developments and open problems./ **Registrations:** Applications must be received before *May 15 2003* in order to be considered by the selection committee. Registration fee of 900 Euro includes accomodation with full board. Application form and additional information are available from http://www.sa.infn.it/NeuralGroup/CorticalDynamicsSchool2003/. Applications should be sent by ordinary mail to the codirector of the school: Prof. Maria Marinaro IIASS Via Pellegrino 19, I-84019 Vietri sul Mare (Sa) Italy or by fax to: +39 089 761 189 (att.ne: Prof. M. Marinaro) or by electronic mail to: iiass.vietri at tin.it subject: summer school **Location** The "Ettore Majorana" International Centre for Scientific Culture takes its inspiration from the outstanding Italian physicist, after whom the Centre was named. Embracing 110 Schools , covering all branches of Science, the Centre is situated in the old pre-mediaeval city of Erice where three restored monasteries provide an appropriate setting for high intellectual endeavour. These monasteries are now named after great Scientists and strong supporters of the "Ettore Majorana" Centre. There are living quarters in all three Monasteries for people attending the Courses of the Centre. **The John von Neumann (1903-1957) Centenary will be celebrated during the meeting.** Additional information are available at: http://www.sa.infn.it/NeuralGroup/CorticalDynamicsSchool2003/ ---- From J.A.Bullinaria at cs.bham.ac.uk Wed Feb 12 07:09:01 2003 From: J.A.Bullinaria at cs.bham.ac.uk (John A Bullinaria) Date: Wed, 12 Feb 2003 12:09:01 +0000 (GMT) Subject: VACANCIES: Computational Intelligence, Birmingham, UK Message-ID: ------------------------------------------------------------------------ VACANCY: The Centre of Excellence in Computational Intelligence and Applications at Birmingham, UK, has the following openings. Two Research Fellows/Associates in Computational Intelligence (Ref. No. S36545/03, http://www.bham.ac.uk/personnel/s36545.htm) The Centre Manager (Ref. No. S36544/03, http://www.bham.ac.uk/personnel/s36544.htm) ------------------------------------------------------------------------ The School of Computer Science has recently set up a Centre of Excellence in Computational Intelligence and Applications, with substantial funding from the Advantage West Midlands (the regional development agency), to capitalise on and exploit the world-class research in the School for the benefit of industry and businesses (especially those in the West Midlands region). Applications are now invited for the posts of the Centre Manager and two research fellows/associates. The posts are available immediately until 31 March 2007 in the first instance. (The post of the Centre Secretary will be advertised separately.) The successful applicant for the Centre Manager is expected to play a key role in the management and future growth of the Centre. He/She must have excellent analytical and problem solving skills, demonstrated by previous experiences and achievements. He/She should have a very good first degree or postgraduate degree (PhD preferred) in a science or engineering subject (computer science or IT preferred). He/She must have excellent management, communications and people skills, and enjoy working with both business and academic people. He/She should have a background or be interested in computational intelligence. He/She must be self-motivated and capable of working both independently and as a team member. The successful applicants for research fellows/associates must have excellent analytical and problem solving skills in computational intelligence and excellent programming and software development skills. They should have a PhD degree in computer science/engineering or a closely related field, or at least a very good honours degree with significant research and development experiences in computational intelligence. They should demonstrate willingness and interest in tackling real-world problems and applying computational intelligence techniques to industry and businesses. They should be good team players. Excellent written and oral communication skills are required. The School of Computer Science is a leading research school in computer science in the UK. It was rated 5 for its research excellence in the latest (2001) research assessment exercise. The School has a world-leading group in natural computation and computational intelligence (http://www/cs/bham.ac.uk/research/NC). It also runs an EPSRC supported MSc programme in natural computation (http://www.cs.bham.ac.uk/study/postgraduate-taught/msc-nc/). The group includes more than 25 researchers (including permanent and visiting staff and PhD students), working on a wide range of topics in natural computation and computational intelligence. The starting salary for the Centre Manager is on the academic related scale in the range GBP18,265 - GBP33,679 per annum. (Depending on experience and qualifications). The starting salary for the research fellows/associates is on the research scale in the range GBP18,265 - GBP30,660 per annum. (Depending on experience and qualifications). For further particulars, please visit http://www.bham.ac.uk/personnel/s36544.htm (Manager) http://www.bham.ac.uk/personnel/s36545.htm (RFs) For informal enquiries, please contact the Centre Director, Prof Xin Yao (X.Yao at cs.bham.ac.uk). CLOSING DATE FOR RECEIPT OF APPLICATIONS: 4 March 2003 (late application may be considered) APPLICATION FORMS RETURNABLE TO The Director of Personnel Services The University of Birmingham Edgbaston, Birmingham, B15 2TT England RECRUITMENT OFFICE FAX NUMBER +44 121 414 4802 RECRUITMENT OFFICE TELEPHONE NUMBER +44 121 414 6486 RECRUITMENT OFFICE E-MAIL ADDRESS j.a.gerald at bham.ac.uk -------------------------------------------------------------------------- From bogus@does.not.exist.com Tue Feb 18 09:05:05 2003 From: bogus@does.not.exist.com () Date: Tue, 18 Feb 2003 14:05:05 -0000 Subject: AI Stats 2003: proceedings now available on-line Message-ID: <6EDEB53BA6EA96458F3CEC96BB0282D2021DE7B7@tvp-msg-03.europe.corp.microsoft.com> From David.Hansel at biomedicale.univ-paris5.fr Tue Feb 18 04:59:47 2003 From: David.Hansel at biomedicale.univ-paris5.fr (David Hansel) Date: Tue, 18 Feb 2003 09:59:47 +0000 Subject: Les Houches summer school: METHODS AND MODELS IN NEUROPHYSICS Message-ID: <3E520413.9030603@biomedicale.univ-paris5.fr> * NATO Advanced Study Institute METHODS AND MODELS IN NEUROPHYSICS July 28 - August 29, 2003* Scientific Direction: C. C. Chow (Pittsburgh), B. Gutkin (London), D. Hansel and C. Meunier (Paris), I. Segev (Jerusalem) _Program_ Opening lecture: E. Marder (Waltham, USA) Why would a self-respecting experimental biologist be susceptible to theory? _Lecture series:_ L. Abbott (Waltham, USA), P. Bressloff (Salt Lake City, USA), E. Brown (Boston, USA), J. Rinzel (New York, USA), H. Sompolinsky (Jerusalem, Israel), D. Terman (Colombus, USA), T. Tishby (Jerusalem, Israel) _Short lectures and seminars:_ N. Brunel (Paris, France), W. Gerstner (Lausanne, Switzerland), D. Golomb (Beersheva, Israel), G. Mato (Bariloche, Argentina), C. Pouzat (Paris, France), M. Shelley (New York, USA), A. Treves (Trieste, Italy), M. Tsodyks (Rehovot, Israel), C. van Vreeswijk (Paris, France), F. Wolf (Gottingen, Germany). _Topical workshops:_ _Workshop 1_: The neuron in the network. L. Graham (Paris, France) and others to be announced _Workshop 2_: Dynamics in the somatosensory system E. Ahissar (Rehovot, Israel), M. Brecht (Heidelberg, Germany), D. Kleinfeld (San Diego, USA), R. Petersen (Trieste, Italy) _ Workshop 3 _: Learning and Memory G.Q. Bi (Pittsburgh, USA), Y. Dudai (Rehovot, Israel), J. Taube (Hanover,USA), and others to be announced _Registration_ Applications must be received before March 7, 2003. A contribution of 900 euros per participant is requested for full accomodation. A few grants are available. Application forms and additional information are available from the School at Ecole d'ete de Physique theorique La Cote des Chavants, 74310 Les Houches, France Phone: 00-33 -4 50 54 40 69 - Fax: 00 33 -4 50 55 53 25 Email: secretariat.houches at ujf-grenoble.fr Web: http://www-houches.ujf-grenoble.fr/ Les Houches is a resort village of the Chamonix valley facing the Mont-Blanc range. Established in 1951, the Physics School is affiliated with Universite Joseph Fourier (Grenoble), INPG and supported by the Ministere de la Jeunesse, de l'Education Nationale et de la Recherche , by the Centre National de la Recherche Scientifique and by the Commissariat a l'Energie Atomique. This session received support from NATO IBRO and CNRS. From bogus@does.not.exist.com Tue Feb 18 11:16:15 2003 From: bogus@does.not.exist.com () Date: Tue, 18 Feb 2003 17:16:15 +0100 Subject: first announcement of the First European School on Neuroengineering "Massimo Grattarola" Message-ID: <5C052AA22466074FADC82C208D5C5719800F63@EVS02.idc.cww.telecomitalia.it> From d.mareschal at bbk.ac.uk Tue Feb 18 06:21:39 2003 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Tue, 18 Feb 2003 11:21:39 +0000 Subject: Phd Studentships Message-ID: The School of Psychology, Birkbeck College has a number of full-time Phd Studentships on offer for Phds starting in October 2003. Birkbeck College is part of the University of London and is situated in the central Bloomsbury area of London, in close proximity to University College London, The Insitute of Cognitive Neuroscience, the Gatsby Computational Neurosciences Unit, the Institue of Child Health, and the Insitute of Education. The School of Psychology has a very active internationally recognised research programme with particular interests in cognitive sciences, cognitive neurosciences, computational neuroscience, and cognitive and social development. However, the School welcomes applications for studentships in all areas of psychology in both full-time and part-time programmes. The School of Psychology also includes: The Centre for Brain and Cognitive Development (http://www.cbcd.bbk.ac.uk/cbcd.html) For more information about the Schools research profile and studentships available, please visit our website: http://www.psyc.bbk.ac.uk OR contact: Ms Mina Daniel Postgraduate Administrator Tel.: 020 7631 6862 E-mail: s.daniel at psychology.bbk.ac.uk ================================================= Dr. Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 (0)20 7631-6582/6226 reception: 6207 fax +44 (0)20 7631-6312 http://www.psyc.bbk.ac.uk/people/academic/mareschal_d/ ================================================= From markman at psyvax.psy.utexas.edu Tue Feb 18 10:13:53 2003 From: markman at psyvax.psy.utexas.edu (Art Markman) Date: Tue, 18 Feb 2003 09:13:53 -0600 Subject: Cognitive Science Society Virtual Colloquium Message-ID: The Cognitive Science Society is hosting a 2002-2003 virtual colloquium series presented live via the Internet, with the with the fourth talk given by Dr. John Anderson. Register now to attend: www.ctaresource.com/CognitiveScience. Time: Friday February 28, 2003 1:00pm US Eastern Standard Time Presenter: Dr. John Anderson Carnegie Mellon University, Department of Psychology Topic: Use of a Cognitive Architecture and fMRI to Mutually inform Each Other or A Tale of Three Buffers We will describe the interaction between cognitive modeling and brain imaging. Two fMRI studies will be described. The first was concerned with the solution of algebraic equations. We tried to relate the brain regions discovered to components of a prior ACT-R model that had been developed. A left posterior parietal region corresponded to the behavior of a module in ACT-R that maintains an image of the equation and performs mental transformations on it. A left prefrontal region corresponded to the behavior of a module that retrieves relevant information such as arithmetic facts. A left motor region corresponded to the behavior of module that programs hand movements. We will describe how we were able to fit precisely the BOLD functions obtained from these regions given the operation of the ACT-R model. To show that these regions were not specific to mathematics and to turn our model-fitting exercise from postdiction to prediction we performed a second study using a more abstract symbol-manipulation task. The model fits were equally good if not better, although we had to adjust our a priori rehearsal assumptions. The second study identified an anterior cingulate particle whose behavior appears to correspond to the conflict resolution process in ACT-R. This research illustrates profitable back and forth that is possible between brain imaging and cognitive modeling. The basic methodology can be applied to help shape any information processing architecture, not just ACT-R. Further information about this talk, the colloquium series, a schedule of future talks, and an archive of previous talks are available at http://www.cognitivesciencesociety.org/colloquium Contact Janet Morrow, cta at aptima.com with any questions about registration for this seminar. Please forward this invitation to colleagues who would benefit from this seminar or the series. This series is sponsored by the Office of Naval Research. Sincerely, Art Markman markman at psy.utexas.edu Dr. Arthur B. Markman University of Texas Department of Psychology Austin, TX 78712 512-232-4645 From carl at tuebingen.mpg.de Tue Feb 18 11:48:43 2003 From: carl at tuebingen.mpg.de (Carl Edward Rasmussen) Date: Tue, 18 Feb 2003 17:48:43 +0100 (CET) Subject: Openings at the Max Plank Institute for Biological Cybernetics Message-ID: Dear Colleagues: Several positions at various levels (corresponding to graduate student, Postdoc, assistant professor) are available in the Empirical Inference department at the Max Planck Institute in Tuebingen, Germany, studying learning theory and algorithms with applications in various domains. Faculty, current postdocs and visitors of the department include O. Bousquet, O. Chapelle, A. Elisseeff, G. Raetsch, C. Rasmussen, B. Schoelkopf, K. Tsuda, V. Vapnik, J. Weston, and A. Zien (see http://www.kyb.tuebingen.mpg.de/bs). We invite applications of candidates with an outstanding academic record including a strong mathematical or analytical background. In particular we seek people interested in kernel methods such as SVMs and Gaussian Processes, and inference in complex probabilistic models. Max Planck Institutes are publicly funded research labs with an emphasis on excellence in basic research. Tuebingen is a small university town in southern Germany, see http://www.tuebingen.de/kultur/english/index.html for some pictures. Inquiries and applications, including a CV, a statement of research interests and accomplishments should be should be sent, preferably before 10th March 2003, by email to carl at tuebingen.mpg.de or mail to: Carl Edward Rasmussen Max Planck Institute for Biological Cybernetics Spemannstr. 38 72076 Tuebingen Germany Tel. +49 7071 601 556 Fax +49 7071 601 552 In addition, two letters of reference should be sent by mail directly from the referees to the address above. From jms at isep.ipp.pt Wed Feb 19 02:57:24 2003 From: jms at isep.ipp.pt (Jorge M. Santos) Date: Wed, 19 Feb 2003 07:57:24 -0000 Subject: SUMMER SCHOOL ON NEURAL NETWORKS - NN2003 - First announcement Message-ID: <000f01c2d7ec$8b9bea60$1101a8c0@mat.isep.ipp.pt> We appreciate if you can forward this Announcement to your Colleagues, Professors, Students or Mailing lists. ----------------------------------------------------------------------- P L E A S E C I R C U L A T E We apologize if you receive this announcement more than once. -------------------------------------------------------------------------= FIRST ANNOUNCEMENT ************************************************* SUMMER SCHOOL ON NEURAL NETWORKS in SUPERVISED CLASSIFICATION, REGRESSION and DATA MINING July 7-11, 2003, ISEP - Porto, Portugal ************************************************* Web page: http://www.nn.isep.ipp.pt GENERAL INFORMATION The Summer School will be held at Porto, Portugal, jointly organized by the Polytechnic School of Engineering of Porto (ISEP) and the Faculty of Engineering, Porto University (FEUP). Following the considerable success reached by the NN2002 Summer School, the NN2003 edition includes lectures addressing new advances both in NN paradigms and in applications. It will run in parallel sessions allowing each participant to tailor the school to his/her own interest. COURSE CONTENTS Neural networks (NN) have become a very important tool in classification and regression tasks. The applications are nowadays abundant, e.g. in = the engineering, economy and biology areas. The Summer School on NN is dedicated to explain relevant NN paradigms, namely multilayer = perceptrons (MLP), radial basis function networks (RBF), support vector machines=20 (SVM) and entropy-based networks (ENN) used for classification and regression tasks, illustrated with applications to real data. Specific topics are also presented, namely genetic algorithms (GA) and NN, decision trees = and NN, co-operative structures of NN, time series analysis with NN and data mining using NN. Classes include practical sessions with appropriate software tools. The trainee has, therefore, the opportunity to apply the taught concepts and become conversant with a broad range of NN topics and applications. Official language will be English. TARGET AUDIENCE Graduates and researchers interested in applying Neural networks to = their professional activity and as a research tool. PROGRAMME COMMITTEE - Darrell Whitley (Professor, Dept. of Computer Science, Colorado = State University, USA) - Fernando Sereno (Assistant Professor, High School of Education, Portugal) - Jo=E3o Gama (Assistant Professor, Faculty of Economy, University of Porto, Portugal) - Joaquim Marques de S=E1 (Associate Professor, Dept. Electr. and Comp. Engineering; Fac. of Engineering, University of Porto, Portugal) - Jos=E9 Carlos Pr=EDncipe (BellSouth Professor, Director Computational NeuroEngineering, University of Florida, USA) - Lu=EDs Torgo (Assistant Professor, Faculty of Economy, University of Porto, Portugal) - Mark J. Embrechts (Associate Professor, Decision Sciences and Engineering Systems Faculty, Rensselaer Polytechnic Institute, Troy, N.Y., USA) - Mohamed Kamel (Professor, Dept. of Systems Design Engineering, University of Waterloo, Ontario, Canada) - Paulo Cort=EAs (Assistant Professor, University of Minho, Portugal) - Pavel Brazdil (Full Professor, Faculty of Economy, University of = Porto, Portugal) - Steve R. Gunn (Senior Lecturer, Dept. of Electronics and Computer Science, University of Southampton, UK) LOCAL ORGANIZING COMMITTEE (LOC) - Vitor Costa - Assistant Professor, Dept. Mathematics, ISEP, Portugal - J. Paulo Meixedo - Assistant, Dept. Mathematics, ISEP, Portugal - Jorge M. Santos - Assistant, Dept. Mathematics, ISEP, Portugal PRELIMINARY PROGRAMME A preliminary programme (including invited lecturers) and further informations about the classes are available at the school webpage. (http://www.nn.isep.ipp.pt) SCHOOL LOCATION The city of Porto will host the event, with the meeting being organized=20 by ISEP in collaboration with FEUP. Porto is Portugal's second largest = city, having been classified by UNESCO as World Heritage for its old town=20 centre at river Douro side. It is the administrative centre of Northern of Portugal, worldwide renown for its Port Wine Cellars. Porto has an international airport, with connections to all major European airports. All other public transports (train, bus, etc) can also be used to reach Porto. It has an extensive network of buses and a tram, which makes it very easy to stroll around the town, and train and bus connections to=20 many tourist attractions in the region. Lisbon is three hours away by train, and all other major Portuguese cities can be easily reached either by = car or by train. Important note: Visa may be required for citizens of = several European and overseas countries. Please contact your local Portuguese Consulates beforehand (typically no less than one month in advance). REGISTRATION Please find the registration form available at the WWW site of the conference. Please fill at your earlier convenience the registration form and send it to the LOC. NOTE: Special prices will be offered to those whom attended the NN2002. The registration fee for participants amounts to: - Early registration fee (payed before the 15th of May) * 300 Euro (students, ISEP and FEUP staff, and APPIA members) and to * 350 Euro (all other participants) - Late registration fee (payed after the 15th of May) * 350 Euro (students, ISEP and FEUP staff, and APPIA members) and to * 400 Euro (all other participants) The registration fee includes: * school package * coffee breaks * daily lunch * welcome reception * school banquet All participants are required to register prior to the start of the School - until the 15th of May - even if you choose to pay the late registration fee at the registration desk. Please note that the number of participants is limited, so it is conceivable that the late registration period will effectively be shorter than advertised. ACCOMMODATION The detailed procedure on how to book accommodation will be announced later. FINANCIAL ASSISTANCE Special consideration will be taken to secure some support for students and colleagues from Central and Eastern Europe. However, in the best possible case, this support will only be partial. Please check the next announcement or the School webpage. SOCIAL PROGRAMME Details on the Social and Cultural Programme for NN-2003 will be=20 announced later. CONTACT ADDRESS LOC - Summer School NN-2003 Departamento de Matem=E1tica Instituto Superior de Engenharia do Porto Rua Dr. Ant=F3nio Bernardino de Almeida 431 4200-072 PORTO / PORTUGAL Email: nn-2003 at isep.ipp.pt Programme Chair: Prof. Marques de S=E1 Tel. 225081828 - Email: jmsa at fe.up.pt From: esann To: "'Connectionists at cs.cmu.edu'" References: From bogus@does.not.exist.com Wed Feb 19 07:33:26 2003 From: bogus@does.not.exist.com () Date: Wed, 19 Feb 2003 13:33:26 +0100 Subject: ESANN'2003 programme ( European Symposium on Artificial Neural Networks) Message-ID: ---------------------------------------------------- | | | ESANN'2003 | | | | 11th European Symposium | | on Artificial Neural Networks | | | | Bruges (Belgium) - April 23-24-25, 2003 | | | | Preliminary programme | ---------------------------------------------------- The preliminary programme of the ESANN'2003 conference is now available on the Web: http://www.dice.ucl.ac.be/esann For those of you who maintain WWW pages including lists of related ANN sites: we would appreciate if you could add the above URL to your list; thank you very much! We try as much as possible to avoid multiple sendings of this call for papers; however please apologize if you receive this e-mail twice, despite our precautions. For 11 years the ESANN conference has become a major event in the field of neural computation. ESANN is a human-size conference focusing on fundamental aspects of artificial neural networks (theory, models, algorithms, links with statistics, data analysis, biological background,...). This year, 84 scientific communications will be presented, covering most areas of the neural computation field. The programme of the conference can be found at the URL http://www.dice.ucl.ac.be/esann, together with practical information about the conference venue, registration,... Other information can be obtained by sending an e-mail to esann at dice.ucl.ac.be . ======================================================== ESANN - European Symposium on Artificial Neural Networks http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews,... Michel Verleysen Univ. Cath. de Louvain - Microelectronics Laboratory 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at dice.ucl.ac.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at dice.ucl.ac.be ======================================================== From H.Bowman at ukc.ac.uk Wed Feb 19 09:30:41 2003 From: H.Bowman at ukc.ac.uk (hb5) Date: Wed, 19 Feb 2003 14:30:41 +0000 Subject: Job in Computational Modelling of Cognition Message-ID: <3E539511.6C592086@ukc.ac.uk> RESEARCH ASSOCIATE IN COMPUTATIONAL MODELLING OF COGNITION (R03/15) Research IA scale : 20,311-27,339 pounds p.a. Applications are invited for a Postdoctoral Research Associate post at the University of Kent at Canterbury, UK, to work on an EPSRC funded project entitled "Computational Modelling of Salience Sensitive Control in Humans and Artificial Systems" (details of which can be found on the following web-page, http://www.cs.ukc.ac.uk/people/staff/hb5/attention.html). The project is a collaboration with the Medical Research Council's Cognition and Brain Sciences Unit in Cambridge. The objective of the research is to construct computational models of the time course of human attention. This will particularly focus on simulating data arising from ongoing empirical studies of the Attentional Blink and the Psychological Refactory Period, which are being carried out at the Cognition and Brain Sciences Unit. A diverse set of modelling notations will be employed including neural networks, temporal logic and process algebra. These models will not only increase our understanding of human attention, they will also allow us to construct computer interfaces that are more sensitive to the human user and to develop robots that perform more effectively in dynamically changing environments. Applicants should have or should be in the process of finishing a PhD. Due to the cross disciplinary nature of the research, a suitable candidate could have studied in any of the following areas: Cognitive Psychology, Cognitive Neuroscience, Artificial Intelligence, Computer Science, Electronics, Physics, etc. Most importantly though we seek an applicant who is open to cross-disciplinary influences. The skills that will be employed in the research project are diverse, and include, - Connectionist modelling of cognitive processes. - An understanding of the human perception and attention systems. - Formal specification techniques, as employed in computer science, such as process algebra and temporal logic. - Expertise in robotics and human computer interaction. Due to the diverse nature of this skill set, it is very unlikely that we will find a single candidate that combines all these skills, consequently a candidate with even a small subset of these skills is still encouraged to apply. The post is available from 1 June 2003 for a period of 3 years. Further particulars and an Equal Opportunities Monitoring Form can be downloaded here: http://www.ukc.ac.uk/registry/personnel/vacancies/research.html#r0315 Alternatively you can telephone the Personnel Office for further particulars and application details on +44-(0)1227 827837 (24 hours) or e-mail: personnel at ukc.ac.uk quoting Ref. No.R03/15. Text phone users please telephone +44-(0)1227 824145. Informal enquires can be directed to Dr Howard Bowman (H.Bowman at ukc.ac.uk). Further details about the Computer Science Department can be found at http://www.cs.ukc.ac.uk/ Closing date for applications: 12 noon Friday 14 March 2003 From kdharris at andromeda.rutgers.edu Wed Feb 19 17:55:56 2003 From: kdharris at andromeda.rutgers.edu (Ken Harris) Date: Wed, 19 Feb 2003 17:55:56 -0500 Subject: Announcing KlustaKwik 1.5 Message-ID: Dear Connectionists I am pleased to announce the release of version 1.5 of KlustaKwik, a program for fast automatic clustering using a mixture of Gaussians model. It can be downloaded from http://osiris.rutgers.edu/Buzsaki/software. Further details follow below. Best regards, Ken Harris. ----------------------------------------------- KlustaKwik is a program for unsupervised classification of multidimensional continuous data. It arose from a specific need - automatic sorting of neuronal action potential waveforms (see KD Harris et al, Journal of Neurophysiology 84:401-414,2000), but works for any type of data. We needed a program that would: 1) Fit a mixture of Gaussians with unconstrained covariance matrices 2) Automatically choose the number of mixture components 3) Be robust against noise 4) Reduce the problem of local minima 5) Run fast on large data sets (up to 100000 points, 48 dimensions) Speed in particular was essential. KlustaKwik is based on the CEM algorithm of Celeux and Govaert (which is faster than the standard EM algorithm), and also uses several tricks to improve execution speed while maintaining good performance. On our data, it runs at least 10 times faster than Autoclass. The main improvement in version 1.5 is a cluster splitting feature. KlustaKwik allows for a variable number of clusters to be fit, penalized by AIC. The program periodically checks if splitting any cluster would improve the overall score. It also checks to see if deleting any cluster and reallocating its points would improve overall score. The splitting and deletion features allow the program to often escape from local minima, reducing sensitivity to the initial number of clusters, and reducing the total number of starts needed for a data set. From dgw at MIT.EDU Thu Feb 20 15:31:31 2003 From: dgw at MIT.EDU (David Weininger) Date: Thu, 20 Feb 2003 15:31:31 -0500 Subject: book announcement--Standish Message-ID: <200302201531313210@outgoing.mit.edu> I thought readers of the Connectionists List might be interested in this book. For more information, please visit http://mitpress.mit.edu/0262692813/ Thank you! Best, David Artifical Life VIII Proceedings of the Eighth International Conference on Artificial Life edited by Russell Standish, Mark A. Bedau, and Hussein A. Abbass The term "artificial life" describes research into synthetic systems that possess some of the essential properties of life. This interdisciplinary field includes biologists, computer scientists, physicists, chemists, geneticists, and others. Artificial life may be viewed as an attempt to understand high-level behavior from low-level rules--for example, how the simple interactions between ants and their environment lead to complex trail-following behavior. An understanding of such relationships in particular systems can suggest novel solutions to complex real-world problems such as disease prevention, stock-market prediction, and data mining on the Internet. Since their inception in 1987, the Artificial Life meetings have grown from small workshops to truly international conferences, reflecting the field's increasing appeal to researchers in all areas of science. Russell Standish is Director of the High Performance Computing Support Unit and Adjunct Associate Professor in the School of Mathematics at the University of New South Wales. Mark A. Bedau is Professor of Philosophy and Humanities at Reed College, Adjunct Professor of Systems Science at Portland State University, and Editor-in-Chief of the MIT Press journal Artificial Life. Hussein A. Abbass is Senior Lecturer and Director of the Artificial Life and Adaptive Robotics Lab, School of Computer Science, Australian Defense Force Academy, and Honorary Associate at the University of New England. 8 1/2 x 11, 504 pp., paper, ISBN 0-262-69281-3 Complex Adaptive Systems series A Bradford Book ______________________ David Weininger Associate Publicist The MIT Press 5 Cambridge Center, 4th Floor Cambridge, MA 02142 617 253 2079 617 253 1709 fax http://mitpress.mit.edu From rebollol at aston.ac.uk Fri Feb 21 09:59:12 2003 From: rebollol at aston.ac.uk (L REBOLLO-NEIRA) Date: Fri, 21 Feb 2003 14:59:12 +0000 Subject: postdoc Message-ID: RESEARCH ASSOCIATE: "Biorthogonal techniques for optimal signal representation". Starting salary 20.311 pounds pa (2 years and 7 months contract) Applications are invited for a Post Doctoral Research Associate to work on a EPSRC funded project. The project will focus on developing a framework for signal representation outside the traditional orthogonal basis setting. Further details on the research project can be found in http://www.ncrg.aston.ac.uk/Research.html by clicking on the link for "Biorthogonal techniques for optimal signal representation" Applicants should hold a PhD in Physics, Mathematics, Computer Science or related discipline. The work requires strong mathematical background and good computational skills. The successful candidate will have the opportunity to join the well established and internationally recognized research group NCRG http://www.ncrg.aston.ac.uk The post is tenable as soon as possible. Informal enquiries should be directed to Dr Laura Rebollo-Neira: rebollol at aston.ac.uk Further particulars and application forms may be obtained electronically on http://www.aston.ac.uk/hr/recruitment.htm or from Personnel Office on Tel (0) 121 359 0870 email b.a.power at aston.ac.uk quoting Ref R03/46/98. From deniz at cnel.ufl.edu Fri Feb 21 10:57:13 2003 From: deniz at cnel.ufl.edu (Deniz Erdogmus) Date: Fri, 21 Feb 2003 10:57:13 -0500 Subject: Deadline Reminder: IEEE-TNN Special Issue on Information Theoretic Learning References: <3E149939.72F07F4F@cnel.ufl.edu> Message-ID: <3E564C59.6616282B@cnel.ufl.edu> Dear Colleagues, This is a reminder for the upcoming special issue of the IEEE Transactions on Neural Networks on Information Theoretic Learning. The paper submission deadline is March 15, 2003. To see the call for papers or to submit a paper please visit the paper submission webpage at: http://www.cnel.ufl.edu/~tnn_itl/ Prospective authors can also register their intent by submitting only an abstract at the same website. -- Deniz Erdogmus, Ph.D. Post-doctoral Research Associate Computational NeuroEngineering Laboratory, EB 486 Electrical and Computer Engineering Department University of Florida Gainesville, FL 32611 Phone: 1-352-3922682 Fax: 1-352-3920044 http://www.cnel.ufl.edu/~deniz/ From P.J.Lisboa at livjm.ac.uk Fri Feb 21 19:37:47 2003 From: P.J.Lisboa at livjm.ac.uk (Lisboa, Paulo) Date: Sat, 22 Feb 2003 00:37:47 -0000 Subject: NNESMED/CIMED 2nd Call for Papers Message-ID: Dear Colleagues, A second and final call for papers has been issued for NNESMED/CIMED 2003, with the deadline for submissions extended until Friday 7th March. Submission information is listed in this message and full details about the conference may be found at the conference website http://www.shu.ac.uk/conference/nnesmed/. Paulo Lisboa. Fifth International Conference on Neural Networks and Expert Systems in Medicine and Healthcare and First International Conference on Computational Intelligence in Medicine and Healthcare, NNESMED/CIMED 2003. Sheffield Hallam University, 21-23 July, 2003. NNESMED and CIMED are focused on the application of intelligent computational methods and systems to support all areas of biomedical, clinical and healthcare practice, making it a strongly interdisciplinary conference, bringing together healthcare specialists, clinicians, biomedical engineers, computer scientists, communication and computer network engineers, and applied mathematicians. It traditionally follows a single-track format to ensure that all presentations, whatever the mode of delivery, are well attended. The language of the conference is English. SUBMISSION OF PAPERS Authors are requested to submit an extended abstract (two pages in length, single spaced) which includes the paper title, the authors' names, affiliations, e-mail and postal addresses, the name of the corresponding author and their telephone and fax numbers, a short summary of the abstract (for the website) and the extended abstract itself, by 7 March 2003. Extended abstracts should clearly identify the medical or healthcare context of the work, the methodology used, the advances made and the significance of the results. Extended abstracts should only concern significant work already completed. Extended abstracts on currently unfinished or future work should not be submitted. The material submitted must be original, and must neither have been published nor be under consideration for publication elsewhere. Papers will be accepted as either full session oral papers or as poster papers. The authors of poster papers will also be timetabled for a 4 minute oral presentation at the commencement of the poster session. The summaries of the extended abstracts accepted for the conference will be placed on the conference website. The text should be prepared in Word using font Times New Roman size 12 bold face for the title only, and size 10, not bold, for the rest of abstract. Authors should submit their abstracts as attachments to an e-mail sent to conference21 at shu.ac.uk . Authors without access to e-mail should post four copies to: Conference 21, Sheffield Hallam University, City Campus, Sheffield, S1 1WB, England. Authors whose abstracts are accepted will be asked to develop them into full camera-ready papers of 4-6 pages in length for inclusion in the conference proceedings. After the conference, selected papers will be recommended for expansion and submission to the International Journal "Artificial Intelligence in Medicine" (Elsevier Science, http://www.elsevier.com/locate/issn/09333657) or to the "Journal of Soft Computing" (Elsevier Science, http://www.elsevier.com/locate/asoc/), where they will undergo the usual review process. IMPORTANT DEADLINES * Submission of extended abstracts 7 March 2003 * Notification of provisional acceptance 31 March 2003 * Submission of full papers (camera ready) 18 April 2003 From Daniel.Herrmann at de.bosch.com Mon Feb 24 05:35:02 2003 From: Daniel.Herrmann at de.bosch.com (Herrmann Daniel (FV/FLD)) Date: Mon, 24 Feb 2003 11:35:02 +0100 Subject: phd-positions Message-ID: Please forward this information to your students: ----------------------------------------------------------------------- There will be soon some phd-positions available at the R&D Department for Microsystems of Robert Bosch GmbH in Stuttgart (Germany) on applications of kernel methods to design centering in MST, process monitoring etc. ----------------------------------------------------------------------- Bosch is one of leading suppliers in the automobile industry, see www.bosch.com. At moment the topic of the phd can be adapted to the background of the candidate. The contract lasts for three years and the salary is about 28.000 Euro. Please contact me for more information. With Regards / Mit freundlichen Gr??en Daniel Herrmann -------------------------------------------- Daniel Herrmann Robert Bosch GmbH, FV/FLD [R&D Microsystems] P.O. Box 10 60 50, D-70079 Stuttgart Germany Tel. +49-711 811 7563 Fax +49-711 811 269196 mailto:Daniel.Herrmann at de.bosch.com From gustavo.camps at uv.es Mon Feb 24 04:50:41 2003 From: gustavo.camps at uv.es (Gustavo Camps i Valls) Date: Mon, 24 Feb 2003 10:50:41 +0100 Subject: 2nd CfP: Special Session on ``Adaptive, Neural and Kernel Methods in Medicine''. Message-ID: <3E59EAF1.1647697A@uv.es> Dear collegues: I formally invite you to submit to the Special session entitled ``Adaptive, Neural and Kernel Methods in Medicine'' in the International Workshop on Artificial Neural Networks (IWANN) to be held June, 2003 in Balearic Islands, Spain. More information on the congress and the session can be found at http://62.204.199.18/iwann2003/ http://iwann.uned.es/ http://iwann.uned.es:9673/Sessions/ViewSession?id=38 Deadline: Feb, 28 2003 Scope: The aim of the workshop is to present state-of-the-art information processing tools in medicine applications. Adaptive systems, Artificial Neural Networks and kernel-based methods such as Support Vector Machines, Gaussian Processes, boosting-based approaches and Kernel PCA/ICA will be paid attention. The workshop aims to bring together a group of international researchers from machine learning and signal processing for discussing results and dissemination of ideas, with the objective of highlighting new research directions in health sciences, bioinformatics, medicine and biomedical engineering. Novel methods and application examples are wellcome. Look forward to seeing you there. Best regards, Gustavo Camps-Valls, PhD. -- _____________________________________________________________ Gustavo Camps-Valls - gcamps at uv.es Grup de Processament Digital de Senyals - http://gpds.uv.es/ Dpt. Enginyeria Electr?nica. Universitat de Val?ncia. Tlf.: +0034-(9)6-3160197 - Fax: +0034-(9)6-3160466 C/ Dr. Moliner, 50. 46100 - Burjassot (Val?ncia). Spain. Personal Web Page: http://www.uv.es/~gcamps _____________________________________________________________ From mpp at us.ibm.com Mon Feb 24 15:39:29 2003 From: mpp at us.ibm.com (Michael Perrone) Date: Mon, 24 Feb 2003 15:39:29 -0500 Subject: PhD Job Announcement: IBM Research Message-ID: The IBM TJ Watson Research Center has an immediate opening for a Ph.D. researcher in handwriting recognition. Details are below. Please apply at the following website: http://careers.peopleclick.com/jobposts/Client40_GLDTR/BU1/External/139-2294.htm?ShowReturn=Yes Regards, Michael Perrone IBM T.J. Watson Research Center 914-945-1779 __________________________________________________________________________ IBM Research Staff Member - Handwriting Recognition Job ID Job Category Job Level Location Travel Job Type K065368 Research Staff Experienced NY,Yorktown 0-20% Full-time Member Professional Heights Regular Job Details Generates highly novel ideas, evaluates them, plans, and is involved in their execution and implementation and/or invents and designs complex products and/or processes. Disseminates the results of such activities through publications, patent disclosures, seminar participation, internal documentation. Represents IBM at professional meetings, in professional societies, and universities. Keeps technically abreast of the literature. Functions as an internal consultant in the areas of prof. expertise and provides technical guidance. May direct technically, within the broad mission of the group, activities of other RSMs in the implementation of ideas for which he/she is primarily responsible. Assumes additional responsibilities as assigned. Requires a Ph.D. in mathematics, physics, engineering, or computer science. Requires demonstrated proficiency and/or potential in multimodal user interfaces, such as handwriting recognition and speech recognition. Required Skills C, C++, Java and XML programming. Statistics / Mathematics / Probability. Research experience in handwriting and/or Speech recognition. From m.usher at psychology.bbk.ac.uk Mon Feb 24 11:30:22 2003 From: m.usher at psychology.bbk.ac.uk (DR M USHER) Date: Mon, 24 Feb 2003 16:30:22 +0000 (GMT) Subject: PhD studentships Message-ID: Dear Collegues, I apologize in advance if you received this message more than once. Please bring this to the attention of relevant applicants. Sincerely, Marius Usher, PhD Reader in Psychology Birkbeck College, Univ. of London www.psyc.bbk.ac.uk/people/academic/usher_m I would like to encourage strong candidates (with solid background in experimental-psychology OR cognitive-science AND in computational methods) to apply for the following PhD studentship opportunities at the Birkbeck College. The School of Psychology, Birkbeck College, University of London offers supervision in Cognitive Sciences and Computational Cognitive Neuroscience. Birkbeck College is part of the University of London and is situated in the central Bloomsbury area of London. The research environment benefits from close proximity with the Institute of Cognitive Neuroscience, the Gatsby Computational Neurosciences Unit and the Institute of Child Health. The School of Psychology has a moderate sized dynamic, international postgraduate community that provides both a cutting edge and intimate environment for learning and research. Potential supervisors in the Computational Cognitive Neuroscience Lab: Richard Cooper (http://www.psyc.bbk.ac.uk/people/academic/cooper_r/) Models of executive processes and their disorders; relations between executive processes and lower-level processes; routine and non-routine action selection; monitoring and error correction; modeling tools and methodologies. Denis Mareschal (http://www.psyc.bbk.ac.uk/people/academic/mareshal_d/) Constructing and testing models of categorisation in infancy, statistical learning models of reasoning in children and infants. Michael Thomas (http://www.psyc.bbk.ac.uk/people/academic/thomas_m/) Modeling of language development in Williams Syndrome; current computational approaches to individual differences and intelligence; computational models of autism Marius Usher (http://www.psyc.bbk.ac.uk/people/academic/usher_m/) Computational and behavioural studies of verbal short-term memory, language, reasoning and individual and age differences; choice and decision making; visual short-term memory for single and bound visual features; psychophysical studies of temporal interactions in grouping. For more information on the CCN lab see http://www.psyc.bbk.ac.uk/research/comp/index.html/ Financial support is available on a competitive basis through EPSRC studentships and internal School of Psychology Studentships. The School of Psychology also has ESRC recognition. Further information can be obtained from: http://www.psyc.bbk.ac.uk/ For general inquiries email: s.daniel at psychology.bbk.ac.uk. For specific inquiries, email one of the potential supervisors. From maki at cslab.kecl.ntt.co.jp Mon Feb 24 23:14:47 2003 From: maki at cslab.kecl.ntt.co.jp (Shoji Makino) Date: Tue, 25 Feb 2003 13:14:47 +0900 Subject: One month before ICA2003 in Nara, JAPAN, April 1-4, 2003 Message-ID: <4.0.1-J.20030225131136.029bfe50@earth> Dear All, We have one month before the ICA2003 (Fourth International Symposium on Independent Component Analysis and Blind Signal Separation) will be held in April 1-4, 2003, Nara, Japan. It will be held just before ICASSP2003 in April 6-10, Hong Kong. The ICA2003 Book of Abstract is now posted on our web site: http://ica2003.jp/. Get all of the information you need to plan your trip from our web site. Conference registration will be closed shortly, so register now. April is a cherry blossom season and hotels are very crowded. We recommend you to book your hotel as soon as possible. See you soon in Nara, the city with a World Heritage history. Best regards, General chair: Shun-ichi Amari Organizing chair: Shoji Makino Program chairs: Andrzej Cichocki Noboru Murata From auke.ijspeert at epfl.ch Tue Feb 25 03:12:05 2003 From: auke.ijspeert at epfl.ch (Auke Ijspeert) Date: Tue, 25 Feb 2003 09:12:05 +0100 Subject: Java applet: Neuromechanical simulation of salamander locomotion Message-ID: <3E5B2555.7050209@epfl.ch> People interested in the neural control of locomotion might be interested in a Java applet that we recently developed of a neuromechanical simulation of salamander locomotion. The applet can be tested on the following page: http://lslwww.epfl.ch/birg/ (cf the Salamander Java applet link). The project investigates the control of locomotion in salamander, and the transition from swimming to walking during vertebrate evolution. We study whether neural controllers for swimming similar to those of the lamprey can be extended to control both the swimming and walking of the salamander, and the gait transition between these two modes. The salamander is believed to be one of the modern tetrapods closest to the first vertebrate having made the transition from aquatic to terrestrial habitats during evolution. Using a neuromechanical simulation of the salamander, i.e. a simulation which combines a mechanical model of the body and a neural network model of the locomotor central pattern generator, we investigate several organizations of neural networks capable of producing, and switching between, the typical swimming and walking gaits of the salamander. Comments and feedback are welcome. Best regards, Auke Ijspeert and Sebastien Catherinet Ps: More details concerning the simulation can be found in the following paper: Ijspeert A.J.: A connectionist central pattern generator for the aquatic and terrestrial gaits of a simulated salamander, Biological Cybernetics, Vol. 84:5, 2001, pp 331-348 -- ----------------------------------------------------------------- Dr Auke Jan Ijspeert SNF (Swiss National Science Foundation) Assistant Professor School of Computer and Communication Sciences EPFL, Swiss Federal Institute of Technology, Lausanne CH 1015 Lausanne, Switzerland Office: INN 241 Tel: +41 21 693 2658, Fax: +41 21 693 3705 www: http://lslwww.epfl.ch/birg Email: Auke.Ijspeert at epfl.ch Adjunct Assistant Professor, Department of Computer Science, University of Southern California ----------------------------------------------------------------- From l.wiskott at biologie.hu-berlin.de Tue Feb 25 07:34:23 2003 From: l.wiskott at biologie.hu-berlin.de (Laurenz Wiskott) Date: 25 Feb 2003 12:34:23 -0000 Subject: paper available: model of complex cells in V1 Message-ID: <20030225123423.26473.qmail@huxley.biologie.hu-berlin.de> SLOW FEATURE ANALYSIS YIELDS A RICH REPERTOIRE OF COMPLEX-CELL PROPERTIES by Pietro Berkes and Laurenz Wiskott Abstract: In this study, we investigate temporal slowness as a learning principle for receptive fields using slow feature analysis, a new algorithm to determine functions that extract slowly varying signals from the input data. We find that the learned functions trained on image sequences develop many properties found also experimentally in complex cells of primary visual cortex, such as direction selectivity, non-orthogonal inhibition, end-inhibition and side-inhibition. Our results demonstrate that a single unsupervised learning principle can account for such a rich repertoire of receptive field properties. Available from: http://cogprints.ecs.soton.ac.uk/archive/00002785/ Reference: Berkes, P. and Wiskott, L. (2003). Slow feature analysis yields a rich repertoire of complex-cell properties. Cognitive Sciences EPrint Archive (CogPrint) 2785, http://cogprints.ecs.soton.ac.uk/archive/00002785/, (). Additional Information: http://itb.biologie.hu-berlin.de/~wiskott/Projects/SFA-ReceptiveFields.html -- Dr. Laurenz Wiskott, Institute for Theoretical Biology, Berlin http://itb.biologie.hu-berlin.de/~wiskott/ l.wiskott at biologie.hu-berlin.de From geoff at cns.georgetown.edu Thu Feb 27 20:48:26 2003 From: geoff at cns.georgetown.edu (geoff@cns.georgetown.edu) Date: Thu, 27 Feb 2003 20:48:26 -0500 Subject: Postdoc position available Message-ID: <200302280148.h1S1mQO12337@newk.cns.georgetown.edu> POSTDOC IN MODELS OF RETINOTECTAL MAP FORMATION Geoff Goodhill Dept of Neuroscience Georgetown University Medical Center Washington DC A postdoctoral position is now available in my lab for an NIH-funded project to develop new theoretical models of retinotectal map formation. This project is a collaboration with John Flanagan at Harvard University (http://cellbio.med.harvard.edu/faculty/flanagan). The goal is to understand the initial activity-independent mechanisms by which axons find their targets in the tectum, and the models will be closely tied to current experimental data regarding Eph/ephrin gradients. A list of relevant papers can be found below. To apply, send a CV, a letter of interest, and names and addresses (including email) of at least two referees to: Geoffrey J Goodhill, PhD Associate Professor, Department of Neuroscience Georgetown University Medical Center 3900 Reservoir Road NW, Washington DC 20007 Tel: (202) 687 6889, Fax: (202) 687 0617 Email: geoff at georgetown.edu Homepage: cns.georgetown.edu Review of applications will start immediately and continue until the position is filled. Some relevant papers: Goodhill, G.J. & Richards, L.J. (1999). Retinotectal maps: molecules, models, and misplaced data. Trends in Neurosciences, 22, 529-534. http://cns.georgetown.edu/~geoff/pub/goodhill_richards_99.pdf Goodhill, G.J. (2002). Development of retinotectal maps, in ``The Handbook of Brain Theory and Neural Networks'', 2nd edition, ed. Michael Arbib, MIT Press, 335-339. Feldheim DA, Kim YI, Bergemann AD, Frisen J, Barbacid M, Flanagan JG. (2000). Genetic analysis of ephrin-A2 and ephrin-A5 shows their requirement in multiple aspects of retinocollicular mapping. Neuron, 25, 563-574. Goodhill, G.J. (2000). Dating behavior of the retinal ganglion cell. Neuron, 25, 501-503. [Comment on the Flanagan article above] http://cns.georgetown.edu/~geoff/pub/goodhill_neuron_00.pdf From terry at salk.edu Sat Feb 1 18:50:20 2003 From: terry at salk.edu (Terry Sejnowski) Date: Sat, 1 Feb 2003 15:50:20 -0800 (PST) Subject: Telluride Workshop deadline Message-ID: <200302012350.h11NoK596876@purkinje.salk.edu> ------------------------------------------------------------------------ NEUROMORPHIC ENGINEERING WORKSHOP Sunday, JUNE 29 - Saturday, JULY 19, 2003 TELLURIDE, COLORADO http://www.ini.unizh.ch/telluride/ ------------------------------------------------------------------------ Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Timmer HORIUCHI (Johns Hopkins University) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Christof KOCH (California Institute of Technology) Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) ------------------------------------------------------------------------ We invite applications for the annual three week "Telluride Workshop and Summer School on Neuromorphic Engineering" that will be held in Telluride, Colorado from Sunday, June 29 to Saturday, July 19, 2003. The application deadline is FRIDAY, MARCH 14, and application instructions are described at the bottom of this document. Like each of these workshops that have taken place since 1994, the 2002 Workshop and Summer School on Neuromorphic Engineering, sponsored by the National Science Foundation, the Whitaker Foundation, the Office of Naval Research, the Defence Advanced Research Projects Agency, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology, was an exciting event and a great success. We strongly encourage interested parties to browse through the previous workshop web pages located at: http://www.ini.unizh.ch/telluride For a discussion of the underlying science and technology and a report on the 2001 workshop, see the September 20, 2001 issue of "The Economist": http://www.economist.com/science/tq/displayStory.cfm?Story_ID=779503 GOALS: Carver Mead introduced the term "Neuromorphic Engineering" for a new field based on the design and fabrication of artificial neural systems, such as vision systems, head-eye systems, and roving robots, whose architecture and design principles are based on those of biological nervous systems. The goal of this workshop is to bring together young investigators and more established researchers from academia with their counterparts in industry and national laboratories, working on both neurobiological as well as engineering aspects of sensory systems and sensory-motor integration. The focus of the workshop will be on active participation, with demonstration systems and hands on experience for all participants. Neuromorphic engineering has a wide range of applications from nonlinear adaptive control of complex systems to the design of smart sensors, vision, speech understanding and robotics. Many of the fundamental principles in this field, such as the use of learning methods and the design of parallel hardware (with an emphasis on analog and asynchronous digital VLSI), are inspired by biological systems. However, existing applications are modest and the challenge of scaling up from small artificial neural networks and designing completely autonomous systems at the levels achieved by biological systems lies ahead. The assumption underlying this three week workshop is that the next generation of neuromorphic systems would benefit from closer attention to the principles found through experimental and theoretical studies of real biological nervous systems as whole systems. FORMAT: The three week summer school will include background lectures on systems neuroscience (in particular learning, oculo-motor and other motor systems and attention), practical tutorials on analog VLSI design, small mobile robots (Koalas, Kheperas, LEGO robots, and biobugs), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, the majority of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control * central pattern generator * robotics * swarm robotics * multichip communication * analog VLSI * learning The active perception project group will emphasize vision and human sensory-motor coordination. Issues to be covered will include spatial localization and constancy, attention, motor planning, eye movements, and the use of visual motion information for motor control. The central pattern generator group will focus on small walking and undulating robots. It will look at characteristics and sources of parts for building robots, play with working examples of legged and segmented robots, and discuss CPG's and theories of nonlinear oscillators for locomotion. It will also explore the use of simple analog VLSI sensors for autonomous robots. The robotics group will use rovers and working digital vision boards as well as other possible sensors to investigate issues of sensorimotor integration, navigation and learning. The audition group aims to develop biologically plausible algorithms and aVLSI implementations of specific auditory tasks such as source localization and tracking, and sound pattern recognition. Projects will be integrated with visual and motor tasks in the context of a robot platform. The multichip communication project group will use existing interchip communication interfaces to program small networks of artificial neurons to exhibit particular behaviors such as amplification, oscillation, and associative memory. Issues in multichip communication will be discussed. This year we will also have *200* biobugs, kindly donated by the WowWee Toys division of Hasbro in Hong Kong. B.I.O.-Bugs, short for Bio-mechanical Integrated Organisms, are autonomous creatures, each measuring about one foot and weighing about one pound (www.wowwee.com/biobugs/biointerface.html). This will permit us to carry out experiments in collective/swarm robotics. LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350 miles). Great Lakes Aviation and America West Express airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do NOT rent a car. Bring hiking boots, warm clothes, rain gear and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around mid April 2003. Participants are expected to pay a $275.00 workshop fee at that time in order to reserve a place in the workshop. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. Travel reimbursement of up to $500 for US domestic travel and up to $800 for overseas travel will be possible if financial help is needed (Please specify on the application). HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e., postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage qualified women and minority candidates to apply. Application should include: * First name, Last name, Affiliation, valid e-mail address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Description of demonstrations that could be brought to the workshop. * Two letters of recommendation Complete applications should be sent to: Terrence Sejnowski The Salk Institute 10010 North Torrey Pines Road San Diego, CA 92037 e-mail: telluride at salk.edu FAX: (858) 587 0417 APPLICATION DEADLINE: MARCH 14, 2003 From terry at salk.edu Mon Feb 3 13:44:39 2003 From: terry at salk.edu (Terry Sejnowski) Date: Mon, 3 Feb 2003 10:44:39 -0800 (PST) Subject: NEURAL COMPUTATION 15:3 In-Reply-To: <200301152207.h0FM7QD79176@purkinje.salk.edu> Message-ID: <200302031844.h13IidS98237@purkinje.salk.edu> Neural Computation - Contents - Volume 15, Number 3 - March 1, 2003 ARTICLE Synchronization in Networks of Excitatory and Inhibitory Neurons with Sparse, Random Connectivity Christoph Borgers and Nancy Kopell NOTES The Effects of Input Rate and Synchrony on a Coincidence Detector: Analytical Solution Shawn Mikula and Ernst Niebur A Theoretical Model of Axon Guidance By the Robo Code Geoffrey Goodhill LETTERS Spike-Driven Synaptic Dynamics Generating Working Memory States Daniel J. Amit and Gianluigi Mongillo A Stochastic Method to Predict the Consequence of Arbitrary Forms of Spike-Timing-Dependent Plasticity Hideyuki Cateau and Tomoki Fukai Permitted and Forbidden Sets in Symmetric Threshold-Linear Networks Richard H.R. Hahnloser, H. Sebastian Seung and Jean-Jacques Slotine Multistability Analysis for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions Zhang Yi, K. K. Tan and T. H. Lee Simple-Cell-Like Receptive Fields Maximize Temporal Coherence in Natural Video Jarmo Hurri and Aapo Hyvarinen Continuous-Time Symmetric Hopfield Nets Are Computationally Universal Jiri Sima and Pekka Orponen ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2003 - VOLUME 15 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $95 $101.65 $143 Institution $590 $631.30 $638 * 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 dayan at gatsby.ucl.ac.uk Mon Feb 3 11:46:21 2003 From: dayan at gatsby.ucl.ac.uk (Peter Dayan) Date: Mon, 3 Feb 2003 16:46:21 +0000 Subject: Faculty position: Gatsby Computational Neuroscience Unit Message-ID: <20030203164620.A18789@miller.gatsby.ucl.ac.uk> The Gatsby Computational Neuroscience Unit is looking to recruit a lecturer (roughly equivalent to an assistant professor). We seek someone with interests from across the range of theoretical neuroscience and machine learning that would complement and bolster our existing strengths in neural representation, neural computation, and foundational and applied aspects of learning and Bayesian statistics. There is also the opportunity to run a human psychophysics lab in the service of testing theories. Remuneration will be at a level appropriate to the international standing of the successful candidate. The Gatsby Unit was set up at University College London as a research institute devoted to computational neuroscience and machine learning. We have core funding for four faculty, five postdocs and around ten PhD students. We have no undergraduate programme, so only graduate-level teaching is required. We are located in Queen Square, London, in close proximity to the Institutes of Neurology and Cognitive Neuroscience and the Functional Imaging Lab, and also have close ties with the Departments of Anatomy, Computer Science, Psychology, Physiology and Statistics at UCL and with groups in Physics and Experimental Psychology at Cambridge and beyond. Applications, including a CV, a statement of research interests and accomplishments and full contact details for three referees should be sent by 14th March 2003 by email to Alexandra Boss at alexandra at gatsby.ucl.ac.uk, or by mail to her at Gatsby Computational Neuroscience Unit, UCL, Alexandra House, 17 Queen Square, London WC1N 3AR, UK. For further information, please see www.gatsby.ucl.ac.uk or contact Peter Dayan at dayan at gatsby.ucl.ac.uk From robbie at bcs.rochester.edu Tue Feb 4 10:51:23 2003 From: robbie at bcs.rochester.edu (Robert Jacobs) Date: Tue, 04 Feb 2003 10:51:23 -0500 Subject: 5 postdoc positions available Message-ID: <5.1.1.6.0.20030204104911.02e45d30@bcs.rochester.edu> A non-text attachment was scrubbed... Name: not available Type: multipart/alternative Size: 2765 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/00000000/d8710521/attachment-0001.bin From canete at ctima.uma.es Tue Feb 4 06:40:39 2003 From: canete at ctima.uma.es (=?iso-8859-1?Q?Javier_Fern=E1ndez_de_Ca=F1ete?=) Date: Tue, 4 Feb 2003 12:40:39 +0100 Subject: EANN'2003. Second CALL FOR PAPERS. Message-ID: <002101c2cc42$468dc840$836dd696@isa.uma.es> Dear colleague: This is a "one month submission reminder" to all interested individuals that the deadline for submitting extended abstracts to the conference on Engineering Applications on Neural Networks 2003 (EANN'03) is February 28, 2003. This conference will be held at the beautiful "Melia Torremolinos Hotel" at Torremolinos, Costa del Sol, SPAIN, from 8 to 10 September 2003. All information regarding this conference can be found on our website at http://www.isa.uma.es/eann03 Please refer to this website for formatting and submission requirements. If you have any questions about the conference, please feel free to contact me at eann03 at ctima.uma.es Hoping to seeing you at EANN'03 With regards Javier Fernandez de Canete Prof. Javier Fernandez de Canete, Ph. D. EANN2003 Conference Secretariat E.T.S.I. Informatica Universidad de Malaga Campus de Teatinos s/n 29071 Malaga SPAIN Phone: +34-95-2132887 Fax: +34-95-2133361 e_mail: canete at ctima.uma.es From bogus@does.not.exist.com Wed Feb 5 07:34:35 2003 From: bogus@does.not.exist.com () Date: Wed, 5 Feb 2003 12:34:35 -0000 Subject: Professorship in Neuromorphic Computing Systems Message-ID: <736F0925D69F9941B3BA8AEED0F5E75C5F406B@02-CSEXCH.uopnet.plymouth.ac.uk> Please post and circulate (apologies for cross listings) Professorship in Neuromorphic Computing Systems University of Plymouth, UK The University of Plymouth is currently seeking to make new Professorial appointments in the Computing discipline within the Faculty of Technology. Outstanding candidates are sought in a number of specialist areas, and candidates whose specialist expertise is in neuromorphic computing systems, in particular in vision, audition or sensory-motor systems, are hereby invited to apply. Such candidates will be encouraged to work closely with other research groups in the Faculty, including the newly established Centre for Theoretical and Computational Neuroscience (see below for further details of this research Centre). Appointees will also be expected to contribute to the development of undergraduate and postgraduate programmes in computing within the Faculty of Technology, and to provide research leadership in their area. Candidates must have a substantial record of successful research and teaching experience, a strong publication record, and evidence of success in the acquisition of research grants. The University has also reserved certain specific Lectureships which will be associated with these positions and used to support research growth in the appointees' specialist areas. Potential applicants should initially contact, by email, Professor Mike Denham (mdenham at plymouth.ac.uk) in order to discuss their application. In this respect, it would be helpful if a brief curriculum vitae and an indication of research interests could be included with the initial email. Centre for Theoretical and Computational Neuroscience, University of Plymouth, UK This newly-established Centre specialises in the application of rigorous, quantitative approaches, including mathematical and computational modelling and psychophysics, to understanding information coding, processing, storage and transmission in the brain and its manifestation in perception and action. Areas of study include: visual and auditory perception and psychophysics; sensory-motor control, in particular oculomotor control; and mathematical and computational modelling of the cortical neural circuitry underlying perception, attention, learning and memory, and motor control. Academic staff in the Centre are: Prof Jochen Braun (vision); Dr Susan Denham (audition); Prof Chris Harris (sensory-motor control); Prof Roman Borisyuk (mathematical and computational modelling); Prof Mike Denham (mathematical and computational modelling). The Centre has a number of externally-funded research programmes and strong international links, including with the Institute of Neuroinformatics at ETH, Zurich, and the Koch laboratory at Caltech. It has a strong interest and is currently active in collaborating with researchers in the neuromorphic systems area, in particular in the implementation of the computational principles and models of neural processing it is investigating within artificial systems, in particular in vision, audition and sensory-motor systems. From mvanross at inf.ed.ac.uk Thu Feb 6 06:26:47 2003 From: mvanross at inf.ed.ac.uk (Mark van Rossum) Date: Thu, 6 Feb 2003 11:26:47 +0000 (GMT) Subject: PhD Studentships Neuroinformatics in Edinburgh UK Message-ID: 4 YEAR DOCTORAL TRAINING (PhD) IN NEUROINFORMATICS. UNIVERSITY OF EDINBURGH We invite applications for the PhD program in the newly established Edinburgh Doctoral Training Centre in Neuroinformatics. The programme is made up of 3 themes: 1) Computational and Cognitive Neurocience - analytical and computational modelling of the nervous system, visual processing, sensory coding. 2) Neuromorphic Engineering and Neural Computation - Artificial sensor perception and analysis, neuromorphic modelling, spiking computation and mixed-mode VLSI, evolutionary optimisation of physical systems, neurally inspired algorithms, neurorobotics. 3) Simulation, Analysis, Visualisation and Data Handling - software systems and computational techniques for neuroscience and neural engineering. The 4 year programme in Neuroinformatics consists of an introductory year of training in neuroscience, informatics techniques and smaller lab-based research projects, followed by 3 years of Ph.D. research study related to one of the above subjects. The programme has a strong interdiscplinary character and is ideal for students who want to apply their skills to neuroinformatics problems. Students with a strong background in computer science, electronics, mathematics, physics or engineering are particularly welcome to apply, but motivated students with other backgrounds will be considered as well. We will be accepting an average of 10 students a year. Students will be based initially in the Institute for Adaptive and Neural Computation in the School of Informatics, the UK's largest and highest-quality academic computer-science group. Edinburgh has a strong research community in all of the areas listed above and leads the UK in integrating these into a coherent programme in Neuroinformatics. Edinburgh has in the past been voted as 'best place to live in Britain', and has many exciting cultural and student activities. The stipend is set in the region of 10,000 pounds (15,000 Euros) in the first year and 13,000 pounds (20,000 Euros/Dollars) per annum in years 2-4. Full fees are paid. The studentships are available to UK students. Funding for EU students is currently unclear. Applicants who are not citizens or longstanding residents of EU countries will need to find their own funding. For full application details, and further information of areas of study at the Centre, consult the website: http://www.anc.ed.ac.uk/neuroinformatics or send email to neuroinformatics-phd at anc.ed.ac.uk Applications received by February 28th will receive priority treatment. Mark van Rossum ==== mvanross at inf.ed.ac.uk ===== http://homepages.inf.ed.ac.uk/mvanross From memory at cogs.nbu.bg Thu Feb 6 09:28:49 2003 From: memory at cogs.nbu.bg (CogSci Summer School) Date: Thu, 6 Feb 2003 16:28:49 +0200 Subject: Deadline approaching Message-ID: Advanced Interdisciplinary Workshop on Constructive Memory: Data and Models Sofia, New Bulgarian University, July 12-14, 2003 The aim of the workshop will be to challenge our current understanding of human memory by integrating data with theoretical and computational models and by bringing researchers from a variety of domains together. The workshop topics will include: * False Memory and Memory Illusions * Interaction between memory and reasoning, between memory and imagination * Autobiographical memory * Spatial Memory * Memory for Actions and Events * Memory for Faces and Objects * WM and constructive processes * Context-Sensitivity of Human Memory * Collective memory The workshop is deliberately interdisciplinary and will cover a variety of methods: * lab experiments * field studies * computer simulations * mathematical models * brain imaging * brain lesions The workshop program will consist of invited key speaker talks which will be challenged by discussants, short talks by regular participants, and numerous discussions and working groups. In parallel to the workshop an International Summer School in Cognitive Science will take place. Key talks * Jay McClelland (Carnegie Mellon University, USA) Emergence of Theory-like Knowledge from Experience: A Parallel-Distributed Processing Account * Elizabeth Loftus (University of Washington, USA) - False Memories and Other Mind Changes * Alan Baddeley (University of Bristol, UK) - Constructive Processes in Working Memory * Daniel Schacter (Harvard University, USA) - The Seven Sins of Memory: A Cognitive Neuroscience Perspective * Morris Moscovitch (University of Toronto, Canada) Remote Memory, Consolidation and Hippocampal-Neocortical Interaction: Evidence from the Laboratory and Clinic. * Robert Bjork and Elizabeth Bjork (University of California, Los Angeles, USA) - The Role of Retrieval-Induced Forgetting in the Construction and Distortion of Memories * Michael Anderson (University of Oregon, USA) - Inhibitory Processes and the Regulation of Awareness * Martin Conway (University of Durham, UK) & Amanda Barnier (University of New South Wales, Australia) - On the Accessibility of Autobiographical Memories: Shaping the Self * Johannes Engelkamp (Saarland University, Germany) - What is Special about Memory for Actions? * William Hirst (New School for Social Research, NY, USA) The Construction of a Collective Memory * Jeroen Raaijmakers (University of Amsterdam, The Netherlands) - Towards a General Theory of Human Memory * Boicho Kokinov (New Bulgarian University) - The AMBR Model of Episodic Memory Construction and Distortion: Interaction between Memory and Reasoning Call for Papers Potential participants are invited to submit papers in electronic form (MS Word or PDF format) for presentation during the workshop. The papers should be not longer than 10 single spaced pages, including tables, figures, references, and appendices and use Times New Roman Font size 10. The papers may address any of the topics described above. Interdisciplinary work is especially welcome. Priority will be given to papers that open up new issues, challenge the current understanding of human memory, present new models or data. Papers should be sent by April 1st 2003 to the following address: memory at cogs.nbu.bg Program Committee Michael Anderson (University of Oregon, USA) Alan Baddeley (University of Bristol, UK) Robert Bjork (University of California, Los Angeles, USA) Martin Conway (University of Durham, UK) Johannes Engelkamp (Saarland University, Germany) William Hirst (New School for Social Research, NY, USA) - Co-Chair Boicho Kokinov (New Bulgarian University) - Co-Chair Elizabeth Loftus (University of Washington, USA) Jay McClelland (Carnegie Mellon University, USA) Morris Moscovitch (University of Toronto, Canada) Jeroen Raaijmakers (University of Amsterdam, The Netherlands) Daniel Schacter (Harvard University, USA) For more information look at: http://www.nbu.bg/cogs/events/workshop.html Central and East European Center for Cognitive Science New Bulgarian University 21 Montevideo Str. Sofia 1618 phone: 955-75-18 e-mail: school at cogs.nbu.bg memory at cogs.nbu.bg Radostina Belcheva Administrative manager Central and East European Center for Cognitive Science Svetlana Petkova Administrative manager Central and East European Center for Cognitive Science From mm at cse.ogi.edu Thu Feb 6 14:43:48 2003 From: mm at cse.ogi.edu (Melanie Mitchell) Date: Thu, 6 Feb 2003 11:43:48 -0800 Subject: Faculty Positions at OGI School of Science and Engineering Message-ID: <15938.47860.698159.509423@sangre.cse.ogi.edu> I wanted to bring to your attention the following advertisement for faculty recruitment at OGI. Adaptive systems and machine learning is one of our specific target areas for hiring. OGI is putting significant resources into building a strong and diverse Laboratory for Adaptive Systems, and we expect to hire between two and four people in this area within the next five years. Our recent merger with the Oregon Health & Science University has opened up great opportunities for collaboration with researchers in biological and medical sciences, and our close proximity to the OHSU Neurological Sciences Institute has already resulted in collaborations between our respective faculties in the fields of neural modeling and neural computation. OGI's current adaptive systems faculty includes: Dan Hammerstrom: Biologically inspired computation, VLSI chip design, neural networks Marwan Jabri: Intelligent signal processing, biologically inspired control for robotics Todd Leen: Machine learning, local and mixture models, neurophysiological modeling Melanie Mitchell: Evolutionary computation, cognitive science, complex systems John Moody: Reinforcement learning, neural networks, time series analysis, data mining, computational finance Misha Pavel: Cognitive science, biologically inspired computation, biomedical engineering Xubo Song: Image processing, statistical pattern recognition Eric Wan: Neural networks, adaptive signal processing and control We are looking for outstanding individuals in any area of machine learning or adaptive systems to join our faculty. Please pass this on to anyone you think might be interested. --------------------------------------------------------------------------- Faculty Positions at the OGI School of Science and Engineering The Department of Computer Science and Engineering invites applications for faculty positions at all ranks. The current strengths of our department include graphics and visualization, adaptive systems and machine learning, databases and data mining, networking, programming languages, software systems, human-computer interaction, spoken language systems, software engineering, control, computer architecture, image processing, and applied formal methods and verification of both hardware and software. In addition to these areas, our target areas for hiring include bioinformatics and computational biology, security, mobile and embedded systems, real-time and reactive systems, high-performance computing, vision, robotics, and sensor fusion. While these are particular areas of interest, we will consider outstanding candidates in any area of computer science and engineering. Building on a shared commitment to excellence in graduate education and research, Oregon Graduate Institute of Science and Technology (OGI) merged with Oregon Health Sciences University (OHSU) on July 1, 2001. OGI now is the OGI School of Science and Engineering in the re-named Oregon Health & Science University (OHSU). The merger is enabling the CSE department to expand in core disciplines and establish strong interdisciplinary collaborations among researchers in information technology, health care, biomedical engineering, and environmental and biological sciences. Significant collaborations between OGI and OHSU have existed for 30 years. The typical teaching load in CSE is 2 graduate-level classes per year. Faculty receive contracts of 2-5 years duration, renewable annually with satisfactory academic performance. NSF, NIH and other federal research sponsors recognize OGI faculty appointments as being equivalent to tenured positions. OGI is located 12 miles west of Portland, Oregon, in the heart of the Silicon Forest. Portland's thriving high-tech community, extensive cultural amenities and spectacular natural surroundings combine to make the quality of life here extraordinary. To learn more about the department, OGI, OHSU and Portland, please visit www.cse.ogi.edu. To apply, send a brief description of your research interests, the names of at least three references, and a curriculum vitae with a list of publications to: Chair, Recruiting Committee Department of Computer Science and Engineering OGI School of Science and Engineering at OHSU 20000 NW Walker Road Beaverton, Oregon 97006 The email address for inquiries is: csedept at cse.ogi.edu. OGI/OHSU is an Equal Opportunity/Affirmative Action employer. We particularly welcome applications from women, minorities, and individuals with disabilities. From erik at bbf.uia.ac.be Tue Feb 4 12:40:15 2003 From: erik at bbf.uia.ac.be (Erik De Schutter) Date: Tue, 4 Feb 2003 18:40:15 +0100 Subject: CNS*03: FINAL CALL FOR PAPERS (changed deadline) Message-ID: FINAL CALL FOR PAPERS: SUBMISSION DEADLINE: February 23, 2003 midnight DEADLINE HAS BEEN EXTENDED BY ONE WEEK: We can now announce substantial travel grants for students traveling to the meeting plus reduced registration fees compared to last year. More info when the registration openslater this year. Twelfth Annual Computational Neuroscience Meeting CNS*2003 July 5 - July 9, 2003 Alicante, Spain http://www.neuroinf.org/CNS.shtml Info at cp at bbf.uia.ac.be CNS*2003 will be held in Alicante from Saturday, July 5, 2003 to Wednesday, July 9. The main meeting will be July 5 - 7 at the Hotel Meli=E1 (poster sessions) and at the CAM Cultural Center (oral presentations). The main meeting consists of 6 oral sessions (one each morning and afternoon) and 3 early evening poster sessions. Workshops will be held at the University Miguel Hern=E1ndez (Medical School Campus) July 8 - 9. New is that some workshops will be mini-symposia or tutorials, a list of currently planned workshops can be found at the website. The conference dinner will take place in the Santa B=E1rbara castle overlooking the city and the sea on Sunday, July 6. For tourist information see http://www.alicanteturismo.com, more specific practical information will be made available through the conference website. Papers can include experimental, model-based, as well as more abstract theoretical approaches to understanding neurobiological computation. We especially encourage papers that mix experimental and theoretical studies. We also accept papers that describe new technical approaches to theoretical and experimental issues in computational neuroscience or relevant software packages. The paper submission procedure is again completely electronic this year. There will not be any meeting announcement through surface mail, instead you find the meeting poster attached. PAPER SUBMISSION Papers for the meeting can be submitted ONLY through the web site at http://www.neuroinf.org/CNS.shtml Papers can be submitted either as a 1000 word summary or as a full paper (max 6 typeset pages). Full papers stand a better chance of being accepted for oral presentation. You will need to submit the paper in pdf format (if necessary Elsevier can help in converting your paper to pdf) and the 100 word abstract as text. You will also need to select two categories which describe your paper and which will guide the selection of reviewers. In addition we encourage you to also submit your paper to the Elsevier preprint server (http://www.computersciencepreprints.com). All submissions will be acknowledged by email. THE REVIEW PROCESS All submitted papers will be first reviewed by the program committee. Papers will be judged and accepted for the meeting based on the clarity with which the work is described and the biological relevance of the research. For this reason authors should be careful to make the connection to biology clear. We reject only a small fraction of the papers (~ 5%) and this usually based on absence of biological relevance (e.g. pure machine learning). We will notify authors of meeting acceptance before end of March. The second stage of review involves evaluation of submissions which requested an oral presentation by two independent referees. In addition to perceived quality as an oral presentation, the novelty of the research and the diversity and coherence of the overall program will be considered. To ensure diversity, those who have given talks in the recent past will not be selected and multiple oral presentations from the same lab will be discouraged. All accepted papers not selected for oral talks as well as papers explicitly submitted as poster presentations will be included in one of three evening poster sessions. Authors will be notified of the presentation format of their papers by begin of May. CONFERENCE PROCEEDINGS The proceedings volume is published each year as a special supplement to the journal Neurocomputing. In addition the proceedings are published in a hardbound edition by Elsevier Press. Only 200 papers will be published in the proceedings volume. If more than 200 papers are submitted (which is likely) the following rules will apply: each presenting author (who has to register for the meeting) can publish at most one paper in the proceedings book. In case of multi-author papers the same rule applies: one of the authors is considered presenting author and this person has to register at the meeting and cannot publish another paper. If more than 200 presenting authors wish to publish their papers in the proceedings volume the ranking based on the review process will be used to select the top 200 papers. Paper submissions to the conference proceedings are a process separate from the current call for papers: a new submission will need to be done in the early fall of 2003 for which authors will receive detailed instructions. For reference, papers presented at CNS*99 can be found in volumes 32-33 of Neurocomputing (2000), those of CNS*00 in volumes 38-40 (2001) and those of CNS*01 in volumes 44-46 (2002). INVITED SPEAKERS: Yang Dan (University of California Berkeley, USA) Peter Dayan (Gatsby Computational Neuroscience Unit, London, UK) Henry Markram (Brain Mind Institute Lausanne, Switzerland) ORGANIZING COMMITTEE: The CNS meeting is organized by the Computational Meeting Organization Program chair: Erik De Schutter (University of Antwerp, Belgium) Local organizer: Albert Compte (University Miguel Hern=E1ndez, Spain) Workshop organizer: Maneesh Sahani (University of California, San Francisco, USA) Government Liaison: Dennis Glanzman (NIMH/NIH, USA) and Yuan Liu (NINDS/NIH, USA) Program Committee: Upinder Bhalla (National Centre for Biological Sciences, India) Victoria Booth (New Jersey Institute of Technology, USA) Alain Destexhe (CNRS Gif-sur-Yvette, France) John Hertz (Nordita, Denmark) Bill Holmes (Ohio University, USA) Hidetoshi Ikeno (Himeji Institute of Technology, Japan) Barry Richmond (NIMH, USA) Eytan Ruppin (Tel Aviv University) Frances Skinner (University Toronto, Canada) From giacomo at ini.phys.ethz.ch Tue Feb 11 04:09:26 2003 From: giacomo at ini.phys.ethz.ch (Giacomo Indiveri) Date: Tue, 11 Feb 2003 10:09:26 +0100 Subject: Neuromorphic Engineering Workshop: SECOND CALL FOR APPLICATIONS Message-ID: <3E48BDC6.9010502@ini.phys.ethz.ch> Please post and distribute to collegues and friends http://www.ini.unizh.ch/telluride/announcement.html SECOND CALL FOR APPLICATIONS (sorry for cross-postings) ------------------------------------------------------------------------ NEUROMORPHIC ENGINEERING WORKSHOP Sunday, JUNE 29 - Saturday, JULY 19, 2003 TELLURIDE, COLORADO http://www.ini.unizh.ch/telluride/ ------------------------------------------------------------------------ Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Ralph ETIENNE-CUMMINGS (University of Maryland) Timmer HORIUCHI (University of Maryland) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Christof KOCH (California Institute of Technology) Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) ------------------------------------------------------------------------- We invite applications for the annual three week "Telluride Workshop and Summer School on Neuromorphic Engineering" that will be held in Telluride, Colorado from Sunday, June 29 to Saturday, July 19, 2003. The application deadline is FRIDAY, MARCH 14, and application instructions are described at the bottom of this document. Like each of these workshops that have taken place since 1994, the 2002 Workshop and Summer School on Neuromorphic Engineering, sponsored by the National Science Foundation, the Whitaker Foundation, the Office of Naval Research, the Defence Advanced Research Projects Agency, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology, was an exciting event and a great success. We strongly encourage interested parties to browse through the previous workshop web pages located at: http://www.ini.unizh.ch/telluride For a discussion of the underlying science and technology and a report on the 2001 workshop, see the September 20, 2001 issue of "The Economist": http://www.economist.com/science/tq/displayStory.cfm?Story_ID=779503 GOALS: Carver Mead introduced the term "Neuromorphic Engineering" for a new field based on the design and fabrication of artificial neural systems, such as vision systems, head-eye systems, and roving robots, whose architecture and design principles are based on those of biological nervous systems. The goal of this workshop is to bring together young investigators and more established researchers from academia with their counterparts in industry and national laboratories, working on both neurobiological as well as engineering aspects of sensory systems and sensory-motor integration. The focus of the workshop will be on active participation, with demonstration systems and hands on experience for all participants. Neuromorphic engineering has a wide range of applications from nonlinear adaptive control of complex systems to the design of smart sensors, vision, speech understanding and robotics. Many of the fundamental principles in this field, such as the use of learning methods and the design of parallel hardware (with an emphasis on analog and asynchronous digital VLSI), are inspired by biological systems. However, existing applications are modest and the challenge of scaling up from small artificial neural networks and designing completely autonomous systems at the levels achieved by biological systems lies ahead. The assumption underlying this three week workshop is that the next generation of neuromorphic systems would benefit from closer attention to the principles found through experimental and theoretical studies of real biological nervous systems as whole systems. FORMAT: The three week summer school will include background lectures on systems neuroscience (in particular learning, oculo-motor and other motor systems and attention), practical tutorials on analog VLSI design, small mobile robots (Koalas, Kheperas, LEGO robots, and biobugs), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, the majority of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control * central pattern generator * robotics * swarm robotics * multichip communication * analog VLSI * learning The active perception project group will emphasize vision and human sensory-motor coordination. Issues to be covered will include spatial localization and constancy, attention, motor planning, eye movements, and the use of visual motion information for motor control. The central pattern generator group will focus on small walking and undulating robots. It will look at characteristics and sources of parts for building robots, play with working examples of legged and segmented robots, and discuss CPG's and theories of nonlinear oscillators for locomotion. It will also explore the use of simple analog VLSI sensors for autonomous robots. The robotics group will use rovers and working digital vision boards as well as other possible sensors to investigate issues of sensorimotor integration, navigation and learning. The audition group aims to develop biologically plausible algorithms and aVLSI implementations of specific auditory tasks such as source localization and tracking, and sound pattern recognition. Projects will be integrated with visual and motor tasks in the context of a robot platform. The multichip communication project group will use existing interchip communication interfaces to program small networks of artificial neurons to exhibit particular behaviors such as amplification, oscillation, and associative memory. Issues in multichip communication will be discussed. This year we will also have *200* biobugs, kindly donated by the WowWee Toys division of Hasbro in Hong Kong. B.I.O.-Bugs, short for Bio-mechanical Integrated Organisms, are autonomous creatures, each measuring about one foot and weighing about one pound (www.wowwee.com/biobugs/biointerface.html). This will permit us to carry out experiments in collective/swarm robotics. LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350 miles). Great Lakes Aviation and America West Express airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do NOT rent a car. Bring hiking boots, warm clothes, rain gear and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around mid April 2003. Participants are expected to pay a $275.00 workshop fee at that time in order to reserve a place in the workshop. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. Travel reimbursement of up to $500 for US domestic travel and up to $800 for overseas travel will be possible if financial help is needed (Please specify on the application). HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e., postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage qualified women and minority candidates to apply. Application should include: * First name, Last name, Affiliation, valid e-mail address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Description of demonstrations that could be brought to the workshop. * Two letters of recommendation Complete applications should be sent to: Terrence Sejnowski The Salk Institute 10010 North Torrey Pines Road San Diego, CA 92037 e-mail: telluride at salk.edu FAX: (858) 587 0417 APPLICATION DEADLINE: MARCH 14, 2003 From Peter.Andras at newcastle.ac.uk Tue Feb 11 10:06:57 2003 From: Peter.Andras at newcastle.ac.uk (Peter Andras) Date: Tue, 11 Feb 2003 15:06:57 -0000 Subject: Postdoc job / Deadline: 24 February Message-ID: <20CC6C4061CBB04A98656ED3209B203C430533@bond.ncl.ac.uk> Research Associate, School of Computing Science, =A318,265 - =A327,339 Medical Research Council funded postdoctoral position based in the School of Computing Science, University of Newcastle, UK. A postdoctoral research associate is required to work on the development of knowledge discovery and knowledge management tools and applications for GRID-enabled neuroinformatics. The candidates should have a PhD in computer science, neuroinformatics, neuroscience, or related areas, and good knowledge and experience of objected oriented software design and development (e.g., Java, C/C++). Experience in any of the following areas is beneficial: using artificial intelligence methods (e.g., neural networks, text and data mining), working with web-databases (e.g., neuroscience databases), developing distributed systems (e.g., distributed databases). The post is for up to three years. The salary depends on experience and it is on the RA1A scale range: =A318,265 - =A327,339. For further enquiries e-mail Dr Peter Andras at peter.andras at ncl.ac.uk. Applications including an application form (download from the web-site), a CV, and names and addresses of two referees should be sent to Mrs A. Jackson, School of Computing Science, Claremont Tower, Claremont Road, Newcastle upon Tyne NE1 7RU, or by email to: Anke.Jackson at ncl.ac.uk. Closing date is 24 February 2003. Job reference: D520R Web: http://www.ncl.ac.uk/vacancies/vacancy.phtml?ref=3DD520R ----------------- Dr Peter Andras Lecturer Claremont Tower School of Computing Science University of Newcastle Newcastle upon Tyne NE1 7RU UK Tel. +44-191-2227946 Fax. +44-191-2228232 Web: www.staff.ncl.ac.uk/peter.andras From mhb0 at Lehigh.EDU Tue Feb 11 09:08:37 2003 From: mhb0 at Lehigh.EDU (Mark H. Bickhard) Date: Tue, 11 Feb 2003 09:08:37 -0500 Subject: Final CFP Message-ID: <3E4903E4.6F5A4E87@lehigh.edu> FINAL CALL FOR PAPERS Interactivist Summer Institute 2003 July 22-26, 2003 Botanical Auditorium Copenhagen, Denmark Join us in exploring the frontiers of understanding of life, mind, and cognition. There is a growing recognition - across many disciplines - that phenomena of life and mind, including cognition and representation, are emergents of far-from-equilibrium, interactive, autonomous systems. Mind and biology, mind and agent, are being re-united. The classical treatment of cognition and representation within a formalist framework of encodingist assumptions is widely recognized as a fruitless maze of blind alleys. From neurobiology to robotics, from cognitive science to philosophy of mind and language, dynamic and interactive alternatives are being explored. Dynamic systems approaches and autonomous agent research join in the effort. The interactivist model offers a theoretical approach to matters of life and mind, ranging from evolutionary- and neuro-biology - including the emergence of biological function ? through representation, perception, motivation, memory, learning and development, emotions, consciousness, language, rationality, sociality, personality and psychopathology. This work has developed interfaces with studies of central nervous system functioning, the ontology of process, autonomous agents, philosophy of science, and all areas of psychology, philosophy, and cognitive science that address the person. The conference will involve both tutorials addressing central parts and aspects of the interactive model, and papers addressing current work of relevance to this general approach. This will be our second Summer Institute; the first was in 2001 at Lehigh University, Bethlehem, PA, USA. The intention is for this Summer Institute to become a traditional biennial meeting where those sharing the core ideas of interactivism will meet and discuss their work, try to reconstruct its historical roots, put forward current research in different fields that fits the interactivist framework, and define research topics for prospective graduate students. People working in philosophy of mind, linguistics, social sciences, artificial intelligence, cognitive robotics, theoretical biology, and other fields related to the sciences of mind are invited to send their paper submission or statement of interest for participation to the organizers. http://www.lehigh.edu/~interact/isi2003/isi2003.html -- Mark H. Bickhard 17 Memorial Drive East Lehigh University Bethlehem, PA 18015 610-758-3633 mark at bickhard.name http://www.bickhard.ws/ From cindy at bu.edu Tue Feb 11 14:44:37 2003 From: cindy at bu.edu (Cynthia Bradford) Date: Tue, 11 Feb 2003 14:44:37 -0500 Subject: Neural Networks 16(2) Message-ID: <200302111944.h1BJibe04196@cns-pc75.bu.edu> NEURAL NETWORKS 16(2) Contents - Volume 16, Number 2 - 2003 ------------------------------------------------------------------ NEURAL NETWORKS LETTERS: A complex-valued nonlinear neural adaptive filter with a gradient adaptive amplitude of the activation function Andrew I. Hanna and Danilo P. Mandic CONTRIBUTED ARTICLES: ***** Neuroscience and Neuropsychology ***** Self-organizing continuous attractor networks and motor function S.M. Stringer, E.T. Rolls, T.P. Trappenberg, and I.E.T. de Araujo ***** Mathematical and Computational Analysis ***** Zonal function network frames on the sphere H.N. Mhaskar, F.J. Narcowich, and J.D. Ward On motion detection through a multi-layer neural network architecture Antonio Fernandez-Caballero, Jose Mira, Miguel A. Fernandez, and Ana E. Delgado Dual extended Kalman filtering in recurrent neural networks Chi-Sing Leung and Law-Wan Chan Kalman filters improve LSTM network performance in problems unsolvable by traditional recurrent nets Juan Antonio Perez-Ortiz, Felix A. Gers, Douglas Eck, and Jurgen Schmidhuber Intelligent optimal control with dynamic neural networks Yasar Becerikli, Ahmet Ferit Konar, and Tariq Samad Clustering ensembles of neural network models Bart Bakker and Tom Heskes ***** Engineering and Design ***** Neural network based tracking control of a flexible macro-micro manipulator system X.P. Cheng and R.V. Patel BOOK REVIEWS: Review of "Graphical models: Foundations of neural computation" (Michael I. Jordan and Terrence J. Sejnowski, editors) by Gary R. Bradski Review of "Introduction to neural and cognitive modeling: Second edition" (Daniel S. Levine, author) by Haluk Ogmen CURRENT EVENTS ------------------------------------------------------------------ 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 (regular) Y 13,000 (regular) Neural Networks (plus 2,000 enrollment fee) $20 (student) SEK 460 (student) Y 11,000 (student) (plus 2,000 enrollment fee) ----------------------------------------------------------------------------- membership without $30 SEK 200 not available to Neural Networks non-students (subscribe through another society) Y 5,000 (student) (plus 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 19 Mantua Road Mount Royal NJ 08061 USA 856 423 0162 (phone) 856 423 3420 (fax) innshq at talley.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 c/o Professor Takashi Nagano Faculty of Engineering Hosei University 3-7-2, Kajinocho, Koganei-shi Tokyo 184-8584 Japan 81 42 387 6350 (phone and fax) jnns at k.hosei.ac.jp http://jnns.inf.eng.tamagawa.ac.jp/home-j.html ----------------------------------------------------------------- From jelinek at jhu.edu Tue Feb 11 06:59:35 2003 From: jelinek at jhu.edu (Fred Jelinek) Date: Tue, 11 Feb 2003 06:59:35 -0500 Subject: NSF-supported Summer Internships Message-ID: <6284-Tue11Feb2003065935-0500-jason@cs.jhu.edu> Dear Colleague: The Center for Language and Speech Processing at the Johns Hopkins University is offering a unique summer internship opportunity, which we would like you to bring to the attention of your best students in the current junior class. Preliminary applications for these internships are due at the end of this week. This internship is unique in the sense that the selected students will participate in cutting edge research as full members alongside leading scientists from industry, academia, and the government. The exciting nature of the internship is the exposure of the undergraduate students to the emerging fields of language engineering, such as automatic speech recognition (ASR), natural language processing (NLP) and machine translation (MT). We are specifically looking to attract new talent into the field and, as such, do not require the students to have prior knowledge of language engineering technology. Please take a few moments to nominate suitable bright students for this internship. On-line applications for the program can be found at http://www.clsp.jhu.edu/ along with additional information regarding plans for the 2003 Workshop and information on past workshops. The application deadline is February 15, 2003. If you have questions, please contact us by phone (410-516-4237), e-mail (sec at clsp.jhu.edu) or via the Internet http://www.clsp.jhu.edu Sincerely, Frederick Jelinek J.S. Smith Professor and Director --------------------------------------------------------------------------- Team Project Descriptions for this Summer --------------------------------------------------------------------------- 1. Syntax for Statistical Machine Translation In recent evaluations of machine translation systems, statistical systems based on probabilistic models have outperformed classical approaches based on interpretation, transfer, and generation. Nonetheless, the output of statistical systems often contains obvious grammatical errors. This can be attributed to the fact that the syntactic well-formedness is only influenced by local n-gram language models and simple alignment models. We aim to integrate syntactic structure into statistical models to address this problem. A very convenient and promising approach for this integration is the maximum entropy framework, which allows to integrate many different knowledge sources into an overall model and to train the combination weights discriminatively. This approach will allow us to extend a baseline system easily by adding new feature functions. The workshop will start with a strong baseline -- the alignment template statistical machine translation system that obtained best results in the 2002 DARPA MT evaluations. During the workshop, we will incrementally add new features representing syntactic knowledge that deal with specific problems of the underlying baseline. We want to investigate a broad range of possible feature functions, from very simple binary features to sophisticated tree-to-tree translation models. Simple feature functions might test if a certain constituent occurs in the source and the target language parse tree. More sophisticated features will be derived from an alignment model where whole sub-trees in source and target can be aligned node by node. We also plan to investigate features based on projection of parse trees from one language onto strings of another, a useful technique when parses are available for only one of the two languages. We will extend previous tree-based alignment models by allowing partial tree alignments when the two syntactic structures are not isomorphic. We will work with the Chinese-English data from the recent evaluations, as large amounts of sentence-aligned training corpora, as well as multiple reference translations are available. This will also allow us to compare our results with the various systems participating in the evaluations. In addition, annotation is underway on a Chinese-English parallel tree-bank. We plan to evaluate the improvement of our system using both automatic metrics for comparison with reference translations (BLEU and NIST) as well as subjective evaluations of adequacy and fluency. We hope both to improve machine translation performance and advance the understanding of how linguistic representations can be integrated into statistical models of language. --------------------------------------------------------------------------- 2. Semantic Analysis Over Sparse Data The aim of the task is to verify the feasibility of a machine learning-based semantic approach to the data sparseness problem that is encountered in many areas of natural language processing such as language modeling, text classification, question answering and information extraction. The suggested approach takes advantage of several technologies for supervised and unsupervised sense disambiguation that have been developed in the last decade and of several resources that have been made available. The task is motivated by the fact that current language processing models are considerably affected by sparseness of training data, and current solutions, like class-based approaches, do not elicit appropriate information: the semantic nature and linguistic expressiveness of automatically derived word classes is unclear. Many of these limitations originate from the fact that fine-grained automatic sense disambiguation is not applicable on a large scale. The workshop will develop a weakly supervised method for sense modeling (i.e. reduction of possible word senses in corpora according to their genre) and apply it to a huge corpus in order to coarsely sense-disambiguate it. This can be viewed as an incremental step towards fine-grained sense disambiguation. The created semantic repository as well as the developed techniques will be made available as resources for future work on language modeling, semantic acquisition for text extraction, question answering, summarization, and most other natural language processing tasks. --------------------------------------------------------------------------- 3. Dialectal Chinese Speech Recognition There are eight major dialectal regions in addition to Mandarin (Northern China) in China, including Wu (Southern Jiangsu, Zhejiang, and Shanghai), Yue (Guangdong, Hong Kong, Nanning Guangxi), Min (Fujian, Shantou Guangdong, Haikou Hainan, Taipei Taiwan), Hakka (Meixian Guangdong, Hsin-chu Taiwan), Xiang (Hunan), Gan (Jiangxi), Hui (Anhui), and Jin (Shanxi). These dialects can be further divided into more than 40 sub-categories. Although the Chinese dialects share a written language and standard Chinese (Putonghua) is widely spoken in most regions, speech is still strongly influenced by the native dialects. This great linguistic diversity poses problems for automatic speech and language technology. Automatic speech recognition relies to a great extent on the consistent pronunciation and usage of words within a language. In Chinese, word usage, pronunciation, and syntax and grammar vary depending on the speaker's dialect. As a result speech recognition systems constructed to process standard Chinese (Putonghua) perform poorly for the great majority of the population. The goal of our summer project is to develop a general framework to model phonetic, lexical, and pronunciation variability in dialectal Chinese automatic speech recognition tasks. The baseline system is a standard Chinese recognizer. The goal of our research is to find suitable methods that employ dialect-related knowledge and training data (in relatively small quantities) to modify the baseline system to obtain a dialectal Chinese recognizer for the specific dialect of interest. For practical reasons during the summer, we will focus on one specific dialect, for example the Wu dialect or the Chuan dialect. However the techniques we intend to develop should be broadly applicable. Our project will build on established ASR tools and systems developed for standard Chinese. In particular, our previous studies in pronunciation modeling have established baseline Mandarin ASR systems along with their component lexicons and language model collections. However, little previous work or resources are available to support research in Chinese dialect variation for ASR. Our pre-workshop will therefore focus on further infrastructure development: * Dialectal Lexicon Construction. We will establish an electronic dialect dictionary for the chosen dialect. The lexicon will be constructed to represent both standard and dialectal pronunciations. * Dialectal Chinese Database Collection. We will set up a dialectal Chinese speech database with canonical pinyin level and dialectal pinyin level transcriptions. The database could contain two parts: read speech and spontaneous speech. For the spontaneous speech part, the generalized initial/final (GIF) level transcription should be also included. Our effort at the workshop will be to employ these materials to develop ASR system components that can be adapted from standard Chinese to the chosen dialect. Emphasis will be placed on developing techniques that work robustly with relatively small (or even no) dialect data. Research will focus primarily on acoustic phenomena, rather than syntax or grammatical variation, which we intend to pursue after establishing baseline ASR experiments. --------------------------------------------------------------------------- 4. Confidence Estimation for Natural Language Applications Significant progress has been made in natural language processing (NLP) technologies in recent years, but most still do not match human performance. Since many applications of these technologies require human-quality results, some form of manual intervention is necessary. The success of such applications therefore depends heavily on the extent to which errors can be automatically detected and signaled to a human user. In our project we will attempt to devise a generic method for NLP error detection by studying the problem of Confidence Estimation (CE) in NLP results within a Machine Learning (ML) framework. Although widely used in Automatic Speech Recognition (ASR) applications, this approach has not yet been extensively pursued in other areas of NLP. In ASR, error recovery is entirely based on confidence measures: results with a low level of confidence are rejected and the user is asked to repeat his or her statement. We argue that a large number of other NLP applications could benefit from such an approach. For instance, when post-editing MT output, a human translator could revise only those automatic translations that have a high probability of being wrong. Apart from improving user interactions, CE methods could also be used to improve the underlying technologies. For example, bootstrap learning could be based on outputs with a high confidence level, and NLP output re-scoring could depend on probabilities of correctness. Our basic approach will be to use a statistical Machine Learning (ML) framework to post-process NLP results: an additional ML layer will be trained to discriminate between correct and incorrect NLP results and compute a confidence measure (CM) that is an estimate of the probability of an output being correct. We will test this approach on a statistical MT application using a very strong baseline MT system. Specifically, we will start off with the same training corpus (Chinese-English data from recent NIST evaluations), and baseline system as the Syntax for Statistical Machine Translation team. During the workshop we will investigate a variety of confidence features and test their effects on the discriminative power of our CM using Receiver Operating Characteristic (ROC) curves. We will investigate features intended to capture the amount of overlap, or consensus, among the system's n-best translation hypotheses, features focusing on the reliability of estimates from the training corpus, ones intended to capture the inherent difficulty of the source sentence under translation, and those that exploit information from the base statistical MT system. Other themes for investigation include a comparison of different ML frameworks such as Neural Nets or Support Vector Machines, and a determination of the optimal granularity for confidence estimates (sentence-level, word-level, etc). Two methods will be used to evaluate final results. First, we will perform a re-scoring experiment where the n-best translation alternatives output by the baseline system will be re-ordered according to their confidence estimates. The results will be measured using the standard automatic evaluation metric BLEU, and should be directly comparable to those obtained by the Syntax for Statistical Machine Translation team. We expect this to lead to many insights about the differences between our approach and theirs. Another method of evaluation will be to estimate the tradeoff between final translation quality and amount of human effort invested, in a simulated post-editing scenario. --------------------------------------------------------------------------- From nat at site.uottawa.ca Tue Feb 11 19:46:59 2003 From: nat at site.uottawa.ca (Nathalie Japkowicz) Date: Tue, 11 Feb 2003 19:46:59 -0500 (EST) Subject: Workshop: Learning from Imbalanced Data Sets Message-ID: CALL FOR PAPERS ICML-KDD'2003 Workshop: Learning from Imbalanced Data Sets II Thursday, August 21, 2003 Washington, DC ------------------------------------------------------------------------ Organizers: ----------- Nitesh Chawla, Business Analytic Solutions, CIBC (chawla at csee.usf.edu) Nathalie Japkowicz, University of Ottawa (nat at site.uottawa.ca) Aleksander Kolcz, America Online, Inc. (ark at pikespeak.uccs.edu) ------------------------------------------------------------------------ Workshop Page: -------------- http://www.site.uottawa.ca/~nat/Workshop2003/workshop2003.html ------------------------------------------------------------------------ Workshop Description: --------------------- Overview: Recent years brought increased interest in applying machine learning techniques to difficult "real-world" problems, many of which are characterized by imbalanced learning data, where at least one class is under-represented relative to others. Examples include (but are not limited to): fraud/intrusion detection, risk management, medical diagnosis/monitoring, bioinformatics, text categorization and personalization of information. The problem of imbalanced data is often associated with asymmetric costs of misclassifying elements of different classes. Additionally the distribution of the test data may differ from that of the learning sample and the true misclassification costs may be unknown at learning time. The AAAI-2000 Workshop on "Learning from Imbalanced Data Sets" provided the first venue where this important problem was explicitly addressed and has been received with much interest. The related ICML-2000 Workshop on "Cost-Sensitive Learning" provided another venue for addressing the problem of asymmetric costs of different classes and features. Although much awareness of the issues related to data imbalance has been raised, many of the key problems still remain open and are in fact encountered more often, especially when applied to massive datasets. We believe that it would be of value to the machine learning community to not only examine the progress achieved in this area over the last three years but also discuss the current school of thought on research in learning from imbalanced datasets. Based on our understanding of class imbalance problem, the following topics of discussion are proposed (but not limited to): * sampling (under-, over-, progressive, active) * post-processing of learned models * accounting for class imbalance via inductive bias * one-sided learning * handling uncertainty of target distribution and misclassification costs * handling varying amounts (class dependent) of label noise Proposed Format: The workshop will open with an invited talk by Foster Provost that will introduce and overview the topic. Presentations will then be organized into several sessions corresponding roughly to the to the categories identified above. The workshop will conclude with a discussion during which a distinguished guest will comment on the presentations of the day, and open the floor for general discussion. Proposed Length: One Day during which each panel will be allocated 1 to 2 hours, depending on the number of contributions and the expected length of the discussion session. Workshop Notes: The accepted papers will be available electronically from the workhop website, and also as printed workshop notes to the attendees. Submissions: Authors are invited to submit papers on the topics outlined above or on other related issues. Submissions should not exceed 8 pages, and should be in line with the ICML style sheet. Electronic submissions, in PDF format, are prefered and should be sent to: Nitesh Chawla at chawla at morden.csee.usf.edu If electronic submissions are inconvenient, please send four hard copies of your submission to: Dr. Nitesh Chawla Business Analytic Solutions, TBRM, CIBC, BCE Place, 161 Bay Street, 11th Floor, Toronto, Ontario M5J 2S8, Canada ------------------------------------------------------------------------ Timetable: ---------- * Submission deadline: May 1, 2003 * Notification date: May 25, 2003 * Final date for camera-ready copies to organizers: June 8, 2003 ------------------------------------------------------------------------ Invited Speakers: ----------------- Foster Provost New York University, USA Others To Be Announced ------------------------------------------------------------------------ Program Committee: ------------------ Kevin Bowyer University of Notre Dame, USA Chris Drummond National Research Council, Canada Charles Elkan University of California San Diego, USA Marko Grobelnik Jozef Stefan Institute, Slovenia Larry Hall University of South Florida, USA Robert Holte University of Alberta, Canada W.Philip Kegelmeyer Sandia National Labs, USA Miroslav Kubat University of Miami, USA Aleksandar Lazarevic University of Minnesotta, USA Charles Ling University of Western Ontario, Canada Dragos Margineantu Boeing Corporation, USA Foster Provost New York University, USA Gary Weiss AT&T Labs, USA ----------------------------------------------------------------------- Nathalie Japkowicz, Ph.D. Office: SITE Building 5-029 Assistant Professor Phone: (613) 562-5800 x6693 School of Information E-mail:nat at site.uottawa.ca Technology & Engineering WWW: http://www.site.uottawa.ca/~nat University of Ottawa FAX: (613) 562-5664 Street Address: 800 King Edward Avenue, P.O. Box 450 Stn. A Ottawa, Ontario, Canada K1N 6N5 ----------------------------------------------------------------------- From bengioy at IRO.UMontreal.CA Tue Feb 11 14:17:04 2003 From: bengioy at IRO.UMontreal.CA (Yoshua Bengio) Date: Tue, 11 Feb 2003 14:17:04 -0500 Subject: date change, Montreal workshop on Advances in Machine Learning Message-ID: <20030211141704.A31458@lmlp.iro.umontreal.ca> ----- Forwarded message from Balazs Kegl ----- Due to a date conflict with a major conference, we have had to reschedule the Workshop on Advances in Machine Learning from June 2-6 to June 9-13. We apologize for the inconvenience it may cause. The paper submission deadline remains March 31. -------------------------------------------------------------------------- Call for papers Workshop on Advances in Machine Learning Montreal, Canada, June 9-13, 2003 URL: www.iro.umontreal.ca/~lisa/workshop2003.html Organizers: Yoshua Bengio, Balazs Kegl (University of Montreal) Doina Precup (McGill University) Scope: Probabilities are at the core of recent advances in the theory and practice of machine learning algorithms. The workshop will focus on three broad areas where these advances are crucial: statistical learning theory, learning algorithms, and reinforcement learning. The workshop will therefore bring together experts from each of these three important domains. Among the sub-topics that will be covered, we note: variational methods, graphical models, the curse of dimensionality, empirical methods to take advantage of theories of generalization error, and some of the applications of these new methods. On the theoretical side, in recent years a lot of effort has been devoted to explain the generalization abilities of popular learning algorithms such as voting classifiers and kernel methods. Some of these results have given rise to general principles that can guide practical classifier design. Some (non-exclusive) sub-topics in this aspect of the workshop include Rademacher and Gaussian complexities, algorithmic stability and generalization, localized complexities and results on the generalization ability of voting classifiers and kernel-based methods. On the algorithmic side, one of the emphasis of recent years has been on probabilistic models that attempt to capture the complex structure in the data, often by discovering the main lower-dimensional features that explain the data. This raises interesting and difficult questions on how to train such models, but such algorithms may have wide ranging applications in domains in which the data has interesting structure that may be explained at multiple levels, such as in vision and language. In reinforcement learning (RL), recent research has brought significant advances in some of the traditional problems, such as understanding the interplay between RL algorithms and function approximation, and extending RL beyond MDPs. At the same time, new areas of research, such as computational game theory, have developed at the interface between RL and probabilistic learning methods. In this workshop, we invite presentations on all RL topics, ranging from theoretical development to practical applications. Invited speakers: Rich Sutton, U. Massachusetts, MA, USA Andy Barto, U. Massachusetts, MA, USA (to confirm) Satinder Singh, U. Michigan, Ann Arbour, MI, USA Sridhar Mahadevan, U. Massachusetts Peter Bartlett, U. California Berkeley, CA, USA Vladimir Koltchinskii, U. New Mexico, NM, USA Yann Le Cun, NEC Research, NJ, USA Paolo Frasconi, U. Firenze, Italy Dale Schuurmans, Waterloo U., Ontario, Canada Nando de Freitas, U. British Columbia, BC, Canada Sam Roweis, U. Toronto, Ontario, Canada Geoff Hinton, U. Toronto, Ontario, Canada Important dates: March 31, Paper submission deadline April 15, Notification of paper acceptance/rejection. Submission: Papers should be submitted electronically to kegl at iro.umontreal.ca. Papers can be submitted either as a postscript or a pdf (acrobat) file. No proceedings are currently planned. Registration: The registration fees are minimal: regular registration fees are 100$CAN. Reduced rate for students from a Canadian academic institution: 50$CAN. Venue: The workshop will take place at the Centre de Recherches Mathematiques, on the campus of Universite de Montreal, in lively and beautiful Montreal, Canada. The conference will be held in the Pavillon Andre Aisenstadt, 2920 chemin de la Tour. ----- End forwarded message ----- Yoshua Bengio Full Professor / Professeur titulaire Canada Research Chair in Statistical Learning Algorithms / titulaire de la chaire de recherche du Canada en algorithmes d'apprentissage statistique D?partement d'Informatique et Recherche Op?rationnelle Universit? de Montr?al, adresse postale: C.P. 6128 Succ. Centre-Ville, Montr?al, Qu?bec, Canada H3C 3J7 adresse civique: 2920 Chemin de la Tour, Montr?al, Qu?bec, Canada H3T 1J8, #2194 Tel: 514-343-6804. Fax: 514-343-5834. Bureau 3339. http://www.iro.umontreal.ca/~bengioy http://www.iro.umontreal.ca/~lisa From silvia at sa.infn.it Tue Feb 11 17:37:43 2003 From: silvia at sa.infn.it (Silvia Scarpetta) Date: Tue, 11 Feb 2003 23:37:43 +0100 Subject: Announcement of Erice School on Cortical Dynamics 31 Oct - 6 Nov 2003 Message-ID: <3E497B37.5070502@sa.infn.it> *International School on Neural Nets "E.R. Caianiello"* JOINTLY ORGANIZED BY IIASS International Institute for Advanced Scientific Studies and EMFCSC Ettore Majorana Foundation and Center for Scientific Culture *8th Course:** Computational Neuroscience: Cortical Dynamics * *31 Oct.- 6 Nov. 2003 * *Ettore Majorana Centre* * *Erice (Sicily) ITALY homepage: http://www.sa.infn.it/NeuralGroup/CorticalDynamicsSchool2003/ *Directors of the Course:* Maria Marinaro (Dept. of Physics "E.R. Caianiello", Univ. of Salerno, Italy) Peter Erdi (Kalamazoo College, USA & _KFKI Res. Inst. Part. and Nucl. Phys. Hung. Acad. Sci._ Hungary ) *Lecturers:* *Luigi Agnati *- Dept. of Neuroscience Karolinka Inst.,Sweden & Modena Univ. Italy *Peter Dayan * - Gatsby Computational Neuroscience Unit, UCL, UK - abstract _*Peter Erdi *_ - CCSS Kalamazoo College USA & KFKI Hung. Accad.of Science Hungary - Codirector - abstract *Bruce P Graham* - Dept of Computer Science and Mathematics, Univ. of Stirling UK- abstract *John Hertz* - Nordita, DK - abstract *Zhaoping Li* - Univ. College of London, UK - abstract *Ronen Segev * - School of Physics and Astronomy, Tel Aviv University, Israel - abstract *Ivan Soltesz* - Dept. of Anatomy and Neurobiology, Univ. of California, USA - abstract *Misha Tsodyks* - Dept. of Neurobiology Weizmann Institute of Science, Israel *Ichiro Tsuda* - Dept. of Mathematics, Hokkaido University, Japan -abstract *Alessandro Treves* - Sissa, Cognitive Neuroscience, Trieste, It - abstract **Scientific Program ** /Recently the amount of experimental data available to computational neuroscience community grows steadily, //due to the development of new experimental technique.//The data obtained with these modern techniques allows a degree of comparison with modeling results that so far was not possible. At the same time new and stronger theoretical ideas are being developed from all over the world, borrowing ideas and tools from different fields of science, such as physics and mathematics. / /The goal of the school is to present an up-to-date description of the experimental and theoretical results and of the current efforts to investigate processing, transmission and imprinting of information in the brain, focusing on cortical area. Cortical areas play a key role in important functions like those related to the memory. A systematic description of cortical rhythms and cortical neural plasticity will be given, from its structural basis to its functional significance. / /The school is devoted to students with different scientific background (physics, mathematics, biology, neuroscience, etc.) who wish to learn recent developments in computational neuroscience and cortical dynamics. The basic concepts will be introduced, with emphasis on the underlying //physical concepts//, //common principles and connections between experimental data and biophysically-based as well abstract models. Then cortical dynamics will be investigated, focusing on recent developments and open problems./ **Registrations:** Applications must be received before *May 15 2003* in order to be considered by the selection committee. Registration fee of 900 Euro includes accomodation with full board. Application form and additional information are available from http://www.sa.infn.it/NeuralGroup/CorticalDynamicsSchool2003/. Applications should be sent by ordinary mail to the codirector of the school: Prof. Maria Marinaro IIASS Via Pellegrino 19, I-84019 Vietri sul Mare (Sa) Italy or by fax to: +39 089 761 189 (att.ne: Prof. M. Marinaro) or by electronic mail to: iiass.vietri at tin.it subject: summer school **Location** The "Ettore Majorana" International Centre for Scientific Culture takes its inspiration from the outstanding Italian physicist, after whom the Centre was named. Embracing 110 Schools , covering all branches of Science, the Centre is situated in the old pre-mediaeval city of Erice where three restored monasteries provide an appropriate setting for high intellectual endeavour. These monasteries are now named after great Scientists and strong supporters of the "Ettore Majorana" Centre. There are living quarters in all three Monasteries for people attending the Courses of the Centre. **The John von Neumann (1903-1957) Centenary will be celebrated during the meeting.** Additional information are available at: http://www.sa.infn.it/NeuralGroup/CorticalDynamicsSchool2003/ ---- From J.A.Bullinaria at cs.bham.ac.uk Wed Feb 12 07:09:01 2003 From: J.A.Bullinaria at cs.bham.ac.uk (John A Bullinaria) Date: Wed, 12 Feb 2003 12:09:01 +0000 (GMT) Subject: VACANCIES: Computational Intelligence, Birmingham, UK Message-ID: ------------------------------------------------------------------------ VACANCY: The Centre of Excellence in Computational Intelligence and Applications at Birmingham, UK, has the following openings. Two Research Fellows/Associates in Computational Intelligence (Ref. No. S36545/03, http://www.bham.ac.uk/personnel/s36545.htm) The Centre Manager (Ref. No. S36544/03, http://www.bham.ac.uk/personnel/s36544.htm) ------------------------------------------------------------------------ The School of Computer Science has recently set up a Centre of Excellence in Computational Intelligence and Applications, with substantial funding from the Advantage West Midlands (the regional development agency), to capitalise on and exploit the world-class research in the School for the benefit of industry and businesses (especially those in the West Midlands region). Applications are now invited for the posts of the Centre Manager and two research fellows/associates. The posts are available immediately until 31 March 2007 in the first instance. (The post of the Centre Secretary will be advertised separately.) The successful applicant for the Centre Manager is expected to play a key role in the management and future growth of the Centre. He/She must have excellent analytical and problem solving skills, demonstrated by previous experiences and achievements. He/She should have a very good first degree or postgraduate degree (PhD preferred) in a science or engineering subject (computer science or IT preferred). He/She must have excellent management, communications and people skills, and enjoy working with both business and academic people. He/She should have a background or be interested in computational intelligence. He/She must be self-motivated and capable of working both independently and as a team member. The successful applicants for research fellows/associates must have excellent analytical and problem solving skills in computational intelligence and excellent programming and software development skills. They should have a PhD degree in computer science/engineering or a closely related field, or at least a very good honours degree with significant research and development experiences in computational intelligence. They should demonstrate willingness and interest in tackling real-world problems and applying computational intelligence techniques to industry and businesses. They should be good team players. Excellent written and oral communication skills are required. The School of Computer Science is a leading research school in computer science in the UK. It was rated 5 for its research excellence in the latest (2001) research assessment exercise. The School has a world-leading group in natural computation and computational intelligence (http://www/cs/bham.ac.uk/research/NC). It also runs an EPSRC supported MSc programme in natural computation (http://www.cs.bham.ac.uk/study/postgraduate-taught/msc-nc/). The group includes more than 25 researchers (including permanent and visiting staff and PhD students), working on a wide range of topics in natural computation and computational intelligence. The starting salary for the Centre Manager is on the academic related scale in the range GBP18,265 - GBP33,679 per annum. (Depending on experience and qualifications). The starting salary for the research fellows/associates is on the research scale in the range GBP18,265 - GBP30,660 per annum. (Depending on experience and qualifications). For further particulars, please visit http://www.bham.ac.uk/personnel/s36544.htm (Manager) http://www.bham.ac.uk/personnel/s36545.htm (RFs) For informal enquiries, please contact the Centre Director, Prof Xin Yao (X.Yao at cs.bham.ac.uk). CLOSING DATE FOR RECEIPT OF APPLICATIONS: 4 March 2003 (late application may be considered) APPLICATION FORMS RETURNABLE TO The Director of Personnel Services The University of Birmingham Edgbaston, Birmingham, B15 2TT England RECRUITMENT OFFICE FAX NUMBER +44 121 414 4802 RECRUITMENT OFFICE TELEPHONE NUMBER +44 121 414 6486 RECRUITMENT OFFICE E-MAIL ADDRESS j.a.gerald at bham.ac.uk -------------------------------------------------------------------------- From bogus@does.not.exist.com Tue Feb 18 09:05:05 2003 From: bogus@does.not.exist.com () Date: Tue, 18 Feb 2003 14:05:05 -0000 Subject: AI Stats 2003: proceedings now available on-line Message-ID: <6EDEB53BA6EA96458F3CEC96BB0282D2021DE7B7@tvp-msg-03.europe.corp.microsoft.com> From David.Hansel at biomedicale.univ-paris5.fr Tue Feb 18 04:59:47 2003 From: David.Hansel at biomedicale.univ-paris5.fr (David Hansel) Date: Tue, 18 Feb 2003 09:59:47 +0000 Subject: Les Houches summer school: METHODS AND MODELS IN NEUROPHYSICS Message-ID: <3E520413.9030603@biomedicale.univ-paris5.fr> * NATO Advanced Study Institute METHODS AND MODELS IN NEUROPHYSICS July 28 - August 29, 2003* Scientific Direction: C. C. Chow (Pittsburgh), B. Gutkin (London), D. Hansel and C. Meunier (Paris), I. Segev (Jerusalem) _Program_ Opening lecture: E. Marder (Waltham, USA) Why would a self-respecting experimental biologist be susceptible to theory? _Lecture series:_ L. Abbott (Waltham, USA), P. Bressloff (Salt Lake City, USA), E. Brown (Boston, USA), J. Rinzel (New York, USA), H. Sompolinsky (Jerusalem, Israel), D. Terman (Colombus, USA), T. Tishby (Jerusalem, Israel) _Short lectures and seminars:_ N. Brunel (Paris, France), W. Gerstner (Lausanne, Switzerland), D. Golomb (Beersheva, Israel), G. Mato (Bariloche, Argentina), C. Pouzat (Paris, France), M. Shelley (New York, USA), A. Treves (Trieste, Italy), M. Tsodyks (Rehovot, Israel), C. van Vreeswijk (Paris, France), F. Wolf (Gottingen, Germany). _Topical workshops:_ _Workshop 1_: The neuron in the network. L. Graham (Paris, France) and others to be announced _Workshop 2_: Dynamics in the somatosensory system E. Ahissar (Rehovot, Israel), M. Brecht (Heidelberg, Germany), D. Kleinfeld (San Diego, USA), R. Petersen (Trieste, Italy) _ Workshop 3 _: Learning and Memory G.Q. Bi (Pittsburgh, USA), Y. Dudai (Rehovot, Israel), J. Taube (Hanover,USA), and others to be announced _Registration_ Applications must be received before March 7, 2003. A contribution of 900 euros per participant is requested for full accomodation. A few grants are available. Application forms and additional information are available from the School at Ecole d'ete de Physique theorique La Cote des Chavants, 74310 Les Houches, France Phone: 00-33 -4 50 54 40 69 - Fax: 00 33 -4 50 55 53 25 Email: secretariat.houches at ujf-grenoble.fr Web: http://www-houches.ujf-grenoble.fr/ Les Houches is a resort village of the Chamonix valley facing the Mont-Blanc range. Established in 1951, the Physics School is affiliated with Universite Joseph Fourier (Grenoble), INPG and supported by the Ministere de la Jeunesse, de l'Education Nationale et de la Recherche , by the Centre National de la Recherche Scientifique and by the Commissariat a l'Energie Atomique. This session received support from NATO IBRO and CNRS. From bogus@does.not.exist.com Tue Feb 18 11:16:15 2003 From: bogus@does.not.exist.com () Date: Tue, 18 Feb 2003 17:16:15 +0100 Subject: first announcement of the First European School on Neuroengineering "Massimo Grattarola" Message-ID: <5C052AA22466074FADC82C208D5C5719800F63@EVS02.idc.cww.telecomitalia.it> From d.mareschal at bbk.ac.uk Tue Feb 18 06:21:39 2003 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Tue, 18 Feb 2003 11:21:39 +0000 Subject: Phd Studentships Message-ID: The School of Psychology, Birkbeck College has a number of full-time Phd Studentships on offer for Phds starting in October 2003. Birkbeck College is part of the University of London and is situated in the central Bloomsbury area of London, in close proximity to University College London, The Insitute of Cognitive Neuroscience, the Gatsby Computational Neurosciences Unit, the Institue of Child Health, and the Insitute of Education. The School of Psychology has a very active internationally recognised research programme with particular interests in cognitive sciences, cognitive neurosciences, computational neuroscience, and cognitive and social development. However, the School welcomes applications for studentships in all areas of psychology in both full-time and part-time programmes. The School of Psychology also includes: The Centre for Brain and Cognitive Development (http://www.cbcd.bbk.ac.uk/cbcd.html) For more information about the Schools research profile and studentships available, please visit our website: http://www.psyc.bbk.ac.uk OR contact: Ms Mina Daniel Postgraduate Administrator Tel.: 020 7631 6862 E-mail: s.daniel at psychology.bbk.ac.uk ================================================= Dr. Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 (0)20 7631-6582/6226 reception: 6207 fax +44 (0)20 7631-6312 http://www.psyc.bbk.ac.uk/people/academic/mareschal_d/ ================================================= From markman at psyvax.psy.utexas.edu Tue Feb 18 10:13:53 2003 From: markman at psyvax.psy.utexas.edu (Art Markman) Date: Tue, 18 Feb 2003 09:13:53 -0600 Subject: Cognitive Science Society Virtual Colloquium Message-ID: The Cognitive Science Society is hosting a 2002-2003 virtual colloquium series presented live via the Internet, with the with the fourth talk given by Dr. John Anderson. Register now to attend: www.ctaresource.com/CognitiveScience. Time: Friday February 28, 2003 1:00pm US Eastern Standard Time Presenter: Dr. John Anderson Carnegie Mellon University, Department of Psychology Topic: Use of a Cognitive Architecture and fMRI to Mutually inform Each Other or A Tale of Three Buffers We will describe the interaction between cognitive modeling and brain imaging. Two fMRI studies will be described. The first was concerned with the solution of algebraic equations. We tried to relate the brain regions discovered to components of a prior ACT-R model that had been developed. A left posterior parietal region corresponded to the behavior of a module in ACT-R that maintains an image of the equation and performs mental transformations on it. A left prefrontal region corresponded to the behavior of a module that retrieves relevant information such as arithmetic facts. A left motor region corresponded to the behavior of module that programs hand movements. We will describe how we were able to fit precisely the BOLD functions obtained from these regions given the operation of the ACT-R model. To show that these regions were not specific to mathematics and to turn our model-fitting exercise from postdiction to prediction we performed a second study using a more abstract symbol-manipulation task. The model fits were equally good if not better, although we had to adjust our a priori rehearsal assumptions. The second study identified an anterior cingulate particle whose behavior appears to correspond to the conflict resolution process in ACT-R. This research illustrates profitable back and forth that is possible between brain imaging and cognitive modeling. The basic methodology can be applied to help shape any information processing architecture, not just ACT-R. Further information about this talk, the colloquium series, a schedule of future talks, and an archive of previous talks are available at http://www.cognitivesciencesociety.org/colloquium Contact Janet Morrow, cta at aptima.com with any questions about registration for this seminar. Please forward this invitation to colleagues who would benefit from this seminar or the series. This series is sponsored by the Office of Naval Research. Sincerely, Art Markman markman at psy.utexas.edu Dr. Arthur B. Markman University of Texas Department of Psychology Austin, TX 78712 512-232-4645 From carl at tuebingen.mpg.de Tue Feb 18 11:48:43 2003 From: carl at tuebingen.mpg.de (Carl Edward Rasmussen) Date: Tue, 18 Feb 2003 17:48:43 +0100 (CET) Subject: Openings at the Max Plank Institute for Biological Cybernetics Message-ID: Dear Colleagues: Several positions at various levels (corresponding to graduate student, Postdoc, assistant professor) are available in the Empirical Inference department at the Max Planck Institute in Tuebingen, Germany, studying learning theory and algorithms with applications in various domains. Faculty, current postdocs and visitors of the department include O. Bousquet, O. Chapelle, A. Elisseeff, G. Raetsch, C. Rasmussen, B. Schoelkopf, K. Tsuda, V. Vapnik, J. Weston, and A. Zien (see http://www.kyb.tuebingen.mpg.de/bs). We invite applications of candidates with an outstanding academic record including a strong mathematical or analytical background. In particular we seek people interested in kernel methods such as SVMs and Gaussian Processes, and inference in complex probabilistic models. Max Planck Institutes are publicly funded research labs with an emphasis on excellence in basic research. Tuebingen is a small university town in southern Germany, see http://www.tuebingen.de/kultur/english/index.html for some pictures. Inquiries and applications, including a CV, a statement of research interests and accomplishments should be should be sent, preferably before 10th March 2003, by email to carl at tuebingen.mpg.de or mail to: Carl Edward Rasmussen Max Planck Institute for Biological Cybernetics Spemannstr. 38 72076 Tuebingen Germany Tel. +49 7071 601 556 Fax +49 7071 601 552 In addition, two letters of reference should be sent by mail directly from the referees to the address above. From jms at isep.ipp.pt Wed Feb 19 02:57:24 2003 From: jms at isep.ipp.pt (Jorge M. Santos) Date: Wed, 19 Feb 2003 07:57:24 -0000 Subject: SUMMER SCHOOL ON NEURAL NETWORKS - NN2003 - First announcement Message-ID: <000f01c2d7ec$8b9bea60$1101a8c0@mat.isep.ipp.pt> We appreciate if you can forward this Announcement to your Colleagues, Professors, Students or Mailing lists. ----------------------------------------------------------------------- P L E A S E C I R C U L A T E We apologize if you receive this announcement more than once. -------------------------------------------------------------------------= FIRST ANNOUNCEMENT ************************************************* SUMMER SCHOOL ON NEURAL NETWORKS in SUPERVISED CLASSIFICATION, REGRESSION and DATA MINING July 7-11, 2003, ISEP - Porto, Portugal ************************************************* Web page: http://www.nn.isep.ipp.pt GENERAL INFORMATION The Summer School will be held at Porto, Portugal, jointly organized by the Polytechnic School of Engineering of Porto (ISEP) and the Faculty of Engineering, Porto University (FEUP). Following the considerable success reached by the NN2002 Summer School, the NN2003 edition includes lectures addressing new advances both in NN paradigms and in applications. It will run in parallel sessions allowing each participant to tailor the school to his/her own interest. COURSE CONTENTS Neural networks (NN) have become a very important tool in classification and regression tasks. The applications are nowadays abundant, e.g. in = the engineering, economy and biology areas. The Summer School on NN is dedicated to explain relevant NN paradigms, namely multilayer = perceptrons (MLP), radial basis function networks (RBF), support vector machines=20 (SVM) and entropy-based networks (ENN) used for classification and regression tasks, illustrated with applications to real data. Specific topics are also presented, namely genetic algorithms (GA) and NN, decision trees = and NN, co-operative structures of NN, time series analysis with NN and data mining using NN. Classes include practical sessions with appropriate software tools. The trainee has, therefore, the opportunity to apply the taught concepts and become conversant with a broad range of NN topics and applications. Official language will be English. TARGET AUDIENCE Graduates and researchers interested in applying Neural networks to = their professional activity and as a research tool. PROGRAMME COMMITTEE - Darrell Whitley (Professor, Dept. of Computer Science, Colorado = State University, USA) - Fernando Sereno (Assistant Professor, High School of Education, Portugal) - Jo=E3o Gama (Assistant Professor, Faculty of Economy, University of Porto, Portugal) - Joaquim Marques de S=E1 (Associate Professor, Dept. Electr. and Comp. Engineering; Fac. of Engineering, University of Porto, Portugal) - Jos=E9 Carlos Pr=EDncipe (BellSouth Professor, Director Computational NeuroEngineering, University of Florida, USA) - Lu=EDs Torgo (Assistant Professor, Faculty of Economy, University of Porto, Portugal) - Mark J. Embrechts (Associate Professor, Decision Sciences and Engineering Systems Faculty, Rensselaer Polytechnic Institute, Troy, N.Y., USA) - Mohamed Kamel (Professor, Dept. of Systems Design Engineering, University of Waterloo, Ontario, Canada) - Paulo Cort=EAs (Assistant Professor, University of Minho, Portugal) - Pavel Brazdil (Full Professor, Faculty of Economy, University of = Porto, Portugal) - Steve R. Gunn (Senior Lecturer, Dept. of Electronics and Computer Science, University of Southampton, UK) LOCAL ORGANIZING COMMITTEE (LOC) - Vitor Costa - Assistant Professor, Dept. Mathematics, ISEP, Portugal - J. Paulo Meixedo - Assistant, Dept. Mathematics, ISEP, Portugal - Jorge M. Santos - Assistant, Dept. Mathematics, ISEP, Portugal PRELIMINARY PROGRAMME A preliminary programme (including invited lecturers) and further informations about the classes are available at the school webpage. (http://www.nn.isep.ipp.pt) SCHOOL LOCATION The city of Porto will host the event, with the meeting being organized=20 by ISEP in collaboration with FEUP. Porto is Portugal's second largest = city, having been classified by UNESCO as World Heritage for its old town=20 centre at river Douro side. It is the administrative centre of Northern of Portugal, worldwide renown for its Port Wine Cellars. Porto has an international airport, with connections to all major European airports. All other public transports (train, bus, etc) can also be used to reach Porto. It has an extensive network of buses and a tram, which makes it very easy to stroll around the town, and train and bus connections to=20 many tourist attractions in the region. Lisbon is three hours away by train, and all other major Portuguese cities can be easily reached either by = car or by train. Important note: Visa may be required for citizens of = several European and overseas countries. Please contact your local Portuguese Consulates beforehand (typically no less than one month in advance). REGISTRATION Please find the registration form available at the WWW site of the conference. Please fill at your earlier convenience the registration form and send it to the LOC. NOTE: Special prices will be offered to those whom attended the NN2002. The registration fee for participants amounts to: - Early registration fee (payed before the 15th of May) * 300 Euro (students, ISEP and FEUP staff, and APPIA members) and to * 350 Euro (all other participants) - Late registration fee (payed after the 15th of May) * 350 Euro (students, ISEP and FEUP staff, and APPIA members) and to * 400 Euro (all other participants) The registration fee includes: * school package * coffee breaks * daily lunch * welcome reception * school banquet All participants are required to register prior to the start of the School - until the 15th of May - even if you choose to pay the late registration fee at the registration desk. Please note that the number of participants is limited, so it is conceivable that the late registration period will effectively be shorter than advertised. ACCOMMODATION The detailed procedure on how to book accommodation will be announced later. FINANCIAL ASSISTANCE Special consideration will be taken to secure some support for students and colleagues from Central and Eastern Europe. However, in the best possible case, this support will only be partial. Please check the next announcement or the School webpage. SOCIAL PROGRAMME Details on the Social and Cultural Programme for NN-2003 will be=20 announced later. CONTACT ADDRESS LOC - Summer School NN-2003 Departamento de Matem=E1tica Instituto Superior de Engenharia do Porto Rua Dr. Ant=F3nio Bernardino de Almeida 431 4200-072 PORTO / PORTUGAL Email: nn-2003 at isep.ipp.pt Programme Chair: Prof. Marques de S=E1 Tel. 225081828 - Email: jmsa at fe.up.pt From: esann To: "'Connectionists at cs.cmu.edu'" References: From bogus@does.not.exist.com Wed Feb 19 07:33:26 2003 From: bogus@does.not.exist.com () Date: Wed, 19 Feb 2003 13:33:26 +0100 Subject: ESANN'2003 programme ( European Symposium on Artificial Neural Networks) Message-ID: ---------------------------------------------------- | | | ESANN'2003 | | | | 11th European Symposium | | on Artificial Neural Networks | | | | Bruges (Belgium) - April 23-24-25, 2003 | | | | Preliminary programme | ---------------------------------------------------- The preliminary programme of the ESANN'2003 conference is now available on the Web: http://www.dice.ucl.ac.be/esann For those of you who maintain WWW pages including lists of related ANN sites: we would appreciate if you could add the above URL to your list; thank you very much! We try as much as possible to avoid multiple sendings of this call for papers; however please apologize if you receive this e-mail twice, despite our precautions. For 11 years the ESANN conference has become a major event in the field of neural computation. ESANN is a human-size conference focusing on fundamental aspects of artificial neural networks (theory, models, algorithms, links with statistics, data analysis, biological background,...). This year, 84 scientific communications will be presented, covering most areas of the neural computation field. The programme of the conference can be found at the URL http://www.dice.ucl.ac.be/esann, together with practical information about the conference venue, registration,... Other information can be obtained by sending an e-mail to esann at dice.ucl.ac.be . ======================================================== ESANN - European Symposium on Artificial Neural Networks http://www.dice.ucl.ac.be/esann * For submissions of papers, reviews,... Michel Verleysen Univ. Cath. de Louvain - Microelectronics Laboratory 3, pl. du Levant - B-1348 Louvain-la-Neuve - Belgium tel: +32 10 47 25 51 - fax: + 32 10 47 25 98 mailto:esann at dice.ucl.ac.be * Conference secretariat d-side conference services 24 av. L. Mommaerts - B-1140 Evere - Belgium tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00 mailto:esann at dice.ucl.ac.be ======================================================== From H.Bowman at ukc.ac.uk Wed Feb 19 09:30:41 2003 From: H.Bowman at ukc.ac.uk (hb5) Date: Wed, 19 Feb 2003 14:30:41 +0000 Subject: Job in Computational Modelling of Cognition Message-ID: <3E539511.6C592086@ukc.ac.uk> RESEARCH ASSOCIATE IN COMPUTATIONAL MODELLING OF COGNITION (R03/15) Research IA scale : 20,311-27,339 pounds p.a. Applications are invited for a Postdoctoral Research Associate post at the University of Kent at Canterbury, UK, to work on an EPSRC funded project entitled "Computational Modelling of Salience Sensitive Control in Humans and Artificial Systems" (details of which can be found on the following web-page, http://www.cs.ukc.ac.uk/people/staff/hb5/attention.html). The project is a collaboration with the Medical Research Council's Cognition and Brain Sciences Unit in Cambridge. The objective of the research is to construct computational models of the time course of human attention. This will particularly focus on simulating data arising from ongoing empirical studies of the Attentional Blink and the Psychological Refactory Period, which are being carried out at the Cognition and Brain Sciences Unit. A diverse set of modelling notations will be employed including neural networks, temporal logic and process algebra. These models will not only increase our understanding of human attention, they will also allow us to construct computer interfaces that are more sensitive to the human user and to develop robots that perform more effectively in dynamically changing environments. Applicants should have or should be in the process of finishing a PhD. Due to the cross disciplinary nature of the research, a suitable candidate could have studied in any of the following areas: Cognitive Psychology, Cognitive Neuroscience, Artificial Intelligence, Computer Science, Electronics, Physics, etc. Most importantly though we seek an applicant who is open to cross-disciplinary influences. The skills that will be employed in the research project are diverse, and include, - Connectionist modelling of cognitive processes. - An understanding of the human perception and attention systems. - Formal specification techniques, as employed in computer science, such as process algebra and temporal logic. - Expertise in robotics and human computer interaction. Due to the diverse nature of this skill set, it is very unlikely that we will find a single candidate that combines all these skills, consequently a candidate with even a small subset of these skills is still encouraged to apply. The post is available from 1 June 2003 for a period of 3 years. Further particulars and an Equal Opportunities Monitoring Form can be downloaded here: http://www.ukc.ac.uk/registry/personnel/vacancies/research.html#r0315 Alternatively you can telephone the Personnel Office for further particulars and application details on +44-(0)1227 827837 (24 hours) or e-mail: personnel at ukc.ac.uk quoting Ref. No.R03/15. Text phone users please telephone +44-(0)1227 824145. Informal enquires can be directed to Dr Howard Bowman (H.Bowman at ukc.ac.uk). Further details about the Computer Science Department can be found at http://www.cs.ukc.ac.uk/ Closing date for applications: 12 noon Friday 14 March 2003 From kdharris at andromeda.rutgers.edu Wed Feb 19 17:55:56 2003 From: kdharris at andromeda.rutgers.edu (Ken Harris) Date: Wed, 19 Feb 2003 17:55:56 -0500 Subject: Announcing KlustaKwik 1.5 Message-ID: Dear Connectionists I am pleased to announce the release of version 1.5 of KlustaKwik, a program for fast automatic clustering using a mixture of Gaussians model. It can be downloaded from http://osiris.rutgers.edu/Buzsaki/software. Further details follow below. Best regards, Ken Harris. ----------------------------------------------- KlustaKwik is a program for unsupervised classification of multidimensional continuous data. It arose from a specific need - automatic sorting of neuronal action potential waveforms (see KD Harris et al, Journal of Neurophysiology 84:401-414,2000), but works for any type of data. We needed a program that would: 1) Fit a mixture of Gaussians with unconstrained covariance matrices 2) Automatically choose the number of mixture components 3) Be robust against noise 4) Reduce the problem of local minima 5) Run fast on large data sets (up to 100000 points, 48 dimensions) Speed in particular was essential. KlustaKwik is based on the CEM algorithm of Celeux and Govaert (which is faster than the standard EM algorithm), and also uses several tricks to improve execution speed while maintaining good performance. On our data, it runs at least 10 times faster than Autoclass. The main improvement in version 1.5 is a cluster splitting feature. KlustaKwik allows for a variable number of clusters to be fit, penalized by AIC. The program periodically checks if splitting any cluster would improve the overall score. It also checks to see if deleting any cluster and reallocating its points would improve overall score. The splitting and deletion features allow the program to often escape from local minima, reducing sensitivity to the initial number of clusters, and reducing the total number of starts needed for a data set. From dgw at MIT.EDU Thu Feb 20 15:31:31 2003 From: dgw at MIT.EDU (David Weininger) Date: Thu, 20 Feb 2003 15:31:31 -0500 Subject: book announcement--Standish Message-ID: <200302201531313210@outgoing.mit.edu> I thought readers of the Connectionists List might be interested in this book. For more information, please visit http://mitpress.mit.edu/0262692813/ Thank you! Best, David Artifical Life VIII Proceedings of the Eighth International Conference on Artificial Life edited by Russell Standish, Mark A. Bedau, and Hussein A. Abbass The term "artificial life" describes research into synthetic systems that possess some of the essential properties of life. This interdisciplinary field includes biologists, computer scientists, physicists, chemists, geneticists, and others. Artificial life may be viewed as an attempt to understand high-level behavior from low-level rules--for example, how the simple interactions between ants and their environment lead to complex trail-following behavior. An understanding of such relationships in particular systems can suggest novel solutions to complex real-world problems such as disease prevention, stock-market prediction, and data mining on the Internet. Since their inception in 1987, the Artificial Life meetings have grown from small workshops to truly international conferences, reflecting the field's increasing appeal to researchers in all areas of science. Russell Standish is Director of the High Performance Computing Support Unit and Adjunct Associate Professor in the School of Mathematics at the University of New South Wales. Mark A. Bedau is Professor of Philosophy and Humanities at Reed College, Adjunct Professor of Systems Science at Portland State University, and Editor-in-Chief of the MIT Press journal Artificial Life. Hussein A. Abbass is Senior Lecturer and Director of the Artificial Life and Adaptive Robotics Lab, School of Computer Science, Australian Defense Force Academy, and Honorary Associate at the University of New England. 8 1/2 x 11, 504 pp., paper, ISBN 0-262-69281-3 Complex Adaptive Systems series A Bradford Book ______________________ David Weininger Associate Publicist The MIT Press 5 Cambridge Center, 4th Floor Cambridge, MA 02142 617 253 2079 617 253 1709 fax http://mitpress.mit.edu From rebollol at aston.ac.uk Fri Feb 21 09:59:12 2003 From: rebollol at aston.ac.uk (L REBOLLO-NEIRA) Date: Fri, 21 Feb 2003 14:59:12 +0000 Subject: postdoc Message-ID: RESEARCH ASSOCIATE: "Biorthogonal techniques for optimal signal representation". Starting salary 20.311 pounds pa (2 years and 7 months contract) Applications are invited for a Post Doctoral Research Associate to work on a EPSRC funded project. The project will focus on developing a framework for signal representation outside the traditional orthogonal basis setting. Further details on the research project can be found in http://www.ncrg.aston.ac.uk/Research.html by clicking on the link for "Biorthogonal techniques for optimal signal representation" Applicants should hold a PhD in Physics, Mathematics, Computer Science or related discipline. The work requires strong mathematical background and good computational skills. The successful candidate will have the opportunity to join the well established and internationally recognized research group NCRG http://www.ncrg.aston.ac.uk The post is tenable as soon as possible. Informal enquiries should be directed to Dr Laura Rebollo-Neira: rebollol at aston.ac.uk Further particulars and application forms may be obtained electronically on http://www.aston.ac.uk/hr/recruitment.htm or from Personnel Office on Tel (0) 121 359 0870 email b.a.power at aston.ac.uk quoting Ref R03/46/98. From deniz at cnel.ufl.edu Fri Feb 21 10:57:13 2003 From: deniz at cnel.ufl.edu (Deniz Erdogmus) Date: Fri, 21 Feb 2003 10:57:13 -0500 Subject: Deadline Reminder: IEEE-TNN Special Issue on Information Theoretic Learning References: <3E149939.72F07F4F@cnel.ufl.edu> Message-ID: <3E564C59.6616282B@cnel.ufl.edu> Dear Colleagues, This is a reminder for the upcoming special issue of the IEEE Transactions on Neural Networks on Information Theoretic Learning. The paper submission deadline is March 15, 2003. To see the call for papers or to submit a paper please visit the paper submission webpage at: http://www.cnel.ufl.edu/~tnn_itl/ Prospective authors can also register their intent by submitting only an abstract at the same website. -- Deniz Erdogmus, Ph.D. Post-doctoral Research Associate Computational NeuroEngineering Laboratory, EB 486 Electrical and Computer Engineering Department University of Florida Gainesville, FL 32611 Phone: 1-352-3922682 Fax: 1-352-3920044 http://www.cnel.ufl.edu/~deniz/ From P.J.Lisboa at livjm.ac.uk Fri Feb 21 19:37:47 2003 From: P.J.Lisboa at livjm.ac.uk (Lisboa, Paulo) Date: Sat, 22 Feb 2003 00:37:47 -0000 Subject: NNESMED/CIMED 2nd Call for Papers Message-ID: Dear Colleagues, A second and final call for papers has been issued for NNESMED/CIMED 2003, with the deadline for submissions extended until Friday 7th March. Submission information is listed in this message and full details about the conference may be found at the conference website http://www.shu.ac.uk/conference/nnesmed/. Paulo Lisboa. Fifth International Conference on Neural Networks and Expert Systems in Medicine and Healthcare and First International Conference on Computational Intelligence in Medicine and Healthcare, NNESMED/CIMED 2003. Sheffield Hallam University, 21-23 July, 2003. NNESMED and CIMED are focused on the application of intelligent computational methods and systems to support all areas of biomedical, clinical and healthcare practice, making it a strongly interdisciplinary conference, bringing together healthcare specialists, clinicians, biomedical engineers, computer scientists, communication and computer network engineers, and applied mathematicians. It traditionally follows a single-track format to ensure that all presentations, whatever the mode of delivery, are well attended. The language of the conference is English. SUBMISSION OF PAPERS Authors are requested to submit an extended abstract (two pages in length, single spaced) which includes the paper title, the authors' names, affiliations, e-mail and postal addresses, the name of the corresponding author and their telephone and fax numbers, a short summary of the abstract (for the website) and the extended abstract itself, by 7 March 2003. Extended abstracts should clearly identify the medical or healthcare context of the work, the methodology used, the advances made and the significance of the results. Extended abstracts should only concern significant work already completed. Extended abstracts on currently unfinished or future work should not be submitted. The material submitted must be original, and must neither have been published nor be under consideration for publication elsewhere. Papers will be accepted as either full session oral papers or as poster papers. The authors of poster papers will also be timetabled for a 4 minute oral presentation at the commencement of the poster session. The summaries of the extended abstracts accepted for the conference will be placed on the conference website. The text should be prepared in Word using font Times New Roman size 12 bold face for the title only, and size 10, not bold, for the rest of abstract. Authors should submit their abstracts as attachments to an e-mail sent to conference21 at shu.ac.uk . Authors without access to e-mail should post four copies to: Conference 21, Sheffield Hallam University, City Campus, Sheffield, S1 1WB, England. Authors whose abstracts are accepted will be asked to develop them into full camera-ready papers of 4-6 pages in length for inclusion in the conference proceedings. After the conference, selected papers will be recommended for expansion and submission to the International Journal "Artificial Intelligence in Medicine" (Elsevier Science, http://www.elsevier.com/locate/issn/09333657) or to the "Journal of Soft Computing" (Elsevier Science, http://www.elsevier.com/locate/asoc/), where they will undergo the usual review process. IMPORTANT DEADLINES * Submission of extended abstracts 7 March 2003 * Notification of provisional acceptance 31 March 2003 * Submission of full papers (camera ready) 18 April 2003 From Daniel.Herrmann at de.bosch.com Mon Feb 24 05:35:02 2003 From: Daniel.Herrmann at de.bosch.com (Herrmann Daniel (FV/FLD)) Date: Mon, 24 Feb 2003 11:35:02 +0100 Subject: phd-positions Message-ID: Please forward this information to your students: ----------------------------------------------------------------------- There will be soon some phd-positions available at the R&D Department for Microsystems of Robert Bosch GmbH in Stuttgart (Germany) on applications of kernel methods to design centering in MST, process monitoring etc. ----------------------------------------------------------------------- Bosch is one of leading suppliers in the automobile industry, see www.bosch.com. At moment the topic of the phd can be adapted to the background of the candidate. The contract lasts for three years and the salary is about 28.000 Euro. Please contact me for more information. With Regards / Mit freundlichen Gr??en Daniel Herrmann -------------------------------------------- Daniel Herrmann Robert Bosch GmbH, FV/FLD [R&D Microsystems] P.O. Box 10 60 50, D-70079 Stuttgart Germany Tel. +49-711 811 7563 Fax +49-711 811 269196 mailto:Daniel.Herrmann at de.bosch.com From gustavo.camps at uv.es Mon Feb 24 04:50:41 2003 From: gustavo.camps at uv.es (Gustavo Camps i Valls) Date: Mon, 24 Feb 2003 10:50:41 +0100 Subject: 2nd CfP: Special Session on ``Adaptive, Neural and Kernel Methods in Medicine''. Message-ID: <3E59EAF1.1647697A@uv.es> Dear collegues: I formally invite you to submit to the Special session entitled ``Adaptive, Neural and Kernel Methods in Medicine'' in the International Workshop on Artificial Neural Networks (IWANN) to be held June, 2003 in Balearic Islands, Spain. More information on the congress and the session can be found at http://62.204.199.18/iwann2003/ http://iwann.uned.es/ http://iwann.uned.es:9673/Sessions/ViewSession?id=38 Deadline: Feb, 28 2003 Scope: The aim of the workshop is to present state-of-the-art information processing tools in medicine applications. Adaptive systems, Artificial Neural Networks and kernel-based methods such as Support Vector Machines, Gaussian Processes, boosting-based approaches and Kernel PCA/ICA will be paid attention. The workshop aims to bring together a group of international researchers from machine learning and signal processing for discussing results and dissemination of ideas, with the objective of highlighting new research directions in health sciences, bioinformatics, medicine and biomedical engineering. Novel methods and application examples are wellcome. Look forward to seeing you there. Best regards, Gustavo Camps-Valls, PhD. -- _____________________________________________________________ Gustavo Camps-Valls - gcamps at uv.es Grup de Processament Digital de Senyals - http://gpds.uv.es/ Dpt. Enginyeria Electr?nica. Universitat de Val?ncia. Tlf.: +0034-(9)6-3160197 - Fax: +0034-(9)6-3160466 C/ Dr. Moliner, 50. 46100 - Burjassot (Val?ncia). Spain. Personal Web Page: http://www.uv.es/~gcamps _____________________________________________________________ From mpp at us.ibm.com Mon Feb 24 15:39:29 2003 From: mpp at us.ibm.com (Michael Perrone) Date: Mon, 24 Feb 2003 15:39:29 -0500 Subject: PhD Job Announcement: IBM Research Message-ID: The IBM TJ Watson Research Center has an immediate opening for a Ph.D. researcher in handwriting recognition. Details are below. Please apply at the following website: http://careers.peopleclick.com/jobposts/Client40_GLDTR/BU1/External/139-2294.htm?ShowReturn=Yes Regards, Michael Perrone IBM T.J. Watson Research Center 914-945-1779 __________________________________________________________________________ IBM Research Staff Member - Handwriting Recognition Job ID Job Category Job Level Location Travel Job Type K065368 Research Staff Experienced NY,Yorktown 0-20% Full-time Member Professional Heights Regular Job Details Generates highly novel ideas, evaluates them, plans, and is involved in their execution and implementation and/or invents and designs complex products and/or processes. Disseminates the results of such activities through publications, patent disclosures, seminar participation, internal documentation. Represents IBM at professional meetings, in professional societies, and universities. Keeps technically abreast of the literature. Functions as an internal consultant in the areas of prof. expertise and provides technical guidance. May direct technically, within the broad mission of the group, activities of other RSMs in the implementation of ideas for which he/she is primarily responsible. Assumes additional responsibilities as assigned. Requires a Ph.D. in mathematics, physics, engineering, or computer science. Requires demonstrated proficiency and/or potential in multimodal user interfaces, such as handwriting recognition and speech recognition. Required Skills C, C++, Java and XML programming. Statistics / Mathematics / Probability. Research experience in handwriting and/or Speech recognition. From m.usher at psychology.bbk.ac.uk Mon Feb 24 11:30:22 2003 From: m.usher at psychology.bbk.ac.uk (DR M USHER) Date: Mon, 24 Feb 2003 16:30:22 +0000 (GMT) Subject: PhD studentships Message-ID: Dear Collegues, I apologize in advance if you received this message more than once. Please bring this to the attention of relevant applicants. Sincerely, Marius Usher, PhD Reader in Psychology Birkbeck College, Univ. of London www.psyc.bbk.ac.uk/people/academic/usher_m I would like to encourage strong candidates (with solid background in experimental-psychology OR cognitive-science AND in computational methods) to apply for the following PhD studentship opportunities at the Birkbeck College. The School of Psychology, Birkbeck College, University of London offers supervision in Cognitive Sciences and Computational Cognitive Neuroscience. Birkbeck College is part of the University of London and is situated in the central Bloomsbury area of London. The research environment benefits from close proximity with the Institute of Cognitive Neuroscience, the Gatsby Computational Neurosciences Unit and the Institute of Child Health. The School of Psychology has a moderate sized dynamic, international postgraduate community that provides both a cutting edge and intimate environment for learning and research. Potential supervisors in the Computational Cognitive Neuroscience Lab: Richard Cooper (http://www.psyc.bbk.ac.uk/people/academic/cooper_r/) Models of executive processes and their disorders; relations between executive processes and lower-level processes; routine and non-routine action selection; monitoring and error correction; modeling tools and methodologies. Denis Mareschal (http://www.psyc.bbk.ac.uk/people/academic/mareshal_d/) Constructing and testing models of categorisation in infancy, statistical learning models of reasoning in children and infants. Michael Thomas (http://www.psyc.bbk.ac.uk/people/academic/thomas_m/) Modeling of language development in Williams Syndrome; current computational approaches to individual differences and intelligence; computational models of autism Marius Usher (http://www.psyc.bbk.ac.uk/people/academic/usher_m/) Computational and behavioural studies of verbal short-term memory, language, reasoning and individual and age differences; choice and decision making; visual short-term memory for single and bound visual features; psychophysical studies of temporal interactions in grouping. For more information on the CCN lab see http://www.psyc.bbk.ac.uk/research/comp/index.html/ Financial support is available on a competitive basis through EPSRC studentships and internal School of Psychology Studentships. The School of Psychology also has ESRC recognition. Further information can be obtained from: http://www.psyc.bbk.ac.uk/ For general inquiries email: s.daniel at psychology.bbk.ac.uk. For specific inquiries, email one of the potential supervisors. From maki at cslab.kecl.ntt.co.jp Mon Feb 24 23:14:47 2003 From: maki at cslab.kecl.ntt.co.jp (Shoji Makino) Date: Tue, 25 Feb 2003 13:14:47 +0900 Subject: One month before ICA2003 in Nara, JAPAN, April 1-4, 2003 Message-ID: <4.0.1-J.20030225131136.029bfe50@earth> Dear All, We have one month before the ICA2003 (Fourth International Symposium on Independent Component Analysis and Blind Signal Separation) will be held in April 1-4, 2003, Nara, Japan. It will be held just before ICASSP2003 in April 6-10, Hong Kong. The ICA2003 Book of Abstract is now posted on our web site: http://ica2003.jp/. Get all of the information you need to plan your trip from our web site. Conference registration will be closed shortly, so register now. April is a cherry blossom season and hotels are very crowded. We recommend you to book your hotel as soon as possible. See you soon in Nara, the city with a World Heritage history. Best regards, General chair: Shun-ichi Amari Organizing chair: Shoji Makino Program chairs: Andrzej Cichocki Noboru Murata From auke.ijspeert at epfl.ch Tue Feb 25 03:12:05 2003 From: auke.ijspeert at epfl.ch (Auke Ijspeert) Date: Tue, 25 Feb 2003 09:12:05 +0100 Subject: Java applet: Neuromechanical simulation of salamander locomotion Message-ID: <3E5B2555.7050209@epfl.ch> People interested in the neural control of locomotion might be interested in a Java applet that we recently developed of a neuromechanical simulation of salamander locomotion. The applet can be tested on the following page: http://lslwww.epfl.ch/birg/ (cf the Salamander Java applet link). The project investigates the control of locomotion in salamander, and the transition from swimming to walking during vertebrate evolution. We study whether neural controllers for swimming similar to those of the lamprey can be extended to control both the swimming and walking of the salamander, and the gait transition between these two modes. The salamander is believed to be one of the modern tetrapods closest to the first vertebrate having made the transition from aquatic to terrestrial habitats during evolution. Using a neuromechanical simulation of the salamander, i.e. a simulation which combines a mechanical model of the body and a neural network model of the locomotor central pattern generator, we investigate several organizations of neural networks capable of producing, and switching between, the typical swimming and walking gaits of the salamander. Comments and feedback are welcome. Best regards, Auke Ijspeert and Sebastien Catherinet Ps: More details concerning the simulation can be found in the following paper: Ijspeert A.J.: A connectionist central pattern generator for the aquatic and terrestrial gaits of a simulated salamander, Biological Cybernetics, Vol. 84:5, 2001, pp 331-348 -- ----------------------------------------------------------------- Dr Auke Jan Ijspeert SNF (Swiss National Science Foundation) Assistant Professor School of Computer and Communication Sciences EPFL, Swiss Federal Institute of Technology, Lausanne CH 1015 Lausanne, Switzerland Office: INN 241 Tel: +41 21 693 2658, Fax: +41 21 693 3705 www: http://lslwww.epfl.ch/birg Email: Auke.Ijspeert at epfl.ch Adjunct Assistant Professor, Department of Computer Science, University of Southern California ----------------------------------------------------------------- From l.wiskott at biologie.hu-berlin.de Tue Feb 25 07:34:23 2003 From: l.wiskott at biologie.hu-berlin.de (Laurenz Wiskott) Date: 25 Feb 2003 12:34:23 -0000 Subject: paper available: model of complex cells in V1 Message-ID: <20030225123423.26473.qmail@huxley.biologie.hu-berlin.de> SLOW FEATURE ANALYSIS YIELDS A RICH REPERTOIRE OF COMPLEX-CELL PROPERTIES by Pietro Berkes and Laurenz Wiskott Abstract: In this study, we investigate temporal slowness as a learning principle for receptive fields using slow feature analysis, a new algorithm to determine functions that extract slowly varying signals from the input data. We find that the learned functions trained on image sequences develop many properties found also experimentally in complex cells of primary visual cortex, such as direction selectivity, non-orthogonal inhibition, end-inhibition and side-inhibition. Our results demonstrate that a single unsupervised learning principle can account for such a rich repertoire of receptive field properties. Available from: http://cogprints.ecs.soton.ac.uk/archive/00002785/ Reference: Berkes, P. and Wiskott, L. (2003). Slow feature analysis yields a rich repertoire of complex-cell properties. Cognitive Sciences EPrint Archive (CogPrint) 2785, http://cogprints.ecs.soton.ac.uk/archive/00002785/, (). Additional Information: http://itb.biologie.hu-berlin.de/~wiskott/Projects/SFA-ReceptiveFields.html -- Dr. Laurenz Wiskott, Institute for Theoretical Biology, Berlin http://itb.biologie.hu-berlin.de/~wiskott/ l.wiskott at biologie.hu-berlin.de From geoff at cns.georgetown.edu Thu Feb 27 20:48:26 2003 From: geoff at cns.georgetown.edu (geoff@cns.georgetown.edu) Date: Thu, 27 Feb 2003 20:48:26 -0500 Subject: Postdoc position available Message-ID: <200302280148.h1S1mQO12337@newk.cns.georgetown.edu> POSTDOC IN MODELS OF RETINOTECTAL MAP FORMATION Geoff Goodhill Dept of Neuroscience Georgetown University Medical Center Washington DC A postdoctoral position is now available in my lab for an NIH-funded project to develop new theoretical models of retinotectal map formation. This project is a collaboration with John Flanagan at Harvard University (http://cellbio.med.harvard.edu/faculty/flanagan). The goal is to understand the initial activity-independent mechanisms by which axons find their targets in the tectum, and the models will be closely tied to current experimental data regarding Eph/ephrin gradients. A list of relevant papers can be found below. To apply, send a CV, a letter of interest, and names and addresses (including email) of at least two referees to: Geoffrey J Goodhill, PhD Associate Professor, Department of Neuroscience Georgetown University Medical Center 3900 Reservoir Road NW, Washington DC 20007 Tel: (202) 687 6889, Fax: (202) 687 0617 Email: geoff at georgetown.edu Homepage: cns.georgetown.edu Review of applications will start immediately and continue until the position is filled. Some relevant papers: Goodhill, G.J. & Richards, L.J. (1999). Retinotectal maps: molecules, models, and misplaced data. Trends in Neurosciences, 22, 529-534. http://cns.georgetown.edu/~geoff/pub/goodhill_richards_99.pdf Goodhill, G.J. (2002). Development of retinotectal maps, in ``The Handbook of Brain Theory and Neural Networks'', 2nd edition, ed. Michael Arbib, MIT Press, 335-339. Feldheim DA, Kim YI, Bergemann AD, Frisen J, Barbacid M, Flanagan JG. (2000). Genetic analysis of ephrin-A2 and ephrin-A5 shows their requirement in multiple aspects of retinocollicular mapping. Neuron, 25, 563-574. Goodhill, G.J. (2000). Dating behavior of the retinal ganglion cell. Neuron, 25, 501-503. [Comment on the Flanagan article above] http://cns.georgetown.edu/~geoff/pub/goodhill_neuron_00.pdf