From harnad at ecs.soton.ac.uk Fri Oct 1 12:06:11 2004 From: harnad at ecs.soton.ac.uk (Stevan Harnad) Date: Fri, 1 Oct 2004 17:06:11 +0100 (BST) Subject: Open access questionnaire: Call for respondents (fwd) Message-ID: *Apologies for cross-posting* ---------- Forwarded message ---------- From a.swan at talk21.com Fri Oct 1 11:56:10 2004 From: a.swan at talk21.com (Alma Swan) Date: Fri, 1 Oct 2004 16:56:10 +0100 Subject: Open access questionnaire: Call for respondents Message-ID: Dear Colleague, Open access to scholarly journal articles is a topic of growing importance. Open access enables free and immediate electronic access to a scholar's work. Studies show that open access increases the impact of - and number of citations to - work made accessible in this way. We are interested in understanding scholars' views on open access publishing and self-archiving and would very much like to hear your opinions. Please would you help by completing the questionnaire at http://www.keyperspectives.co.uk/OA/sarchiv.htm. It will be used to inform universities, research funders and scholars themselves of the state of play and how open access is progressing. Naturally, all responses will be treated as confidential and you may opt to remain anonymous if you wish. Thank you in advance for your cooperation. We do value your input and advice. Yours sincerely, Alma Swan, PhD Key Perspectives Ltd Truro United Kingdom From r.kempter at biologie.hu-berlin.de Fri Oct 1 08:31:21 2004 From: r.kempter at biologie.hu-berlin.de (Richard Kempter) Date: Fri, 1 Oct 2004 14:31:21 +0200 Subject: FINAL CALL: Berlin Autumn School LEARNING AND MEMORY, Oct 11-13, 2004. Message-ID: <20041001123121.GA28347@pauling.biologie.hu-berlin.de> Announcement, program, and final call for participation: Berlin Autumn School LEARNING AND MEMORY: MOLECULAR MECHANISMS - CELLULAR PROCESSES - MATHEMATICAL MODELS October 11-13, 2004 Berlin, Germany Learning and memory are central ingredients for proper biological function in changing environments. Both processes are of particular importance for neuroscience but they also play a significant role in other biological disciplines. This autumn school focuses on the basic molecular and cellular processes underlying learning and memory in neural systems, with emphasis on synaptic plasticity. Experimental approaches will be discussed in close relation with the corresponding mathematical models, both at an introductory level. The last day of the school will bridge between the physiological and behavioral level and also touch on learning and memory in the immune system. REGISTRATION: E-mail to Richard Kempter before October 4 r.kempter at biologie.hu-berlin.de PROGRAM Monday, October 11: 8:30 - 9:00 Arrival 9.00 - 9:15 Opening of the Autumn School 9.15 - 10.45 Dietmar Schmitz (NWFZ, Charite) Cellular processes of learning and memory: Development & current state of concepts and experiments (I) 11.15 - 12.45 Andreas Herz (ITB, HU Berlin) Modelling short-term synaptic plasticity with differential equations and iterated maps (I) 15.15 - 16.45 Dietmar Kuhl (Neurobiology, FU Berlin) Molecular and cellular mechanisms of learning and memory (I) 17.15 - 18.45 Hanspeter Herzel (ITB, Charite) Modelling molecular signal transduction chains and networks 19.00 - Reception and Dinner Tuesday, October 12: 9.15 - 10.45 Dietmar Schmitz (NWFZ, Charite) Cellular processes of learning and memory: Development & current state of concepts and experiments (II) 11.15 - 12.45 Andreas Herz (ITB, HU Berlin) Modelling short-term synaptic plasticity with differential equations and iterated maps (II) 15.15 - 16.45 Dietmar Kuhl (Neurobiology, FU Berlin) Molecular and cellular mechanisms of learning and memory (II) 17.15 - 18.45 Laurenz Wiskott (ITB, HU Berlin) Modelling learning and memory: The systems level Wednesday, October 13: 9.15 - 10.15 Dietmar Schmitz (NWFZ, Charite) Short- and long-term plasticity of the mossy fiber synapse 10.15 - 11.15 Richard Kempter (ITB, HU Berlin) Hippocampal plasticity: Learning behavioral sequences 11.45 - 12.45 Andreas Radbruch (DRFZ, Berlin) Memory in the immune system 15.15 - 16.15 Gerd Kempermann (Max Delbrueck Center, Berlin) Adult neurogenesis 16.15 - 17.15 Livia de Hoz (Neurophysiology, Charite) Memory consolidation 17.45 - 19.15 Andreas Herz (ITB, HU Berlin) The Hebbian memory trace: New insight from bee olfaction LOCATION: Lecture Hall 12, Department of Biology, Humboldt-Universitaet zu Berlin, Invalidenstrasse 43, 10115 Berlin-Mitte. REGISTRATION: E-mail to Richard Kempter before October 4: r.kempter at biologie.hu-berlin.de The registration fee of 30 Euro (students 15 Euro) is to be paid upon arrival and includes the buffet on Monday (Oct 11) evening. For details, please visit: http://itb.biologie.hu-berlin.de/events/memory.html PDF poster of this announcement: http://itb.biologie.hu-berlin.de/~kempter/berlin_autumn_school/learning_and_memory_2004.pdf -- The autumn school on "Learning and Memory" is organized by the DFG Collaborative Research Center ("Sonderforschungsbereich", SFB 618) "Theoretical Biology: Robustness, Modularity, and Evolutionary Design of Living Systems" Humboldt-Universitaet zu Berlin Department of Biology Invalidenstrasse 43 10115 Berlin, Germany http://www.biologie.hu-berlin.de/forschung/SFB_618/ From Gunnar.Raetsch at tuebingen.mpg.de Mon Oct 4 15:58:54 2004 From: Gunnar.Raetsch at tuebingen.mpg.de (Gunnar Raetsch) Date: Mon, 4 Oct 2004 21:58:54 +0200 Subject: Two Books: Advanced Lectures on Machine Learning Message-ID: Dear Connectionists, I would like to announce two recent books: Advanced Lectures on Machine Learning Tutorial Lectures from the Machine Learning Summer Schools (http://mlss.cc) in Canberra (Australia), Tuebingen (Germany) & Berder (France) published by Springer Verlag as LNAI 3176 (O. Bousquet, U. von Luxburg, G. Raetsch, Eds) http://www.springerlink.com/link.asp?id=lrh41y849xdh LNAI 2600 (S. Mendelson & A.J. Smola, Eds) http://www.springerlink.com/link.asp?id=4brrn87rrdpn Please find the tables of contents below. Best regards, Gunnar LNAI 3176 (O. Bousquet, U. von Luxburg, G. Raetsch, Eds) http://www.springerlink.com/link.asp?id=lrh41y849xdh -------------------------------------------------------- * An Introduction to Pattern Classification (Elad Yom-Tov) * Some Notes on Applied Mathematics for Machine Learning (Christopher J.C. Burges) * Bayesian Inference: An Introduction to Principles and Practice in Machine Learning (Michael E. Tipping) * Gaussian Processes in Machine Learning (Carl Edward Rasmussen) * Unsupervised Learning (Zoubin Ghahramani) * Monte Carlo Methods for Absolute Beginners (Christophe Andrieu) * Stochastic Learning (L?on Bottou) * Introduction to Statistical Learning Theory (Olivier Bousquet, St?phane Boucheron and G?bor Lugosi) * Concentration Inequalities (St?phane Boucheron, G?bor Lugosi and Olivier Bousquet) LNAI 2600 (S. Mendelson & A.J. Smola, Eds) http://www.springerlink.com/link.asp?id=4brrn87rrdpn -------------------------------------------------------- * A Few Notes on Statistical Learning Theory (Shahar Mendelson) * A Short Introduction to Learning with Kernels (Bernhard Sch?lkopf and Alexander J. Smola) * Bayesian Kernel Methods (Alexander J. Smola and Bernhard Sch?lkopf) * An Introduction to Boosting and Leveraging (Ron Meir and Gunnar R?tsch) * An Introduction to Reinforcement Learning Theory: Value Function Methods (Peter L. Bartlett) * Learning Comprehensible Theories from Structured Data (J.W. Lloyd) * Algorithms for Association Rules (Markus Hegland) * Online Learning of Linear Classifiers (Jyrki Kivinen) +-----------------------------------------------------------------+ Gunnar R"atsch http://www.tuebingen.mpg.de/~raetsch MPI for Biological Cybernetics Gunnar.Raetsch at tuebingen.mpg.de Spemannstr. 38 Tel: (+49) 7071 601 563 72076 T"ubingen, Germany Fax: (+49) 7071 601 552 +-----------------------------------------------------------------+ Gunnar R"atsch http://www.first.fhg.de/~raetsch Fraunhofer FIRST mailto:Gunnar.Raetsch at first.fhg.de Kekulestr. 7 Tel: (+49) 30 6392 1882 12489 Berlin, Germany Fax: (+49) 30 6392 1805 From rsun at rpi.edu Mon Oct 4 12:27:02 2004 From: rsun at rpi.edu (Professor Ron Sun) Date: Mon, 04 Oct 2004 12:27:02 -0400 Subject: Cognitive Science Ph.D program at RPI Message-ID: <416179D6.70702@rpi.edu> I am looking for a few Ph.D students. The Ph.D program of the Cognitive Science department at RPI is accepting applications. Graduate assistantships and other forms of financial support for graduate students are available. Prospective graduate students with interests in Cognitive Science, especially in learning and skill acquisition and in the relationship between cognition and sociality, are encouraged to apply. Prospective applicants should have background in computer science (the equivalent of a BS in computer science), and have some prior exposure to psychology, artificial intelligence, connectionist models (neural networks), multi-agent systems, and other related areas. Students with a Master's degree already completed are preferred. RPI is a top-tier research university. This new CogSci department has identified the Ph.D program and research as its primary missions. The department is conducting research in a number of areas: cognitive modeling, human and machine learning, multi-agent interactions and social simulation, neural networks and connectionist models, human and machine reasoning, cognitive engineering, and so on. See the Web page below regarding my research: http://www.cogsci.rpi.edu/~rsun For the application procedure, see http://www.cogsci.rpi.edu/ The application deadline is Jan.15, 2005. If you decide to apply, follow the official procedure as outlined on the Web page. Send me a short email (in plain text, ASCII) AFTER you have completed the application. -- =================================================================== Professor Ron Sun Cognitive Science Department Rensselaer Polytechnic Institute 110 Eighth Street, Carnegie 302A Troy, NY 12180, USA phone: 518-276-3409 fax: 518-276-3017 email: rsun at rpi.edu web: http://www.cogsci.rpi.edu/~rsun =================================================================== From ptodd at mpib-berlin.mpg.de Tue Oct 5 14:51:09 2004 From: ptodd at mpib-berlin.mpg.de (Peter M. Todd) Date: Tue, 05 Oct 2004 20:51:09 +0200 Subject: special issue of Adaptive Behavior on CTRNN cognitive modeling now freely available Message-ID: <4162ED1D.6090902@mpib-berlin.mpg.de> Dear colleagues, the journal Adaptive Behavior, covering models of behavior in animals and artificial agents, is now available in a new electronic form (including extensive cross-referencing) from the publisher, Sage, at http://adb.sagepub.com/archive/ Until the end of October, full-text access to current and past volumes (back to vol. 9) of Adaptive Behavior is available *free of charge*, so please take this opportunity to check out the recent contents. Of particular interest to connectionists will be the special issue 11:4, centering on a target article by Randall Beer, "*The Dynamics of Active Categorical Perception in an Evolved Model Agent", *along with accompanying commentaries by a number of authors discussing what we can learn about cognition by studying continuous-time recurrent neural networks. best wishes, Peter Todd Editor-in-Chief, Adaptive Behavior -- .............................................................. ' `. : Dr. Peter M. Todd : : Max Planck Institute for Human Development : : Center for Adaptive Behavior and Cognition : : Lentzeallee 94 : : 14195 Berlin GERMANY : : : : Editor-in-Chief, Adaptive Behavior : : Journal WWW: http://www.adaptive-behavior.org : : : : Email: ptodd at mpib-berlin.mpg.de : : WWW: http://www-abc.mpib-berlin.mpg.de/users/ptodd : : Phone: (+49) (30) 824 06 347 or 824 06 430 (secretary) : : Fax: (+49) (30) 824 06 394 or 824 99 39 : : : `..............................................................' From maass at igi.tu-graz.ac.at Tue Oct 5 12:37:21 2004 From: maass at igi.tu-graz.ac.at (Wolfgang Maass) Date: Tue, 05 Oct 2004 18:37:21 +0200 Subject: position for Phd student Message-ID: <4162CDC1.3030806@igi.tu-graz.ac.at> A position for a Phd-student is available in our research group on Neural Computation/Computational Neuroscience with emphasis on SOFTWARE FOR SIMULATIONS OF LARGER NEURAL SYSTEMS. The student is expected to have experience in software design (especially Linux, C++, Matlab, distributed computing), interest in creating software for distributed simulations of larger neural systems (especially visual areas), and in exploring computational properties and learning capabilities of neural systems. The student will spend about half of his/her time on research, and the other half on programming and software maintainance. No teaching is required. See http://www.lsm.tugraz.at/ for a software system that has previously been developed at our institute. Relevant courses and seminars for Phd-students are carried out in English, leading to a Phd in Computer Science. Applications should be sent to Wolfgang Maass maass at igi.tugraz.at -- Wolfgang Maass Professor of Computer Science Technische Universitaet Graz http://www.igi.tugraz.at/maass/ From cindy at bu.edu Wed Oct 6 10:51:14 2004 From: cindy at bu.edu (Cynthia Bradford) Date: Wed, 6 Oct 2004 10:51:14 -0400 Subject: three postdoctoral positions at Boston University Message-ID: <093101c4abb3$edb22fb0$903dc580@cnspc31> THREE POSTDOCTORAL FELLOWS DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS BOSTON UNIVERSITY Three postdoctoral fellows are sought to join the Boston University Department of Cognitive and Neural Systems as part of a major new NSF Science of Learning Center called CELEST (Center of Excellence for Learning in Education, Science, and Technology; Stephen Grossberg, PI; http://www.cns.bu.edu/CELEST). All three fellowships are available immediately for a minimum commitment of two years. Each fellow should have significant graduate training and published research in behavioral and brain modeling using neural networks, or in neuromorphic modeling in technology. One fellow will carry out basic research in developing biological neural networks in one or more CELEST research areas, in addition to working with CELEST colleagues to develop large-scale system models of brain and behavior. The other two postdoctoral fellows would combine basic research in behavioral and brain modeling and/or neuromorphic technology with education projects aimed at bringing current modeling knowledge about how the brain works into educational curricula at multiple levels. One fellow will work primarily with web-based materials, the other with printed materials. These postdocs would also interact with CELEST members to develop these educational resources. CELEST offers a wide range of excellent opportunities for broadening knowledge of neural modeling and experimentation, technological applications, and educational technology and outreach. Boston University is an Equal Opportunity/Affirmative Action Employer. Please send a curriculum vitae, 3 letters of recommendation, and illustrative research articles to: CELEST Postdoctoral Search, Room 203, Department of Cognitive and Neural Systems, Boston University, 677 Beacon Street, Boston, MA 02215. From fiori at unipg.it Thu Oct 7 05:56:25 2004 From: fiori at unipg.it (Simone G.O. FIORI) Date: Thu, 07 Oct 2004 11:56:25 +0200 Subject: Two essays on unsupervised learning theory. Message-ID: <1.5.4.32.20041007095625.022cabe4@unipg.it> Dear Connectionists, I take the liberty to announce the availability of two new papers on unsupervised complex-valued neural networks learning and on relative uncertainty learning theory. Best regards, Simone Fiori =*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*= "Non-linear Complex-Valued Extensions of Hebbian Learning: An Essay" by S. Fiori, University of Perugia (Italy) Accepted on Neural Computation Abstract: The Hebbian paradigm is perhaps the most known unsupervised learning theory in connectionism. It has inspired a wide research activity in the artificial neural network field because it embodies some interesting properties such as locality and the capability of being applicable to the basic weight-and-sum structure of neuron models. The plain Hebbian principle, however, also presents some inherent theoretical limitations that make it unpractical in most cases. Therefore, modifications of the basic Hebbian learning paradigm have been proposed over the last twenty years in order to design profitable signal/data processing algorithms. Such modifications led to the principal-component- analysis-type class of learning rules along with their non-linear extensions. The aim of this essay is primarily to present part of the existing fragmented material in the field of principal component learning within a unified view and contextually to motivate and present extensions of previous works on Hebbian learning to complex-weighted linear neural networks. This work benefits from previous studies on linear signal decomposition by artificial neural networks, non-quadratic component optimization and reconstruction error definition, neural parameters adaptation by constrained optimization of complex-valued learning criteria and orthonormality expression via the insertion of topological elements in the networks or by modifying the network learning criterion. In particular, the considered learning principles and their analysis concern complex-valued principal/minor component/subspace linear/non-linear rules for complex-weighted neural structures, both feedforward and laterally-connected. Draft (68 pages) available at: http://www.unipg.it/sfr/publications/rcpca.pdf =*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*= "Relative Uncertainty Learning Theory: An Essay" by S. Fiori, University of Perugia (Italy) Accepted on International Journal of Neural Systems Abstract: The aim of this manuscript is to present a detailed analysis of the algebraic and geometric properties of relative uncertainty theory (RUT) applied to neural networks learning. Through the algebraic analysis of the original learning criterion, it is shown that RUT gives rise to principal-subspace-analysis- type learning equations. Through an algebraic-geometric analysis, the behavior of such matrix-type learning equations is illustrated, with particular emphasis to the existence of certain invariant manifolds. Draft (33 pages) available at: http://www.unipg.it/sfr/publications/ijns-mut.pdf ======================================================= | Dr Simone FIORI (Elec. Eng., Ph.D.) | | * Faculty of Engineering - Perugia University * | | * Polo Didattico e Scientifico del Ternano * | | Via Pentima bassa, 21 - 05100 TERNI (Italy) | | Tel. 0744 492937 - Fax: +39 0744 492925 | | eMail: fiori at unipg.it - Web: http://www.unipg.it/sfr/ | ======================================================= | "Quelli che s'innamoran di pratica sanza scienza, son | | come il nocchiere, ch'entra in navilio sanza timone o | | bussola, che mai ha certezza dove si vada." | | (Leonardo da Vinci) | ======================================================= From terry at salk.edu Fri Oct 8 01:53:08 2004 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 7 Oct 2004 22:53:08 -0700 Subject: UCSD Computational Neurobiology Training Program Message-ID: <200410080553.i985r8cn011727@sherryl.salk.edu> DEADLINE: JANUARY 7, 2005 COMPUTATIONAL NEUROBIOLOGY GRADUATE PROGRAM Department of Biology - University of California, San Diego http://biology.ucsd.edu/grad/CN_overview.html The goal of the Computational Neurobiology Graduate Program at UCSD is to train researchers who are equally at home measuring large-scale brain activity, analyzing the data with advanced computational techniques, and developing new models for brain development and function. Financial support for students enrolled in this training program is available through an NSF Integrative Graduate Education and Research Training (IGERT) award. Candidates from a wide range of backgrounds are invited to apply, including Biology, Psychology, Computer Science, Physics and Mathematics. The three major themes in the training program are: 1. Neurobiology of Neural Systems: Anatomy, physiology and behavior of systems of neurons. Using modern neuroanatomical, behavioral, neuropharmacological and electrophysiological techniques. Lectures, wet laboratories and computer simulations, as well as research rotations. Major new imaging and recording techniques also will be taught, including two-photon laser scanning microscopy and functional magnetic resonance imaging (fMRI). 2. Algorithms and Realizations for the Analysis of Neuronal Data: New algorithms and techniques for analyzing data obtained from physiological recording, with an emphasis on recordings from large populations of neurons with imaging and multielectrode recording techniques. New methods for the study of co-ordinated activity, such as multi-taper spectral analysis and Independent Component Analysis (ICA). 3. Neuroinformatics, Dynamics and Control of Systems of Neurons: Theoretical aspects of single cell function and emergent properties as many neurons interact among themselves and react to sensory inputs. A synthesis of approaches from mathematics and physical sciences as well as biology will be used to explore the collective properties and nonlinear dynamics of neuronal systems, as well as issues of sensory coding and motor control. Participating Faculty include: * Henry Abarbanel (Physics): Nonlinear and oscillatory dynamics; modeling central pattern generators in the lobster stomatogastric ganglion. Director, Institute for Nonlinear Systems at UCSD * Thomas Albright (Salk Institute): Motion processing in primate visual cortex; linking single neurons to perception; fMRI in awake, behaving monkeys. Director, Sloan Center for Theoretical Neurobiology * Scott Baden (Computer Science and Engineering): High performance computing and management of complexity; MCell simulations of cell signaling. * Darwin Berg (Neurobiology): Regulation synaptic components, assembly and localization, function and long-term stability. * Richard Buxton (Radiology, School of Medicine): Brain imaging using MRI. fundamental aspects of cortical blood flow. * Garrison Cottrell (Computer Science and Engineering): Dynamical neural network models and learning algorithms * Anders Dale (Radiology, School of Medicine): Functional brain imaging; integration of metabolic and electromagnetic brain signals. * Virginia De Sa (Cognitive Science): Computational basis of perception and learning (both human and machine); multi-sensory integration and contextual influences * Mark Ellisman (Neurosciences, School of Medicine): High resolution electron and light microscopy; anatomical reconstructions. Director, National Center for Microscopy and Imaging Research * Marla Feller (Neurobiology): Mechanisms and function of spontaneous activity in the developing nervous system including the retina, spinal cord, hippocampus and neocortex. * Robert Hecht-Nielsen (Electrical and Computer Engineering): Neural computation and the functional organization of the cerebral cortex. Founder of Hecht-Nielsen Corporation * Harvey Karten (Neurosciences, School of Medicine): Anatomical, physiological and computational studies of the retina and optic tectum of birds and squirrels * David Kleinfeld (Physics): Active sensation in rats; properties of neuronal assemblies; optical imaging of large-scale activity. * William Kristan (Neurobiology): Computational Neuroethology; functional and developmental studies of the leech nervous system, including studies of the bending reflex and locomotion. Director, Neurosciences Graduate Program at UCSD * Herbert Levine (Physics): Nonlinear dynamics and pattern formation in physical and biological systems, including cardiac dynamics and the growth and form of bacterial colonies * Thomas Liu (Radiology, School of Medicine): Brain imaging using MRI. * Scott Makeig (Institute for Neural Computation): Analysis of cognitive event-related brain dynamics and fMRI using time-frequency and Independent Component Analysis * Javier Movellan (Institute for Neural Computation): Sensory fusion and learning algorithms for continuous stochastic systems * Mikhael Rabinovich (Institute for Nonlinear Science): Dynamical systems analysis of the stomatogastric ganglion of the lobster and the antenna lobe of insects * Terrence Sejnowski (Salk Institute/Neurobiology): Computational neurobiology; physiological studies of neuronal reliability and synaptic mechanisms. Director, Institute for Neural Computation * Martin Sereno (Cognitive Science): Neural bases of visual cognition and language using anatomical, electrophysiological, computational, and non-invasive brain imaging techniques * Nicholas Spitzer (Neurobiology): Regulation of ionic channels and neurotransmitters in neurons; effects of electrical activity in developing neurons on neural function. Chair of Neurobiology * Charles Stevens (Salk Institute): Synaptic physiology; physiological studies and biophysical models of synaptic plasticity in hippocampal neurons * Jochen Triesch (Cognitive Science): Sensory integration, visual psychophysics, vision systems and robotics, human-robot interaction, cognitive developmental * Emo Todorov (Cognitive Science): Neural control of movement; sensorimotor psychophysics in visuohaptic virtual environments; modeling the motor system. * Roger Tsien (Chemistry): Second messenger systems in neurons; development of new optical and MRI probes of neuron function, including calcium indicators and caged neurotransmitters * Hal White (Economics): Statistical learning theory. * Mark Whitehead (Neurosurgery, School of Medicine): Peripheral and central taste systems; anatomical and functional studies of regions in the caudal brainstem important for feeding behavior * Ruth Williams (Mathematics): Probabilistic analysis of stochastic systems and continuous learning algorithms Requests for application materials should be sent to the University of California, San Diego, Division of Biological Sciences 0348, Graduate Admissions Office, 9500 Gilman Drive, La Jolla, CA, 92093-0348 or to [gradprog at biomail.ucsd.edu]. The deadline for completed application materials, including letters of recommendation, is January 7, 2005. For more information about applying to the UCSD Biology Graduate Program. A preapplication is not required for the Computational Neurobiology Program. Contact ttomp at ucsd.edu for further information about admissions to the program. From H.Bowman at kent.ac.uk Fri Oct 8 09:45:48 2004 From: H.Bowman at kent.ac.uk (H. Bowman) Date: Fri, 08 Oct 2004 14:45:48 +0100 Subject: Conference Proceedings Available Message-ID: <41669A0C.5050205@kent.ac.uk> I have a number of copies of the following conference proceedings available at a reduced price. Progress in Neural Processing - Vol. 15 CONNECTIONIST MODELS OF COGNITION AND PERCEPTION II Proceedings of the Eighth Neural Computation and Psychology Workshop University of Kent, UK August 2003 Publisher : World Scientific edited by Howard Bowman (University of Kent, UK) & Christophe Labiouse (University of Liege, Belgium) Copies are available at the price of 20 (note, the publishers are currently selling this volume at a price of 65!). If you are interested in buying a copy at the reduced rate, then send an email to, H.Bowman at kent.ac.uk. Details of the volume can be found at: http://www.worldscibooks.com/books/compsci/5508.html Regards, Howard From fuernkranz at informatik.tu-darmstadt.de Sun Oct 10 17:46:13 2004 From: fuernkranz at informatik.tu-darmstadt.de (Johannes Fuernkranz) Date: Sun, 10 Oct 2004 23:46:13 +0200 Subject: GfKl-05 Special Track on Ranking, Multi-Label Classification and Preference Learning Message-ID: <4169ADA5.4060802@informatik.tu-darmstadt.de> Special Track on Ranking, Multi-Label Classification and Preference Learning GfKl-05 Magdeburg, Germany, 9-11 March 2005 Focus This track focusses on learning techniques for tackling prediction problems that transgress the two traditional disciplines, classification (prediciton of categorical variables) and regression (prediction of numerical variables). In particular, it will focus on approaches that predict more complex structures such as ordered categories, hierarchies, sets, lists, partial or total relations, etc. Papers that describe algorithms, theoretical results or applications in these areas are of interest for this special track. Submission of Abstracts Participants intending to present a talk are requested to submit an abstract at the main conference site. The abstract will be reviewed, and authors of accepeted abstracts will be invited to submit a full version of the paper to the post-conference proceedings (which will undergo a second round of reviewing). The proceedings will be published by Springer-Verlag in the 'Studies in Classification, Data Analysis, and Knowledge Organization' series. Track Chairs Johannes Frnkranz TU Darmstadt, Knowledge Engineering Group E-mail: fuernkranz at informatik.tu-darmstadt.de Eyke Hllermeier Philipps-Universitt Marburg, FB Mathematik und Informatik E-mail: eyke at mathematik.uni-marburg.de Important Dates November 1, 2004: Deadline for abstract submission January 17, 2005: Notification of acceptance March 9 - 11, 2005: Conference April 24, 2005: Submission of full paper -- Johannes Fuernkranz Knowledge Engineering Group, TU Darmstadt From Marie.Cottrell at univ-paris1.fr Tue Oct 12 08:37:57 2004 From: Marie.Cottrell at univ-paris1.fr (Marie Cottrell) Date: Tue, 12 Oct 2004 14:37:57 +0200 Subject: CFP WSOM'05 Message-ID: <5.0.2.1.2.20041012143734.023cf338@asterix.univ-paris1.fr> Please find the preliminary Call For Papers for the WSOM'05 conference, (Workshop on Self-Organizing Maps), which will take place in Paris, University Paris 1, Panth?on-Sorbonne, from Monday 5th September 2005 to Thursday 8th. Manuscript Submission deadline : 15 April 2005. Please forward to any colleagues who may be interested ------------------------------------------------------------------------------------------------------- CALL FOR PAPERS 5th Workshop on Self Organizing Maps (WSOM'05) Paris, University Paris 1, Panth?on-Sorbonne 5th-8th September 2005 WEB page (under construction) http://samos.univ-paris1.fr/wsom/wsom05.html OBJECTIVES The Self-Organizing Map (SOM) with its related extensions is the most popular artificial neural algorithm for use in unsupervised learning and data visualization. Over 5,000 publications have been reported in the open literature, and many commercial projects employ the SOM as the tool for solving hard real-world problems. WSOM'05 is the discussion forum where your ideas and techniques are polished, and aims to unveil the results of hot researches and popularize the use of the SOM for technical public. Following the highly successful meetings held in 1997 and 1999 (Helsinki University of Technology), 2001 (University of Lincolnshire and Humberside), 2003 (Kyushu Institute of Technology), a further workshop in this established series will bring together researchers and users of the SOM and related techniques. TOPICS Topics will include, but are not limited to, the following: Self-organization Unsupervised learning (including PCA/NLPCA, ICA/NLICA, Principal Curves/Surfaces) Theory and extensions Optimization Hardware and architecture Signal processing, image processing and vision Time-series analysis Text and document analysis Financial analysis Data visualization and mining Bioinformatics Robotics, ... All papers will be peer reviewed on the basis of a full length manuscript and acceptance will be based on quality, originality and relevance. Accepted papers will be published in the conference proceedings. IMPORTANT DATES Manuscript Submission 15 April 2005 Acceptance Notification 15 May 2005 Camera Ready Submission 30 May 2005 Advance Registration 15 June 2005 PAPER SUBMISSION Only electronic submissions are accepted. The mailing address and instructions for authors will be soon available on the WEB page. For further details, please contact the Organization Chairman Marie Cottrell (cottrell at univ-paris1.fr) Organized by the SAMOS-MATISSE, University of Paris 1. ************************************************* 3% of the European GDP for Science : When and How ? 3% du PIB europ?en pour la Science : Quand et Comment ? http://fer.apinc.org ************************************************ Marie Cottrell Tel et fax(prof): 33 1 44 07 89 22 SAMOS-MATISSE Universite Paris 1 E-mail : cottrell at univ-paris1.fr http://samos.univ-paris1.fr Postal address : 90, rue de Tolbiac 75634 PARIS CEDEX 13 Address of the laboratory : 72, rue Regnault 75013 Paris (m?tro Porte d'Ivry) -- Ce message a ?t? v?rifi? par MailScanner pour des virus ou des polluriels et rien de suspect n'a ?t? trouv?. From bernhard.schoelkopf at tuebingen.mpg.de Mon Oct 11 06:22:34 2004 From: bernhard.schoelkopf at tuebingen.mpg.de (Bernhard Schoelkopf) Date: Mon, 11 Oct 2004 12:22:34 +0200 Subject: CAS - MPG Partner Institute in the field of Computational and Theoretical Biology Message-ID: The Chinese Academy of Sciences (CAS) and the Max-Planck-Gesellschaft (MPG) intend to establish a CAS - MPG PARTNER INSTITUTE IN THE FIELD OF COMPUTATIONAL AND THEORETICAL BIOLOGY Applications are invited for the positions of up to three full-time department directors. Legally and administratively the Partner Institute will be an institute of the CAS, located on the CAS Campus of the Shanghai Institutes for Biological Sciences (SIBS). The aim of this interdisciplinary and theoretically oriented Institute is to account for the increasing involvement of mathematical, computer-science and engineering methods in modern biology and to allow for novel approaches of research at the interfaces between disciplines (e.g. bioinformatics, computational biology, systems biology, computation biophysics, theoretical neurobiology or evolutionary biology). The proximity to experimentally oriented, internationally competitive research institutes on the SIBS campus guarantees close scientific cooperation and interaction between theoretical and experimental research. Strong collaboration with one or more Max Planck Institutes in Germany is expected from the directors and will be expressively documented and fostered by appointing them as External Scientific Members of MPG. To aid the final definition of promising reseach areas and the identification of suitable candidates, the Chinese Academy of Sciences and the Max-Planck-Gesellschaft will jointly organize a Symposium on Perspectives in Computational and Theoretical Biology which will be held in Shanghai on December 19 - 20, 2004. We invite applications from scientists with an outstanding international research record who are willing to take full advantage of the unique challenge to build up a new, interdisciplinary and theoretical/computational institute by cooperating with the experimental institutes on the SIBS campus and in association with a Max Planck Institute in Germany. The recruitment and appointment procedure for the director positions will be carried out jointly by CAS and MPG. The positions will offer full scientific and economic independence equivalent to that of a director/head of department at a Max Planck Institute. The initial appointment will be for five years and can be extended after review by the Institute's internationally composed Scientific Advisory Board. Qualified candidates should submit a curriculum vitae, a short statement of research interests and scientific goals, reprints of key publications and the topic (or abstract) of the intended presentation at the symposium. To ensure full consideration, please submit a hard copy of your application before October 31, 2004 to CHEN Zhu (Vice President of CAS) Chinese Adademy of Sciences 52 Sanlihe Road Beijing 100864 P.R. China and PDF-files of your application to the contact persons in Munich and Shanghai: E-mail: spielmann at gv.mpg.de Barbara SPIELMANN Max-Planck-Gesellschaft Hofgartenstrasse 8 D ? 80539 M?nchen Germany Tel.: +49-89-2108 1365 Fax: +49-89-2108 1041 E-mail: yyyang at sibs.ac.cn YANG Yanyun Shanghai Institutes for Biological Sciences Chinese Academy of Sciences 319 Yue Yang Road Shanghai 200031, P. R. China Tel: +86?21-5492 0965 Fax: +86?21-5492 0968 From bogus@does.not.exist.com Wed Oct 13 11:10:11 2004 From: bogus@does.not.exist.com () Date: Wed, 13 Oct 2004 10:10:11 -0500 Subject: postdoctoral position Message-ID: From bower at uthscsa.edu Thu Oct 14 20:03:17 2004 From: bower at uthscsa.edu (Jim Bower) Date: Thu, 14 Oct 2004 19:03:17 -0500 Subject: WAM-BAMM*05 in San Antonio Message-ID: ----------------------------------------------------------------------------- Announcing the World Association of Modelers (WAM) First Annual Biologically Accurate Modeling Meeting (BAMM) WAM-BAMM*05 In Association with the Second GENESIS USERS MEETING GUM*05 March 31st - April 2nd In beautiful San Antonio Texas http://www.WAM-BAMM.org Meeting objective: To bring together modelers and experimentalists using Realistic Modeling techniques to better understand biological systems. Subjects considered: Modeling techniques, simulator design, modeling results, modeling inspired biological experimentation, and world modeling community coordination. Meeting Structure: Thursday March 31st will be devoted to a series of tutorials and round table discussions on Biological modeling. Tutorials will be offered by leading experts in realistic modeling and the interaction between modeling and experimental biology. Friday and Saturday will be devoted to oral and poster presentations by meeting participants and invited speakers. Important Dates: --------------- Meeting pre-registration: Via the WAM-BAMM web site: www.wam-bamm.org, assures you receive future meeting mailings. Deadline for proposing tutorials: December 1, 2004 Give a tutorial on techniques of biologically realistic modeling at WAM-BAMM. Send a brief description of the proposed tutorial to wambamm05 at wam-bamm.org. Authors of accepted tutorial presentations will be provided free meeting registration. Deadline for proposed research presentations: December 15, 2004 Submission form is available on the WAM-BAMM web site: www.wam-bamm.org Student registration deadline for travel grants: February 1, 2005 Funding is available for student travel grants. (see web site). Deadline for early registration: February 15, 2005 Advanced registration $ 99 for graduate students, $ 149 for all others (30% increase after deadline) Deadline for guaranteed housing at the conference rate: March 1, 2005 The meeting will be held at the historic Menger Hotel in Downtown San Antonio, next to the Alamo and the famous San Antonio River Walk. Room rates $109 (single or double), $ 119 (3-4). Arrival date for the meeting: March 30th, 2005 The famous WAM-BAM Banquet, Rodeo, and Blue Bonnet Festival: Saturday, April 2, 2005 Depart from San Antonio: April 3, 2005 More information on WAM-BAM can be found at www.wam-bamm.org, or by contacting us at wam-bamm at wam-bamm.org. From ecuadros at spc.org.pe Thu Oct 21 12:13:35 2004 From: ecuadros at spc.org.pe (Ernesto Cuadros-Vargas) Date: Thu, 21 Oct 2004 11:13:35 -0500 Subject: CFP IJCNN05 Special Session "Constructive/Hierarchical Self-Organizing Maps" Message-ID: <447901c4b789$d18da4e0$a1c279c8@characato> Call for Papers for a Special Session "Constructive/Hierarchical Self-Organizing Maps" International Joint INNS-IEEE Conference on Neural Networks (IJCNN) 2005 Hilton Bonaventure Hotel, Montreal, Quebec, Canada July 31- August 4, 2005, IJCNN 2005, (http://faculty.uwb.edu/ijcnn05) The aims of this session is to bring together researchers working on novel constructive models based on Self-Organizing Maps (SOM). This area brings together knowledge from Hierarchical Information Retrieval, Access Methods such as Spatial and Metric Access Methods, Constructive Techniques, etc. Topics include but are not restricted to: * Hierarchical SOM * Constructive SOM * Self-evolving architectures * Evolving and Evolutionary Self-Organizing Maps, * Incorporating Access Methods on Self-Orgainzing Maps * Techniques to find an appropriate SOM architecture * Similarity Information Retrieval * Bayesian Approaches Organizers: Prof. Dr. Ernesto Cuadros-Vargas - ecuadros at spc.org.pe Peruvian Computer Society, Peru and Prof. Dra. Roseli Ap. Francelin Romero - rafrance at icmc.usp.br University of Sao Paulo, Brazil Submissions and deadlines: 26 October 2004: An abstract (1 page) should be sent electronically to the organizers 15 December 2004: A full paper (see the IJCNN'05 instructions for submissions) sent to the organizers. 5 January 2005: Reviews and a notification of acceptance/rejection sent to the authors. 31 January 2005: Final paper submitted to the special session electronically (IJCNN'05 portal) All accepted papers will be published in the IJCNN 2005 Proceedings. Papers not accepted for the special session can be submitted as regular submissions for IJCNN'05 (the deadline is also January 31, 2005). Authors will be invited to submit extended versions of their papers to a special issue of an international journal. Each paper must have the title, authors with e-mails/web sites, and a detailed abstract as possible. All accepted papers must be presented at the conference. *************************************************************** Prof. Dr. Ernesto Cuadros-Vargas Peruvian Computer Society ecuadros at spc.org.pe http://socios.spc.org.pe/ecuadros Phone: +51-54-400416 (home) or +51-54-934-1932 (cellular) *************************************************************** From swells at hrl.com Thu Oct 21 12:19:41 2004 From: swells at hrl.com (Sheryl Wells) Date: Thu, 21 Oct 2004 09:19:41 -0700 Subject: research position at HRL Laboratories Message-ID: <4177E19D.3040605@hrl.com> A non-text attachment was scrubbed... Name: not available Type: multipart/mixed Size: 1426 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/00000000/4c31eb5d/attachment.bin From p.husbands at sussex.ac.uk Thu Oct 21 09:54:09 2004 From: p.husbands at sussex.ac.uk (Phil Husbands) Date: Thu, 21 Oct 2004 14:54:09 +0100 Subject: post-doc position neuronal modelling/interfacing Message-ID: <16133484.1098370449@philh-home-pc.crn.cogs.susx.ac.uk> Post-doctoral position, University of Sussex Non-linear media computing A three year post is available (to start ASAP) to work on an exciting project on non-linear media computing in The Centre for Computational Neuroscience and Robotics, University of Sussex (www.informatics.sussex.ac.uk/ccnr/ ). Suitable for a talented researcher with experience in one or more of the following areas: computational neuroscience, machine learning, evolutionary computing, neuron/silicon interfacing. Good computational skills are required, ability in mathematics and electronics is desirable. This post is part of a multidisciplinary project, in collaboration with the University of West of England and Leeds University, in which computer scientists, neuroscientists, chemists, cell biologists and engineers will study information processing in chemical and (biological) neuronal non-linear media in order to try and determine fundamental principles for the design of novel non-linear media computers and to abstract novel computational mechanisms. The post-doc will be involved in computational and mathematical modelling, particularly of NO volume signalling, and investigating the efficacy of evolutionary algorithms for designing cultured neuronal network structures to create a computing resource capable of satisfying a given objective. The successful applicant will work very closely with a neuroscience post-doc as part of a team led by Profs. Phil Husbands and Michael O?Shea. Applicants should email a full CV to Phil Husbands (philh at sussex.ac.uk) by November 15th 2004. The project is funded by EPSRC. Starting salary approx. ?27,000 depending on experience. From larryy at apple.com Fri Oct 22 11:59:11 2004 From: larryy at apple.com (Larry Yaeger) Date: Fri, 22 Oct 2004 10:59:11 -0500 Subject: Robotics/Cognitive Science faculty positions at IU Message-ID: Indiana University, Bloomington, IN. Two faculty positions beginning August 2005. As part of a series of new appointments, the Cognitive Science Program at Indiana University seeks one senior and one junior level appointment in the general area of intersection of cognitive science and robotics. Senior applicants should have a strong record of research and teaching, a desire to take a leadership position, and a record supporting such a position. Applicants for the junior level position should have a record that demonstrates an excellent potential in the areas of research and teaching. Applicant's areas of expertise may but do not have to include biomorphic robotics, evolutionary robotics, artificial life, and embodied cognition. Successful applicants will take a leadership role in the planning and execution of a new, state-of-the-art laboratory for teaching and research. Applicants should send full dossiers, including letters of recommendation or names and addresses of referees. Indiana University is an equal opportunity/affirmative action employer. Applications from women and minority group members are especially encouraged. Please send materials to Professor Richard Shiffrin, Search Committee, Cognitive Science Program, 1033 E. Third St., Sycamore 0014, Bloomington, IN 47405. Applications received by December 1, 2004 are assured full consideration. Please see our website: http://www.cogs.indiana.edu for information regarding additional open faculty positions. From marc-oliver.gewaltig at honda-ri.de Fri Oct 22 07:56:22 2004 From: marc-oliver.gewaltig at honda-ri.de (Marc-Oliver Gewaltig) Date: Fri, 22 Oct 2004 13:56:22 +0200 Subject: Release of the Neural Simulation Tool NEST 1.0 Message-ID: <200410221356.22491.marc-oliver.gewaltig@honda-ri.de> October 22 2004 The NEST Initiative is pleased to announce the release of the neural simulation tool NEST. * NEST is designed specifically for the simulation of large networks of biologically realistic point-neurons (10^4-10^5 neurons), and provides extensive support for hierarchically structured networks. * NEST is both flexible and efficient, and supports parallel simulation on multi-processor computers. * NEST has been tested on a range of Unix varieties, including Linux, Mac OS X, Solaris and Tru64 Unix. Windows is supported via the Cygwin environment. * NEST can be downloaded under an open source license from the NEST Initiative website http://www.nest-initiative.org On that website, you will find more information about NEST, the NEST Initiative, and mailing lists around NEST. -- Dr. Marc-Oliver Gewaltig ------------------------------------ Honda Research Institute Europe GmbH Carl-Legien-Str. 30 D-63073 Offenbach/Main, Germany http://www.honda-ri.de From skoenig at usc.edu Tue Oct 26 21:12:04 2004 From: skoenig at usc.edu (Sven Koenig) Date: Tue, 26 Oct 2004 18:12:04 -0700 (PDT) Subject: CFP: JMLR Special Issue on "Learning in Large Probabilistic Environments" Message-ID: CALL FOR PAPERS Journal of Machine Learning Research Special Issue on Learning in Large Probabilistic Environments Guest Editors Sven Koenig, Shie Mannor and Georgios Theocharous http://www.jmlr.org/cfp/llpe.html We invite papers on learning in large probabilistic environments for a special issue of the Journal of Machine Learning Research (JMLR). One of the fundamental problems of artificial Intelligence is how to enable systems (for example, mobile robots, manufacturing systems, or diagnostic systems) embedded in complex environments to achieve their long-term goals efficiently. A natural approach is to model such systems as agents that interact with their environment through actions, perceptions and rewards. These agents choose actions after every observation, aiming to maximize their long-term reward. Learning allows them to improve their initial strategy based on the history of successful and unsuccessful interactions with the environment. This special issue is intended to serve as an outlet for recent advances in learning in such environments, often called reinforcement learning. We welcome both theoretical advances in this field as well as detailed reports on applications of learning in large probabilistic domains. Topics of interest include: * Theoretical foundations of learning in large probabilistic environments. * Completely and partially observable Markov decision process models (MDPs) and similar models. Learning with factored state or action spaces, continuous state spaces, action spaces or time models, hybrid models, relational learning, concurrency. * Heuristics and approximations. Policy and value function approximations, Monte Carlo and advanced simulation methods. * Spatio-temporal abstractions. Dynamic factorization, hierarchy and relational structure. * Interactive learning. Guided exploration, combining supervised and unsupervised learning, shaping, and learning from very few examples. * Learning in complex systems. Function approximation, dimensionality reduction, feature selection for learning, and alternative state representations. * Cooperative and competitive multi-agent reinforcement learning. Learning in nonstationary domains and stochastic, network, and dynamic games. * Real world applications. Medicine, finance, robotics, manufacturing, security, etc. Submission procedure: Submit papers to the standard JMLR submission system http://jmlr.csail.mit.edu/manudb Please include a note stating that your submission is for the special issue on Learning in Large Probabilistic Environments. Important Dates: * Submission due: April 15th, 2005 * Decision: August 1st, 2005 * Final version due: October 1st, 2005 For further details or enquiries, please contact the guest editors: Sven Koenig (skoenig at usc.edu) Shie Mannor (shie at ece.mcgill.ca) Georgios Theocharous (georgios.theocharous at intel.com) From rmeir at ee.technion.ac.il Tue Oct 26 16:41:57 2004 From: rmeir at ee.technion.ac.il (Ron Meir) Date: Tue, 26 Oct 2004 22:41:57 +0200 Subject: CALL FOR PAPERS - COLT 2005 Message-ID: <009301c4bb9c$6ebbcbf0$0300a8c0@ron1> [Apologies to multiple recipients of this announcement ] CALL FOR PAPERS The Eighteenth Annual Conference on Learning Theory Bertinoro, Italy, June 27-30, 2005 http://learningtheory.org/colt2005 The Eighteenth Annual COLT (Conference on Learning Theory, formerly Workshop on Computational Learning Theory) will be held in Bertinoro, Italy, June 27-30, 2005 We invite submissions of papers addressing the theoretical modeling and analysis of all aspects of learning and empirical inference. We strongly support a broad definition of learning theory, including: * Analysis of learning algorithms and their generalization ability * Computational complexity of learning * Bayesian analysis * Statistical mechanics of learning systems * Optimization procedures for learning * Inductive inference * Boolean function learning * Inductive logic programming * Unsupervised and semi-supervised learning * On-line learning and relative loss bounds * Learning in planning and control (including reinforcement learning) * Mathematical analysis of learning in related fields (e.g. game theory, neuroscience) We welcome theoretical papers about learning that do not fit into the above categories. We are particularly interested in papers that include viewpoints that are new to the COLT community. While the primary focus of the conference is theoretical, papers can be strengthened by the inclusion of relevant experimental results. We also welcome experimental and algorithmic papers provided they are relevant to the focus of the conference by elucidating theoretical results in learning. All papers will appear in the proceedings, to be published in the Springer Lecture Notes in Artificial Intelligence series. The proceedings will appear both as a printed book and in a full-text electronic version, thus we require electronic submissions. Papers that have previously appeared in journals or at other conferences, or that are being submitted to other conferences are not appropriate for COLT. PAPER FORMAT: Submissions should include the title, authors' names, postal and email addresses, and a 200-word summary of the paper suitable for the conference program. They should be no longer than 15 pages using the Springer LNCS style file (see http://www.springer.de/comp/lncs/authors.html). Your paper should include a clear definition of the theoretical model used and a clear description of the results, as well as a discussion of their significance, including comparison to other work. Submit papers electronically in pdf or ps format (for details see conference website). While it is not expected that all full proofs can be included in the paper, authors should strive to at least present partial proofs which will enable the reviewers to understand the main ideas and methods used. The paper should also attempt to be as self-contained as possible. OPEN PROBLEMS SESSION: We also invite submission of open problems (see separate call). These should be constrained to two pages using the same formatting as for the full papers. There is a shorter reviewing period for the open problems. Accepted contributions will be allocated short presentation slots in a special open problems session and will be allowed two pages each in the proceedings. ELECTRONIC SUBMISSION INSTRUCTIONS: Will become available in early December at http://learningtheory.org/colt2005 PROGRAM CO-CHAIRS: Peter Auer (U of Leoben) and Ron Meir (Technion) PROGRAM COMMITTEE: Shai Ben-David (Waterloo), Avrim Blum (Carnegie Mellon), Peter Bartlett (Berkeley), Nader Bshouty (Technion), Ran El-Yaniv (Technion), Yoav Freund (Columbia), Ralf Herbrich (Microsoft), Marcus Hutter (IDSIA), Tony Jebara (Columbia), Vladimir Koltchinskii (New Mexico), Phil Long (Columbia), Gabor Lugosi (Barcelona), Shie Mannor (McGill), Shahar Mendelson (ANU), Massimiliano Pontil (University College), Daniel Reidenbach (U Kaiserslautern), Dan Roth (U Illinois Urbana-Champaign), Michael Schmitt (Ruhr University Bochum), Rocco Servedio (Columbia), Hans Ulrich Simon (Ruhr University Bochum), Volodya Vovk (Royal Holloway), Manfred Warmuth (UC Santa Cruz), Tong Zhang (IBM) CONFERENCE AND LOCAL ARRANGEMENTS CHAIRS: Nicolo Cesa Bianchi (Universita di Milano) and Claudio Gentile (Universita dell?Insubria) OPEN PROBLEMS CO-CHAIRS: Adam Klivans (Toyota Institute) and Rocco Servedio (Columbia) MARK FULK AWARD: This awards is for the best paper authored or coauthored by a student. Eligible authors who wish to be considered for this prize should indicate this on their submission's title page. INVITED SPEAKERS: Sergiu Hart (Hebrew University), Wulfram Gerstner (EPFL), Satinder Singh (Michigan) From bogus@does.not.exist.com Mon Oct 25 15:21:26 2004 From: bogus@does.not.exist.com () Date: Mon, 25 Oct 2004 20:21:26 +0100 Subject: PhD Studentship Message-ID: <51D8DD363F91404B8DE8C73D7601869DBA5C7B@ccexchange-2.cns.cranfield.ac.uk> From dgw at MIT.EDU Thu Oct 28 13:41:27 2004 From: dgw at MIT.EDU (David Weininger) Date: Thu, 28 Oct 2004 13:41:27 -0400 Subject: book announcement--Alpaydin Message-ID: <2004102813412723682@outgoing.mit.edu> I thought readers of the Connectionists List might be interested in this book. For more information, please visit http://mitpress.mit.edu/0262012111/ Thank you! Best, David Introduction to Machine Learning Ethem Alpaydin The goal of machine learning is to program computers to use example data or past experience to solve a given problem. Many successful applications of machine learning exist already, including systems that analyze past sales data to predict customer behavior, recognize faces or spoken speech, optimize robot behavior so that a task can be completed using minimum resources, and extract knowledge from bioinformatics data. Introduction to Machine Learning is a comprehensive textbook on the subject, covering a broad array of topics not usually included in introductory machine learning texts. It discusses many methods based in different fields, including statistics, pattern recognition, neural networks, artificial intelligence, signal processing, control, and data mining, in order to present a unified treatment of machine learning problems and solutions. All learning algorithms are explained so that the student can easily move from the equations in the book to a computer program. The book can be used by advanced undergraduates and graduate students who have completed courses in computer programming, probability, calculus, and linear algebra. It will also be of interest to engineers in the field who are concerned with the application of machine learning methods. After an introduction that defines machine learning and gives examples of machine learning applications, the book covers supervised learning, Bayesian decision theory, parametric methods, multivariate methods, dimensionality reduction, clustering, nonparametric methods, decision trees, linear discrimination, multilayer perceptrons, local models, hidden Markov models, assessing and comparing classification algorithms, combining multiple learners, and reinforcement learning. Detailed table of contents available at http://www.cmpe.boun.edu.tr/~ethem/i2ml/ Ethem Alpaydin is Professor in the Department of Computer Engineering at Bogazi?i University, Istanbul October 2004, 7 x 9, 400 pp., 135 illus., cloth, ISBN 0-262-01211-1 Adaptive Computation and Machine Learning series ______________________ David Weininger Associate Publicist The MIT Press 5 Cambridge Center, 4th Floor Cambridge, MA 02142 617 253 2079 617 253 1709 fax http://mitpress.mit.edu From gerhard.widmer at jku.at Wed Oct 13 05:20:07 2004 From: gerhard.widmer at jku.at (Gerhard Widmer) Date: Wed, 13 Oct 2004 11:20:07 +0200 Subject: [Mlnet] Open University Position in Austria Message-ID: <416CF347.2060505@jku.at> OPEN POSITION AT THE JOHANNES KEPLER UNIVERSITY LINZ, AUSTRIA: ASSISTANT PROFESSOR (LECTURER) AT THE POST-DOCTORAL LEVEL The newly founded DEPARTMENT OF COMPUTATIONAL PERCEPTION at the Johannes Kepler University Linz, Austria, headed by Prof. Gerhard Widmer, has an open position for a Full-time Assistant Professor ("Universit?tsassistent") at the post-doctoral level, with a contract limited to 4-6 years. REQUIREMENTS: - a doctorate in computer science or a related field - research experience in one or several of the following areas: Artificial/Computational Intelligence, Machine Learning, Sensor Data Interpretation and Signal Analysis, Intelligent Audio/Music/Video/Image Processing, Intelligente Data Analysis, Time Series Processing, Pattern Recognition. The candidate is expected to build up his/her own research program, to be active in the acquisition of research funding, and to contribute to the department's teaching and administration. LANGUAGE: Fluency in German is not a prerequisite, though a passive command of the German language would be beneficial. Excellent English is required. Teaching can be done in English for the first one or two years. MORE INFORMATION: Prof. Gerhard Widmer Tel.: +43 - 732 - 2468 1510 e-mail: gerhard.widmer at jku.at WWW: www.oefai.at/~gerhard For some of our recent research in the area of machine learning and intelligent music processing see http://www.oefai.at/~gerhard or http://www.ai.univie.ac.at/oefai/ml/ Women are particularly encouraged to apply and will be given priority in case of equal qualification. The OFFICIAL ANNOUNCEMENT (in German) can be found at http://www.cp.jku.at/stellenausschreibung.html . DEADLINE FOR APPLICATION: October 27, 2004 Please send your application with relevant documents (CV, picture, publications list / sample publications, copies of academic documents) to: Personalabteilung der Zentralen Dienste der Universit?t Linz A-4040 Linz/Auhof AUSTRIA and make sure to refer to "Anzeigennummer 1148" (ID of this announcement) in your cover letter. The application can be written in English, of course. ***************************************************************** Gerhard Widmer Department of Computational Perception Tel: +43 732 2468 1510 Johannes Kepler University Linz Altenberger Strasse 69 gerhard.widmer at jku.at A-4040 Linz, Austria http://www.cp.jku.at ***************************************************************** _______________________________________________ Mlnet mailing list Mlnet at ais.fraunhofer.de http://lists.ais.fraunhofer.de/mailman/listinfo/mlnet From harnad at ecs.soton.ac.uk Fri Oct 1 12:06:11 2004 From: harnad at ecs.soton.ac.uk (Stevan Harnad) Date: Fri, 1 Oct 2004 17:06:11 +0100 (BST) Subject: Open access questionnaire: Call for respondents (fwd) Message-ID: *Apologies for cross-posting* ---------- Forwarded message ---------- From a.swan at talk21.com Fri Oct 1 11:56:10 2004 From: a.swan at talk21.com (Alma Swan) Date: Fri, 1 Oct 2004 16:56:10 +0100 Subject: Open access questionnaire: Call for respondents Message-ID: Dear Colleague, Open access to scholarly journal articles is a topic of growing importance. Open access enables free and immediate electronic access to a scholar's work. Studies show that open access increases the impact of - and number of citations to - work made accessible in this way. We are interested in understanding scholars' views on open access publishing and self-archiving and would very much like to hear your opinions. Please would you help by completing the questionnaire at http://www.keyperspectives.co.uk/OA/sarchiv.htm. It will be used to inform universities, research funders and scholars themselves of the state of play and how open access is progressing. Naturally, all responses will be treated as confidential and you may opt to remain anonymous if you wish. Thank you in advance for your cooperation. We do value your input and advice. Yours sincerely, Alma Swan, PhD Key Perspectives Ltd Truro United Kingdom From r.kempter at biologie.hu-berlin.de Fri Oct 1 08:31:21 2004 From: r.kempter at biologie.hu-berlin.de (Richard Kempter) Date: Fri, 1 Oct 2004 14:31:21 +0200 Subject: FINAL CALL: Berlin Autumn School LEARNING AND MEMORY, Oct 11-13, 2004. Message-ID: <20041001123121.GA28347@pauling.biologie.hu-berlin.de> Announcement, program, and final call for participation: Berlin Autumn School LEARNING AND MEMORY: MOLECULAR MECHANISMS - CELLULAR PROCESSES - MATHEMATICAL MODELS October 11-13, 2004 Berlin, Germany Learning and memory are central ingredients for proper biological function in changing environments. Both processes are of particular importance for neuroscience but they also play a significant role in other biological disciplines. This autumn school focuses on the basic molecular and cellular processes underlying learning and memory in neural systems, with emphasis on synaptic plasticity. Experimental approaches will be discussed in close relation with the corresponding mathematical models, both at an introductory level. The last day of the school will bridge between the physiological and behavioral level and also touch on learning and memory in the immune system. REGISTRATION: E-mail to Richard Kempter before October 4 r.kempter at biologie.hu-berlin.de PROGRAM Monday, October 11: 8:30 - 9:00 Arrival 9.00 - 9:15 Opening of the Autumn School 9.15 - 10.45 Dietmar Schmitz (NWFZ, Charite) Cellular processes of learning and memory: Development & current state of concepts and experiments (I) 11.15 - 12.45 Andreas Herz (ITB, HU Berlin) Modelling short-term synaptic plasticity with differential equations and iterated maps (I) 15.15 - 16.45 Dietmar Kuhl (Neurobiology, FU Berlin) Molecular and cellular mechanisms of learning and memory (I) 17.15 - 18.45 Hanspeter Herzel (ITB, Charite) Modelling molecular signal transduction chains and networks 19.00 - Reception and Dinner Tuesday, October 12: 9.15 - 10.45 Dietmar Schmitz (NWFZ, Charite) Cellular processes of learning and memory: Development & current state of concepts and experiments (II) 11.15 - 12.45 Andreas Herz (ITB, HU Berlin) Modelling short-term synaptic plasticity with differential equations and iterated maps (II) 15.15 - 16.45 Dietmar Kuhl (Neurobiology, FU Berlin) Molecular and cellular mechanisms of learning and memory (II) 17.15 - 18.45 Laurenz Wiskott (ITB, HU Berlin) Modelling learning and memory: The systems level Wednesday, October 13: 9.15 - 10.15 Dietmar Schmitz (NWFZ, Charite) Short- and long-term plasticity of the mossy fiber synapse 10.15 - 11.15 Richard Kempter (ITB, HU Berlin) Hippocampal plasticity: Learning behavioral sequences 11.45 - 12.45 Andreas Radbruch (DRFZ, Berlin) Memory in the immune system 15.15 - 16.15 Gerd Kempermann (Max Delbrueck Center, Berlin) Adult neurogenesis 16.15 - 17.15 Livia de Hoz (Neurophysiology, Charite) Memory consolidation 17.45 - 19.15 Andreas Herz (ITB, HU Berlin) The Hebbian memory trace: New insight from bee olfaction LOCATION: Lecture Hall 12, Department of Biology, Humboldt-Universitaet zu Berlin, Invalidenstrasse 43, 10115 Berlin-Mitte. REGISTRATION: E-mail to Richard Kempter before October 4: r.kempter at biologie.hu-berlin.de The registration fee of 30 Euro (students 15 Euro) is to be paid upon arrival and includes the buffet on Monday (Oct 11) evening. For details, please visit: http://itb.biologie.hu-berlin.de/events/memory.html PDF poster of this announcement: http://itb.biologie.hu-berlin.de/~kempter/berlin_autumn_school/learning_and_memory_2004.pdf -- The autumn school on "Learning and Memory" is organized by the DFG Collaborative Research Center ("Sonderforschungsbereich", SFB 618) "Theoretical Biology: Robustness, Modularity, and Evolutionary Design of Living Systems" Humboldt-Universitaet zu Berlin Department of Biology Invalidenstrasse 43 10115 Berlin, Germany http://www.biologie.hu-berlin.de/forschung/SFB_618/ From Gunnar.Raetsch at tuebingen.mpg.de Mon Oct 4 15:58:54 2004 From: Gunnar.Raetsch at tuebingen.mpg.de (Gunnar Raetsch) Date: Mon, 4 Oct 2004 21:58:54 +0200 Subject: Two Books: Advanced Lectures on Machine Learning Message-ID: Dear Connectionists, I would like to announce two recent books: Advanced Lectures on Machine Learning Tutorial Lectures from the Machine Learning Summer Schools (http://mlss.cc) in Canberra (Australia), Tuebingen (Germany) & Berder (France) published by Springer Verlag as LNAI 3176 (O. Bousquet, U. von Luxburg, G. Raetsch, Eds) http://www.springerlink.com/link.asp?id=lrh41y849xdh LNAI 2600 (S. Mendelson & A.J. Smola, Eds) http://www.springerlink.com/link.asp?id=4brrn87rrdpn Please find the tables of contents below. Best regards, Gunnar LNAI 3176 (O. Bousquet, U. von Luxburg, G. Raetsch, Eds) http://www.springerlink.com/link.asp?id=lrh41y849xdh -------------------------------------------------------- * An Introduction to Pattern Classification (Elad Yom-Tov) * Some Notes on Applied Mathematics for Machine Learning (Christopher J.C. Burges) * Bayesian Inference: An Introduction to Principles and Practice in Machine Learning (Michael E. Tipping) * Gaussian Processes in Machine Learning (Carl Edward Rasmussen) * Unsupervised Learning (Zoubin Ghahramani) * Monte Carlo Methods for Absolute Beginners (Christophe Andrieu) * Stochastic Learning (L?on Bottou) * Introduction to Statistical Learning Theory (Olivier Bousquet, St?phane Boucheron and G?bor Lugosi) * Concentration Inequalities (St?phane Boucheron, G?bor Lugosi and Olivier Bousquet) LNAI 2600 (S. Mendelson & A.J. Smola, Eds) http://www.springerlink.com/link.asp?id=4brrn87rrdpn -------------------------------------------------------- * A Few Notes on Statistical Learning Theory (Shahar Mendelson) * A Short Introduction to Learning with Kernels (Bernhard Sch?lkopf and Alexander J. Smola) * Bayesian Kernel Methods (Alexander J. Smola and Bernhard Sch?lkopf) * An Introduction to Boosting and Leveraging (Ron Meir and Gunnar R?tsch) * An Introduction to Reinforcement Learning Theory: Value Function Methods (Peter L. Bartlett) * Learning Comprehensible Theories from Structured Data (J.W. Lloyd) * Algorithms for Association Rules (Markus Hegland) * Online Learning of Linear Classifiers (Jyrki Kivinen) +-----------------------------------------------------------------+ Gunnar R"atsch http://www.tuebingen.mpg.de/~raetsch MPI for Biological Cybernetics Gunnar.Raetsch at tuebingen.mpg.de Spemannstr. 38 Tel: (+49) 7071 601 563 72076 T"ubingen, Germany Fax: (+49) 7071 601 552 +-----------------------------------------------------------------+ Gunnar R"atsch http://www.first.fhg.de/~raetsch Fraunhofer FIRST mailto:Gunnar.Raetsch at first.fhg.de Kekulestr. 7 Tel: (+49) 30 6392 1882 12489 Berlin, Germany Fax: (+49) 30 6392 1805 From rsun at rpi.edu Mon Oct 4 12:27:02 2004 From: rsun at rpi.edu (Professor Ron Sun) Date: Mon, 04 Oct 2004 12:27:02 -0400 Subject: Cognitive Science Ph.D program at RPI Message-ID: <416179D6.70702@rpi.edu> I am looking for a few Ph.D students. The Ph.D program of the Cognitive Science department at RPI is accepting applications. Graduate assistantships and other forms of financial support for graduate students are available. Prospective graduate students with interests in Cognitive Science, especially in learning and skill acquisition and in the relationship between cognition and sociality, are encouraged to apply. Prospective applicants should have background in computer science (the equivalent of a BS in computer science), and have some prior exposure to psychology, artificial intelligence, connectionist models (neural networks), multi-agent systems, and other related areas. Students with a Master's degree already completed are preferred. RPI is a top-tier research university. This new CogSci department has identified the Ph.D program and research as its primary missions. The department is conducting research in a number of areas: cognitive modeling, human and machine learning, multi-agent interactions and social simulation, neural networks and connectionist models, human and machine reasoning, cognitive engineering, and so on. See the Web page below regarding my research: http://www.cogsci.rpi.edu/~rsun For the application procedure, see http://www.cogsci.rpi.edu/ The application deadline is Jan.15, 2005. If you decide to apply, follow the official procedure as outlined on the Web page. Send me a short email (in plain text, ASCII) AFTER you have completed the application. -- =================================================================== Professor Ron Sun Cognitive Science Department Rensselaer Polytechnic Institute 110 Eighth Street, Carnegie 302A Troy, NY 12180, USA phone: 518-276-3409 fax: 518-276-3017 email: rsun at rpi.edu web: http://www.cogsci.rpi.edu/~rsun =================================================================== From ptodd at mpib-berlin.mpg.de Tue Oct 5 14:51:09 2004 From: ptodd at mpib-berlin.mpg.de (Peter M. Todd) Date: Tue, 05 Oct 2004 20:51:09 +0200 Subject: special issue of Adaptive Behavior on CTRNN cognitive modeling now freely available Message-ID: <4162ED1D.6090902@mpib-berlin.mpg.de> Dear colleagues, the journal Adaptive Behavior, covering models of behavior in animals and artificial agents, is now available in a new electronic form (including extensive cross-referencing) from the publisher, Sage, at http://adb.sagepub.com/archive/ Until the end of October, full-text access to current and past volumes (back to vol. 9) of Adaptive Behavior is available *free of charge*, so please take this opportunity to check out the recent contents. Of particular interest to connectionists will be the special issue 11:4, centering on a target article by Randall Beer, "*The Dynamics of Active Categorical Perception in an Evolved Model Agent", *along with accompanying commentaries by a number of authors discussing what we can learn about cognition by studying continuous-time recurrent neural networks. best wishes, Peter Todd Editor-in-Chief, Adaptive Behavior -- .............................................................. ' `. : Dr. Peter M. Todd : : Max Planck Institute for Human Development : : Center for Adaptive Behavior and Cognition : : Lentzeallee 94 : : 14195 Berlin GERMANY : : : : Editor-in-Chief, Adaptive Behavior : : Journal WWW: http://www.adaptive-behavior.org : : : : Email: ptodd at mpib-berlin.mpg.de : : WWW: http://www-abc.mpib-berlin.mpg.de/users/ptodd : : Phone: (+49) (30) 824 06 347 or 824 06 430 (secretary) : : Fax: (+49) (30) 824 06 394 or 824 99 39 : : : `..............................................................' From maass at igi.tu-graz.ac.at Tue Oct 5 12:37:21 2004 From: maass at igi.tu-graz.ac.at (Wolfgang Maass) Date: Tue, 05 Oct 2004 18:37:21 +0200 Subject: position for Phd student Message-ID: <4162CDC1.3030806@igi.tu-graz.ac.at> A position for a Phd-student is available in our research group on Neural Computation/Computational Neuroscience with emphasis on SOFTWARE FOR SIMULATIONS OF LARGER NEURAL SYSTEMS. The student is expected to have experience in software design (especially Linux, C++, Matlab, distributed computing), interest in creating software for distributed simulations of larger neural systems (especially visual areas), and in exploring computational properties and learning capabilities of neural systems. The student will spend about half of his/her time on research, and the other half on programming and software maintainance. No teaching is required. See http://www.lsm.tugraz.at/ for a software system that has previously been developed at our institute. Relevant courses and seminars for Phd-students are carried out in English, leading to a Phd in Computer Science. Applications should be sent to Wolfgang Maass maass at igi.tugraz.at -- Wolfgang Maass Professor of Computer Science Technische Universitaet Graz http://www.igi.tugraz.at/maass/ From cindy at bu.edu Wed Oct 6 10:51:14 2004 From: cindy at bu.edu (Cynthia Bradford) Date: Wed, 6 Oct 2004 10:51:14 -0400 Subject: three postdoctoral positions at Boston University Message-ID: <093101c4abb3$edb22fb0$903dc580@cnspc31> THREE POSTDOCTORAL FELLOWS DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS BOSTON UNIVERSITY Three postdoctoral fellows are sought to join the Boston University Department of Cognitive and Neural Systems as part of a major new NSF Science of Learning Center called CELEST (Center of Excellence for Learning in Education, Science, and Technology; Stephen Grossberg, PI; http://www.cns.bu.edu/CELEST). All three fellowships are available immediately for a minimum commitment of two years. Each fellow should have significant graduate training and published research in behavioral and brain modeling using neural networks, or in neuromorphic modeling in technology. One fellow will carry out basic research in developing biological neural networks in one or more CELEST research areas, in addition to working with CELEST colleagues to develop large-scale system models of brain and behavior. The other two postdoctoral fellows would combine basic research in behavioral and brain modeling and/or neuromorphic technology with education projects aimed at bringing current modeling knowledge about how the brain works into educational curricula at multiple levels. One fellow will work primarily with web-based materials, the other with printed materials. These postdocs would also interact with CELEST members to develop these educational resources. CELEST offers a wide range of excellent opportunities for broadening knowledge of neural modeling and experimentation, technological applications, and educational technology and outreach. Boston University is an Equal Opportunity/Affirmative Action Employer. Please send a curriculum vitae, 3 letters of recommendation, and illustrative research articles to: CELEST Postdoctoral Search, Room 203, Department of Cognitive and Neural Systems, Boston University, 677 Beacon Street, Boston, MA 02215. From fiori at unipg.it Thu Oct 7 05:56:25 2004 From: fiori at unipg.it (Simone G.O. FIORI) Date: Thu, 07 Oct 2004 11:56:25 +0200 Subject: Two essays on unsupervised learning theory. Message-ID: <1.5.4.32.20041007095625.022cabe4@unipg.it> Dear Connectionists, I take the liberty to announce the availability of two new papers on unsupervised complex-valued neural networks learning and on relative uncertainty learning theory. Best regards, Simone Fiori =*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*= "Non-linear Complex-Valued Extensions of Hebbian Learning: An Essay" by S. Fiori, University of Perugia (Italy) Accepted on Neural Computation Abstract: The Hebbian paradigm is perhaps the most known unsupervised learning theory in connectionism. It has inspired a wide research activity in the artificial neural network field because it embodies some interesting properties such as locality and the capability of being applicable to the basic weight-and-sum structure of neuron models. The plain Hebbian principle, however, also presents some inherent theoretical limitations that make it unpractical in most cases. Therefore, modifications of the basic Hebbian learning paradigm have been proposed over the last twenty years in order to design profitable signal/data processing algorithms. Such modifications led to the principal-component- analysis-type class of learning rules along with their non-linear extensions. The aim of this essay is primarily to present part of the existing fragmented material in the field of principal component learning within a unified view and contextually to motivate and present extensions of previous works on Hebbian learning to complex-weighted linear neural networks. This work benefits from previous studies on linear signal decomposition by artificial neural networks, non-quadratic component optimization and reconstruction error definition, neural parameters adaptation by constrained optimization of complex-valued learning criteria and orthonormality expression via the insertion of topological elements in the networks or by modifying the network learning criterion. In particular, the considered learning principles and their analysis concern complex-valued principal/minor component/subspace linear/non-linear rules for complex-weighted neural structures, both feedforward and laterally-connected. Draft (68 pages) available at: http://www.unipg.it/sfr/publications/rcpca.pdf =*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*= "Relative Uncertainty Learning Theory: An Essay" by S. Fiori, University of Perugia (Italy) Accepted on International Journal of Neural Systems Abstract: The aim of this manuscript is to present a detailed analysis of the algebraic and geometric properties of relative uncertainty theory (RUT) applied to neural networks learning. Through the algebraic analysis of the original learning criterion, it is shown that RUT gives rise to principal-subspace-analysis- type learning equations. Through an algebraic-geometric analysis, the behavior of such matrix-type learning equations is illustrated, with particular emphasis to the existence of certain invariant manifolds. Draft (33 pages) available at: http://www.unipg.it/sfr/publications/ijns-mut.pdf ======================================================= | Dr Simone FIORI (Elec. Eng., Ph.D.) | | * Faculty of Engineering - Perugia University * | | * Polo Didattico e Scientifico del Ternano * | | Via Pentima bassa, 21 - 05100 TERNI (Italy) | | Tel. 0744 492937 - Fax: +39 0744 492925 | | eMail: fiori at unipg.it - Web: http://www.unipg.it/sfr/ | ======================================================= | "Quelli che s'innamoran di pratica sanza scienza, son | | come il nocchiere, ch'entra in navilio sanza timone o | | bussola, che mai ha certezza dove si vada." | | (Leonardo da Vinci) | ======================================================= From terry at salk.edu Fri Oct 8 01:53:08 2004 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 7 Oct 2004 22:53:08 -0700 Subject: UCSD Computational Neurobiology Training Program Message-ID: <200410080553.i985r8cn011727@sherryl.salk.edu> DEADLINE: JANUARY 7, 2005 COMPUTATIONAL NEUROBIOLOGY GRADUATE PROGRAM Department of Biology - University of California, San Diego http://biology.ucsd.edu/grad/CN_overview.html The goal of the Computational Neurobiology Graduate Program at UCSD is to train researchers who are equally at home measuring large-scale brain activity, analyzing the data with advanced computational techniques, and developing new models for brain development and function. Financial support for students enrolled in this training program is available through an NSF Integrative Graduate Education and Research Training (IGERT) award. Candidates from a wide range of backgrounds are invited to apply, including Biology, Psychology, Computer Science, Physics and Mathematics. The three major themes in the training program are: 1. Neurobiology of Neural Systems: Anatomy, physiology and behavior of systems of neurons. Using modern neuroanatomical, behavioral, neuropharmacological and electrophysiological techniques. Lectures, wet laboratories and computer simulations, as well as research rotations. Major new imaging and recording techniques also will be taught, including two-photon laser scanning microscopy and functional magnetic resonance imaging (fMRI). 2. Algorithms and Realizations for the Analysis of Neuronal Data: New algorithms and techniques for analyzing data obtained from physiological recording, with an emphasis on recordings from large populations of neurons with imaging and multielectrode recording techniques. New methods for the study of co-ordinated activity, such as multi-taper spectral analysis and Independent Component Analysis (ICA). 3. Neuroinformatics, Dynamics and Control of Systems of Neurons: Theoretical aspects of single cell function and emergent properties as many neurons interact among themselves and react to sensory inputs. A synthesis of approaches from mathematics and physical sciences as well as biology will be used to explore the collective properties and nonlinear dynamics of neuronal systems, as well as issues of sensory coding and motor control. Participating Faculty include: * Henry Abarbanel (Physics): Nonlinear and oscillatory dynamics; modeling central pattern generators in the lobster stomatogastric ganglion. Director, Institute for Nonlinear Systems at UCSD * Thomas Albright (Salk Institute): Motion processing in primate visual cortex; linking single neurons to perception; fMRI in awake, behaving monkeys. Director, Sloan Center for Theoretical Neurobiology * Scott Baden (Computer Science and Engineering): High performance computing and management of complexity; MCell simulations of cell signaling. * Darwin Berg (Neurobiology): Regulation synaptic components, assembly and localization, function and long-term stability. * Richard Buxton (Radiology, School of Medicine): Brain imaging using MRI. fundamental aspects of cortical blood flow. * Garrison Cottrell (Computer Science and Engineering): Dynamical neural network models and learning algorithms * Anders Dale (Radiology, School of Medicine): Functional brain imaging; integration of metabolic and electromagnetic brain signals. * Virginia De Sa (Cognitive Science): Computational basis of perception and learning (both human and machine); multi-sensory integration and contextual influences * Mark Ellisman (Neurosciences, School of Medicine): High resolution electron and light microscopy; anatomical reconstructions. Director, National Center for Microscopy and Imaging Research * Marla Feller (Neurobiology): Mechanisms and function of spontaneous activity in the developing nervous system including the retina, spinal cord, hippocampus and neocortex. * Robert Hecht-Nielsen (Electrical and Computer Engineering): Neural computation and the functional organization of the cerebral cortex. Founder of Hecht-Nielsen Corporation * Harvey Karten (Neurosciences, School of Medicine): Anatomical, physiological and computational studies of the retina and optic tectum of birds and squirrels * David Kleinfeld (Physics): Active sensation in rats; properties of neuronal assemblies; optical imaging of large-scale activity. * William Kristan (Neurobiology): Computational Neuroethology; functional and developmental studies of the leech nervous system, including studies of the bending reflex and locomotion. Director, Neurosciences Graduate Program at UCSD * Herbert Levine (Physics): Nonlinear dynamics and pattern formation in physical and biological systems, including cardiac dynamics and the growth and form of bacterial colonies * Thomas Liu (Radiology, School of Medicine): Brain imaging using MRI. * Scott Makeig (Institute for Neural Computation): Analysis of cognitive event-related brain dynamics and fMRI using time-frequency and Independent Component Analysis * Javier Movellan (Institute for Neural Computation): Sensory fusion and learning algorithms for continuous stochastic systems * Mikhael Rabinovich (Institute for Nonlinear Science): Dynamical systems analysis of the stomatogastric ganglion of the lobster and the antenna lobe of insects * Terrence Sejnowski (Salk Institute/Neurobiology): Computational neurobiology; physiological studies of neuronal reliability and synaptic mechanisms. Director, Institute for Neural Computation * Martin Sereno (Cognitive Science): Neural bases of visual cognition and language using anatomical, electrophysiological, computational, and non-invasive brain imaging techniques * Nicholas Spitzer (Neurobiology): Regulation of ionic channels and neurotransmitters in neurons; effects of electrical activity in developing neurons on neural function. Chair of Neurobiology * Charles Stevens (Salk Institute): Synaptic physiology; physiological studies and biophysical models of synaptic plasticity in hippocampal neurons * Jochen Triesch (Cognitive Science): Sensory integration, visual psychophysics, vision systems and robotics, human-robot interaction, cognitive developmental * Emo Todorov (Cognitive Science): Neural control of movement; sensorimotor psychophysics in visuohaptic virtual environments; modeling the motor system. * Roger Tsien (Chemistry): Second messenger systems in neurons; development of new optical and MRI probes of neuron function, including calcium indicators and caged neurotransmitters * Hal White (Economics): Statistical learning theory. * Mark Whitehead (Neurosurgery, School of Medicine): Peripheral and central taste systems; anatomical and functional studies of regions in the caudal brainstem important for feeding behavior * Ruth Williams (Mathematics): Probabilistic analysis of stochastic systems and continuous learning algorithms Requests for application materials should be sent to the University of California, San Diego, Division of Biological Sciences 0348, Graduate Admissions Office, 9500 Gilman Drive, La Jolla, CA, 92093-0348 or to [gradprog at biomail.ucsd.edu]. The deadline for completed application materials, including letters of recommendation, is January 7, 2005. For more information about applying to the UCSD Biology Graduate Program. A preapplication is not required for the Computational Neurobiology Program. Contact ttomp at ucsd.edu for further information about admissions to the program. From H.Bowman at kent.ac.uk Fri Oct 8 09:45:48 2004 From: H.Bowman at kent.ac.uk (H. Bowman) Date: Fri, 08 Oct 2004 14:45:48 +0100 Subject: Conference Proceedings Available Message-ID: <41669A0C.5050205@kent.ac.uk> I have a number of copies of the following conference proceedings available at a reduced price. Progress in Neural Processing - Vol. 15 CONNECTIONIST MODELS OF COGNITION AND PERCEPTION II Proceedings of the Eighth Neural Computation and Psychology Workshop University of Kent, UK August 2003 Publisher : World Scientific edited by Howard Bowman (University of Kent, UK) & Christophe Labiouse (University of Liege, Belgium) Copies are available at the price of 20 (note, the publishers are currently selling this volume at a price of 65!). If you are interested in buying a copy at the reduced rate, then send an email to, H.Bowman at kent.ac.uk. Details of the volume can be found at: http://www.worldscibooks.com/books/compsci/5508.html Regards, Howard From fuernkranz at informatik.tu-darmstadt.de Sun Oct 10 17:46:13 2004 From: fuernkranz at informatik.tu-darmstadt.de (Johannes Fuernkranz) Date: Sun, 10 Oct 2004 23:46:13 +0200 Subject: GfKl-05 Special Track on Ranking, Multi-Label Classification and Preference Learning Message-ID: <4169ADA5.4060802@informatik.tu-darmstadt.de> Special Track on Ranking, Multi-Label Classification and Preference Learning GfKl-05 Magdeburg, Germany, 9-11 March 2005 Focus This track focusses on learning techniques for tackling prediction problems that transgress the two traditional disciplines, classification (prediciton of categorical variables) and regression (prediction of numerical variables). In particular, it will focus on approaches that predict more complex structures such as ordered categories, hierarchies, sets, lists, partial or total relations, etc. Papers that describe algorithms, theoretical results or applications in these areas are of interest for this special track. Submission of Abstracts Participants intending to present a talk are requested to submit an abstract at the main conference site. The abstract will be reviewed, and authors of accepeted abstracts will be invited to submit a full version of the paper to the post-conference proceedings (which will undergo a second round of reviewing). The proceedings will be published by Springer-Verlag in the 'Studies in Classification, Data Analysis, and Knowledge Organization' series. Track Chairs Johannes Frnkranz TU Darmstadt, Knowledge Engineering Group E-mail: fuernkranz at informatik.tu-darmstadt.de Eyke Hllermeier Philipps-Universitt Marburg, FB Mathematik und Informatik E-mail: eyke at mathematik.uni-marburg.de Important Dates November 1, 2004: Deadline for abstract submission January 17, 2005: Notification of acceptance March 9 - 11, 2005: Conference April 24, 2005: Submission of full paper -- Johannes Fuernkranz Knowledge Engineering Group, TU Darmstadt From Marie.Cottrell at univ-paris1.fr Tue Oct 12 08:37:57 2004 From: Marie.Cottrell at univ-paris1.fr (Marie Cottrell) Date: Tue, 12 Oct 2004 14:37:57 +0200 Subject: CFP WSOM'05 Message-ID: <5.0.2.1.2.20041012143734.023cf338@asterix.univ-paris1.fr> Please find the preliminary Call For Papers for the WSOM'05 conference, (Workshop on Self-Organizing Maps), which will take place in Paris, University Paris 1, Panth?on-Sorbonne, from Monday 5th September 2005 to Thursday 8th. Manuscript Submission deadline : 15 April 2005. Please forward to any colleagues who may be interested ------------------------------------------------------------------------------------------------------- CALL FOR PAPERS 5th Workshop on Self Organizing Maps (WSOM'05) Paris, University Paris 1, Panth?on-Sorbonne 5th-8th September 2005 WEB page (under construction) http://samos.univ-paris1.fr/wsom/wsom05.html OBJECTIVES The Self-Organizing Map (SOM) with its related extensions is the most popular artificial neural algorithm for use in unsupervised learning and data visualization. Over 5,000 publications have been reported in the open literature, and many commercial projects employ the SOM as the tool for solving hard real-world problems. WSOM'05 is the discussion forum where your ideas and techniques are polished, and aims to unveil the results of hot researches and popularize the use of the SOM for technical public. Following the highly successful meetings held in 1997 and 1999 (Helsinki University of Technology), 2001 (University of Lincolnshire and Humberside), 2003 (Kyushu Institute of Technology), a further workshop in this established series will bring together researchers and users of the SOM and related techniques. TOPICS Topics will include, but are not limited to, the following: Self-organization Unsupervised learning (including PCA/NLPCA, ICA/NLICA, Principal Curves/Surfaces) Theory and extensions Optimization Hardware and architecture Signal processing, image processing and vision Time-series analysis Text and document analysis Financial analysis Data visualization and mining Bioinformatics Robotics, ... All papers will be peer reviewed on the basis of a full length manuscript and acceptance will be based on quality, originality and relevance. Accepted papers will be published in the conference proceedings. IMPORTANT DATES Manuscript Submission 15 April 2005 Acceptance Notification 15 May 2005 Camera Ready Submission 30 May 2005 Advance Registration 15 June 2005 PAPER SUBMISSION Only electronic submissions are accepted. The mailing address and instructions for authors will be soon available on the WEB page. For further details, please contact the Organization Chairman Marie Cottrell (cottrell at univ-paris1.fr) Organized by the SAMOS-MATISSE, University of Paris 1. ************************************************* 3% of the European GDP for Science : When and How ? 3% du PIB europ?en pour la Science : Quand et Comment ? http://fer.apinc.org ************************************************ Marie Cottrell Tel et fax(prof): 33 1 44 07 89 22 SAMOS-MATISSE Universite Paris 1 E-mail : cottrell at univ-paris1.fr http://samos.univ-paris1.fr Postal address : 90, rue de Tolbiac 75634 PARIS CEDEX 13 Address of the laboratory : 72, rue Regnault 75013 Paris (m?tro Porte d'Ivry) -- Ce message a ?t? v?rifi? par MailScanner pour des virus ou des polluriels et rien de suspect n'a ?t? trouv?. From bernhard.schoelkopf at tuebingen.mpg.de Mon Oct 11 06:22:34 2004 From: bernhard.schoelkopf at tuebingen.mpg.de (Bernhard Schoelkopf) Date: Mon, 11 Oct 2004 12:22:34 +0200 Subject: CAS - MPG Partner Institute in the field of Computational and Theoretical Biology Message-ID: The Chinese Academy of Sciences (CAS) and the Max-Planck-Gesellschaft (MPG) intend to establish a CAS - MPG PARTNER INSTITUTE IN THE FIELD OF COMPUTATIONAL AND THEORETICAL BIOLOGY Applications are invited for the positions of up to three full-time department directors. Legally and administratively the Partner Institute will be an institute of the CAS, located on the CAS Campus of the Shanghai Institutes for Biological Sciences (SIBS). The aim of this interdisciplinary and theoretically oriented Institute is to account for the increasing involvement of mathematical, computer-science and engineering methods in modern biology and to allow for novel approaches of research at the interfaces between disciplines (e.g. bioinformatics, computational biology, systems biology, computation biophysics, theoretical neurobiology or evolutionary biology). The proximity to experimentally oriented, internationally competitive research institutes on the SIBS campus guarantees close scientific cooperation and interaction between theoretical and experimental research. Strong collaboration with one or more Max Planck Institutes in Germany is expected from the directors and will be expressively documented and fostered by appointing them as External Scientific Members of MPG. To aid the final definition of promising reseach areas and the identification of suitable candidates, the Chinese Academy of Sciences and the Max-Planck-Gesellschaft will jointly organize a Symposium on Perspectives in Computational and Theoretical Biology which will be held in Shanghai on December 19 - 20, 2004. We invite applications from scientists with an outstanding international research record who are willing to take full advantage of the unique challenge to build up a new, interdisciplinary and theoretical/computational institute by cooperating with the experimental institutes on the SIBS campus and in association with a Max Planck Institute in Germany. The recruitment and appointment procedure for the director positions will be carried out jointly by CAS and MPG. The positions will offer full scientific and economic independence equivalent to that of a director/head of department at a Max Planck Institute. The initial appointment will be for five years and can be extended after review by the Institute's internationally composed Scientific Advisory Board. Qualified candidates should submit a curriculum vitae, a short statement of research interests and scientific goals, reprints of key publications and the topic (or abstract) of the intended presentation at the symposium. To ensure full consideration, please submit a hard copy of your application before October 31, 2004 to CHEN Zhu (Vice President of CAS) Chinese Adademy of Sciences 52 Sanlihe Road Beijing 100864 P.R. China and PDF-files of your application to the contact persons in Munich and Shanghai: E-mail: spielmann at gv.mpg.de Barbara SPIELMANN Max-Planck-Gesellschaft Hofgartenstrasse 8 D ? 80539 M?nchen Germany Tel.: +49-89-2108 1365 Fax: +49-89-2108 1041 E-mail: yyyang at sibs.ac.cn YANG Yanyun Shanghai Institutes for Biological Sciences Chinese Academy of Sciences 319 Yue Yang Road Shanghai 200031, P. R. China Tel: +86?21-5492 0965 Fax: +86?21-5492 0968 From bogus@does.not.exist.com Wed Oct 13 11:10:11 2004 From: bogus@does.not.exist.com () Date: Wed, 13 Oct 2004 10:10:11 -0500 Subject: postdoctoral position Message-ID: From bower at uthscsa.edu Thu Oct 14 20:03:17 2004 From: bower at uthscsa.edu (Jim Bower) Date: Thu, 14 Oct 2004 19:03:17 -0500 Subject: WAM-BAMM*05 in San Antonio Message-ID: ----------------------------------------------------------------------------- Announcing the World Association of Modelers (WAM) First Annual Biologically Accurate Modeling Meeting (BAMM) WAM-BAMM*05 In Association with the Second GENESIS USERS MEETING GUM*05 March 31st - April 2nd In beautiful San Antonio Texas http://www.WAM-BAMM.org Meeting objective: To bring together modelers and experimentalists using Realistic Modeling techniques to better understand biological systems. Subjects considered: Modeling techniques, simulator design, modeling results, modeling inspired biological experimentation, and world modeling community coordination. Meeting Structure: Thursday March 31st will be devoted to a series of tutorials and round table discussions on Biological modeling. Tutorials will be offered by leading experts in realistic modeling and the interaction between modeling and experimental biology. Friday and Saturday will be devoted to oral and poster presentations by meeting participants and invited speakers. Important Dates: --------------- Meeting pre-registration: Via the WAM-BAMM web site: www.wam-bamm.org, assures you receive future meeting mailings. Deadline for proposing tutorials: December 1, 2004 Give a tutorial on techniques of biologically realistic modeling at WAM-BAMM. Send a brief description of the proposed tutorial to wambamm05 at wam-bamm.org. Authors of accepted tutorial presentations will be provided free meeting registration. Deadline for proposed research presentations: December 15, 2004 Submission form is available on the WAM-BAMM web site: www.wam-bamm.org Student registration deadline for travel grants: February 1, 2005 Funding is available for student travel grants. (see web site). Deadline for early registration: February 15, 2005 Advanced registration $ 99 for graduate students, $ 149 for all others (30% increase after deadline) Deadline for guaranteed housing at the conference rate: March 1, 2005 The meeting will be held at the historic Menger Hotel in Downtown San Antonio, next to the Alamo and the famous San Antonio River Walk. Room rates $109 (single or double), $ 119 (3-4). Arrival date for the meeting: March 30th, 2005 The famous WAM-BAM Banquet, Rodeo, and Blue Bonnet Festival: Saturday, April 2, 2005 Depart from San Antonio: April 3, 2005 More information on WAM-BAM can be found at www.wam-bamm.org, or by contacting us at wam-bamm at wam-bamm.org. From ecuadros at spc.org.pe Thu Oct 21 12:13:35 2004 From: ecuadros at spc.org.pe (Ernesto Cuadros-Vargas) Date: Thu, 21 Oct 2004 11:13:35 -0500 Subject: CFP IJCNN05 Special Session "Constructive/Hierarchical Self-Organizing Maps" Message-ID: <447901c4b789$d18da4e0$a1c279c8@characato> Call for Papers for a Special Session "Constructive/Hierarchical Self-Organizing Maps" International Joint INNS-IEEE Conference on Neural Networks (IJCNN) 2005 Hilton Bonaventure Hotel, Montreal, Quebec, Canada July 31- August 4, 2005, IJCNN 2005, (http://faculty.uwb.edu/ijcnn05) The aims of this session is to bring together researchers working on novel constructive models based on Self-Organizing Maps (SOM). This area brings together knowledge from Hierarchical Information Retrieval, Access Methods such as Spatial and Metric Access Methods, Constructive Techniques, etc. Topics include but are not restricted to: * Hierarchical SOM * Constructive SOM * Self-evolving architectures * Evolving and Evolutionary Self-Organizing Maps, * Incorporating Access Methods on Self-Orgainzing Maps * Techniques to find an appropriate SOM architecture * Similarity Information Retrieval * Bayesian Approaches Organizers: Prof. Dr. Ernesto Cuadros-Vargas - ecuadros at spc.org.pe Peruvian Computer Society, Peru and Prof. Dra. Roseli Ap. Francelin Romero - rafrance at icmc.usp.br University of Sao Paulo, Brazil Submissions and deadlines: 26 October 2004: An abstract (1 page) should be sent electronically to the organizers 15 December 2004: A full paper (see the IJCNN'05 instructions for submissions) sent to the organizers. 5 January 2005: Reviews and a notification of acceptance/rejection sent to the authors. 31 January 2005: Final paper submitted to the special session electronically (IJCNN'05 portal) All accepted papers will be published in the IJCNN 2005 Proceedings. Papers not accepted for the special session can be submitted as regular submissions for IJCNN'05 (the deadline is also January 31, 2005). Authors will be invited to submit extended versions of their papers to a special issue of an international journal. Each paper must have the title, authors with e-mails/web sites, and a detailed abstract as possible. All accepted papers must be presented at the conference. *************************************************************** Prof. Dr. Ernesto Cuadros-Vargas Peruvian Computer Society ecuadros at spc.org.pe http://socios.spc.org.pe/ecuadros Phone: +51-54-400416 (home) or +51-54-934-1932 (cellular) *************************************************************** From swells at hrl.com Thu Oct 21 12:19:41 2004 From: swells at hrl.com (Sheryl Wells) Date: Thu, 21 Oct 2004 09:19:41 -0700 Subject: research position at HRL Laboratories Message-ID: <4177E19D.3040605@hrl.com> A non-text attachment was scrubbed... Name: not available Type: multipart/mixed Size: 1426 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/00000000/4c31eb5d/attachment-0001.bin From p.husbands at sussex.ac.uk Thu Oct 21 09:54:09 2004 From: p.husbands at sussex.ac.uk (Phil Husbands) Date: Thu, 21 Oct 2004 14:54:09 +0100 Subject: post-doc position neuronal modelling/interfacing Message-ID: <16133484.1098370449@philh-home-pc.crn.cogs.susx.ac.uk> Post-doctoral position, University of Sussex Non-linear media computing A three year post is available (to start ASAP) to work on an exciting project on non-linear media computing in The Centre for Computational Neuroscience and Robotics, University of Sussex (www.informatics.sussex.ac.uk/ccnr/ ). Suitable for a talented researcher with experience in one or more of the following areas: computational neuroscience, machine learning, evolutionary computing, neuron/silicon interfacing. Good computational skills are required, ability in mathematics and electronics is desirable. This post is part of a multidisciplinary project, in collaboration with the University of West of England and Leeds University, in which computer scientists, neuroscientists, chemists, cell biologists and engineers will study information processing in chemical and (biological) neuronal non-linear media in order to try and determine fundamental principles for the design of novel non-linear media computers and to abstract novel computational mechanisms. The post-doc will be involved in computational and mathematical modelling, particularly of NO volume signalling, and investigating the efficacy of evolutionary algorithms for designing cultured neuronal network structures to create a computing resource capable of satisfying a given objective. The successful applicant will work very closely with a neuroscience post-doc as part of a team led by Profs. Phil Husbands and Michael O?Shea. Applicants should email a full CV to Phil Husbands (philh at sussex.ac.uk) by November 15th 2004. The project is funded by EPSRC. Starting salary approx. ?27,000 depending on experience. From larryy at apple.com Fri Oct 22 11:59:11 2004 From: larryy at apple.com (Larry Yaeger) Date: Fri, 22 Oct 2004 10:59:11 -0500 Subject: Robotics/Cognitive Science faculty positions at IU Message-ID: Indiana University, Bloomington, IN. Two faculty positions beginning August 2005. As part of a series of new appointments, the Cognitive Science Program at Indiana University seeks one senior and one junior level appointment in the general area of intersection of cognitive science and robotics. Senior applicants should have a strong record of research and teaching, a desire to take a leadership position, and a record supporting such a position. Applicants for the junior level position should have a record that demonstrates an excellent potential in the areas of research and teaching. Applicant's areas of expertise may but do not have to include biomorphic robotics, evolutionary robotics, artificial life, and embodied cognition. Successful applicants will take a leadership role in the planning and execution of a new, state-of-the-art laboratory for teaching and research. Applicants should send full dossiers, including letters of recommendation or names and addresses of referees. Indiana University is an equal opportunity/affirmative action employer. Applications from women and minority group members are especially encouraged. Please send materials to Professor Richard Shiffrin, Search Committee, Cognitive Science Program, 1033 E. Third St., Sycamore 0014, Bloomington, IN 47405. Applications received by December 1, 2004 are assured full consideration. Please see our website: http://www.cogs.indiana.edu for information regarding additional open faculty positions. From marc-oliver.gewaltig at honda-ri.de Fri Oct 22 07:56:22 2004 From: marc-oliver.gewaltig at honda-ri.de (Marc-Oliver Gewaltig) Date: Fri, 22 Oct 2004 13:56:22 +0200 Subject: Release of the Neural Simulation Tool NEST 1.0 Message-ID: <200410221356.22491.marc-oliver.gewaltig@honda-ri.de> October 22 2004 The NEST Initiative is pleased to announce the release of the neural simulation tool NEST. * NEST is designed specifically for the simulation of large networks of biologically realistic point-neurons (10^4-10^5 neurons), and provides extensive support for hierarchically structured networks. * NEST is both flexible and efficient, and supports parallel simulation on multi-processor computers. * NEST has been tested on a range of Unix varieties, including Linux, Mac OS X, Solaris and Tru64 Unix. Windows is supported via the Cygwin environment. * NEST can be downloaded under an open source license from the NEST Initiative website http://www.nest-initiative.org On that website, you will find more information about NEST, the NEST Initiative, and mailing lists around NEST. -- Dr. Marc-Oliver Gewaltig ------------------------------------ Honda Research Institute Europe GmbH Carl-Legien-Str. 30 D-63073 Offenbach/Main, Germany http://www.honda-ri.de From skoenig at usc.edu Tue Oct 26 21:12:04 2004 From: skoenig at usc.edu (Sven Koenig) Date: Tue, 26 Oct 2004 18:12:04 -0700 (PDT) Subject: CFP: JMLR Special Issue on "Learning in Large Probabilistic Environments" Message-ID: CALL FOR PAPERS Journal of Machine Learning Research Special Issue on Learning in Large Probabilistic Environments Guest Editors Sven Koenig, Shie Mannor and Georgios Theocharous http://www.jmlr.org/cfp/llpe.html We invite papers on learning in large probabilistic environments for a special issue of the Journal of Machine Learning Research (JMLR). One of the fundamental problems of artificial Intelligence is how to enable systems (for example, mobile robots, manufacturing systems, or diagnostic systems) embedded in complex environments to achieve their long-term goals efficiently. A natural approach is to model such systems as agents that interact with their environment through actions, perceptions and rewards. These agents choose actions after every observation, aiming to maximize their long-term reward. Learning allows them to improve their initial strategy based on the history of successful and unsuccessful interactions with the environment. This special issue is intended to serve as an outlet for recent advances in learning in such environments, often called reinforcement learning. We welcome both theoretical advances in this field as well as detailed reports on applications of learning in large probabilistic domains. Topics of interest include: * Theoretical foundations of learning in large probabilistic environments. * Completely and partially observable Markov decision process models (MDPs) and similar models. Learning with factored state or action spaces, continuous state spaces, action spaces or time models, hybrid models, relational learning, concurrency. * Heuristics and approximations. Policy and value function approximations, Monte Carlo and advanced simulation methods. * Spatio-temporal abstractions. Dynamic factorization, hierarchy and relational structure. * Interactive learning. Guided exploration, combining supervised and unsupervised learning, shaping, and learning from very few examples. * Learning in complex systems. Function approximation, dimensionality reduction, feature selection for learning, and alternative state representations. * Cooperative and competitive multi-agent reinforcement learning. Learning in nonstationary domains and stochastic, network, and dynamic games. * Real world applications. Medicine, finance, robotics, manufacturing, security, etc. Submission procedure: Submit papers to the standard JMLR submission system http://jmlr.csail.mit.edu/manudb Please include a note stating that your submission is for the special issue on Learning in Large Probabilistic Environments. Important Dates: * Submission due: April 15th, 2005 * Decision: August 1st, 2005 * Final version due: October 1st, 2005 For further details or enquiries, please contact the guest editors: Sven Koenig (skoenig at usc.edu) Shie Mannor (shie at ece.mcgill.ca) Georgios Theocharous (georgios.theocharous at intel.com) From rmeir at ee.technion.ac.il Tue Oct 26 16:41:57 2004 From: rmeir at ee.technion.ac.il (Ron Meir) Date: Tue, 26 Oct 2004 22:41:57 +0200 Subject: CALL FOR PAPERS - COLT 2005 Message-ID: <009301c4bb9c$6ebbcbf0$0300a8c0@ron1> [Apologies to multiple recipients of this announcement ] CALL FOR PAPERS The Eighteenth Annual Conference on Learning Theory Bertinoro, Italy, June 27-30, 2005 http://learningtheory.org/colt2005 The Eighteenth Annual COLT (Conference on Learning Theory, formerly Workshop on Computational Learning Theory) will be held in Bertinoro, Italy, June 27-30, 2005 We invite submissions of papers addressing the theoretical modeling and analysis of all aspects of learning and empirical inference. We strongly support a broad definition of learning theory, including: * Analysis of learning algorithms and their generalization ability * Computational complexity of learning * Bayesian analysis * Statistical mechanics of learning systems * Optimization procedures for learning * Inductive inference * Boolean function learning * Inductive logic programming * Unsupervised and semi-supervised learning * On-line learning and relative loss bounds * Learning in planning and control (including reinforcement learning) * Mathematical analysis of learning in related fields (e.g. game theory, neuroscience) We welcome theoretical papers about learning that do not fit into the above categories. We are particularly interested in papers that include viewpoints that are new to the COLT community. While the primary focus of the conference is theoretical, papers can be strengthened by the inclusion of relevant experimental results. We also welcome experimental and algorithmic papers provided they are relevant to the focus of the conference by elucidating theoretical results in learning. All papers will appear in the proceedings, to be published in the Springer Lecture Notes in Artificial Intelligence series. The proceedings will appear both as a printed book and in a full-text electronic version, thus we require electronic submissions. Papers that have previously appeared in journals or at other conferences, or that are being submitted to other conferences are not appropriate for COLT. PAPER FORMAT: Submissions should include the title, authors' names, postal and email addresses, and a 200-word summary of the paper suitable for the conference program. They should be no longer than 15 pages using the Springer LNCS style file (see http://www.springer.de/comp/lncs/authors.html). Your paper should include a clear definition of the theoretical model used and a clear description of the results, as well as a discussion of their significance, including comparison to other work. Submit papers electronically in pdf or ps format (for details see conference website). While it is not expected that all full proofs can be included in the paper, authors should strive to at least present partial proofs which will enable the reviewers to understand the main ideas and methods used. The paper should also attempt to be as self-contained as possible. OPEN PROBLEMS SESSION: We also invite submission of open problems (see separate call). These should be constrained to two pages using the same formatting as for the full papers. There is a shorter reviewing period for the open problems. Accepted contributions will be allocated short presentation slots in a special open problems session and will be allowed two pages each in the proceedings. ELECTRONIC SUBMISSION INSTRUCTIONS: Will become available in early December at http://learningtheory.org/colt2005 PROGRAM CO-CHAIRS: Peter Auer (U of Leoben) and Ron Meir (Technion) PROGRAM COMMITTEE: Shai Ben-David (Waterloo), Avrim Blum (Carnegie Mellon), Peter Bartlett (Berkeley), Nader Bshouty (Technion), Ran El-Yaniv (Technion), Yoav Freund (Columbia), Ralf Herbrich (Microsoft), Marcus Hutter (IDSIA), Tony Jebara (Columbia), Vladimir Koltchinskii (New Mexico), Phil Long (Columbia), Gabor Lugosi (Barcelona), Shie Mannor (McGill), Shahar Mendelson (ANU), Massimiliano Pontil (University College), Daniel Reidenbach (U Kaiserslautern), Dan Roth (U Illinois Urbana-Champaign), Michael Schmitt (Ruhr University Bochum), Rocco Servedio (Columbia), Hans Ulrich Simon (Ruhr University Bochum), Volodya Vovk (Royal Holloway), Manfred Warmuth (UC Santa Cruz), Tong Zhang (IBM) CONFERENCE AND LOCAL ARRANGEMENTS CHAIRS: Nicolo Cesa Bianchi (Universita di Milano) and Claudio Gentile (Universita dell?Insubria) OPEN PROBLEMS CO-CHAIRS: Adam Klivans (Toyota Institute) and Rocco Servedio (Columbia) MARK FULK AWARD: This awards is for the best paper authored or coauthored by a student. Eligible authors who wish to be considered for this prize should indicate this on their submission's title page. INVITED SPEAKERS: Sergiu Hart (Hebrew University), Wulfram Gerstner (EPFL), Satinder Singh (Michigan) From bogus@does.not.exist.com Mon Oct 25 15:21:26 2004 From: bogus@does.not.exist.com () Date: Mon, 25 Oct 2004 20:21:26 +0100 Subject: PhD Studentship Message-ID: <51D8DD363F91404B8DE8C73D7601869DBA5C7B@ccexchange-2.cns.cranfield.ac.uk> From dgw at MIT.EDU Thu Oct 28 13:41:27 2004 From: dgw at MIT.EDU (David Weininger) Date: Thu, 28 Oct 2004 13:41:27 -0400 Subject: book announcement--Alpaydin Message-ID: <2004102813412723682@outgoing.mit.edu> I thought readers of the Connectionists List might be interested in this book. For more information, please visit http://mitpress.mit.edu/0262012111/ Thank you! Best, David Introduction to Machine Learning Ethem Alpaydin The goal of machine learning is to program computers to use example data or past experience to solve a given problem. Many successful applications of machine learning exist already, including systems that analyze past sales data to predict customer behavior, recognize faces or spoken speech, optimize robot behavior so that a task can be completed using minimum resources, and extract knowledge from bioinformatics data. Introduction to Machine Learning is a comprehensive textbook on the subject, covering a broad array of topics not usually included in introductory machine learning texts. It discusses many methods based in different fields, including statistics, pattern recognition, neural networks, artificial intelligence, signal processing, control, and data mining, in order to present a unified treatment of machine learning problems and solutions. All learning algorithms are explained so that the student can easily move from the equations in the book to a computer program. The book can be used by advanced undergraduates and graduate students who have completed courses in computer programming, probability, calculus, and linear algebra. It will also be of interest to engineers in the field who are concerned with the application of machine learning methods. After an introduction that defines machine learning and gives examples of machine learning applications, the book covers supervised learning, Bayesian decision theory, parametric methods, multivariate methods, dimensionality reduction, clustering, nonparametric methods, decision trees, linear discrimination, multilayer perceptrons, local models, hidden Markov models, assessing and comparing classification algorithms, combining multiple learners, and reinforcement learning. Detailed table of contents available at http://www.cmpe.boun.edu.tr/~ethem/i2ml/ Ethem Alpaydin is Professor in the Department of Computer Engineering at Bogazi?i University, Istanbul October 2004, 7 x 9, 400 pp., 135 illus., cloth, ISBN 0-262-01211-1 Adaptive Computation and Machine Learning series ______________________ David Weininger Associate Publicist The MIT Press 5 Cambridge Center, 4th Floor Cambridge, MA 02142 617 253 2079 617 253 1709 fax http://mitpress.mit.edu From gerhard.widmer at jku.at Wed Oct 13 05:20:07 2004 From: gerhard.widmer at jku.at (Gerhard Widmer) Date: Wed, 13 Oct 2004 11:20:07 +0200 Subject: [Mlnet] Open University Position in Austria Message-ID: <416CF347.2060505@jku.at> OPEN POSITION AT THE JOHANNES KEPLER UNIVERSITY LINZ, AUSTRIA: ASSISTANT PROFESSOR (LECTURER) AT THE POST-DOCTORAL LEVEL The newly founded DEPARTMENT OF COMPUTATIONAL PERCEPTION at the Johannes Kepler University Linz, Austria, headed by Prof. Gerhard Widmer, has an open position for a Full-time Assistant Professor ("Universit?tsassistent") at the post-doctoral level, with a contract limited to 4-6 years. REQUIREMENTS: - a doctorate in computer science or a related field - research experience in one or several of the following areas: Artificial/Computational Intelligence, Machine Learning, Sensor Data Interpretation and Signal Analysis, Intelligent Audio/Music/Video/Image Processing, Intelligente Data Analysis, Time Series Processing, Pattern Recognition. The candidate is expected to build up his/her own research program, to be active in the acquisition of research funding, and to contribute to the department's teaching and administration. LANGUAGE: Fluency in German is not a prerequisite, though a passive command of the German language would be beneficial. Excellent English is required. Teaching can be done in English for the first one or two years. MORE INFORMATION: Prof. Gerhard Widmer Tel.: +43 - 732 - 2468 1510 e-mail: gerhard.widmer at jku.at WWW: www.oefai.at/~gerhard For some of our recent research in the area of machine learning and intelligent music processing see http://www.oefai.at/~gerhard or http://www.ai.univie.ac.at/oefai/ml/ Women are particularly encouraged to apply and will be given priority in case of equal qualification. The OFFICIAL ANNOUNCEMENT (in German) can be found at http://www.cp.jku.at/stellenausschreibung.html . DEADLINE FOR APPLICATION: October 27, 2004 Please send your application with relevant documents (CV, picture, publications list / sample publications, copies of academic documents) to: Personalabteilung der Zentralen Dienste der Universit?t Linz A-4040 Linz/Auhof AUSTRIA and make sure to refer to "Anzeigennummer 1148" (ID of this announcement) in your cover letter. The application can be written in English, of course. ***************************************************************** Gerhard Widmer Department of Computational Perception Tel: +43 732 2468 1510 Johannes Kepler University Linz Altenberger Strasse 69 gerhard.widmer at jku.at A-4040 Linz, Austria http://www.cp.jku.at ***************************************************************** _______________________________________________ Mlnet mailing list Mlnet at ais.fraunhofer.de http://lists.ais.fraunhofer.de/mailman/listinfo/mlnet