From ted.carnevale at yale.edu Mon Mar 3 15:26:20 2008 From: ted.carnevale at yale.edu (Ted Carnevale) Date: Mon, 03 Mar 2008 15:26:20 -0500 Subject: Connectionists: NEURON 2008 Summer Course Message-ID: <47CC5EEC.2020108@yale.edu> COURSE ANNOUNCEMENT What: "The NEURON Simulation Environment" (NEURON 2008 Summer Course) http://www.neuron.yale.edu/neuron/nscsd2008/nscsd2008.html When: Saturday, June 21, through Wednesday, June 25, 2008 Where: The Institute for Neural Computation at the University of California, San Diego, CA Organizers: N.T. Carnevale and M.L. Hines Description: This intensive hands-on course covers the design, construction, and use of models in the NEURON simulation environment. It is intended primarily for those who are concerned with models of biological neurons and neural networks that are closely linked to empirical observations, e.g. experimentalists who wish to incorporate modeling in their research plans, and theoreticians who are interested in the principles of biological computation. The course is designed to be useful and informative for registrants at all levels of experience, from those who are just beginning to those who are already quite familiar with NEURON or other simulation tools. Registration is limited to 20, and the deadline for receipt of applications is Monday, June 2, 2008. For more information see http://www.neuron.yale.edu/neuron/nscsd2008/nscsd2008.html or contact Ted Carnevale Neurobiology Dept. Yale University School of Medicine PO Box 208001 New Haven, CT 06520-8001. phone 203-494-7381 email ted.carnevale at yale.edu Supported in part by: National Institutes of Health Institute for Neural Computation http://inc.ucsd.edu/ Contractual terms require inclusion of the following statement: This course is not sponsored by the University of California. From sudderth at eecs.berkeley.edu Mon Mar 3 16:12:58 2008 From: sudderth at eecs.berkeley.edu (Erik Sudderth) Date: Mon, 03 Mar 2008 13:12:58 -0800 Subject: Connectionists: CFP: IEEE PAMI Special Issue on Probabilistic Graphical Models in Computer Vision Message-ID: <47CC69DA.7060005@eecs.berkeley.edu> IEEE Transactions on Pattern Analysis and Machine Intelligence Call for Papers Special Issue on Probabilistic Graphical Models in Computer Vision Guest Editors: Qiang Ji, Rensselaer Polytechnic Institute; Jiebo Luo, Kodak Research; Dimitris Metaxas, Rutgers University; Antonio Torralba, Massachusetts Institute of Technology; Thomas Huang, University of Illinois at Urbana-Champaign, and Erik Sudderth, University of California at Berkeley. Topic Description and Justification An exciting development over the last decade has been the gradually widespread adoption of probabilistic graphical models (PGMs) in many areas of computer vision and pattern recognition. Many problems in computer vision can be viewed as the search, in a specific domain, for a coherent global interpretation and understanding from local, uncertain, and ambiguous observations. Graphical models provide a unified framework for representing the observations and the domain-specific contextual knowledge, and for performing recognition and classification through rigorous probabilistic inference. In addition, PGMs readily capture the correlations and dependencies among the observations, as well as between observations and domain or commonsense knowledge, and allow systematic quantification and propagation of the uncertainties associated with data and inference. Graphical models can be classified into directed and undirected models. The directed graphs include Bayesian Networks (BNs) and Hidden Markov Models (HMMs), while the undirected graphs include Markov Random Fields (MRFs) and Conditional Random Fields (CRFs). Both directed and undirected graphical models have been widely used in computer vision. For example, HMMs are used in computer vision for motion analysis and activity understanding, while MRFs are extensively used for image labeling, segmentation, and stereo reconstruction. The latest research uses BNs in computer vision for representing causal relationships such as for facial expression recognition, active vision, visual surveillance, and for data mining and pattern discovery in pattern recognition. CRFs provide an appealing alternative to MRFs for supervised image segmentation and labeling, since they can easily incorporate expressive, non-local features. Another emerging trend is to use graphical models to integrate context and prior knowledge with visual cues in vision and multimedia systems. Despite their importance and recent successes, PGMs' use in computer vision still has tremendous room to expand in scope, depth, and rigor. Their use is especially important for robust and high level visual understanding and interpretation. This special issue is dedicated to promoting systematic and rigorous use of PGMs for various problems in computer vision. We are interested in applications of PGMs in all areas of computer vision , including (but not limited to) 1) image and video modeling 2) image and video segmentation 3) object detection 4) object and scene recognition 5) high level event and activity understanding 6) motion estimation and tracking 7) new inference and learning (both structure and parameters) theories for graphical models arising in vision applications 8) generative and discriminative models 9) models incorporating contextual, domain, or commonsense knowledge Tentative Timelines August 16, 2008 Submission deadline October 25, 2008 Notification of acceptance April 18, 2009 Camera-ready manuscript due October 1, 2009 Targeted publication date Paper submission and review The papers should be submitted online through PAMI manuscript central site, with a note/tag designating the manuscript to this special issue. All submissions will be peer-reviewed by at least 3 experts in the field. Priority will be given to work with high novelty and potential impacts. We will return without review submissions that we feel are not well aligned with our goals for the special issue. From ps629 at columbia.edu Tue Mar 4 08:27:12 2008 From: ps629 at columbia.edu (Paul Sajda) Date: Tue, 4 Mar 2008 08:27:12 -0500 Subject: Connectionists: Postdoctoral Research Fellow: Cortically-coupled Computer Vision Message-ID: <718CFE84-BD2C-4792-80BD-308879A8D45F@columbia.edu> Postdoctoral Research Fellow: 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 April 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 From terry at salk.edu Tue Mar 4 13:46:07 2008 From: terry at salk.edu (Terry Sejnowski) Date: Tue, 04 Mar 2008 10:46:07 -0800 Subject: Connectionists: NEURAL COMPUTATION - March 2008 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 20, Number 3 - March 1, 2008 Article A Sensorimotor Approach to Sound Localization Murat Aytekin, Cynthia Moss and Jonathan Simon Note A Note on Lewicki-Sejnowski Gradient for Learning Overcomplete Representations Zhaoshui He, Shengli Xie, Liqing Zhang and Andrzej Cichocki Letters Valuations for Spike Train Prediction Vladimir Itskov, Carina Curto and Kenneth D. Harris How Optimal Stimuli for Sensory Neurons are Constrained by Network Architecture Christopher DiMattina and Kechen Zhang A Principle for Learning Egocentric-Allocentric Transformation Patrick Byrne and Suzanna Becker Bayesian Model Comparison in Non-Linear BOLD fMRI Hemodynamics Daniel Jacobsen, Lars Kai Hansen and Kristoffer Madsen Implications of Noise and Neural Heterogeneity for Vestibulo-ocular Reflex Fidelity Timothy Hospedales, Mark van Rossum, Bruce Graham and Mayank Dutia Minimum Acceleration Criterion with Constraints Implies Bang-Bang Control as an Underlying Principle for Optimal Trajectories of Arm Reaching Movements Amir Karniel and Shay Ben-Itzhak Dynamics of Learning Near Singularities in Layered Networks Haikun Wei, Jun Zhang, Florent Cousseau, Tomoko Ozeki and Shun-ichi Amari A Cooperative Recurrent Neural Network for Solving L1 Estimation Problems with General Linear Constraints Youshen Xia and Kamel S. Mohamed ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2008 - VOLUME 20 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $63.60 $123 $54 $57.24 Individual $110 $116.60 $173 $99 $104.94 Institution $849 $899.94 $912 $756 $801.36 * includes 6% GST MIT Press Journals, 238 Main Street, Suite 500, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu http://mitpressjournals.org/neuralcomp ----- From cuehara at oist.jp Tue Mar 4 20:48:35 2008 From: cuehara at oist.jp (cuehara) Date: Wed, 5 Mar 2008 10:48:35 +0900 Subject: Connectionists: Neural Networks: Special Issue 2009 "Brain Machine Interface" Call for Papers Message-ID: <1AE0E18B-BEB0-4341-B183-A3ABB6821D9C@oist.jp> *********************************************** CALL FOR PAPERS 2009 Special Issue of Neural Networks "Brain Machine Interface" *********************************************** Recent developments of interfaces that enable a direct communication between the brain and machine are expected to extend the applicability of systems neuroscience and will foster a variety of innovative advances in neuro-technology. Brain Machine Interfaces (BMI), or Brain Computer Interfaces (BCI) will allow humans to operate computers, robotic arms, wheelchairs, prosthetic devices and other instruments by using only the signals of their brain. This neuro- technology may help severely disabled but cognitively intact patients to communicate and interact with outside world. At the same time, this technology will lead to innovative modalities of interaction for the healthy. Developing new algorithms to decode the cognitive signals from the individual brain signals and learning how the brain adapts to novel environments when interacting directly with the computer will also lead to better understanding of the brain. Thus, in the near future BMI/BCI research will bring about major advances in brain science and information technology. BMI/BCI research is multidisciplinary in nature. This work is firmly based in the basic and computational neurosciences, disciplines like signal processing, machine learning, robotics, rehabilitation engineering, electrode hardware engineering and ethics play a pivotal role in the advancement of this young field. The interest in this field of research has grown tremendously during the last decade. Thus, publishing a special issue to integrate multidisciplinary studies on BMI is very timely for catalyzing further development in this active field of research. This Special Issue will focus on recent advances in the studies of BMI/ BCI, and will incorporate papers from broad range of disciplines e.g. invasive and noninvasive BMI/BCI, techniques for decoding brain- derived signals, neuroethics and applications of neuro-technology. Co-Editors: Tadashi Isa Eberhard E. Fetz Klaus-Robert M?ller Submission: Please access our on-line submission system http://ees.elsevier.com/neunet/ Deadline for submission: September 30, 2008 Notification of final acceptance: May 15, 2009 Deadline for submission of final papers: June 15, 2009 Format: as normal papers in the journal Contact: Neural Networks Okinawa Office e-mail: nneo at oist.jp Neural Networks Official Homepage: http://www.elsevier.com/wps/find/journaldescription.cws_home/841/description ******************************************************** Neural Networks Editorial Office 12-22 Suzaki, Uruma, Okinawa, 904-2234, Japan Phone: +81-98-921-3933; Fax: +81-98-921-3873 Email: nneo at oist.jp ******************************************************** From g.goodhill at uq.edu.au Sun Mar 2 01:42:30 2008 From: g.goodhill at uq.edu.au (Geoffrey Goodhill) Date: Sun, 2 Mar 2008 16:42:30 +1000 Subject: Connectionists: Network issue 19.1 Message-ID: Network: Computation in Neural Systems Issue 19.1 (March 2008) http://www.informaworld.com/smpp/title~content=g790932537~db=all Editorial Geoffrey Goodhill Daniel Amit (1938-2007) Nicolas Brunel Book Review: Dynamical systems in neuroscience: The geometry of excitability and bursting, by Eugene M. Izhikevich Bard Ermentrout Inferring the capacity of the vector Poisson channel with a Bernoulli model Don H. Johnson and Ilan N. Goodman Inferring input nonlinearities in neural encoding models Misha B. Ahrens, Liam Paninski and Maneesh Sahani (FREE ACCESS until March 16th 2008) Information measure for analyzing specific spiking patterns and applications to LGN bursts Kate S. Gaudry and Pamela Reinagel ------- Geoff Goodhill Editor-in-Chief, Network: Computation in Neural Systems http://www.gbhap.com/journals/titles/0954898X.asp From ahu at cs.stir.ac.uk Sun Mar 2 18:37:22 2008 From: ahu at cs.stir.ac.uk (Dr. Amir Hussain) Date: Sun, 2 Mar 2008 23:37:22 -0000 (GMT) Subject: Connectionists: Final Call for Papers: Brain Inspired Cognitive Systems (BICS 2008), Sao Luis, Brazil, 24-27 June 2008 Message-ID: <3191.92.8.229.68.1204501042.squirrel@www.cs.stir.ac.uk> Please forward the final CFP (below) for the Third International Brain Inspired Cognitive Systems (BICS 2008) Conference to interested colleagues . Key Points: A Book will be published by Springer based on expanded and revised versions of ALL accepted BICS 2008 papers ? Submit your extended abstracts at: http://www.x-cd.com/bics08/abstract.cfm Final Submission Deadline (for Extended Abstracts/Draft Papers): 20 March 2008; Confirmed Keynote Speakers: Shun-Ichi Amari (RIKEN Brain Science Institute, Japan), Jose Carlos Principe (University of Florida, USA); and, there will be several plenary discussions led by world-leading researchers - for more details, see the CFP below (or the Conference website: http://www.ufma.br/bics2008) Thank you and we look forward to seeing you in Sao Luis, Brazil! Amir Hussain, Co-Chair BICS 2008 Centre for Cognitive & Computational Neuroscience University of Stirling, Scotland, UK, E-mail: a.hussain at cs.stir.ac.uk >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> BICS 2008 -Third International Brain Inspired Cognitive Systems Conference Sao Luis, Maranhao, Brazil June 24-27, 2008 http://www.ufma.br/bics2008 FINAL CALL FOR PAPERS ? Deadline: MARCH 20th 2008! ******************* This is the last chance to contribute to this biennial conference which brings to Brazil and the South American Continent the most up-to-date discussions on how knowledge of the brain both aids intelligent system design and is informed by it. It identifies the forefront of research in the area and points to the most exciting lines for future research. BICS 2008 presents a unique and timely opportunity for Brazilian and South American researchers to present their work to an international audience and for international researchers to showcase their work in Brazil. Confirmed Keynote Speakers: Shun-ichi Amari (Brain Science Institute, RIKEN, Japan) Jose Carlos Pri?ncipe (University of Florida Gainsville, USA) The conference will involve all attendees in plenary presentations and discussions of a quality for which biennial BICS conferences have become well known - previously in Scotland (BICS 2004), Greece (BICS 2006) and now Brazil (BICS 2008). The plenary discussions headed by symposium chairs are (provisionally): Ron Chrisley: 7 years of Machine Consciousness - what are the new insights? Igor Aleksander: 'How Computational Neuroscience dovetails with Computational Intelligence. Leslie Smith: Essential Neuromorphic Substrates for Intelligent Systems of the Future Amir Hussain: New Potential from Advances in Neural Systems Engineering. Overall Plenary (all will be encouraged to contribute): The real future for Brain Inspiration A Book will be published by Springer based on expanded and revised versions of all accepted BICS2008 papers. CONFERENCE INFORMATION: http://www.ufma.br/bics2008 General Chair: Allan Kardec Barros Depto. Eng. Eletrica, Universidad de Federal do Maranhao, Brazil. Confirmed speakers: Symposia Second International ICSC Symposium on Models of Consciousness (MoC 2008) >From foundations to implementations Chair: Ron Chrisley , University of Sussex, U.K. Fourth International ICSC Symposium on Biologically Inspired Systems (BIS 2008) Design and implementation of biologically inspired and neuromorphic systems Chair: Leslie Smith, University of Stirling, U.K. Third International ICSC Symposium on Cognitive Neuro Science (CNS 2008) Models of cognitive systems; Chair: Igor Aleksander, Imperial College London, U.K Fifth International ICSC Symposium on Neural Computation (NC 2008) Progress in neural systems Chair: Amir Hussain, University of Stirling, U.K. Why this conference, and who should attend: The biennial Brain Inspired Cognitive Systems 2008 aims to bring together leading scientists and engineers who use analytic, formal or computational methods both to understand the prodigious processing properties of biological systems, particularly the brain, and to exploit such knowledge to advance technology towards ever higher levels of cognitive competence. The four major symposia are organized in patterns that encourage cross-fertilization across the symposia topics. This emphasizes that, following the success of BICS 2004 (Stirling, Scotland) and BICS 2006 (Greece), BICS 2008 will continue be a major point of contact for researchers and practitioners who can benefit from not only the major advances in their specialist fields but also from the diversity of each other's views. Each of the four mornings is devoted to papers that will be selected for their clear novelty and proven scientific impact, while the afternoons will provide scope for researchers to present their current work and discuss their aims and ambitions. Debates across disciplines will unite researchers with differing perspectives. Final Deadline for submissions: March 20th 2008 ~~~~~~~~~~~~~~~~~~~~~~~~~~ You may submit your extended abstract at http://www.x-cd.com/bics08/abstract.cfm ~~~~~~~~~~~~~~~~~~~~~~~~~~ SUB-THEMES (including, but not limited to): Models of consciousness: (MoC) Global Workspace Theory Imagination/synthetic phenomenology Virtual Machine Approaches Axiomatic Models Control Theory/Methodology Developmental/Infant Models Will/volition/emotion/affect Philosophical implications Grounding in neurophysiology Enactive approaches Heterophenomenology Cognitive Neuroscience (CNS) Attentional Mechanisms Cognitive Neuroscience of Sensory Modalities CN of volition Affective Systems Language Cortical Models Sub-Cortical Models Cerebellar Models Event location in the brain Others Biologically Inspired Systems (BIS) Brain Inspired (BI) Vision BI Audition and sound processing BI Other sensory modalities BI Motion processing BI Robotics BI Evolutionary systems BI Oscillatory systems BI Signal processing BI Learning Neuromorphic systems Others Neural Computation (NC) Hybrid Systems NC Learning NC Control Systems NC Signal Processing Architectures Devices Pattern Classifiers Support Vector Machines Fuzzy or Neuro-Fuzzy Systems Evolutionary Neural Networks Biological Neural Network Models Applications Others Important Dates: Conference Dates: 24-27 June 2008 Submission Deadline: 20 March 2008 Acceptance Notification: 20th April 2008 Publications: Expanded and revised versions of all accepted BICS2008 papers will be published in a follow-on Springer Book. For more details, contact the BICS 2008 Publications Chair: Dr. Amir Hussain (E-mail: ahu at cs.stir.ac.uk). ORGANIZED BY: Planning Division ICSC Interdisciplinary Research NAISO Natural and Artificial Intelligence Systems Organization www.icsc.ab.ca Canada BICS 2008 Co-Sponsors: IEEE UK & RI Computational Intelligence Society Chapter IEEE UK & RI Industry Applications Society Chapter Springer -- The University of Stirling is a university established in Scotland by charter at Stirling, FK9 4LA. Privileged/Confidential Information may be contained in this message. If you are not the addressee indicated in this message (or responsible for delivery of the message to such person), you may not disclose, copy or deliver this message to anyone and any action taken or omitted to be taken in reliance on it, is prohibited and may be unlawful. In such case, you should destroy this message and kindly notify the sender by reply email. Please advise immediately if you or your employer do not consent to Internet email for messages of this kind. From roman at cs.cas.cz Wed Mar 5 05:48:25 2008 From: roman at cs.cas.cz (roman@cs.cas.cz) Date: Wed, 5 Mar 2008 11:48:25 +0100 (CET) Subject: Connectionists: ICANN'08 deadline extended Message-ID: <1547.12.180.114.2.1204714105.squirrel@www.cs.cas.cz> ******************************************************************** ICANN 2008 EXTENDED SUBMISSION DEADLINE MARCH 10 2008 ******************************************************************** Dear Colleague Due to numerous requests we decided to extend the submission deadline for ICANN 2008 to March 10, 2008 for regular papers and to March 20, 2008 for papers intended for special sessions and workshops. Papers in LNCS style of maximal length 10 pages can be submitted at http://www.icann2008.org/submit The conference proceedings will be published in Springer's Lecture Notes in Computer Science series. ******************************************************************** The 18th International Conference on Artificial Neural Networks, ICANN 2008, will be held on September 3-6 at the Diplomat hotel, Prague, Czech Republic. ICANN - International Conference on Artificial Neural Networks is an annual conference organized since 1998 by the ENNS - European Neural Network Society in co-operation with the International Neural Network Society and the Japanese Neural Network Society and it is a premier event in all topics related to neural networks. ICANN 2008 welcomes contributions on the theory od neurocomputing, algorithms and applications. Papers can be either submitted as regular papers or to special sessions: * Coupling, Synchronies and Firing Patterns: from Cognition to Disease * Constructive Neural Networks or workshops: * New Trends in Self-organization and Optimization of Artificial Neural Networks * Adaptive Mechanisms of the Perception-Action Cycle For more information please visit http://www.icann2008.org Sincerely, Vera Kurkova Chair of the Program Committee of ICANN 2008 From steve at cns.bu.edu Wed Mar 5 12:57:35 2008 From: steve at cns.bu.edu (Stephen Grossberg) Date: Wed, 5 Mar 2008 12:57:35 -0500 Subject: Connectionists: temporal dynamics of decision-making during motion perception in the visual cortex Message-ID: The following article is now available at http://www.cns.bu.edu/Profiles/Grossberg : Grossberg, S. and Pilly, P. Temporal dynamics of decision-making during motion perception in the visual cortex. Vision Research, in press. ABSTRACT How does the brain make decisions? Speed and accuracy of perceptual decisions covary with certainty in the input, and correlate with the rate of evidence accumulation in parietal and frontal cortical "decision neurons." A biophysically realistic model of interactions within and between Retina/LGN and cortical areas V1, MT, MST, and LIP, gated by basal ganglia, simulates dynamic properties of decision-making in response to ambiguous visual motion stimuli used by Newsome, Shadlen, and colleagues in their neurophysiological experiments. The model clarifies how brain circuits that solve the aperture problem interact with a recurrent competitive network with self-normalizing choice properties to carry out probabilistic decisions in real time. Some scientists claim that perception and decision-making can be described using Bayesian inference or related general statistical ideas, that estimate the optimal interpretation of the stimulus given priors and likelihoods. However, such concepts do not propose the neocortical mechanisms that enable perception, and make decisions. The present model explains behavioral and neurophysiological decision-making data without an appeal to Bayesian concepts and, unlike other existing models of these data, generates perceptual representations and choice dynamics in response to the experimental visual stimuli. Quantitative model simulations include the time course of LIP neuronal dynamics, as well as behavioral accuracy and reaction time properties, during both correct and error trials at different levels of input ambiguity in both fixed duration and reaction time tasks. Model MT/MST interactions compute the global direction of random dot motion stimuli, while model LIP computes the stochastic perceptual decision that leads to a saccadic eye movement. Key words: motion perception; direction discrimination; decision-making; visual cortex; aperture problem; noise-saturation dilemma; recurrent competitive field; Bayesian inference; MT; MST; LIP From charlie.kemp at bme.gatech.edu Thu Mar 6 05:11:26 2008 From: charlie.kemp at bme.gatech.edu (Charlie Kemp) Date: Thu, 06 Mar 2008 05:11:26 -0500 Subject: Connectionists: ICDL 2008: Call for Papers (revised) Message-ID: <47CFC34E.10004@bme.gatech.edu> 7th International Conference on Development and Learning Asilomar Conference Center, Monterey, California August 9th-12th, 2008, http://www.icdl08.org/ Call for Papers The scope of development and learning covered by this conference includes perceptual, cognitive, behavioral, emotional and all other mental capabilities that are exhibited by humans, higher animals, artificial systems and robots. Investigations of the biological and computational mechanisms of mental development are expected to improve our understanding of the working of the whole range of mental capabilities in humans and to enable autonomous development of these highly complex capabilities by robots and other artificial systems. The International Conference on Development and Learning strives to bring together researchers in neuroscience, psychology, artificial intelligence and robotics and other related areas to encourage understanding and cross-fertilization of the latest ideas and results from the different disciplines. ICDL 2008 will accept two types of submissions: 1) Full six-page paper submissions. Accepted papers will be included in the conference proceedings and will be selected for either an oral presentation or as a featured poster presentation. Featured posters will have a 1 minute "teaser" presentation as part of the main conference session and will be showcased in the poster sessions. Authors of accepted 6-page papers (whether they are selected for oral or poster presentation) will have the OPTION of archiving their papers through IEEE Xplore. 2) One-page poster abstract submissions. To encourage late-breaking results or for work that is not sufficiently mature for a full paper, ICDL will accept 1-page abstracts. These submissions will NOT be included in the conference proceedings. Accepted abstracts will be presented during the evening poster sessions. Important dates: March 31 Full 6-page paper submissions due May 12 Notification for full papers (accept/reject) May 21 1-page poster abstracts due May 28 Notification for poster abstracts (accept/reject) June 2 Camera-ready papers due Plenary Speakers: * Richard Aslin, U. of Rochester * Terry Jernigan, UCSD * Andrew Ng, Stanford General Chairs: * Jay McClelland, Stanford * Juyang Weng, Michigan State Program Chairs: * Gedeon Deak, UCSD * Brian Scassellati, Yale Sponsored by: * IEEE Computational Intelligence Society * Cognitive Science Society For more information please check the conference web site: http://www.icdl08.org/ From acompte at clinic.ub.es Thu Mar 6 11:21:04 2008 From: acompte at clinic.ub.es (Albert Compte) Date: Thu, 06 Mar 2008 17:21:04 +0100 Subject: Connectionists: POSTDOCTORAL POSITION in THEORETICAL NEUROBIOLOGY in BARCELONA Message-ID: <1204820464.6795.32.camel@laptop> POSTDOCTORAL POSITION AVAILABLE IN THEORETICAL NEUROSCIENCE with Albert Compte, Laboratory for Theoretical Neurobiology of Cortical Circuits, IDIBAPS (Institute for Biomedical Research "August Pi i Sunyer", Barcelona, Spain): http://complab.fcrb.es In the laboratory, we focus our research on the exploration of the mechanisms that operate in the cerebral cortex during perceptual and cognitive processes, using computer and mathematical modelling. Projects cover a range of topics in dynamics of neural networks, and involve close interactions with collaborating experimental laboratories (neurophysiology, neuropharmacology, neuroimaging). The IDIBAPS is the largest biomedical research institute in Spain, and the presence of our lab represents a unique opportunity to bring closer computational approaches to clinical experimental problems. You can find a description of our research and publications in our webpage http://complab.fcrb.es We are currently seeking applicants for a project on the modeling of cognitive function (attention, working memory,...) and dysfunction (schizophrenia,...) with biophysically detailed multiple-area models. The project will involve psychophysical experimentation and, depending on candidate qualifications, fMRI experiments. The project involves close interaction with neuroimaging, neurophysiology and neuropharmacology labs. Candidates should have good analytical mathematical skills (Physics or similar) and simulation experience. Familiarity with neuroscience and neurophysiology is also highly valued. Neuroscientists are also welcome to apply if they have some experience in computer coding. The initial appointment is for 20 months, during which further competitive funding should be secured for further extensions. Salary is around 26.000 euros annually. Send your CV and a statement of goals to -- Albert Compte, PhD Theoretical Cortical Neurobiology Group IDIBAPS C/ Villarroel 170 08036 Barcelona Spain Telf. +34 93 227 5400 (ext. 4151) E-mail: acompte at clinic.ub.es Webpage: http://complab.fcrb.es From arjen.van.ooyen at falw.vu.nl Fri Mar 7 05:59:30 2008 From: arjen.van.ooyen at falw.vu.nl (Arjen van Ooyen) Date: Fri, 07 Mar 2008 11:59:30 +0100 Subject: Connectionists: Positions in Computational Neuroscience at CNCR, Amsterdam Message-ID: <47D12012.4040603@falw.vu.nl> Applications are invited for two research positions in the Neuroinformatics Group of the Center for Neurogenomics and Cognitive Research (CNCR), VU University Amsterdam. The positions are funded by a EU-FP7 grant for the Collaborative Large-scale Integrating Project Self-Constructing Computing Systems (SECO). Using a combined computational and experimental approach, the SECO project investigates the principles by which populations of real or artificial neurons can grow and assemble themselves into functioning circuits. The first 4-year project, for a postdoctoral researcher, is on the development of dendritic and axonal growth models. The aim is to create models for neuronal morphogenesis in which cells develop through growth cone migration and branching, and formation of synaptic connections in interaction with their environment. A major challenge is to find a balanced level of description of neuronal outgrowth based on local mechanisms and interactions in space and time that will be suitable for an algorithmic implementation. The models will be used to study the development of cortical and thalamic circuitry. The ideal candidate should combine a strong neurobiological interest and knowledge with a solid background in neuro-biophysics and extensive experience in computational modeling and computer programming. The second 4 (or 3)-year project, for a PhD student (or postdoctoral researcher), focuses on the reciprocal interactions between neuronal network structure and activity dynamics in developing neural circuits. Using computational models, we will explore the impact of activity-dependent plasticity rules on the evolution of developing neuronal networks under their own (spontaneous) firing activity. The research will be guided by the hypothesis that networks will evolve towards self-consistent states, in which firing patterns stabilizes the synaptic connectivity structure that also gives rise to these firing patterns. The ideal candidate should combine a strong neurobiological interest and knowledge with an excellent background in computational neuroscience and neuronal network research. Candidates of both projects will contribute significantly to the collaborative effort of the SECO consortium. For further information about these positions, please contact Dr. Arjen van Ooyen, arjen.van.ooyen at cncr.vu.nl, or Dr. Jaap van Pelt, jaap.van.pelt at cncr.vu.nl. Application letters including a CV, research experience, a short statement of research interests, and contact details of two referees should be sent by email to Dr. Arjen van Ooyen before the 1st of April 2008. -- Dr. Arjen van Ooyen Neuroinformatics Group Department of Experimental Neurophysiology Center for Neurogenomics and Cognitive Research VU University Amsterdam De Boelelaan 1085 1081 HV Amsterdam The Netherlands E-mail: arjen.van.ooyen at cncr.vu.nl Phone: +31.20.5987090 Fax: +31.20.5987112 Room: B-451 Web: http://www.bio.vu.nl/enf/vanooyen From remi.munos at inria.fr Fri Mar 7 10:37:28 2008 From: remi.munos at inria.fr (Remi Munos) Date: Fri, 7 Mar 2008 16:37:28 +0100 Subject: Connectionists: EWRL08 call for contributions Message-ID: <200803071637.28192.remi.munos@inria.fr> Please distribute to anyone who may be interested: (apologies for multiple postings) ************************************************************ 2nd Call for Contributions EUROPEAN WORKSHOP ON REINFORCEMENT LEARNING (EWRL) 2008 June 30 - July 3, 2008 INRIA Lille-Nord Europe, France http://ewrl08.futurs.inria.fr INFORMATION ----------- European Workshop on Reinforcement Learning (EWRL) is a (biennial) series of events that is being organized since 1994. To date, the sequential decision making problem with delayed rewards has been studied, under various guises, by various communities: machine learning, control, economics, applied mathematics, psychology and biology to name the foremost. EWRL'08, the eighth workshop in the series as well, aims to serve as a forum to discuss the current state-of-the-art and future research directions in this continuously growing field. We intend to make this an exciting event not only for the European RL community but also international researchers from related areas with many opportunities to share new knowledge and encourage collaborative work. We also hope to help the emergence of European projects in the 7th framework program that fall into the scope of RL. EWRL'08 is planned to be a theme oriented event in which each main theme will be allocated a half-day session including (i) an overview or tutorial, (ii) technical contributions in the form of long and short papers, followed by (iii) discussions. There will be two special sessions; a general discussion session entitled "Where are we heading? - Current and Future Trends in RL", and a demonstration session entitled "Real-life Applications of RL". Prof. Rich Sutton, University of Alberta, will also be our special guest. Topics of interest include but not limited to: * Exploration vs Exploitation Trade-off * (Function) Approximation in RL * Knowledge Representation in RL * Theorical RL (Convergence and performance bounds, Complexity issues, Sensitivity analysis) * Multi-Agent RL * Regret-minimization Algorithms in Games * Direct Policy Search and Policy Gradient Methods * Reward design and inverse RL * Bayesian vs Frequentist Approaches * RL and Statistical Learning * Metrics for Empirical Comparisons in RL * Reducing RL to Inference, Regression and Classification * RL to Sequence Prediction * RL from Biological and Psychological Perspectives More information about the event can be found at EWRL'08 web site http://ewrl08.futurs.inria.fr SCIENTIFIC COMMITTEE ------------------ * Peter Auer * Peter Dayan * Kurt Driessens * Alain Dutech * Yaakov Engel * Damien Ernst * Frederick Garcia * Mohammad Ghavamzadeh * Daniel Kudenko * Michail G. Lagoudakis * Pier Luca Lanzi * Francisco Melo * Ann Nowe * Martijn van Otterlo * Jan Peters * Olivier Pietquin * Pascal Poupart * Martin Riedmiller * Daniil Ryabko * R?gis Sabbadin * Bruno Scherrer * Olivier Sigaud * Rich Sutton * Csaba Szepesvari * Athanasios Vasilakos * Chris Watkins * Shimon Whiteson * Marco Wiering * Jeremy Wyatt * Martin Zinkevich EWRL'08 is organized by the team-project SequeL of INRIA Lille-Nord Europe. (http://sequel.futurs.inria.fr) IMPORTANT DATES --------------- Submission Deadline: April 10, 2008 (Extended) Notification of Acceptance: May 10, 2008 Workshop: June 30 - July 3, 2008 (The week before ICML'08, COLT'08 and UAI'08 in Helsinki) EWRL'08 is a FREE event, there won't be any registration fee. But, we kindly request you to complete a registration form for organizational purposes. Registration form will be online on April 1, 2008. Limited travel grants are available to help fund travel and accommodation for (PhD) students. Interested students should visit our web site and fill-in the application form until April 30, 2008. Please contact us for more information. SUBMISSION ---------- * Paper: Papers should be prepared in LNCS format and should not exceed 14 pages. We also encourage short papers (4-6 pages) from students that present ongoing research. A poster may be designed alongside a presentation. Posters will be exhibited during the workshop so as to help people interactions. After the workshop, a selection of papers will be published as a "Lecture Notes in Artificial Intelligence" volume by Springer. Papers submitted to other conferences can be submitted to EWRL'08, regardless of their acceptance in these conferences. However, only those that are copyright free are eligible for being published in the proceedings. We welcome papers that have been accepted to ICML 2008 (for presentation only); such papers are exempt from the reviewing process, and authors can submit either just the title, the abstract, or the article itself. Please check out EWRL'08 web site for more information about submission. * Tutorial: Please provide the title, speaker, abstract, and a plan/draft for the tutorial. An electronic version (pdf) of the presentation should be provided on the workshop website. It should be delivered at least a week beforehand. * Demonstration: Please provide the title and abstract of your demonstration, as well as any multimedia document that can illustrate it. LOCATION -------- The workshop will take place at IRCICA building, around the scientific campus of Lille, northern France. Lille, the third largest metropolitan area in France, lies on the Brussels-Paris-London connection and is easily accessible by high-speed TGV trains or by plane. More information can be found at the web site of Lille Tourist office (http://www.lilletourism.com). -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: message-footer.txt Url: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080307/0e6d5002/message-footer.txt From wahba at stat.wisc.edu Fri Mar 7 22:27:52 2008 From: wahba at stat.wisc.edu (Grace Wahba) Date: Fri, 7 Mar 2008 21:27:52 -0600 Subject: Connectionists: LASSO-Patternsearch paper Message-ID: <200803080327.m283RqNn022943@juno.stat.wisc.edu> Available at http://www.stat.wisc.edu/~wahba -> TRLIST W. Shi, G. Wahba, S. Wright, K. Lee, R. Klein and B. Klein. LASSO-Patternsearch Algorithm with Applications to Ophthalmology and Genomic Data " February 2008. To appear, Statistics and Its Interface(SII) The LASSO-Patternsearch algorithm is proposed to efficiently identify patterns of multiple dichotomous risk factors for outcomes of interest in demographic and genomic studies. The patterns considered are those that arise naturally from the log linear expansion of the multivariate Bernoulli density. The method is designed for the case where there is a possibly very large number of candidate patterns but it is believed that only a relatively small number are important. A LASSO is used to greatly reduce the number of candidate patterns, using a novel computational algorithm that can handle an extremely large number of unknowns simultaneously. The patterns surviving the LASSO are further pruned in the framework of (parametric) generalized linear models. A novel tuning procedure based on the GACV for Bernoulli outcomes, modified to act as a model selector, is used at both steps. We applied the method to myopia data from the population-based Beaver Dam Eye Study, exposing physiologically interesting interacting risk factors. We then applied the the method to data from a generative model of Rheumatoid Arthritis based on Problem 3 from the Genetic Analysis Workshop 15, successfully demonstrating its potential to efficiently recover higher order patterns from attribute vectors of length typical of genomic studies. From steve at cns.bu.edu Fri Mar 7 21:05:52 2008 From: steve at cns.bu.edu (Stephen Grossberg) Date: Fri, 7 Mar 2008 21:05:52 -0500 Subject: Connectionists: A Neural System for Natural Scene Classification Message-ID: The following article is now available at http://www.cns.bu.edu/Profiles/Grossberg : Grossberg, S. and Huang, T.-R. ARTSCENE: A Neural System for Natural Scene Classification. Journal of Vision, in press. ABSTRACT How do humans rapidly recognize a scene? How can neural models capture this biological competence to achieve state-of-the-art scene classification? The ARTSCENE neural system classifies natural scene photographs by using multiple spatial scales to efficiently accumulate evidence for gist and texture. ARTSCENE embodies a coarse-to-fine Texture Size Ranking Principle whereby spatial attention processes multiple scales of scenic information, from global gist to local textures, to learn and recognize scenic properties. The model can incrementally learn and rapidly predict scene identity by gist information alone, and then accumulate learned evidence from scenic textures to refine this hypothesis. The model shows how texture-fitting allocations of spatial attention, called attentional shrouds, can facilitate scene recognition, particularly when they include a border of adjacent textures. Using grid gist plus three shroud textures on a benchmark photograph dataset, ARTSCENE discriminates 4 landscape scene categories (coast, forest, mountain and countryside) with up to 91.85% correct on a test set, outperforms alternative models in the literature which use biologically implausible computations, and outperforms component systems that use either gist or texture information alone. KEYWORDS: scene classification; gist; texture; spatial attention; coarse-to-fine processing; attentional shroud; multiple-scale processing; ARTMAP From georgios.theocharous at intel.com Fri Mar 7 17:42:51 2008 From: georgios.theocharous at intel.com (Theocharous, Georgios) Date: Fri, 7 Mar 2008 14:42:51 -0800 Subject: Connectionists: machine learning intership at Intel Reseacrh Santa Clara Message-ID: <0FC2A0D7FE451749B331A673BFE35D430153C564@orsmsx423.amr.corp.intel.com> Intel Research, Santa Clara, CA An internship position is available for a Ph.D. student in the areas of machine learning, human activity recognition, decision making under uncertainty and online learning with experts. At Intel research, a project titled "Everyday Sensing and Perception" (ESP), which is composed of 12 research scientists, is chartered at developing technology for recognizing everyday human activity context with high accuracy and most of the time. An integral part of the project is context guidance, which we have termed as "Interaction Planning". Interaction planning systems interact with humans over a period of time to help them achieve desired goals. Such systems could be a virtual teacher/coach, a task assistant, or an entertainer. Depending on the user's level of expertise/familiarity, attentiveness, willingness to reach her goals, preferred interaction style (e.g., hands-off vs. hands-on), cognitive capacities (e.g. child vs. adult vs. senile), perceived relationship (e.g. teacher vs. entertainer), level of urgency (e.g. tight schedule vs. relaxed), the system picks different content, frequency and tones for message delivery. A conventional approach to the problem is to model users explicitly at this level of detail. In practice, detailed modeling may not be feasible or tractable. The focus of the research is to develop techniques that achieve the quality of models that represent humans mental state in great detail while avoiding the modeling overhead and slowdown of such models. The desired qualities of an applicant are: * Experience in implementing real life machine learning systems. * Expert in decision making approaches under uncertainty, such as partially observable Markov decision process (POMDPs). * Knowledgeable in online learning with expert advice algorithms. * Expert with learning and inference in graphical models such as DBNs. * Classical machine learning expertise. Internships are expected to be at least 10-12 weeks long during the summer months. The successful candidate will participate in implementing a real life interaction planning system , perform experiments, develop new algorithms and theory for interaction planning, and finally submit a paper to one of the premier AI and machine learning conferences. To apply: * Request two short reference letters from your advisor or from someone you have interned with before. * Email your CV, the reference letters and the dates you will be able to join to: georgios.theocharous at intel.com From emmanuel.vincent at irisa.fr Fri Mar 7 12:08:11 2008 From: emmanuel.vincent at irisa.fr (Emmanuel Vincent) Date: Fri, 07 Mar 2008 18:08:11 +0100 Subject: Connectionists: PhD offers on probabilistic audio modeling Message-ID: <47D1767B.6010904@irisa.fr> Dear list, Please forward this offer to anyone who might be interested. The METISS group at IRISA, Rennes, France is seeking candidates for a PhD thesis on either of the following subjects: "Adaptive spectral and spatial models for audio source separation" and "Probabilistic object-based representation of audio signals, applied to high-level music description and classification". Details are available at http://www.inria.fr/travailler/mrted/en/doc/details.html?nPostingTargetID=5495 http://www.inria.fr/travailler/mrted/en/doc/details.html?nPostingTargetID=5557 Applications should be made online at the above addresses before May 15, 2008. Best regards, -- Emmanuel Vincent METISS Project-Team IRISA-INRIA Campus de Beaulieu, 35042 Rennes cedex, France Phone: +332 9984 2269 - Fax: +332 9984 7171 Web: http://www.irisa.fr/metiss/members/evincent/ From petkov at cs.rug.nl Fri Mar 7 13:23:40 2008 From: petkov at cs.rug.nl (Nicolai Petkov) Date: Fri, 7 Mar 2008 19:23:40 +0100 Subject: Connectionists: full-scholarship PhD student position in Biologically motivated object recognition Message-ID: <003601c88080$5e1a99f0$af337d81@iwi175> A full-scholarship PhD student position in Computer Science at a leading European university. http://www.cs.rug.nl/~petkov/vacancies/2007PhDstudent_shape.html PhD student position in Biologically motivated object recognition Institute of Mathematics and Computing Science University of Groningen Topic of research The objective of the project is to develop an object recognition technique that is motivated by the function of the visual cortex. Major aspects are representation and learning. Type and level of the position This is a temporary research position at the level of a PhD student for a period of maximum four years. The tuition fees will be waived and the student will receive a full scholarship. In this period the student will follow relevant courses and prepare and defend a PhD thesis. The position is embedded in the research group Intelligent Systems. The tradition of the group is that PhD theses are based on excellent papers in high imact journals so that our PhD graduates have a very strong competative position on the academic market. Thesis director and supervisor will be professor N. Petkov. The University of Groningen is a leading European research university. Our requirements on your qualifications You are a university graduate (at the level of diploma or master of science level) in one of the following disciplines: computer science, artificial intelligence, computational neuroscience, electrical engineering, biophysics, physics. You have a demonstrated interest in the neurosciences. You have an excellent academic record (GPA) and belong to the top 5% of the graduates of your year and preferrably have a graduation with a distinction such as honors or cum laude. You are fluent in English language and able to write scientific articles and reports (to be proven by your graduation thesis or another comparable report or co-authorship of published scientific articles). How to apply Send the following information: 1) an application letter with a CV, 2) a specification of GPA and transcript of records, 3) an indication of your position in the class and year (e.g. 1st in a class of 20), 4) evidence of excellence (e.g. graduation with honors) and a list of relevant awards, 5) proofs of involvement in research (e.g. co-authorship of scientific articles), 6) a description of your ideas for research in the specified area, 7) names and email addresses of three scientists (typically your former professors) who can give a reference for you. to prof.dr. Nicolai Petkov (petkov at cs dot rug dot nl). Applicants will be asked to do a short assignment in order to demonstrate their research abilities. The position will be open until a suitable candidate is found. From dancoisne at bccn.uni-freiburg.de Mon Mar 10 10:40:31 2008 From: dancoisne at bccn.uni-freiburg.de (Florence Dancoisne) Date: Mon, 10 Mar 2008 15:40:31 +0100 Subject: Connectionists: 13th Advanced Course in Computational Neuroscience - final announcement Message-ID: <47D5485F.6000706@bccn.uni-freiburg.de> 13th ADVANCED COURSE IN COMPUTATIONAL NEUROSCIENCE (A Bernstein/Gatsby Neuroscience School) Final Announcement August 4th - 29th, 2008 Freiburg, Germany DIRECTORS: * Israel Nelken (Hebrew University, Jerusalem, Israel) * Nicolas Brunel (CNRS Paris) * John Rinzel (NYU, New York, USA) * Peter Latham (University College London, UK) LOCAL ORGANIZER: * Florence Dancoisne (Bernstein Center for Computational Neuroscience Freiburg) After three years in Arcachon (France), the Advanced Course in Computational Neuroscience will be held in Freiburg in Breisgau (Germany) this year for its 13th edition, and until 2010. The Advanced Course in Computational Neuroscience is for advanced graduate students and postdoctoral fellows who are interested in learning the essentials of the field. The course has two complementary parts. Mornings are devoted to lectures given by distinguished international faculty on topics across the breadth of experimental and computational neuroscience. During the rest of the day, students are given practical training in the art and practice of neural modelling, by pursuing a project of their choosing under the close supervision of expert tutors. The first week of the course introduces students to essential neurobiological concepts and to the most important techniques in modelling single cells, networks and neural systems. Students learn how to solve their research problems using software packages such as MATLAB, NEST, NEURON, XPP, etc. During the following three weeks the lectures cover specific brain areas and functions. Topics range from modelling single cells and subcellular processes through the simulation of simple circuits, large neuronal networks and system level models of the brain. The course ends with project presentations by the students. The course is designed for advanced graduate students and postdoctoral fellows from a variety of disciplines, including neuroscience, physics, electrical engineering, computer science, mathematics and psychology. Students are expected to have a keen interest and basic background in neurobiology as well as some computer experience. Students of any nationality can apply. A maximum of 30 students will be accepted. The fee for the course will be EUR 500; this will cover tuition, lodging, breakfast and dinner. There will be a limited number of course fee scholarships, and travel stipends available for students who need financial help for attending the course. We specifically encourage applications from researchers who work in the developing world. These students will be selected according to the normal submission procedure. Applications, including a description of the target project must be submitted electronically (see below) and will need to be accompanied by the names and email details of two referees who have agreed to furnish references. Applicants will need to ensure that their referees have submitted their references. Applications will be assessed by a committee, with selection being based on the following criteria: the scientific quality of the candidate (CV) and of the project, the recommendation letters, and evidence that the course will afford substantial benefit to the candidate. Please apply electronically using a web browser. More information and access to the application database: http://www.neuroinf.org/courses/EUCOURSE/F08/index.shtml Contact address: * Fiona Siegfried Bernstein Center for Computational Neuroscience Freiburg Albert-Ludwigs-Universitat Freiburg Hansastrasse 9A 79104 Freiburg Germany * mail: siegfried at bccn.uni-freiburg.de Application deadline: March 28th, 2008 Deadline for letters of recommendation: March 28th, 2008 Notification of results: April 25th, 2008 confirmed FACULTY: Ad Aertsen, U. Freiburg, Germany Amos Arieli, Weizmann Institute, Israel Jeff Beck, U. of Rochester, USA Nathaniel Daw, NYU, USA Erik De Schutter, OIST, Japan Alain Destexhe, CNRS Gif, France Wulfram Gerstner, EFPL, Switzerland Marc-Oliver Gewaltig, Honda, Germany Zhaoping Li, UCL, UK David Hansel, CNRS Paris, France Yael Niv, Princeton, USA Stefano Panzeri, U. of Manchester, UK Jonathan Pillow, UCL, UK Yifat Prut, Hebrew U. Israel Yasser Roudi, UCL, UK Idan Segev, Hebrew U., Israel Alex Thomson, UL, UK Mark Van Rossum, U. of Edinburgh, UK confirmed TUTORS Janet Best, Ohio State, USA Hermann Cuntz, UCL, UK Moritz Helias, U. Freiburg, Germany Alex Lerchner, UCL, UK Tim Vogels, Columbia, USA SYSTEM ADMINISTRATOR Bernd Wiebelt, U. Freiburg, Germany -- Florence Dancoisne Bernstein Center for Computational Neuroscience Freiburg Administrative Coordinator Hansastr. 9A D-79104 Freiburg http://www.bccn.uni-freiburg.de phone: + 49 761 203 9314 fax: + 49 761 203 9559 From nips2008publicity at gmail.com Sun Mar 9 18:49:23 2008 From: nips2008publicity at gmail.com (Antonio Torralba) Date: Sun, 9 Mar 2008 18:49:23 -0400 Subject: Connectionists: NIPS'2008 preliminary call for papers Message-ID: NIPS*2008 PRELIMINARY CALL FOR PAPERS Deadline for Paper Submissions: June 6, 2008, 23:59 Universal Standard Time (4:59pm Pacific Daylight Time). Submissions are solicited for the Twenty Second Annual meeting of an interdisciplinary Conference (December 8-11) that brings together researchers interested in all aspects of neural and statistical processing and computation. The Conference will include invited talks as well as oral and poster presentations of refereed papers. It is single track and highly selective. Preceding the main Conference will be one day of Tutorial (December 7), and following will be two days of Workshops at Whistler/Blackcomb ski resort (December 12-13). Submissions: Papers are solicited in all areas of neural information processing and statistical learning, including (but not limited to): * Algorithms and Architectures: statistical learning algorithms, neural networks, kernel methods, graphical models, Gaussian processes, dimensionality reduction and manifold learning, model selection, combinatorial optimization, relational learning. * Applications: innovative applications or fielded systems that use machine learning, including systems for time series prediction, bioinformatics, text/web analysis, multimedia processing, and robotics. * Brain Imaging: neuroimaging, cognitive neuroscience, EEG (electroencephalogram), ERP (event related potentials), MEG (magnetoencephalogram), fMRI (functional magnetic resonance imaging), brain mapping, brain segmentation, brain computer interfaces. * Cognitive Science and Artificial Intelligence: theoretical, computational, or experimental studies of perception, psychophysics, human or animal learning, memory, reasoning, problem solving, natural language processing, and neuropsychology. * Control and Reinforcement Learning: decision and control, exploration, planning, navigation, Markov decision processes, game-playing, multi-agent coordination, computational models of classical and operant conditioning. * Hardware Technologies: analog and digital VLSI, neuromorphic engineering, computational sensors and actuators, microrobotics, bioMEMS, neural prostheses, photonics, molecular and quantum computing. * Learning Theory: generalization, regularization and model selection, Bayesian learning, spaces of functions and kernels, statistical physics of learning, online learning and competitive analysis, hardness of learning and approximations, large deviations and asymptotic analysis, information theory. * Neuroscience: theoretical and experimental studies of processing and transmission of information in biological neurons and networks, including spike train generation, synaptic modulation, plasticity and adaptation. * Speech and Signal Processing: recognition, coding, synthesis, denoising, segmentation, source separation, auditory perception, psychoacoustics, dynamical systems, recurrent networks, Language Models, Dynamic and Temporal models. * Visual Processing: biological and machine vision, image processing and coding, segmentation, object detection and recognition, motion detection and tracking, visual psychophysics, visual scene analysis and interpretation. Evaluation Criteria: Submissions will be refereed on the basis of technical quality, novelty, potential impact, and clarity. Papers that balance new algorithmic contributions with a more applied focus are particularly encouraged. These include papers that contain a substantial evaluation on real-world problems, or papers that combine results on novel applications with analysis of their relevance from a machine learning perspective. We would also like to encourage submissions by authors who are new to NIPS. Submission Instructions: all submissions will be made electronically at http://nips2008.confmaster.net. Submissions must be in PDF format. As in previous years, reviewing will be double-blind: the reviewers will not know the identities of the authors. Papers will be limited to 8 pages, including figures and references, in the NIPS style. Complete submission and formatting instructions, including style files, can be found at the NIPS website: http://nips.cc. Electronic submissions will be accepted until midnight June 6, 2008, Universal Standard Time (5pm Pacific Daylight Time). There will be an opportunity after the meeting to revise accepted manuscripts. Demonstrations: There is a separate Demonstration track at NIPS. Authors wishing to submit to the Demonstration track should consult the Call for Demonstrations (coming soon). Workshops: The workshops will be held at Whistler/Blackcomb ski resort from December 12-13. The upcoming workshop proposal will provide details. Program Committee: Jean-Yves Audibert (Ecole Nationale des Ponts et Chauss?es) Francis Bach (INRIA - Ecole Normale Sup?rieure) Yoshua Bengio (Universit? de Montr?al) [Co-Chair] Kristin Bennett (Rensselaer Polytechnic Institute) Michael Bowling (University of Alberta) Aaron Courville (Universit? de Montr?al) Koby Crammer (University of Pennsylvania) Sanjoy Dasgupta (University of California, San Diego) Nathaniel Daw (New York University) Eleazar Eskin (Univerisity of California, Los Angeles) David Fleet (University of Toronto) Paolo Frasconi (Universit? di Firenze) Arthur Gretton (Max Planck Institute) Tony Jebara (Columbia University) Chris Manning (Stanford University) Ron Meir (Technion) Noboru Murata (Waseda University) Erkki Oja (Helsinki University of Technology) Doina Precup (McGill University) Stefan Schaal (University of Southern California) Dale Schuurmans (University of Alberta) [Co-Chair] Fei Sha (Yahoo! Research) Alan Stocker (New York University) Ingo Steinwart (Los Alamos National Laboratory) Erik Sudderth (University of California, Berkeley) Yee-Whye Teh (University College London) Antonio Torralba (Massachusetts Institute of Technology) Larry Wasserman (Carnegie Mellon University) Max Welling (University of California, Irvine) From S.Gielen at science.ru.nl Tue Mar 11 04:46:38 2008 From: S.Gielen at science.ru.nl (Stan Gielen) Date: Tue, 11 Mar 2008 09:46:38 +0100 Subject: Connectionists: Vacancy for full-professor in NeuroInformatics/Computational Neuroscience Message-ID: <47D646EE.3090004@science.ru.nl> The Radboud University Nijmegen considers Cognitive Neuroscience as one of its prime topics of research. For more information about the research activities, we refer to - the Donders Centre for Cognitive NeuroImaging (http://www.ru.nl/fcdonders/) - the newly established Donders Centre for Neuroscience (www.ru.nl/dcn ) - the Nijmegen Institute for Cognition and Information (http://www.ru.nl/socialewetenschappen/nici/) The Radboud University Nijmegen is looking for a *Full Professor in NeuroInformatics/Computational Neuroscience. * * * The candidate will have the opportunity to establish his/her own group with tenured scientists, post docs and PhD students. A job description is added as an attachment to this e-mail. Further information about the position can be obtained from the Director of the Research Institute, prof. dr. C. Gielen, tel. +31 24 3614244 or S.Gielen at science.ru.nl -- Prof. dr. C. Gielen Dept. of Biophysics Radboud University Nijmegen Geert Grooteplein 21 6525 EZ Nijmegen The Netherlands e-mail : S.Gielen at science.ru.nl tel.: 0031 (0)24 3614242 www : http://www.mbfys.ru.nl/~stan/ From juergen at idsia.ch Tue Mar 11 04:25:46 2008 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Tue, 11 Mar 2008 09:25:46 +0100 Subject: Connectionists: Postdoc at the Swiss AI lab IDSIA - seq2008 Message-ID: <0a9e6e92e3063d80e2d50aaf78c0de64@idsia.ch> We are seeking an outstanding postdoc in the field of machine learning, with experience / interest in at least some of the following topics: learning algorithms for sequence processing, program learning, recurrent neural networks (RNN), hidden Markov models, statistical / Bayesian approaches, algorithmic information theory, artificial evolution, in particular RNN evolution, recurrent support vector machines, etc. Goal: to advance the state of the art in learning algorithms for sequence processing, and to solve challenging learning tasks involving dynamically changing inputs, such as time series prediction, recognition of complex objects in the sensory input stream of virtual or real robots, etc. Salary: ~ SFR 72,000 per year ~ US$ 70,000 (7 March 2008) Start: now or soon To apply, please follow the instructions under http://www.idsia.ch/~juergen/seq2008.html Juergen Schmidhuber -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 2415 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080311/72a23354/smime.bin From hitzler at aifb.uni-karlsruhe.de Mon Mar 10 10:25:03 2008 From: hitzler at aifb.uni-karlsruhe.de (Pascal Hitzler) Date: Mon, 10 Mar 2008 15:25:03 +0100 Subject: Connectionists: CfP Journal Special Issue on Recurrent Neural Networks Message-ID: <47D544BF.1040005@aifb.uni-karlsruhe.de> Call for Papers: Journal Special Issue on == Perspectives and Challenges for Recurrent Neural Networks == Guest Editors: Marco Gori, Barbara Hammer, Pascal Hitzler, Guenther Palm Special issue of the Elsevier Journal of Algorithms in Cognition, Informatics and Logic http://www.elsevier.com/wps/find/journaldescription.cws_home/622851/description = SCOPE = Recurrent neural networks (RNNs) enable flexible machine learning tools which can directly process spatiotemporal and other structured data and which offer a rich dynamic repertoire as time dependent systems. They promise to be efficient signal-processing models which are biologically plausible and optimally suited for a wide range of industrial applications on the one hand, and an explanation of cognitive phenomena of the human brain on the other hand. Despite these facts, however, the design of efficient training methods for RNNs as well as their mathematical investigation with respect to reliable information representation and generalization abilities when dealing with complex data structures is still a challenge. It has led to diverse approaches and architectures including echo and liquid-state-machines, long short term memory, recursive and graph networks, core neuro-symbolic integration, etc. Interestingly, very heterogeneous domains are included, such as logic, chaotic systems, and biological networks. The aim of the special issue is to bring together recent work developed in the field of recurrent information processing, which bridges the gap between different approaches and which sheds some light on canonical solutions or principled problems which occur in the context of recursive information processing when considered across the disciplines. = TOPICS = We particularly encourage submissions connected to the following non-exhaustive list of topics: - new learning paradigms of RNNs such as unsupervised learning or reservoire learning - biologically plausible methods - integration of RNNs and symbolic reasoning - universal approaches for general data structures such as sets or graphs - methods which address the generalization ability of RNNs - challenging applications which have the potential to be benchmark problems - visionary papers concerning the future of RNNs = SUBMISSIONS = Deadline for submissions is 18th of July, 2008. Submissions shall follow the guidelines laid out for the Journal of Algorithms in Cognition, Informatics and Logic, which can be found under . Submissions shall be sent as pdf to Pascal Hitzler, hitzler at aifb.uni-karlsruhe.de = EDITORIAL BOARD = Guilherme da Alencar Barreto, Universidade Federal do Ceara, Brasil Monica Bianchini, University of Siena, Italy Howard Blair, Syracuse University, USA Hendrik Blockeel, KU Leuven, Belgium Mikael Boden, University of Queensland, Australia Matthew Cook, ETH Zuerich, Switzerland Artur d'Avila Garcez, City University London, UK Luc de Raedt, KU Leuven, Belgium Steffen Hoelldobler, TU Dresden, Germany Herbert Jaeger, Jacobs University Bremen, Germany Stefan C. Kremer, University of Guleph, Canada Kai-Uwe Kuehnberger, University of Osnabrueck, Germany Alessio Micheli, University of Pisa, Italy Barak Pearlmutter, NUI Maynooth, Ireland Juergen Schmidhuber, TU Munich, Germany Alessandro Sperduti, University of Padova, Italy Jochen Steil, University of Bielefeld, Germany Peter Tino, University of Bermingham, UK Edmondo Trentin, University of Siena, Italy Thomas Wennekers, University of Plymouth, UK This Call for Papers is available online under http://www.neural-symbolic.org/RNN_CfP.txt -- 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 jpineau at cs.mcgill.ca Sun Mar 9 21:31:02 2008 From: jpineau at cs.mcgill.ca (Joelle Pineau) Date: Sun, 9 Mar 2008 21:31:02 -0400 (EDT) Subject: Connectionists: Call for papers: AAAI 2008 Workshop on Advancements in POMDP Solvers References: In-Reply-To: Message-ID: <58846.76.74.195.108.1205112662.squirrel@mail.cs.mcgill.ca> AAAI 2008 Workshop on Advancements in POMDP Solvers http://research.microsoft.com/~guyshani/AAAIWorkshop/Main.html Description: Over the past decade, much advancement was achieved in the field of POMDP solvers. The size of POMDPs that solvers can handle has increased by orders of magnitude. Solvers developed ten years ago were hardly able to handle more than 10 states, while modern solvers scale up to models with millions of states. New techniques compute approximate policies of manageable complexity, thus allowing us to handle larger and more complicated POMDPs. This advancement was achieved by a few orthogonal approaches - the use of point-based techniques, finite-state controllers, efficient model representations, model compression techniques, hierarchical decompositions, inference-based techniques, and improved algorithms for online search. Topics: This workshop is designed to bring together researchers currently working on POMDP solvers, as well as those with complimentary interests. A main objective is to identify remaining barriers preventing full-scale POMDP deployment, as well as key scientific opportunities. The workshop is also intended to introduce new people to the current advancements in POMDP solvers. Format: The workshop will begin with a set of short tutorials over various advancements in POMDP solvers: 1.Point based algorithms - insights into the point-based approach. Overview of the basic operations and the various approaches. Introduction to relevant algorithms: PBVI, Perseus, HSVI, FSVI. 2.Compression and efficient representation - an overview of various techniques for compressing POMDPs, such as belief state compression and linear compression. A description of efficient descriptions for factored POMDPs such as Algebraic Decision Diagrams (ADDs). 3.Online belief space search - overview of various algorithms and new advancements in online belief space search. 4.Policy iteration algorithms - using techniques such as finite state controllers to efficiently learn policies directly, without computing a value function. The workshop will continue by a set of short presentations of work in the field of POMDP solvers. Accepted papers will have 15 minutes for presentation of the main contributions. We will then follow up by a poster presentation of all accepted papers that will allow for an extended discussion with the authors of the papers. Submissions: We invite researchers in the field to submit papers discussing: *New methods for solving POMDPs. *Improvements of existing solvers. *Empirical studies that illuminate the difficulties and opportunities in POMDP solvers. *Complimentary methods for optimal control under partial observability. *Studies of implementations of POMDP solvers to real life problems. Submissions should be 6 pages long and follow the standard AAAI guidelines (http://www.aaai.org/Publications/Author/author.php). We also welcome submissions of papers that were previously published in conferences and journals. Authors of accepted papers must sign the distribution permission form (http://www.aaai.org/Publications/Author/distribute-permission.pdf). A PDF or PS version of the paper should be submitted by email to guyshani at microsoft.com. Schedule: *Submission deadline: April 7, 2008 *Notification date: April 21, 2008 *Accepted paper submission deadline: May 5, 2008 Organizing Committee: *Joelle Pineau, McGill University, jpineau at cs.mcgill.ca *Pascal Poupart, University of Waterloo, ppoupart at cs.uwaterloo.ca *Guy Shani, Microsoft Research, guyshani at microsoft.com, 425-7051561 *Trey Smith, Carnegie Mellon University West / NASA Ames Research Center, trey.smith at west.cmu.edu From j.sitte at qut.edu.au Tue Mar 11 08:20:20 2008 From: j.sitte at qut.edu.au (Joaquin Sitte) Date: Tue, 11 Mar 2008 22:20:20 +1000 Subject: Connectionists: Reminder: Deadline approaching Speciai Issue: Dynamics and learning in Recurrent Neural Networks Message-ID: <4FA7C33AA4AE7B47AD990ABF50DBF4090C91A62569@QUTEXMBX01.qut.edu.au> Deadline approaching! Special issue of Advances in Artificial Neural Systems on http://www.hindawi.com/journals/aans Dynamics and Learning in Recurrent Neural Networks Advances in Artificial Neural Systems welcomes original research papers and authorative reviews for a special issue on Dynamics and Learning in Recurrent Neural Networks scheduled for publication in October 2008. Deadline for submissions: 1 April 2008. First round of review: 1 July 2008 Tentative Publication: 1 October 2008 Feedback connections are ubiquitous in natural neural system, especially within the layers of the neocortex. From mathematical models of networks of simple neural elements with feedback connections we know that these can in principle reproduce the behaviour of almost any dynamical system. These networks can exhibit from limit point to strange attractor dynamics and have been found to be able to perform useful functions such as associative memory, pattern recognition, optimization, central pattern generators and more. While feedforward neural Networks are well understood, our understanding of recurrent neural network is still rather rudimentary. This special issue of Advances in Artificial Neural System will highlight the current state of the knowledge on how to configure the connectivity of the artificial neural networks to produce a desired dynamic behaviour. In this context, the discovery of learning methods, understood as the automatic configuration driven by sensor inputs, is a primordial objective recurrent neural network research. The scope of his special issue includes discrete and continuous state networks in simulation and hardware realization. Specific topics include, but are not limited to, Attractor Networks, Cooperative-Competitive networks, Recurrent Support Vector Machines, Echo-state and Liquid-state networks, Bayesian Inference and Belief Networks, Patchy cortical networks, Spike-based plasticity in recurrent networks and neuromorphic implementations of recurrent networks. Dr. Joaquin Sitte, Associate Professor. School of Software Engineering and Data Communication Faculty of Information Technology Queensland University of Technology GPO Box 2434, Brisbane, Q 4001 Australia Phone +61 7 3138 2755 Fax +61 7 3138 1801 e-mail: j.sitte at qut.edu.au homepage http://www.fit.qut.edu.au/~sitte Dr. Joaquin Sitte, Associate Professor. Faculty of Information Technology Queensland University of Technology GPO Box 2434, Brisbane, Q 4001 Australia Phone +61 7 3138 2755 Fax +61 7 3138 1801 e-mail: j.sitte at qut.edu.au homepage http://www.fit.qut.edu.au/~sitte -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080311/b8816bb1/attachment.html From cardoso at bcos.uni-freiburg.de Wed Mar 19 08:40:39 2008 From: cardoso at bcos.uni-freiburg.de (Simone Cardoso de Oliveira) Date: Wed, 19 Mar 2008 13:40:39 +0100 Subject: Connectionists: Bernstein Award 2008, Funding for Independent Research Groups in the are of Computational Neuroscience, in Germany Message-ID: <47E109C7.4020100@bcos.uni-freiburg.de> Dear connectionists, within the Bernstein Network for Computational Neuroscience, the German Federal Ministry of of Education and Research (BMBF) has once more announced a call for proposals for the 'Bernstein Award 2008'. This grant allows young researchers of any nationality to get fundig (up to 1.25 M?, over a period of 5 years) for their own, independent research group, to be installed at any German University or research institution. Please find the complete announcement on the webpage: http://www.bernstein-zentren.de/en/551.php or see below. ------------------------------------------------------------------------------------------------------------------------------------ Announcement of the Federal Ministry of Education and Research (BMBF) from Regulations for the "Bernstein Award" Funding Initiative within the framework of the National Network for Computational Neuroscience 14.11.2007 1. Funding purpose and legal basis 1.1 Funding purpose Computational Neuroscience is a very dynamic research discipline in the field of the neurosciences. With its interdisciplinary approach and systematic cooperation between biology, medicine, physics, mathematics and computer science, this research area promises the accelerated generation of new findings as well as major impetus for application-oriented fields such as health research, information technology and education. The BMBF has established four "Bernstein Centres for Computational Neuroscience" (http://www.bernstein-zentren.de/en/index.php) within the framework of its "National Network for Computational Neuroscience" funding activity. These high-performing centres are the main structural elements of the National Network. This means that a new structure has been created which is necessary for developing a new quality in Computational Neuroscience, for networking this research area and for promoting its international visibility. It is particularly important to attract excellent young researchers in order to lastingly establish and strengthen Computational Neuroscience as a field of research in Germany. The Bernstein Centres contribute substantially to achieving this goal with their concepts for supporting junior researchers by means of study programmes and postgraduate research groups. But there is also a great need to attract and support young researchers at the level of research group leaders, where they will be able to develop their own research profiles and attain greater scientific independence by establishing and heading their own junior research groups. The "Bernstein Award" funding activity aims to support research projects in the field of Computational Neuroscience, thus enabling excellent young researchers working in this field to implement innovative project ideas in Computational Neuroscience in the German research environment. This is intended to promote the academic qualification of these outstanding young researchers, among other things. The projects supported under the "Bernstein Award" initiative will become an integral part of the National Network for Computational Neuroscience and give new impetus to scientific activities. As announced in the funding regulations for the "Bernstein Award" initiative of 21 March 2006, the Federal Ministry of Education and Research intends to support one research project under this initiative in 2008. 1.2. Legal basis Project grants can be awarded in accordance with the present funding regulations, the BMBF's standard terms and conditions for grants on expenditure or cost basis and the administrative regulations under section 44 of the Federal Budget Code (BHO). Applicants have no legal claim to a grant. The grant-awarding agency will decide freely after due assessment of the circumstances within the framework of the budget funds available. 2. Object of funding Funding is provided for research projects which have been designed by German or non-German young scientists (post-docs) and which will be carried out by these young scientists at a German research institution. Researchers are expected to furnish evidence of extraordinary scientific achievements in the field of Computational Neuroscience. By realizing research projects which they have designed and will supervise themselves and by establishing their own junior research group, the young project leaders are to be given an opportunity to conduct independent research. The funded research projects are to be conducted at a German university or scientific institution (see section 3 below) within or outside the Bernstein Centres. The funded projects of the young researchers are to be integrated in the National Network for Computational Neuroscience in order to strengthen this network. The young researchers should therefore participate in the annual workshops and status seminars of the Bernstein Centres. The purpose of the status seminars is to facilitate exchanges on the progress and results of research and to promote networking between the Bernstein Centres. 3. Grant recipients Research proposals may be submitted by institutions of higher education and non-university research institutions based in Germany. Research institutions which receive joint basic funding from the Federal Government and the L?nder can only be awarded project funding to cover their additional expenditure under certain conditions. 4. Prerequisites for funding Funding under the "Bernstein Award" initiative is only provided for innovative research projects which have been designed by outstanding post-docs and will be conducted by them at a university or non-university research institution in Germany (see sections 2 and 3 above). A project will only be eligible for funding if the university or research institution concerned employs the young researcher during the funding period. Furthermore, the host institution is expected to provide the working facilities required for carrying out the project (basic equipment in terms of laboratory space and other infrastructure) and to support the young researcher in all matters. A statement made to that effect by the host institution must be included with the project outline to be submitted in accordance with section 7.2.1 below. In their own interest, applicants should familiarize themselves with the EU's Research Framework Programme in the context of the planned national project. They should check whether the planned project includes specific European components which make it eligible for exclusive EU funding. Applicants should also examine whether a supplementary application for funding can be submitted to the EU in the context of the planned national project. Applicants should briefly state the results of these investigations in their national application 5. Type, scope and rates of funding Project funding may be awarded in the form of non-repayable grants. Grants for universities, research and science institutions and similar establishments will be calculated on the basis of the project-related expenditure eligible for funding (grants for Helmholtz centres and the Fraunhofer Gesellschaft (FhG) will be calculated on the basis of the project-related costs eligible for funding); in individual cases, up to 100 per cent of this expenditure/these costs can be funded. The European Commission's Community Framework for State Aid for Research and Development must be taken into account when fixing the rates of funding. The Community Framework allows differentiated rules on extra percentage points for collaborative projects proposed by applicants from the new German L?nder and for small and medium-sized enterprises (SMEs), which may result in a higher rate of funding. Under the "Bernstein Award" initiative, funding will be provided for one research project per year to the extent that this is possible within the confines of relevant medium-term fiscal planning. The maximum funding period for each individual project is five years. Funding for each individual project can amount to up to ?1.25 million over the entire project period. During the project period, funding can be provided for the salary of the young project leader (up to salary group E14 TV?D or Ib BAT), for up to two positions for further scientific staff (E13 TV?D or IIa BAT), and for the required technical personnel in accordance with the relevant collective agreements. Funding cannot be provided for posts which are financed from public funds. Equipment and investment costs will be reimbursed in accordance with the other terms and conditions which are applicable (see sections 6 and 7 below, for example). 6. Other terms and conditions for awarding funds The Auxiliary Terms and Conditions for Funds Provided by the BMBF to Commercial Companies for Research and Development Projects on a Cost Basis (Nebenbestimmungen f?r Zuwendungen auf Kostenbasis des BMBF an Unternehmen der gewerblichen Wirtschaft f?r Forschungs- und Entwicklungsvorhaben - NKBF 98) will be part of the notification of award for grants on a cost basis. The General Auxiliary Conditions for Grants for the Promotion of Projects (Allgemeine Nebenbestimmungen f?r Zuwendungen zur Projektf?rderung - ANBest-P) and the Special Auxiliary Terms and Conditions for Funds Provided by the BMBF for the Promotion of Projects on an Expenditure Basis (Besondere Nebenbestimmungen f?r Zuwendungen des BMBF zur Projektf?rderung auf Ausgabenbasis - BNBest-BMBF 98) will be part of the notification of award for grants on an expenditure basis. 7. Procedure 7.1. Involvement of a project management organization and request for documents The Federal Ministry of Education and Research has commissioned the following project management organization to implement the funding activity: Projekttr?ger PT-DLR - Projekttr?ger Gesundheitsforschung Heinrich-Konen-Str. 1 53227 Bonn Germany Tel.: + 49 (0)228-3821 210 (Sekretariat) Fax: + 49 (0)228-3821 257 Internet: http://www.dlr.de/pt/desktopdefault.aspx/tabid-4270/6848_read-6936/ The contact is Dr. Kr?ger (Tel.: + 49 (0)228-3821 296). Application forms, guidelines, information for applicants and the auxiliary terms and conditions are available here or can be obtained from the project management organization. Applicants are strongly advised to use the electronic application system "easy" for drafting formal applications. 7.2 Two-tiered funding procedure The funding procedure is two-tiered. 7.2.1 Submission and selection of project outlines In a first step, written project outlines must be submitted by post to the project management organization (PT-DLR) by 2 June 2008 at the latest. If necessary, further selection rounds will be carried out on the basis of these funding regulations. The deadlines for the submission of project outlines will be published on http://www.gesundheitsforschung-bmbf.de/en/175.php in due course. With a view to the international evaluation procedure, it is recommended that the project outlines be submitted to the PT-DLR in English. The deadline for submission is not a cut-off deadline. However, it may prove impossible to consider project outlines which are received after that date. Young German and non-German researchers who meet the criteria set out in this announcement (see section 4 above) are entitled to submit project outlines in agreement with the host university or research institution. The project outlines must include a description structured along the following lines: * Name of the young researcher, full office address, contact details (phone, fax, e-mail). * A meaningful CV (up to five pages, Arial 11 pt) which includes achievements in Computational Neuroscience (e. g. supervision of young researchers, national and international cooperation, raising of external funds, invitations to or hosting of conferences, membership of editorial boards of relevant scientific journals, expert opinions, other activities) * List of publications * Preliminary project description for the research programme of the entire proposed junior research group, including all planned scientific and technical staff members (up to ten pages Arial 11 pt) and a financial plan * Statement from the university or research institution at which the research programme is to be carried out confirming that the young researcher will be provided with the working facilities needed to perform the project (basic equipment in terms of laboratory space and other infrastructure) and will be supported in all matters. Applicants are requested to submit 10 copies of their outlines. No legal claims can be derived from the submission of a project outline. The evaluation of the project outlines received will involve external experts and be based on the following criteria: 1. Previous achievements of the young researcher in the field of Computational Neuroscience * Scientific work including publications * Supervisory activities * International activities * Other activities (raising of external funds, etc.) 2. Quality of the proposed research programme * Scientific and methodical quality * Scientific expertise of the applicant * Innovative potential * Relevance to the research focuses of the host institution A suitable project idea will be selected for funding on the basis of the evaluation. The applicants will be informed in writing about the result of the selection procedure. 7.2.2 Submission of formal applications and decision-making procedure In a second step, applicants whose project outlines have received a positive evaluation will be invited to submit (within six weeks of the invitation) a formal application of the institution where the research project is to be carried out; a decision on this formal application will be taken after the final evaluation. The approval, payment of and accounting for the funds as well as proof and examination of proper use and, if necessary, the revocation of the award and reclaiming of the funds awarded are governed by the administrative regulations pertaining to section 44 of the Federal Budget Code (BHO) and sections 48 to 49a of the Administrative Procedure Act (VwVfG) unless deviation is allowed under the present funding regulations. 8. Entry into force These funding regulations will enter into force on the date of publication in the Federal Gazette (Bundesanzeiger). Berlin, 29 October 2007 Federal Ministry of Education and Research Dr. Christiane Buchholz Molecular Life Sciences Division -- 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 bowlby at bu.edu Wed Mar 19 14:50:06 2008 From: bowlby at bu.edu (Brian Bowlby) Date: Wed, 19 Mar 2008 14:50:06 -0400 Subject: Connectionists: 12th ICCNS: Call for Registration Message-ID: <960D6E19-180D-41CC-8F19-0055E059046B@bu.edu> Apologies if you receive more than one copy of this email. TWELFTH INTERNATIONAL CONFERENCE ON COGNITIVE AND NEURAL SYSTEMS May 14?17, 2008 Boston University 677 Beacon Street Boston, Massachusetts 02215 USA http://www.cns.bu.edu/meetings/ Sponsored by the Boston University Center for Adaptive Systems, Department of Cognitive and Neural Systems (http://www.cns.bu.edu/), and Center of Excellence for Learning in Education, Science, and Technology (http://cns.bu.edu/CELEST/) with financial support from the National Science Foundation CONFIRMED INVITED SPEAKERS: Workshop on Dynamics of Cortical-Hippocampal Interactions for Memory Guided Behavior: Neil Burgess, Howard Eichenbaum, Michael Hasselmo, David Redish, Trygve Solstad, David Touretzky Workshop on Computing with Neural Interfaces: Theodore Berger, John Donoghue, Donald Eddington, Phil Kennedy, Krishna Shenoy, John Wyatt Keynote Lecturers: Gyorgy Buzsaki and Gail Carpenter Invited Speakers: Cynthia Breazeal, Peter Dayan, Greg DeAngelis, Stephen Grossberg, Joy Hirsch, Ranu Jung, Gordon Logan, Javier Movellan, Charan Ranganath, John Reynolds, and Daniel Salzman Please visit the web site for conference details, including: --the registration form (http://cns-web.bu.edu/cns-meeting/registration.html ) --a presentation schedule (http://cns-web.bu.edu/cns-meeting/schedule.html ) --local lodging options (http://cns-web.bu.edu/cns-meeting/hotels.html) -- Brian Bowlby, PhD 677 Beacon Street Director of Computation Labs Boston, MA 02215 Cognitive and Neural Systems 617-353-7673 Boston University bowlby at bu.edu -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080319/cf745074/attachment-0001.html From s.li.1 at bham.ac.uk Wed Mar 19 19:46:32 2008 From: s.li.1 at bham.ac.uk (Sheng Li) Date: Wed, 19 Mar 2008 23:46:32 +0000 Subject: Connectionists: Research Fellow in Computational Neuroscience Message-ID: <468E635F877FE94BBEFFC0309BCA1954E75B46@psgfs4.adf.bham.ac.uk> Research Fellow in Computational Neuroscience A Research Fellow position is available at the Cognitive NeuroImaging Lab, School of Psychology, University of Birmingham, UK. The work focuses on theoretical modelling and advanced computational analyses of electrophysiological and functional imaging data (MRI, EEG, MEG). Research in the lab examines the neural basis of perceptual decisions and learning across the lifespan (http://cnil.bham.ac.uk/ ). The School of Psychology at the University of Birmingham is a top class 5* department that has a dynamic group in Cognitive Neuroscience with strong links to Computer Science and Engineering and a state-of-the-art Imaging Centre (3T scanner), access to a large group of screened neuropsychological patients, EEG/ERP systems, TMS delivery systems, robot systems for haptic research, and several systems for eye movement tracking and kinematic analysis. You should have a background and hold a PhD. in Computer Science, Physics, Applied Mathematics, Engineering, Neuroscience or a related field. Advanced programming skills (e.g. Matlab, C, OpenGL) are necessary and experience with behavioural, imaging and signal processing methods is desirable. If you are interested please send a CV and a statement of research interests to Prof. Zoe Kourtzi: z.kourtzi at bham.ac.uk. best regards Zoe Kourtzi, PhD Chair of Brain Imaging Behavioural and Brain Sciences School of Psychology University of Birmingham Edgbaston, Birmingham B15 2TT UK tel: 121 414 8509 fax: 121 414 3342 fax: 121 414 4897 e-mail: z.kourtzi at bham.ac.uk web: http://cnil.bham.ac.uk/ From ale at sissa.it Thu Mar 20 05:54:19 2008 From: ale at sissa.it (Alessandro Treves) Date: Thu, 20 Mar 2008 10:54:19 +0100 Subject: Connectionists: SISSA Spring faculty search Message-ID: <20080320105419.zj7wc6eu4gw8o4sk@webmail.sissa.it> The Cognitive Neuroscience Sector at SISSA seeks to recruit independent group leaders. The 3-year Plan approved by SISSA last Fall includes strengthening cognitive neuroscience research and identifies as priorities: - Behavioural Neuroscience, investigated through electrophysiology in awake animals - Cognitive Development and/or Learning - Functional Imaging, in connection with the new fMRI-sharing agreement in Udine - Language and/or Higher Cognitive Function The Sector aims to identify up to 3 suitable candidates already this Spring, although the appointments and so the establishment of new research groups may be scattered over the period 2008-10. The Sector is particularly interested in reaching candidates with no previous history of collaboration with SISSA. If selected, they will be offered positions at a level commensurate with their qualifications, in the expectation that within 5 years they will succeed in obtaining tenure as Associate or Full Professors. Candidates with whose work SISSA is familiar may be offered ad hoc arrangements if selected, but they will first be assessed together with the others. SISSA is one of the three purely postgraduate and postdoctoral institutions within the Italian university system. It operates in English and the Sector is keen to enhance its international character and its intellectual diversity. The Sector currently has 23 PhD students supported on SISSA fellowships, almost half of whom are not Italians. Postdocs, however, are normally supported by individual research funding. Faculty members are required to teach limited PhD mini-courses, and to individually supervise the research of students in their groups. Current faculty members are Mathew Diamond, Jacques Mehler, Raffaella Rumiati, Tim Shallice and Alessandro Treves, with visiting professors Evan Balaban, Luca Bonatti and Marina Nespor. Further information about the Sector can be found on the webpage http://www.sissa.it/cns/ Those interested should write to Alessandro Treves, alessandrotreves at gmail.com, before April 30th, 2008, attaching their curriculum vitae. Receipt of CVs will be acknowledged weekly. ---------------------------------------------------------------- SISSA Webmail https://webmail.sissa.it/ Powered by Horde http://www.horde.org/ From juergen at idsia.ch Tue Mar 11 04:27:50 2008 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Tue, 11 Mar 2008 09:27:50 +0100 Subject: Connectionists: Postdoc at the Swiss AI lab IDSIA - seq2008 Message-ID: <55a3df742672b5f494f28f63ac8f2120@idsia.ch> We are seeking an outstanding postdoc in the field of machine learning, with experience / interest in at least some of the following topics: learning algorithms for sequence processing, program learning, recurrent neural networks (RNN), hidden Markov models, statistical / Bayesian approaches, algorithmic information theory, artificial evolution, in particular RNN evolution, recurrent support vector machines, etc. Goal: to advance the state of the art in learning algorithms for sequence processing, and to solve challenging learning tasks involving dynamically changing inputs, such as time series prediction, recognition of complex objects in the sensory input stream of virtual or real robots, etc. Salary: ~ SFR 72,000 per year ~ US$ 70,000 (7 March 2008) Start: now or soon To apply, please follow the instructions under http://www.idsia.ch/~juergen/seq2008.html Juergen Schmidhuber -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 2415 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080311/9b23b88e/smime-0001.bin From peter.andras at newcastle.ac.uk Wed Mar 12 07:47:12 2008 From: peter.andras at newcastle.ac.uk (Peter Andras) Date: Wed, 12 Mar 2008 11:47:12 -0000 Subject: Connectionists: PhD Studentship in computational neuroscience Message-ID: <7DD36077F4007D429A17CF8B03D6AABE0431DB57@moonraker.campus.ncl.ac.uk> PhD studentship in computational neuroscience A 3 year PhD studentship is available (pending approval) at the School of Computing Science of Newcastle University (www.cs.ncl.ac.uk), in the area of computational neuroscience with a focus on the analysis of the activity of the crab stomatogastric ganglion (STG). The project will involve the use of high resolution voltage-sensitive dye imaging of the STG together with simultaneous electrical recording of neurons, and computational analysis of the imaging data. The aim of the project is to identify neurons on the basis of their optically recorded activity profiles and to describe the behaviour of the ganglion in terms of probabilistic transition rules of recorded neural activity patterns. The project may include collaboration with labs from the US and Germany. The project will also be associated with the Newcastle Institute of Neuroscience (http://www.ncl.ac.uk/ion/). The funding for the studentship is provided by the EPSRC. The studentship covers subsistence (about ?12,940 per year) and academic fees. The studentship is normally available for EU citizens who are resident in the UK. Applicants should have, or expect to obtain, a First Class BSc, or higher degree, in Computer Science, Physics, Mathematics, Statistics, Biology or other related field with a strong interest in computational analysis of biological systems. Deadline for application is 15 April 2008. Applicants should follow the normal electronic admissions procedure: http://www.ncl.ac.uk/postgraduate/apply/. In the application form, where you are asked to indicate the research area/project, please mention that you wish to be considered for a PhD Research Studentship. For further enquiries please email: Dr Peter Andras (www.staf.ncl.ac.uk/peter.andras/) at peter.andras at ncl.ac.uk. From v.steuber at herts.ac.uk Wed Mar 12 09:18:32 2008 From: v.steuber at herts.ac.uk (Volker Steuber) Date: Wed, 12 Mar 2008 13:18:32 +0000 Subject: Connectionists: Postdoctoral Research Fellow in Computational Neuroscience Message-ID: <47D7D828.9050602@herts.ac.uk> Postdoctoral Research Fellow in Computational Neuroscience Science and Technology Research Institute University of Hertfordshire ?23,000 - ?25,100 p.a. 3 years fixed term contract in the first instance Closing date: 9 April 2008 Quote Reference: EN8363X Applications are invited for a three year postdoc position in computational neuroscience. The project will focus on information processing in the vestibular cerebellum and involve the construction of a detailed model of the cerebellar cortex in 3D that is based on new physiological and morphological data. The position is funded by a Systems Biology Fellowship from the BBSRC (UK) and the ANR (France) and requires close collaboration with experimental and theoretical neuroscientists at UCL, the Ecole Normale Sup?rieure, Universit? Paris Descartes and Universit? Paris 5. More details about our research interests can be found under http://homepages.feis.herts.ac.uk/~comqvs/ and in these recent publications: Steuber, V., Mittmann, W., Hoebeek, F.E., Silver, R.A., De Zeeuw, C.I., Hausser, M. and De Schutter, E. (2007). Cerebellar LTD and pattern recognition by Purkinje cells. Neuron 54, 121-136. Gleeson, P. Steuber, V. and Silver, R.A. (2007). neuroConstruct: A tool for modeling networks of neurons in 3D space. Neuron 54, 219-235. You should have a PhD in computational neuroscience or a related discipline. Previous experience in biologically realistic modelling and knowledge of simulation tools such as NEURON or GENESIS is not required, but would be an advantage. Good scientific communication and writing skills and the ability to work as part of a team are essential. The UH Science and Technology Research Institute has been rated as 4 (national excellence with evidence of international excellence) at the last UK university research assessment exercise. It is located in Hatfield in Hertfordshire, just north of London. The University offers a range of benefits including a final salary pension scheme, professional development, family friendly policies, child care vouchers, waiving of course fees for the children of staff at UH, discounted memberships at the Hertfordshire Sports Village and generous annual leave. For informal enquiries contact Dr Volker Steuber (v.steuber at herts.ac.uk , Tel +44 1707 284350). Apply online at http://recruitment.herts.ac.uk/recruit or request an application pack from Human Resources on 01707 284802 (24hr voicemail), quoting reference EN8363X. Dr Volker Steuber Senior Lecturer (Research) in Biocomputation School of Computer Science Science and Technology Research Institute University of Hertfordshire College Lane, Hatfield, Herts, AL10 9AB UK Tel +44 (0) 1707 284350 v.steuber at herts.ac.uk -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080312/8b2236f4/attachment-0001.html From steve at cns.bu.edu Thu Mar 13 16:03:16 2008 From: steve at cns.bu.edu (Stephen Grossberg) Date: Thu, 13 Mar 2008 16:03:16 -0400 Subject: Connectionists: Laminar cortical dynamics of working memory, sequence learning, and performance Message-ID: The following article is now available at http://www.cns.bu.edu/Profiles/Grossberg : Grossberg, S. and Pearson, L. Laminar cortical dynamics of cognitive and motor working memory, sequence learning, and performance: Toward a unified theory of how the cerebral cortex works Psychological Review, in press ABSTRACT How does the brain carry out working memory storage, categorization, and voluntary performance of event sequences? The LIST PARSE neural model proposes an answer to this question that unifies the explanation of cognitive, neurophysiological, and anatomical data from humans and monkeys. It quantitatively simulates human cognitive data about immediate serial recall and free recall, and monkey neurophysiological data from the prefrontal cortex obtained during sequential sensory-motor imitation and planned performance. The model clarifies why both spatial and non-spatial working memories share the same type of circuit design. It proposes how the laminar circuits of lateral prefrontal cortex carry out working memory storage of event sequences within layers 6 and 4, how these event sequences are unitized through learning into list chunks within layer 2/3, and how these stored sequences can be recalled at variable rates that are under volitional control by the basal ganglia. These laminar prefrontal circuits are variations of laminar circuits in the visual cortex that have been used to explain data about how the brain sees. These examples from visual and prefrontal cortex illustrate how laminar neocortex can represent both spatial and temporal information, and open the way towards understanding how other behaviors may be represented and controlled by variations on a shared laminar neocortical design. Keywords: working memory, competitive queuing, immediate serial recall, immediate free recall, delayed free recall, continuous-distracter free recall, sensory-motor imitation, chunking, sequence learning, prefrontal cortex, parietal cortex, position coding, rank order cells, cerebral cortex, laminar computing From terry at salk.edu Thu Mar 13 17:30:35 2008 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 13 Mar 2008 14:30:35 -0700 Subject: Connectionists: Back Issues of Neural Computation online In-Reply-To: Message-ID: All papers published in Neural Computation starting with Volume 1 in 1989 can now be downloaded from the MIT Press website: http://www.mitpressjournals.org/loi/neco In addition, Early Access to papers that are in press can also be downloaded from this site. Terry ----- From Dominique.Martinez at loria.fr Thu Mar 13 18:20:30 2008 From: Dominique.Martinez at loria.fr (Dominique.Martinez@loria.fr) Date: Thu, 13 Mar 2008 23:20:30 +0100 Subject: Connectionists: PhD position in computational neuroscience, INRA Versailles, France Message-ID: <1205446830.47d9a8ae6ffc9@www.loria.fr> PhD position in computational neuroscience, INRA Versailles, France : Applicants are invited for a PhD position in the field of theoretical neuroscience with a focus on olfaction. The successful applicant will perform research in modelling the insect olfactory system. The aim of the project is to understand the mechanisms of odour coding by means of a multidisciplinary approach combining models and experiments. The candidate will have to interact with other researchers in a mixed team of modellers using mathematical and computational methods and experimentalists performing electrophysiological recordings of neurons in a noctuid moth. Candidates should hold an engineering degree or a master degree in a relevant discipline (Computer Science, Mathematics or Physics). The candidate should have expertise in programming, and should demonstrate a strong interest in biophysics, systems neuroscience, or cognitive neuroscience. The work will be performed at the National Institute for Agricultural Research (INRA) in Versailles, at half an hour train from down-town Paris. The project also includes collaboration with the National Institute for Computer Sciences (LORIA-INRIA) in Nancy, France. The position is for three years, starting on Sept. 2008 and is funded by INRA. Applications including a CV, a motivation letter and the names of two references must be sent electronically to Jean-Pierre Rospars (Rospars at versailles.inra.fr) and Dominique Martinez (Dominique.Martinez at loria.fr). The closing date for applications is May 15, 2008. Selected candidates will be interviewed in Paris early in June. From rsun at rpi.edu Fri Mar 14 14:46:43 2008 From: rsun at rpi.edu (Professor Ron Sun) Date: Fri, 14 Mar 2008 14:46:43 -0400 Subject: Connectionists: INNS Award nominations Message-ID: **** 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 juergen at idsia.ch Mon Mar 17 05:42:05 2008 From: juergen at idsia.ch (Juergen Schmidhuber) Date: Mon, 17 Mar 2008 10:42:05 +0100 Subject: Connectionists: recurrent network references Message-ID: <078ca65920b940eb89b606c02b8f1a5b@idsia.ch> Dear connectionists, we are in the process of writing a textbook on recurrent neural networks (RNN) for sequence processing & program learning with & without teachers, to be published by Cambridge University Press: http://www.idsia.ch/~juergen/rnnbook.html Quite a few references to previous papers on RNN written by many of you can already be found in the following incomplete and unordered bibfiles: http://www.idsia.ch/~juergen/bib.bib http://www.idsia.ch/~juergen/idsia.bib but many important citations are still missing. To make sure we give a comprehensive overview of the field, we ask those who contributed to it to send me their list of relevant references, preferably bibtex, plus url-pointers to the corresponding pdf-files, with cc to santiago at idsia.ch. For each of your papers, could you please also send five lines or so stating why this was novel back then, possibly tinged by the benefit of hindsight? Please also forward this message to others who might be interested. Thanks a lot! J?rgen Schmidhuber Faustino Gomez Santiago Fernandez Alex Graves Sepp Hochreiter -------------- next part -------------- A non-text attachment was scrubbed... Name: smime.p7s Type: application/pkcs7-signature Size: 2415 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080317/9942fa3b/smime-0001.bin From franco at dii.unisi.it Mon Mar 17 13:28:07 2008 From: franco at dii.unisi.it (Franco Scarselli) Date: Mon, 17 Mar 2008 18:28:07 +0100 Subject: Connectionists: Deadline extension: KES2008 Special Session on "ADVANCED NEURAL PROCESSING SYSTEMS" Message-ID: <47DEAA27.3050702@dii.unisi.it> ** Our apologies if you receive multiple copies of this announcement ** Following requests from prospective authors, the deadline for the paper submission to the KES2008 Special Session on "ADVANCED NEURAL PROCESSING SYSTEMS" has been extended to March 25th, 2008. Please note that no additional extension can be granted. *********************************************************************** Special Session "ADVANCED NEURAL PROCESSING SYSTEMS" 12th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems Zagreb, Croatia 3, 4 and 5 September 2008 Call for papers The research in the neural network field has come to its maturity, both from the theoretical and the practical point of view. Nevertheless, some problems still remain unsolved, since classical connectionist models seem unable to cope with difficult applications, involving complex data. Recent studies on statistical pattern recognition and neural networks show possible directions to exploit structural information in problems which are inherently of topological nature. On the other hand, the actual trend for facing difficult applications is that of using hybrid approaches, integrating in a unique framework neural networks, kernel machines, and statistical techniques. This new scenario imposes studying new models, new learning algorithms, and assessing their properties both theoretically and experimentally. The scope of this session is, but not limited to: - Algorithms and Architectures: statistical learning algorithms, neural networks, kernel methods, dimensionality reduction and manifold learning, model selection. - Applications: innovative applications that use machine learning, including systems for time series prediction, bioinformatics, text/web analysis, multimedia processing, and robotics. - Cognitive Science and Artificial Intelligence: theoretical, computational, or experimental studies of perception, reasoning, problem solving, and natural language processing. - Control and Reinforcement Learning: planning, navigation, Markov decision processes, game-playing. - Learning Theory: generalization, regularization and model selection, new learning paradigms, spaces of functions and kernels, online learning and competitive analysis, hardness of learning and approximations, information theory. - Learning in Graphical Domains: neural network models for graphs, SVMs and kernel methods for graphs, probabilistic models for graphs, statistical relational learning, and pattern recognition applications involving graphical data. Paper submission Authors are encouraged to submit high quality, original work that has neither appeared in, nor is under consideration by, other conferences/journals. All submissions will be refereed by experts in the field based on originality, significance, and clarity. The conference preceedings will be published by Springer-Verlag in Lecture Notes in AI as part of the LNCS/LNAI series. When formatting papers - that must be no more than eight (8) pages long, including figures and bibliography - please refer to the Springer-Verlag site and strictly follow the instructions for LNCS authors (http://www.springer.de/comp/lncs/authors.html). Important Dates . Deadline for paper submission: March 25th 2008 . Notification of acceptance: April 10th 2008 . Camera-ready papers: May 1st 2008 Organized by: Chairs . Monica Bianchini, Marco Maggini, Franco Scarselli University of Siena, Italy Program Committee . Simone Fiori, Politechnic University of Marche, Italy . Barbara Hammer, Clausthal University of Technology, Germany . Simone Marinai - University of Florence, Italy . Alfredo Petrosino, University of Naples "Parthenope", Italy . Friedhelm Schwenker, University of Ulm, Germany . Peter Tino, The University of Birmingham, United Kingdom . Edmondo Trentin, University of Siena, Italy Other details are available at: http://www.dii.unisi.it/~monica/KES2008_SSANPS/index.html From tobias at nld.ds.mpg.de Tue Mar 18 06:33:59 2008 From: tobias at nld.ds.mpg.de (Tobias Niemann) Date: Tue, 18 Mar 2008 11:33:59 +0100 Subject: Connectionists: Two PostDoctoral or Ph.D. student positions In-Reply-To: <46F11EC2.6060905@nld.ds.mpg.de> References: <46F11EC2.6060905@nld.ds.mpg.de> Message-ID: <47DF9A97.1000408@nld.ds.mpg.de> Job Offer: Two PostDoctoral or Ph.D. student positions The Bernstein Center for Neurotechnology Goettingen (BCNT) invites applications for Two PostDoctoral or Ph.D. student positions in the project ?Magnetic stimulation in cell culture and brain?. In this German-Israeli cooperation between the Max-Planck-Institute for Dynamics and Self-Organization, the Weizmann Institute (Rehovot, Israel) and the Medical School of G?ttingen University, we will combine numerical simulations, experimental work on neuronal cultures and clinical trials to achieve a detailed understanding of the cellular effects of magnetic stimulation (TMS) and direct current stimulation (tDCS). With this background we hope to achieve a rational design of therapeutic treatment paradigms for these brain stimulations. In this context two foci should be covered by the successful applicants: 1. numerical simulations of neurons on various levels of complexity. In addition numerical simulations of electromagnetic fields in space with anisotropic impedance will be performed. 2. experiments with magnetic stimulation in both, clinical trials and in vivo / in vitro model systems. The aim is to test and transfer new stimulation paradigms. The successful applicants will get the opportunity to develop skills is both areas. The successful applicant is interested in tackling problems in an interdisciplinary group and has a degree in neuroscience, physics, applied mathematics or engeneering and experience with numerical simulations. Goettingen is a university town with a long tradition and a vivid student atmosphere ? and it is a center of neuroscience research in Germany. Besides the recently established BCNT and several institutes of the Goettingen University the neuroscience community also includes three Max-Planck-Institutes, the Bernstein Center for Computational Neuroscience, the European Neuroscience Institute, the Center for Molecular Physiology of the Brain and the German Primate Center. Goettingen will host the Third International Conference on Transcranial Magnetic and Direct Current Stimulation. The initial appointment will be for two years, with the possibility of extension. Salary for the PhD positions is according to the German TV?D (?Entgeltgruppe? 13 or 14, depending on qualifications) with benefits. We are committed to employing more disabled individuals and especially encourage them to apply. We aim to increase the number of women in those areas where they are underrepresented and urge them to apply. Applications (including a statement of interest, CV, publication list, certificates, addresses of references) should consist of one pdf-document and sent to Dr. Andreas Neef: aneef at gwdg.de or Prof. Walter Paulus: wpaulus at med.uni-goettingen.de. From elli.chatzopoulou at incf.org Tue Mar 18 06:51:35 2008 From: elli.chatzopoulou at incf.org (INCF - Elli Chatzopoulou) Date: Tue, 18 Mar 2008 11:51:35 +0100 Subject: Connectionists: 1st INCF Congress of Neuroinformatics Message-ID: <47DF9EB7.9050806@incf.org> The organizers of Neuroinformatics 2008 are inviting you and your research team to register for the: 1st INCF Congress of Neuroinformatics: *Databasing and Modeling the Brain* /Stockholm, Sweden -September 7-9, 2008 / Neuroinformatics 2008 will focus on dissemination of recent progress and community building in this emerging field. The congress is organized as a single track event, with 6 keynote speakers, 5 workshops, and 2 poster sessions, as well as live demos of neuroinformatics applications. Online registration and abstract submission is now open! *www.neuroinformatics2008.org* /Keynote Speakers:/ -Mark Ellisman -Mitsuo Kawato -Mary Kennedy -Henry Markram -Idan Segev -David Van Essen *Workshops* -Future hardware challenges to scientific computing Erik de Schutter (chair), Gabriel Wittum, Marc-Oliver Gewaltig, John Shalf -Neurogenomics meets bioinformatics meets neuroinformatics in database research Robert Williams (chair), Ed Lein, Seth Grant, Kristen Harris -Extraction if structural and functional information from brain images Ulla Ruotsalainen (chair), Arthur Toga, Alan Evans, Thomas Mrsic-Fl?gel -Challenges and benefits of multichannel electrophysiology Andrzej Wrobel (chair), Gy?rgy Buzsaki, Miguel Nicolelis, Xiaoqin Wang *Special session* Perspectives in funding research in neuroinformatics Kathie Olsen, Wolfgang Boch We especially encourage junior researchers to submit abstracts for the poster session. We kindly ask you to spread information about the conference to potentially interested colleagues and target groups. -- Elli Chatzopoulou, Ph.D. Scientific Information and Public Relations Officer International Neuroinformatics Coordinating Facility Secretariat Karolinska Institutet Nobels v?g 15A SE-171 77 Stockholm Sweden Email: elli.chatzopoulou at incf.org Phone: +46 8 524 87491 Mobile: +46 7 614 87491 Fax: +46 8 524 87150 web: www.incf.org From junmeizhu at gmail.com Tue Mar 18 10:17:41 2008 From: junmeizhu at gmail.com (Junmei Zhu) Date: Tue, 18 Mar 2008 15:17:41 +0100 Subject: Connectionists: FIAS PhD/Postdoc position in theoretical neuroscience Message-ID: <5b32f48a0803180717r5d30aff1tf6ea69d97fbe9e72@mail.gmail.com> PhD/Postdoc position Theoretical neuroscience Prof. von der Malsburg Frankfurt Institute for Advanced Studies (FIAS) Frankfurt, Germany Analysis of complex dynamical systems in the context of brain development and function. The position is either for a motivated student to work toward his/her PhD (in Physics, Mathematics, Computer Science or similar) or for a postdoc whose research interests are in line with this project. Requirements: - Solid analytical skills - Background in physics (theoretical, dynamics, fluid dynamics, plasma) or mathematics (dynamical systems) - Interested in dealing with real complex systems of many degrees of freedom, and open to using computers as assistance for analysis - Experience with neuroscience welcome but not essential - Good communication skills in English For more information on the research, please visit the Frankfurt Vision Initiative (http://fias.uni-frankfurt.de/bernstein) or the FIAS neuro group (http://fias.uni-frankfurt.de/neuro/) project SECO. Questions may be directed to Dr. Junmei Zhu at jzhu at fias.uni-frankfurt.de. The position is available now. Screening starts immediately and will continue until the position is filled. Application (postdocs and students) should include: - CV - statement of research interests - list of relevant courses and projects with grade (students) - 2 best publications (postdocs) - 2-3 letters of recommendation Send application to Dr. Junmei Zhu jzhu at fias.uni-frankfurt.de FIAS, Ruth-Moufang-Str. 1 60438 Frankfurt am Main, Germany Phone: +49 69 798-47616 From remi.munos at inria.fr Fri Mar 21 09:43:34 2008 From: remi.munos at inria.fr (Remi Munos) Date: Fri, 21 Mar 2008 14:43:34 +0100 Subject: Connectionists: MACHINE LEARNING SUMMER SCHOOL Message-ID: <200803211443.34596.remi.munos@inria.fr> ============================================================= 10th MACHINE LEARNING SUMMER SCHOOL MLSS'08 September 1-15, Ile de Re, France. ============================================================= http://mlss08.futurs.inria.fr email : mlss08 at inria.fr (Thanks for forwarding this Announcement to potential candidates and apologies for multiple copies). THE APPLICATION PROCESS IS OPEN until APRIL 15, 2008 http://mlss08.futurs.inria.fr/application Machine Learning is a foundational discipline of the Information Sciences. It combines theory from areas as diverse as Statistics, Mathematics, Engineering, and Information Technology with many practical and relevant real life applications. The aim of the summer school is to cover the entire spectrum from theory to practice. It is mainly targeted at research students, academics, and IT professionals from all over the world. The program will feature introductory courses at the beginning to provide basic working knowledge of Machine Learning. Building on this introductory material, advanced topics will be covered progressively over the duration of the school. Subjects will be covered both in lectures (4-6 per topic) and in practical courses (where students will have the chance to implement methods for themselves); and are taught by world experts in their fields. This school is suited to PhD and Masters students, as well as advanced undergraduates, provides an excellent opportunity for interaction with top researchers in a broad cross-section of machine learning disciplines. The confirmes speakers are: * Shai Ben-David (University of Waterloo) /"Theoretical Foundations of Clustering"/ * Stephane Canu (INSA de Rouen) /"Introduction to Kernel Methods"/ * Manuel Davy (CNRS/Predict&Control) /"Parametric and Non-parametric Bayesian Learning"/ * Pierre Del Moral (Universite de Bordeaux) /"On the Foundations and the Applications of i-MCMC Methods"/ * Isabelle Guyon (ClopiNet) * Yann LeCun (New York university) /"Supervised and Unsupervised Learning with Energy-Based Models"/ * Rich Sutton (University of Alberta) /"Reinforcement Learning and Knowledge Representation"/ * Patrick Wolfe (Harvard University) /"Overcomplete Representations with Incomplete Data: Learning Bayesian Models for Sparsity"/ The program is available at http://mlss08.futurs.inria.fr/ *Please find more information about registrations and application form at http://mlss08.futurs.inria.fr/application We are loking forward to seeing you in Ile de Re, France. Best regards, the MLSS organizing committee mlss08 at inria.fr http://mlss08.futurs.inria.fr/ From retienne at jhu.edu Fri Mar 21 10:10:11 2008 From: retienne at jhu.edu (Ralph Etienne-Cummings) Date: Fri, 21 Mar 2008 10:10:11 -0400 Subject: Connectionists: 2008 Telluride Neuromorphic Cognition Engineering Workshop Application DEADLINE: 23rd of March Message-ID: <47E3C1C3.2050406@jhu.edu> NEUROMORPHIC COGNITION ENGINEERING WORKSHOP Sunday, JUNE 29th - Saturday, JULY 19th, 2008 Telluride, Colorado Call for Applications Deadline: March 23rd, 2008 Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Ralph ETIENNE-CUMMINGS (Johns Hopkins University) Paul HASLER (Georgia Institute of Technology) Timmer HORIUCHI (University of Maryland) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Tobias Delbruck (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) Barbara SHINN-CUNNINGHAM (Boston University) Andre van SCHAIK(University of Sydney) We invite applications for a three week summer workshop that will be held in Telluride, Colorado from Sunday, June 29th to Saturday, July 19th, 2008. The application deadline is Friday, March 23rd, and application instructions are described at the bottom of this document. The 2008 Workshop and Summer School on Neuromorphic Engineering is sponsored by the National Science Foundation, Institute of Neuromorphic Engineering, Air Force Office of Scientific Research, Institute for Neuroinformatics - ETHZ, Georgia Institute of Technology, University of Maryland - College Park, Johns Hopkins University, Boston University, University of Sydney, and the Salk Institute. Last year's workshop was an exciting event and a great success. We strongly encourage interested parties to browse through the previous workshop web pages at: http://ine-web.org/workshops/past-workshops GOALS: Neuromorphic engineers design and fabricate artificial neural systems whose detailed architecture, design, and computational principles are based on those of biological nervous systems. Over the past 12 years, this research community has focused on the understanding of low-level sensory processing and systems infrastructure; efforts are now expanding to apply this knowledge and infrastructure to addressing higher-level problems in perception, cognition, and learning. The annual three-week intensive Workshop (held in Telluride, Colorado) consists of background lectures (from leading researchers in biological, cognitive, computational, engineering and learning sciences), practical tutorials (from state-of-the-art practitioners), hands-on projects (involving established researchers and newcomers/students), and special interest discussion groups (proposed by the workshop participants). In this workshop and through the Institute for Neuromorphic Engineering (INE), the mission is to promote interaction between senior and junior researchers; to educate new members of the community; to introduce new enabling fields and applications to the community; to promote on-going collaborative activities emerging from the Workshop, and to promote a self-sustaining research field. */ /* FORMAT: The three week summer workshop will include background lectures on systems and cognitive neuroscience (in particular sensory processing, learning and memory, motor systems and attention), practical tutorials on analog VLSI design, mobile robots, hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, many of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, cognitive systems, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control and locomotion * robotics * multichip communication * analog VLSI * learning and memory * neuroprosthetic systems * cognitive neuroscience and attention LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350miles). Great Lakes Aviation and America West Express airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do not rent a car. Bring hiking boots, warm clothes, rain gear, and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around mid April 2008. The Workshop covers all your accommodations and facilities costs. You are responsible for your own travel to the Workshop. For expenses not covered by federal funds, a Workshop registration fee is required. The fee is $500 per participant, however, due to the difference in travel cost, we offer a discount to the non-US participants. European registration fees will be reduced by $250; non-US/non-European registration fees will be reduced by $400. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e. postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage women and minority candidates to apply. The application website is (after February 15th, 2008): http://ine-web.org/telluride-conference-2008/apply/ Application will include: * First name, Last name, Affiliation, valid e-mail address. * Curriculum Vitae. * One page summary of background and interests relevant to the workshop. * Two letters of recommendation (uploaded directly by references). The application deadline is Friday, March 23, 2008. Applicants will be notified by e-mail by the end of April. ---------------------------------------------------------------------------------------- Ralph Etienne-Cummings Associate Professor Department of Electrical and Computer Engineering 105 Barton Hall/3400 N. Charles St. Johns Hopkins University Baltimore, MD 21218 Email: retienne at jhu.edu E URL: http://etienne.ece.jhu.edu/~etienne Tel: 410 - 516 - 3494 Fax: 410 - 516 - 5566 From tetiana.aksenova at cea.fr Fri Mar 21 10:24:23 2008 From: tetiana.aksenova at cea.fr (AKSENOVA Tetiana 218551) Date: Fri, 21 Mar 2008 15:24:23 +0100 Subject: Connectionists: PhD studentship in neural engineering at CEA, Grenoble, France Message-ID: PhD position in neural engineering for an excellent PhD student at CEA, Grenoble, France. http://www-instn.cea.fr/Publication_Sujet.php3?nomfichier=SL-DRT-08-148&lang=EN&id_rubrique=140 Applicants are invited for a PhD position in the field of neural engineering with the focus on Brain Computer Interface. The successful applicant will perform research in signal processing, modelling from experimental data, machine learning, and fast calculations for on-line real time applications. The aim of the project is the development of self paced ECoG based BCI by means of a multidisciplinary study combining modelling and experiments. The candidate will have to interact with other researchers in a mixed team of mathematicians and engineers using mathematical and computational methods as well as of experimentalists performing BCI in animals and humans. Candidates should hold an engineering degree or a master degree in a relevant discipline (Computer Science, Mathematics or Physics). The candidate should have expertise in programming (MatLab, C(C++) ), and should demonstrate a strong interest in biophysics. The work will be performed at the Centre of Atomic Energy (CEA, Grenoble, France) at the Laboratory of Microelectronics for Health, LETI-Minatec, CEA. The position is for three years, starting on September-October 2008 and is funded by CEA. Applications including a CV, a motivation letter and the names of two references must be sent electronically to Tetiana Aksenova (tetiana.aksenova at cea.fr), Stephane Bonnet (stephane.bonnet at cea.fr) and Regis Guillemaud (regis.guillemaud at cea.fr). The closing date for applications is April 20, 2008. Selected candidates will be interviewed in Grenoble. Tetiana Aksenova CEA L?ti MINATEC D?partement des micro-Technologies pour la Biologie et la Sant? (DTBS) Laboratoire LE2S 17 Rue des Martyrs - 38054 Grenoble Cedex 9 Tel: +33 438 78 03 20 Fax: +33 438 78 54 56 Email : tetiana.aksenova at cea.fr -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080321/41b4bd03/attachment-0001.html From kdharris at andromeda.rutgers.edu Fri Mar 21 15:00:39 2008 From: kdharris at andromeda.rutgers.edu (kdharris@andromeda.rutgers.edu) Date: Fri, 21 Mar 2008 15:00:39 -0400 (EDT) Subject: Connectionists: Axonal backpropagation in real neural networks Message-ID: <62397.216.165.126.18.1206126039.squirrel@webmail.newark.rutgers.edu> Dear Connectionists, The "backprop" algorithm is the most successful neural network algorithm for real-world applications, but is not considered a serious model for neuronal plasticity in the brain. Overwhelming experimental evidence shows that information can flow backward along axons; it just cannot do so fast enough for implementation of the backprop algorithm. In a recent article, I review the experimental evidence on such "retroaxonal" signaling in the nervous system, and suggest how retroaxonal signals propagating at physiologically reasonable speeds could control learning in neuronal networks, based on the hypothesis that strengthening of a neuron's output synapses stabilizes recent changes in the same neuron's inputs. As a consequence, neural representations that provide useful information to their downstream targets, and thus for behavior, are stabilized. A candidate molecular mechanism for this process, involving the activation of CREB by retrograde neurotrophin signals, is proposed. The article may be found in the latest issue of Trends in Neurosciences, or freely online at: http://andromeda.rutgers.edu/~kdharris/backprop.pdf "Stability of the fittest: organizing learning with retroaxonal signals", TINS 31:130-136 (2008). Sincerely, Kenneth D. Harris ------------------------ Kenneth D. Harris, Ph.D. Assistant Professor Center for Molecular and Behavioral Neuroscience Rutgers, The State University of New Jersey 197 University Avenue Newark NJ 07102, USA phone: 973 353 1080, x3331 fax: 973 353 1272 Visiting Assistant Professor Smilow Neuroscience Program and Dept of Otolaryngology NYU Medical Center 550 1st Avenue, New York NY 10016 phone: 212 263 9295 email: kdharris at andromeda.rutgers.edu web: http://qneuro.rutgers.edu From jbednar at inf.ed.ac.uk Wed Mar 26 08:45:36 2008 From: jbednar at inf.ed.ac.uk (James A. Bednar) Date: Wed, 26 Mar 2008 12:45:36 +0000 Subject: Connectionists: PhD studentships in Neuroinformatics and Computational Neuroscience, Edinburgh Message-ID: <18410.17776.900085.638637@lodestar.inf.ed.ac.uk> UPDATE: Application deadline extended to 15 April 2008! PhD studentships in Neuroinformatics and Computational Neuroscience, Edinburgh We invite applications for 12 fully-funded PhD studentships at the University of Edinburgh Doctoral Training Centre (DTC) in Neuroinformatics and Computational Neuroscience. The DTC is a world-class centre for research at the interface between neuroscience and the engineering and physical sciences. Our four-year programme is ideal for students with strong computational and analytical skills who want to work on problems in neuroscience and related fields. The first year consists of courses in neuroscience and informatics, as well as lab projects. This is followed by a three-year PhD project done in collaboration with one of the many departments and institutes affiliated with the DTC. The DTC focuses on research into understanding the brain and the nervous system using computational models and experiments, and also includes applying findings from neuroscience to build better software and hardware (robots and microcircuits), and using advanced methods to improve data handling and analysis including clinical diagnosis. PhD topics fall into five main areas: * Computational neuroscience: Using analytical and computational models, potentially supplemented with experiments, to gain quantitative understanding of the nervous system. Current projects focus on the development and function of sensory and motor systems, including neural coding, learning, and memory. * Cognitive science: Studying human cognitive processes and analysing them in computational terms. * Biomedical imaging algorithms and tools: Using advanced data analysis techniques, such as machine learning and Bayesian approaches, for imaging-based diagnosis and research. * Software systems and applications: Using discoveries from neuroscience to develop intelligent computer interfaces and software that can handle real-life data. * Neurorobotics and VLSI: Using insights from neuroscience to help build better hardware, such as neuromorphic VLSI circuits and robots that perform robustly under natural conditions. Edinburgh has a world-class research community in these areas and leads the UK in creating a coherent programme in neuroinformatics and computational neuroscience. Edinburgh has been voted 'best place to live in Britain', and has many exciting cultural and student activities. Students with a strong background in computer science, mathematics, physics, or engineering are particularly welcome to apply. Motivated students with other backgrounds will also be considered. Up to 12 full studentships (?12,600-?14,000 pa) are available to UK students and a small number of EU students. Non-EU/non-UK applicants will need to provide their own funding and evidence thereof. Further information and application forms can be obtained from: http://www.anc.ed.ac.uk/dtc The application deadline is 15 April 2008 for entry September 2008. From roland.baddeley at bristol.ac.uk Thu Mar 27 12:13:49 2008 From: roland.baddeley at bristol.ac.uk (Roland Baddeley) Date: Thu, 27 Mar 2008 16:13:49 -0000 Subject: Connectionists: Phd position studying motion camouflage available at Bristol University Message-ID: <010601c89025$9cf8a630$d6e9f290$@baddeley@bristol.ac.uk> PhD position available on Motion Camouflage A three year fully-funded CASE studentship at the University of Bristol is available to study animal camouflage. In particular the project will investigate how moving animals minimize their visibility. The student will be primarily based in the Department of Experimental Psychology, but the project is strongly inter-disciplinary (at the interface between biology, perceptual psychology and computer vision) and will be co-supervised by Roland Baddeley and Nick Scott-Samuel (Department of Experimental Psychology), Innes Cuthill (School of Biological Sciences) and Adam Shohet (from the defence research company QinetiQ). The student will also be a member of the Bristol Vision Institute, one of the university's prioritised research themes. Bristol has an outstanding strength in this field, spanning four University Faculties (Science, Engineering, Medicine and Art) - including the Departments of Experimental Psychology, Biological Sciences, Computer Science, Engineering Mathematics, Mathematics, Electrical and Electronic Engineering, Bristol Eye Hospital, Anatomy and History of Art. There will be a fair amount of flexibility on how this problem is approached, including approaches based on 1) psychophysics using human observers: manipulating various characteristics of artificial animal camouflage patterns within natural realistic backgrounds and observing which factors affect their visibility. 2) Natural image statistics and the statistics of animal coloration patterns: viewing both backgrounds and animal coloration patterns as textures, and using machine learning techniques to look at the mapping between environmental niche, and the coloration patterns displayed. 3) Looking at the spatio-temporal statistics of animal environments with a view to seeing which aspects of animal coloration will aid in reducing the visibility of a moving animal; and 4) Constructing and comparing various simple ideal observer models of predator/prey detection, and comparing these with observed behaviour. This list is not exclusive, but as can be seen, the position would be of potential interest not only to a behavioural ecologist who wants to learn about vision, image analysis and computer modelling, but also a more computational person who would like to apply their skills in a really very interesting area. The list of supervisors includes people with interests and skills in areas ranging from motion perception, to image modelling, to behavioural ecology, to the application of these ideas to designing man-made camouflage. To apply, download and fill in the form "Postgraduate research programme - application form" at http://www.bris.ac.uk/prospectus/postgraduate/2008/intro/8. Note that where the form requires you to state the source of funding, put "Already secured - CASE Award funded by QinetiQ" and in the section "Outline of proposed research" put "Not applicable - research proposal written by supervisors". Send the completed application form to the Faculty of Science (NOT the supervisors) at the address given. The web page also has referee forms which you should download, send to your (two) referees, and ask them to send the references directly to the Faculty of Science. For more information email Roland Baddeley at: Roland.Baddeley at bristol.ac.uk In any case, it would also be a good idea to email Roland to say you have applied, after contacting Innes Cuthill, so that we can chase up the Faculty Office if they are slow in passing information on. A poster version of this message is available at http://fleeting.psy.bris.ac.uk/Motion%20camouflage.pdf -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080327/43981455/attachment.html From bengioy at iro.umontreal.ca Thu Mar 27 13:38:44 2008 From: bengioy at iro.umontreal.ca (Yoshua Bengio) Date: Thu, 27 Mar 2008 13:38:44 -0400 Subject: Connectionists: post-doc announcement, learning deep architectures Message-ID: <47EBDBA4.7010905@iro.UMontreal.CA> Dear Colleagues, Please find below an announcement for a post-doc position in my lab, on the topic of learning algorithms for deep architectures. POST-DOCTORAL FELLOWSHIP Starting date: now to January 2009 Duration: one or two years Location: University of Montreal, CS dept, machine learning lab (http://www.iro.umontreal.ca/~lisa) Sponsored by an NSERC strategic grant and a Google grant. Faculty involved in the research: Yoshua Bengio, Pascal Vincent, Douglas Eck at UdeM, collaboration with Geoff Hinton at UofT and Yann Le Cun at NYU in CIAR's NCAP program (http://www.ciar.ca/web/home.nsf/pages/ncap) Salary: negotiable premium on top of NSERC baseline. The candidate should already have a strong machine learning background, displaying skills in algorithms and mathematics (statistics, probabilility, optimization, linear algebra). Preference will be given to candidates having previously conducted research involving graphical models (especially with hidden variables), unsupervised learning of factor models, and / or neural networks. Research topic of the grant: Theoretical results strongly suggest that in order to learn the kind of complicated functions that can represent high-level abstractions (e.g. in vision, language, and other AI-level tasks), one may need "deep architectures", which are composed of multiple levels of non-linear operations (such as in neural nets with many hidden layers). Searching the parameter space of deep architectures is a difficult optimization task, but learning algorithms (e.g. Deep Belief Networks) have recently been proposed to tackle this problem with notable success, beating the state-of-the-art in certain areas. The grant focusses on improving and expanding upon the new crop of learning algorithms that have been proposed to address the difficult optimization task that learning deep architectures entails, and in particular the discovery of multiple levels of representation that capture and disentangle the main factors of variation explaining the data distribution. The algorithms will be tested and geared towards large datasets involving images, text, and music, some artificially generated and some real. For more on this topic, see the web page of this recent workshop held at NIPS'2007: http://www.iro.umontreal.ca/~lisa/twiki/bin/view.cgi/Public/DeepLearningWorkshopNIPS2007 -- Yoshua Bengio From dayan at gatsby.ucl.ac.uk Thu Mar 27 18:01:49 2008 From: dayan at gatsby.ucl.ac.uk (Peter Dayan) Date: Thu, 27 Mar 2008 22:01:49 +0000 Subject: Connectionists: Gatsby Postdoc Training Fellowships In-Reply-To: <20070708230220.GA2602@crick.gatsby.ucl.ac.uk> References: <20061013122857.GA10331@flies.gatsby.ucl.ac.uk> <20070708230220.GA2602@crick.gatsby.ucl.ac.uk> Message-ID: <20080327220149.GA13656@crick.gatsby.ucl.ac.uk> Postdoctoral Training Fellowships - Theoretical Neuroscience The Gatsby Computational Neuroscience Unit invites applications for postdoctoral training fellowships in theoretical neuroscience and related areas. The Gatsby Unit is a centre for theoretical neuroscience and machine learning, focusing on the interpretation of neural data, population coding, perceptual processing, neural dynamics, neuromodulation, and learning. The Unit also has significant interests across a range of areas in machine learning. For further details of our research please see: http://www.gatsby.ucl.ac.uk/research.html The Unit provides a unique environment in which a critical mass of theoreticians interact closely with each other and with other world-class research groups in related departments at UCL, including Anatomy, Computer Science, Functional Imaging, Physics, Physiology, Psychology, Neurology, Ophthalmology, and Statistics, and the cross-faculty Centre for Computational Statistics and Machine Learning. The Unit's visitor and seminar programmes enable staff and students to engage with leading researchers from across the world. Candidates must have a strong analytical background and demonstrable interest and expertise in theoretical neuroscience. Salaries are competitive, based on experience and achievement. Funding for the positions is available for an initial period of between one and two years. Applicants should send in pdf, plain text or Word format a CV, a statement of research interests, and the names and full contact details (including e-mail addresses) of three referees to: asstadmin at gatsby.ucl.ac.uk Applicants are directed to further particulars about the positions available from: http://www.gatsby.ucl.ac.uk/vacancies The closing date for applications is 27 April 2008. From olivier.buffet at loria.fr Tue Mar 25 11:21:38 2008 From: olivier.buffet at loria.fr (Olivier Buffet) Date: Tue, 25 Mar 2008 16:21:38 +0100 Subject: Connectionists: Call for Participation: 6th International Planning Competition (Uncertainty Part) Message-ID: <47E91882.6000500@loria.fr> Call for Participation: ----------------------- 6th International Planning Competition (Uncertainty Part) IMPORTANT: the *POMDP* track is back ! Organizers: ----------- Daniel Bryce, SRI International Olivier Buffet, LORIA-INRIA [ ippc-2008-organizers at loria.fr ] Overview: --------- The past two IPCs have included tracks for probabilistic and non-deterministic planning, and this call for participation seeks feedback from potential competitors in the upcoming competition. In addition to the information contained here, the organizers have setup a wiki at: http://ippc-2008.loria.fr/ to exchange software and test problems, as well as a mailing list (subscribe by sending an email with the subject "subscribe ippc-2008" to mailto:sympa at loria.fr, what can be done with the following link: mailto:sympa at loria.fr?subject=subscribe%20ippc-2008 ). The competition will include tracks for - non-observable non-deterministic (conformant) planning, - observable non-deterministic planning, - fully observable probabilistic planning and - partially observable probabilistic planning (if at least 4 participants enter the track). More details on these tracks and on how the competition will be run can be found on the official site for the uncertainty part of the IPC: http://ippc-2008.loria.fr/ Timetable: ---------- * April 1st Registration Deadline * April 1st Release of 1-2 domains in each track for practice * June-August Competition Participant Registration Form: ------------------------------ Send it to ippc-2008-organizers at loria.fr . You may want to fill one form per planner. * Planner name: * Team members and contact information: * Tracks of interests: (indicate [yes/no]) o Fully-Observable Non-Deterministic [ ] o Non-Observable Non-Deterministic [ ] o Fully-Observable Probabilistic [ ] o Partially-Observable Probabilistic [ ] * Comments/Questions (schedule, language, etc.): Note: persons who already declared their interest in the uncertainty part of the competition should fill and send back this form if their situation regarding the competition has changed. From frederic.alexandre at loria.fr Thu Mar 27 10:14:13 2008 From: frederic.alexandre at loria.fr (Frederic Alexandre) Date: Thu, 27 Mar 2008 15:14:13 +0100 Subject: Connectionists: Postdoc position on Learning and Emotions Message-ID: <47EBABB5.5010808@loria.fr> A postdoc position is available in the CORTEX group, INRIA-Nancy, France, in the domain of Learning and Emotions to begin by end of 2008. Candidates should apply on-line (see address below) but can also directly contact me for any question. alexandre http://www.inria.fr/travailler/mrted/en/postdoc/details.html?id=PNGFK026203F3VBQB6G68LOE1&LOV5=4508&LOV2=4490&LOV6=4513&LG=EN&Resultsperpage=20&nPostingID=1896&nPostingTargetID=4868&option=52&sort=DESC&nDepartmentID=19 Learning and Emotions Position type: Post-doctoral Fellow Functional area: Nancy Research theme: Cognitive systems Project: CORTEX Environnement http://cortex.loria.fr/ Missions In the domain of machine learning, learning is traditionally considered as an optimisation process, where one tries to appromimate as accurately and as quickly as possible a function to get the best performances with regard to a global criterion. As studies from biology and psychology about the role of emotions in learning are considered, it appears that learning is not a linear neither global process : each new example or situation does not trigger the same level of learning but is modulated by emotions. For example, it is sufficient to be burned one time to learn that fire is dangerous. Also, simple innate or learned emotional reactions can be used as a scaffolding to realize more complex learning. For example being attracted by novelty is interesting to quickly explore a scene and can be a solution to the curse of dimensionality. In the framework of the embodiment of cognition and more particularly of autonomous robotics, it is important to modulate learning, depending on the situations, particularly to manage critical situations and to incrementally learn in highly dimensional spaces, as encountered in real environments. The goal of this postdoctoral position is to help us think to the emotional solution to develop new methodologies of learning, to find in the neuroscience domains structural and functional hints about the role of emotions in learning and to study how these hints can be introduced in neuronal modules compatible with those developped in our team. Activit?s Step 1 : bibliographical studies on two domains : (i) description in different domains of neuroscience (physiology, cognitive neuroscience, behavioral biology) of neuronal expression (central and peripheric) of emotions and their impact on the rational brain ; (ii) familiarization with the formalism of neuronal computations developped in the team (neural fields) and with sensorimotor models previously developped. Step 2 : study and experimentation of bio-inspired models previously developped in this perspective and particularly pavlovian conditioning models (ex : Schmajuk), amygdala models (ex : Moren), models linking basal ganglia with the prefrontal lobe (ex : Doya, Girard). The software developments will be made with the formalism of neuronal computation developped in the team (neural fields). Step 3 : development of robotic experiments : choice of a scenario of incremental learning ; determination of emotional stimuli and of their embodiment ; realisation of a protocole of interaction of the robot with the environment including a series of learning stages from repondant conditioning to instrumental conditioning. Campaign of tests to determine the performances and characteristics of such a learning and comparison with simple sensorimotor learning. Comp?tences et Profil First of all, the applicant should have an experience and education in cognitive neuroscience, particularly in the emotional domain. An experience in bio-inspired neuronal modeling is also an important point. Abilities in computer science should be mentionned. A knowledge and practice in neural fields would be appreciated. Duration of the contract : 12 to 24 months -- Frederic ALEXANDRE http://www.loria.fr/~falex/ -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080327/a81a4c91/attachment.html From L.Berthouze at sussex.ac.uk Fri Mar 28 07:09:07 2008 From: L.Berthouze at sussex.ac.uk (Luc Berthouze) Date: Fri, 28 Mar 2008 11:09:07 +0000 Subject: Connectionists: CFP Epigenetic Robotics 2008 (new deadline: 16 April 2008) Message-ID: <2965ED92-1FC3-4742-8BFA-B03E08361EA4@sussex.ac.uk> ***NOTE NEW SUBMISSION DEADLINE!*** 16 April 2008 CALL FOR PAPERS: Epigenetic Robotics 2008 31 July - 2 August, 2008, Brighton, UK Eighth International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems http://www.epigenetic-robotics.org Email: epirob08 at epigenetic-robotics.org ***2008 Conference Theme*** Evolution and Development: Related Processes of Change Location: University of Sussex, Brighton, UK Important Dates: ---------------- 16 April 2008: Deadline for submission of papers & posters 31 May 2008: Notification of acceptance of papers & posters 30 June 2008: Deadline for camera ready papers 31 July - 2 August 2008: EpiRob08 @ Brighton Keynote Speakers ----------------- Prof. Eva Jablonka (Tel Aviv University, Israel) Prof. Susan Oyama (John Jay College, New York, USA) Dr. Domenico Parisi (Institute of Cognitive Sciences and Technologies, CNR, Rome, Italy) Prof. Claudio Stern (University College London, UK) Conference Theme: ------------------ In the past 7 years, the Epigenetic Robotics annual conference has established itself as a unique place where original interdisciplinary research from developmental sciences, neuroscience, biology, cognitive robotics, and artificial intelligence is being presented. Psychological theory and empirical evidence is being used to inform epigenetic robotic models, and these models can be used as theoretical tools to make experimental predictions in developmental psychology. As in previous years, we encourage submissions from researchers whose work broadly intersects the fields (and subdisciplines) of developmental science, robotics, and neuroscience. As a special feature, this year we are also highlighting a specific organizational theme: evolution and development as related processes of change. The particular focus of this theme is on the dynamic interplay between ontogeny and phylogeny. In other words, how do new abilities and skills that emerge during development influence the path of evolution, and how do subsequent evolutionary changes help to create new developmental trajectories? This is a question that fits well within the mission of epigenetic robotics, as it spans not only a wide range of research areas and academic disciplines (e.g., biology, psychology, AI and machine learning, linguistics, anthropology, etc.) but also a broad spectrum of spatial and temporal scales (e.g., neurons, brains, social communities, cultures, etc.). We are especially interested in submissions that will enhance the emerging dialog between evolutionary and developmental perspectives. Relevant topics include, but are not limited to: - Artificial embryology - Morphogenesis, differentiation, and regulation - Behavioral inheritance and social learning - The evolution of language acquisition - Phylogenetic constraints on perceptual processing (e.g., face perception) - Neuroplasticity and the evolution of cognition - Evolutionary influences on mother-infant bonding - Modularity of mind (evolutionary constraints on neural processing) - Tool-use and problem-solving in humans, non-human primates, and machines Modes of Submission: -------------------- (1) Regular Submission (8-page max). After review, regular submissions will either be accepted or rejected (no revision as short papers or posters). Regular submissions will be allocated 8 pages in the Proceedings. (2) Abstract Submission (1-page max). After review, selected authors will be invited to present a poster. Abstract submissions will be allocated 2 pages in the Proceedings. Submission instructions will be available from the EpiRob website: http://www.epigenetic-robotics.org. Email submissions and/or questions regarding the submission process to epirob08-PC at epigenetic-robotics.org. Related Events: --------------- Note that "Artificial Life XI" (http://www.alifexi.org/) will be hosted in Winchester, UK (5-8 August 2008), and that we encourage participants to attend both meetings. Organizing Committee: --------------------- Christian Balkenius (Lund University, Sweden) Luc Berthouze (University of Sussex, UK) Lola Ca?amero (University of Hertfordshire, UK) Matthew Schlesinger (Southern Illinois University, USA) --- Dr Luc Berthouze, Senior Lecturer Centre for Computational Neuroscience and Robotics (CCNR) Department of Informatics University of Sussex Brighton BN1 9QH, UK Tel: +44 1273 877206 Fax: +44 1273 877873 From t.heskes at science.ru.nl Fri Mar 28 11:33:45 2008 From: t.heskes at science.ru.nl (Tom Heskes) Date: Fri, 28 Mar 2008 16:33:45 +0100 Subject: Connectionists: Neurocomputing volume 71 (issues 4-6) Message-ID: <47ED0FD9.5060905@science.ru.nl> Neurocomputing volume 71 (issues 4-6) ------- SPECIAL PAPERS (Neural networks: Algorithms and applications, ISNN 2007) Neural networks: Algorithms and applications (editorial) Derong Liu, Huaguang Zhang and Sanqing Hu LMI approach for global robust stability of Cohen?Grossberg neural networks with multiple delays C. Ji, H.G. Zhang and Y. Wei Analysis of the dynamical behavior of a feedback auto-associative memory Mahmood Amiri, Sohrab Saeb, Mohammad Javad Yazdanpanah and S. Ali Seyyedsalehi Global exponential stability of a class of BAM networks with time-varying delays and continuously distributed delays Baoxian Wang, Jigui Jian and Chuande Guo LMI-based finite-time boundedness analysis of neural networks with parametric uncertainties Yanjun Shen and Cuicui Li Stability analysis of high-order Hopfield type neural networks with uncertainty Bingji Xu, Qun Wang and Xiaoxin Liao Positive invariant and global exponential attractive sets of neural networks with time-varying delays Xiaoxin Liao, Qi Luo and Zhigang Zeng Soft-computing techniques and ARMA model for time series prediction I. Rojas, O. Valenzuela, F. Rojas, A. Guillen, L.J. Herrera, H. Pomares, L. Marquez and M. Pasadas An artificial neural network method for combining gene prediction based on equitable weights You Zhou, Yanchun Liang, Chengquan Hu, Liupu Wang and Xiaohu Shi Artificial-neural-networks-based surface roughness Pokayoke system for end-milling operations Bernie P. Huang, Joseph C. Chen and Ye Li Online prediction model based on support vector machine Wenjian Wang, Changqian Men and Weizhen Lu Using an adaptive self-tuning approach to forecast power loads Zhiling Lin, Dapeng Zhang, Liqun Gao and Zhi Kong A self-organizing fuzzy neural network and its applications to function approximation and forecast modeling Junfei Qiao and Huidong Wang Linear programming minimum sphere set covering for extreme learning machines Xun-Kai Wei and Ying-Hong Li Incremental extreme learning machine with fully complex hidden nodes Guang-Bin Huang, Ming-Bin Li, Lei Chen and Chee-Kheong Siew A novel framework for automatic generation of fuzzy neural networks Meng Joo Er and Yi Zhou Recursive DLS solution for extreme learning machine-based channel equalizer JunSeok Lim A clustering-based approach for inferring recurrent neural networks as gene regulatory networks Wei-Po Lee and Kung-Cheng Yang Support vector machine classification for large data sets via minimum enclosing ball clustering Jair Cervantes, Xiaoou Li, Wen Yu and Kang Li Unsupervised learning neural network with convex constraint: Structure and algorithm Hengqing Tong, Tianzhen Liu and Qiaoling Tong The estimate for approximation error of neural networks: A constructive approach Feilong Cao, Tingfan Xie and Zongben Xu A RBFNN approach for DoA estimation of ultra wideband antenna array Min Wang, Shuyuan Yang, Shunjun Wu and Feng Luo A two stage neural network-based personal identification system using handprint Jun Kong, Yinghua Lu, Shuhua Wang, Miao Qi and Hongzhi Li Design of an artificial bionic neural network to control fish-robot's locomotion Daibing Zhang, Dewen Hu, Lincheng Shen and Haibin Xie A behavior controller based on spiking neural networks for mobile robots Xiuqing Wang, Zeng-Guang Hou, Anmin Zou, Min Tan and Long Cheng ------- SPECIAL PAPERS (50 Years of Artificial Intelligence: a Neuronal Approach) 50 years of artificial intelligence: A neuronal approach Pages 667-669 Antonio Fern?ndez-Caballero, Jos? Mira and Gustavo Deco Symbols versus connections: 50 years of artificial intelligence Jos? Mira Mira On the nature of neural information: A critique of the received view 50 years later Xabier Barandiaran and Alvaro Moreno Rate versus time representation of high-frequency spectral notches in the peripheral auditory system: A computational modeling study Enrique A. Lopez-Poveda, Ana Alves-Pinto, Alan R. Palmer and Almudena Eustaquio-Mart?n A conceptual frame with two neural mechanisms to model selective visual attention processes Jos? Mira, Ana E. Delgado, Mar?a T. L?pez, Antonio Fern?ndez-Caballero and Miguel A. Fern?ndez Topos: Spiking neural networks for temporal pattern recognition in complex real sounds Pablo Gonz?lez-Nalda and Blanca Cases ANN+GIS: An automated system for property valuation Noelia Garc?a, Mat?as G?mez and Esteban Alfaro A robust model of the neuronal regulator of the lower urinary tract based on artificial neural networks Francisco Maci? P?rez, Juan Manuel Garc?a Chamizo, Antonio Soriano Pay? and Daniel Ruiz Fern?ndez On the application of different evolutionary algorithms to the alignment problem in statistical machine translation Luis Rodr?guez, Ismael Garc?a-Varea and Jos? A. G?mez A retinomorphic architecture based on discrete-time cellular neural networks using reconfigurable computing J. Javier Mart?nez, F. Javier Toledo, Eduardo Fern?ndez and Jos? M. Ferr?ndez Parametric improvement of lateral interaction in accumulative computation in motion-based segmentation Javier Mart?nez-Cantos, Enrique Carmona, Antonio Fern?ndez-Caballero and Mar?a T. L?pez ------- REGULAR PAPERS Efficient design of neural network tree using a new splitting criterion Pradipta Maji Dynamic modular fuzzy neural classifier with tree-based structure identification Minas Pertselakis and Andreas Stafylopatis Existence and globally exponential stability of periodic solution of BAM neural networks with impulses and recent-history distributed delays Haibo Gu, Haijun Jiang and Zhidong Teng Robust stability of discrete-time stochastic neural networks with time-varying delays Yurong Liu, Zidong Wang and Xiaohui Liu Asymptotic and robust stability of genetic regulatory networks with time-varying delays Fengli Ren and Jinde Cao A max-piecewise-linear neural network for function approximation Chengtao Wen and Xiaoyan Ma Dynamic visual selective attention model Sang-Woo Ban, Inwon Lee and Minho Lee ConSOM: A conceptional self-organizing map model for text clustering Yuanchao Liu, Xiaolong Wang and Chong Wu Stability of non-autonomous bidirectional associative memory neural networks with delay Minghui Jiang and Yi Shen Input?output modelling with decomposed neuro-fuzzy ARX model Marjan Golob and Boris Tovornik Adaptive neural network algorithm for control design of rigid-link electrically driven robots S.N. Huang, K.K. Tan and T.H. Lee A combined adaptive network and fuzzy inference system (ANFIS) approach for overcurrent relay system M. Geethanjali and S. Mary Raja Slochanal PSO trained ANN-based differential protection scheme for power transformers M. Geethanjali, S. Mary Raja Slochanal and R. Bhavani Geometrical synthesis of MLP neural networks Rita Delogu, Alessandra Fanni and Augusto Montisci An orthogonal forward regression technique for sparse kernel density estimation S. Chen, X. Hong and C.J. Harris Efficient computations of gapped string kernels based on suffix kernel Chuanhuan Yin, Shengfeng Tian, Shaomin Mu and Chong Shao EvOL-Neuron: Neuronal morphology generation Ben Torben-Nielsen, Karl Tuyls and Eric Postma On blind source separation using generalized eigenvalues with a new metric Hai-lin Liu and Yiu-ming Cheung Artificial neural network using pattern recognition for security assessment and analysis K. Shanti Swarup Simulating global properties of electroencephalograms with minimal random neural networks Peter beim Graben and J?rgen Kurths An adaptive fuzzy c-means clustering-based mixtures of experts model for unlabeled data classification Hong-Jie Xing and Bao-Gang Hu A unified framework to exploit information in BCI data for continuous prediction Xiaoyuan Zhu, Jiankang Wu, Yimin Cheng and Yixiao Wang Asymptotic behavior of discrete solutions to delayed neural networks with impulses Hong Zhang and Lansun Chen ------- BRIEF PAPERS New global exponential stability results for neutral type neural networks with distributed time delays R. Rakkiyappan and P. Balasubramaniam Novelty detection with constructive probabilistic neural networks Adriano L.I. Oliveira, Flavio R.G. Costa and Clovis O.S. Filho Evolving artificial neural networks using an improved PSO and DPSO Jianbo Yu, Shijin Wang and Lifeng Xi Using a bank of binary Hopfield networks as constraints solver in hybrid algorithms Sancho Salcedo-Sanz, Emilio G. Ortiz-Garc?a, Angel M. P?rez-Bellido and Jose A. Portilla-Figueras Stability analysis of Cohen?Grossberg neural networks with time-varying and distributed delays Tao Li and Shu-min Fei MACBSE: Extracting signals with linear autocorrelations Zhenwei Shi, Dan Zhang and Changshui Zhang A novel condensing tree structure for rough set feature selection Ming Yang and Ping Yang A note on ?solving arithmetic problems using feed-forward neural networks? Suneeta Agarwal View-independent face recognition with Mixture of Experts Reza Ebrahimpour, Ehsanollah Kabir, Hossein Esteky and Mohammad Reza Yousefi ------- JOURNAL SITE: http://www.elsevier.com/locate/neucom SCIENCE DIRECT: http://www.sciencedirect.com/science/issue/5660-2008-999289995-679357 From t.heskes at science.ru.nl Fri Mar 28 11:36:09 2008 From: t.heskes at science.ru.nl (Tom Heskes) Date: Fri, 28 Mar 2008 16:36:09 +0100 Subject: Connectionists: Neurocomputing volume 71 (issues 7-9) Message-ID: <47ED1069.30202@science.ru.nl> Neurocomputing volume 71 (issues 7-9) ------- SPECIAL PAPERS (Progress in Modeling, Theory, and Application of Computational Intelligence, ESANN 2007) Progress in modeling, theory, and application of computational intelligence (editorial) Fabrice Rossi, Michael Biehl and Cecilio Angulo Bah?n Temporal coding with synchronization and acceleration as complementary mechanisms Thomas Burwick Contribution of the GABA shift to the transition from structural initialization to working stage in biologically realistic networks Andreas Herzog, Karsten Kube, Bernd Michaelis, Ana D. de Lima, Thomas Baltz and Thomas Voigt Delay learning and polychronization for reservoir computing H?l?ne Paugam-Moisy, R?gis Martinez and Samy Bengio Improving reservoirs using intrinsic plasticity Benjamin Schrauwen, Marion Wardermann, David Verstraeten, Jochen J. Steil and Dirk Stroobandt Syntactic systematicity in sentence processing with a recurrent self-organizing network Igor Farka? and Matthew W. Crocker Natural Actor-Critic Jan Peters and Stefan Schaal Following non-stationary distributions by controlling the vector quantization accuracy of a growing neural gas network Herv? Frezza-Buet A multi-objective approach to RBF network learning Illya Kokshenev and Antonio Padua Braga Learning dynamics and robustness of vector quantization and neural gas Aree Witoelar, Michael Biehl, Anarta Ghosh and Barbara Hammer Support vector machines for interval discriminant analysis C. Angulo, D. Anguita, L. Gonzalez-Abril and J.A. Ortega Kernel-based online machine learning and support vector reduction Sumeet Agarwal, V. Vijaya Saradhi and Harish Karnick A kernel-based method for pattern extraction in random process signals Majid M. Beigi and Andreas Zell Causal reasoning by evaluating the complexity of conditional densities with kernel methods Xiaohai Sun, Dominik Janzing and Bernhard Sch?lkopf Batch kernel SOM and related Laplacian methods for social network analysis Romain Boulet, Bertrand Jouve, Fabrice Rossi and Nathalie Villa Mixtures of robust probabilistic principal component analyzers C?dric Archambeau, Nicolas Delannay and Michel Verleysen Learning topology of a labeled data set with the supervised generative Gaussian graph Pierre Gaillard, Micha?l Aupetit and G?rard Govaert Collaborative filtering with interlaced generalized linear models Nicolas Delannay and Michel Verleysen Agglomerative independent variable group analysis Antti Honkela, Jeremias Sepp? and Esa Alhoniemi Estimating the number of components in a mixture of multilayer perceptrons M. Olteanu and J. Rynkiewicz ------- REGULAR PAPERS Adaptive compliant force?motion control of coordinated non-holonomic mobile manipulators interacting with unknown non-rigid environments Zhijun Li, Weidong Chen and Jun Luo A sequential multi-category classifier using radial basis function networks S. Suresh, N. Sundararajan and P. Saratchandran An asynchronous recurrent linear threshold network approach to solving the traveling salesman problem E.J. Teoh, K.C. Tan, H.J. Tang, C. Xiang and C.K. Goh Stability and synchronization of random brain networks with a distribution of connection strengths R.T. Gray and P.A. Robinson Time series prediction using evolving radial basis function networks with new encoding scheme Haiping Du and Nong Zhang Evaluation of neural networks-based controllers in batch polymerisation of methyl methacrylate E.E. Ekpo and I.M. Mujtaba Limited receptive area neural classifier for texture recognition of mechanically treated metal surfaces O. Makeyev, E. Sazonov, T. Baidyk and A. Mart?n Bifurcation analysis in a discrete-time single-directional network with delays Shangjiang Guo, Xianhua Tang and Lihong Huang A multi-swarm optimizer based fuzzy modeling approach for dynamic systems processing Ben Niu, Yunlong Zhu, Xiaoxian He and Hai Shen Error-driven active learning in growing radial basis function networks for early robot learning Qinggang Meng and Mark Lee A theoretical framework for multiple neural network systems Mike W. Shields and Matthew C. Casey Third-order generalization: A new approach to categorizing higher-order generalization Richard Neville Blind separation of fetal electrocardiograms by annealed expectation maximization Jiann-Ming Wu A definition of partial derivative of random functions and its application to RBFNN sensitivity analysis Xi-Zhao Wang, Chun-Guo Li, Daniel So Yeung, ShiJi Song and HuiMin Feng On the implicit acquisition of a context-free grammar by a simple recurrent neural network Bo Cartling An algorithm for extracting fetal electrocardiogram Yunxia Li and Zhang Yi Global asymptotic stability of delay BAM neural networks with impulses via nonsmooth analysis Zhen Wen and Jitao Sun Incremental margin algorithm for large margin classifiers Saul C. Leite and Raul Fonseca Neto Adaptive control of nonlinear PID-based analog neural networks for a nonholonomic mobile robot Jun Ye An estimation of the domain of attraction for recurrent neural networks with time-varying delays Jun Xu, Yong-Yan Cao, Daoying Pi and Youxian Sun Incorporating prior knowledge in support vector machines for classification: A review Fabien Lauer and G?rard Bloch Global exponential periodicity of three-unit neural networks in a ring with time-varying delays Chuangxia Huang, Yigang He, Lihong Huang and Mingyong Lai Evolutionary ensemble of diverse artificial neural networks using speciation Kyung-Joong Kim and Sung-Bae Cho Mathematical-model-based design of silicon burst neurons Takashi Kohno and Kazuyuki Aihara A neural model for the integration of stereopsis and motion parallax in structure from motion Julian Martin Fernandez and Bart Farell Wavelet packets approach to blind separation of statistically dependent sources Ivica Kopriva and Damir Ser?ic' A parameterless feature ranking algorithm based on MI Jin-Jie Huang, Yun-Ze Cai and Xiao-Ming Xu Morphologically constrained ICA for extracting weak temporally correlated signals Zhi-Lin Zhang An error-counting network for pattern classification Kar-Ann Toh Spike-timing-dependent plasticity in small-world networks Karsten Kube, Andreas Herzog, Bernd Michaelis, Ana D. de Lima and Thomas Voigt Delay-dependent stability analysis for impulsive neural networks with time varying delays Shujun Long and Daoyi Xu Bayesian nonstationary source separation Qinghua Huang, Jie Yang and Yue Zhou ------- BRIEF PAPERS Facial expression recognition based on two-dimensional discriminant locality preserving projections Ruicong Zhi and Qiuqi Ruan A new fuzzy approach for handling class labels in canonical correlation analysis Yanyan Liu, Xiuping Liu and Zhixun Su Neural networks stabilization and disturbance attenuation for nonlinear switched impulsive systems Fei Long and Shumin Fei A neural networks learning algorithm for minor component analysis and its convergence analysis Dezhong Peng, Zhang Yi, JianCheng Lv and Yong Xiang ------- CORRIGENDUM Corrigendum to ?Exponential state estimation for recurrent neural networks with distributed delays? [Neurocomputing 71(1?3) (2007) 428?438] Tao Li and Shu-min Fei ------- JOURNAL SITE: http://www.elsevier.com/locate/neucom SCIENCE DIRECT: http://www.sciencedirect.com/science/issue/5660-2008-999289992-683423 From mr287 at georgetown.edu Mon Mar 31 16:47:55 2008 From: mr287 at georgetown.edu (Maximilian Riesenhuber) Date: Mon, 31 Mar 2008 16:47:55 -0400 Subject: Connectionists: Postdoctoral Position: EEG of fast visual recognition Message-ID: <47F14DFB.1040608@georgetown.edu> Postdoctoral Position: EEG of fast visual recognition Riesenhuber Lab Department of Neuroscience Georgetown University Washington, DC We have an opening for a postdoctoral fellow, starting immediately, to participate in a research project studying the neural mechanisms underlying "fast" object recognition using high-density EEG, focusing on attentional requirements and interference between recognition tasks (e.g., under dual-task conditions), as part of a larger collaborative project aiming to develop a real-time neurally-based target detection system combining machine and biological vision. A strong quantitative background and experience in neural data analysis are required. Experience with EEG and psychophysics is a strong plus, as is training in biological and/or machine vision. Experience with Mac OS X, MATLAB, and C++ preferred. Our lab investigates the computational mechanisms underlying human object recognition as a gateway to understanding information processing and learning in cortex. In our work, we combine computational modeling with psychophysical, fMRI and most recently EEG data from our own lab and collaborators, as well as with single unit data obtained in collaboration with physiology labs. For more information, see http://maxlab.neuro.georgetown.edu. The position is for one year, with the option to renew for two additional years, given satisfactory performance and available funding. Salary is competitive. Candidates should be US citizens or permanent residents. Interested candidates should send a CV, a brief (1 page) statement of research interests, representative reprints, and the names and contact information of three references by email to Maximilian Riesenhuber (mr287 at georgetown.edu). Review of applications will begin immediately, and will continue until the position is filled. Informal inquiries are welcome. ********************************************************************** Maximilian Riesenhuber phone: 202-687-9198 Department of Neuroscience fax: 202-784-3562 Georgetown University Medical Center email: mr287 at georgetown.edu Research Building Room WP-12 3970 Reservoir Rd., NW Washington, DC 20007 http://maxlab.neuro.georgetown.edu ********************************************************************** From online at gavrila.net Fri Mar 28 14:25:26 2008 From: online at gavrila.net (online@gavrila.net) Date: Fri, 28 Mar 2008 19:25:26 +0100 Subject: Connectionists: JOB: POST-DOC IN COMPUTER VISION - UNIV. OF AMSTERDAM, NL Message-ID: <20080328192526.sbkv3fa48wgsow4w@webmail.df.eu> The Intelligent Autonomous System (IAS) Group of the University of Amsterdam, The Netherlands, has an immediate opening for a Post-Doctoral Researcher in the area of computer vision and temporal data modelling. The open position considers the topic of video-based HUMAN ACTIVITY RECOGNITION in dynamic and cluttered environments. The particular application context is abnormal behaviour detection in surveillance (e.g. aggression), but generality to other scenarios is desirable. Issues such as learning human appearance and motion, use of low-level features vs. 3D body pose recovery, tracking and movement classification are to be addressed. The open position furthermore investigates the fusion of video and audio information, and the role of context modelling. A unique realistic data set collected at a train station with professional actors and multiple synchronized cameras and microphones is available. We are looking for a highly motivated individual with an (existing or soon-expected) Ph.D. in the domain of computer vision and pattern recognition, preferably in the "Looking at People" area. The successful applicant will have a proven track record and be comfortable in formulating and pursuing research goals independently. The candidate will furthermore have good communication skills and able to collaborate effectively with other members of a research team. A certain affinity towards turning complex techniques into real-world practice (with the associated strong programming skills) is important. Good English skills are essential. The open position involves an interesting research domain that provides rich publication potential. The Post-Doctoral Researcher will lead one or more PhD students and possibly several MS students, amplifying his/her impact. The University of Amsterdam hosts an internationally recognized vision group which offers ample opportunities for technical exchange, see http://www.science.uva.nl/research/isla/ Funding for this 2 yr post-doctoral position is provided by the Dutch Science Foundation NWO. Monthly salary ranges from EUR 2708 to EUR 3442 (brutto) depending on experience. Funding prospects after 2 years are very good, because of a forthcoming EU project. Inquiries are welcome. Prospective applicants please email - cover letter (explaining suitability) - resume - copy of academic record - references and - supporting materials, e.g. Ph.D. Thesis (draft), publications to Prof. Dr. D.M. Gavrila Intelligent Perception Systems Faculty of Science, University of Amsterdam [my-last-name]@science.uva.nl See also http://www.gavrila.net From charlie.kemp at bme.gatech.edu Sat Mar 29 13:17:09 2008 From: charlie.kemp at bme.gatech.edu (Charlie Kemp) Date: Sat, 29 Mar 2008 13:17:09 -0400 Subject: Connectionists: ICDL 2008: Call for Papers (*deadlines extended*) Message-ID: <47EE7995.9040804@bme.gatech.edu> Due to numerous requests, the organizing committee for ICDL 2008 has decided to extend the submission deadline until April 14, 2008. All related deadlines have been moved back by two weeks. ============================================================== 7th International Conference on Development and Learning Asilomar Conference Center, Monterey, California August 9th-12th, 2008, http://www.icdl08.org/ Call for Papers The scope of development and learning covered by this conference includes perceptual, cognitive, behavioral, emotional and all other mental capabilities that are exhibited by humans, higher animals, artificial systems and robots. Investigations of the biological and computational mechanisms of mental development are expected to improve our understanding of the working of the whole range of mental capabilities in humans and to enable autonomous development of these highly complex capabilities by robots and other artificial systems. The International Conference on Development and Learning strives to bring together researchers in neuroscience, psychology, artificial intelligence and robotics and other related areas to encourage understanding and cross-fertilization of the latest ideas and results from the different disciplines. ICDL 2008 will accept two types of submissions: 1) Full six-page paper submissions. Accepted papers will be included in the conference proceedings and will be selected for either an oral presentation or as a featured poster presentation. Featured posters will have a 1 minute "teaser" presentation as part of the main conference session and will be showcased in the poster sessions. Authors of accepted 6-page papers (whether they are selected for oral or poster presentation) will have the OPTION of archiving their papers through IEEE Xplore. 2) One-page poster abstract submissions. To encourage late-breaking results or for work that is not sufficiently mature for a full paper, ICDL will accept 1-page abstracts. These submissions will NOT be included in the conference proceedings. Accepted abstracts will be presented during the evening poster sessions. Important dates (*extended*): April 14, 2008: Submission deadline for Full (6 page) papers May 26, 2008: Accept/Reject notification for full papers June 4, 2008: Submission deadline for 1-page poster abstracts June 11, 2008: Accept/Reject notification for poster abstracts June 16, 2008: Camera-ready papers due Plenary Speakers: * Richard Aslin, U. of Rochester * Terry Jernigan, UCSD * Andrew Ng, Stanford General Chairs: * Jay McClelland, Stanford * Juyang Weng, Michigan State Program Chairs: * Gedeon Deak, UCSD * Brian Scassellati, Yale Sponsored by: * IEEE Computational Intelligence Society * Cognitive Science Society For more information please check the conference web site: http://www.icdl08.org/ From fredrik.linaker at accenture.com Mon Mar 31 07:57:15 2008 From: fredrik.linaker at accenture.com (fredrik.linaker@accenture.com) Date: Mon, 31 Mar 2008 13:57:15 +0200 Subject: Connectionists: Position: Researcher in Accenture's European technology lab Message-ID: <66076B9B818A594FAF5EFF4A11C63CCE02DF7F7A@EMEXM1116.dir.svc.accenture.com> Accenture Technology Labs Position: Permanent researcher Description: Accenture Technology Labs is the technology research and development (R&D) organization within Accenture. Accenture is a global management consulting, technology services and outsourcing company with more than 178,000 people in 49 countries. In addition to building cutting-edge technology demonstrators, our R&D professionals continually seek to develop next wave technologies and understand their impact on businesses. Working closely with Accenture's global groups, the Labs help clients innovate for competitive advantage. The Labs are located in Chicago (USA), Silicon Valley (USA), Sophia Antipolis (France), and Bangalore (India). The European location of Accenture Technology Labs is in Sophia Antipolis in France, one of Europe's leading science and technology parks with more than 1,200 international R&D organizations and companies. There, our multi-cultural Labs team members look at technological developments and applications likely to influence clients' businesses in Europe within the 2-5 year timeframe. The European Labs also host more than 90 client workshops per year demonstrating technological innovation applied to clients' businesses. Our European research team focuses more specifically on the following areas: Mobility and Sensors, Analytics and Insight, and Human Computer Interactions. People with a Connectionist background and interest tend to fit our team profile very well. Job summary: The role of an Accenture Technology Labs researcher is to conceive, plan, and conduct applied research projects producing original results of patentable and publishable scope and quality. Research deliverables include demonstration prototypes illustrating business applications of cutting-edge technologies. The researcher is also responsible for effectively communicating research results to both business and to scientific audiences. Location: Sophia Antipolis, France Requirements: - Out-of-the-box thinker - Ph.D. in Computer Science, Information Technologies or equivalent field - Experience ranging from recent graduates to several years of experience - Solid programming skills - Demonstrated ability to generate new ideas and innovate - Autonomous and self-starter - Excellent communication skills in English - A strong interest in leading edge technology and business How to apply? Send a CV and cover letter to fredrik.linaker at accenture.com (with the subject "Researcher Position") For more information visit: http://www.accenture.com/techlabs Best regards, Fredrik Linaker, PhD Research Manager, Accenture Technology Labs 449 route des Cr?tes BP 99, 06902 Sophia Antipolis, FRANCE Email: fredrik.linaker at accenture.com This message is for the designated recipient only and may contain privileged, proprietary, or otherwise private information. If you have received it in error, please notify the sender immediately and delete the original. Any other use of the email by you is prohibited.