From zemel at cs.toronto.edu Fri Jun 1 14:23:06 2001 From: zemel at cs.toronto.edu (Richard Zemel) Date: Fri, 1 Jun 2001 14:23:06 -0400 Subject: NIPS*2001 Call For Workshop Proposals Message-ID: <01Jun1.142326edt.453201-24086@jane.cs.toronto.edu> *@* NEW LOCATION: WHISTLER, BC, CANADA *@* Call for Workshop Proposals Neural Information Processing Systems -- Natural and Synthetic NIPS*2001 Post-Conference Workshops -- December 7 and 8, 2001 Whistler/Blackcomb Resort, BC, CANADA Following the regular program of the Neural Information Processing Systems 2001 conference in Vancouver, BC, Canada, workshops on various current topics in neural information processing will be held on December 7 and 8, 2001, in Whistler, BC, Canada. We invite researchers interested in chairing one of these workshops to submit workshop proposals. The goal of the workshops is to provide an informal forum for researchers to discuss important research questions and challenges. Controversial issues, open problems, and comparisons of competing approaches are encouraged and preferred as workshop topics. Representation of alternative viewpoints and panel-style discussions are particularly encouraged. Workshop topics include, but are not limited to, the following: Active Learning, Architectural Issues, Attention, Audition, Bayesian Analysis, Bayesian Networks, Benchmarking, Brain Imaging, Computational Complexity, Computational Molecular Biology, Control, Genetic Algorithms, Graphical Models, Hippocampus and Memory, Hybrid Supervised/Unsupervised Learning Methods, Hybrid HMM/ANN Systems, Implementations, Independent Component Analysis, Mean-Field Methods, Markov Chain Monte-Carlo Methods, Music, Network Dynamics, Neural Coding, Neural Plasticity, On-Line Learning, Optimization, Recurrent Nets, Robot Learning, Rule Extraction, Self-Organization, Sensory Biophysics, Signal Processing, Spike Timing, Support Vectors, Speech, Time Series, Topological Maps, and Vision. Detailed descriptions of previous workshops may be found at http://www.cs.cmu.edu/Groups/NIPS/NIPS2000/Workshops There will be six hours of workshop meetings per day, split into morning and afternoon sessions, with free time inbetween for ongoing individual exchange or outdoor activities. Selected workshops may be invited to submit their workshop proceedings for publication as part of a new series of monographs for the post-NIPS workshops. Workshop organizers have several responsibilities including: * Coordinating workshop participation and content, which includes - arranging short informal presentations by experts, - arranging for expert commentators to sit on a discussion panel, - formulating a set of discussion topics, etc. * Moderating the discussion, and reporting its findings and conclusions to the group during evening plenary sessions. * Writing a brief summary and/or coordinating submitted material for post-conference electronic dissemination. SUBMISSION INSTRUCTIONS Interested parties should submit a short proposal for a workshop of interest via email by July 8, 2001. Proposals should include title, description of what the workshop is to address and accomplish, proposed workshop length (1 or 2 days), planned format (e.g., lectures, group discussions, panel discussion, combinations of the above, etc.), and proposed speakers. Names of potential invitees should be given where possible. Preference will be given to workshops that reserve a significant portion of time for open discussion or panel discussion, as opposed to pure ``mini-conference'' format. An example format is: * Tutorial lecture providing background and introducing terminology relevant to the topic. * Two short lectures introducing different approaches, alternating with discussions after each lecture. * Discussion or panel presentation. * Short talks or panels alternating with discussion and question/answer sessions. * General discussion and wrap-up. We suggest that organizers allocate at least 50% of the workshop schedule to questions, discussion, and breaks. Past experience suggests that workshops otherwise degrade into mini-conferences as talks begin to run over. For the same reason, we strongly recommend that each workshop include no more than 12 talks. The proposal should motivate why the topic is of interest or controversial, why it should be discussed, and who the targeted group of participants is. It also should include a brief resume of the prospective workshop chair with a list of publications to establish scholarship in the field. We encourage workshops that build, continue, or arise from one or more workshops from previous years. Please mention any such connections. NIPS does not provide travel funding for workshop speakers. In the past, some workshops have sought and received funding from external sources to bring in outside speakers. In addition, the organizers of each accepted workshop can name up to four people (six people for 2-day workshops) to receive free registration for the workshop program. Submissions should include contact name (if there is more than one organizer, please designate one organizer as the ``contact person'') as well as addresses, email addresses, phone and fax numbers for all organizers. Proposals should be emailed as plain text to nips-workshop-proposal at cs.unm.edu. Please do not use attachments, Microsoft Word, postscript, html, or pdf files. Questions may be addressed to nips-workshop-admin at cs.unm.edu. Information about the main conference and the workshop program can be found at http://www.cs.cmu.edu/Web/Groups/NIPS. Virginia de Sa, University of California, San Francisco Barak Pearlmutter, University of New Mexico NIPS*2001 Workshops Co-Chairs PROPOSALS MUST BE RECEIVED BY JULY 8, 2001 -Please Post- From r.roy at cranfield.ac.uk Fri Jun 1 13:01:12 2001 From: r.roy at cranfield.ac.uk (Roy, Rajkumar) Date: Fri, 1 Jun 2001 18:01:12 +0100 Subject: CFP: Applied Soft Computing Journal Message-ID: <2812AF10DCF1D41192DD0008C74C244C199DBB@oulton.sims.cranfield.ac.uk> ================================================== APPLIED SOFT COMPUTING Publisher: Elsevier Science The Official Journal of the World Federation on Soft Computing (WFSC) Journal homepage: http://www.elsevier.com/locate/asoc/ =================================================== CALL FOR PAPERS ************************ Applied Soft Computing is an international journal promoting an integrated view of soft computing to solve real life problems. Soft computing is a collection of methodologies, which aim to exploit tolerance for imprecision, uncertainty and partial truth to achieve tractability, robustness and low solution cost. The focus is to publish the highest quality research in application and convergence of the areas of Fuzzy Logic, Neural Networks, Evolutionary Computing, Rough Sets and other similar techniques to address real world complexities. Applied Soft Computing is a 'rolling' publication: articles are published as soon as the editor in chief has accepted them. Therefore, the web site will continuously be updated with new articles and the publication time will be short. Major topics ------------ The scope of this journal covers the following soft computing and related techniques, interactions between several soft computing techniques, and their industrial applications: * Fuzzy Computing * Neuro Computing * Evolutionary Computing * Probabilistic Computing * Immunological Computing * Hybrid Methods * Intelligent Agents and Agent Theory * Causal Models * Case-based Reasoning * Chaos Theory * Interactive Computational Models The application areas of interest include but are not limited to: * Decision Support * Process and System Control * System Identification and Modelling * Optimisation * Signal or Image Processing * Vision or Pattern Recognition * Condition Monitoring * Fault Diagnosis * Systems Integration * Internet Tools * Human-Machine Interface * Time Series Prediction * Robotics * Motion Control and Power Electronics * Biomedical Engineering * Virtual Reality * Reactive Distributed AI * Telecommunications * Consumer Electronics * Industrial Electronics * Manufacturing Systems * Power and Energy * Data Mining * Data Visualisation * Intelligent Information Retrieval * Bio-inspired Systems * Autonomous Reasoning * Intelligent Agents Publication ----------- Authors are invited to submit technical papers(no limit on max. number of pages), state of the art survey papers, industry reports (max. 5 pages) and book reviews. Authors are encouraged to utilise the opportunity given by this on-line publication to include animations, software demonstrations, and video clips etc. The papers will be published on Elsevier Science Web Site as soon as they are accepted, which enables authors to publish their work FAST and readers get the latest work in Soft Computing on their desktop! There will be a free hardcopy of volume available to authors by the end of the year. So have your latest research published on the Applied Soft Computing Website and get a FREE hardcopy of the volume that includes your paper later. For any further queries, paper submission and special issue proposals, please contact: Dr. Rajkumar Roy Editor in Chief 'Applied Soft Computing' Department of Enterprise Integration, School of Industrial and Manufacturing Science, Cranfield University, Cranfield, Bedford, MK43 0AL, United Kingdom. Tel: +44 (0)1234 754072 or +44 (0)1234 750111 Ext. 2423 , Fax: +44 (0)1234 750852 Email: asoc at cranfield.ac.uk Journal Website: http://www.elsevier.com/locate/asoc/ ---------------------------------------------------------------------------- -------- From benus at elf.stuba.sk Tue Jun 5 10:28:25 2001 From: benus at elf.stuba.sk (Lubica Benuskova) Date: Tue, 5 Jun 2001 16:28:25 +0200 (MET DST) Subject: Paper on experience-dependent cortical plasticity Message-ID: Dear Connectionists, the preprint of the following article: "Theory for normal and impaired experience-dependent plasticity in neocortex of adult rats" Proc. Natl. Acad. Sci. USA 98(5): 2797-2802, 2001. by Benuskova L, Rema V, Armstrong-James M and Ebner FF can be downloaded from http://www.dcs.elf.stuba.sk/~benus/#publications Abstract: We model experience-dependent plasticity in the cortical representation of whiskers (the barrel cortex) in normal adult rats, and in adult rats that were prenatally exposed to alcohol. Prenatal exposure to alcohol (PAE) caused marked deficits in experience-dependent plasticity in a cortical barrel-column. Cortical plasticity was induced by trimming all whiskers on one side of the face except two. This manipulation produces high activity from the intact whiskers which contrasts with low activity from the cut whiskers while avoiding any nerve damage. By a computational model we show that the evolution of neuronal responses in a single barrel-column following this sensory bias is consistent with the synaptic modifications that follow the rules of the Bienenstock, Cooper and Munro (BCM) theory. The BCM theory postulates that a neuron possesses a moving synaptic modification threshold, $\theta_M$, which dictates whether the neuron's activity at any given instant will lead to strengthening or weakening of its input synapses. The current value of $\theta_M$ changes proportionally to the square of the neuron's activity averaged over some recent past. In the model of alcohol impaired cortex, the effective $\theta_M$ has been set to a level unattainable by the depressed levels of cortical activity. Abnormally low activity leads to ``impaired'' synaptic plasticity that is consistent with experimental findings. Based on experimental and computational results we discuss how elevated $\theta_M$ may be related to the abnormally low expression of N-methyl-D-aspartate receptors (NMDARs) and the membrane translocation of Ca$^{2+}$/calmodulin-dependent protein kinase II (CaMKII) in adult rat cortex subjected to prenatal alcohol exposure. Lubica Benuskova, PhD ------------------------------------------------------- Slovak Technical University Dept. of Computer Science and Engineering Ilkovicova 3, 812 19 Bratislava 1, Slovakia ------------------------------------------------------- Phone: (+421 7) 602 91 696 Fax: (+421 7) 654 20 587 E-mail: benus at elf.stuba.sk, benus at dcs.elf.stuba.sk http://www.dcs.elf.stuba.sk/~benus From JaneD at tandf.co.uk Wed Jun 6 04:09:45 2001 From: JaneD at tandf.co.uk (Jane Dawson) Date: Wed, 6 Jun 2001 09:09:45 +0100 Subject: OPAL/Cognitive Neuropsychology Message-ID: <001801c0ee60$0cc82bd0$a97775c1@tandf.co.uk> Dear Colleague I am pleased to announce that Psychology Press, part of the Taylor & Francis Group, have just launched OPAL - Online Psychology Alerting - a FREE service for those with a specific interest in behavioural sciences. This is a special email service designed to deliver tables of contents for any Psychology Press, Taylor & Francis, Brunner-Routledge, or Carfax behavioural science journal in advance of publication, to anyone who has requested the information. All you need to do is register, and you will be sent contents pages of the journal(s) of your choice from that point onwards, in advance of the printed edition. You can request contents pages either for any number of individual titles, or for one or more of our sub-categories or a main category, and you may unsubscribe at any time. For each of your choices, you will receive the relevant bibliographic information: journal title, volume/issue number and the ISSN. You will also receive full contents details, names of authors and the appropriate page numbers from the printed version. This will give you advance notice of what is being published, making it easier for you to retrieve the exact information you require from the hard copy once it arrives in your library, or electronically from the online version of the journal. Titles that may be of interest are: Cognitive Neuropsychiatry Cognitive Neuropsychology European Journal of Cognitive Psychology Thinking and Reasoning Visual Cognition Laterality Memory To register for this complimentary service, please visit: http://www.psypress.co.uk/opal/ and click on the OPAL button. For further information on the above titles, please visit: http://www.psypress.co.uk/journals.html To find out more about online journals in behavioral science, please see the Psychology Online section of the Psychology Press website: http://www.psypress.co.uk If you have any questions regarding this service, please email: OPAL at psypress.co.uk From sfr at unipg.it Wed Jun 6 17:06:28 2001 From: sfr at unipg.it (Simone G.O. Fiori (Pg)) Date: Wed, 06 Jun 2001 23:06:28 +0200 Subject: Papers on neural and neuromorphic blind signal processing. Message-ID: <1.5.4.32.20010606210628.01811d00@unipg.it> Dear Connectionists, I would like to draw your attention to three new papers of potential interest to people working on unsupervised artificial neural networks and neuromorphic adaptive filtering for blind signal processing. Best regards, Simone Fiori Hybrid Independent Component Analysis by Adaptive LUT Activation Function Neurons ================================================================== by S. Fiori - Neural Networks and Adaptive Systems Research Group University of Perugia, Perugia (Italy) Journal: Neural Networks (Pergamon press) Download at: http://www.unipg.it/~sfr/publications/nnt2001.ps Abstract The aim of this paper is to present an efficient implementation of unsupervised adaptive-activation function neurons dedicated to one-dimensional probability density estimation, with application to independent component analysis. The proposed implementation is a computationally light improvement to adaptive pseudo-polynomial neurons, recently presented in (Fiori, 2000a), and bases upon the concept of `look-up table' (LUT) neurons. Keywords: Adaptive activation function neurons; Look-up-table neurons; Independent component analysis; Minimal mutual information principle; Kullback-Leibler divergence; Natural gradient. ~~~~~~~~~~~~~~~~~~~~ Notes on Cost Functions and Estimators for `Bussgang' Adaptive Blind Equalization ================================================================== by S. Fiori - Neural Networks and Adaptive Systems Research Group University of Perugia, Perugia (Italy) Journal: European Transactions on Telecommunications (ETT) Download at: http://www.unipg.it/~sfr/publications/ett2001.ps Abstract The aim of this paper is to present some remarks on the cost functions for blind channel equalization by `Bussgang' algorithms recently discused in the literature; also, some possible associated non-Bayesian estimators are considered with details, and the effects of the choice of such estimators in relation to `Bussgang' neuromorphic filtering are briefly investigated. ~~~~~~~~~~~~~~~~~~~~ A Contribution to (Neuromorphic) Blind Deconvolution by Flexible Approximated Bayesian Estimation ================================================================= by S. Fiori - Neural Networks and Adaptive Systems Research Group University of Perugia, Perugia (Italy) Journal: Signal Processing (Elsevier) Download at: http://www.unipg.it/~sfr/publications/SIGPROC2001.ps Abstract `Bussgang' deconvolution techniques for blind digital channels equalization rely on a Bayesian estimator of the source sequence defined on the basis of channel/equalizer cascade model which involves the definition of deconvolution noise. In this paper we consider four `Bussgang' blind deconvolution algorithms for uniformly-distributed source signals and investigate their numerical performances as well as some of their analytical features. Particularly, we show that the algorithm, introduced by the present author, provided by a flexible (neuromorphic) estimator is effective as it does not require to make any hypothesis about convolutional noise level and exhibits satisfactory numerical performances. =================================================== Dr Simone Fiori (EE, PhD)- Assistant Professor Neural Networks and Adaptive Systems Research Group DIE - University of Perugia - Perugia (Italy) eMail: sfr at unipg.it Fax: +39 0744 492925 Web: http://www.unipg.it/~sfr/ =================================================== From mschmitt at lmi.ruhr-uni-bochum.de Thu Jun 7 04:45:16 2001 From: mschmitt at lmi.ruhr-uni-bochum.de (Michael Schmitt) Date: Thu, 07 Jun 2001 10:45:16 +0200 Subject: Preprint on Local Receptive Field Neural Networks Message-ID: <3B1F3F1C.E1CF5ABA@lmi.ruhr-uni-bochum.de> Dear Connectionists, a preprint of the paper "Neural networks with local receptive fields and superlinear VC dimension" by Michael Schmitt is available on-line from http://www.ruhr-uni-bochum.de/lmi/mschmitt/receptive.ps.gz (39 pages gzipped PostScript). This paper has been accepted by Neural Computation in its first submitted version. (They say that this is the first time that they have accepted a first time submission.) Regards, Michael Schmitt ------------------------------------------------------------ TITLE: Neural networks with local receptive fields and superlinear VC dimension AUTHOR: Michael Schmitt ABSTRACT Local receptive field neurons comprise such well-known and widely used unit types as radial basis function neurons and neurons with center-surround receptive field. We study the Vapnik-Chervonenkis (VC) dimension of feedforward neural networks with one hidden layer of these units. For several variants of local receptive field neurons we show that the VC dimension of these networks is superlinear. In particular, we establish the bound $\Omega(W\log k)$ for any reasonably sized network with $W$ parameters and $k$ hidden nodes. This bound is shown to hold for discrete center-surround receptive field neurons, which are physiologically relevant models of cells in the mammalian visual system, for neurons computing a difference of Gaussians, which are popular in computational vision, and for standard radial basis function (RBF) neurons, a major alternative to sigmoidal neurons in artificial neural networks. The result for RBF neural networks is of particular interest since it answers a question that has been open for several years. The results also give rise to lower bounds for networks with fixed input dimension. Regarding constants all bounds are larger than those known thus far for similar architectures with sigmoidal neurons. The superlinear lower bounds contrast with linear upper bounds for single local receptive field neurons also derived here. -- Michael Schmitt LS Mathematik & Informatik, Fakultaet fuer Mathematik Ruhr-Universitaet Bochum, D-44780 Bochum, Germany Phone: +49 234 32-23209 , Fax: +49 234 32-14465 http://www.ruhr-uni-bochum.de/lmi/mschmitt/ From ken at phy.ucsf.edu Fri Jun 8 01:17:22 2001 From: ken at phy.ucsf.edu (Ken Miller) Date: Thu, 7 Jun 2001 22:17:22 -0700 Subject: Research Scientist Position: Probabilistic Modeling for Spike-Sorting Message-ID: <15136.24546.194623.9937@coltrane.ucsf.edu> RESEARCH SCIENTIST NEEDED: PROBABILISTIC MODELING FOR SPIKE SORTING Keck Center for Integrative Neuroscience UCSF San Francisco, CA We have an opening for a research scientist to work on developing methods for sorting "spikes" (action potentials) in neurophysiological recordings. This position pays a competitive professional salary. The problem of spike sorting is a challenging one of signal processing, time-series analysis, and unsupervised clustering, We plan to apply the methods of probabilistic modeling and model comparison. A starting point for our work will be the thesis work of Sahani, http://www.vis.caltech.edu/~maneesh/thesis/. The PI's on the project are Ken Miller (www.keck.ucsf.edu/~ken) and Philip Sabes (www.keck.ucsf.edu/~sabes), UCSF. The scientist will be expected to implement spike sorting algorithms, and in collaboration with the PI's to systematically test alternative algorithms and devise and test improved algorithms. Understanding of and experience with statistical inference and probabilistic modeling, or sufficient theoretical training to quickly master the same, is required; experience applying theoretical methods to analyze real data is strongly preferred. Sufficient scientific programming abilities to easily implement and test alternative algorithms is required. Prototyping will typically be done in Matlab, implementation in C or C++. It is expected that the candidate will have a Ph.D. in a quantitative field. The scientist will work closely with a programmer who will also be working fulltime on this project. The position is expected to run for approximately two years. Please send a CV and arrange to have two letters of reference sent to: Paul Puri Spikesorting Search Dept. of Physiology UCSF San Francisco, CA 94143-0444 or to spikesort at phy.ucsf.edu From Roberto.Prevete at na.infn.it Fri Jun 8 06:01:53 2001 From: Roberto.Prevete at na.infn.it (Roberto Prevete) Date: Fri, 08 Jun 2001 12:01:53 +0200 Subject: Preprint on AN ALGEBRAIC APPROACH TO THE AUTONOMOUSLY SELF-ADAPTABLE BOOLEAN NEURAL Message-ID: <3B20A28E.D5F278CB@na.infn.it> Dear Connectionists, a preprint of the book "AN ALGEBRAIC APPROACH TO THE AUTONOMOUSLY SELF-ADAPTABLE BOOLEAN NEURAL" by Francesco E. Lauria and Roberto Prevete is available on-line from http://www.na.infn.it/Gener/cyber/report.html, into the folder NeuralNetworks/News (zipped Word file) This book is in print by Liguori Ed. Via Posillipo 394 I-80123 Napoli, Italy (EU) ++39 081 720 61 11 phone Regards, Roberto Prevete ------------------------------------------------------------ TITLE: AN ALGEBRAIC APPROACH TO THE AUTONOMOUSLY SELF-ADAPTABLE BOOLEAN NEURAL AUTHORS: Francesco E. Lauria and Roberto Prevete INFM & Dipartimento di Scienze Fisiche, Universit? di Napoli Federico II Complesso Universitario di Monte Sant? Angelo, Via Vicinale Cupa Cintia 16 I-80126 Napoli, Italy (EU) lauria at na.infn.it CONTENTS Chapter 1 THE BOOLEAN NEURAL NET, OR BNN. Chapter 2. THE KNOWLEDGE REPRESENTATION IN THE BNN. Chapter 3. THE DATA STRUCTURE EMBEDDED IN A BNN. Chapter 4. THE BNN AND THE HEBBIAN RULE. Chapter 5. THE ADAPTABLE BNN, OR ABNN Chapter 6. A GABNN AS AN AUTONOMOUSLY SELF-TRAINABLE CONTROL SYSTEM. Chapter 7. THE JAVA PACKAGE IT.NA.CY.NNET. Chapter 8. CONCLUSIONS. From Andres.PerezUribe at unifr.ch Mon Jun 11 11:30:25 2001 From: Andres.PerezUribe at unifr.ch (Andres Perez-Uribe) Date: Mon, 11 Jun 2001 17:30:25 +0200 Subject: postdoc position in Fribourg, Switzerland Message-ID: <1010611173025.ZM25192@ufps25> Post-Doctoral Research Position The position ------------ The position is intended for an enthusiastic postgraduate, who have terminated her/his PhD studies. The candidate will participate in the research activities that are conducted within the WELCOME project. Her/his duties may concern : (i) the use of learning and evolutionary techniques to provide adaptation to the new network-oriented computing frameworks (ubiquitous computing and intelligent networks), (ii) the development of adaptable Agent-based methodologies for Internet-based infrastructures and mobile robots/devices, (iii) the tackling of Human Machine Interaction issues, together with supervision of two Ph.D research works. As far as possible she/he will build contacts with external academic or commercial organizations, and promote industrial applications of her/his research. Moreover, she/he will follow student projects realted to her/his topics of research. An open-mind to interdisciplinary approaches and to non-standard innovation techniques will be appreciated. The position is to be taken September 1st, 2001 (or at convenience). It is granted for two years by the Swiss National Foundation for Scientific Research (with a possibility of renewal once). Job location is Fribourg, a french-german bilingual middle-size city in Switzerland. The requirements ---------------- *Education: Ph.D in Computer Science (or a related area) *Ability to speak, read and write French or German or English *Proficient in one or several topics, such as: * Autonomous mobile robots, Adaptive Systems * Agent Technology, Multi-Agent Systems * Artificial Neural Networks, Artificial Life, Evolutionary Computing * Intelligent Networks, Distributed Systems and/or Coordination Languages, * Human Computer Interaction, Immersive and Ubiquitous Computing, Force-feedback interaction, Augmented or virtual reality * Object-Oriented design techniques, Java programming, Jini technology The research group ------------------ The Parallelism and Artificial Intelligence (PAI) group is a rapidly growing and dynamic research group that concentrates its research on hot topics related to new information and communication technologies. His interests encompass namely the methodologies of Autonomous and Adaptive Systems, Collective Intelligence, Evolutionary Computing, Agent Technology, Massively Distributed Systems, and Intelligent Networks, but also the field of Human Computer Interaction, where it addresses specifically the Immersive trend and Ubiquitous Computing. Research resources ------------------ The group holds a UNIX workstation environment, and PC and Macintosh machines. In particular, it possesses about 20 Khepera robots: 7 of them are equipped with radio communication modules, grippers (arms), and linear vision, and one of them has a CCD color camera. We have explored both single-robot learning tasks and collective robotic behaviors (See the description of the CALIMA and AMOC projects). Moreover, we are acquiring new mobile devices (wearable eyeglasses, PALM devices, etc.) for our research in Ubiquitous computing, human-machine interfaces, and intelligent networks. Applications with CV and research paper list must be sent to (Email submissions are encouraged): Prof. Bat Hirsbrunner University of Fribourg, ch. du Muse 3, CH-1700 Fribourg Tel.: +41 (0)26 300 8465 (secretariat - morning) Email: beat.hirsbrunner at unifr.ch URL: http://www-iiuf.unifr.ch/pai/ ----------------------------------------------------------------------- -- Andres PEREZ-URIBE Postdoctoral Fellow and Lecturer Parallelism and Artificial Intelligence Group (PAI) Department of Informatics, University of Fribourg, Switzerland Ch. du Musee 3, CH-1700 Fribourg, Office 2.76b Perolles Tel. +41-26-300-8473, Fax +41-26-300-9731 Email:Andres.PerezUribe at unifr.ch, http://www-iiuf.unifr.ch/~aperezu/ From j-patton at northwestern.edu Mon Jun 11 12:18:31 2001 From: j-patton at northwestern.edu (Jim Patton) Date: Mon, 11 Jun 2001 11:18:31 -0500 Subject: Preprint: Linear combinations of nonlinear models Message-ID: <4.2.0.58.20010611110945.00ac8be0@merle.acns.nwu.edu> The following paper has been accepted by Biological Cybernetics. Preprints are available from: LINEAR COMBINATIONS OF NONLINEAR MODELS FOR PREDICTING HUMAN-MACHINE INTERFACE FORCES James L. Patton & Ferdinando A. Mussa-Ivaldi Sensory Motor Performance Program, Rehabilitation Institute of Chicago Physical Medicine and Rehabilitation, Northwestern University Medical School In press, Biological Cybernetics, May, 2001 ABSTRACT This study presents a computational framework that capitalizes on known human neuromechanical characteristics during limb movements in order to predict man-machine interactions. A parallel-distributed approach, the mixture of nonlinear models, fits the relationship between the measured kinematics and kinetics at the handle of a robot. Each element of the mixture represented the arm and its controller as a feedforward nonlinear model of inverse dynamics plus a linear approximation of musculotendonous impedance. We evaluated this approach with data from experiments where subjects held a handle of a planar manipulandum robot and attempted to make point-to-point reaching movements. We compared the performance to the more conventional approach of a constrained, nonlinear optimization of the parameters. On average, the mixture of nonlinear models accounted for 0.79 0.11 (1 SD), and force errors were 0.73% 0.20% of the maximum exerted force. Solutions were acquired in half the time with significantly better fit. However, both approaches equally suffered from the simplifying assumptions, namely, that the human neuromechanical system consisted of a feedforward controller coupled with linear impedances and a moving state equilibrium. Hence, predictability was best limited to the first half of the movement. The mixture of nonlinear models may be useful in man-machine tasks such as in telerobotics, fly-by-wire vehicles, robotic training and rehabilitation. ______________________________________________________________________ J A M E S P A T T O N , P H . D . Research Scientist Sensory Motor Performance Prog., Rehabilitation Institute of Chicago Physical Med & Rehabilitation, Northwestern University Med School 345 East Superior, Room 1406, Chicago, IL 60611 312-238-1277 (OFFICE) -2208 (FAX) -1232 (LAB) -3381 (SECRETARY) CELL PHONE MESSAGING (<150 char.): 8473341056 at msg.myvzw.com ______________________________________________________________________ From clinton at compneuro.umn.edu Mon Jun 11 15:29:25 2001 From: clinton at compneuro.umn.edu (Kathleen Clinton) Date: Mon, 11 Jun 2001 14:29:25 -0500 Subject: NEURON Workshop Announcement Message-ID: <3B251C15.56A57B6F@compneuro.umn.edu> ****************************** NEURON Workshop Announcement ****************************** Michael Hines and Ted Carnevale of Yale University will conduct a three to five day workshop on NEURON, a computer code that simulates neural systems. The workshop will be held from August 20-24, 2001 at the University of Minnesota Supercomputing Institute in Minneapolis, Minnesota. Registration is open to students and researchers from academic, corporate, and industrial organizations. Space is limited, and registrations will be accepted on a first-come, first-serve basis. **Topics and Format** Participants may attend the workshop for three or five days. The first three days cover material necessary for the most common applications in neuroscience research and education. The fourth and fifth days deal with advanced topics of users whose projects may require problem-specific customizations. Windows and Linux platforms will be used on computers provided by IBM. Days 1 - 3 "Fundamentals of Using the NEURON Simulation Environment" The first three days will cover the material that is required for informed use of the NEURON simulation environment. The emphasis will be on applying the graphical interface, which enables maximum productivity and conceptual control over models while at the same time reducing or eliminating the need to write code. Participants will be building their own models from the start of the course. By the end of the third day they will be well prepared to use NEURON on their own to explore a wide range of neural phenomena. Topics will include: Integration methods --accuracy, stability, and computational efficiency --fixed order, fixed timestep integration --global and local variable order, variable timestep integration Strategies for increasing computational efficiency. Using NEURON's graphical interface to --construct models of individual neurons with architectures that range from the simplest spherical cell to detailed models based on quantitative morphometric data (the CellBuilder). --construct models that combine neurons with electronic instrumentation (i.e. capacitors, resistors, amplifiers, current sources and voltage sources) (the Linear Circuit Builder). --construct network models that include artificial neurons, model cells with anatomical and biophysical properties, and hybrid nets with both kinds of cells (the Network Builder). --control simulations. --display simulation results as functions of time and space. --analyze simulation results. --analyze the electrotonic properties of neurons. Adding new biophysical mechanisms. Uses of the Vector class such as --synthesizing custom stimuli --analyzing experimental data --recording and analyzing simulation results Managing modeling projects. Days 4 and 5 "Beyond the GUI" The fourth and fifth days deal with advanced topics for users whose projects may require problem-specific customizations. Topics will include: Advanced use of the CellBuilder, Network Builder, and Linear Circuit Builder. When and how to modify model specification, initialization, and NEURON's main computational loop. Exploiting special features of the Network Connection class for efficient implementation of use-dependent synaptic plasticity. Using NEURON's tools for optimizing models. Parallelizing computations. Using new features of the extracellular mechanism for --extracellular stimulation and recording --implementation of gap junctions and ephaptic interactions Developing new GUI tools. **Registration** For academic or government employees the registration fee is $155 for the first three days and $245 for the full five days. These fees are $310 and $490, respectively, for corporate or industrial participants. Registration forms can be obtained at www.compneuro.umn.edu/NEURONregistration.html or from the workshop coordinator, Kathleen Clinton, at clinton at compneuro.umn.edu or (612) 625-8424. **Lodging** Out-of-town participants may stay at the Holiday Inn Metrodome in Minneapolis. It is within walking distance of the Supercomputing Institute. Participants are responsible for making their own hotel reservations. When making reservations, participants should state that they are attending the NEURON Workshop. A small block of rooms is available until July 28, 2001. Reservations can be arranged by calling (800) 448-3663 or (612) 333-4646. From luca at idsia.ch Mon Jun 11 06:53:16 2001 From: luca at idsia.ch (Luca Maria Gambardella) Date: Mon, 11 Jun 2001 12:53:16 +0200 Subject: IDSIA: Two Post DOC Positions in Robotics, Swarm Intelligence and Machine learning Message-ID: <5.0.2.1.0.20010611123223.04abf040@mailhost.idsia.ch> Apologize for multiple copies. ============================================================================== Job Opening in Robotics, Swarm Intelligence, Machine Learning and Simulation ============================================================================== TWO POST DOC POSITIONS for 3 years funded by the Future and Emerging Technologies (FET) program of the Commission of the European Community is open for applications. IDSIA, http://www.idsia.ch Istituto Dalle Molle di Studi sull'Intelligenza Artificiale, Galleria 2, 6928 Manno-Lugano, Switzerland APPLICATION DEADLINE: July 30th 2001 STARTING: October 2001: We are looking for two Post Doctoral candidates to work on the new European Project SWARM-BOTS starting October 2001. SWARM-BOTS is about the design and implementation of self-organising and self assembling artifacts called swarm-bots. The approach is inspired by recent studies in swarm intelligence, i.e., by studies of the self-organising and self-assembling capabilities shown by social insects and other animal societies. The main scientific goal of the project is a better understanding of swarm intelligence principles and of the use of these principles in engineering, while the main tangible goal is the demonstration of the validity of the approach followed by means of the construction of at least one such artifact. The expected results are therefore the further development of the swarm intelligence discipline and the design and construction of a first example of swarm-bots, that is, an artifact composed of a number of simpler robots capable of self-assembling and self-organising to adapt to its environment. The project will last 36 months and will see the combined effort of scientists from four European laboratories (IRIDIA Bruxelles, IDSIA Lugano, EPFL Lausanne, CNR-IP Rome) ====================== CONTACT INFORMATION ===================== If you wish to apply, please send (i) Detailed curriculum vitae (ii) List of three references (and their email addresses) (iii) Transcripts of undergraduate and graduate (if applicable) studies (iv) Concise statement of your research interests (two pages max). Candidates are also encouraged to submit their scores in the Graduate Record Examination (GRE) general test (if available). Applications can also be submitted electronically (in plain ASCII or postscript format) to mailto:luca at idsia.ch. Please connect "SWB2001PD" with your first and last name in the message subject. Please send all documents to: Luca Maria Gambardella IDSIA Galleria 2 6928 Manno-Lugano Switzerland Phone : +41 91 - 610 8663 Fax : +41 91 - 610 8661 Secretary: +41 91 - 6108660 mailto:luca at idsia.ch http://www.idsia.ch/luca From zemel at cs.toronto.edu Wed Jun 13 16:46:25 2001 From: zemel at cs.toronto.edu (Richard Zemel) Date: Wed, 13 Jun 2001 16:46:25 -0400 Subject: Reminder: Upcoming deadlines for NIPS*2001 Message-ID: <01Jun13.164647edt.453154-28229@jane.cs.toronto.edu> ========================================== Neural Information Processing Systems Natural and Synthetic Monday, Dec. 3 -- Saturday, Dec. 8, 2001 Vancouver, British Columbia, Canada Whistler Ski Resort ========================================== Deadlines: PAPER SUBMISSIONS: June 20, 2001 WORKSHOP PROPOSALS: July 8, 2001 For submission info, see http://www.cs.cmu.edu/Web/Groups/NIPS Invited speakers: Barbara Finlay -- How brains evolve, and the consequences for computation Alison Gopnik -- Babies and Bayes-nets: Causal inference and theory-formation in children, chimps, scientists and computers Jon M. Kleinberg -- Decentralized network algorithms: Small-world phenomena and the dynamics of information Tom Knight -- TBA Judea Pearl -- Causal inference as an exercise in computational learning Shihab Shamma -- Common principles in auditory and visual processing Tutorials: Luc Devroye -- Nonparametric density estimation: VC to the rescue Daphne Koller & Nir Friedman -- Learning Bayesian networks from data Shawn Lockery -- Chemotaxis: Gradient ascent by simple living organisms and their neural networks. Christopher Manning -- Probabilistic linguistics and probabilistic models of natural language processing Bernhard Scholkopf -- SVM and Kernel methods Sebastian Thrun -- Probabilistic robotics Also...remember that NIPS is heading north this year, to Vancouver From isahara at crl.go.jp Wed Jun 13 07:42:41 2001 From: isahara at crl.go.jp (ISAHARA Hitoshi) Date: Wed, 13 Jun 2001 20:42:41 +0900 Subject: CFP [NLPNN2001] Message-ID: <200106131142.UAA22552@lettuce.crl.go.jp> ==================================================================== Call for Papers --- NLPRS2001 Workshop The Second Workshop on Natural Language Processing and Neural Networks (NLPNN2001) Tokyo, Japan, November 30, 2001 http://www2.crl.go.jp/jt/a132/members/qma/NLPNN2001/index.html Artificial neural networks (ANN) based natural language processing (NLP) research began in the early 1980s with papers on implementing semantic networks in ANNs, word-sense disambiguation, anaphora resolution, and syntactic parsing. Since then, with the boom of NLP research based on very large corpora, the ANN, as a powerful parallel and distributed learning/processing machine, attract a more great deal of attention from both the ANN and NLP researchers and have been successfully used in many areas of NLP. This second workshop on NLP and ANN is to be held in Tokyo as a post-conference workshop of NLPRS2001. It continues the work of the first workshop on NLP and ANN, NLPNN99, successfully held in Beijing two years ago. NLPNN2001 will provide a forum for researchers in the areas of ANN and NLP who are interested in advancing the state of the art in developing NLP techniques using neural networks. For more information on NLPRS2001, see . The papers presented at NLPNN99 are available from . Submissions are invited on all NLP topics in the context of using ANN techniques. A submission consists of a two-page summary (2000 words or less), accompanied by paper title, author information including full names, affiliations of all authors, and the postal and email addresses of the corresponding author. Submissions will be reviewed by the Workshop Program Committee, and authors will be notified of acceptance or rejection by email. Submit by email to qma at crl.go.jp IMPORTANT DATES Summary submission deadline: July 31, 2001 Notification of acceptance: August 15, 2001 Camera ready papers due: September 26, 2001 Inquiries concerning the workshop can be sent to one of the organizers either by email to qma at crl.go.jp or by post to the following address: Dr. Qing Ma Computational Linguistics Group Keihanna Human Info-Communication Research Center Communications Research Laboratory 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0289, Japan Organizers Hitoshi Isahara (Communications Research Laboratory, Japan) Qing Ma (Communications Research Laboratory, Japan) Program Committee Qing Ma (Communications Research Laboratory, Japan), Chair Gary Geunbae Lee (Pohang University of Science and Technology, Korea) Caroline Lyon (University of Hertfordshire, UK) Daniel Memmi (LEIBNIZ-IMAG, France) Risto Miikkulainen (University of Texas, USA) Ron Sun (University of Missouri-Columbia, USA) Naoto Takahashi (AIST, Japan) Ming Zhou (Microsoft Research China, China) other members will be announced shortly ==================================================================== From kap-listman at wkap.nl Wed Jun 13 20:18:16 2001 From: kap-listman at wkap.nl (kap-listman@wkap.nl) Date: Thu, 14 Jun 2001 02:18:16 +0200 (METDST) Subject: New Issue: Neural Processing Letters. Vol. 13, Issue 3 Message-ID: <200106140018.CAA13709@wkap.nl> Kluwer ALERT, the free notification service from Kluwer Academic/PLENUM Publishers and Kluwer Law International ------------------------------------------------------------ Neural Processing Letters ISSN 1370-4621 http://www.wkap.nl/issuetoc.htm/1370-4621+13+3+2001 Vol. 13, Issue 3, June 2001. TITLE: Sequential Extraction of Minor Components AUTHOR(S): Tianping Chen, Shun-Ichi Amari, Noboru Murata KEYWORD(S): minor component, sequential algorithm. PAGE(S): 195-201 TITLE: Evolving Stacked Time Series Predictors with Multiple Window Scales and Sampling Gaps AUTHOR(S): Zheng Rong Yang, Weiping Lu, Robert G. Harrison KEYWORD(S): evolutionary programming, forecasting, neural networks, stacking, time series. PAGE(S): 203-211 TITLE: Reinforcement Learning Using the Stochastic Fuzzy Min-Max Neural Network AUTHOR(S): Aristidis Likas KEYWORD(S): fuzzy min-max neural network, pole balancing problem, reinforcement learning, stochastic automaton. PAGE(S): 213-220 TITLE: Recursive Partitioning Technique for Combining Multiple Classifiers AUTHOR(S): Terry Windeatt KEYWORD(S): binary feature, constructive, ensemble, MLP, monotonic, multiple classifier, partition, separable, spectral, support vector. PAGE(S): 221-236 TITLE: Temporal Kohonen Map and the Recurrent Self-Organizing Map: Analytical and Experimental Comparison AUTHOR(S): Markus Varsta, Jukka Heikkonen, Jouko Lampinen, Jose Del R. Millan KEYWORD(S): convergence analysis, self-organizing maps, temporal sequence processing. PAGE(S): 237-251 TITLE: Maharadja: A System for the Real Time Simulation of RBF with the Mahalanobis Distance AUTHOR(S): Bertrand Granado, Andrea Pinna, Luc Gaborit, Patrick Garda KEYWORD(S): FPGA, low-power consumption, Mahalanobis distance, neural hardware, RBF, real time. PAGE(S): 253-266 TITLE: A Neuro-Based Optimization Algorithm for Tiling Problems with Rotation AUTHOR(S): Shinsuke Manabe, Hideki Asai KEYWORD(S): analog neural network, rotation of polyominoes, tiling problem, 2-D neural array. PAGE(S): 267-275 TITLE: Authors index AUTHOR(S): KEYWORD(S): analog neural network, rotation of polyominoes, tiling problem, 2-D neural array. PAGE(S): 277-277 TITLE: Volume contents AUTHOR(S): KEYWORD(S): analog neural network, rotation of polyominoes, tiling problem, 2-D neural array. PAGE(S): 279-280 -------------------------------------------------------------- Thank you for your interest in Kluwer's books and journals. NORTH, CENTRAL AND SOUTH AMERICA Kluwer Academic Publishers Order Department, PO Box 358 Accord Station, Hingham, MA 02018-0358 USA Telephone (781) 871-6600 Fax (781) 681-9045 E-Mail: kluwer at wkap.com EUROPE, ASIA AND AFRICA Kluwer Academic Publishers Distribution Center PO Box 322 3300 AH Dordrecht The Netherlands Telephone 31-78-6392392 Fax 31-78-6546474 E-Mail: orderdept at wkap.nl From dbarber at dai.ed.ac.uk Fri Jun 15 13:01:32 2001 From: dbarber at dai.ed.ac.uk (David Barber) Date: Fri, 15 Jun 2001 18:01:32 +0100 Subject: Research Fellowship: Graphical Models Message-ID: <3B2A3F6B.2F51E7D2@dai.ed.ac.uk> UNIVERSITY OF EDINBURGH: DIVISION OF INFORMATICS RESEARCH FELLOWSHIP IN GRAPHICAL MODELS The project, which runs for three years, aims to exploit the interface between models and techniques in physics (statistical mechanics) and informatics. Whilst the project is primarily theoretical, the emphasis is to study systems and techniques with direct application in areas of probabilistic inference in large stochastic systems, including pattern processing, error correcting codes, and cryptography. The scope of the project is broad and includes potentially the modelling of complex biological systems. Ideally you will have postgraduate experience in the mathematical, physical or computing sciences Salary scale: 16,775 - 25,213 Pounds Sterling Per Annum Please quote Ref: 316428WW For further particulars and an application pack visit our web site (www.ed.ac.uk) or telephone the recruitment line on 0131-650-2511. Closing Date: 29 JUNE 2001 Further Particulars: ==================== RESEARCH FELLOWSHIP IN GRAPHICAL MODELS The Institute for Adaptive and Neural Computation, part of the Division of Informatics, seeks a research fellow in the field of Graphical Models. The aim of the project is to develop methods to deal with large scalestochastic systems with applications in machine learning and related fields. The framework within which this work will be carried out is Graphical Models, which exploit graph theoretic concepts in a probabilistic setting. The project aims to exploit the interface between models and techniques in physics (statistical mechanics) and informatics. Whilst the project is primarily theoretical, the emphasis is to study systems and techniques with direct application in areas of probabilistic inference, including pattern processing, error correcting codes, and cryptography. The scope of the project is broad and includes potentially the modelling of complex biological systems. Skills and Qualifications: The candidate is expected to have postgraduate experience in the mathematical, physical or computing sciences. Familiarity with statistical mechanics and Graphical Models would be an advantage. The candidate should be highly motivated and keen to participate in a lively interdisciplinary environment. The position is available for a period of three years. For informal enquiries, please contact David Barber dbarber at dai.ed.ac.uk Tel +44 (0)131 650 4491; Fax +44 (0)870 130 5014 From wahba at stat.wisc.edu Fri Jun 15 20:14:01 2001 From: wahba at stat.wisc.edu (Grace Wahba) Date: Fri, 15 Jun 2001 19:14:01 -0500 (CDT) Subject: On the \xi\alpha and GACV for tuning SVM's Message-ID: <200106160014.TAA04917@hera.stat.wisc.edu> Paper available: "On the Relation Between the GACV and Joachims' \xi\alpha Method for Tuning Support Vector Machines, With Extensions to the Nonstandard Case". by Grace Wahba, Yi Lin, Yoonkyung Lee and Hao Zhang UW-Madison Statistics TR 1039 ftp://ftp.stat.wisc.edu/pub/wahba/xan.ps Abstract We rederive a form of Joachims' $\xi\alpha$ method for tuning Support Vector Machines by the same approach as was used to derive the GACV, and show how the two methods are related. We generalize the $\si\alpha$ method to the nonstandard case of nonrepresentative training set and unequal misclassification costs and compare the results to the GACV estimate for the standard and nonstandard cases. From rsun at cecs.missouri.edu Sun Jun 17 13:40:55 2001 From: rsun at cecs.missouri.edu (rsun@cecs.missouri.edu) Date: Sun, 17 Jun 2001 12:40:55 -0500 Subject: THE INTERACTION OF EXPLICIT AND IMPLICIT LEARNING: A Symposium at CogSci'2001 Message-ID: <200106171740.f5HHete27995@ari1.cecs.missouri.edu> THE INTERACTION OF EXPLICIT AND IMPLICIT LEARNING A Symposium at CogSci'2001 (August 1-4, 2001), Edinburgh, Scotland =============================================================== Titles of the Talks: Axel Cleeremans: ``Behavioral, neural, and computational correlates of implicit and explicit learning" Zoltan Dienes: ``The effect of prior knowledge on implicit learning" Bob Mathews: ``Finding the optimal mix of implicit and explicit learning" Ron Sun: ``The synergy of the implciit and the explicit" ================================================================= The symposium will be held on August 4th, 2001, 2:30 - 4:10 pm. See http://www.hcrc.ed.ac.uk/cogsci2001/programme.html for futher details of the 23rd Cognitive Science Conference, Edinburgh, Scotland. ================================================================= Background: The role of implicit learning in skill acquisition and the distinction between implicit and explicit learning have been widely recognized in recent years (see, e.g., Reber 1989, Stanley et al 1989, Willingham et al 1989, Anderson 1993), Although implicit learning has been actively investigated, the complex and multifaceted interaction between the implicit and the explicit and the importance of this interaction have not been universally recognized; to a large extent, such interaction has been downplayed or ignored, with only a few notable exceptions. Research has been focused on showing the LACK of explicit learning in various learning settings (see especially Lewicki et al 1987) and on the controversies stemming from such claims. Despite the lack of studies of interaction, it has been gaining recognition that it is difficult, if not impossible, to find a situation in which only one type of learning is engaged (Reber 1989, Seger 1994, but see Lewicki et al 1987). Our review of existing data has indicated that, while one can manipulate conditions to emphasize one or the other type, in most situations, both types of learning are involved, with varying amounts of contributions from each (see, e.g., Sun et al 2000; see also Stanley et al 1989, Willingham et al 1989). Likewise, in the development of cognitive architectures (e.g., Rosenbloom et al 1993, Anderson 1993), the distinction between procedural and declarative knowledge has been proposed for a long time, and advocated or adopted by many in the field (see especially Anderson 1993). The distinction maps roughly onto the distinction between the explicit and implicit knowledge, because procedural knowledge is generally inaccessible while declarative knowledge is generally accessible and thus explicit. However, in work on cognitive architectures, focus has been almost exclusively on ``top-down" models (that is, learning first explicit knowledge and then implicit knowledge on the basis of the former), the bottom-up direction (that is, learning first implicit knowledge and then explicit knowledge, or learning both in parallel) has been largely ignored, paralleling and reflecting the related neglect of %the complex and multifaceted the interaction of explicit and implicit processes in the skill learning literature. However, there are a few scattered pieces of work that did demonstrate the parallel development of the two types of knowledge or the extraction of explicit knowledge from implicit knowledge (e.g, Willingham et al 1989, Stanley et al 1989, Sun et al 2000), contrary to usual top-down approaches in developing cognitive architectures. Many issues arise with regard to the interaction between implicit and explicit processes, which we need to look into if we want to better understand this interaction: How can we best capture implicit processes computationally? How can we best capture explicit processes computationally? How do the two types of knowledge develop along side each other and influence each other's development? Is bottom-up learning (or parallel learning) possible, besides top-down learning? How can they (bottom-up learning, top-down learning, and parallel learning) be realized computationally? How do the two types of acquired knowledge interact during skilled performance? What is the impact of that interaction on performance? How do we capture such impact computationally? =========================================================================== Prof. Ron Sun http://www.cecs.missouri.edu/~rsun CECS Department phone: (573) 884-7662 University of Missouri-Columbia fax: (573) 882 8318 201 Engineering Building West Columbia, MO 65211-2060 email: rsun at cecs.missouri.edu http://www.cecs.missouri.edu/~rsun http://www.cecs.missouri.edu/~rsun/journal.html http://www.elsevier.com/locate/cogsys =========================================================================== From ingber at ingber.com Tue Jun 19 08:08:44 2001 From: ingber at ingber.com (Lester Ingber) Date: Tue, 19 Jun 2001 07:08:44 -0500 Subject: Computational Finance Position Message-ID: <20010619070843.A11248@ingber.com> Updated on http://www.ingber.com/drw_positions.html If you have very strong credentials for a position described below, please send your resume to: Prof. Lester Ingber Director Research & Development DRW Investments LLC [http://www.drwtrading.com] 311 S Wacker Dr Ste 900 Chicago, IL 60606 Email (preferred) ingber at drwtrading.com Computational Finance Position Experienced programmer in Maxima/Macsyma/Mathematica/Maple and Java/C/C++. Previous financial experience preferred. Excellent background in Physics, Math, or similar disciplines, at least at PhD level. This position requires the abilities to work long hours on multiple projects, requiring a wide range of technical and creative applications (some easy, some hard), transpiring at several time scales, with shifting priorities. Salary is competitive, with a bonus scaled to your contributions to profits of the company. Selection Process The R&D group will screen all applications, and a long list will be generated for phone interviews. Other applicants will not be contacted further; in previous years we have had up to 1000 applicants per position. From these phone interviews, a short list will be generated for face-to-face interviews in Chicago. Applicants may stay in Chicago the previous night if required. To perform due diligence, candidates will be asked to spend 1-2 hours on a coding exam. They will have opportunities to discuss this position with several people in DRW. -- Lester Ingber ingber at ingber.com www.ingber.com ingber at alumni.caltech.edu www.alumni.caltech.edu/~ingber From aapo at james.hut.fi Thu Jun 21 09:42:55 2001 From: aapo at james.hut.fi (Aapo Hyvarinen) Date: Thu, 21 Jun 2001 16:42:55 +0300 Subject: Papers on natural image statistics and V1 Message-ID: Dear Colleagues, the following papers are now available on the web. ------------------------------------------------------------ P.O. Hoyer and A. Hyvarinen. A non-negative sparse coding network learns contour coding and integration from natural images. Submitted manuscript. http://www.cis.hut.fi/aapo/ps/gz/contours.ps.gz Abstract: An important approach in visual neuroscience considers how the function of the early visual system relates to the statistics of its natural input. Previous studies have shown how many basic properties of the primary visual cortex, such as the receptive fields of simple and complex cells and the spatial organization (topography) of the cells, can be understood as efficient coding of natural images. Here we extend the framework by considering how the responses of complex cells could be efficiently coded by a higher-order neural layer. This leads to contour coding and end-stopped receptive fields. Interestingly, contour integration can in this framework be seen as a direct result of top-down noise reduction, suggesting such a role for cortico-cortical feedback connections in the visual cortex. ------------------------------------------------------------ A. Hyvarinen and P.O. Hoyer. A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images. Vision Research, in press. http://www.cis.hut.fi/aapo/ps/gz/VR01.ps.gz Abstract: The classical receptive fields of simple cells in the visual cortex have been shown to emerge from the statistical properties of natural images by forcing the cell responses to be maximally sparse, i.e. significantly activated only rarely. Here, we show that this single principle of sparseness can also lead to emergence of topography (columnar organization) and complex cell properties as well. These are obtained by maximizing the sparsenesses of locally pooled energies, which correspond to complex cell outputs. Thus we obtain a highly parsimonious model of how these properties of the visual cortex are adapted to the characteristics of the natural input. ------------------------------------------------------------ A. Hyvarinen and M. Inki. Estimating overcomplete independent component bases for image windows. Submitted manuscript. http://www.cis.hut.fi/aapo/ps/gz/JMIV02.ps.gz Abstract: Estimating overcomplete ICA bases for image windows is a difficult problem. Most algorithms are based on approximations of the likelihood, which leads to computationally heavy procedures. Here we first review the existing methods, and then introduce two algorithms that are based on heuristic approximations and estimate an approximate overcomplete basis quite fast. The algorithms are based on quasi-orthogonality in high-dimensional spaces, and the gaussianization procedure, respectively. ---------------------------------------------------- Aapo Hyvarinen Neural Networks Research Centre Helsinki University of Technology P.O.Box 5400, FIN-02015 HUT, Finland Tel: +358-9-4513278, Fax: +358-9-4513277 Email: Aapo.Hyvarinen at hut.fi Home page: http://www.cis.hut.fi/aapo/ ---------------------------------------------------- From zhouzh at nju.edu.cn Thu Jun 21 23:21:44 2001 From: zhouzh at nju.edu.cn (zhouzh) Date: Fri, 22 Jun 2001 11:21:44 +0800 Subject: An IJCAI-01 paper and its demo Message-ID: <001701c0faca$76fb4390$1e3077ca@daniel> Dear colleagues, Below is a paper to be presented at IJCAI-01: Title: Genetic algorithm based selective neural network ensemble Author: Zhi-Hua Zhou, Jian-Xin Wu, Yuan Jiang, and Shi-Fu Chen Abstract: Neural network ensemble is a learning paradigm where several neural networks are jointly used to solve a problem. In this paper, the relationship between the generalization ability of the neural network ensemble and the correlation of the individual neural networks is analyzed, which reveals that ensembling a selective subset of individual networks is superior to ensembling all the individual networks in some cases. Therefore an approach named GASEN is proposed, which trains several individual neural networks and then employs genetic algorithm to select an optimum subset of individual networks to constitute an ensemble. Experimental results show that, comparing with a popular ensemble approach, i.e. averaging all, and a theoretically optimum selective ensemble approach, i.e. enumerating, GASEN has preferable performance in generating ensembles with strong generalization ability in relatively small computational cost. The paper is available at http://cs.nju.edu.cn/people/zhouzh/zhouzh.files/Publication/zwjc_ijcai01.pdf Its demo is available at http://cs.nju.edu.cn/people/zhouzh/zhouzh.files/MLNN_Group/freeware/Gasen.zip Regards Zhihua ----------------------------------------------- Zhi-Hua ZHOU Ph.d. National Lab for Novel Software Technology Nanjing University Hankou Road 22 Nanjing 210093, P.R.China Tel: +86-25-359-3163 Fax: +86-25-330-0710 URL: http://cs.nju.edu.cn/people/zhouzh/ Email: zhouzh at nju.edu.cn ----------------------------------------------- From marco at cs.uu.nl Fri Jun 22 05:44:40 2001 From: marco at cs.uu.nl (Marco Wiering) Date: Fri, 22 Jun 2001 11:44:40 +0200 (MET DST) Subject: CFP: European Workshop on Reinforcement Learning (EWRL5) Message-ID: <20010622094440.ABCD74545@mail.cs.uu.nl> Call for Participation The Fifth European Workshop on Reinforcement Learning (EWRL5'2001) 5 and 6 October 2001 Utrecht, the Netherlands The biennial European Workshop on Reinforcement Learning (EWRL) will take place in Utrecht, the Netherlands this year. The goal is to gather researchers interested in Reinforcement Learning and its applications. The invited talk will be presented by Prof. Leslie Kaelbling. We encourage the submission of a 2-page abstract, on any aspect of Reinforcement Learning including (but not restricted to): Theoretical aspects of reinforcement learning Function approximation in reinforcement learning Exploration in reinforcement learning Direct vs. Indirect reinforcement learning Multi-agent reinforcement learning Robotic reinforcement learning Novel algorithms for reinforcement learning Reinforcement learning for complex problem solving Reinforcement learning for dynamic replanning Reinforcement learning and game theory The extended abstracts will be published in a proceedings. Important dates: Submission deadline : 10 August 2001 Acceptance/rejection notification : 3 September 2001 Submission of camera ready abstracts : 12 September 2001 Presentations at EWRL : 5/6 October 2001 For further information, we refer to the website: http://www.cs.uu.nl/~marco/EWRL5.html We look forward to seeing you at EWRL'2001 this year. Marco Wiering (marco at cs.uu.nl) Marco Dorigo (mdorigo at ulb.ac.be) From stefan.wermter at sunderland.ac.uk Mon Jun 25 11:28:54 2001 From: stefan.wermter at sunderland.ac.uk (Stefan.Wermter) Date: Mon, 25 Jun 2001 16:28:54 +0100 Subject: 2 new funded PhD studentships in Computing Message-ID: <3B3758B6.36AF9CB2@sunderland.ac.uk> With respect to this email list I would like to encourage applications from computing students for 2 PhD studentships in intelligent systems (e.g. neural networks, hybrid systems, cognitive neuroscience, neuro/fuzzy systems, machine learning, with applications in e.g. in natural language processing or robotics) General application text for all areas of interest below Stefan Wermter ------------------------------------- Funded Phd Opportunities in Computing, Engineering & Technology The School of Computing, Engineering & Technology at the University of Sunderland is seeking high quality, motivated applicants wishing to gain a PhD or MPhil in the disciplines of Computing, Mathematical Sciences, Engineering and Technology. The school has a strong and growing research profile with EPSRC-funded research, numerous EU-funded projects and a vibrant community of over 100 researchers. The School is well-resourced and offers excellent facilities with much state-of the art computing equipment and not only offers high quality postgraduate but also undergraduate programmes accredited by professional societies. We look for applications in both computing and mathematics as well as general engineering for two fully-funded PhD studentships. Students wishing to apply for the 2 funded places should look at the list of proposed projects available at http://www.cet.sunderland.ac.uk/postgrad/projects.html and indicate in their application which of these projects they would wish to undertake. The closing date for the 2 funded places is 8/7/01. Self-funding MPhil & PhD students are also welcome to apply at any time for full-time, part-time and distance learning research degrees in any of the areas detailed below. The main research groups in computing & mathematics are: intelligent systems (major strengths in neural networks, natural language engineering, hybrid systems, cognitive neuroscience, neuro/fuzzy systems, machine learning: Professor Stefan Wermter - stefan.wermter at sunderland.ac.uk +44 191 5153279); http://www.his.sunderland.ac.uk/~cs0stw/Projects/suggested_topics_titles.html human computer systems (includes themes such as multimedia, computer-aided learning, computing for the disabled and human computer interaction evaluation methodologies: Professor Gilbert Cockton - gilbert.cockton at sunderland.ac.uk +44 191 5153394); software engineering (focussed on practical areas especially software testingand the organisationalrisks of implementing information systems, methodologies and solutions for industry: Professor Helen Edwards helen.edwards at sunderland.ac.uk +44 191 5152786 or Professor Barrie Thompson barrie.thompson at sunderland.ac.uk +44 191 5152769); electronic commerce (encompasses the development and promotion of standards in thisdynamic area with a special interest in the area of electronic procurement: Kevin Ginty - kevin.ginty at sunderland.ac.uk or Albert Bokma albert.bokma at sunderland.ac.uk +44 191 5153233); decision support systems (covers a diverse range of activitiesin statistics & mathematics at the boundary ofComputer Science and Statistics and Operational Research: Professor Eric Fletcher eric.fletcher at sunderland.ac.uk +44 191 5152822 or Professor Alfredo Moscardini alfredo.moscardini at sunderland.ac.uk +44 191 5152763); In order to apply please send a full CV (including 2 referees and indicating the project for which you wish to apply) to the address below. You may also find out more about either our PhD or MPhil research degrees, the current studentships and grants available by looking at: http://www.cet.sunderland.ac.uk/postgrad or getting in touch with: Dr. Chris. Bowerman - Principal Lecturer in Research Student Management School of Computing, Engineering & Technology, University of Sunderland, Informatics Centre, St Peter's Way, Sunderland, Tyne & Wear, GB-SR6 0DD Email: chris.bowerman at sunderland.ac.uk -------------------------------------------- *************************************** Professor Stefan Wermter Research Chair in Intelligent Systems University of Sunderland Centre of Informatics, SCET St Peters Way Sunderland SR6 0DD United Kingdom phone: +44 191 515 3279 fax: +44 191 515 3553 email: stefan.wermter at sunderland.ac.uk http://www.his.sunderland.ac.uk/~cs0stw/ http://www.his.sunderland.ac.uk/ **************************************** From espaa at exeter.ac.uk Tue Jun 26 09:48:12 2001 From: espaa at exeter.ac.uk (Oliver Jenkin) Date: Tue, 26 Jun 2001 14:48:12 +0100 (GMT Daylight Time) Subject: Special issue on Image Indexation Message-ID: Pattern Analysis & Applications ISSN: 1433-7541 (printed version) ISSN: 1433-755X (electronic version) Table of Contents Vol. 4 Issue 2/3 Jean-Michel Jolion : Editorial Pattern Analysis & Applications 4 (2001) 2/3, 81-82 Article in PDF format (79 KB)=20 S. Berretti, A. Del Bimbo, E. Vicario: Modelling Spatial Relationships between Colour Clusters Pattern Analysis & Applications 4 (2001) 2/3, 83-92 Article in PDF format (671 KB)=20 N. Tsapatsoulis, Y. Avrithis, S. Kollias: Facial Image Indexing in Multimedia Databases Pattern Analysis & Applications 4 (2001) 2/3, 93-107 Article in PDF format (488 KB)=20 Laurent Amsaleg, Patrick Gros: Content-based Retrienal Using Local Descriptors: Problems and Issues from a Database Perspective Pattern Analysis & Applications 4 (2001) 2/3, 108-124 Article in PDF format (1190 KB)=20 Joo-Hwee Lim: Building Visual Vocabulary for Image Indexation and Query Formulation Pattern Analysis & Applications 4 (2001) 2/3, 125-139 Article in PDF format (1598 KB)=20 Jorma Laaksonen, Markus Koskela, Sami Laakso, Erkki Oja: Self-Organising Maps as a Relevance Feedback Technique in Content-Based Image Retrieval Pattern Analysis & Applications 4 (2001) 2/3, 140-152 Article in PDF format (556 KB)=20 J. Fournier, M. Cord, S. Philipp-Foliguet: RETIN: A Content-Based Image Indexing and Retrieval System Pattern Analysis & Applications 4 (2001) 2/3, 153-173 Article in PDF format (1048 KB)=20 ByoungChul Ko, Jing Peng, Hyeran Byun: Region-based Image Retrieval Using Probabilistic Feature Relevance Learning Pattern Analysis & Applications 4 (2001) 2/3, 174-184 Article in PDF format (991 KB)=20 Patricia Ladret, Anne Gu=E9rin-Dugu=E9: Categorisation and Retrieval of Scene Photographs from JPEG Compressed Database Pattern Analysis & Applications 4 (2001) 2/3, 185-199 Article in PDF format (691 KB)=20 E. Louupias, S. Bres: Key Points-based Indexing for Pre-attentive Similarities: The KIWI System Pattern Analysis & Applications 4 (2001) 2/3, 200-214 Article in PDF format (1295 KB)=20 Linhui Jia, Leslie Kitchen: Object-Based Image Content Characterisation for Semantic-Level Image Similarity Calculation Pattern Analysis & Applications 4 (2001) 2/3, 215-226 Article in PDF format (454 KB)=20 --- End Forwarded Message --- __________________________________________ Oliver Jenkin Pattern Analysis and Applications Journal Department of Computer Science University of Exeter Exeter EX4 4PT UK Tel: +44-1392-264061 Fax: +44-1392-264067 E-mail: espaa at ex.ac.uk Web: http://www.dcs.ex.ac.uk/paa ____________________________________________ From j.v.stone at sheffield.ac.uk Tue Jun 26 11:23:53 2001 From: j.v.stone at sheffield.ac.uk (Jim Stone) Date: Tue, 26 Jun 2001 16:23:53 +0100 Subject: source separation code available Message-ID: MatLab code (version 5.2) for implementing blind source separation is available from: http://www.shef.ac.uk/~pc1jvs/ This site also contains a demonstration of the method working on instantaneous mixtures of musical sounds. The code is an implementation of the method described in the current issue of Neural Computation: Stone JV, "Blind Source Separation Using Temporal Predictability", Neural Computation, 13(7), pp 1559-1547, July, 2001. The above web site also contains MatLab code (written in 1999) for performing spatial, temporal, spatiotemporal, and weak model ICA of 2D images using a conjugate gradient method to maximise the function defined in Bell and Sejnowski's paper: Bell, A and Sejnowski, T "An information-maximization approach to blind separation and blind deconvolution", Neural Computation}, 7, pp 1129-1159, 1995. Jim Stone. ,--------------------------------------------------------------------------. | Dr Jim Stone, Sheffield University Research Fellow | +-------------------------------------------------------------------------+ | Psychology Department, | Email: j.v.stone at sheffield.ac.uk | | Sheffield University | Tel : +44 114 222 6522 | | Sheffield, S10 2UR, | Fax: +44 114 276 6515 | | England. | http://www.shef.ac.uk/~pc1jvs/ | `---------------------------------------------------------------------------' From terry at salk.edu Wed Jun 27 17:45:45 2001 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 27 Jun 2001 14:45:45 -0700 (PDT) Subject: NEURAL COMPUTATION 13:8 Message-ID: <200106272145.f5RLjjK38750@purkinje.salk.edu> Neural Computation - Contents - Volume 13, Number 8 - August 1, 2001 ARTICLE Orientation, Scale, and Discontinuity as Emergent Properties of Illusory Contour Shape Lance R. Williams and Karvel K. Thornber LETTERS Orientation Tuning Properties of Simple Cells in Area V1 Derived from an Approximate Analysis of Nonlinear Neural Field Models Thomas Wennekers Computational Design and Nonlinear Dynamics of a Recurrent Network Model of the Primary Visual Cortex Zhaoping Li A Hierarchical Dynamical Map as a Basic Frame for Cortical Mapping and Its Application to Priming Osamu Hoshino, Satoru Inoue, Yoshiki Kashimori and Takeshi Kambara Dynamical Stability Conditions for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions Heiko Wersing, Wolf-Jurgen Beyn and Helge Ritter An Information-Based Neural Approach to Constraint Satisfaction Henrik Jonsson and Bo Soderberg Recurrence Methods in the Analysis of Learning Processes S. Mendelson and I. Nelken Subspace Information Criterion for Model Selection Masashi Sugiyama and Hidemitsu Ogawa Convergent Decomposition Techniques for Training RBF Neural Networks C. Buzzi, L. Grippo and M. Sciandrone ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2001 - VOLUME 13 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $88 $94.16 $136 Institution $460 $492.20 $508 * 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 ps629 at columbia.edu Wed Jun 27 12:14:16 2001 From: ps629 at columbia.edu (Paul Sajda) Date: Wed, 27 Jun 2001 09:14:16 -0700 Subject: Postdoc Position in Comp Neural Modeling Message-ID: <3B3A0657.863AC685@columbia.edu> Postdoctoral Position in Computational Neural Modeling--a two year position is available immediately for conducting research in modeling of neural mechanisms for visual scene analysis, with particular applications to spatio-temporal and hyperspectral imagery. A mathematical and computational background is desired, particularly in probabilistic modeling and optimization. This position will be part of a multi-university research team (UPenn, Columbia and MIT) investigating biomimetic methods for analysis of literal and non-literal imagery through a combination of experimental physiology, neuromorphic design and simulation, computational modeling and visual psycophysics. Applicants should send a CV, three representative papers and the names of three references to Prof. Paul Sajda, Department of Biomedical Engineering, Columbia University, 530 W 120th Street, NY, NY 10027. Or email to ps629 at columbia.edu. -- Paul Sajda, Ph.D. Associate Professor Department of Biomedical Engineering 530 W 120th Street Columbia University New York, NY 10027 tel: (212) 854-5279 fax: (212) 854-8725 email: ps629 at columbia.edu From curt at citrus.ucr.edu Wed Jun 27 15:56:09 2001 From: curt at citrus.ucr.edu (Dr. Curt Burgess) Date: Wed, 27 Jun 2001 12:56:09 -0700 Subject: Two Cognitive Psychology positions, Univ Calif, Riverside Message-ID: Dear Connectionists - I wanted to particularly let people on this list know that we will have two job searches this coming fall. Someone doing connectionist work would be of particular interest to a number of us in the cognitive group (currently six faculty in psychology). We are undergoing considerable growth on our campus. Our department will likely almost double in size by 2010. We are scheduled to move into a renovated building in two years. We have just received word that Psychology will have its own new building in 2007 or 2008 with around twice the space we currently have. These two positions are junior level. However, we may also be able to hire at the senior level within the guidelines of a new hiring initiative specifically designed to target senior faculty of notable reputation. Thus, we are very interested in identifying individuals who might be interested in this opportunity. If you have any questions, please feel free to contact either me or Chris Chiarello (see below). Curt Burgess ------------------------------- COGNITIVE PSYCHOLOGIST TWO POSITIONS. The Department of Psychology, University of California, Riverside, invites applications for two tenure-track Assistant Professor positions in Cognitive Psychology, beginning July 1, 2002. The Ph.D. degree is required at the time of the appointment. Salary will be commensurate with education and experience. We seek applicants whose research investigates fundamental mechanisms of cognition including memory, language, perception, or attention, which are areas of strength within the current program. We are also interested in individuals whose research is relevant to cognitive aging. Applicants should also be committed to excellence in undergraduate and graduate education. Review of completed applications will begin Oct. 15, 2001 and continue until the position is filled. Interested candidates should send their curriculum vitae, reprints, a cover letter describing research and teaching interests, and arrange to have three letters of recommendation sent to: Dr. Christine Chiarello Chair, Cognitive Psychology Search Committee Department of Psychology - Box D University of California - Riverside Riverside, CA 92521 The Riverside campus of the University of California is growing rapidly and has an excellent psychology department with a strong record of success in research, teaching, and extramural funding. For information on the Department of Psychology, see our web site at: http://www.psych.ucr.edu/. The campus is centrally located in Southern California, about 50 miles east of Los Angeles and less than an hour's drive from the area's mountains, deserts, and beaches. The University of California, Riverside is an equal opportunity employer/affirmative action employer. -- Dr. Curt Burgess, Computational Cognition Lab Associate Editor, Brain and Cognition Chair of Graduate Admissions for Psychology Department of Psychology, University of California 1419 Life Science Building Riverside, CA 92521-0426 URL: http://locutus.ucr.edu/ Internet: curt at citrus.ucr.edu MaBellNet: (909) 787-2392 FAX: (909) 787-3985 *** have you visited http://www.psychgrad.org ?? *** From abbass at cs.adfa.edu.au Thu Jun 28 00:43:46 2001 From: abbass at cs.adfa.edu.au (Hussein A. Abbass) Date: Thu, 28 Jun 2001 14:43:46 +1000 Subject: CFP: The Inaugural workshop on Artificial Life (AL'01), Adelaide, Australia. 11-Dec-2001 Message-ID: <3.0.6.32.20010628144346.00896990@csadfa.cs.adfa.edu.au> Dear colleague I would appreciate it very much if you can post our first call for papers to your colleague and students. Best Regards, Hussein. The Inaugural workshop on Artificial Life (AL'01) http://www.cs.adfa.edu.au/~abbass/ALL/ Adelaide, Australia. 11-Dec-2001 To be held within the 14th Australian Joint Conference on Artificial Intelligence (AI'01) http://www.cs.adelaide.edu.au/AI2001/ December 2001 IMPORTANT ******* A special issue in an outstanding journal is being investigated Call For Papers =============== The Inaugural workshop on Artificial Life, (AL'01), will be held in conjunction with the Australian Joint Conference on Artificial Intelligence in December 2001. Usually, the term "Artificial Life" (Alife) is used to delineate systems that exhibit some properties of life. Research in Alife ranges from analyzing and understanding life and nature - at least as we may believe it is - to modeling biological systems or solving biological problems. Alife is a large interdisciplinary research area covering research from computer science, biology, chemistry, physics, engineering, sociology, and psychology. Research in Alife can be generically classified into three main areas: ? Biological behavior as a metaphor for computational models; such as Ant Algorithms, Ant Colony Optimization, Marriage in Honey-Bees Optimization, Immune Systems, Neural Networks, Evolutionary Algorithms, forest, and DNA computing. ? Computational models that reproduce/duplicate a biological behavior; such as Swarm Intelligence, Simulation, Cellular Automaton ? Computational models to solve biological problems; such as Bio-informatics The aim of this workshop is to get together computer scientists, biologists, chemists, engineers, geneticists, physicists, and others, to gain more understanding of the mystery hidden in life and to expose researchers to the recent advances in this fast developing area. Topics of interest include, but not limited to, * Ant Algorithms * Ant Colony Optimization * Applications of ALife technologies * Bioinformatics * Biological agents and robotics * Cellular automaton * Complex systems * Emergence * Evolutionary and adaptive dynamics * Marriage in Honey-bees Optimization * Multi-agent systems * Origin of life * Self-organization * Self-replication * Simulation and synthesis tools and methodologies * Swarm Intelligence * and Other related topics Location ======== University of South Australia, Adelaide, Australia Important Dates =============== Submission of papers: 15-Sep-2001 Notification to authors: 26-Oct-2001 Camera ready format: 09-Nov-2001 Workshop date: 11-Dec-2001 Paper Format and Review Process =============================== Each paper will be reviewed by at least two members of the program committee. After the final decision is made regarding the papers, authors will receive the instructions for the final submission of their papers accompanied with the reports of the reviewers. At least one author is expected to attend at the workshop to present his/her paper. All papers must have a title page that includes a title, a 300-400 word abstract, a list of keywords, the names and addresses of all authors, their email addresses, and their telephone and fax numbers. Publication =========== Accepted papers will be published in the workshop proceedings with an ISBN number. The maximum number of pages is 10. A special issue in an outstanding journal is currently being negotiated. All papers submitted to the workshop will be considered to the special issue. Depending on the number of submissions to the workshop, submission to the special issue will most likely be restricted to the workshop participants. Workshop Chair ============== Hussein A. Abbass University of New South Wales, School of Computer Science, Australian Defence Force Academy Campus, NorthCott Drive, Canberra, ACT2600, Australia. Email: abbass at cs.adfa.edu.au Fax: +61-2-62688581 Workshop Program Committee ========================== Eric Bonabeau (Icosystem & Santa Fe, USA) Dipankar Dasgupta (Memphis, USA) Marco Dorigo (Libre de Bruxelles, Belgium) David Fogel (Natural Selection, USA) Tim Hendtlass (Swinburne, Australia) Jun Jo (Griffith, Australia) Nikola Kasabov (Otago, New Zealand) Jong-Hwan Kim (KAIST, Korea) Erhan Kozan (QUT, Australia) Xiaodong Li (RMIT, Australia) Bob Mckay (UNSW, Australia) Saeid Nahavandi (Deakin, Australia) Akira Namatame (Defence Academy, Japan) Marcus Randall (Bond, Australia) Guy Theraulaz (Paul Sabatier, France) Prahlad Vadakkepat (National University, Singapore) Brijesh Verma (Griffith, Australia) Xin Yao (Birmingham, UK) Dr. Hussein A. Abbass (BA, BSc, PG-Dip, M.Phil., M.Sc., Ph.D.) University of New South Wales, School of Computer Science, Australian Defence Force Academy Campus, NorthCott Drive, Canberra, ACT2600, Australia. Email: abbass at cs.adfa.edu.au http: http://www.cs.adfa.edu.au/~abbass Tel.(M) (+61) 0402212977 Tel.(H) (+61) (2) 62578757 Tel.(W) (+61) (2) 62688158 Fax.(W) (+61) (2) 62688581 From goldfarb at unb.ca Thu Jun 28 01:41:22 2001 From: goldfarb at unb.ca (Lev Goldfarb) Date: Thu, 28 Jun 2001 02:41:22 -0300 (ADT) Subject: What is a structural represetation? Message-ID: (Our apologies if you receive multiple copies of this announcement) Dear colleagues, The following paper, titled "What is a structural representation?", ( http://www.cs.unb.ca/profs/goldfarb/struct.ps ) which we believe to be, in a sense, the first one formally addressing the issue of structural representation and proposing the formal ETS model, should be of interest to many researchers in various areas. It implies, in particular, that the properly understood (non-trivial) "structural" representations cannot be "replaced" by the classical numeric, e.g. vector-space-based, representations. Moreover, the concept of "structural" representation emerging from the ETS model is not the one familiar to all of you. (The abstract of the paper is appended below; for a change, the default paper size is A4. Unfortunately for some, the language of the paper is of necessity quite formal, since the main concepts do not have any analogues and therefore must be treated carefully.) Although the proposed model was motivated by, and will be applied to, the "real" problems coming from such areas as pattern recognition, machine learning, data mining, cheminformatics, bioinformatics, and many others, in view of the required radical rethinking that must now go into its implementations, at this time, we can only offer a very preliminary discussion, in the following companion paper, addressing the model's potential applications in chemistry http://www.cs.unb.ca/profs/goldfarb/cadd.ps (please keep in mind that the last paper was written on the basis of an earlier draft of the paper we are announcing now and it will be updated accordingly next month). We intend to discuss the paper shortly on INDUCTIVE mailing list. (To subscribe, send to INDUCTIVE-SERVER at UNB.CA the following text SUBSCRIBE INDUCTIVE FIRSTNAME LASTNAME) We would greatly appreciate any comments regarding both of the above papers. Best regards, Lev Goldfarb Tel: 506-458-7271 Faculty of Computer Science Tel(secret.): 453-4566 University of New Brunswick Fax: 506-453-3566 P.O. Box 4400 E-mail: goldfarb at unb.ca Fredericton, N.B., E3B 5A3 Home tel: 506-455-4323 Canada http://www.cs.unb.ca/profs/goldfarb/goldfarb.htm ***************************************************************************** WHAT IS A STRUCTURAL REPRESENTATION? Lev Goldfarb, Oleg Golubitsky, Dmitry Korkin Faculty of Computer Science University of New Brunswick Fredericton, NB, Canada We outline a formal foundation for a "structural" (or "symbolic") object/event representation, the necessity of which is acutely felt in all sciences, including mathematics and computer science. The proposed foundation incorporates two hypotheses: 1) the object's formative history must be an integral part of the object representation and 2) the process of object construction is irreversible, i.e. the "trajectory" of the object's formative evolution does not intersect itself. The last hypothesis is equivalent to the generalized axiom of (structural) induction. Some of the main difficulties associated with the transition from the classical numeric to the structural representations appear to be related precisely to the development of a formal framework satisfying these two hypotheses. The concept of (inductive) class--which has inspired the development of this approach to structural representation--differs fundamentally from the known concepts of class. In the proposed, evolving transformations system (ETS), model, the class is defined by the transformation system---a finite set of weighted transformations acting on the class progenitor--and the generation of the class elements is associated with the corresponding generative process which also induces the class typicality measure. Moreover, in the ETS model, a fundamental role of the object's class in the object's representation is clarified: the representation of an object must include the class. From the point of view of ETS model, the classical discrete representations, e.g. strings and graphs, appear now as incomplete special cases, the proper completion of which should incorporate the corresponding formative histories, i.e. those of the corresponding strings or graphs. From J.A.Bullinaria at cs.bham.ac.uk Thu Jun 28 09:36:33 2001 From: J.A.Bullinaria at cs.bham.ac.uk (John A Bullinaria) Date: Thu, 28 Jun 2001 14:36:33 +0100 (BST) Subject: Studentships in Natural Computation Message-ID: ------------------------- Scholarships/Studentships ------------------------- MSc/PGDip/PGCert in Natural Computation ======================================= http://www.cs.bham.ac.uk/natcomp School of Computer Science The University of Birmingham, UK Starting in October 2001, we are offering an advanced 12 month MSc programme in Natural Computation (i.e. computational systems that use ideas and inspirations from natural biological, ecological and physical systems). This will comprise of six taught modules in Neural Computation, Evolutionary Computation, Molecular and Quantum Computation, Nature Inspired Optimisation, Nature Inspired Learning, and Nature Inspired Design; two mini research projects; and one full scale research project. PGDip and PGCert are available for shorter periods. Part-time studies are welcome. The programme is supported by the EPSRC through its Master's Level Training Packages, and by a number of leading companies. It is open to candidates with a very good honours degree or equivalent qualifications in Computer Science/Engineering or closely related areas. A small number of fully funded EPSRC studentships (scholarships) are available to UK/EU students. A small number of scholarships funded by the European Commission under its ASIA-ITC programme are available to Indian students. Additional financial support from our industrial partners may be available during the main project period. Further details are available from our Web-site at: http://www.cs.bham.ac.uk/natcomp or via email: Admissions at cs.bham.ac.uk Please note that the official closing date for applications is 15th July 2001, though good applications may still be considered after that date. From E.Koning at elsevier.nl Thu Jun 28 03:45:20 2001 From: E.Koning at elsevier.nl (Koning, Esther (ELS)) Date: Thu, 28 Jun 2001 09:45:20 +0200 Subject: free online access to three special issues of Neural Networks Message-ID: Dear Connectionists, We are pleased to inform you that three special issues of the Neural Networks journal are available free online at http://www.elsevier/com/cite * Organisation of Computation in Brain-like Systems (1999) edited by E. K=F6rner, Gen Matsumoto, Mitsuo Kawato * Neural Control and Robotics: Biology and Technology (1998) edited by R. Brooks, S. Grossberg, L. Optican * Consciousness for Neural Networks (1997) edited by J. Taylor, W. Freeman In addition, the abstracts and full text (PDF files) of the journal Cognitive Systems Research are available free at www.elsevier.com/cite through the end of 2001, and may be of interest to you. Best regards, Esther Koning From bbs at bbsonline.org Fri Jun 29 16:53:12 2001 From: bbs at bbsonline.org (Stevan Harnad - Behavioral & Brain Sciences (Editor)) Date: Fri, 29 Jun 2001 16:53:12 -0400 Subject: Webb: Can robots make good models of biological behaviour? -- BBS Call for Commentators Message-ID: Below is the abstract of a forthcoming BBS target article [Please note that this paper was in fact accepted and archived to the web in February 2001 but the recent move of BBS to New York delayed the Call until now.] Can robots make good models of biological behaviour? by Barbara Webb http://www.bbsonline.org/Preprints/Webb/ This article has been accepted for publication in Behavioral and Brain Sciences (BBS), an international, interdisciplinary journal providing Open Peer Commentary on important and controversial current research in the biobehavioral and cognitive sciences. Commentators must be BBS Associates or nominated by a BBS Associate. To be considered as a commentator for this article, to suggest other appropriate commentators, or for information about how to become a BBS Associate, please reply by EMAIL within three (3) weeks to: calls at bbsonline.org The Calls are sent to 8000 BBS Associates, so there is no expectation (indeed, it would be calamitous) that each recipient should comment on every occasion! Hence there is no need to reply except if you wish to comment, or to nominate someone to comment. If you are not a BBS Associate, please approach a current BBS Associate (there are currently over 10,000 worldwide) who is familiar with your work to nominate you. All past BBS authors, referees and commentators are eligible to become BBS Associates. A full electronic list of current BBS Associates is available at this location to help you select a name: http://www.bbsonline.org/Instructions/assoclist.html If no current BBS Associate knows your work, please send us your Curriculum Vitae and BBS will circulate it to appropriate Associates to ask whether they would be prepared to nominate you. (In the meantime, your name, address and email address will be entered into our database as an unaffiliated investigator.) To help us put together a balanced list of commentators, please give some indication of the aspects of the topic on which you would bring your areas of expertise to bear if you were selected as a commentator. To help you decide whether you would be an appropriate commentator for this article, an electronic draft is retrievable from the online BBSPrints Archive, at the URL that follows the abstract below. _____________________________________________________________ Can robots make good models of biological behaviour? Barbara Webb Centre for Computational and Cognitive Neuroscience Department of Psychology University of Stirling Stirling FK9 4LA Scotland, U.K. b.h.webb at stir.ac.uk www.stir.ac.uk/psychology/Staff/bhw1/ KEYWORDS: models; simulation; animal behaviour; neuroethology; robotics; realism; levels. ABSTRACT: How should biological behaviour be modelled? A relatively new approach is to investigate problems in neuroethology by building physical robot models of biological sensorimotor systems. The explication and justification of this approach are here placed within a framework for describing and comparing models in the behavioural and biological sciences. First, simulation models - the representation of a hypothesis about a target system - are distinguished from several other relationships also termed 'modelling' in discussions of scientific explanation. Seven dimensions on which simulation models can differ are defined and distinctions between them discussed: (1) Relevance: whether the model tests and generates hypotheses applicable to biology. (2) Level: the elemental units of the model in the hierarchy from atoms to societies. (3) Generality: the range of biological systems the model can represent. (4) Abstraction: the complexity, relative to the target, or amount of detail included in the model. (5) Structural accuracy: how well the model represents the actual mechanisms underlying the behaviour. (6) Performance match: to what extent the model behaviour matches the target behaviour (7) Medium: the physical basis by which the model is implemented No specific position in the space of models thus defined is the only correct one, but a good modelling methodology should be explicit about its position and the justification for that position. It is argued that in building robot models biological relevance is more effective than loose biological inspiration; multiple levels can be integrated; that generality cannot be assumed but might emerge from studying specific instances; abstraction is better done by simplification than idealisation; accuracy can be approached through iterations of complete systems; that the model should be able to match and predict target behaviour; and that a physical medium can have significant advantages. These arguments reflect the view that biological behaviour needs to be studied and modelled in context, that is in terms of the real problems faced by real animals in real environments. http://www.bbsonline.org/Preprints/Webb/ ___________________________________________________________ Please do not prepare a commentary yet. Just let us know, after having inspected it, what relevant expertise you feel you would bring to bear on what aspect of the article. We will then let you know whether it was possible to include your name on the final formal list of invitees. _______________________________________________________________________ *** SUPPLEMENTARY ANNOUNCEMENTS *** (1) The authors of scientific articles are not paid money for their refereed research papers; they give them away. What they want is to reach all interested researchers worldwide, so as to maximize the potential research impact of their findings. Subscription/Site-License/Pay-Per-View costs are accordingly access-barriers, and hence impact-barriers for this give-away research literature. There is now a way to free the entire refereed journal literature, for everyone, everywhere, immediately, by mounting interoperable university eprint archives, and self-archiving all refereed research papers in them. Please see: http://www.eprints.org http://www.openarchives.org/ http://www.dlib.org/dlib/december99/12harnad.html --------------------------------------------------------------------- (2) All authors in the biobehavioral and cognitive sciences are strongly encouraged to self-archive all their papers in their own institution's Eprint Archives or in CogPrints, the Eprint Archive for the biobehavioral and cognitive sciences: http://cogprints.soton.ac.uk/ It is extremely simple to self-archive and will make all of our papers available to all of us everywhere, at no cost to anyone, forever. Authors of BBS papers wishing to archive their already published BBS Target Articles should submit it to BBSPrints Archive. Information about the archiving of BBS' entire backcatalogue will be sent to you in the near future. Meantime please see: http://www.bbsonline.org/help/ and http://www.bbsonline.org/Instructions/ --------------------------------------------------------------------- (3) Call for Book Nominations for BBS Multiple Book Review In the past, Behavioral and Brain Sciences (BBS) had only been able to do 1-2 BBS multiple book treatments per year, because of our limited annual page quota. BBS's new expanded page quota will make it possible for us to increase the number of books we treat per year, so this is an excellent time for BBS Associates and biobehavioral/cognitive scientists in general to nominate books you would like to see accorded BBS multiple book review. (Authors may self-nominate, but books can only be selected on the basis of multiple nominations.) It would be very helpful if you indicated in what way a BBS Multiple Book Review of the book(s) you nominate would be useful to the field (and of course a rich list of potential reviewers would be the best evidence of its potential impact!). From zemel at cs.toronto.edu Fri Jun 1 14:23:06 2001 From: zemel at cs.toronto.edu (Richard Zemel) Date: Fri, 1 Jun 2001 14:23:06 -0400 Subject: NIPS*2001 Call For Workshop Proposals Message-ID: <01Jun1.142326edt.453201-24086@jane.cs.toronto.edu> *@* NEW LOCATION: WHISTLER, BC, CANADA *@* Call for Workshop Proposals Neural Information Processing Systems -- Natural and Synthetic NIPS*2001 Post-Conference Workshops -- December 7 and 8, 2001 Whistler/Blackcomb Resort, BC, CANADA Following the regular program of the Neural Information Processing Systems 2001 conference in Vancouver, BC, Canada, workshops on various current topics in neural information processing will be held on December 7 and 8, 2001, in Whistler, BC, Canada. We invite researchers interested in chairing one of these workshops to submit workshop proposals. The goal of the workshops is to provide an informal forum for researchers to discuss important research questions and challenges. Controversial issues, open problems, and comparisons of competing approaches are encouraged and preferred as workshop topics. Representation of alternative viewpoints and panel-style discussions are particularly encouraged. Workshop topics include, but are not limited to, the following: Active Learning, Architectural Issues, Attention, Audition, Bayesian Analysis, Bayesian Networks, Benchmarking, Brain Imaging, Computational Complexity, Computational Molecular Biology, Control, Genetic Algorithms, Graphical Models, Hippocampus and Memory, Hybrid Supervised/Unsupervised Learning Methods, Hybrid HMM/ANN Systems, Implementations, Independent Component Analysis, Mean-Field Methods, Markov Chain Monte-Carlo Methods, Music, Network Dynamics, Neural Coding, Neural Plasticity, On-Line Learning, Optimization, Recurrent Nets, Robot Learning, Rule Extraction, Self-Organization, Sensory Biophysics, Signal Processing, Spike Timing, Support Vectors, Speech, Time Series, Topological Maps, and Vision. Detailed descriptions of previous workshops may be found at http://www.cs.cmu.edu/Groups/NIPS/NIPS2000/Workshops There will be six hours of workshop meetings per day, split into morning and afternoon sessions, with free time inbetween for ongoing individual exchange or outdoor activities. Selected workshops may be invited to submit their workshop proceedings for publication as part of a new series of monographs for the post-NIPS workshops. Workshop organizers have several responsibilities including: * Coordinating workshop participation and content, which includes - arranging short informal presentations by experts, - arranging for expert commentators to sit on a discussion panel, - formulating a set of discussion topics, etc. * Moderating the discussion, and reporting its findings and conclusions to the group during evening plenary sessions. * Writing a brief summary and/or coordinating submitted material for post-conference electronic dissemination. SUBMISSION INSTRUCTIONS Interested parties should submit a short proposal for a workshop of interest via email by July 8, 2001. Proposals should include title, description of what the workshop is to address and accomplish, proposed workshop length (1 or 2 days), planned format (e.g., lectures, group discussions, panel discussion, combinations of the above, etc.), and proposed speakers. Names of potential invitees should be given where possible. Preference will be given to workshops that reserve a significant portion of time for open discussion or panel discussion, as opposed to pure ``mini-conference'' format. An example format is: * Tutorial lecture providing background and introducing terminology relevant to the topic. * Two short lectures introducing different approaches, alternating with discussions after each lecture. * Discussion or panel presentation. * Short talks or panels alternating with discussion and question/answer sessions. * General discussion and wrap-up. We suggest that organizers allocate at least 50% of the workshop schedule to questions, discussion, and breaks. Past experience suggests that workshops otherwise degrade into mini-conferences as talks begin to run over. For the same reason, we strongly recommend that each workshop include no more than 12 talks. The proposal should motivate why the topic is of interest or controversial, why it should be discussed, and who the targeted group of participants is. It also should include a brief resume of the prospective workshop chair with a list of publications to establish scholarship in the field. We encourage workshops that build, continue, or arise from one or more workshops from previous years. Please mention any such connections. NIPS does not provide travel funding for workshop speakers. In the past, some workshops have sought and received funding from external sources to bring in outside speakers. In addition, the organizers of each accepted workshop can name up to four people (six people for 2-day workshops) to receive free registration for the workshop program. Submissions should include contact name (if there is more than one organizer, please designate one organizer as the ``contact person'') as well as addresses, email addresses, phone and fax numbers for all organizers. Proposals should be emailed as plain text to nips-workshop-proposal at cs.unm.edu. Please do not use attachments, Microsoft Word, postscript, html, or pdf files. Questions may be addressed to nips-workshop-admin at cs.unm.edu. Information about the main conference and the workshop program can be found at http://www.cs.cmu.edu/Web/Groups/NIPS. Virginia de Sa, University of California, San Francisco Barak Pearlmutter, University of New Mexico NIPS*2001 Workshops Co-Chairs PROPOSALS MUST BE RECEIVED BY JULY 8, 2001 -Please Post- From r.roy at cranfield.ac.uk Fri Jun 1 13:01:12 2001 From: r.roy at cranfield.ac.uk (Roy, Rajkumar) Date: Fri, 1 Jun 2001 18:01:12 +0100 Subject: CFP: Applied Soft Computing Journal Message-ID: <2812AF10DCF1D41192DD0008C74C244C199DBB@oulton.sims.cranfield.ac.uk> ================================================== APPLIED SOFT COMPUTING Publisher: Elsevier Science The Official Journal of the World Federation on Soft Computing (WFSC) Journal homepage: http://www.elsevier.com/locate/asoc/ =================================================== CALL FOR PAPERS ************************ Applied Soft Computing is an international journal promoting an integrated view of soft computing to solve real life problems. Soft computing is a collection of methodologies, which aim to exploit tolerance for imprecision, uncertainty and partial truth to achieve tractability, robustness and low solution cost. The focus is to publish the highest quality research in application and convergence of the areas of Fuzzy Logic, Neural Networks, Evolutionary Computing, Rough Sets and other similar techniques to address real world complexities. Applied Soft Computing is a 'rolling' publication: articles are published as soon as the editor in chief has accepted them. Therefore, the web site will continuously be updated with new articles and the publication time will be short. Major topics ------------ The scope of this journal covers the following soft computing and related techniques, interactions between several soft computing techniques, and their industrial applications: * Fuzzy Computing * Neuro Computing * Evolutionary Computing * Probabilistic Computing * Immunological Computing * Hybrid Methods * Intelligent Agents and Agent Theory * Causal Models * Case-based Reasoning * Chaos Theory * Interactive Computational Models The application areas of interest include but are not limited to: * Decision Support * Process and System Control * System Identification and Modelling * Optimisation * Signal or Image Processing * Vision or Pattern Recognition * Condition Monitoring * Fault Diagnosis * Systems Integration * Internet Tools * Human-Machine Interface * Time Series Prediction * Robotics * Motion Control and Power Electronics * Biomedical Engineering * Virtual Reality * Reactive Distributed AI * Telecommunications * Consumer Electronics * Industrial Electronics * Manufacturing Systems * Power and Energy * Data Mining * Data Visualisation * Intelligent Information Retrieval * Bio-inspired Systems * Autonomous Reasoning * Intelligent Agents Publication ----------- Authors are invited to submit technical papers(no limit on max. number of pages), state of the art survey papers, industry reports (max. 5 pages) and book reviews. Authors are encouraged to utilise the opportunity given by this on-line publication to include animations, software demonstrations, and video clips etc. The papers will be published on Elsevier Science Web Site as soon as they are accepted, which enables authors to publish their work FAST and readers get the latest work in Soft Computing on their desktop! There will be a free hardcopy of volume available to authors by the end of the year. So have your latest research published on the Applied Soft Computing Website and get a FREE hardcopy of the volume that includes your paper later. For any further queries, paper submission and special issue proposals, please contact: Dr. Rajkumar Roy Editor in Chief 'Applied Soft Computing' Department of Enterprise Integration, School of Industrial and Manufacturing Science, Cranfield University, Cranfield, Bedford, MK43 0AL, United Kingdom. Tel: +44 (0)1234 754072 or +44 (0)1234 750111 Ext. 2423 , Fax: +44 (0)1234 750852 Email: asoc at cranfield.ac.uk Journal Website: http://www.elsevier.com/locate/asoc/ ---------------------------------------------------------------------------- -------- From benus at elf.stuba.sk Tue Jun 5 10:28:25 2001 From: benus at elf.stuba.sk (Lubica Benuskova) Date: Tue, 5 Jun 2001 16:28:25 +0200 (MET DST) Subject: Paper on experience-dependent cortical plasticity Message-ID: Dear Connectionists, the preprint of the following article: "Theory for normal and impaired experience-dependent plasticity in neocortex of adult rats" Proc. Natl. Acad. Sci. USA 98(5): 2797-2802, 2001. by Benuskova L, Rema V, Armstrong-James M and Ebner FF can be downloaded from http://www.dcs.elf.stuba.sk/~benus/#publications Abstract: We model experience-dependent plasticity in the cortical representation of whiskers (the barrel cortex) in normal adult rats, and in adult rats that were prenatally exposed to alcohol. Prenatal exposure to alcohol (PAE) caused marked deficits in experience-dependent plasticity in a cortical barrel-column. Cortical plasticity was induced by trimming all whiskers on one side of the face except two. This manipulation produces high activity from the intact whiskers which contrasts with low activity from the cut whiskers while avoiding any nerve damage. By a computational model we show that the evolution of neuronal responses in a single barrel-column following this sensory bias is consistent with the synaptic modifications that follow the rules of the Bienenstock, Cooper and Munro (BCM) theory. The BCM theory postulates that a neuron possesses a moving synaptic modification threshold, $\theta_M$, which dictates whether the neuron's activity at any given instant will lead to strengthening or weakening of its input synapses. The current value of $\theta_M$ changes proportionally to the square of the neuron's activity averaged over some recent past. In the model of alcohol impaired cortex, the effective $\theta_M$ has been set to a level unattainable by the depressed levels of cortical activity. Abnormally low activity leads to ``impaired'' synaptic plasticity that is consistent with experimental findings. Based on experimental and computational results we discuss how elevated $\theta_M$ may be related to the abnormally low expression of N-methyl-D-aspartate receptors (NMDARs) and the membrane translocation of Ca$^{2+}$/calmodulin-dependent protein kinase II (CaMKII) in adult rat cortex subjected to prenatal alcohol exposure. Lubica Benuskova, PhD ------------------------------------------------------- Slovak Technical University Dept. of Computer Science and Engineering Ilkovicova 3, 812 19 Bratislava 1, Slovakia ------------------------------------------------------- Phone: (+421 7) 602 91 696 Fax: (+421 7) 654 20 587 E-mail: benus at elf.stuba.sk, benus at dcs.elf.stuba.sk http://www.dcs.elf.stuba.sk/~benus From JaneD at tandf.co.uk Wed Jun 6 04:09:45 2001 From: JaneD at tandf.co.uk (Jane Dawson) Date: Wed, 6 Jun 2001 09:09:45 +0100 Subject: OPAL/Cognitive Neuropsychology Message-ID: <001801c0ee60$0cc82bd0$a97775c1@tandf.co.uk> Dear Colleague I am pleased to announce that Psychology Press, part of the Taylor & Francis Group, have just launched OPAL - Online Psychology Alerting - a FREE service for those with a specific interest in behavioural sciences. This is a special email service designed to deliver tables of contents for any Psychology Press, Taylor & Francis, Brunner-Routledge, or Carfax behavioural science journal in advance of publication, to anyone who has requested the information. All you need to do is register, and you will be sent contents pages of the journal(s) of your choice from that point onwards, in advance of the printed edition. You can request contents pages either for any number of individual titles, or for one or more of our sub-categories or a main category, and you may unsubscribe at any time. For each of your choices, you will receive the relevant bibliographic information: journal title, volume/issue number and the ISSN. You will also receive full contents details, names of authors and the appropriate page numbers from the printed version. This will give you advance notice of what is being published, making it easier for you to retrieve the exact information you require from the hard copy once it arrives in your library, or electronically from the online version of the journal. Titles that may be of interest are: Cognitive Neuropsychiatry Cognitive Neuropsychology European Journal of Cognitive Psychology Thinking and Reasoning Visual Cognition Laterality Memory To register for this complimentary service, please visit: http://www.psypress.co.uk/opal/ and click on the OPAL button. For further information on the above titles, please visit: http://www.psypress.co.uk/journals.html To find out more about online journals in behavioral science, please see the Psychology Online section of the Psychology Press website: http://www.psypress.co.uk If you have any questions regarding this service, please email: OPAL at psypress.co.uk From sfr at unipg.it Wed Jun 6 17:06:28 2001 From: sfr at unipg.it (Simone G.O. Fiori (Pg)) Date: Wed, 06 Jun 2001 23:06:28 +0200 Subject: Papers on neural and neuromorphic blind signal processing. Message-ID: <1.5.4.32.20010606210628.01811d00@unipg.it> Dear Connectionists, I would like to draw your attention to three new papers of potential interest to people working on unsupervised artificial neural networks and neuromorphic adaptive filtering for blind signal processing. Best regards, Simone Fiori Hybrid Independent Component Analysis by Adaptive LUT Activation Function Neurons ================================================================== by S. Fiori - Neural Networks and Adaptive Systems Research Group University of Perugia, Perugia (Italy) Journal: Neural Networks (Pergamon press) Download at: http://www.unipg.it/~sfr/publications/nnt2001.ps Abstract The aim of this paper is to present an efficient implementation of unsupervised adaptive-activation function neurons dedicated to one-dimensional probability density estimation, with application to independent component analysis. The proposed implementation is a computationally light improvement to adaptive pseudo-polynomial neurons, recently presented in (Fiori, 2000a), and bases upon the concept of `look-up table' (LUT) neurons. Keywords: Adaptive activation function neurons; Look-up-table neurons; Independent component analysis; Minimal mutual information principle; Kullback-Leibler divergence; Natural gradient. ~~~~~~~~~~~~~~~~~~~~ Notes on Cost Functions and Estimators for `Bussgang' Adaptive Blind Equalization ================================================================== by S. Fiori - Neural Networks and Adaptive Systems Research Group University of Perugia, Perugia (Italy) Journal: European Transactions on Telecommunications (ETT) Download at: http://www.unipg.it/~sfr/publications/ett2001.ps Abstract The aim of this paper is to present some remarks on the cost functions for blind channel equalization by `Bussgang' algorithms recently discused in the literature; also, some possible associated non-Bayesian estimators are considered with details, and the effects of the choice of such estimators in relation to `Bussgang' neuromorphic filtering are briefly investigated. ~~~~~~~~~~~~~~~~~~~~ A Contribution to (Neuromorphic) Blind Deconvolution by Flexible Approximated Bayesian Estimation ================================================================= by S. Fiori - Neural Networks and Adaptive Systems Research Group University of Perugia, Perugia (Italy) Journal: Signal Processing (Elsevier) Download at: http://www.unipg.it/~sfr/publications/SIGPROC2001.ps Abstract `Bussgang' deconvolution techniques for blind digital channels equalization rely on a Bayesian estimator of the source sequence defined on the basis of channel/equalizer cascade model which involves the definition of deconvolution noise. In this paper we consider four `Bussgang' blind deconvolution algorithms for uniformly-distributed source signals and investigate their numerical performances as well as some of their analytical features. Particularly, we show that the algorithm, introduced by the present author, provided by a flexible (neuromorphic) estimator is effective as it does not require to make any hypothesis about convolutional noise level and exhibits satisfactory numerical performances. =================================================== Dr Simone Fiori (EE, PhD)- Assistant Professor Neural Networks and Adaptive Systems Research Group DIE - University of Perugia - Perugia (Italy) eMail: sfr at unipg.it Fax: +39 0744 492925 Web: http://www.unipg.it/~sfr/ =================================================== From mschmitt at lmi.ruhr-uni-bochum.de Thu Jun 7 04:45:16 2001 From: mschmitt at lmi.ruhr-uni-bochum.de (Michael Schmitt) Date: Thu, 07 Jun 2001 10:45:16 +0200 Subject: Preprint on Local Receptive Field Neural Networks Message-ID: <3B1F3F1C.E1CF5ABA@lmi.ruhr-uni-bochum.de> Dear Connectionists, a preprint of the paper "Neural networks with local receptive fields and superlinear VC dimension" by Michael Schmitt is available on-line from http://www.ruhr-uni-bochum.de/lmi/mschmitt/receptive.ps.gz (39 pages gzipped PostScript). This paper has been accepted by Neural Computation in its first submitted version. (They say that this is the first time that they have accepted a first time submission.) Regards, Michael Schmitt ------------------------------------------------------------ TITLE: Neural networks with local receptive fields and superlinear VC dimension AUTHOR: Michael Schmitt ABSTRACT Local receptive field neurons comprise such well-known and widely used unit types as radial basis function neurons and neurons with center-surround receptive field. We study the Vapnik-Chervonenkis (VC) dimension of feedforward neural networks with one hidden layer of these units. For several variants of local receptive field neurons we show that the VC dimension of these networks is superlinear. In particular, we establish the bound $\Omega(W\log k)$ for any reasonably sized network with $W$ parameters and $k$ hidden nodes. This bound is shown to hold for discrete center-surround receptive field neurons, which are physiologically relevant models of cells in the mammalian visual system, for neurons computing a difference of Gaussians, which are popular in computational vision, and for standard radial basis function (RBF) neurons, a major alternative to sigmoidal neurons in artificial neural networks. The result for RBF neural networks is of particular interest since it answers a question that has been open for several years. The results also give rise to lower bounds for networks with fixed input dimension. Regarding constants all bounds are larger than those known thus far for similar architectures with sigmoidal neurons. The superlinear lower bounds contrast with linear upper bounds for single local receptive field neurons also derived here. -- Michael Schmitt LS Mathematik & Informatik, Fakultaet fuer Mathematik Ruhr-Universitaet Bochum, D-44780 Bochum, Germany Phone: +49 234 32-23209 , Fax: +49 234 32-14465 http://www.ruhr-uni-bochum.de/lmi/mschmitt/ From ken at phy.ucsf.edu Fri Jun 8 01:17:22 2001 From: ken at phy.ucsf.edu (Ken Miller) Date: Thu, 7 Jun 2001 22:17:22 -0700 Subject: Research Scientist Position: Probabilistic Modeling for Spike-Sorting Message-ID: <15136.24546.194623.9937@coltrane.ucsf.edu> RESEARCH SCIENTIST NEEDED: PROBABILISTIC MODELING FOR SPIKE SORTING Keck Center for Integrative Neuroscience UCSF San Francisco, CA We have an opening for a research scientist to work on developing methods for sorting "spikes" (action potentials) in neurophysiological recordings. This position pays a competitive professional salary. The problem of spike sorting is a challenging one of signal processing, time-series analysis, and unsupervised clustering, We plan to apply the methods of probabilistic modeling and model comparison. A starting point for our work will be the thesis work of Sahani, http://www.vis.caltech.edu/~maneesh/thesis/. The PI's on the project are Ken Miller (www.keck.ucsf.edu/~ken) and Philip Sabes (www.keck.ucsf.edu/~sabes), UCSF. The scientist will be expected to implement spike sorting algorithms, and in collaboration with the PI's to systematically test alternative algorithms and devise and test improved algorithms. Understanding of and experience with statistical inference and probabilistic modeling, or sufficient theoretical training to quickly master the same, is required; experience applying theoretical methods to analyze real data is strongly preferred. Sufficient scientific programming abilities to easily implement and test alternative algorithms is required. Prototyping will typically be done in Matlab, implementation in C or C++. It is expected that the candidate will have a Ph.D. in a quantitative field. The scientist will work closely with a programmer who will also be working fulltime on this project. The position is expected to run for approximately two years. Please send a CV and arrange to have two letters of reference sent to: Paul Puri Spikesorting Search Dept. of Physiology UCSF San Francisco, CA 94143-0444 or to spikesort at phy.ucsf.edu From Roberto.Prevete at na.infn.it Fri Jun 8 06:01:53 2001 From: Roberto.Prevete at na.infn.it (Roberto Prevete) Date: Fri, 08 Jun 2001 12:01:53 +0200 Subject: Preprint on AN ALGEBRAIC APPROACH TO THE AUTONOMOUSLY SELF-ADAPTABLE BOOLEAN NEURAL Message-ID: <3B20A28E.D5F278CB@na.infn.it> Dear Connectionists, a preprint of the book "AN ALGEBRAIC APPROACH TO THE AUTONOMOUSLY SELF-ADAPTABLE BOOLEAN NEURAL" by Francesco E. Lauria and Roberto Prevete is available on-line from http://www.na.infn.it/Gener/cyber/report.html, into the folder NeuralNetworks/News (zipped Word file) This book is in print by Liguori Ed. Via Posillipo 394 I-80123 Napoli, Italy (EU) ++39 081 720 61 11 phone Regards, Roberto Prevete ------------------------------------------------------------ TITLE: AN ALGEBRAIC APPROACH TO THE AUTONOMOUSLY SELF-ADAPTABLE BOOLEAN NEURAL AUTHORS: Francesco E. Lauria and Roberto Prevete INFM & Dipartimento di Scienze Fisiche, Universit? di Napoli Federico II Complesso Universitario di Monte Sant? Angelo, Via Vicinale Cupa Cintia 16 I-80126 Napoli, Italy (EU) lauria at na.infn.it CONTENTS Chapter 1 THE BOOLEAN NEURAL NET, OR BNN. Chapter 2. THE KNOWLEDGE REPRESENTATION IN THE BNN. Chapter 3. THE DATA STRUCTURE EMBEDDED IN A BNN. Chapter 4. THE BNN AND THE HEBBIAN RULE. Chapter 5. THE ADAPTABLE BNN, OR ABNN Chapter 6. A GABNN AS AN AUTONOMOUSLY SELF-TRAINABLE CONTROL SYSTEM. Chapter 7. THE JAVA PACKAGE IT.NA.CY.NNET. Chapter 8. CONCLUSIONS. From Andres.PerezUribe at unifr.ch Mon Jun 11 11:30:25 2001 From: Andres.PerezUribe at unifr.ch (Andres Perez-Uribe) Date: Mon, 11 Jun 2001 17:30:25 +0200 Subject: postdoc position in Fribourg, Switzerland Message-ID: <1010611173025.ZM25192@ufps25> Post-Doctoral Research Position The position ------------ The position is intended for an enthusiastic postgraduate, who have terminated her/his PhD studies. The candidate will participate in the research activities that are conducted within the WELCOME project. Her/his duties may concern : (i) the use of learning and evolutionary techniques to provide adaptation to the new network-oriented computing frameworks (ubiquitous computing and intelligent networks), (ii) the development of adaptable Agent-based methodologies for Internet-based infrastructures and mobile robots/devices, (iii) the tackling of Human Machine Interaction issues, together with supervision of two Ph.D research works. As far as possible she/he will build contacts with external academic or commercial organizations, and promote industrial applications of her/his research. Moreover, she/he will follow student projects realted to her/his topics of research. An open-mind to interdisciplinary approaches and to non-standard innovation techniques will be appreciated. The position is to be taken September 1st, 2001 (or at convenience). It is granted for two years by the Swiss National Foundation for Scientific Research (with a possibility of renewal once). Job location is Fribourg, a french-german bilingual middle-size city in Switzerland. The requirements ---------------- *Education: Ph.D in Computer Science (or a related area) *Ability to speak, read and write French or German or English *Proficient in one or several topics, such as: * Autonomous mobile robots, Adaptive Systems * Agent Technology, Multi-Agent Systems * Artificial Neural Networks, Artificial Life, Evolutionary Computing * Intelligent Networks, Distributed Systems and/or Coordination Languages, * Human Computer Interaction, Immersive and Ubiquitous Computing, Force-feedback interaction, Augmented or virtual reality * Object-Oriented design techniques, Java programming, Jini technology The research group ------------------ The Parallelism and Artificial Intelligence (PAI) group is a rapidly growing and dynamic research group that concentrates its research on hot topics related to new information and communication technologies. His interests encompass namely the methodologies of Autonomous and Adaptive Systems, Collective Intelligence, Evolutionary Computing, Agent Technology, Massively Distributed Systems, and Intelligent Networks, but also the field of Human Computer Interaction, where it addresses specifically the Immersive trend and Ubiquitous Computing. Research resources ------------------ The group holds a UNIX workstation environment, and PC and Macintosh machines. In particular, it possesses about 20 Khepera robots: 7 of them are equipped with radio communication modules, grippers (arms), and linear vision, and one of them has a CCD color camera. We have explored both single-robot learning tasks and collective robotic behaviors (See the description of the CALIMA and AMOC projects). Moreover, we are acquiring new mobile devices (wearable eyeglasses, PALM devices, etc.) for our research in Ubiquitous computing, human-machine interfaces, and intelligent networks. Applications with CV and research paper list must be sent to (Email submissions are encouraged): Prof. Bat Hirsbrunner University of Fribourg, ch. du Muse 3, CH-1700 Fribourg Tel.: +41 (0)26 300 8465 (secretariat - morning) Email: beat.hirsbrunner at unifr.ch URL: http://www-iiuf.unifr.ch/pai/ ----------------------------------------------------------------------- -- Andres PEREZ-URIBE Postdoctoral Fellow and Lecturer Parallelism and Artificial Intelligence Group (PAI) Department of Informatics, University of Fribourg, Switzerland Ch. du Musee 3, CH-1700 Fribourg, Office 2.76b Perolles Tel. +41-26-300-8473, Fax +41-26-300-9731 Email:Andres.PerezUribe at unifr.ch, http://www-iiuf.unifr.ch/~aperezu/ From j-patton at northwestern.edu Mon Jun 11 12:18:31 2001 From: j-patton at northwestern.edu (Jim Patton) Date: Mon, 11 Jun 2001 11:18:31 -0500 Subject: Preprint: Linear combinations of nonlinear models Message-ID: <4.2.0.58.20010611110945.00ac8be0@merle.acns.nwu.edu> The following paper has been accepted by Biological Cybernetics. Preprints are available from: LINEAR COMBINATIONS OF NONLINEAR MODELS FOR PREDICTING HUMAN-MACHINE INTERFACE FORCES James L. Patton & Ferdinando A. Mussa-Ivaldi Sensory Motor Performance Program, Rehabilitation Institute of Chicago Physical Medicine and Rehabilitation, Northwestern University Medical School In press, Biological Cybernetics, May, 2001 ABSTRACT This study presents a computational framework that capitalizes on known human neuromechanical characteristics during limb movements in order to predict man-machine interactions. A parallel-distributed approach, the mixture of nonlinear models, fits the relationship between the measured kinematics and kinetics at the handle of a robot. Each element of the mixture represented the arm and its controller as a feedforward nonlinear model of inverse dynamics plus a linear approximation of musculotendonous impedance. We evaluated this approach with data from experiments where subjects held a handle of a planar manipulandum robot and attempted to make point-to-point reaching movements. We compared the performance to the more conventional approach of a constrained, nonlinear optimization of the parameters. On average, the mixture of nonlinear models accounted for 0.79 0.11 (1 SD), and force errors were 0.73% 0.20% of the maximum exerted force. Solutions were acquired in half the time with significantly better fit. However, both approaches equally suffered from the simplifying assumptions, namely, that the human neuromechanical system consisted of a feedforward controller coupled with linear impedances and a moving state equilibrium. Hence, predictability was best limited to the first half of the movement. The mixture of nonlinear models may be useful in man-machine tasks such as in telerobotics, fly-by-wire vehicles, robotic training and rehabilitation. ______________________________________________________________________ J A M E S P A T T O N , P H . D . Research Scientist Sensory Motor Performance Prog., Rehabilitation Institute of Chicago Physical Med & Rehabilitation, Northwestern University Med School 345 East Superior, Room 1406, Chicago, IL 60611 312-238-1277 (OFFICE) -2208 (FAX) -1232 (LAB) -3381 (SECRETARY) CELL PHONE MESSAGING (<150 char.): 8473341056 at msg.myvzw.com ______________________________________________________________________ From clinton at compneuro.umn.edu Mon Jun 11 15:29:25 2001 From: clinton at compneuro.umn.edu (Kathleen Clinton) Date: Mon, 11 Jun 2001 14:29:25 -0500 Subject: NEURON Workshop Announcement Message-ID: <3B251C15.56A57B6F@compneuro.umn.edu> ****************************** NEURON Workshop Announcement ****************************** Michael Hines and Ted Carnevale of Yale University will conduct a three to five day workshop on NEURON, a computer code that simulates neural systems. The workshop will be held from August 20-24, 2001 at the University of Minnesota Supercomputing Institute in Minneapolis, Minnesota. Registration is open to students and researchers from academic, corporate, and industrial organizations. Space is limited, and registrations will be accepted on a first-come, first-serve basis. **Topics and Format** Participants may attend the workshop for three or five days. The first three days cover material necessary for the most common applications in neuroscience research and education. The fourth and fifth days deal with advanced topics of users whose projects may require problem-specific customizations. Windows and Linux platforms will be used on computers provided by IBM. Days 1 - 3 "Fundamentals of Using the NEURON Simulation Environment" The first three days will cover the material that is required for informed use of the NEURON simulation environment. The emphasis will be on applying the graphical interface, which enables maximum productivity and conceptual control over models while at the same time reducing or eliminating the need to write code. Participants will be building their own models from the start of the course. By the end of the third day they will be well prepared to use NEURON on their own to explore a wide range of neural phenomena. Topics will include: Integration methods --accuracy, stability, and computational efficiency --fixed order, fixed timestep integration --global and local variable order, variable timestep integration Strategies for increasing computational efficiency. Using NEURON's graphical interface to --construct models of individual neurons with architectures that range from the simplest spherical cell to detailed models based on quantitative morphometric data (the CellBuilder). --construct models that combine neurons with electronic instrumentation (i.e. capacitors, resistors, amplifiers, current sources and voltage sources) (the Linear Circuit Builder). --construct network models that include artificial neurons, model cells with anatomical and biophysical properties, and hybrid nets with both kinds of cells (the Network Builder). --control simulations. --display simulation results as functions of time and space. --analyze simulation results. --analyze the electrotonic properties of neurons. Adding new biophysical mechanisms. Uses of the Vector class such as --synthesizing custom stimuli --analyzing experimental data --recording and analyzing simulation results Managing modeling projects. Days 4 and 5 "Beyond the GUI" The fourth and fifth days deal with advanced topics for users whose projects may require problem-specific customizations. Topics will include: Advanced use of the CellBuilder, Network Builder, and Linear Circuit Builder. When and how to modify model specification, initialization, and NEURON's main computational loop. Exploiting special features of the Network Connection class for efficient implementation of use-dependent synaptic plasticity. Using NEURON's tools for optimizing models. Parallelizing computations. Using new features of the extracellular mechanism for --extracellular stimulation and recording --implementation of gap junctions and ephaptic interactions Developing new GUI tools. **Registration** For academic or government employees the registration fee is $155 for the first three days and $245 for the full five days. These fees are $310 and $490, respectively, for corporate or industrial participants. Registration forms can be obtained at www.compneuro.umn.edu/NEURONregistration.html or from the workshop coordinator, Kathleen Clinton, at clinton at compneuro.umn.edu or (612) 625-8424. **Lodging** Out-of-town participants may stay at the Holiday Inn Metrodome in Minneapolis. It is within walking distance of the Supercomputing Institute. Participants are responsible for making their own hotel reservations. When making reservations, participants should state that they are attending the NEURON Workshop. A small block of rooms is available until July 28, 2001. Reservations can be arranged by calling (800) 448-3663 or (612) 333-4646. From luca at idsia.ch Mon Jun 11 06:53:16 2001 From: luca at idsia.ch (Luca Maria Gambardella) Date: Mon, 11 Jun 2001 12:53:16 +0200 Subject: IDSIA: Two Post DOC Positions in Robotics, Swarm Intelligence and Machine learning Message-ID: <5.0.2.1.0.20010611123223.04abf040@mailhost.idsia.ch> Apologize for multiple copies. ============================================================================== Job Opening in Robotics, Swarm Intelligence, Machine Learning and Simulation ============================================================================== TWO POST DOC POSITIONS for 3 years funded by the Future and Emerging Technologies (FET) program of the Commission of the European Community is open for applications. IDSIA, http://www.idsia.ch Istituto Dalle Molle di Studi sull'Intelligenza Artificiale, Galleria 2, 6928 Manno-Lugano, Switzerland APPLICATION DEADLINE: July 30th 2001 STARTING: October 2001: We are looking for two Post Doctoral candidates to work on the new European Project SWARM-BOTS starting October 2001. SWARM-BOTS is about the design and implementation of self-organising and self assembling artifacts called swarm-bots. The approach is inspired by recent studies in swarm intelligence, i.e., by studies of the self-organising and self-assembling capabilities shown by social insects and other animal societies. The main scientific goal of the project is a better understanding of swarm intelligence principles and of the use of these principles in engineering, while the main tangible goal is the demonstration of the validity of the approach followed by means of the construction of at least one such artifact. The expected results are therefore the further development of the swarm intelligence discipline and the design and construction of a first example of swarm-bots, that is, an artifact composed of a number of simpler robots capable of self-assembling and self-organising to adapt to its environment. The project will last 36 months and will see the combined effort of scientists from four European laboratories (IRIDIA Bruxelles, IDSIA Lugano, EPFL Lausanne, CNR-IP Rome) ====================== CONTACT INFORMATION ===================== If you wish to apply, please send (i) Detailed curriculum vitae (ii) List of three references (and their email addresses) (iii) Transcripts of undergraduate and graduate (if applicable) studies (iv) Concise statement of your research interests (two pages max). Candidates are also encouraged to submit their scores in the Graduate Record Examination (GRE) general test (if available). Applications can also be submitted electronically (in plain ASCII or postscript format) to mailto:luca at idsia.ch. Please connect "SWB2001PD" with your first and last name in the message subject. Please send all documents to: Luca Maria Gambardella IDSIA Galleria 2 6928 Manno-Lugano Switzerland Phone : +41 91 - 610 8663 Fax : +41 91 - 610 8661 Secretary: +41 91 - 6108660 mailto:luca at idsia.ch http://www.idsia.ch/luca From zemel at cs.toronto.edu Wed Jun 13 16:46:25 2001 From: zemel at cs.toronto.edu (Richard Zemel) Date: Wed, 13 Jun 2001 16:46:25 -0400 Subject: Reminder: Upcoming deadlines for NIPS*2001 Message-ID: <01Jun13.164647edt.453154-28229@jane.cs.toronto.edu> ========================================== Neural Information Processing Systems Natural and Synthetic Monday, Dec. 3 -- Saturday, Dec. 8, 2001 Vancouver, British Columbia, Canada Whistler Ski Resort ========================================== Deadlines: PAPER SUBMISSIONS: June 20, 2001 WORKSHOP PROPOSALS: July 8, 2001 For submission info, see http://www.cs.cmu.edu/Web/Groups/NIPS Invited speakers: Barbara Finlay -- How brains evolve, and the consequences for computation Alison Gopnik -- Babies and Bayes-nets: Causal inference and theory-formation in children, chimps, scientists and computers Jon M. Kleinberg -- Decentralized network algorithms: Small-world phenomena and the dynamics of information Tom Knight -- TBA Judea Pearl -- Causal inference as an exercise in computational learning Shihab Shamma -- Common principles in auditory and visual processing Tutorials: Luc Devroye -- Nonparametric density estimation: VC to the rescue Daphne Koller & Nir Friedman -- Learning Bayesian networks from data Shawn Lockery -- Chemotaxis: Gradient ascent by simple living organisms and their neural networks. Christopher Manning -- Probabilistic linguistics and probabilistic models of natural language processing Bernhard Scholkopf -- SVM and Kernel methods Sebastian Thrun -- Probabilistic robotics Also...remember that NIPS is heading north this year, to Vancouver From isahara at crl.go.jp Wed Jun 13 07:42:41 2001 From: isahara at crl.go.jp (ISAHARA Hitoshi) Date: Wed, 13 Jun 2001 20:42:41 +0900 Subject: CFP [NLPNN2001] Message-ID: <200106131142.UAA22552@lettuce.crl.go.jp> ==================================================================== Call for Papers --- NLPRS2001 Workshop The Second Workshop on Natural Language Processing and Neural Networks (NLPNN2001) Tokyo, Japan, November 30, 2001 http://www2.crl.go.jp/jt/a132/members/qma/NLPNN2001/index.html Artificial neural networks (ANN) based natural language processing (NLP) research began in the early 1980s with papers on implementing semantic networks in ANNs, word-sense disambiguation, anaphora resolution, and syntactic parsing. Since then, with the boom of NLP research based on very large corpora, the ANN, as a powerful parallel and distributed learning/processing machine, attract a more great deal of attention from both the ANN and NLP researchers and have been successfully used in many areas of NLP. This second workshop on NLP and ANN is to be held in Tokyo as a post-conference workshop of NLPRS2001. It continues the work of the first workshop on NLP and ANN, NLPNN99, successfully held in Beijing two years ago. NLPNN2001 will provide a forum for researchers in the areas of ANN and NLP who are interested in advancing the state of the art in developing NLP techniques using neural networks. For more information on NLPRS2001, see . The papers presented at NLPNN99 are available from . Submissions are invited on all NLP topics in the context of using ANN techniques. A submission consists of a two-page summary (2000 words or less), accompanied by paper title, author information including full names, affiliations of all authors, and the postal and email addresses of the corresponding author. Submissions will be reviewed by the Workshop Program Committee, and authors will be notified of acceptance or rejection by email. Submit by email to qma at crl.go.jp IMPORTANT DATES Summary submission deadline: July 31, 2001 Notification of acceptance: August 15, 2001 Camera ready papers due: September 26, 2001 Inquiries concerning the workshop can be sent to one of the organizers either by email to qma at crl.go.jp or by post to the following address: Dr. Qing Ma Computational Linguistics Group Keihanna Human Info-Communication Research Center Communications Research Laboratory 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0289, Japan Organizers Hitoshi Isahara (Communications Research Laboratory, Japan) Qing Ma (Communications Research Laboratory, Japan) Program Committee Qing Ma (Communications Research Laboratory, Japan), Chair Gary Geunbae Lee (Pohang University of Science and Technology, Korea) Caroline Lyon (University of Hertfordshire, UK) Daniel Memmi (LEIBNIZ-IMAG, France) Risto Miikkulainen (University of Texas, USA) Ron Sun (University of Missouri-Columbia, USA) Naoto Takahashi (AIST, Japan) Ming Zhou (Microsoft Research China, China) other members will be announced shortly ==================================================================== From kap-listman at wkap.nl Wed Jun 13 20:18:16 2001 From: kap-listman at wkap.nl (kap-listman@wkap.nl) Date: Thu, 14 Jun 2001 02:18:16 +0200 (METDST) Subject: New Issue: Neural Processing Letters. Vol. 13, Issue 3 Message-ID: <200106140018.CAA13709@wkap.nl> Kluwer ALERT, the free notification service from Kluwer Academic/PLENUM Publishers and Kluwer Law International ------------------------------------------------------------ Neural Processing Letters ISSN 1370-4621 http://www.wkap.nl/issuetoc.htm/1370-4621+13+3+2001 Vol. 13, Issue 3, June 2001. TITLE: Sequential Extraction of Minor Components AUTHOR(S): Tianping Chen, Shun-Ichi Amari, Noboru Murata KEYWORD(S): minor component, sequential algorithm. PAGE(S): 195-201 TITLE: Evolving Stacked Time Series Predictors with Multiple Window Scales and Sampling Gaps AUTHOR(S): Zheng Rong Yang, Weiping Lu, Robert G. Harrison KEYWORD(S): evolutionary programming, forecasting, neural networks, stacking, time series. PAGE(S): 203-211 TITLE: Reinforcement Learning Using the Stochastic Fuzzy Min-Max Neural Network AUTHOR(S): Aristidis Likas KEYWORD(S): fuzzy min-max neural network, pole balancing problem, reinforcement learning, stochastic automaton. PAGE(S): 213-220 TITLE: Recursive Partitioning Technique for Combining Multiple Classifiers AUTHOR(S): Terry Windeatt KEYWORD(S): binary feature, constructive, ensemble, MLP, monotonic, multiple classifier, partition, separable, spectral, support vector. PAGE(S): 221-236 TITLE: Temporal Kohonen Map and the Recurrent Self-Organizing Map: Analytical and Experimental Comparison AUTHOR(S): Markus Varsta, Jukka Heikkonen, Jouko Lampinen, Jose Del R. Millan KEYWORD(S): convergence analysis, self-organizing maps, temporal sequence processing. PAGE(S): 237-251 TITLE: Maharadja: A System for the Real Time Simulation of RBF with the Mahalanobis Distance AUTHOR(S): Bertrand Granado, Andrea Pinna, Luc Gaborit, Patrick Garda KEYWORD(S): FPGA, low-power consumption, Mahalanobis distance, neural hardware, RBF, real time. PAGE(S): 253-266 TITLE: A Neuro-Based Optimization Algorithm for Tiling Problems with Rotation AUTHOR(S): Shinsuke Manabe, Hideki Asai KEYWORD(S): analog neural network, rotation of polyominoes, tiling problem, 2-D neural array. PAGE(S): 267-275 TITLE: Authors index AUTHOR(S): KEYWORD(S): analog neural network, rotation of polyominoes, tiling problem, 2-D neural array. PAGE(S): 277-277 TITLE: Volume contents AUTHOR(S): KEYWORD(S): analog neural network, rotation of polyominoes, tiling problem, 2-D neural array. PAGE(S): 279-280 -------------------------------------------------------------- Thank you for your interest in Kluwer's books and journals. NORTH, CENTRAL AND SOUTH AMERICA Kluwer Academic Publishers Order Department, PO Box 358 Accord Station, Hingham, MA 02018-0358 USA Telephone (781) 871-6600 Fax (781) 681-9045 E-Mail: kluwer at wkap.com EUROPE, ASIA AND AFRICA Kluwer Academic Publishers Distribution Center PO Box 322 3300 AH Dordrecht The Netherlands Telephone 31-78-6392392 Fax 31-78-6546474 E-Mail: orderdept at wkap.nl From dbarber at dai.ed.ac.uk Fri Jun 15 13:01:32 2001 From: dbarber at dai.ed.ac.uk (David Barber) Date: Fri, 15 Jun 2001 18:01:32 +0100 Subject: Research Fellowship: Graphical Models Message-ID: <3B2A3F6B.2F51E7D2@dai.ed.ac.uk> UNIVERSITY OF EDINBURGH: DIVISION OF INFORMATICS RESEARCH FELLOWSHIP IN GRAPHICAL MODELS The project, which runs for three years, aims to exploit the interface between models and techniques in physics (statistical mechanics) and informatics. Whilst the project is primarily theoretical, the emphasis is to study systems and techniques with direct application in areas of probabilistic inference in large stochastic systems, including pattern processing, error correcting codes, and cryptography. The scope of the project is broad and includes potentially the modelling of complex biological systems. Ideally you will have postgraduate experience in the mathematical, physical or computing sciences Salary scale: 16,775 - 25,213 Pounds Sterling Per Annum Please quote Ref: 316428WW For further particulars and an application pack visit our web site (www.ed.ac.uk) or telephone the recruitment line on 0131-650-2511. Closing Date: 29 JUNE 2001 Further Particulars: ==================== RESEARCH FELLOWSHIP IN GRAPHICAL MODELS The Institute for Adaptive and Neural Computation, part of the Division of Informatics, seeks a research fellow in the field of Graphical Models. The aim of the project is to develop methods to deal with large scalestochastic systems with applications in machine learning and related fields. The framework within which this work will be carried out is Graphical Models, which exploit graph theoretic concepts in a probabilistic setting. The project aims to exploit the interface between models and techniques in physics (statistical mechanics) and informatics. Whilst the project is primarily theoretical, the emphasis is to study systems and techniques with direct application in areas of probabilistic inference, including pattern processing, error correcting codes, and cryptography. The scope of the project is broad and includes potentially the modelling of complex biological systems. Skills and Qualifications: The candidate is expected to have postgraduate experience in the mathematical, physical or computing sciences. Familiarity with statistical mechanics and Graphical Models would be an advantage. The candidate should be highly motivated and keen to participate in a lively interdisciplinary environment. The position is available for a period of three years. For informal enquiries, please contact David Barber dbarber at dai.ed.ac.uk Tel +44 (0)131 650 4491; Fax +44 (0)870 130 5014 From wahba at stat.wisc.edu Fri Jun 15 20:14:01 2001 From: wahba at stat.wisc.edu (Grace Wahba) Date: Fri, 15 Jun 2001 19:14:01 -0500 (CDT) Subject: On the \xi\alpha and GACV for tuning SVM's Message-ID: <200106160014.TAA04917@hera.stat.wisc.edu> Paper available: "On the Relation Between the GACV and Joachims' \xi\alpha Method for Tuning Support Vector Machines, With Extensions to the Nonstandard Case". by Grace Wahba, Yi Lin, Yoonkyung Lee and Hao Zhang UW-Madison Statistics TR 1039 ftp://ftp.stat.wisc.edu/pub/wahba/xan.ps Abstract We rederive a form of Joachims' $\xi\alpha$ method for tuning Support Vector Machines by the same approach as was used to derive the GACV, and show how the two methods are related. We generalize the $\si\alpha$ method to the nonstandard case of nonrepresentative training set and unequal misclassification costs and compare the results to the GACV estimate for the standard and nonstandard cases. From rsun at cecs.missouri.edu Sun Jun 17 13:40:55 2001 From: rsun at cecs.missouri.edu (rsun@cecs.missouri.edu) Date: Sun, 17 Jun 2001 12:40:55 -0500 Subject: THE INTERACTION OF EXPLICIT AND IMPLICIT LEARNING: A Symposium at CogSci'2001 Message-ID: <200106171740.f5HHete27995@ari1.cecs.missouri.edu> THE INTERACTION OF EXPLICIT AND IMPLICIT LEARNING A Symposium at CogSci'2001 (August 1-4, 2001), Edinburgh, Scotland =============================================================== Titles of the Talks: Axel Cleeremans: ``Behavioral, neural, and computational correlates of implicit and explicit learning" Zoltan Dienes: ``The effect of prior knowledge on implicit learning" Bob Mathews: ``Finding the optimal mix of implicit and explicit learning" Ron Sun: ``The synergy of the implciit and the explicit" ================================================================= The symposium will be held on August 4th, 2001, 2:30 - 4:10 pm. See http://www.hcrc.ed.ac.uk/cogsci2001/programme.html for futher details of the 23rd Cognitive Science Conference, Edinburgh, Scotland. ================================================================= Background: The role of implicit learning in skill acquisition and the distinction between implicit and explicit learning have been widely recognized in recent years (see, e.g., Reber 1989, Stanley et al 1989, Willingham et al 1989, Anderson 1993), Although implicit learning has been actively investigated, the complex and multifaceted interaction between the implicit and the explicit and the importance of this interaction have not been universally recognized; to a large extent, such interaction has been downplayed or ignored, with only a few notable exceptions. Research has been focused on showing the LACK of explicit learning in various learning settings (see especially Lewicki et al 1987) and on the controversies stemming from such claims. Despite the lack of studies of interaction, it has been gaining recognition that it is difficult, if not impossible, to find a situation in which only one type of learning is engaged (Reber 1989, Seger 1994, but see Lewicki et al 1987). Our review of existing data has indicated that, while one can manipulate conditions to emphasize one or the other type, in most situations, both types of learning are involved, with varying amounts of contributions from each (see, e.g., Sun et al 2000; see also Stanley et al 1989, Willingham et al 1989). Likewise, in the development of cognitive architectures (e.g., Rosenbloom et al 1993, Anderson 1993), the distinction between procedural and declarative knowledge has been proposed for a long time, and advocated or adopted by many in the field (see especially Anderson 1993). The distinction maps roughly onto the distinction between the explicit and implicit knowledge, because procedural knowledge is generally inaccessible while declarative knowledge is generally accessible and thus explicit. However, in work on cognitive architectures, focus has been almost exclusively on ``top-down" models (that is, learning first explicit knowledge and then implicit knowledge on the basis of the former), the bottom-up direction (that is, learning first implicit knowledge and then explicit knowledge, or learning both in parallel) has been largely ignored, paralleling and reflecting the related neglect of %the complex and multifaceted the interaction of explicit and implicit processes in the skill learning literature. However, there are a few scattered pieces of work that did demonstrate the parallel development of the two types of knowledge or the extraction of explicit knowledge from implicit knowledge (e.g, Willingham et al 1989, Stanley et al 1989, Sun et al 2000), contrary to usual top-down approaches in developing cognitive architectures. Many issues arise with regard to the interaction between implicit and explicit processes, which we need to look into if we want to better understand this interaction: How can we best capture implicit processes computationally? How can we best capture explicit processes computationally? How do the two types of knowledge develop along side each other and influence each other's development? Is bottom-up learning (or parallel learning) possible, besides top-down learning? How can they (bottom-up learning, top-down learning, and parallel learning) be realized computationally? How do the two types of acquired knowledge interact during skilled performance? What is the impact of that interaction on performance? How do we capture such impact computationally? =========================================================================== Prof. Ron Sun http://www.cecs.missouri.edu/~rsun CECS Department phone: (573) 884-7662 University of Missouri-Columbia fax: (573) 882 8318 201 Engineering Building West Columbia, MO 65211-2060 email: rsun at cecs.missouri.edu http://www.cecs.missouri.edu/~rsun http://www.cecs.missouri.edu/~rsun/journal.html http://www.elsevier.com/locate/cogsys =========================================================================== From ingber at ingber.com Tue Jun 19 08:08:44 2001 From: ingber at ingber.com (Lester Ingber) Date: Tue, 19 Jun 2001 07:08:44 -0500 Subject: Computational Finance Position Message-ID: <20010619070843.A11248@ingber.com> Updated on http://www.ingber.com/drw_positions.html If you have very strong credentials for a position described below, please send your resume to: Prof. Lester Ingber Director Research & Development DRW Investments LLC [http://www.drwtrading.com] 311 S Wacker Dr Ste 900 Chicago, IL 60606 Email (preferred) ingber at drwtrading.com Computational Finance Position Experienced programmer in Maxima/Macsyma/Mathematica/Maple and Java/C/C++. Previous financial experience preferred. Excellent background in Physics, Math, or similar disciplines, at least at PhD level. This position requires the abilities to work long hours on multiple projects, requiring a wide range of technical and creative applications (some easy, some hard), transpiring at several time scales, with shifting priorities. Salary is competitive, with a bonus scaled to your contributions to profits of the company. Selection Process The R&D group will screen all applications, and a long list will be generated for phone interviews. Other applicants will not be contacted further; in previous years we have had up to 1000 applicants per position. From these phone interviews, a short list will be generated for face-to-face interviews in Chicago. Applicants may stay in Chicago the previous night if required. To perform due diligence, candidates will be asked to spend 1-2 hours on a coding exam. They will have opportunities to discuss this position with several people in DRW. -- Lester Ingber ingber at ingber.com www.ingber.com ingber at alumni.caltech.edu www.alumni.caltech.edu/~ingber From aapo at james.hut.fi Thu Jun 21 09:42:55 2001 From: aapo at james.hut.fi (Aapo Hyvarinen) Date: Thu, 21 Jun 2001 16:42:55 +0300 Subject: Papers on natural image statistics and V1 Message-ID: Dear Colleagues, the following papers are now available on the web. ------------------------------------------------------------ P.O. Hoyer and A. Hyvarinen. A non-negative sparse coding network learns contour coding and integration from natural images. Submitted manuscript. http://www.cis.hut.fi/aapo/ps/gz/contours.ps.gz Abstract: An important approach in visual neuroscience considers how the function of the early visual system relates to the statistics of its natural input. Previous studies have shown how many basic properties of the primary visual cortex, such as the receptive fields of simple and complex cells and the spatial organization (topography) of the cells, can be understood as efficient coding of natural images. Here we extend the framework by considering how the responses of complex cells could be efficiently coded by a higher-order neural layer. This leads to contour coding and end-stopped receptive fields. Interestingly, contour integration can in this framework be seen as a direct result of top-down noise reduction, suggesting such a role for cortico-cortical feedback connections in the visual cortex. ------------------------------------------------------------ A. Hyvarinen and P.O. Hoyer. A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images. Vision Research, in press. http://www.cis.hut.fi/aapo/ps/gz/VR01.ps.gz Abstract: The classical receptive fields of simple cells in the visual cortex have been shown to emerge from the statistical properties of natural images by forcing the cell responses to be maximally sparse, i.e. significantly activated only rarely. Here, we show that this single principle of sparseness can also lead to emergence of topography (columnar organization) and complex cell properties as well. These are obtained by maximizing the sparsenesses of locally pooled energies, which correspond to complex cell outputs. Thus we obtain a highly parsimonious model of how these properties of the visual cortex are adapted to the characteristics of the natural input. ------------------------------------------------------------ A. Hyvarinen and M. Inki. Estimating overcomplete independent component bases for image windows. Submitted manuscript. http://www.cis.hut.fi/aapo/ps/gz/JMIV02.ps.gz Abstract: Estimating overcomplete ICA bases for image windows is a difficult problem. Most algorithms are based on approximations of the likelihood, which leads to computationally heavy procedures. Here we first review the existing methods, and then introduce two algorithms that are based on heuristic approximations and estimate an approximate overcomplete basis quite fast. The algorithms are based on quasi-orthogonality in high-dimensional spaces, and the gaussianization procedure, respectively. ---------------------------------------------------- Aapo Hyvarinen Neural Networks Research Centre Helsinki University of Technology P.O.Box 5400, FIN-02015 HUT, Finland Tel: +358-9-4513278, Fax: +358-9-4513277 Email: Aapo.Hyvarinen at hut.fi Home page: http://www.cis.hut.fi/aapo/ ---------------------------------------------------- From zhouzh at nju.edu.cn Thu Jun 21 23:21:44 2001 From: zhouzh at nju.edu.cn (zhouzh) Date: Fri, 22 Jun 2001 11:21:44 +0800 Subject: An IJCAI-01 paper and its demo Message-ID: <001701c0faca$76fb4390$1e3077ca@daniel> Dear colleagues, Below is a paper to be presented at IJCAI-01: Title: Genetic algorithm based selective neural network ensemble Author: Zhi-Hua Zhou, Jian-Xin Wu, Yuan Jiang, and Shi-Fu Chen Abstract: Neural network ensemble is a learning paradigm where several neural networks are jointly used to solve a problem. In this paper, the relationship between the generalization ability of the neural network ensemble and the correlation of the individual neural networks is analyzed, which reveals that ensembling a selective subset of individual networks is superior to ensembling all the individual networks in some cases. Therefore an approach named GASEN is proposed, which trains several individual neural networks and then employs genetic algorithm to select an optimum subset of individual networks to constitute an ensemble. Experimental results show that, comparing with a popular ensemble approach, i.e. averaging all, and a theoretically optimum selective ensemble approach, i.e. enumerating, GASEN has preferable performance in generating ensembles with strong generalization ability in relatively small computational cost. The paper is available at http://cs.nju.edu.cn/people/zhouzh/zhouzh.files/Publication/zwjc_ijcai01.pdf Its demo is available at http://cs.nju.edu.cn/people/zhouzh/zhouzh.files/MLNN_Group/freeware/Gasen.zip Regards Zhihua ----------------------------------------------- Zhi-Hua ZHOU Ph.d. National Lab for Novel Software Technology Nanjing University Hankou Road 22 Nanjing 210093, P.R.China Tel: +86-25-359-3163 Fax: +86-25-330-0710 URL: http://cs.nju.edu.cn/people/zhouzh/ Email: zhouzh at nju.edu.cn ----------------------------------------------- From marco at cs.uu.nl Fri Jun 22 05:44:40 2001 From: marco at cs.uu.nl (Marco Wiering) Date: Fri, 22 Jun 2001 11:44:40 +0200 (MET DST) Subject: CFP: European Workshop on Reinforcement Learning (EWRL5) Message-ID: <20010622094440.ABCD74545@mail.cs.uu.nl> Call for Participation The Fifth European Workshop on Reinforcement Learning (EWRL5'2001) 5 and 6 October 2001 Utrecht, the Netherlands The biennial European Workshop on Reinforcement Learning (EWRL) will take place in Utrecht, the Netherlands this year. The goal is to gather researchers interested in Reinforcement Learning and its applications. The invited talk will be presented by Prof. Leslie Kaelbling. We encourage the submission of a 2-page abstract, on any aspect of Reinforcement Learning including (but not restricted to): Theoretical aspects of reinforcement learning Function approximation in reinforcement learning Exploration in reinforcement learning Direct vs. Indirect reinforcement learning Multi-agent reinforcement learning Robotic reinforcement learning Novel algorithms for reinforcement learning Reinforcement learning for complex problem solving Reinforcement learning for dynamic replanning Reinforcement learning and game theory The extended abstracts will be published in a proceedings. Important dates: Submission deadline : 10 August 2001 Acceptance/rejection notification : 3 September 2001 Submission of camera ready abstracts : 12 September 2001 Presentations at EWRL : 5/6 October 2001 For further information, we refer to the website: http://www.cs.uu.nl/~marco/EWRL5.html We look forward to seeing you at EWRL'2001 this year. Marco Wiering (marco at cs.uu.nl) Marco Dorigo (mdorigo at ulb.ac.be) From stefan.wermter at sunderland.ac.uk Mon Jun 25 11:28:54 2001 From: stefan.wermter at sunderland.ac.uk (Stefan.Wermter) Date: Mon, 25 Jun 2001 16:28:54 +0100 Subject: 2 new funded PhD studentships in Computing Message-ID: <3B3758B6.36AF9CB2@sunderland.ac.uk> With respect to this email list I would like to encourage applications from computing students for 2 PhD studentships in intelligent systems (e.g. neural networks, hybrid systems, cognitive neuroscience, neuro/fuzzy systems, machine learning, with applications in e.g. in natural language processing or robotics) General application text for all areas of interest below Stefan Wermter ------------------------------------- Funded Phd Opportunities in Computing, Engineering & Technology The School of Computing, Engineering & Technology at the University of Sunderland is seeking high quality, motivated applicants wishing to gain a PhD or MPhil in the disciplines of Computing, Mathematical Sciences, Engineering and Technology. The school has a strong and growing research profile with EPSRC-funded research, numerous EU-funded projects and a vibrant community of over 100 researchers. The School is well-resourced and offers excellent facilities with much state-of the art computing equipment and not only offers high quality postgraduate but also undergraduate programmes accredited by professional societies. We look for applications in both computing and mathematics as well as general engineering for two fully-funded PhD studentships. Students wishing to apply for the 2 funded places should look at the list of proposed projects available at http://www.cet.sunderland.ac.uk/postgrad/projects.html and indicate in their application which of these projects they would wish to undertake. The closing date for the 2 funded places is 8/7/01. Self-funding MPhil & PhD students are also welcome to apply at any time for full-time, part-time and distance learning research degrees in any of the areas detailed below. The main research groups in computing & mathematics are: intelligent systems (major strengths in neural networks, natural language engineering, hybrid systems, cognitive neuroscience, neuro/fuzzy systems, machine learning: Professor Stefan Wermter - stefan.wermter at sunderland.ac.uk +44 191 5153279); http://www.his.sunderland.ac.uk/~cs0stw/Projects/suggested_topics_titles.html human computer systems (includes themes such as multimedia, computer-aided learning, computing for the disabled and human computer interaction evaluation methodologies: Professor Gilbert Cockton - gilbert.cockton at sunderland.ac.uk +44 191 5153394); software engineering (focussed on practical areas especially software testingand the organisationalrisks of implementing information systems, methodologies and solutions for industry: Professor Helen Edwards helen.edwards at sunderland.ac.uk +44 191 5152786 or Professor Barrie Thompson barrie.thompson at sunderland.ac.uk +44 191 5152769); electronic commerce (encompasses the development and promotion of standards in thisdynamic area with a special interest in the area of electronic procurement: Kevin Ginty - kevin.ginty at sunderland.ac.uk or Albert Bokma albert.bokma at sunderland.ac.uk +44 191 5153233); decision support systems (covers a diverse range of activitiesin statistics & mathematics at the boundary ofComputer Science and Statistics and Operational Research: Professor Eric Fletcher eric.fletcher at sunderland.ac.uk +44 191 5152822 or Professor Alfredo Moscardini alfredo.moscardini at sunderland.ac.uk +44 191 5152763); In order to apply please send a full CV (including 2 referees and indicating the project for which you wish to apply) to the address below. You may also find out more about either our PhD or MPhil research degrees, the current studentships and grants available by looking at: http://www.cet.sunderland.ac.uk/postgrad or getting in touch with: Dr. Chris. Bowerman - Principal Lecturer in Research Student Management School of Computing, Engineering & Technology, University of Sunderland, Informatics Centre, St Peter's Way, Sunderland, Tyne & Wear, GB-SR6 0DD Email: chris.bowerman at sunderland.ac.uk -------------------------------------------- *************************************** Professor Stefan Wermter Research Chair in Intelligent Systems University of Sunderland Centre of Informatics, SCET St Peters Way Sunderland SR6 0DD United Kingdom phone: +44 191 515 3279 fax: +44 191 515 3553 email: stefan.wermter at sunderland.ac.uk http://www.his.sunderland.ac.uk/~cs0stw/ http://www.his.sunderland.ac.uk/ **************************************** From espaa at exeter.ac.uk Tue Jun 26 09:48:12 2001 From: espaa at exeter.ac.uk (Oliver Jenkin) Date: Tue, 26 Jun 2001 14:48:12 +0100 (GMT Daylight Time) Subject: Special issue on Image Indexation Message-ID: Pattern Analysis & Applications ISSN: 1433-7541 (printed version) ISSN: 1433-755X (electronic version) Table of Contents Vol. 4 Issue 2/3 Jean-Michel Jolion : Editorial Pattern Analysis & Applications 4 (2001) 2/3, 81-82 Article in PDF format (79 KB)=20 S. Berretti, A. Del Bimbo, E. Vicario: Modelling Spatial Relationships between Colour Clusters Pattern Analysis & Applications 4 (2001) 2/3, 83-92 Article in PDF format (671 KB)=20 N. Tsapatsoulis, Y. Avrithis, S. Kollias: Facial Image Indexing in Multimedia Databases Pattern Analysis & Applications 4 (2001) 2/3, 93-107 Article in PDF format (488 KB)=20 Laurent Amsaleg, Patrick Gros: Content-based Retrienal Using Local Descriptors: Problems and Issues from a Database Perspective Pattern Analysis & Applications 4 (2001) 2/3, 108-124 Article in PDF format (1190 KB)=20 Joo-Hwee Lim: Building Visual Vocabulary for Image Indexation and Query Formulation Pattern Analysis & Applications 4 (2001) 2/3, 125-139 Article in PDF format (1598 KB)=20 Jorma Laaksonen, Markus Koskela, Sami Laakso, Erkki Oja: Self-Organising Maps as a Relevance Feedback Technique in Content-Based Image Retrieval Pattern Analysis & Applications 4 (2001) 2/3, 140-152 Article in PDF format (556 KB)=20 J. Fournier, M. Cord, S. Philipp-Foliguet: RETIN: A Content-Based Image Indexing and Retrieval System Pattern Analysis & Applications 4 (2001) 2/3, 153-173 Article in PDF format (1048 KB)=20 ByoungChul Ko, Jing Peng, Hyeran Byun: Region-based Image Retrieval Using Probabilistic Feature Relevance Learning Pattern Analysis & Applications 4 (2001) 2/3, 174-184 Article in PDF format (991 KB)=20 Patricia Ladret, Anne Gu=E9rin-Dugu=E9: Categorisation and Retrieval of Scene Photographs from JPEG Compressed Database Pattern Analysis & Applications 4 (2001) 2/3, 185-199 Article in PDF format (691 KB)=20 E. Louupias, S. Bres: Key Points-based Indexing for Pre-attentive Similarities: The KIWI System Pattern Analysis & Applications 4 (2001) 2/3, 200-214 Article in PDF format (1295 KB)=20 Linhui Jia, Leslie Kitchen: Object-Based Image Content Characterisation for Semantic-Level Image Similarity Calculation Pattern Analysis & Applications 4 (2001) 2/3, 215-226 Article in PDF format (454 KB)=20 --- End Forwarded Message --- __________________________________________ Oliver Jenkin Pattern Analysis and Applications Journal Department of Computer Science University of Exeter Exeter EX4 4PT UK Tel: +44-1392-264061 Fax: +44-1392-264067 E-mail: espaa at ex.ac.uk Web: http://www.dcs.ex.ac.uk/paa ____________________________________________ From j.v.stone at sheffield.ac.uk Tue Jun 26 11:23:53 2001 From: j.v.stone at sheffield.ac.uk (Jim Stone) Date: Tue, 26 Jun 2001 16:23:53 +0100 Subject: source separation code available Message-ID: MatLab code (version 5.2) for implementing blind source separation is available from: http://www.shef.ac.uk/~pc1jvs/ This site also contains a demonstration of the method working on instantaneous mixtures of musical sounds. The code is an implementation of the method described in the current issue of Neural Computation: Stone JV, "Blind Source Separation Using Temporal Predictability", Neural Computation, 13(7), pp 1559-1547, July, 2001. The above web site also contains MatLab code (written in 1999) for performing spatial, temporal, spatiotemporal, and weak model ICA of 2D images using a conjugate gradient method to maximise the function defined in Bell and Sejnowski's paper: Bell, A and Sejnowski, T "An information-maximization approach to blind separation and blind deconvolution", Neural Computation}, 7, pp 1129-1159, 1995. Jim Stone. ,--------------------------------------------------------------------------. | Dr Jim Stone, Sheffield University Research Fellow | +-------------------------------------------------------------------------+ | Psychology Department, | Email: j.v.stone at sheffield.ac.uk | | Sheffield University | Tel : +44 114 222 6522 | | Sheffield, S10 2UR, | Fax: +44 114 276 6515 | | England. | http://www.shef.ac.uk/~pc1jvs/ | `---------------------------------------------------------------------------' From terry at salk.edu Wed Jun 27 17:45:45 2001 From: terry at salk.edu (Terry Sejnowski) Date: Wed, 27 Jun 2001 14:45:45 -0700 (PDT) Subject: NEURAL COMPUTATION 13:8 Message-ID: <200106272145.f5RLjjK38750@purkinje.salk.edu> Neural Computation - Contents - Volume 13, Number 8 - August 1, 2001 ARTICLE Orientation, Scale, and Discontinuity as Emergent Properties of Illusory Contour Shape Lance R. Williams and Karvel K. Thornber LETTERS Orientation Tuning Properties of Simple Cells in Area V1 Derived from an Approximate Analysis of Nonlinear Neural Field Models Thomas Wennekers Computational Design and Nonlinear Dynamics of a Recurrent Network Model of the Primary Visual Cortex Zhaoping Li A Hierarchical Dynamical Map as a Basic Frame for Cortical Mapping and Its Application to Priming Osamu Hoshino, Satoru Inoue, Yoshiki Kashimori and Takeshi Kambara Dynamical Stability Conditions for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions Heiko Wersing, Wolf-Jurgen Beyn and Helge Ritter An Information-Based Neural Approach to Constraint Satisfaction Henrik Jonsson and Bo Soderberg Recurrence Methods in the Analysis of Learning Processes S. Mendelson and I. Nelken Subspace Information Criterion for Model Selection Masashi Sugiyama and Hidemitsu Ogawa Convergent Decomposition Techniques for Training RBF Neural Networks C. Buzzi, L. Grippo and M. Sciandrone ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2001 - VOLUME 13 - 12 ISSUES USA Canada* Other Countries Student/Retired $60 $64.20 $108 Individual $88 $94.16 $136 Institution $460 $492.20 $508 * 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 ps629 at columbia.edu Wed Jun 27 12:14:16 2001 From: ps629 at columbia.edu (Paul Sajda) Date: Wed, 27 Jun 2001 09:14:16 -0700 Subject: Postdoc Position in Comp Neural Modeling Message-ID: <3B3A0657.863AC685@columbia.edu> Postdoctoral Position in Computational Neural Modeling--a two year position is available immediately for conducting research in modeling of neural mechanisms for visual scene analysis, with particular applications to spatio-temporal and hyperspectral imagery. A mathematical and computational background is desired, particularly in probabilistic modeling and optimization. This position will be part of a multi-university research team (UPenn, Columbia and MIT) investigating biomimetic methods for analysis of literal and non-literal imagery through a combination of experimental physiology, neuromorphic design and simulation, computational modeling and visual psycophysics. Applicants should send a CV, three representative papers and the names of three references to Prof. Paul Sajda, Department of Biomedical Engineering, Columbia University, 530 W 120th Street, NY, NY 10027. Or email to ps629 at columbia.edu. -- Paul Sajda, Ph.D. Associate Professor Department of Biomedical Engineering 530 W 120th Street Columbia University New York, NY 10027 tel: (212) 854-5279 fax: (212) 854-8725 email: ps629 at columbia.edu From curt at citrus.ucr.edu Wed Jun 27 15:56:09 2001 From: curt at citrus.ucr.edu (Dr. Curt Burgess) Date: Wed, 27 Jun 2001 12:56:09 -0700 Subject: Two Cognitive Psychology positions, Univ Calif, Riverside Message-ID: Dear Connectionists - I wanted to particularly let people on this list know that we will have two job searches this coming fall. Someone doing connectionist work would be of particular interest to a number of us in the cognitive group (currently six faculty in psychology). We are undergoing considerable growth on our campus. Our department will likely almost double in size by 2010. We are scheduled to move into a renovated building in two years. We have just received word that Psychology will have its own new building in 2007 or 2008 with around twice the space we currently have. These two positions are junior level. However, we may also be able to hire at the senior level within the guidelines of a new hiring initiative specifically designed to target senior faculty of notable reputation. Thus, we are very interested in identifying individuals who might be interested in this opportunity. If you have any questions, please feel free to contact either me or Chris Chiarello (see below). Curt Burgess ------------------------------- COGNITIVE PSYCHOLOGIST TWO POSITIONS. The Department of Psychology, University of California, Riverside, invites applications for two tenure-track Assistant Professor positions in Cognitive Psychology, beginning July 1, 2002. The Ph.D. degree is required at the time of the appointment. Salary will be commensurate with education and experience. We seek applicants whose research investigates fundamental mechanisms of cognition including memory, language, perception, or attention, which are areas of strength within the current program. We are also interested in individuals whose research is relevant to cognitive aging. Applicants should also be committed to excellence in undergraduate and graduate education. Review of completed applications will begin Oct. 15, 2001 and continue until the position is filled. Interested candidates should send their curriculum vitae, reprints, a cover letter describing research and teaching interests, and arrange to have three letters of recommendation sent to: Dr. Christine Chiarello Chair, Cognitive Psychology Search Committee Department of Psychology - Box D University of California - Riverside Riverside, CA 92521 The Riverside campus of the University of California is growing rapidly and has an excellent psychology department with a strong record of success in research, teaching, and extramural funding. For information on the Department of Psychology, see our web site at: http://www.psych.ucr.edu/. The campus is centrally located in Southern California, about 50 miles east of Los Angeles and less than an hour's drive from the area's mountains, deserts, and beaches. The University of California, Riverside is an equal opportunity employer/affirmative action employer. -- Dr. Curt Burgess, Computational Cognition Lab Associate Editor, Brain and Cognition Chair of Graduate Admissions for Psychology Department of Psychology, University of California 1419 Life Science Building Riverside, CA 92521-0426 URL: http://locutus.ucr.edu/ Internet: curt at citrus.ucr.edu MaBellNet: (909) 787-2392 FAX: (909) 787-3985 *** have you visited http://www.psychgrad.org ?? *** From abbass at cs.adfa.edu.au Thu Jun 28 00:43:46 2001 From: abbass at cs.adfa.edu.au (Hussein A. Abbass) Date: Thu, 28 Jun 2001 14:43:46 +1000 Subject: CFP: The Inaugural workshop on Artificial Life (AL'01), Adelaide, Australia. 11-Dec-2001 Message-ID: <3.0.6.32.20010628144346.00896990@csadfa.cs.adfa.edu.au> Dear colleague I would appreciate it very much if you can post our first call for papers to your colleague and students. Best Regards, Hussein. The Inaugural workshop on Artificial Life (AL'01) http://www.cs.adfa.edu.au/~abbass/ALL/ Adelaide, Australia. 11-Dec-2001 To be held within the 14th Australian Joint Conference on Artificial Intelligence (AI'01) http://www.cs.adelaide.edu.au/AI2001/ December 2001 IMPORTANT ******* A special issue in an outstanding journal is being investigated Call For Papers =============== The Inaugural workshop on Artificial Life, (AL'01), will be held in conjunction with the Australian Joint Conference on Artificial Intelligence in December 2001. Usually, the term "Artificial Life" (Alife) is used to delineate systems that exhibit some properties of life. Research in Alife ranges from analyzing and understanding life and nature - at least as we may believe it is - to modeling biological systems or solving biological problems. Alife is a large interdisciplinary research area covering research from computer science, biology, chemistry, physics, engineering, sociology, and psychology. Research in Alife can be generically classified into three main areas: ? Biological behavior as a metaphor for computational models; such as Ant Algorithms, Ant Colony Optimization, Marriage in Honey-Bees Optimization, Immune Systems, Neural Networks, Evolutionary Algorithms, forest, and DNA computing. ? Computational models that reproduce/duplicate a biological behavior; such as Swarm Intelligence, Simulation, Cellular Automaton ? Computational models to solve biological problems; such as Bio-informatics The aim of this workshop is to get together computer scientists, biologists, chemists, engineers, geneticists, physicists, and others, to gain more understanding of the mystery hidden in life and to expose researchers to the recent advances in this fast developing area. Topics of interest include, but not limited to, * Ant Algorithms * Ant Colony Optimization * Applications of ALife technologies * Bioinformatics * Biological agents and robotics * Cellular automaton * Complex systems * Emergence * Evolutionary and adaptive dynamics * Marriage in Honey-bees Optimization * Multi-agent systems * Origin of life * Self-organization * Self-replication * Simulation and synthesis tools and methodologies * Swarm Intelligence * and Other related topics Location ======== University of South Australia, Adelaide, Australia Important Dates =============== Submission of papers: 15-Sep-2001 Notification to authors: 26-Oct-2001 Camera ready format: 09-Nov-2001 Workshop date: 11-Dec-2001 Paper Format and Review Process =============================== Each paper will be reviewed by at least two members of the program committee. After the final decision is made regarding the papers, authors will receive the instructions for the final submission of their papers accompanied with the reports of the reviewers. At least one author is expected to attend at the workshop to present his/her paper. All papers must have a title page that includes a title, a 300-400 word abstract, a list of keywords, the names and addresses of all authors, their email addresses, and their telephone and fax numbers. Publication =========== Accepted papers will be published in the workshop proceedings with an ISBN number. The maximum number of pages is 10. A special issue in an outstanding journal is currently being negotiated. All papers submitted to the workshop will be considered to the special issue. Depending on the number of submissions to the workshop, submission to the special issue will most likely be restricted to the workshop participants. Workshop Chair ============== Hussein A. Abbass University of New South Wales, School of Computer Science, Australian Defence Force Academy Campus, NorthCott Drive, Canberra, ACT2600, Australia. Email: abbass at cs.adfa.edu.au Fax: +61-2-62688581 Workshop Program Committee ========================== Eric Bonabeau (Icosystem & Santa Fe, USA) Dipankar Dasgupta (Memphis, USA) Marco Dorigo (Libre de Bruxelles, Belgium) David Fogel (Natural Selection, USA) Tim Hendtlass (Swinburne, Australia) Jun Jo (Griffith, Australia) Nikola Kasabov (Otago, New Zealand) Jong-Hwan Kim (KAIST, Korea) Erhan Kozan (QUT, Australia) Xiaodong Li (RMIT, Australia) Bob Mckay (UNSW, Australia) Saeid Nahavandi (Deakin, Australia) Akira Namatame (Defence Academy, Japan) Marcus Randall (Bond, Australia) Guy Theraulaz (Paul Sabatier, France) Prahlad Vadakkepat (National University, Singapore) Brijesh Verma (Griffith, Australia) Xin Yao (Birmingham, UK) Dr. Hussein A. Abbass (BA, BSc, PG-Dip, M.Phil., M.Sc., Ph.D.) University of New South Wales, School of Computer Science, Australian Defence Force Academy Campus, NorthCott Drive, Canberra, ACT2600, Australia. Email: abbass at cs.adfa.edu.au http: http://www.cs.adfa.edu.au/~abbass Tel.(M) (+61) 0402212977 Tel.(H) (+61) (2) 62578757 Tel.(W) (+61) (2) 62688158 Fax.(W) (+61) (2) 62688581 From goldfarb at unb.ca Thu Jun 28 01:41:22 2001 From: goldfarb at unb.ca (Lev Goldfarb) Date: Thu, 28 Jun 2001 02:41:22 -0300 (ADT) Subject: What is a structural represetation? Message-ID: (Our apologies if you receive multiple copies of this announcement) Dear colleagues, The following paper, titled "What is a structural representation?", ( http://www.cs.unb.ca/profs/goldfarb/struct.ps ) which we believe to be, in a sense, the first one formally addressing the issue of structural representation and proposing the formal ETS model, should be of interest to many researchers in various areas. It implies, in particular, that the properly understood (non-trivial) "structural" representations cannot be "replaced" by the classical numeric, e.g. vector-space-based, representations. Moreover, the concept of "structural" representation emerging from the ETS model is not the one familiar to all of you. (The abstract of the paper is appended below; for a change, the default paper size is A4. Unfortunately for some, the language of the paper is of necessity quite formal, since the main concepts do not have any analogues and therefore must be treated carefully.) Although the proposed model was motivated by, and will be applied to, the "real" problems coming from such areas as pattern recognition, machine learning, data mining, cheminformatics, bioinformatics, and many others, in view of the required radical rethinking that must now go into its implementations, at this time, we can only offer a very preliminary discussion, in the following companion paper, addressing the model's potential applications in chemistry http://www.cs.unb.ca/profs/goldfarb/cadd.ps (please keep in mind that the last paper was written on the basis of an earlier draft of the paper we are announcing now and it will be updated accordingly next month). We intend to discuss the paper shortly on INDUCTIVE mailing list. (To subscribe, send to INDUCTIVE-SERVER at UNB.CA the following text SUBSCRIBE INDUCTIVE FIRSTNAME LASTNAME) We would greatly appreciate any comments regarding both of the above papers. Best regards, Lev Goldfarb Tel: 506-458-7271 Faculty of Computer Science Tel(secret.): 453-4566 University of New Brunswick Fax: 506-453-3566 P.O. Box 4400 E-mail: goldfarb at unb.ca Fredericton, N.B., E3B 5A3 Home tel: 506-455-4323 Canada http://www.cs.unb.ca/profs/goldfarb/goldfarb.htm ***************************************************************************** WHAT IS A STRUCTURAL REPRESENTATION? Lev Goldfarb, Oleg Golubitsky, Dmitry Korkin Faculty of Computer Science University of New Brunswick Fredericton, NB, Canada We outline a formal foundation for a "structural" (or "symbolic") object/event representation, the necessity of which is acutely felt in all sciences, including mathematics and computer science. The proposed foundation incorporates two hypotheses: 1) the object's formative history must be an integral part of the object representation and 2) the process of object construction is irreversible, i.e. the "trajectory" of the object's formative evolution does not intersect itself. The last hypothesis is equivalent to the generalized axiom of (structural) induction. Some of the main difficulties associated with the transition from the classical numeric to the structural representations appear to be related precisely to the development of a formal framework satisfying these two hypotheses. The concept of (inductive) class--which has inspired the development of this approach to structural representation--differs fundamentally from the known concepts of class. In the proposed, evolving transformations system (ETS), model, the class is defined by the transformation system---a finite set of weighted transformations acting on the class progenitor--and the generation of the class elements is associated with the corresponding generative process which also induces the class typicality measure. Moreover, in the ETS model, a fundamental role of the object's class in the object's representation is clarified: the representation of an object must include the class. From the point of view of ETS model, the classical discrete representations, e.g. strings and graphs, appear now as incomplete special cases, the proper completion of which should incorporate the corresponding formative histories, i.e. those of the corresponding strings or graphs. From J.A.Bullinaria at cs.bham.ac.uk Thu Jun 28 09:36:33 2001 From: J.A.Bullinaria at cs.bham.ac.uk (John A Bullinaria) Date: Thu, 28 Jun 2001 14:36:33 +0100 (BST) Subject: Studentships in Natural Computation Message-ID: ------------------------- Scholarships/Studentships ------------------------- MSc/PGDip/PGCert in Natural Computation ======================================= http://www.cs.bham.ac.uk/natcomp School of Computer Science The University of Birmingham, UK Starting in October 2001, we are offering an advanced 12 month MSc programme in Natural Computation (i.e. computational systems that use ideas and inspirations from natural biological, ecological and physical systems). This will comprise of six taught modules in Neural Computation, Evolutionary Computation, Molecular and Quantum Computation, Nature Inspired Optimisation, Nature Inspired Learning, and Nature Inspired Design; two mini research projects; and one full scale research project. PGDip and PGCert are available for shorter periods. Part-time studies are welcome. The programme is supported by the EPSRC through its Master's Level Training Packages, and by a number of leading companies. It is open to candidates with a very good honours degree or equivalent qualifications in Computer Science/Engineering or closely related areas. A small number of fully funded EPSRC studentships (scholarships) are available to UK/EU students. A small number of scholarships funded by the European Commission under its ASIA-ITC programme are available to Indian students. Additional financial support from our industrial partners may be available during the main project period. Further details are available from our Web-site at: http://www.cs.bham.ac.uk/natcomp or via email: Admissions at cs.bham.ac.uk Please note that the official closing date for applications is 15th July 2001, though good applications may still be considered after that date. From E.Koning at elsevier.nl Thu Jun 28 03:45:20 2001 From: E.Koning at elsevier.nl (Koning, Esther (ELS)) Date: Thu, 28 Jun 2001 09:45:20 +0200 Subject: free online access to three special issues of Neural Networks Message-ID: Dear Connectionists, We are pleased to inform you that three special issues of the Neural Networks journal are available free online at http://www.elsevier/com/cite * Organisation of Computation in Brain-like Systems (1999) edited by E. K=F6rner, Gen Matsumoto, Mitsuo Kawato * Neural Control and Robotics: Biology and Technology (1998) edited by R. Brooks, S. Grossberg, L. Optican * Consciousness for Neural Networks (1997) edited by J. Taylor, W. Freeman In addition, the abstracts and full text (PDF files) of the journal Cognitive Systems Research are available free at www.elsevier.com/cite through the end of 2001, and may be of interest to you. Best regards, Esther Koning From bbs at bbsonline.org Fri Jun 29 16:53:12 2001 From: bbs at bbsonline.org (Stevan Harnad - Behavioral & Brain Sciences (Editor)) Date: Fri, 29 Jun 2001 16:53:12 -0400 Subject: Webb: Can robots make good models of biological behaviour? -- BBS Call for Commentators Message-ID: Below is the abstract of a forthcoming BBS target article [Please note that this paper was in fact accepted and archived to the web in February 2001 but the recent move of BBS to New York delayed the Call until now.] Can robots make good models of biological behaviour? by Barbara Webb http://www.bbsonline.org/Preprints/Webb/ This article has been accepted for publication in Behavioral and Brain Sciences (BBS), an international, interdisciplinary journal providing Open Peer Commentary on important and controversial current research in the biobehavioral and cognitive sciences. Commentators must be BBS Associates or nominated by a BBS Associate. To be considered as a commentator for this article, to suggest other appropriate commentators, or for information about how to become a BBS Associate, please reply by EMAIL within three (3) weeks to: calls at bbsonline.org The Calls are sent to 8000 BBS Associates, so there is no expectation (indeed, it would be calamitous) that each recipient should comment on every occasion! Hence there is no need to reply except if you wish to comment, or to nominate someone to comment. If you are not a BBS Associate, please approach a current BBS Associate (there are currently over 10,000 worldwide) who is familiar with your work to nominate you. All past BBS authors, referees and commentators are eligible to become BBS Associates. A full electronic list of current BBS Associates is available at this location to help you select a name: http://www.bbsonline.org/Instructions/assoclist.html If no current BBS Associate knows your work, please send us your Curriculum Vitae and BBS will circulate it to appropriate Associates to ask whether they would be prepared to nominate you. (In the meantime, your name, address and email address will be entered into our database as an unaffiliated investigator.) To help us put together a balanced list of commentators, please give some indication of the aspects of the topic on which you would bring your areas of expertise to bear if you were selected as a commentator. To help you decide whether you would be an appropriate commentator for this article, an electronic draft is retrievable from the online BBSPrints Archive, at the URL that follows the abstract below. _____________________________________________________________ Can robots make good models of biological behaviour? Barbara Webb Centre for Computational and Cognitive Neuroscience Department of Psychology University of Stirling Stirling FK9 4LA Scotland, U.K. b.h.webb at stir.ac.uk www.stir.ac.uk/psychology/Staff/bhw1/ KEYWORDS: models; simulation; animal behaviour; neuroethology; robotics; realism; levels. ABSTRACT: How should biological behaviour be modelled? A relatively new approach is to investigate problems in neuroethology by building physical robot models of biological sensorimotor systems. The explication and justification of this approach are here placed within a framework for describing and comparing models in the behavioural and biological sciences. First, simulation models - the representation of a hypothesis about a target system - are distinguished from several other relationships also termed 'modelling' in discussions of scientific explanation. Seven dimensions on which simulation models can differ are defined and distinctions between them discussed: (1) Relevance: whether the model tests and generates hypotheses applicable to biology. (2) Level: the elemental units of the model in the hierarchy from atoms to societies. (3) Generality: the range of biological systems the model can represent. (4) Abstraction: the complexity, relative to the target, or amount of detail included in the model. (5) Structural accuracy: how well the model represents the actual mechanisms underlying the behaviour. (6) Performance match: to what extent the model behaviour matches the target behaviour (7) Medium: the physical basis by which the model is implemented No specific position in the space of models thus defined is the only correct one, but a good modelling methodology should be explicit about its position and the justification for that position. It is argued that in building robot models biological relevance is more effective than loose biological inspiration; multiple levels can be integrated; that generality cannot be assumed but might emerge from studying specific instances; abstraction is better done by simplification than idealisation; accuracy can be approached through iterations of complete systems; that the model should be able to match and predict target behaviour; and that a physical medium can have significant advantages. These arguments reflect the view that biological behaviour needs to be studied and modelled in context, that is in terms of the real problems faced by real animals in real environments. http://www.bbsonline.org/Preprints/Webb/ ___________________________________________________________ Please do not prepare a commentary yet. Just let us know, after having inspected it, what relevant expertise you feel you would bring to bear on what aspect of the article. We will then let you know whether it was possible to include your name on the final formal list of invitees. _______________________________________________________________________ *** SUPPLEMENTARY ANNOUNCEMENTS *** (1) The authors of scientific articles are not paid money for their refereed research papers; they give them away. What they want is to reach all interested researchers worldwide, so as to maximize the potential research impact of their findings. Subscription/Site-License/Pay-Per-View costs are accordingly access-barriers, and hence impact-barriers for this give-away research literature. There is now a way to free the entire refereed journal literature, for everyone, everywhere, immediately, by mounting interoperable university eprint archives, and self-archiving all refereed research papers in them. Please see: http://www.eprints.org http://www.openarchives.org/ http://www.dlib.org/dlib/december99/12harnad.html --------------------------------------------------------------------- (2) All authors in the biobehavioral and cognitive sciences are strongly encouraged to self-archive all their papers in their own institution's Eprint Archives or in CogPrints, the Eprint Archive for the biobehavioral and cognitive sciences: http://cogprints.soton.ac.uk/ It is extremely simple to self-archive and will make all of our papers available to all of us everywhere, at no cost to anyone, forever. Authors of BBS papers wishing to archive their already published BBS Target Articles should submit it to BBSPrints Archive. Information about the archiving of BBS' entire backcatalogue will be sent to you in the near future. Meantime please see: http://www.bbsonline.org/help/ and http://www.bbsonline.org/Instructions/ --------------------------------------------------------------------- (3) Call for Book Nominations for BBS Multiple Book Review In the past, Behavioral and Brain Sciences (BBS) had only been able to do 1-2 BBS multiple book treatments per year, because of our limited annual page quota. BBS's new expanded page quota will make it possible for us to increase the number of books we treat per year, so this is an excellent time for BBS Associates and biobehavioral/cognitive scientists in general to nominate books you would like to see accorded BBS multiple book review. (Authors may self-nominate, but books can only be selected on the basis of multiple nominations.) It would be very helpful if you indicated in what way a BBS Multiple Book Review of the book(s) you nominate would be useful to the field (and of course a rich list of potential reviewers would be the best evidence of its potential impact!).