From fsommer at berkeley.edu Thu Apr 3 20:04:44 2008 From: fsommer at berkeley.edu (Fritz Sommer) Date: Thu, 3 Apr 2008 17:04:44 -0700 Subject: Connectionists: CRCNS.ORG: New datasharing website for computational neuroscience Message-ID: CRCNS.ORG: NEW DATASHARING WEBSITE FOR COMPUTATIONAL NEUROSCIENCE The new website http://www.crcns.org is available for sharing resources for computational neuroscience, such as high-quality experimental data sets, analytical tools and models. Currently, the website hosts resources whose preparation have been supported by a new funding track in the joint NSF/NIH program Collaborative Research in Computational Neuroscience. http://www.nsf.gov/funding/pgm_summ.jsp?pims_id=5147 The resources currently available are electrophysiology data from hippocampus, visual and auditory cortices, avian auditory structures, as well as recordings of human eye movements during movie watching. Each resource is documented by a summary page and more detailed documentation written by the resource contributor. Individual discussion forums for each resource enable the interaction and collaboration between people interested in a particular data set. Every CRCNS funding cycle new resources will be added. The history, motives and goals of this data sharing initiative are described in the article: "Data sharing for computational neuroscience" by J. L. Teeters, K. D. Harris, K. J. Millman, B. A. Olshausen, and F. T. Sommer (Neuroinformatics, 2008) http://dx.doi.org/10.1007/s12021-008-9009-y The website has been built and is maintained by the Sommer lab in the Redwood Center for Theoretical Neuroscience at UC Berkeley. Funding for this effort is provided by the NSF. Any feedback or suggestions on how to improve this website is gladly appreciated. Jeff Teeters, Fritz Sommer -------------------------------------------------- Friedrich T. Sommer, Ph.D., Associate Adjunct Professor University of California, Berkeley Redwood Center for Theoretical Neuroscience & HWNI 3210F Tolman Hall MC 3192 Berkeley, CA 94720 phone (510) 642-7251 fax (510) 642-7206 http://redwood.berkeley.edu/wiki/Fritz_Sommer From paolo.delgiudice at iss.infn.it Wed Apr 2 18:57:56 2008 From: paolo.delgiudice at iss.infn.it (paolo del giudice) Date: Thu, 03 Apr 2008 00:57:56 +0200 Subject: Connectionists: Minischool and Workshop on Multiple Time Scales in the Dynamics of the Nervous System Message-ID: Minischool and Workshop on Multiple Time Scales in the Dynamics of the Nervous System ICTP, Trieste, Italy June 16-20 2008 http://agenda.ictp.it/smr.php?1947 Organizers: N. Brunel, P. Del Giudice, S. Franz, R. Zecchina, Fusi The event will focus on the present understanding of the role of multiple time scales in the dynamics of the nervous system. Intrinsic time scales of single neuron dynamics are mostly in the range of a few to a few hundreds of milliseconds. Between such time scales and the very long ones underlying long-lasting metabolic or even functional anatomic changes, time spans ranging from seconds to months are observed to be involved in cognitive processes, and call for a theoretical framework to account for their emergence and role. In many cases it is attractive, if not compelling, to think of such a variety of time scales as the manifestation of a rich repertoire of collective dynamic states in large assemblies of neurons and synapses. Emergence of up and down states, sustained neural activity supporting working memory, collective global oscillations on wide frequency ranges, bursting, ramping activity tuned to task- relevant timing are examples of behaviours still not easily incorporated in a unified theoretical frame. Furthermore, irregularities in the time course of the relevant dynamic quantities are pervasively observed, from the inter-spike intervals of recorded neurons, to the distribution of reaction times observed in psychophysics. The role of noise as a putative constituent element of brain dynamics has just begun to be investigated. The time dimension (and noise) is also a challenging aspect of modeling synaptic changes, as models have to encompass phenomena ranging from short-term facilitation and depression, to Long-Term Potentiation and Depression, to Long- Term memory; learning achieved in one-shot to very slow learning; the effects of neuromodulation on learning. The two-days minischool will provide an up-to-date and broad overview of experimental and theoretical approaches, while the three-days workshop will present more technical and specialized contributions of frontier research. The workshop program will also include a small number of contributed talks and two poster sessions. We encourage applicants willing to present an oral or poster contribution to submit a one-page abstract for evaluation. The meeting will be dedicated to the memory of Prof. Daniel Amit, whose seminal, creative and vigorous activity in the field has inspired and provoked so many of us in the last 20 years. Lecturers: L Abbott (Columbia) XJ Wang (Yale) MV Sanchez-Vives (Barcelona) D Salzman (Columbia) (to be confirmed) Speakers Y Amit (Chicago) D Durstewitz (Plymouth) G Mongillo (Paris) G Rainer (Tubingen) H Sompolinsky (Jerusalem) A Treves (SISSA) S Wang (Princeton) E Zohary (Jerusalem) NEW DEADLINES for requesting participation and for submitting one-page abstract, if not requiring visa or financial support: April 30 2008 -- Paolo Del Giudice Complex Systems Unit Department of Technologies and Health Italian National Institute of Health phone: ++39 06 49902245 fax: ++39 06 49387075 skype: paolodg58 http://neural.iss.infn.it From pelillo at dsi.unive.it Wed Apr 2 16:49:25 2008 From: pelillo at dsi.unive.it (Marcello Pelillo) Date: Wed, 2 Apr 2008 22:49:25 +0200 (CEST) Subject: Connectionists: Postdoc position for EU-FP7 SIMBAD project (Venice, Italy) Message-ID: POSTDOCTORAL POSITION IN COMPUTER VISION AND PATTERN RECOGNITION Ca' Foscari University, Venice, Italy Department of Computer Science Applications are invited for one postdoctoral position at the Department of Computer Science of Ca' Foscari University, Venice, Italy, to undertake research in computer vision and pattern recognition within the context of SIMBAD (Beyond Features: Similarity-Based Pattern Analysis and Recognition). SIMBAD is a three-year EU-FP7 FET (Future and Emerging Technologies) project, started on 1st April 2008, which involves the following partners: - Ca' Foscari University (Venice, Italy) [coordinator] - University of York (England) - Delft University of Technology (The Netherlands) - Insituto Superior T?cnico (Lisbon, Portugal) - ETH Zurich (Switzerland) - University of Verona (Italy) The project aims at bringing to full maturation a paradigm shift that is currently just emerging within the pattern recognition and machine learning domains, where researchers are becoming increasingly aware of the importance of similarity information per se, as opposed to the classical feature-based approach. We aim at undertaking a thorough study of several aspects of similarity-based pattern analysis and recognition methods, from the theoretical, computational, and applicative perspective, with a view to substantially advance the state of the art in the field, and contribute towards the long-term goal of organizing this emerging field into a more coherent whole. The successful candidate will join the Computer Vision and Pattern Recognition Group at Ca' Foscari Universty, headed by Prof. Marcello Pelillo. The group's research activity is focused primarily on graph-theoretic, optimization, and game-theoretic approaches, and in the interplay between continuous and combinatorial methods. The research spans a range of topics including grouping and segmentation, shape analysis and object recognition, structural matching and learning, and contextual pattern recognition. The group has an established international reputation for its work, with a track record of top-level publications. The contribution of the Venice group to the SIMBAD project will be on game-theoretic approaches and structural learning. Candidates should have a PhD in Computer Vision and/or Machine Learning (or at least have submitted the thesis and awaiting the viva). A solid mathematical background and good programming skills are expected. An interest in game-theoretic approaches and/or graph-based learning would be an asset for this position. The appointment will be initially for one year (renewable) starting from 1st June 2008 or soon thereafter. The salary will be about EUR 22,500 per annum plus an additional grant to cover lodging expences, subject to negotiation. For further details or informal enquires please contact Marcello Pelillo (pelillo at dsi.unive.it) or Andrea Torsello (torsello at dsi.unive.it). Applications must be sent by e-mail to Marcello Pelillo (pelillo at dsi.unive.it) and must include a brief letter of application, a CV including a list of publications, and names and e-mail address of at least two referees. Ca' Foscari University is an equal opportunity employer. ________________________________________________________________________ Marcello Pelillo Dipartimento di Informatica Universita' Ca' Foscari di Venezia Via Torino 155, 30172 Venezia Mestre, Italy Tel: (39) 041 2348.440 Fax: (39) 041 2348.419 E-mail: pelillo at dsi.unive.it URL: http://www.dsi.unive.it/~pelillo From axel.hutt at loria.fr Wed Apr 9 10:49:22 2008 From: axel.hutt at loria.fr (Axel HUTT) Date: Wed, 09 Apr 2008 16:49:22 +0200 Subject: Connectionists: PhD-position in machine learning of brain signals Message-ID: <1207752563.25886.100.camel@hydrogen.loria.fr> Announcement of PhD-position in machine learning in Nancy / France: ------------------------------------------------------------------- Detection of multivariate synchronization in brain areas In computational neuroscience, the data analysis of measured activity in the brain promises the gain of knowledge on neural information processing. To this end, a prominent approach is the synchronous measurement of neural activity in different brain areas. The aim of such measurement is the extraction of the information processing in the single brain areas and between them. Moreover different types of neural activity can be measured, such as Local Field Potentials and spiking activity. The PhD-project aims to gain further knowledge from the measured brain signals taking into account the different data types available. Hence the PhD student studies non-adaptive/adaptive and dimensionality reduction techniques and applies these to simulated and experimental data sets. The work will be done in close collaboration with the Max Planck Institute for Biological Cybernetics in Tubingen / Germany. Supervisors: Axel Hutt (CR1) and Bernard Girau (HDR) Location: LORIA, Nancy / France The position starts in September 2008 and lasts for 3 years. For more information, please see http://www.loria.fr/~huttaxel/CORDI2008.html From rsun at rpi.edu Sat Apr 12 22:00:21 2008 From: rsun at rpi.edu (Professor Ron Sun) Date: Sat, 12 Apr 2008 22:00:21 -0400 Subject: Connectionists: Reminder: INNS Award nominations by May 1, 2008 Message-ID: **** Reminder: INNS Award nominations **** INNS (International Neural Networks Society; http://www.inns.org) has a well established awards program, designed to recognize individuals who have made outstanding contributions to the field of Neural Networks. Up to three awards, one in each of the following categories, are presented annually at IJCNN to senior individuals for outstanding contributions made to the field of Neural Networks. The Hebb Award - recognizes achievement in biological learning. The Helmholtz Award - recognizes achievement in sensation/perception. The Gabor Award - recognizes achievement in engineering/application. In addition, there is the Young Investigator Award: up to two awards are presented annually to individuals with no more than five years postdoctoral experience and who are under forty years of age, for significant contributions in the field of Neural Networks. The INNS Awards Committee is now inviting nominations for the 2009 Hebb, Helmholtz, and Gabor awards as well as the Young Investigator awards. You can find the details of the nomination procedure on the INNS Web page: http://www.inns.org; please click on "awards program". I would urge you to think of highly qualified candidates and send in formal nominations for them (see the INNS web page for the instructions). Please email the nominations (along with attachments) directly to the chair of the Awards Committee at rsun at rpi.edu by May 1, 2008. Ron Sun Chair, Awards Committee ======================================================== 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 steve at cns.bu.edu Mon Apr 14 12:23:28 2008 From: steve at cns.bu.edu (Stephen Grossberg) Date: Mon, 14 Apr 2008 12:23:28 -0400 Subject: Connectionists: Spikes, synchrony, and attentive learning by laminar thalamocortical circuits Message-ID: The following article is now available at http://www.cns.bu.edu/Profiles/Grossberg : Grossberg, S. and Versace, M. Spikes, synchrony, and attentive learning by laminar thalamocortical circuits Brain Research, in press ABSTRACT This article develops the Synchronous Matching Adaptive Resonance Theory (SMART) neural model to explain how the brain may coordinate multiple levels of thalamocortical and corticocortical processing to rapidly learn, and stably remember, important information about a changing world. The model clarifies how bottom-up and top-down processes work together to realize this goal, notably how processes of learning, expectation, attention, resonance, and synchrony are coordinated. The model hereby clarifies, for the first time, how the following levels of brain organization coexist to realize cognitive processing properties that regulate fast learning and stable memory of brain representations: single cell properties, such as spiking dynamics, spike-timing-dependent plasticity (STDP), and acetylcholine modulation; detailed laminar thalamic and cortical circuit designs and their interactions; aggregate cell recordings, such as current-source densities and local field potentials; and single cell and large-scale inter-areal oscillations in the gamma and beta frequency domains. In particular, the model predicts how laminar circuits of multiple cortical areas interact with primary and higher-order specific thalamic nuclei and nonspecific thalamic nuclei to carry out attentive visual learning and information processing. The model simulates how synchronization of neuronal spiking occurs within and across brain regions, and triggers STDP. Matches between bottom-up adaptively filtered input patterns and learned top-down expectations cause gamma oscillations that support attention, resonance, learning, and consciousness. Mismatches inhibit learning while causing beta oscillations during reset and hypothesis testing operations that are initiated in the deeper cortical layers. The generality of learned recognition codes is controlled by a vigilance process mediated by acetylcholine. Keywords: attention; learning; STDP; bottom-up filter; top-down expectation; match; prediction; mismatch; LGN; pulvinar; V1; V2; spikes; gamma oscillations; beta oscillations; synchronization; local field potentials; mismatch negativity; acetylcholine; cortical layers; Adaptive Resonance Theory From nkasabov at aut.ac.nz Mon Apr 7 02:06:14 2008 From: nkasabov at aut.ac.nz (Nikola Kasabov) Date: Mon, 07 Apr 2008 18:06:14 +1200 Subject: Connectionists: ICONIP08 and INNS NNN08 conferences in Auckland, NZ, 24-28 .11.2008 Message-ID: <47FA6296.F4EE.00E8.0@aut.ac.nz> ICONIP 2008 and INNS NNN 2008 Conferences, 24-28.11.2008, Auckland NZ ?-------------------------------------------------------------------------------------- The 15th International Conference on Neural Information Processing (ICONIP?08) will be held in Auckland, New Zealand, 25-28 November 2008. Technical co-sponsorship: APNNA, IEEE CIS, INNS, JNNS, ENNS. More information can be found on the web site: http://iconip08.kedri.info ( http://iconip08.kedri.info/ ), where the on-line submission is open now. Deadline: 31st August 2008. General chair: Nik Kasabov (nkasabov at aut.ac.nz). Program Chair: Mario Koeppen (mkoeppen at ieee.org). The First INNS Symposia on ?New Directions in Neural Networks?(INNS-NNN?08) will be held on 24-25 November 2008, preceding the ICONIP 2008 conference. Technical co-sponsorship: INNS, IEEE CIS, JNNS, ENNS, APNNA.More information can be found on the Web site: http://nnn08.kedri.info where papers can be submitted on-line. Deadline: 31st August 2008. General chair: John Weng (weng at cse.msu.edu). Program Chair: Nik Kasabov (nkasabov at aut.ac.nz) ?---------------------------------------------------------------------------------------------------------------------------------------------------- Prof. N.Kasabov General Chair ICONIP 2008 and APNNA President Program Chair INNS-NNN 2008 and INNS President-Elect nkasabov at aut.ac.nz http://www.kedri.info -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080407/0494e244/attachment-0001.html From cardoso at bcos.uni-freiburg.de Mon Apr 7 09:54:13 2008 From: cardoso at bcos.uni-freiburg.de (Simone Cardoso de Oliveira) Date: Mon, 07 Apr 2008 15:54:13 +0200 Subject: Connectionists: Full Professorship (W3) in Theoretical Neuroscience, Berlin Message-ID: <47FA2785.7000207@bcos.uni-freiburg.de> Dear Theoretical Neuroscientists, please spread the word that there is an open faculty position for a Full Professorship (W3) in Theoretical Neuroscience at Humboldt-Universit?t zu Berlin. For further information, see http://www.nature.com/naturejobs/science/jobs/46329 Best regards, Peter Hammerstein Institute for Theoretical Biology Humboldt-Universit?t zu Berlin Berlin, Germany -- Dr. Simone Cardoso de Oliveira Bernstein Coordination Site of the National Network Computational Neuroscience Albert Ludwigs University Freiburg Hansastr. 9A 79104 Freiburg, Germany phone: +49-761-203-9583 fax: +49-761-203-9585 cardoso at bcos.uni-freiburg.de From hitzler at aifb.uni-karlsruhe.de Tue Apr 8 10:45:35 2008 From: hitzler at aifb.uni-karlsruhe.de (Pascal Hitzler) Date: Tue, 08 Apr 2008 16:45:35 +0200 Subject: Connectionists: 2nd CfP: ECAI-08 Workshop on Neural-Symbolic Learning and Reasoning, NeSy'08 Message-ID: <47FB850F.4040402@aifb.uni-karlsruhe.de> FourthInternational Workshop on Neural-Symbolic Learning and Reasoning Workshop at ECAI2008, Patras, Greece, July 2008 http://www.neural-symbolic.org/NeSy08/ NeSy'05 took place at IJCAI-05 NeSy'06 took place at ECAI2006 NeSy'07 took place at IJCAI-07 Call for Papers --------------- Artificial Intelligence researchers continue to face huge challenges in their quest to develop truly intelligent systems. The recent developments in the field of neural-symbolic integration bring an opportunity to integrate well-founded symbolic artificial intelligence with robust neural computing machinery to help tackle some of these challenges. The Workshop on Neural-Symbolic Learning and Reasoning is intended to create an atmosphere of exchange of ideas, providing a forum for the presentation and discussion of the key topics related to neural-symbolic integration. Topics of interest include: * The representation of symbolic knowledge by connectionist systems; * Learning in neural-symbolic systems; * Extraction of symbolic knowledge from trained neural networks; * Reasoning in neural-symbolic systems; * Biological inspiration for neural-symbolic integration; * Neural networks and probabilities; * Applications in robotics, semantic web, engineering, bioinformatics, etc. Keynote speaker: Kai-Uwe K?hnberger, Osnabr?ck Submission Researchers and practitioners are invited to submit original papers that have not been submitted for review or published elsewhere. Submitted papers must be written in English and should not exceed 5 pages in the case of research and experience papers, and 2 pages in the case of position papers (including figures, bibliography and appendices) in ECAI2008 format as described in the ECAI2008 submissions and style guide (http://www.ece.upatras.gr/ecai2008/substyles.htm). All submitted papers will be judged based on their quality, relevance, originality, significance, and soundness. Papers must be submitted directly by email in PDF format to nesy at soi.city.ac.uk Presentation Selected papers will have to be presented during the workshop. The workshop will include extra time for audience discussion of the presentation allowing the group to have a better understanding of the issues, challenges, and ideas being presented. Publication Accepted papers will be published electronically in the CEUR workshop proceedings (bearing an ISSN number). Hardcopies will be distributed during the workshop. Authors of the best papers will be invited to submit a revised and extended version of their papers to the Journal of Logic and Computation, OUP. Important Dates Deadline for submission: May 9th, 2008 Notification of acceptance: May 27th, 2008 Camera-ready paper due: June 6th, 2008 Workshop date: July 21st or 22nd, 2008 ECAI2008 main conference dates: 21st to 25th of July, 2008 Workshop Organisers Artur d'Avila Garcez (City University London, UK) Pascal Hitzler (University Karlsruhe, Germany) Programme Committee (incomplete) Sebastian Bader, TU Dresden, Germany Howard Blair, Syracuse University, U.S.A. Luc de Raedt, KU Leuven, Belgium Marco Gori, University of Siena, Italy Barbara Hammer, TU Clausthal, Germany Ioannis Hatzilygeroudis, University of Patras, Greece Steffen H?lldobler, TU Dresden, Germany Ekaterina Komendantskaya, Sophia Antipolis, France Kai-Uwe K?hnberger, Osnabr?ck, Germany Luis Lamb, Federal University of Rio Grande do Sul, Brazil Roberto Prevete, University of Naples, Italy Dan Roth, University of Illinois at Urbana-Champaign, U.S.A. Anthony K. Seda, University College Cork, Ireland Frank van der Velde, Leiden University, The Netherlands Gerson Zaverucha, Federal University of Rio de Janeiro, Brazil Additional Information General questions concerning the workshop should be addressed to nesy at soi.city.ac.uk. -- PD Dr. Pascal Hitzler Institute AIFB, University of Karlsruhe, 76128 Karlsruhe email: hitzler at aifb.uni-karlsruhe.de fax: +49 721 608 6580 web: http://www.pascal-hitzler.de phone: +49 721 608 4751 http://www.neural-symbolic.org From carnevalet at sbcglobal.net Mon Apr 7 13:40:31 2008 From: carnevalet at sbcglobal.net (Ted Carnevale) Date: Mon, 07 Apr 2008 13:40:31 -0400 Subject: Connectionists: NEURON Summer Course Message-ID: <47FA5C8F.1090102@sbcglobal.net> A few seats remain open for the NEURON Summer Course, but they're going fast, so you should act quickly. For information about the course and the registration form, see http://www.neuron.yale.edu/neuron/nscsd2008/nscsd2008.html --Ted From olivier.buffet at loria.fr Wed Apr 9 11:55:29 2008 From: olivier.buffet at loria.fr (Olivier Buffet) Date: Wed, 09 Apr 2008 17:55:29 +0200 Subject: Connectionists: PhD position in Reinforcement Learning/Planning Message-ID: <47FCE6F1.4030807@loria.fr> PhD position in Reinforcement Learning/Planning at INRIA (Nancy, France): Title: Planning under Uncertainty by Direct Policy Search Summary: Automating the control of discrete event systems is an important issue in a variety of domains: logistics, management of natural ressources, autonomous embedded systems... This is all the more difficult that the system's dynamics is uncertain: - the outcomes of commands depend on external factors; - the system may be modelled approximately; or - observations of the system state are partial and noisy. Such problems can be addressed through the field of probabilistic planning. Classical probabilistic planning algorithms compute the utility (=expected distance to the goal) of each action in each accessible state, which becomes intractable when the state and action spaces grow. This PhD position follows a different direction. The candidate will work on recent and promising algorithms based on optimizing a controller (such as a neural network). The first planner of this type (the Factored-Policy Gradient planner (FPG)) won the probabilistic track of the International Planning Competition 2006. Keywords: probabilistic planning, Reinforcement Learning, Markov Decision Processes, stochastic optimization, policy-gradient For more information and for applications, go to: http://www.talentsplace.com/syndication1/inria/ukdoc/details.html?id=PNGFK026203F3VBQB6G68LOE1&LOV5=4509&LOV2=4490&LOV6=4513&LG=EN&Resultsperpage=20&nPostingID=2418&nPostingTargetID=5800&option=52&sort=DESC&nDepartmentID=28 About INRIA PhD opportunities: http://www.inria.fr/travailler/opportunites/doc.en.html From ASAHTan at ntu.edu.sg Thu Apr 10 04:04:37 2008 From: ASAHTan at ntu.edu.sg (Tan Ah Hwee (Assoc Prof)) Date: Thu, 10 Apr 2008 16:04:37 +0800 Subject: Connectionists: Papers on TD-FALCON and Minefield Navigation Simulator Message-ID: <7CD06E15ADF4104A9F2E4DC2DE678F8904E88095@EXCHANGE21.staff.main.ntu.edu.sg> Dear Colleagues We are pleased to inform the availability of two recently published articles and its associated minefield navigation simulation platform. The preprints of the papers can be downloaded from http://www.ntu.edu.sg/home/asahtan/ under Publications. The minefield simulator (written in JAVA) can be downloaded from http://www.ntu.edu.sg/home/asahtan/ under Downloads. Article 1: Ah-Hwee Tan, Ning Lu and Dan Xiao. Integrating Temporal Difference Methods and Self-Organizing Neural Networks for Reinforcement Learning with Delayed Evaluative Feedback. IEEE Transactions on Neural Networks, Vol. 9, No. 2 (February 2008), 230-244. Abstract: This paper presents a neural architecture for learning category nodes encoding mappings across multi-modal patterns involving sensory inputs, actions, and rewards. By integrating Adaptive Resonance Theory (ART) and temporal difference (TD) methods, the proposed neural model, called TD-FALCON, enables an autonomous agent to adapt and function in a dynamic environment with immediate as well as delayed evaluative feedback (reinforcement) signals. TD-FALCON learns the value functions of the state-action space estimated through on-policy and off-policy temporal difference learning methods, specifically SARSA and Q-Learning. The learned value functions are then used to determine the optimal actions based on an action selection policy. We have developed TD-FALCON systems using various TD learning strategies and compared their performance in terms of task completion, learning speed, as well as time and space efficiency. Experiments based on a minefield navigation task have shown that TD-FALCON systems are able to learn effectively with both immediate and delayed reinforcement and achieve a stable performance in a pace much faster than those of standard gradient descent based reinforcement learning systems. Article 2: Dan Xiao and Ah-Hwee Tan. Self-Organizing Neural Architectures and Cooperative Learning in Multi-Agent Environment. IEEE Transactions on Systems, Man, and Cybernetics - Part B, Vol. 37, No. 6 (December 2007), 1567-1580. TD-FALCON (Temporal Difference - Fusion Architecture for Learning, COgnition, and Navigation) is a generalization of Adaptive Resonance Theory (a class of self-organizing neural networks) that incorporates Temporal Difference (TD) methods for real-time reinforcement learning. In this paper, we investigate how a team of TD-FALCON networks may cooperate to learn and function in a dynamic multi-agent environment based on a minefield navigation task and a predator/prey pursuit task. Experiments on the navigation task demonstrate that TD-FALCON agent teams are able to adapt and function well in a multi-agent environment without an explicit mechanism of collaboration. In comparison, traditional Q-learning agents using gradient descent based feedforward neural networks, trained with the standard backpropagation and the resilient propagation algorithms, produce a significantly poorer level of performance. For the predator/prey pursuit task, we experiment with various cooperative strategies and find that a combination of a high level compressed state representation and a hybrid reward function produces the best results. Using the same cooperative strategy, the TD-FALCON team also outperforms the resilient propagation based reinforcement learners in terms of both task completion rate and learning efficiency. ______________________________________________________________ Dr. Ah-Hwee Tan Director, Emerging Research Lab Associate Professor, School of Computer Engineering Nanyang Technological University Homepage: http://www.ntu.edu.sg/home/asahtan ______________________________________________________________ -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080410/ba9a70af/attachment-0001.html From ywteh at gatsby.ucl.ac.uk Thu Apr 10 07:44:58 2008 From: ywteh at gatsby.ucl.ac.uk (YeeWhye Teh) Date: Thu, 10 Apr 2008 12:44:58 +0100 Subject: Connectionists: CfP: ICML/UAI/COLT 2008 Workshop on Nonparametric Bayes In-Reply-To: References: Message-ID: <90231e670804100444o1359c4fbw8612a91d7ecf4@mail.gmail.com> Call for Abstracts and Participation Nonparametric Bayes 2008 Workshop held at ICML/UAI/COLT 2008 Helsinki, Finland July 9, 2008 http://npbayes.wikidot.com One of the major problems driving current research in statistical machine learning is the search for ways to exploit highly-structured models that are both expressive and tractable. Nonparametric Bayesian methodology provides significant leverage on this problem. In the nonparametric Bayesian framework, the prior distribution is not a fixed parametric form, but is rather a general stochastic process?-a distribution over a possibly uncountably infinite number of random variables. This generality makes it possible to work with prior and posterior distributions on objects such as trees of unbounded depth and breadth, graphs, partitions, sets of monotone functions, sets of smooth functions and sets of general measures. Applications of nonparametric Bayesian methods have begun to appear in disciplines such as information retrieval, natural language processing, machine vision, computational biology, cognitive science and signal processing. Because of their flexibility, they can also be used to express prior knowledge without restricting to small parametric classes. Furthermore, research on nonparametric Bayesian models has served to enhance the links between statistical machine learning and a number of other mathematical disciplines, including stochastic processes, algorithms, optimization, combinatorics and knowledge representation. There have been several previous workshops on nonparametric Bayesian methods at machine learning conferences, including workshops at NIPS in 2003 and 2005 and a workshop at ICML workshop in 2006. This workshop aims to build on the success of these earlier workshops and to catalyze further research. There are many problem areas that need additional attention; these include (1) the development of new Monte Carlo and variational algorithms for inference; (2) the combination of ideas from knowledge representation and nonparametric Bayesian analysis to develop formal languages for specifying and manipulating flexible Bayesian models; (3) the problem of finding objective priors that work in the nonparametric Bayesian setting; (4) theoretical analysis of the conditions under which nonparametric Bayesian methods succeed or fail; and (5) the ongoing need to find compelling applications that serve to exhibit recent developments and to drive further research. This workshop is intended to bring together the growing community of nonparametric Bayesian researchers to explore these and other issues. FORMAT: The one-day workshop consists of three invited talks, three contributed talks, a round-table discussion on theory, methodology and applications, a round-table discussion on general-purpose language and software, a poster session, and a panel discussion. CALL FOR PARTICIPATION: Researchers interested in presenting their work and ideas at the workshop should send an email to npbayes at googlemail.com with the following information: - Title - Authors - Abstract (maximum 2 pages, ICML style pdf) - Preferred contribution (talk, poster, and/or round-table participation) We expect authors to provide a final version of their papers by late June for inclusion on the workshop home page. Papers chosen for contributed talks shall also be expected to liaise with a discussion leader who will be in charge of stimulating discussion of the work at the workshop. DATES: - Abstracts due: May 2, 2008 - Notifications: May 16, 2008 - Final paper due: June 20, 2008 - Workshop: July 9, 2008 ORGANIZERS: - Yee Whye Teh. Gatsby Unit, UCL - Romain Thibaux. Computer Science, Berkeley - Athanasios Kottas. Applied Mathematics and Statistics, UC Santa Cruz - Zoubin Ghahramani. Engineering, Cambridge - Michael I. Jordan. Computer Science and Statistics, UC Berkeley CONTACT: npbayes at googlemail.com -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080410/363cef4c/attachment-0001.html From Elizabeth.Thomas at u-bourgogne.fr Mon Apr 14 03:29:15 2008 From: Elizabeth.Thomas at u-bourgogne.fr (Elizabeth Thomas) Date: Mon, 14 Apr 2008 09:29:15 +0200 Subject: Connectionists: doctoral student in movement studies and machine learning Message-ID: <480307CB.1060400@u-bourgogne.fr> *Doctoral studies in the application of machine learning techniques to the analysis of motor activity* ** We are seeking to recruit a doctoral student who would like to carry out an interdisciplinary study between the areas of signal analyses and movement studies. The study of all motor activities from gait to dance is done by the gathering of kinetic, kinematic and EMG data. Kinematic data is obtained from the displacement of markers placed on the subjects. Kinetic signals provide information on the foot-ground pressure during movements. Finally EMG data is from the electric activity of muscles. As with many biological signals, the analysis of these signals presents us with an important challenge due to their complexity, high variability and noise. The linear techniques which are currently most frequently employed are not sufficiently developed for the analyses of such ?noisy? data. We propose therefore the development of several techniques from machine learning for the analysis of these signals. The PhD student interested in these studies will learn how to use techniques like neural networks and kernel methods. He/She would also learn to use the systems available in the lab for the analyses of movement such as SMART, the Kistler force platform and the Biopac EMG. The thesis will be done under the co-direction of Robert French (Directeur de Recherche, CNRS, LEAD, ( 0380399065, robert.french at u-bourgogne.fr) and Elizabeth Thomas (ma?tre de conf?rence, INSERM U887, 0380396784, elizabeth.thomas at u-bourgogne.fr ). Candidates interested in the grant will have to undergo a competitive interview in Paris in June 2008. More information on Robert French can be seen on http://www.u-bourgogne.fr/lead/people/rfrench.html All interested candidates may send a CV to Robert French and Elizabeth Thomas. From ckiw at inf.ed.ac.uk Mon Apr 14 08:41:27 2008 From: ckiw at inf.ed.ac.uk (Chris Williams) Date: Mon, 14 Apr 2008 13:41:27 +0100 (BST) Subject: Connectionists: ICML 2008 Tutorials programme, July 5 2008 Message-ID: We are pleased to announce the line-up for the ICML 2008 Tutorials, to be held on Sat July 5 in Helsinki, Finland. T1 Painless embeddings of distributions: the function space view Alex Smola, Arthur Gretton, and Kenji Fukumizu T2 Stochastic optimal control theory Bert Kappen, Marc Toussaint T3 Dimensionality Reduction the Probabilistic Way Neil Lawrence T4 Graphical models and variational methods: Message-passing and relaxations Martin Wainwright T5 Playing Machines: Machine Learning Applications in Computer Games Ralf Herbrich, Thore Graepel T6 Beyond Convexity: Submodularity in Machine Learning Andreas Krause, Carlos Guestrin T7 Tutorial on Theory and Applications of Online Learning Shai Shalev-Shwartz, Yoram Singer T8 Visual Object Recognition and Retrieval Rob Fergus T9 Sparse Linear Models: Bayesian Inference and Experimental Design Matthias Seeger For abstracts and links to course webpages see http://icml2008.cs.helsinki.fi/tutorials.shtml Chris Williams ICML 2008 Tutorials chair -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. From carnevalet at sbcglobal.net Tue Apr 15 17:05:46 2008 From: carnevalet at sbcglobal.net (Ted Carnevale) Date: Tue, 15 Apr 2008 17:05:46 -0400 Subject: Connectionists: ModelDB update and survey Message-ID: <480518AA.2020900@sbcglobal.net> ModelDB http://senselab.med.yale.edu/modeldb/ is a searchable on-line database that supports the field of computational neuroscience (CNS) through convenient sharing of published models. It catalyzes advances in CNS by enabling verification of published models--which is essential for scientific reproducibility--and fostering attributed re-use and extension of models. As of April 15, 2008, ModelDB contains 367 models, implemented with more than 30 different programming languages or simulation environments. Model entries include downloadable source code, plus citations and links to the published articles. Survey 1. Have you published a computational neuroscience model that is not already in ModelDB? If so, we invite you to enter it (please contact tom dot morse at yale dot edu). 2. We would also like to hear if you have published any articles that used information obtained from ModelDB, or mentioned ModelDB in another context. 3. We are very interested to hear your comments or suggestions for improving ModelDB. Please send all replies to ted dot carnevale at yale dot edu with the subject line ModelDB update and survey --Ted From S.J.Eglen at damtp.cam.ac.uk Thu Apr 24 16:01:57 2008 From: S.J.Eglen at damtp.cam.ac.uk (Stephen Eglen) Date: Thu, 24 Apr 2008 21:01:57 +0100 Subject: Connectionists: Postdoc opening: modelling development of retinotopic maps Message-ID: <18448.59189.142395.56646@notch.damtp.cam.ac.uk> A postdoctoral position is being offered under a joint computational/experimental Wellcome Trust Programme Grant awarded to Dr Stephen Eglen (Cambridge) in collaboration with Professor David Willshaw (Edinburgh) and Professors Ian Thompson and Uwe Drescher (Kings College London). The aim of the grant is to evaluate the relative contributions of electrical activity as against molecular guidance cues in the development of ordered nerve connections in the vertebrate visual system. The Research Associate will be based at Cambridge and will develop computational models for the formation of retinotectal connections, focusing initially on the roles of spontaneous neural activity. These models will help generate hypotheses that can be tested by the experimental partners. The candidate will also be expected to quantify and analyse relevant experimental data. The job will involve travel to project partners and attendance at workshops and conferences. The ideal candidate will have a first degree in the mathematical or physical sciences, and a PhD in Computational Neuroscience or a closely related discipline. He/She will have an interest in developmental neuroscience and experience in interacting with colleagues across disciplines. Experience in developing computational models in C/Matlab/R is highly advantageous. Good communication skills are also essential, both for working with the project team and publication of results. Informal enquiries should be directed to Dr Stephen Eglen (S.J.Eglen at damtp.cam.ac.uk). The start date for this position is expected to be Summer 2008. The post will be for three years in the first instance with a possibility for renewal for up to two more years. Applications should include a CV, a statement of research and a completed form PD18 Parts I and III (downloadable from http://www.admin.cam.ac.uk/offices/personnel/forms/pd18/), and should be sent to Dr Stephen Eglen, DAMTP-CMS, Wilberforce Road, Cambridge CB3 0WA or emailed to: S.J.Eglen at damtp.cam.ac.uk. Closing date: 22 May 2008. Vacancy Reference No: LE03346 Salary: 25,134-32,796 pounds. Limit of tenure applies (the funds for this post are available three years in the first instance). http://www.admin.cam.ac.uk/offices/hr/jobs/vacancies.cgi?job=3346 -- Stephen Eglen, DAMTP, Centre for Mathematical Sciences Wilberforce Road, Cambridge CB3 0WA, U.K. Tel +44 (0)1223 765 761 S.J.Eglen at damtp.cam.ac.uk Fax +44 (0)1223 760 419 http://www.damtp.cam.ac.uk/user/eglen From christopher.pack at mcgill.ca Fri Apr 18 11:37:28 2008 From: christopher.pack at mcgill.ca (Christopher Pack, Dr.) Date: Fri, 18 Apr 2008 11:37:28 -0400 Subject: Connectionists: Postdoc in visual neurophysiology Message-ID: <88D0960F912D1D418772EA0B479C9B8204272C7D@EXCHANGE2VS3.campus.mcgill.ca> Applications are requested for a postdoctoral position in visual neurophysiology at the Montreal Neurological Institute (MNI), which is part of McGill University's School of Medicine. The MNI is located in downtown Montreal, Canada, and provides a multifaceted neuroscience environment with clinical and research activities housed under one roof. The successful candidate will work with Christopher Pack as part of a collaboration with Dan Butts of Cornell University's Institute of Computational Biomedicine. The goal of the project is to elucidate how visual processing occurs in higher-level cortical areas during naturalistic visual stimulation. It will involve recording neuronal activity from the visual cortex in alert macaque monkeys, as well as the development and application of novel models of visual computation. The lab has facilities for multi-electrode recordings, human psychophysics, TMS, and eye movement monitoring. More information on our current research interests can be found at: http://www.mni.mcgill.ca/research/cpack/index.htm http://physiology.med.cornell.edu/faculty/butts/ The candidate must have obtained a Ph.D. in neuroscience or a related field in the last 3 years and have prior research experience in one or more of the following areas: -computational/theoretical neuroscience -micro-electrode recording of neural activity -analysis of neural signals Starting date is negotiable. Please send curriculum vitae, brief statement of research interests and accomplishments, and names of two references to christopher.pack at mcgill.ca . -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080418/423a98e0/attachment.html From ps629 at columbia.edu Mon Apr 28 11:32:47 2008 From: ps629 at columbia.edu (Paul Sajda) Date: Mon, 28 Apr 2008 11:32:47 -0400 Subject: Connectionists: Postdoctoral position in Cortically-coupled Computer Vision Message-ID: Note we have a second postdoctoral position immediately available Cortically-coupled Computer Vision Columbia University, Department of Biomedical Engineering The Laboratory for Intelligent Imaging and Neural Computing (LIINC) at Columbia University has an immediate opening for a Postdoctoral Fellow to participate in our research program in "Cortically-coupled Computer Vision (C3Vision)". The C3Vision program looks to synergistically couple biological and computer vision systems using a combination of brain machine interfaces, machine learning and pattern classification, and image understanding within the context of understanding the advantages and limits of both biological and computer vision. Applicants should have a background in one, and preferably several, of the following: machine vision (especially content based indexing and automated image labeling), machine learning, neural signal processing, neuroimaging (EEG and/or fMRI), real-time systems design and programming. LIINC is in the Department of Biomedical Engineering at Columbia University and interacts closely with other departments at Columbia, Including Electrical Engineering, Biological Sciences, Computer Science and Neuroscience. In addition, the C3Vision project includes collaborators at other academic institutions as well as in industry, and the project involves both basic and applied research which will ultimately lead to testable systems. Interested candidates should send via email their CV, three representative papers, the names of three references, and cover letter to Prof. Paul Sajda (ps629 at columbia.edu). Applications will be considered until July 2008. The position is for one year, with the option to renew for an additional year, given satisfactory performance and available funding. Paul Sajda, Ph.D. Associate Professor Department of Biomedical Engineering Columbia University 351 Engineering Terrace Building, Mail Code 8904 1210 Amsterdam Avenue New York, NY 10027 tel: (212) 854-5279 fax: (212) 854-8725 email: ps629 at columbia.edu http://liinc.bme.columbia.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080428/6e71b471/attachment.html From cees.van-leeuwen at sunderland.ac.uk Wed Apr 30 03:15:37 2008 From: cees.van-leeuwen at sunderland.ac.uk (Cees Van-leeuwen) Date: Wed, 30 Apr 2008 16:15:37 +0900 Subject: Connectionists: international post-doc positions at RIKEN Message-ID: <1aff241afbb6.1afbb61aff24@sunderland.ac.uk> This is to notify that RIKEN is now accepting applications for Foreign Postdoctoral Researcher (FPR) positions for FY2009. These positions are for foreign young scientists who have demonstrated creative and innovative ideas and who can be expected to achieve broad international recognition in the future. To recruit top class researchers from overseas, we would like to ask for your help. If you have any chance to introduce this program outside RIKEN, it would be highly appreciated. Deadline: Applicants to Host Laboratory: June 13, 2008 Host Laboratory to Reseach Personnel Section:June 27, 2008 For more information, please go to the website below. http://www.riken.go.jp/engn/r-world/info/recruit/080727/index.html -------------- next part -------------- A non-text attachment was scrubbed... Name: bs0cvl.vcf Type: text/x-vcard Size: 361 bytes Desc: Card for Cees Van-leeuwen Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080430/3e3c3c3e/bs0cvl.vcf From bminnery at mitre.org Wed Apr 30 12:30:55 2008 From: bminnery at mitre.org (Minnery, Brad) Date: Wed, 30 Apr 2008 12:30:55 -0400 Subject: Connectionists: Computational Neuroscientist Position at the MITRE Corporation In-Reply-To: References: Message-ID: Greetings, The MITRE Corporation, a not-for-profit organization in McLean VA (http://www.mitre.org/), has several opportunities to work with forward-looking government sponsors seeking to apply the mechanisms and principles of biological intelligence to longstanding problems of national importance. Job Title: SENIOR ARTIFICIAL INTELLIGENCE ENGINEER Key Functions: -- Assist Government Program Managers in developing and managing research programs that exploit our growing understanding of the neurobiological basis of intelligent behavior. -- Monitor and assess the technical state-of-the-art in cognitive and computational neuroscience and neuromorphic engineering. -- Identify opportunities for applying emerging insights from neuroscience research towards problems in the domains of: artificial intelligence, integrated circuit design, automated perception, robotics, human performance, and human-computer interaction. -- Perform original research as necessary to answer specific questions or to provide a proof of concept. Prepare technical presentations, reports and tutorials as necessary to communicate progress and findings to colleagues and government sponsors. Desired Education / Experience: Ph.D. in Neuroscience, Cognitive Science, Artificial Intelligence or related engineering discipline. Experience in computational neuroscience and neuromorphic electronic hardware is preferred. Required Skills: -- Familiarity with quantitative and qualitative concepts in the computational and cognitive neurosciences -- Proficiency in one or more of the leading computational/cognitive neuroscience modeling tools and/or frameworks -- Outstanding oral and written communication skills, including the ability to clearly present complex technical concepts to both technical and non-technical personnel -- Ability to plan, conduct and publish original scientific research -- including the ability to consider alternative approaches and to identify factors affecting cost or risk Desired Skills: -- Familiarity with hardware-based implementations of neural systems, e.g. neuromorphic VLSI -- Computer programming skills, particularly in Matlab and C/C++ -- Proficiency in PDP++, NEURON, Genesis, or any of several popular neural modeling tools -- Strong knowledge of current theoretical and experimental trends in the areas of learning, memory, and visual attention preferred Please apply online at: http://www.mitre.org/employment/index.html When applying, please reference Req ID: 9336 From chaumann at cor-lab.Uni-Bielefeld.DE Thu Apr 24 07:31:50 2008 From: chaumann at cor-lab.Uni-Bielefeld.DE (Carola Haumann) Date: Thu, 24 Apr 2008 13:31:50 +0200 Subject: Connectionists: 2 Scholarships for Postdocs at CoR-Lab / Bielefeld University Message-ID: <48106FA6.2080706@cor-lab.Uni-Bielefeld.DE> Apologies for multiple postings 2 Scholarships for Postdocs at CoR-Lab / Bielefeld University The CoR-Lab has been established at Bielefeld University, Germany, as a research centre for intelligent systems and human-machine interaction. The CoR-Lab forms a strategic partnership between Bielefeld University and the Honda Research Institute Europe GmbH, Germany. It pursues fundamental research in the field of cognitive robots and intelligent systems, where the Honda humanoid robot ASIMO is available as an advanced technological platform. A particular focus of the CoR-Lab is the interdisciplinary integration of expertise in engineering, computer science, brain science, and cognitive sciences, including the humanities and social sciences. The Graduate School that is associated with the CoR-Lab provides an exciting and stimulating environment for enthusiastic and creative postdocs, allowing them to pursue research in international teams in close collaboration with an industrial research institute. The CoR-Lab Graduate School offers 2 scholarships for postdocs. We invite applications from researchers holding an academic degree (Dr./Ph.D.) and meeting the qualifications listed below in detail for both positions. Fluency in English is required. A complete application should include certificates and transcripts of records of the completed course of studies, a CV, a cover letter providing information about the qualification and the motivation to do research in the Graduate School, as well as a short description of the research interests with regard to one of the following two projects: *************************************************************** *Implicit semantic transmission in social learning Analysis and modeling The social context of learning has increasingly gained attention in developmental psychology, cognitive science and robotics. It has been proposed that an agent ? in order to learn ? needs to be grounded in a meaningful embodied activity. The robotic research has just started to benefit from the use of developmental approaches: Orienting towards ?learning by communicating? offers new learning paradigms, within which it can be analyzed how semantic information is transmitted, and which effect the way of transmission has onto learning. So far this paradigm involves face-to-face scenarios, where a tutor is focusing on a student. However, this learning situation is not offered in every culture. Instead, developmental research has shown that children are likely to benefit also from other scenarios. Motivated by animal studies by e.g. Irene Pepperberg on grey parrots which were trained in a social learning paradigm (model-rival-paradigm), it is our goal to investigate multi-party learning scenarios, in which the tutor does not address the student directly but the student is learning while observing a tutoring behaviour towards another person. Thus, our assumption is that learning can take place from both, direct and indirect teaching. With this project, we will investigate the behaviour of tutors and students and study the achieved learning effects in different situations of social learning. Based on the data gathered in psychophysical experiments on both, direct and indirect teaching scenarios, we aim to identify different verbal and non-verbal patterns, e.g. denominating objects, showing an object. Following the identification and classification of these patterns, we aim to develop a generative model for their production. The purpose of this model is twofold. Firstly, it will allow setting up a virtual tutor. A virtual tutor can be used to create simulated dialogues with the virtual tutor replacing the real tutor or tutors and an additional avatar, which replaces the child. Secondly, building a generative model for the behaviour of the tutor will allow us to understand the underlying principles of learning in a social context better and the insights from the modelling will provide valuable feedback on the design of the psychophysical experiments. The results of this research should enable the setup of a social interaction simulation environment, where reproducible experiments between tutor avatars and a robotic artefact could be performed. These experiments will allow testing new hypotheses on how social learning takes place. *************************************************************** * Autonomous Exploration of Manual Interaction Space We gradually increase our manual competence by exploring manual interaction spaces for many different kinds of objects. This is an active process that is very different from passive perception of "samples". The availability of humanoid robot hands offers the opportunity to investigate different strategies for such active exploration in realistic settings. In the present project, the investigation of such strategies shall be pursued from the perspective of ?multimodal proprioception:? correlating joint angles, partial contact information from touch sensors and joint torques as well as visual information about changes in finger and object position in such a way as to make predictions about "useful aspects" for shaping the ongoing interaction. To make this very ambitious goal approachable within the resource bounds of a single project, we will focus on an interesting and important specific case of manual interaction spaces: ?visually supervised object-in-hand manipulation?. More particularly, one could consider rotating an object, e.g. a cube, within the hand such, that certain faces become visible one after the other. This project crucially involves the need to combine visual information with proprioceptive feedback when the fingers explore the faces and edges of the object. A major goal of the project would be to implement a "vertical slice" of explorative skills, ranging from low level finger control and visual perception within an object category, chunking a limited set of action primitives, and planning short action sequences. Generic insights should be about how visual and haptic information has to be combined to drive the exploration process and about suitable principles for shaping the exploration, such as reinforcement learning, active learning driven by information maximization, imitation of previously learnt episodes (instead of statistical learning). Research experience in one or more of the areas visual perception, robotics control, reinforcement learning, active learning, and neural networks is appreciated. *************************************************************** For more information please see: http://www.cor-lab.de/corlab/html/graduate_school/index.php Please send your application until 13 May 2008 (preferably in PDF format) to the Managing Director of the Graduate School: email: chaumann at cor-lab.uni-bielefeld.de Bielefeld University CoR-Lab Graduate School Dr. Carola Haumann 33594 Bielefeld Germany From rammurthy at iiit.ac.in Sat Apr 26 08:02:09 2008 From: rammurthy at iiit.ac.in (ram murthy) Date: Sat, 26 Apr 2008 17:32:09 +0530 Subject: Connectionists: Fw: New Release on Electronics and Computer Message-ID: <012301c8a795$5b4c4570$1524a8c0@iiit1b1ae426b1> New Age InternationalDear Collegue and Moderator, Here is a brief summary of a book that I have written. The details are attached. I wanted to bring to the network of neural net researchers, the timely book. If you feel appropriate, please circulate the details. Interested neural network researchers can buy the book for about 5 DOLLARS. With Regards, Rama Murthy ----- Original Message ----- From: Rohtas To: rammurthy at iiit.ac.in Cc: sgupta Sent: Saturday, April 26, 2008 2:47 PM Subject: New Release on Electronics and Computer Book Details Multidimensional Neural Networks Unified Theory Rama Murthy, G., Faculty Member at the International Institute of Information Technology, Hyderabad. ISBN : 978-81-224-2228-3 Publication Year : Nov, 2007 Edition : 1st Reprint : Pages : 168 Price : Rs. 195 Binding : Paperback About the Book: The book ``Multidimensional Neural Networks (MDNNs): Unified Theory`` has been conceived for serving 3 types of users: Senior undergraduate/graduate students, practising engineers, and advanced neural network researchers. This book is based on the following innovations: a.. Multidimensional (M-D) logic theory i.e., conceiving logic gates/circuits operating on multidimensional arrays b.. Tensor state space representation of certain M-D systems c.. Relation M-D logic gates, M-D codeword tensors, M-D optimal control tensors to M-D neural networks unification d.. Novel complex valued associative memory (CVNN) on the hypercube e.. Novel models of biological neurons such as those with a linear filter model of synapse f.. Neural network based signal processing The subject of M-D neural networks will have the applications in: 1.. Design of versatile associative memories, 2.. Optimal design of intelligent systems, 3.. Pattern recognition systems etc. About the Author: G. Rama Murthy received his Ph.D. degree in Computer Engineering from Purdue University, West Lafayette, U.S.A. He is currently a faculty member at the International Institute of Information Technology, Hyderabad. He has presented/published about 60 research papers in international conferences and journals. He has received awards in All India Technical Essay Contest and All India Electronic Design Competition. He is a member of IEEE, ACM, Eta Kappa Nu, Phi Kappa Phi. Contents: a.. Introduction b.. Multi/Infinite Dimensional Neural Networks, Multi/Infinite Dimensional Logic Theory c.. Multi/Infinite Dimensional Coding Theory: Multi/Infinite Dimensional Neural Networks?Constrained Static Optimization d.. Tensor State Space Representation: Multi Dimensional Systems e.. Unified Theory of Control, Communication and Computation: Multi Dimensional Neural Networks f.. Complex Valued Neural Associative Memory on the Complex Hypercube g.. Optimal Binary Filters: Neural Networks h.. Linear Filter Model of a Synapse: Associated Novel Real/Complex Valued Neural Networks i.. Novel Complex Valued Neural Networks j.. Advanced Theory of Evolution of Living Systems. For more information on Books visit http://www.newagepublishers.com ------------------------------------------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080426/9ac56c43/attachment.html From helies at rpi.edu Wed Apr 23 11:04:45 2008 From: helies at rpi.edu (Sebastien Helie) Date: Wed, 23 Apr 2008 11:04:45 -0400 Subject: Connectionists: ANNOUNCEMENT: CLARION tutorial Message-ID: <916701BD-E509-41DE-BF45-F77EE08951C5@rpi.edu> A full-day tutorial on the CLARION cognitive architecture will take place on July 23rd 2008 at the 30th Annual Conference of the Cognitive Science Society in Washington DC (http://ccc.utexas.edu/ cogsci08/index.html). For participants attending the CogSci2008 conference, the tutorial is free. This full-day tutorial introduces participants to CLARION, a dual- process/dual-representation cognitive architecture that focuses on the distinction between explicit and implicit cognitive processes as well as their synergistic interactions. CLARION is also integrative, involving cognition (reasoning, learning, skill acquisition, etc.), motivation, metacognition, and so on. The presentation will provide a detailed, introductory description, along with many simulations, advanced topics, and formal results. Although some prior exposure to cognitive architectures and artificial neural networks can be helpful, prior understanding of these areas is not required, as the full-day format allows a detailed presentation of basic, as well as advanced, topics related to cognitive modeling using the CLARION cognitive architecture. This tutorial will enable participants to apply the basic concepts, theories, and computational models of CLARION to their own work. For registration, go to: http://ccc.utexas.edu/cogsci08/index.html For more information, please contact Sebastien Helie (helies at rpi.edu) Sebastien Helie, Nick Wilson, Ron Sun Cognitive Science Department, Rensselaer Polytechnic Institute ========================= Sebastien Helie is a postdoctoral research associate in the department of cognitive science at Rensselaer Polytechnic Institute. His research interests are mainly related to unsupervised connectionist modeling, Bayesian modeling, CLARION, and their application to psychology. Nick Wilson is a Ph.D student in the department of cognitive science at Rensselaer Polytechnic Institute. His research interests are mainly related to human motivation, social cognition, and psychological modeling with the CLARION cognitive architecture. Ron Sun is professor in the department of cognitive science at Rensselaer Polytechnic Institute. He is the creator of the CLARION cognitive architecture, and has published numerous papers and books regarding CLARION-based models in psychology and artificial intelligence. ----------------------------------- Sebastien Helie, Ph.D. Postdoctoral research associate Cognitive science department Rensselaer Polytechnic Institute 110 Eighth Street, Carnegie 108 Troy, NY 12180-3590 -- Office: 1107, Sage building Phone: (518) 276-2692 Fax: (518) 276-3017 E-mail: helies at rpi.edu Website: http://www.rpi.edu/~helies ------------------------------------