From steve at cns.bu.edu Mon May 12 19:22:56 2008 From: steve at cns.bu.edu (Stephen Grossberg) Date: Mon, 12 May 2008 23:22:56 -0000 Subject: Connectionists: linking object category learning, spatial and object attention, and eye movement search Message-ID: The following article is now available at http://www.cns.bu.edu/Profiles/Grossberg : Fazl, A., Grossberg, S., & Mingolla, E. View-invariant object category learning, recognition, and search: How spatial and object attention are coordinated using surface-based attentional shrouds. Cognitive Psychology, in press. ABSTRACT How does the brain learn to recognize an object from multiple viewpoints while scanning a scene with eye movements? How does the brain avoid the problem of erroneously classifying parts of different objects together? How are attention and eye movements intelligently coordinated to facilitate object learning? A neural model provides a unified mechanistic explanation of how spatial and object attention work together to search a scene and learn what is in it. The ARTSCAN model predicts how an object's surface representation generates a form-fitting distribution of spatial attention, or "attentional shroud." All surface representations dynamically compete for spatial attention to form a shroud. The winning shroud persists during active scanning of the object. The shroud maintains sustained activity of an emerging view-invariant category representation while multiple view-specific category representations are learned and are linked through associative learning to the view-invariant object category. The shroud also helps to restrict scanning eye movements to salient features on the attended object. Object attention plays a role in controlling and stabilizing the learning of view-specific object categories. Spatial attention hereby coordinates the deployment of object attention during object category learning. Shroud collapse releases a reset signal that inhibits the active view-invariant category in the What cortical processing stream. Then a new shroud, corresponding to a different object, forms in the Where cortical processing stream, and search using attention shifts and eye movements continues to learn new objects throughout a scene. The model mechanistically clarifies basic properties of attention shifts (engage, move, disengage) and inhibition of return. It simulates human reaction time data about object-based spatial attention shifts, and learns with 98.1% accuracy and a compression of 430 on a letter database whose letters vary in size, position, and orientation. The model provides a powerful framework for unifying many data about spatial and object attention, and their interactions during perception, cognition, and action. Keywords: category learning, view-based learning, object recognition, spatial attention, object attention, parietal cortex, inferotemporal cortex, saccadic eye movements, attentional shroud, Adaptive Resonance Theory, surface perception, V2, V3A, V4, PPC, LIP, basal ganglia. From eero at cns.nyu.edu Thu May 15 18:36:57 2008 From: eero at cns.nyu.edu (Eero Simoncelli) Date: Thu, 15 May 2008 22:36:57 -0000 Subject: Connectionists: Conference: Sensory Coding and the Natural Environment, 28 July - 3 Aug 2008, in Tuscany Message-ID: <76D80B63-07B2-4AF0-88F5-F97D35E3C6B7@cns.nyu.edu> Dear Colleagues, The 4th Gordon Research Conference on Sensory Coding and the Natural Environment will take place in Il Ciocco, Italy from 28 July to 3 August, 2008. The meeting is intended to bring together an interdisciplinary collection of researchers interested in understanding the representation and use of ecologically relevant sensory signals in biological systems, along with those interested in characterizing the structure of those signals. The list of invited speakers is provided below. * The full program, and information about registration and submission of abstracts for poster presentation, is available at: http://www.grc.org/programs.aspx?year=2008&program=senscod * When registering, you have the option of submitting an abstract for a poster. Submitted abstracts may be revised up until mid-July. * Registration is open until mid-July, *but* is subject to availability (attendance is limited to 150). Eero Simoncelli and Michael Berry Co-Chairs, Sensory Coding and the Natural Environment, 2008 A Gordon Research Conference ---------------------------------------- SESSION LIST: Scene Statistics and Principles of Nervous System Design Daniel Wolpert, Roland Baddeley Natural Olfaction Gilles Laurent (session chair), Tim Holy, Noam Sobel, Rachel Wilson Adaptation Markus Meister (session chair), Michael Webster, David McAlpine Natural Audition: Neural Kamal Sen (session chair), Tim Gentner, Jan Schnupp, Tatyana Sharpee Natural Audition: Perception Timothy Griffiths (session chair), Josh McDermott, Rhodri Cusack Active Sensation Mathew E. Diamond (session chair), Cynthia Moss, Michele Rucci, Moritz von Heimendahl Statistical Models and Analysis of Natural Scenes Odelia Schwartz (session chair), Mattias Bethge, Maneesh Sahani Natural Vision: Early to Mid Stages David Brainard (session chair), Dario Ringach, Emilio Salinas, Larry Maloney Natural Vision: Late Stages Aude Oliva (session chair), Ed Conner, Jitendra Malik From rjolivet at pharma.uzh.ch Mon May 19 12:13:54 2008 From: rjolivet at pharma.uzh.ch (Renaud Jolivet) Date: Mon, 19 May 2008 18:13:54 +0200 Subject: Connectionists: PhD position announcement // High resolution quantitative optical imaging of neurometabolic and neurovascular coupling mechanisms Message-ID: Apologies for cross-postings. Noninvasive functional neuroimaging tools are widely applied to study the human brain in action. However, the hemodynamic signals of the most extensively used methods are still not well understood. This joint EPFL and ETHZ PhD project aims at understanding the quantitative aspects of hemodynamic changes that occur in the brain. For this aim, novel multimodal high resolution optical imaging tools will be developed and applied in animal experiments. The thesis project (3 years) will consist of the following tasks 1. Development and validation of quantitative spectroscopic optical imaging (Lausanne). 2. In-vivo experiments in the rat and data analysis (Zurich). Applicants should have a strong interest and background in engineering and/or physics. Skills in animal experiments are not mandatory, however, the candidate must be open and interested in this part of the project. Please contact Prof. Bruno Weber (bweber at pharma.unizh.ch) or Prof. Christian Depeursinge (christian.depeursinge at epfl.ch). -- Dr Renaud Jolivet Roche Research Fellow University of Zurich Institute of Pharmacology & Toxicology University Hospital Z?rich Nuclear Medicine R?mistrasse 100 CH-8091 Z?rich Tel: +41 76 437 9798 rjolivet at pharma.uzh.ch http://www.pharma.uzh.ch/research/functionalimaging/members/jolivet.html From nips2008publicity at gmail.com Mon May 19 23:50:21 2008 From: nips2008publicity at gmail.com (Antonio Torralba) Date: Mon, 19 May 2008 23:50:21 -0400 Subject: Connectionists: NIPS 2008 Call For Demonstrations Message-ID: CALL FOR DEMONSTRATIONS - NIPS 2008 Neural Information Processing Systems -- Natural and Synthetic NIPS 2008 Conference -- December 8 - 10, 2008 Hyatt Regency Vancouver, BC, CANADA http://nips.cc Demonstration Proposal Deadline: September 19, 2008 Real-world applications are the ultimate litmus test for intelligent algorithms. And live and interactive demos are the best way to convince people of the power of your ideas! The Neural Information Processing Systems Conference now provides a venue for showing your live and interactive demonstrations. It has a Demonstration Track that will run in parallel with the popular evening Poster sessions. Demonstrators will have a chance to show their live interactive demos, for example in areas such as hardware technology, software systems, neuromorphic and biologically-inspired systems and robotics. The only hard rules are that the demo must show novel technology and must be live and interactive! The full call for demonstrations is at the following URL: http://nips.cc/Conferences/2008/CallForDemos Ralf Herbrich (Microsoft Research) -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080519/81e53964/attachment-0001.html From wschenck at ti.uni-bielefeld.de Tue May 20 07:22:11 2008 From: wschenck at ti.uni-bielefeld.de (Wolfram Schenck) Date: Tue, 20 May 2008 13:22:11 +0200 Subject: Connectionists: Scholarship offer: Analysis of the Sensory-motor Interface of the Blowfly Message-ID: <200805201322.11933.wschenck@ti.uni-bielefeld.de> Offer for a doctoral scholarship in the graduate school associated to the Excellence Cluster "Cognitive Interaction Technology" of Bielefeld University (www.cit-ec.de): ?Analysis of a sensory-motor interface: From optic flow parameters to action selection? Goal of the project is to unravel the relationship between the activation of motion sensitive output neurons of the visual system of the blowfly and the motor circuits controlling locomotion during flight. A large multidimensional data set of neural recordings is already available so that the project will focus on data evaluation. The applicant should hold a university's Master's or Diploma degree in computer science, engineering, mathematics, physics, or biology. A background in data evaluation, pattern recognition, or machine learning is required; knowledge in neurobiology and artificial neural networks is an advantage. Advanced programming skills and the ability to work autonomously are expected. Supervision of the project: Department of Neurobiology (http://www.uni-bielefeld.de/biologie/Neurobiology) and Computer Engineering Group (http://www.ti.uni-bielefeld.de) of Bielefeld University Please send your application with the usual documents (including a detailed letter of motivation and the names and email addresses of two referees) until June 15, 2008 by email to "roland.kern at uni-bielefeld.de". -- Dr.-Ing. Wolfram Schenck Computer Engineering Group, Faculty of Technology, Bielefeld University POB 10 01 31, D-33501 Bielefeld, Germany phone +49 (0)521 106-6162, fax +49 (0)521 106-6440 http://www.ti.uni-bielefeld.de/html/people/wschenck/index.html From rjolivet at pharma.uzh.ch Thu May 22 04:20:06 2008 From: rjolivet at pharma.uzh.ch (Renaud Jolivet) Date: Thu, 22 May 2008 10:20:06 +0200 Subject: Connectionists: Open position for a MSc student :: Modeling the impact of astrocyte-neuron metabolic interactions on neural activity Message-ID: Apologies for cross postings. The group of Prof Bruno Weber (University of Zurich, Institute of Pharmacology and Toxicology) is looking for a talented and motivated Masters student for a computational neuroscience project aimed at understanding the energetic constraints of neuronal activity. The brain uses glucose as its primary energy substrate. Surprisingly however, neurons use lactate ? a glucose derivative ? rather than glucose has their main energy fuel. Lactate is being produced in astrocytes from blood-borne glucose and is then shuttled to neurons instantiating a metabolic connection between astrocytes and neurons. Since this mechanism was originally postulated in 1994, its existence has been the subject of a much heated controversy. We have recently demonstrated using mathematical analysis that this lactate shuttle does take place in vivo, is of significant importance and is regulated by the activity of excitatory neurons as originally postulated. This leaves open the question as to why brain energetic is organized in this fashion. This question is being addressed in the group at the moment using a combination of in vivo experiments and modeling. With this project, we wish to open a new line of research focusing on the role of this lactate shuttle in the regulation of neuronal activity, a mechanism recently described in vitro. The project will consist of developing, simulating and analyzing a network model containing different neuronal and astrocytic subpopulations. Energetic constraints and regulatory mechanisms will be integrated in the network by progressively increasing the complexity of astrocyte?neuron metabolic interactions. This project will make use of the newly developed Brian simulation tool (http://brian.di.ens.fr/) and will be run in collaboration with Dr Romain Brette at Ecole Normale Sup?rieure Paris who developed Brian. Requirements - Strong theoretical background (mathematics, physics or equivalent). - Knowledge of the Python programming language, MATLAB an asset. - Basic knowledge of biology and neuroscience. - Interested in combining theoretical tools with in vivo experiments to address key questions in neuroscience. - Fluent in English. Contact Please contact Dr Renaud Jolivet by e-mail at rjolivet at pharma.uzh.ch or by phone at +41 44 255 3632. Further information about the group can be found at http://www.pharma.uzh.ch/research/functionalimaging.html -- Dr Renaud Jolivet Roche Research Fellow University of Zurich Institute of Pharmacology & Toxicology University Hospital Z?rich Nuclear Medicine R?mistrasse 100 CH-8091 Z?rich Tel: +41 76 437 9798 rjolivet at pharma.uzh.ch http://www.pharma.uzh.ch/research/functionalimaging/members/jolivet.html From gabbiani at bcm.edu Wed May 28 09:56:15 2008 From: gabbiani at bcm.edu (Fabrizio Gabbiani) Date: Wed, 28 May 2008 08:56:15 -0500 Subject: Connectionists: postdoc position: insect neurophysiology and aerodynamics Message-ID: <483D647F.70209@bcm.edu> A postdoctoral position is available in the laboratory of Dr. Fabrizio Gabbiani at Baylor College of Medicine in Houston, Texas. The lab studies mechanisms of visually guided collision avoidance at the cellular, systems, and computational level using a variety of techniques (intra-/extra- cellular recordings, calcium imaging, pharmacology, behavior using high-speed video, compartmental modeling). The goal of the current project is to investigate how flight control and collision avoidance maneuvers are generated in freely flying animals. The postdoctoral fellow will have access to state-of-the art facilities for his/her project, and will be part of an international team based in the US and Europe. Further information about the lab can be found on our web site (http://glab.bcm.tmc.edu) and about the project by contacting Dr. Gabbiani (see below). Applicants should have a strong work ethic, a theoretical/computational background and/or experience with electrophysiology from a neuroethological perspective. Please send CV, statement of interests and the email addresses of at least two referees to Dr. Fabrizio Gabbiani (gabbiani at bcm.edu). -- Fabrizio Gabbiani phone: (713) 798 1849 Department of Neuroscience fax: (713) 798 3946 Baylor College of Medicine email: gabbiani at bcm.edu One Baylor Plaza, web: glab.bcm.tmc.edu Houston, TX 77030 From Yann.Boniface at loria.fr Thu May 29 11:16:54 2008 From: Yann.Boniface at loria.fr (Yann Boniface) Date: Thu, 29 May 2008 17:16:54 +0200 Subject: Connectionists: PhD position in computational neurosciences at Nancy, France: Message-ID: <483EC8E6.4010509@loria.fr> PhD position in computational neurosciences at Nancy, France: In the framework of the MAPS project (Mappings, Adaptation, Plasticity and Spatial computation) funded by the French National Research Agency, we are opening a PhD position on the motivated learning of spatio-temporal inner structuration of spiking neural networks. This project gathers four French partners: - INRIA-CNRS Nancy university http://cortex.loria.fr & http://maia.loria.fr/ - Laboratoire Mouvement et Perception, Marseille - Institut de Neurosciences Cognitives, Marseille - Laboratoire d'InfoRmatique en Image et Syst?mes d'information, Lyon The overall goal of the project is to carry out an etensive study of the superior colliculus using various experiments and recording technics in order to understand the underlying principles that should lead to the design of a realistic neural model. The candidate will have a Master in Computer Science or Applied Mathematics, preferably with insights or interest in Neurosciences thematics. Applications including a CV, should be sent by email to Y.Boniface and A.Dutech (Yann.Boniface at loria.fr,Alain.Dutech at loria.fr) ------------------ subject : Study of the functional properties of neural networks temporal coding Based on neural population mean activity, the Cortex team has designed models of selective visual attention based on distributed, adaptive and numerical computations. However, while those models exhibit strong attentional properties, they fail at properly integrating time, mainly because of their discrete temporal nature. To cope with this problem, a model of visual attention needs to be designed using the spiking neurons paradigm and we would like to push further in this direction by investigating temporal coding and functional properties resulting from learning with regards to the overall network stability. In the long run, we would like to investigate anticipation mechanisms and understand what is the benefit of such temporal coding. We want more particularly to explicit the formation of spatially structured and temporally operant connectivity patterns within the neural substrate with forward and lateral flow. Local Hebbian synaptic rules (temporal or not) will be thoroughly studied in conjunction with other synaptic mechanisms, like short term depression and synaptic traces. Those approaches will be compared with higher level extraction/competition processes that allow the formation of specialized receptor fields. One of the issue is to fill the gap between the classical self-organized feature-extraction models and realistic synaptic based adaptation processes. We hope in particular to clarify the lateral specialization processes that could allow the formation of specialized bubbles of activity. From a broader point a view, this work is to be placed in the framework of multi-modal integration: human cognition is based on a unified view of the world that is build upon perceptions coming from all the different modalities (vision, olfaction, proprioception, etc.). Even if there are dedicated pathways for each of these modalities, this does not result in a fragmented view of the world. In fact, the brain is able to integrate all those modalities and to offer a coherent and unified view. We would like to be able to build such a unified view of the world and this begins by considering first simpler multi-modal associations. From tobias at nld.ds.mpg.de Fri May 16 05:31:22 2008 From: tobias at nld.ds.mpg.de (Tobias Niemann) Date: Fri, 16 May 2008 09:31:22 -0000 Subject: Connectionists: Postdoctoral and PhD student positions in cellular neurophysics/neurophysiology In-Reply-To: <482D3F9A.6020609@nld.ds.mpg.de> References: <46F11EC2.6060905@nld.ds.mpg.de> <47DF9A97.1000408@nld.ds.mpg.de> <482D3F9A.6020609@nld.ds.mpg.de> Message-ID: <482D546D.4050402@nld.ds.mpg.de> The Bernstein Center for Computational Neuroscience G?ttingen invites applications for a Postdoctoral and PhD student positions in cellular neurophysics/neurophysiology The candidates?s research will experimentally analyze the dynamical properties of sodium channels in neocortical neurons in situ and model their role in the operation of cortical neurons and networks and will be part of an integrated international project of the Max Planck Institutes for Dynamics and Self-Organization (G?ttingen) and the Koret School of Veterinary Medicine of the Hebrew University of Jerusalem (Israel), supported by the German-Israeli Foundation for Scientific Research and Development. PhD students will work towards their doctorate either in G?ttingen University?s newly established Graduate School, GGNB or at the Hebrew University of Jerusalem. We are looking for young researchers with a background in biophysics, cellular electrophysiology, or cell biology and a keen interest in interdisciplinary research at the border of experimental and theoretical neuroscience. The ideal candidate will have the ability and desire to push the characterization of cortical sodium currents in intact cortical neurons to a new level of quantitative precision and to analyze their role in the operation of cortical neurons under physiologically realistic conditions. Prior experience with the biophysics of ion channels, with the electrophysiology of neurons, or with cellular imaging methods would be advantageous. Prior knowledge of Neurobiology is desirable but not required. G?ttingen is a center of neuroscience in Europe hosting numerous internationally recognized neuroscience research institutions, including three Max Planck Institutes, the European Neuroscience Institute, the German Primate Research Center, and G?ttingen University's Centers for Systems Neuroscience (ZNV) and for the Molecular Physiology of the Brain (CMPB). The BCCN integrates theoretical and experimental research groups from these institutions to foster interdisciplinary research in computational neuroscience specifically supporting close collaboration between theorists and experimental researchers. Please submit your application preferably in one single PDF-document, including cover letter, CV, list of publications, names of possible referees, relevant certificates until June 15, 2008, to: jobs at bccn-goettingen.de (Subject: NPhysNaCh) While e-mail is preferred, applications may also be submitted in hardcopy to the following address: Dr. Fred Wolf Subject: NPhysNaCh Bernstein Center for Computational Neuroscience (BCCN) G?ttingen Max-Planck-Institute for Dynamics and Self-Organization Bunsenstrasse 10 D - 37073 G?ttingen, Germany http://www.ds.mpg.de The MPIDS is an equal opportunity employer. From tobias at nld.ds.mpg.de Fri May 16 05:50:41 2008 From: tobias at nld.ds.mpg.de (Tobias Niemann) Date: Fri, 16 May 2008 09:50:41 -0000 Subject: Connectionists: PhD student positions in theoretical Neurophysics In-Reply-To: <482D546D.4050402@nld.ds.mpg.de> References: <46F11EC2.6060905@nld.ds.mpg.de> <47DF9A97.1000408@nld.ds.mpg.de> <482D3F9A.6020609@nld.ds.mpg.de> <482D546D.4050402@nld.ds.mpg.de> Message-ID: <482D58F6.4060605@nld.ds.mpg.de> The Bernstein Center for Computational Neuroscience G?ttingen invites applications for PhD student positions in theoretical Neurophysics The student?s research will analyze dynamical self-organization of the functional architecture of neocortical networks in mathematical models and through the quantitative analysis of high resolution live imaging data from neocortical networks in the living brain. The student?s research will be part of an integrated international project of the Max Planck Institute for Dynamics and Self-Organization (G?ttingen), the Carnegie Mellon University (Pittsburgh, USA) and the University of Tokyo (Japan), supported by the Human Frontier Science Program Organization. PhD students will work towards their doctorate in G?ttingen University?s newly established Graduate School, GGNB and collaborate closely with researchers in the US and Japan. We are looking for young researchers with a strong background in computational and theoretical physics or in dynamical systems theory and probabilistic data analysis with a keen interest in interdisciplinary research at the border of Neuroscience and the Physics of Complex Systems. The ideal candidate will have the ability and desire to develop novel approaches for the analysis of dynamical self-organization in living neural networks and to closely collaborate with biological researchers in implementing them in quantitative live imaging experiments. Prior experience in Statistical Physics, Nonlinear Dynamics, and Theoretical Neuroscience would be advantageous. Prior knowledge of Neurobiology is desirable but not required. G?ttingen is a center of neuroscience in Europe hosting numerous internationally recognized neuroscience research institutions, including three Max Planck Institutes, the European Neuroscience Institute, the German Primate Research Center, and G?ttingen University's Centers for Systems Neuroscience (ZNV) and for the Molecular Physiology of the Brain (CMPB). The BCCN integrates theoretical and experimental research groups from these institutions to foster interdisciplinary research in computational neuroscience specifically supporting close collaboration between theorists and experimental researchers. Please submit your application preferably in one single PDF-document, including cover letter, CV, list of publications, names of possible referees, relevant certificates until June 15, 2008, to: jobs at bccn-goettingen.de (Subject: NPhysSO) While e-mail is preferred, applications may also be submitted in hardcopy to the following address: Dr. Fred Wolf Subject: NPhysSO Bernstein Center for Computational Neuroscience (BCCN) G?ttingen Max-Planck-Institute for Dynamics and Self-Organization Bunsenstrasse 10 D - 37073 G?ttingen, Germany http://www.ds.mpg.de The MPIDS is an equal opportunity employer. From netta at comp.leeds.ac.uk Mon May 19 07:36:52 2008 From: netta at comp.leeds.ac.uk (N Cohen) Date: Mon, 19 May 2008 12:36:52 +0100 (BST) Subject: Connectionists: Postdoctoral fellowship in Leeds, UK Message-ID: Postdoctoral Fellowship (Full Time) Biosystems Group School of Computing University of Leeds Leeds, United Kingdom Modelling of complex biological networks ----------------------------------------- A postdoctoral fellowship is available immediately to work with Dr. Netta Cohen at the Biosystems Group, School of Computing in the University of Leeds for approximately two years. Research areas covered in the group include: Computational neuroscience Worm locomotion and neural control Gene regulation networks Stochastic dynamics in complex networks The Biosystems Group offers a unique environment in which a critical mass of modellers and experimentalists interact with each other and with other research groups in related fields, including mathematics, physics, computer science and machine learning, mechanical engineering/robotics and biological sciences. For further details of our research, please see: http://www.comp.leeds.ac.uk/biosystems We are seeking a candidate who can demonstrate excellence in research, a relevant track record in computational modelling for biological systems and strong interpersonal skills. You should be willing to work closely with collaborators modellers or experimentalists. All highly motivated candidates with a PhD in Physical, Mathematical or Computer sciences, or other relevant areas to the project are encouraged to apply. International applications are welcome. University Grade 7 (??28,290- ??33,780 p.a.) or University Grade 8 (??34,79 - ??41,545 p.a.) Exact period of contract is dependent on funding. Informal enquiries to Dr Netta Cohen, tel +44 (0)113 343 6789, email netta at comp.leeds.ac.uk To apply on line please visit jobs.leeds.ac.uk, click on research and follow the link to the Job Ref number below. Alternatively application packs are available from Ms Judi Drew, tel +44 (0)113 343 5432, email j.a.drew at leeds.ac.uk Job ref 312300 Closing date 13 June 2008 Applications received until 13 June 2008 are guaranteed full consideration. From rammurthy at iiit.ac.in Fri May 2 02:59:20 2008 From: rammurthy at iiit.ac.in (ram murthy) Date: Fri, 02 May 2008 06:59:20 -0000 Subject: Connectionists: Multi-Dimensional Neural Networks Book Message-ID: <00e201c8ac21$fcb619f0$1524a8c0@iiit1b1ae426b1> Dear Collegues, I am Dr. G.Rama Murthy. I did my Ph.D degree from Purdue University, West Lafayette. CRUX: (1) I am herewith providing the details of a book on MULTI-DIMENSIONAL NEURAL NETWORKS: UNIFIED THEORY OF CONTROL, COMMUNICATION AND COMPUTATION. It is published by NEW AGE INTERNATIONAL PUBLISHERS 4835/24, Ansari Road, Darya Ganj, New Delhi-110002 E-mail : contactus at newagepublishers.com The PRICE OF THE BOOK is 195 rupees or 5 US dollars. (2) Please consider buying the book for its WORTH. --------------------------------------------------------------------------------- DETAILS OF BOOK ________________________________________________ Multidimensional Neural Networks Unified Theory Rama Murthy, G., Faculty Member at the International Institute of Information Technology, Hyderabad. ISBN : 978-81-224-2228-3 Publication Year : Nov, 2007 Edition : 1st Reprint : Pages : 168 Price : Rs. 195 Binding : Paperback About the Book: The book ``Multidimensional Neural Networks (MDNNs): Unified Theory`` has been conceived for serving 3 types of users: Senior undergraduate/graduate students, practising engineers, and advanced neural network researchers. This book is based on the following innovations: a.. Multidimensional (M-D) logic theory i.e., conceiving logic gates/circuits operating on multidimensional arrays b.. Tensor state space representation of certain M-D systems c.. Relation M-D logic gates, M-D codeword tensors, M-D optimal control tensors to M-D neural networks unification d.. Novel complex valued associative memory (CVNN) on the hypercube e.. Novel models of biological neurons such as those with a linear filter model of synapse f.. Neural network based signal processing The subject of M-D neural networks will have the applications in: 1.. Design of versatile associative memories, 2.. Optimal design of intelligent systems, 3.. Pattern recognition systems etc. About the Author: G. Rama Murthy received his Ph.D. degree in Computer Engineering from Purdue University, West Lafayette, U.S.A. He is currently a faculty member at the International Institute of Information Technology, Hyderabad. He has presented/published about 60 research papers in international conferences and journals. He has received awards in All India Technical Essay Contest and All India Electronic Design Competition. He is a member of IEEE, ACM, Eta Kappa Nu, Phi Kappa Phi. Contents: a.. Introduction b.. Multi/Infinite Dimensional Neural Networks, Multi/Infinite Dimensional Logic Theory c.. Multi/Infinite Dimensional Coding Theory: Multi/Infinite Dimensional Neural Networks?Constrained Static Optimization d.. Tensor State Space Representation: Multi Dimensional Systems e.. Unified Theory of Control, Communication and Computation: Multi Dimensional Neural Networks f.. Complex Valued Neural Associative Memory on the Complex Hypercube g.. Optimal Binary Filters: Neural Networks h.. Linear Filter Model of a Synapse: Associated Novel Real/Complex Valued Neural Networks i.. Novel Complex Valued Neural Networks j.. Advanced Theory of Evolution of Living Systems. For more information on Books visit http://www.newagepublishers.com ------------------------------------------------------------------- With Best Regards, Rama Murthy -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080502/650a2eb2/attachment-0001.html -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: image/jpeg Size: 3339 bytes Desc: not available Url : https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080502/650a2eb2/attachment-0001.jpe From Elizabeth.Thomas at u-bourgogne.fr Mon May 5 06:21:33 2008 From: Elizabeth.Thomas at u-bourgogne.fr (Elizabeth Thomas) Date: Mon, 05 May 2008 10:21:33 -0000 Subject: Connectionists: Postdoctoral fellowship in machine learning and movement analysis Message-ID: <481EDE6C.2080206@u-bourgogne.fr> *Postdoctoral fellowship in movement analysis and machine learning* A postdoctoral fellowship for one year is available for the application of various machine learning techniques to the analysis of movement data. The study of all motor activities from gait to dance is done by the gathering of kinetic, kinematic and EMG data. Kinematic data is obtained from the displacement of markers placed on the subjects. Kinetic signals provide information on the foot-ground pressure during movements. Finally EMG data is from the electric activity of muscles. As with many biological signals, the analysis of these signals presents us with an important challenge due to their complexity, high variability and noise. The linear techniques which are currently most frequently employed are not sufficiently developed for the analyses of such ?noisy? data. We propose therefore the development of several techniques from machine learning for the analyses of these signals. The data will come from various studies that seek to understand the neural control of normal activities such as reaching and also for the evaluation of abnormal gait. In the latter study we will be evaluating various hip prostheses by comparing the EMGs of normal subjects with those of patients. The study will be carried out in the INSERM lab U887 of the University of Bourgogne France in collaboration with the Rheumatology department of the University Hospital. The project will start with an exploration of neural network and kernel methods. The University of Bourgogne in Dijon is approximately an hour away from Paris by the TGV train. The candidate cannot be French and must never have worked in France. The position will have to be filled by November 2008. The candidate would preferably have a background that would fit in a bioengineering department. A good knowledge of Matlab programming will be required. A knowledge of kernel methods would be considered an asset. All interested candidates may send a CV to Elizabeth.Thomas at u-bourgogne.fr . Elizabeth Thomas Ma?tre de conf?rence STAPS INSERM U887 Universit? de Bourgogne, France From oschwart at aecom.yu.edu Mon May 5 09:57:34 2008 From: oschwart at aecom.yu.edu (oschwart@aecom.yu.edu) Date: Mon, 05 May 2008 13:57:34 -0000 Subject: Connectionists: Postdoctoral position in computational/theoretical neuroscience Message-ID: <55348.129.98.90.132.1209995849.squirrel@netmail.aecom.yu.edu> Postdoctoral position in computational/theoretical neuroscience A postdoctoral position is available in the lab of Odelia Schwartz at the Albert Einstein College of Medicine in New York City. Our lab employs tools of computational and theoretical neuroscience, to study systems from the neural level through to perception and behavior. For example, we develop models of sensory processing based on the hypothesis that images and sounds have predictable and quantifiable statistical regularities to which the brain is sensitive. The models are constructed through interplay with physiological and psychophysical data. Example projects: (1) Learning the statistical structure of natural scenes, movies, and eye movement sequences; (2) Modeling how neural populations are affected by contextual information: spatially, what surrounds a given feature or object; and temporally, what has been observed in the past, i.e., adaptation. (3) Modeling hierarchical neural processing. For more information about the lab and recent publications, see: http://neuroscience.aecom.yu.edu/faculty/primary_faculty_pages/schwartz.html The candidate should have a Ph.D. in a relevant discipline, a strong quantitative background, and an interest in neuroscience. Prior experience would ideally include areas such as computational neuroscience, machine learning, statistics and/or signal processing. Albert Einstein College of Medicine (AECOM) offers a vibrant interdisciplinary environment, with a growing systems and computational contingent. AECOM is located in a quiet neighborhood of New York, only a short subway ride from Manhattan. Information about working at the AECOM, including housing for postdocs, can be found at: http://www.aecom.yu.edu/home/belfer_institute/ Initial appointment is for one year and renewable. Salary is competitive and will commensurate with experience. Please send inquiries; or a CV, short statement of research interests, and names and contact information of 3 references to: Odelia Schwartz oschwart at aecom.yu.edu From mark.plumbley at elec.qmul.ac.uk Mon May 5 18:14:13 2008 From: mark.plumbley at elec.qmul.ac.uk (Mark Plumbley) Date: Mon, 05 May 2008 22:14:13 -0000 Subject: Connectionists: Call for Papers: ICArn International Workshop 2008 Message-ID: <3399496864F99445B051FD9556FF3B6FF2878F@staff-mail1.vpn.elec.qmul.ac.uk> Call for Papers ICA Research Network International Workshop 25-26 September, 2008, Liverpool, U.K. www.icarn.org The ICA Research Network is sponsored by the Engineering and Physical Sciences Research Council (EPSRC) in the U.K., and is aimed at improving communications in the area of Blind Source Separation (BSS) and Independent Component Analysis (ICA). The 2008 ICA Research Network Workshop will be held at the University of Liverpool covering the latest developments and techniques in the area of source separation and ICA. Submissions from international participants are most welcome. Topics The workshop will feature keynote addresses and technical presentations (oral and poster), which will be included in the registration. Papers are solicited on topics in the area of source separation or ICA, including but not limited to: Algorithms and Architectures (Non-linear ICA, Probabilistic Models, Sparse Coding, etc), Theory (Optimization, Complex Methods, Time-Frequency Representations, etc), Applications (Audio, Bio-Informatics, Biomedical Engineering, Communications, Finance, Image Processing, Psychology, etc), and novel methods (compressed sensing, non-negative matrix factorization). A special feature of this workshop will be a special poster session where authors will have the opportunity to present their current work in progress. Authors should indicate their preference at the submission stage and submit short papers. Full Paper Submission Procedure Prospective authors are invited to submit camera-ready papers of no more than four A4-size pages in the PDF format. Please use the template and the electronic submission procedure described at the workshop homepage (www.icarn.org). At least one author of each accepted paper must undertake to attend the workshop. Prospective authors can seek clarification using the email address icarnw08 at liverpool.ac.uk. Accepted papers will be published in a bound volume. Authors of the most innovative papers will be invited to submit substantially extended and updated versions of their papers for further review and possible publication in the IET Signal Processing journal. There will be one Best Student Paper Award for the best paper presented at the workshop by a student. Registration costs will include attendance in all the sessions, a copy of the bound proceedings, mid-morning and mid-afternoon refreshments as well as buffet lunches on both days, and the Workshop dinner on the evening of 25 September 2008. Important Dates/Deadlines Submission of papers: 17 June, 2008 Notification of acceptance : 17 July, 2008 Submission of camera-ready accepted paper : 07 August, 2008 Early registration and author registration : 07 August, 2008 Final date for registration : 08 September, 2008 Workshop : 25-26 September, 2008 Website: www.icarn.org Chair A K Nandi Vice-Chair X Zhu Organising Committee A K Nandi X Zhu W Al-Nuaimy M E Davies J Gao M D Plumbley Programme Committee National P Baxter M E Davies R Everson C Fyfe M Girolami C J James A K Nandi M D Plumbley S Sanei X Zhu International J F Cardoso A Cichocki P Comon C Jutten E Oja P Smaragdis -- Dr Mark D Plumbley Centre for Digital Music Department of Electronic Engineering Queen Mary University of London Mile End Road, London E1 4NS, UK Tel: +44 (0)20 7882 7518 Fax: +44 (0)20 7882 7997 Email: mark.plumbley at elec.qmul.ac.uk http://www.elec.qmul.ac.uk/people/markp/ From siwu at sussex.ac.uk Tue May 6 12:02:43 2008 From: siwu at sussex.ac.uk (Si Wu) Date: Tue, 06 May 2008 16:02:43 -0000 Subject: Connectionists: Autuman School on Computational Neuroscience in China Message-ID: Dear Connectionists, Some of you might be interested in the following message: International Autumn School on Computational Neuroscience, October 12-18, Fudan University, Shanghai, CHINA Application DEADLINE: August 1st, 2008. We are pleased to announce that an international school on Computational Neuroscience will be held from October 12 to 18, in Fudan University, Shanghai, China. The school lasts for seven days, including lectures, projects and poster presentations. Lectures will be given by distinguished and leading scientists in the morning sections, and will cover a wide-range of hot topics in the field. Each student will be assigned to a tutor and a project, depending on research interest and background. In the afternoon and the evening sections, students will have opportunity to carry out chosen projects, supervised by tutors. At the end of the school, students are expected to submit a report of five pages, and to present results in a poster form to all participants (poster and discussion sections will be organized). The level of courses is designed for advanced graduate students and postdoctoral fellows in related disciplines. Students are expected to have a solid background in either neuroscience, mathematics, or computer science, and have strong interests in Computational Neuroscience. The maximum number of 30 participants will be accepted. The course is free, but students need to pay costs for lodging and meals which are reasonably cheap in Shanghai. To apply for a position, a candidate needs to submit a CV, a short description of research interest, and two reference letters through the electronic mail of the school: snsa at fudan.edu.cn . All applications will be assessed by the scientific committee, based on the following criteria: 1) the scientific quality of the candidate (CV), 2) the reference letters, and 3) the evidences showing that the school will benefit the candidate's future career substantially. We have a limited number of travelling grants available for international students coming from overseas. Applicants who need this support may specify it in the application. Confirmed speakers in the Autumn School: Shun-ichi Amari (RIKEN, Japan) Guo-qiang Bi (UST, China; Pittsburgh, USA) Zhaoping Li (UCL, UK) John Rinzel (New York, USA) [ partially confirmed at present ] Hugh Robinson (Cambridge, UK) Kechen Zhang (John Hopkins, USA) Scientific Committee: Andreas Dress (CAS-MPG Partner Institute for Computational Biology, Shanghai) Jgen Jost (Max Planck Institute for Mathematics in the Sciences, Germany) Jianfeng Feng (Warwick University, UK; Fudan University, China) Wei Lin (Fudan University, China) Mu-Ming Poo (Berkeley, USA; Institute of Neuroscience, Shanghai) Si Wu (Institute of Neuroscience, Shanghai;Sussex University, UK) -- Dr Si WU Senior Lecturer in Neural Computation Lab. of Bioinformatics and Machine Learning Dept. of Informatics The University of Sussex, UK Tel: 44-1273-678770 From rsun at rpi.edu Wed May 7 14:33:21 2008 From: rsun at rpi.edu (Professor Ron Sun) Date: Wed, 07 May 2008 18:33:21 -0000 Subject: Connectionists: Cognitive Systems Research, Vol. 9, No. 1-2, 2008 References: <5262970.1204714777457.JavaMail.wasadmin@psc1928> Message-ID: <48BE4783-9623-428F-88AC-43ECBC987823@rpi.edu> New issues are now available: * Cognitive Systems Research Volume 9, Issues 1-2, Pages 1-160 (March 2008) special issue: Perspectives on Social Cognition Edited by Leslie Marsh and Christian Onof http://www.sciencedirect.com/science/issue/ 6595-2008-999909998-682307 TABLE OF CONTENTS 2) Introduction to the special issue ?Perspectives on Social Cognition? Pages 1-4 Leslie Marsh and Christian Onof http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PF1WN2-2&md5=30863fe94a74106baf8354b2521a8b 07 3) Functionalism and mental boundaries Pages 5-14 Lawrence A. Shapiro http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PG11DH-4&md5=d1f95b596ec388ad32b6276ef849f0 70 4) Consciousness and the social mind Pages 15-23 Philip Robbins http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PG11DH-3&md5=6b094fab39d22c4db71fc3e51d144c 83 5) Social relationships and groups: New insights on embodied and distributed cognition Pages 24-32 Eliot R. Smith http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PG11DH-1&md5=845b074ef3e719bed340d6af432eae 9c 6) A conceptual and empirical framework for the social distribution of cognition: The case of memory Pages 33-51 Amanda J. Barnier, John Sutton, Celia B. Harris and Robert A. Wilson http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PF1WN2-5&md5=156f2898c288bafae715b159f430ec 64 7) Dynamic empathy: A new formulation for the simulation theory of mind reading Pages 52-63 Teed Rockwell http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PF1WN2-4&md5=2f0c288d31dfacd5a7eb1b0a6e96e5 ed 8) The social-cognitive dynamics of metaphor performance Pages 64-75 Raymond W. Gibbs Jr. and Lynne Cameron http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PF1WN2-1&md5=3808d80bb04fb816b4fae483b2a6f9 52 9) Frege?s puzzle and Frege cases: Defending a quasi-syntactic solution Pages 76-91 Robert D. Rupert http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PF1WN2-3&md5=1dcf5cd18d11441ccbd3f145c64e0b 52 10) Cultural-historical activity theory and the zone of proximal development in the study of idioculture design and implementation Pages 92-103 Robert Lecusay, Lars Rossen and Michael Cole http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PJ053K-1&md5=9772631be935fbab5ec330ba97e2e1 b7 11) The cultural evolution of socially situated cognition Pages 104-114 Liane Gabora http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PG11DH-6&md5=6cfa39132cf705dace2dd43c40fcd1 0d 12) Science as collective knowledge Pages 115-124 Kristina Rolin http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PG11DH-5&md5=349674dc9f94b12ecbcc3a858c36f4 0f 13) Economics, cognitive science and social cognition Pages 125-135 Don Ross http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PF1WN2-6&md5=b4de8b81d76c86fad4f33045a6fb5b 19 14) Stigmergic epistemology, stigmergic cognition Pages 136-149 Leslie Marsh and Christian Onof http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PFDDW4-1&md5=761dc8462c09ea972cf11fcfcdb7d6 9f 15) Methodological situatedness; or, DEEDS worth doing and pursuing Pages 150-159 Joel Walmsley http://www.sciencedirect.com/science? _ob=GatewayURL&_method=citationSearch&_urlVersion=4&_origin=SDVIALERTASC II&_version=1&_uoikey=B6W6C-4PG11DH-2&md5=506d1e82a5d97d26a77cbad923e280 a3 ----------------------------------------------------------------------- See the following Web page for submission, subscription, and other information regarding Cognitive Systems Research: http://www.cogsci.rpi.edu/~rsun/journal.html See http://www.elsevier.com/locate/cogsys for further information regarding accessing these articles If you have questions about features of ScienceDirect, please access the ScienceDirect Info Site at http://www.info.sciencedirect.com ======================================================== 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 hitzler at aifb.uni-karlsruhe.de Thu May 8 04:47:03 2008 From: hitzler at aifb.uni-karlsruhe.de (Pascal Hitzler) Date: Thu, 08 May 2008 08:47:03 -0000 Subject: Connectionists: CfP Journal Special Issue on Recurrent Neural Networks Message-ID: <4822BDFC.8030203@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 hitzler at aifb.uni-karlsruhe.de Fri May 9 14:28:59 2008 From: hitzler at aifb.uni-karlsruhe.de (Pascal Hitzler) Date: Fri, 09 May 2008 18:28:59 -0000 Subject: Connectionists: Final CfP: ECAI-08 Workshop on Neural-Symbolic Learning and Reasoning, NeSy'08 Message-ID: <482497E0.3090009@aifb.uni-karlsruhe.de> Deadline extended: May 16th!!! Fourth International Workshop on Neural-Symbolic Learning and Reasoning Workshop at ECAI2008, Patras, Greece, July 2008 http://www.neural-symbolic.org/NeSy08/ NeSy'05 took place at IJCAI-05 NeSy'06 took place at ECAI2006 NeSy'07 took place at IJCAI-07 Call for Papers --------------- Artificial Intelligence researchers continue to face huge challenges in their quest to develop truly intelligent systems. The recent developments in the field of neural-symbolic integration bring an opportunity to integrate well-founded symbolic artificial intelligence with robust neural computing machinery to help tackle some of these challenges. The Workshop on Neural-Symbolic Learning and Reasoning is intended to create an atmosphere of exchange of ideas, providing a forum for the presentation and discussion of the key topics related to neural-symbolic integration. Topics of interest include: * The representation of symbolic knowledge by connectionist systems; * Learning in neural-symbolic systems; * Extraction of symbolic knowledge from trained neural networks; * Reasoning in neural-symbolic systems; * Biological inspiration for neural-symbolic integration; * Neural networks and probabilities; * Applications in robotics, semantic web, engineering, bioinformatics, etc. Keynote speaker: Kai-Uwe K?hnberger, Osnabr?ck Submission Researchers and practitioners are invited to submit original papers that have not been submitted for review or published elsewhere. Submitted papers must be written in English and should not exceed 5 pages in the case of research and experience papers, and 2 pages in the case of position papers (including figures, bibliography and appendices) in ECAI2008 format as described in the ECAI2008 submissions and style guide (http://www.ece.upatras.gr/ecai2008/substyles.htm). All submitted papers will be judged based on their quality, relevance, originality, significance, and soundness. Papers must be submitted directly by email in PDF format to nesy at soi.city.ac.uk Presentation Selected papers will have to be presented during the workshop. The workshop will include extra time for audience discussion of the presentation allowing the group to have a better understanding of the issues, challenges, and ideas being presented. Publication Accepted papers will be published electronically in the CEUR workshop proceedings (bearing an ISSN number). Hardcopies will be distributed during the workshop. Authors of the best papers will be invited to submit a revised and extended version of their papers to the Journal of Logic and Computation, OUP. Important Dates Deadline for submission: May 16th, 2008 Notification of acceptance: May 30th, 2008 Camera-ready paper due: June 6th, 2008 Workshop date: July 21st or 22nd, 2008 ECAI2008 main conference dates: 21st to 25th of July, 2008 Workshop Organisers Artur d'Avila Garcez (City University London, UK) Pascal Hitzler (University Karlsruhe, Germany) Programme Committee (incomplete) Sebastian Bader, TU Dresden, Germany Howard Blair, Syracuse University, U.S.A. Luc de Raedt, KU Leuven, Belgium Marco Gori, University of Siena, Italy Barbara Hammer, TU Clausthal, Germany Ioannis Hatzilygeroudis, University of Patras, Greece Steffen H?lldobler, TU Dresden, Germany Ekaterina Komendantskaya, Sophia Antipolis, France Kai-Uwe K?hnberger, Osnabr?ck, Germany Luis Lamb, Federal University of Rio Grande do Sul, Brazil Roberto Prevete, University of Naples, Italy Dan Roth, University of Illinois at Urbana-Champaign, U.S.A. Anthony K. Seda, University College Cork, Ireland Frank van der Velde, Leiden University, The Netherlands Gerson Zaverucha, Federal University of Rio de Janeiro, Brazil Additional Information General questions concerning the workshop should be addressed to nesy at soi.city.ac.uk. -- PD Dr. Pascal Hitzler Institute AIFB, University of Karlsruhe, 76128 Karlsruhe email: hitzler at aifb.uni-karlsruhe.de fax: +49 721 608 6580 web: http://www.pascal-hitzler.de phone: +49 721 608 4751 http://www.neural-symbolic.org From elli.chatzopoulou at incf.org Mon May 12 05:25:10 2008 From: elli.chatzopoulou at incf.org (INCF - Elli Chatzopoulou) Date: Mon, 12 May 2008 09:25:10 -0000 Subject: Connectionists: INCF MUSIC project: request for comments Message-ID: <48280D66.6020702@incf.org> The INCF has engaged in the development of software that allows large scale neuron simulators to communicate during runtime. An RFC - Request For Comments - document is now available and open for comments on the proposed design and prototype specifications. MUSIC (Multi-Simulation Coordinator) is a project under the INCF Program on Large-Scale Modeling of the Nervous System. The aim of the INCF MUSIC project is to provide a standardized software interface (an API) on top of the message passing interface (MPI) for communication between parallel applications for large-scale simulation of neural networks. It enables the transfer of massive amounts of event information and continuous values from one parallel application to another, including applications that use different data allocation strategies. In the design of the standard interface, care has also been taken to facilitate easy adaptation of existing simulators and enable straight-forward independent third-party development and community sharing of reusable and interoperable software tools for parallel processing. See http://www.incf.org/programs/modeling/music-multi-simulation-coordinator for more. Download the MUSIC RFC [pdf]: http://www.incf.org/documents/music-rfc.pdf For comments, you can use the mailing list at music-rfc at incf.org to which you can subscribe here: http://lists.incf.org/mailman/listinfo/music-rfc Many thanks to ?rjan Ekeberg and Mikael Djurfeldt for their excellent work so far. -- 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 aag at soi.city.ac.uk Tue May 13 13:49:34 2008 From: aag at soi.city.ac.uk (Artur Garcez) Date: Tue, 13 May 2008 17:49:34 -0000 Subject: Connectionists: Journal of Algorithms thematic issue on Algorithmic Reinforcement Learning (call for papers) Message-ID: <00c701c8b521$b0031780$c55e288a@crayfish> Call for Papers Journal of Algorithms, Elsevier http://www.cs.rhul.ac.uk/~kostas/arl/cfp.html Thematic Issue on "Algorithmic Reinforcement Learning" http://www.elsevier.com/locate/jalgor Aim & Scope Reinforcement learning is an area of machine learning seeking to provide a computational approach to understanding and automating goal-directed learning and decision-making. It addresses the question of how an autonomous agent that senses and acts in its environment can learn to choose optimal actions to achieve its goals. The approach originates from previous work in psychology (particularly animal learning), computer science (particularly dynamic programming), with ongoing work in artificial intelligence (particularly stochastic, symbolic and connectionist learning). More recently, reinforcement learning has been used to provide cognitive models that simulate human performance during problem solving and/or skill acquisition. This special issue of the Journal of Algorithms seeks to celebrate the increasingly multidisciplinary nature of reinforcement learning and, in line with the Journal's manifesto, it proposes to study and present the subject from an algorithmic perspective that we refer to as Algorithmic Reinforcement Learning (ARL). It is hoped in this way that the special volume will serve as a reference in the area, and will help organise and promote the research across sub-areas. We welcome the submission of innovative and mature results in specifying, developing and experimenting with ARL. Approaches that relate, compare and contrast, combine or integrate different areas of reinforcement learning are particularly encouraged. Papers describing innovative developments in the area are also encouraged. Areas of interest include, but are not limited to, the following topics: Multi-agent reinforcement learning Relational reinforcement learning Neuro-symbolic reinforcement learning Bayesian reinforcement learning Reinforcement learning and logic/ILP Reinforcement learning with background knowledge Robust reinforcement learning Reinforcement learning in game theory and bounded rationality Applications Important Dates Submission Deadline: 1st October 2008 Acceptance Notice: 20th January 2009 Final Manuscript: 1st March 2009 Publication Date: 2nd Quarter, 2009 (tentative) Submission Guidelines The work submitted must be in the form of high quality, original papers, which are not simultaneously submitted for publication elsewhere. Papers should be formatted according to the journal style, and not exceed 25 pages including figures, references, etc. The papers must be submitted by sending a PDF version of the complete manuscript to arl-guest-eds at cs.rhul.ac.uk. Submitted papers will be peer reviewed according to their originality, quality and relevance to this special issue and the journal. Guest Editors Dr. Kostas Stathis Computer Science Department, Royal Holloway, University of London, UK URL: http://www.cs.rhul.ac.uk/~kostas Dr. Artur d'Avilla Garcez Computing Department, City University London, UK URL: http://www.soi.city.ac.uk/~aag Dr. Robert Givan Department of Electrical and Computer Engineering, Purdue University, US URL: http://cobweb.ecn.purdue.edu/~givan/ ----------------------------------------------------------------------- Dr. Artur d'Avila Garcez Reader in Computing Department of Computing, School of Informatics City University London, EC1V 0HB, UK Tel: + 44 (0)20 7040 8344 Fax: + 44 (0)20 7040 0244 Email: aag at soi.city.ac.uk URL: http://www.soi.city.ac.uk/~aag ----------------------------------------------------------------------- From ale at sissa.it Fri May 30 14:04:08 2008 From: ale at sissa.it (Alessandro Treves) Date: Fri, 30 May 2008 20:04:08 +0200 Subject: Connectionists: CALL FOR PROPOSALS FOR EBBS SYMPOSIA Message-ID: <20080530200408.a095qmt340occ8ok@webmail.sissa.it> 41ST EBBS Annual General Meeting Rhodes, Greece September 14-18, 2009 CALL FOR PROPOSALS FOR SYMPOSIA The 41st EBBS Annual General Meeting will be held on the Greek island of Rhodes, September 14-18, 2009. The local organising committee, chaired by Fotini Stylianopoulou is enthusiastically committed to the organisation of what will be an outstanding scientific event. The programme, as usual, will be entirely based upon plenary lectures and symposia plus free communications in the form of posters. To have a well-balanced and high scientific quality programme it is most important that the proposals reflect the scientific interests of the EBBS membership. We can only achieve these goals of scientific excellence and membership interest through active participation of EBBS members in formulation of the programme. The EBBS committee, acting as the programme committee, urges members to submit proposals for symposia on topics of their choice and to encourage colleagues, EBBS members or not, to submit proposals. Guidelines: ? Symposia may be proposed by EBBS members or non-members, with no geographical restrictions. ? The organizer should be an established researcher. ? Symposia are two hours in length and comprise four speakers. ? Speakers should ideally provide a balanced mix of presentations of a wide, synthesis or reviewing perspective on the topic covering several years of work, and descriptions of some new data, relevant to the topic. ? Symposia having one young speaker at the doctoral/postdoctoral level will be preferred. ? Speakers, and only speakers, receive a free registration. No other financial assistance is available. Download a form from http://www.ebbs-science.org/ and send your proposal as an attached file by e-mail before June 15, 2008 to the Programme Chair, Nicole van Steinb?chel nvsteinbuechel at med.uni-goettingen.de -- SISSA - Cognitive Neuroscience, now downtown in via Stock 2/2, V fl BUT NOTE, POSTAL ADDRESS: SISSA, via Beirut 2, 34014 Trieste, Italy tel:39-040-3787623 fax:39-040-3787615 http://people.sissa.it/~ale ---------------------------------------------------------------- SISSA Webmail https://webmail.sissa.it/ Powered by Horde http://www.horde.org/ From triesch at fias.uni-frankfurt.de Wed May 14 05:14:29 2008 From: triesch at fias.uni-frankfurt.de (Jochen Triesch) Date: Wed, 14 May 2008 09:14:29 -0000 Subject: Connectionists: 14 open PhD and Post-doc positions in computational vision Message-ID: <482AAD4E.2090709@fias.uni-frankfurt.de> The planned Frankfurt Bernstein Center for Neurotechnology (http://fias.uni-frankfurt.de/bernstein) offers a range of post-doc and PhD positions (14 in total, pending final approval) for theoretical research in: * computational neuroscience * computer vision * machine learning * developmental robotics The initiative will combine basic research in these fields to develop integrated and autonomously learning vision systems. We are looking for highly qualified PhD students and Post-docs who have graduated in any of the subjects above or in related fields such as physics, computer science, engineering, mathematics etc. In general, candidates are required to have a strong analytical background and good programming skills. Good communication skills in English are essential. Research is carried out in international groups located at the Frankfurt Institute for Advanced Studies (http://fias.uni-frankfurt.de/), the Computer Science Dept. of the University of Frankfurt (http://www.uni-frankfurt.de/), the Max Planck Institute for Brain Research (http://www.mpih-frankfurt.mpg.de/), the Honda Research Institute Europe (http://www.honda-ri.de/) and other associated research centers. All collaborating institutions are located in and around the cosmopolitan city of Frankfurt in the heart of Europe. More specifically, positions will be available for the following projects: * Cue-Integration in Large-Scale Multi-Modal Sensory Systems * Learning in Hierarchical Memories of Objects * Analysis of Non-linear Dynamical Systems * Generative Models for Learning and Visual Recognition under Realistic Conditions * On-Camera Foveated Vision (FPGA Implementation) * Development of Hardware and Software for Massively Parallel Implementation of Brain-inspired Vision Systems * Structural Learning of Motion and Depth Estimation * Neural Models of Normal and Abnormal Visual Development in Human Infancy * Dynamical Coordination of Neuronal Responses in Object Representation in the Visual Cortex * Neural Models of the Development of Visual Memory in Infants * The Role of Feedback Signals in Visual Processing Applications to any of the projects above are centrally collected and should be sent to Mrs. Andrea Schoepski . Candidates should list 1-3 projects that interest them. Required Application Materials: * Complete Curriculum Vitae * Copy of Masters or Diploma certificate * Copy of PhD certificate, if applicable * Statement of research interests and achievements * Two or three Letters of Reference * TOEFL or similar proof of proficiency in English Image files of scanned documents are acceptable. Alternatively, you may send ordinary mail to the address: Frankfurt Bernstein Center for Neurotechnology c/o FIAS Johann Wolfgang Goethe University Ruth-Moufang-Str. 1 60438 Frankfurt am Main Germany The review of applications will begin immediately. -- Prof. Dr. Jochen Triesch Johanna Quandt Research Professor Frankfurt Institute for Advanced Studies Web: http://fias.uni-frankfurt.de/~triesch/ Tel: +49 (0)69 798-47531 Fax: +49 (0)69 798-47611 From ferencz at gmail.com Wed May 14 16:47:29 2008 From: ferencz at gmail.com (Andras Ferencz) Date: Wed, 14 May 2008 20:47:29 -0000 Subject: Connectionists: Call for paper: International Workshop on Faces in Real-Life Images Message-ID: <482B4FDA.2090403@gmail.com> International Workshop on Faces in Real-Life Images: Detection, Alignment, and Recognition (In conjunction with ECCV 2008) Call for Papers Electronic submission due: July 23, 2008. Decisions: August 15, 2008. Camera ready due: August 25, 2008 There is rapidly increasing interest in the field of face recognition in image and videos; while there has been a great deal of progress in the past 10 years, much of the work is restricted to constrained settings in which one or more of the many variables that affect appearance, such as lighting, pose, or facial expression, has been controlled. We believe that focusing specifically on ?real-life? data sets will foster the development of new and more general techniques, and will ultimately result in more flexible face recognition systems. This is a new and interesting emergent direction, and we will make this workshop the right place for discussion and for the sharing of ideas on this topic. One aim of the workshop is to encourage collaboration between researchers who do face detection and recognition but may not be familiar with more general object recognition techniques, and those who do object recognition work but have not considered the application of their methods to the face recognition problem. It is interesting to note that one of the best known algorithms for unconstrained face recognition using random forests does not appear on the ?Face Recognition Web Page?. This is probably because the algorithm is known as a generic object recognition algorithm. We want to bring together people from the ?object recognition? community and the ?face recognition? community, and try to understand if they are distinct only for historical reasons or if they rely on different foundations. We solicit contributions in two categories. Category A: Novel methods in Detection, Alignment, and Recognition Papers in this category should present novel scientific contributions in the detection, alignment, or recognition of faces. We are particularly interested in the domain of unconstrained faces in which faces are not presented in a laboratory controlled setting. We encourage authors to show their results on the LFW database, although this is not essential for publication. We are also interested in relationships among detection, alignment and recognition. For example, how can recognition algorithms be used to improve detection performance? Or how do various alignment algorithms effect standard recognition algorithms? We are also interested in the use of hidden variable models, random field models, and other probabilistic models for solving any of these problems. Methods that incorporate an unsupervised, semi-supervised, or transfer learning method are also solicited. Category B: Unconstrained Face Recognition Challenge. The goal of these submissions is to compare algorithms for the unconstrained face recognition problem, and should present results on the Labeled Faces in the Wild database . Authors may submit either a short paper or a regular paper in this Category. For short papers (two pages or less), the authors need only include face recognition results, as described below. These results will be summarized and described by the organizers during the workshop. Authors may give a short description of their methods or refer to other publications which give the details of the algorithms used. Short papers will not appear as separate publications in the workshop proceedings, but will be described collectively in a single summary article describing results on the challenge. For regular papers (of standard ECCV format and length), authors should fully describe algorithms so that the code can be recreated by others. If accepted, these papers will be included in the proceedings of the workshop, but the authors may or may not be allocated an oral presentation, depending upon time availability. Papers that are submitted both to the main ECCV conference and to the workshop will be considered. Details of the LFW database, including formats of data, and organization of training, validation, and testing components, are described in the LFW technical report. It is not essential that an algorithm achieve state-of-the-art performance in order to be published at the workshop, although performance of the algorithm will be an important criterion in establishing the quality of the work. Papers that do not achieve state-of-the-art results may be published in the workshop proceedings depending upon the novelty of the proposed methods, but may not be allocated a talk, since the workshop time is limited. Such contributions will be summarized in a presentation on the overall Unconstrained Face Recognition Challenge. Performance Reporting. Every paper in Category B should report the estimated mean accuracy and the standard error of the mean, as defined on page 7 of the LFW technical report. Users should report results for image-restricted training (described in Section IV.A. of the technical report), but may also report results for unrestricted training (Section IV.B.) if desired. We also encourage authors to submit with their papers data files of results allow the creation of Precision-Recall curves. Instructions about the format of these files will be posted shortly. Format of papers For both Categories of papers, please use the standard ECCV template for paper submissions, including the short papers. Submissions should NOT be anonymous. Papers longer than 14 pages will be returned without review. There is no minimum paper length. website: https://www.cs.umass.edu/~elm/realfaces From opossumnano at gmail.com Fri May 16 04:05:56 2008 From: opossumnano at gmail.com (Tiziano Zito) Date: Fri, 16 May 2008 08:05:56 -0000 Subject: Connectionists: ANN: MDP 2.3 released! Message-ID: <20080516080544.GE24462@diamond.bccn-berlin> Dear collegues, we are proud to announce release 2.3 of the Modular toolkit for Data Processing (MDP): a Python data processing framework. The base of readily available algorithms includes Principal Component Analysis (PCA and NIPALS), four flavors of Independent Component Analysis (CuBICA, FastICA, TDSEP, and JADE), Slow Feature Analysis, Independent Slow Feature Analysis, Gaussian Classifiers, Growing Neural Gas, Fisher Discriminant Analysis, Factor Analysis, Restricted Boltzmann Machine, and many more. What's new in version 2.3? -------------------------- - Enhanced PCA nodes (with SVD, automatic dimensionality reduction, and iterative algorithms). - A complete implementation of the FastICA algorithm. - JADE and TDSEP nodes for more fun with ICA. - Restricted Boltzmann Machine nodes. - The new subpackage "hinet" allows combining nodes in arbitrary feed-forward network architectures with a HTML visualization tool. - The tutorial has been updated with a section on hierarchical networks. - MDP integrated into the official Debian repository as "python-mdp". - A bunch of bug-fixes. Resources --------- Download: http://sourceforge.net/project/showfiles.php?group_id=116959 Homepage: http://mdp-toolkit.sourceforge.net Mailing list: http://sourceforge.net/mail/?group_id=116959 -- Pietro Berkes Gatsby Computational Neuroscience Unit UCL London, United Kingdom Niko Wilbert Institute for Theoretical Biology Humboldt-University Berlin, Germany Tiziano Zito Bernstein Center for Computational Neuroscience Humboldt-University Berlin, Germany From N.Davey at herts.ac.uk Tue May 20 13:46:38 2008 From: N.Davey at herts.ac.uk (Neil Davey) Date: Tue, 20 May 2008 18:46:38 +0100 Subject: Connectionists: PhD in Cognitive Neuroscience of Decision Making and Learning Message-ID: UNIVERSITY OF HERTFORDSHIRE HEALTH AND HUMAN SCIENCES RESEARCH INSTITUTE SCIENCE AND TECHNOLOGY RESEARCH INSTITUTE PhD in Cognitive Neuroscience of Decision Making and Learning Applications are invited from candidates with good first degrees in one of: Cognitive Science, Neuroscience, Cognitive Psychology, Mathematics, Computer Science or related discipline (such as joint honours). This PhD studentship is jointly supported by research staff in the Schools of Psychology and Computer Science. The programme of research will have a primary focus on computational modelling of decision making / reinforcement learning, with the objective of generating results which would then inform experimental studies in human cognition, coupled with functional brain imaging (fMRI). Applicants should have a First or 2:1 class BSc (Hons) in Cognitive Science / Neuroscience / Cognitive Psychology / Maths / Computer Science or related discipline (e.g. joint honours) and exposure to programming (preferably in Matlab, C++ or similar). The research studentship award from the University will be equivalent to ?12,600 per annum bursary plus the payment of the standard UK student fees. For further information and an application form, contact Ms Jill Kilvington, Research Administrator, Health and Human Science Research Institute, Wright Building, University of Hertfordshire, College Lane, Hatfield, Herts AL10 9AB, Tel: 01707 285269 Fax: 01707 284170 or email: j.kilvington at herts.ac.uk To discuss the research programme in more detail then either contact Dr. John Done ( d.j.done at herts.ac.uk, +44(0)1707 286292 or Dr Neil Davey ( n.davey at herts.ac.uk , +44 (0) 1707284310 ) . The closing date for applications is 27/06/2008. Interviews will take place between 21st July and 1st August. Start date will be the beginning of the 2008/9 academic year i.e. end Sept/early Oct. -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080520/20959bc7/attachment-0001.html From jonas at buchli.org Wed May 21 00:58:31 2008 From: jonas at buchli.org (Jonas Buchli) Date: Tue, 20 May 2008 21:58:31 -0700 Subject: Connectionists: Paper: Frequency analysis with oscillators Message-ID: <1211345912.2434.17.camel@moria.buchli.org> Dear Connectionists, we think the following paper might be interesting for some of you: -------------------------------------------------------------------- Frequency analysis with coupled nonlinear oscillators Jonas Buchli, Ludovic Righetti and Auke Jan Ijspeert Abstract We present a method to obtain the frequency spectrum of a signal with a nonlinear dynamical system. The dynamical system is composed of a pool of adaptive frequency oscillators with negative mean-field coupling. For the frequency analysis, the synchronization and adaptation properties of the component oscillators are exploited. The frequency spectrum of the signal is reflected in the statistics of the intrinsic frequencies of the oscillators. The frequency analysis is completely embedded in the dynamics of the system. Thus, no pre-processing or additional parameters, such as time windows, are needed. Representative results of the numerical integration of the system are presented. It is shown, that the oscillators tune to the correct frequencies for both discrete and continuous spectra. Due to its dynamic nature the system is also capable to track non-stationary spectra. Further, we show that the system can be modeled in a probabilistic manner by means of a nonlinear Fokker?Planck equation. The probabilistic treatment is in good agreement with the numerical results, and provides a useful tool to understand the underlying mechanisms leading to convergence. Keywords: Frequency analysis; Coupled oscillators; Adaptive frequency oscillator available online: http://dx.doi.org/10.1016/j.physd.2008.01.014 If you do not have access to the fulltext please contact me for a reprint. Best regards Jonas Buchli -- ------------------------------------------------------- Jonas Buchli, Dr.sc., MSc EE Computational Learning and Motor Control Lab University of Southern California http://www-clmc.usc.edu/ +1 (213) 740 67 17 ------------------------------------------------------- From rsun at rpi.edu Wed May 21 23:33:30 2008 From: rsun at rpi.edu (Professor Ron Sun) Date: Wed, 21 May 2008 23:33:30 -0400 Subject: Connectionists: A full-day tutorial on the CLARION cognitive architecture Message-ID: A full-day tutorial on the CLARION cognitive architecture will take place on July 23rd, 2008, at the 30th Annual Conference of the Cognitive Science Society in Washington DC (http://ccc.utexas.edu/ cogsci08/index.html). For participants attending the CogSci2008 conference, the tutorial is free. This full-day tutorial introduces participants to CLARION, a dual- process/dual-representation cognitive architecture that focuses on the distinction between explicit and implicit cognitive processes, as well as their synergistic interactions. CLARION is also integrative, involving cognition (reasoning, learning, skill acquisition, etc.), motivation, metacognition, and so on. This presentation will provide a detailed, introductory description, along with many simulations, advanced topics, and formal results. Although some prior exposure to cognitive architectures and artificial neural networks can be helpful, prior understanding of these areas is not required, as the full-day format allows a detailed presentation of basic, as well as advanced, topics related to cognitive modeling using the CLARION cognitive architecture. This tutorial will enable participants to apply the basic concepts, theories, and computational models of CLARION to their own work. For registration, go to: http://ccc.utexas.edu/cogsci08/index.html For more information, please contact Sebastien Helie (helies at rpi.edu) ======================================================== 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 auke.ijspeert at epfl.ch Thu May 22 08:54:17 2008 From: auke.ijspeert at epfl.ch (Auke Ijspeert) Date: Thu, 22 May 2008 14:54:17 +0200 Subject: Connectionists: RSS2008 WS on locomotion control, June 28: Call for participation and poster-abstracts Message-ID: <48356CF9.1010607@epfl.ch> Dear connectionists, Researchers in locomotion control and learning might be interested in the following workshop that will take place in Zurich, Switzerland, on June 28 as part of the RSS2008 conference. Best regards, Auke Ijspeert Control of locomotion: from animals to robots Workshop at the "Robotics: Science and Systems" Conference */RSS2008/* , Zurich, Switzerland, Saturday, June 28, 2008. *Organizers*: *Auke Ijspeert *(EPFL, Lausanne, Switzerland), *Paolo Dario * (SSSA, Italy), and *Sten Grillner * (Karolinska Institute, Sweden) Workshop website: http://birg2.epfl.ch/rss2008/ *Description*: The goal of the workshop is to discuss how inspiration from the animal kingdom can help improving locomotion skills in robots, and how robots can be used as scientific tools in animal motor control. All aspects of locomotion will be considered including materials, actuators, sensors, control, and learning. In particular, the workshop aims at exploring how these different aspects can collectively be designed to improve the locomotor skills of future robots. We will discuss possible roads to tackle the challenges related to having robots get out of the labs and move in unstructured and partially unknown terrains. While robotics has clearly something to gain from biological inspiration, we will also discuss how robotics can give something back to biology, namely how robots can be used as scientific tools in animal motor control. For instance, how robots can be used to test hypotheses about neural circuits and/or biomechanical principles in invertebrate and vertebrate animals. *Topics*: Neuro-mechanical coupling, central pattern generators, compliant robots, passive and dynamic walkers, gait transitions, motor learning, swimming robots, crawling robots, walking robots, jumping robots, /etc/. *Format: *The workshop will have an interesting mix of biologists and roboticists as invited speakers (see list below) together with a poster session, whose participants will be selected after an open call for poster (see below). The workshop will be organized such as to provide ample time for discussions. We aim at a 75-25% ratio between presentations and discussions. We therefore suggest having each talk followed by a discussion, i.e. an alternation between talks and discussions. To guide the discussions, we will distribute beforehand a set of strategic questions (emails to speakers and participants + on this web page), and invite speakers and participants to exchange their thoughts about them. For more information, see the workshop website: http://birg2.epfl.ch/rss2008/ *Invited speakers:* ***Paolo Arena*, University of Catania, Italy* Holk** Cruse*, University of Bielefeld, Germany* Paolo Dario*, Scuola Superiore Sant'Anna, Italy.* Robert Full*, UC Berkeley, USA. * Sten** Grillner*, The Nobel Institute for Neurophysiology, Karolinska Institute, Sweden. * Auke Ijspeert*, EPFL, Switzerland. * Hiroshi Kimura*, Kyoto Institute of Technology, Japan. * Roger Quinn*, Case Western Reserve University, USA. * Stefan Schaal*, University of Southern California, USA. * Andre Seyfarth*, University of Jena, Germany. *Call for posters* Researchers in animal and robot locomotion are invited to submit a *2-page abstract* for presenting a poster at the workshop. Accepted poster presenters will also have the opportunity to make a *2-min poster teaser* (i.e. a very short oral presentation) to advertise their poster. Please send your abstract to auke.ijspeert at epfl.ch before *June 14*. Feel free to send it before, since we will review abstracts as they come in and we might have to restrict the number of accepted posters due to space restrictions. *Registration *Participants will need to register to the RSS2008 conference, see http://www.roboticsconference.org/ and http://www.roboticsconference.org/registration.shtml Note that the early registration for RSS2008 with a 100 Swiss Francs discount ends on May 25 (i.e. very soon!). -------------- next part -------------- An HTML attachment was scrubbed... URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20080522/74c15708/attachment-0001.html From vroth at inf.ethz.ch Fri May 23 05:04:06 2008 From: vroth at inf.ethz.ch (Volker Roth) Date: Fri, 23 May 2008 11:04:06 +0200 Subject: Connectionists: PhD positions at ETH Zurich/University of Basel (Switzerland) Message-ID: <48368886.3090507@inf.ethz.ch> ETH Zurich/University of Basel (Switzerland): Applications are invited for two fully-funded PhD positions for the EU project "Similarity-based Pattern Analysis and Recognition (SIMBAD)", which is a joint FET-STREP project involving ETH Zurich, University of Basel, Delft University of Technology (Netherlands), IST Lisbon (Portugal), University of Venice (Italy), University of Verona (Italy), and University of York (England). The project attempts to break new ground in similarity based pattern recognition where we will explore models and associated learning algorithms for non-Euclidean data and non-metric data situations. Application domains of this type arise in computer vision (e.g., shape analysis), in medical image processing and in bioinformatics where often short distances can be reliably estimated but for large distances, the signal to noise ratio drops below one. As a part of the SIMBAD project, the Swiss group, comprising of ETH Zurich and University of Basel, will focus on structure-preserving embeddings of non-metric data into Euclidean spaces and applications thereof to analyze tissue microarray images. Successful applicants will work under the supervision of Prof. Joachim Buhmann (Zurich) and Prof. Volker Roth (Basel). We are looking for highly motivated applicants who should have a profound knowledge in mathematical modeling and in algorithmics. Furthermore, the project requires substantial programming skills and a genuine interest to build a decision support system for pattern analysis. A prerequisite for starting PhD studies at ETHZ/Univ Basel are a Masters degree in Computer Science, Bioinformatics, Mathematics or Physics. An ideal researcher will have a strong background in Statistics and Machine Learning, complemented with a solid programming experience. Excellent oral and written communication skills would be additional assets. The two positions are planned for 3 years. The salary and conditions at ETH Zurich/University of Basel are very attractive. Applications (preferably in electronic form) should be sent to Ms Rita Klute , Tel.(secret.): +41-44-63 26496, Fax: +41-44-63 21562 Institute for Computational Science, ETH Zentrum, CAB G 69.1, Universit?tstrasse 6, CH-8092 Zurich, Switzerland For further inquiries, please contact: Joachim M. Buhmann: jbuhmann at inf.ethz.ch Volker Roth: volker.roth at unibas.ch To apply, email the following to the above mentioned contacts: 1. Your full CV 2. A page discussing your interests and motivation towards the topic. 3. At least one academic reference. -- ===================================================================== Volker Roth Computer Science Dept. Tel.: +41-(0)61-2670549 University of Basel Bernoullistr. 16, CH-4056 Basel, Switzerland email: volker.roth at unibas.ch ===================================================================== From juffi at ke.informatik.tu-darmstadt.de Fri May 23 05:17:09 2008 From: juffi at ke.informatik.tu-darmstadt.de (Johannes Fuernkranz) Date: Fri, 23 May 2008 11:17:09 +0200 Subject: Connectionists: Announcement: Journal of Interesting Negative Results Message-ID: <200805230917.m4N9HA720080@ultra02.rbg.informatik.tu-darmstadt.de> [please distribute, apologies for multiple postings] ------------------------------------------------------------------------ Journal of Intersting Negative Results http://www.jinr.org ------------------------------------------------------------------------ We are happy to announce the on-line publication of the first article in the Journal of Interesting Negative Results in Natural Language Processing and Machine Learning. Please visit http://www.jinr.org and click on "articles". JINR is an electronic journal, with a printed version to be negotiated with a major publisher once we have established a steady presence. The journal will bring to the fore research in Natural Language Processing and Machine Learning that uncovers interesting negative results. It is becoming more and more obvious that the research community in general, and those who work NLP and ML in particular, are biased towards publishing successful ideas and experiments. Insofar as both our research areas focus on theories "proven" via empirical methods, we are sure to encounter ideas that fail at the experimental stage for unexpected, and often interesting, reasons. Much can be learned by analysing why some ideas, while intuitive and plausible, do not work. The importance of counter-examples for disproving conjectures is already well known. Negative results may point to interesting and important open problems. Knowing directions that lead to dead-ends in research can help others avoid replicating paths that take them nowhere. This might accelerate progress or even break through walls! We propose this journal as a resource that gives a voice to negative results which stem from intuitive and justifiable ideas, proven wrong through thorough and well-conducted experiments. We also encourage the submission of short papers/communications presenting counter-examples to usually accepted conjectures or to published papers. The journal's scope encompasses all areas of Natural Language Processing and Machine Learning. Papers published in JINR will meet the highest quality standards, as measured by the originality and significance of the contribution. They will describe research with theoretical and practical significance. All theories and ideas will have to be clearly stated and justified by a deep literature review. From elli.chatzopoulou at incf.org Sun May 25 12:19:02 2008 From: elli.chatzopoulou at incf.org (INCF - Elli Chatzopoulou) Date: Sun, 25 May 2008 18:19:02 +0200 Subject: Connectionists: Reminder: early-registration deadline for Neuroinformatics Congress Message-ID: <48399176.3000806@incf.org> Register by June 2nd and save $150 off the full registration price! Online registration: www.neuroinformatics2008.org The organizers of Neuroinformatics 2008 are inviting you and your research team to the 1st INCF Congress of Neuroinformatics: **Databasing and Modeling the Brain** Stockholm, Sweden -September 7-9, 2008 **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 of structural and functional information from brain images Ulla Ruotsalainen (chair), Katrin Amunts, 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 AND more than 100 posters, including a selection of live demonstrations. We kindly ask you to spread information about the congress 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 at incf.org Phone: +46 8 52487491 Mobile: +46 7 61487491 Fax: +46 8 52487194 URL: www.incf.org From brandt at bcos.uni-freiburg.de Mon May 26 08:29:05 2008 From: brandt at bcos.uni-freiburg.de (Katrin Brandt) Date: Mon, 26 May 2008 14:29:05 +0200 Subject: Connectionists: =?iso-8859-15?q?Announcement_-_new_funding_initia?= =?iso-8859-15?q?tive_=22Bernstein_Focus=3A_Neural_basics_of_learning=22?= Message-ID: <483AAD11.8040108@bcos.uni-freiburg.de> Dear colleagues, we would like to point out that the German Federal Ministry of Education and Research (BMBF) has tendered a new funding initiative "National Network Computational Neuroscience - Bernstein Focus: Neural basics of learning" and encourage you to submit your proposals. The BMBF has established the "National Network Computational Neuroscience" in Germany as a structure for developing a new quality in Computational Neuroscience, for networking this research area and for promoting its international visibility. With the new funding initiative "Bernstein Focus: Neural basics of learning" within this framework the BMBF aims to support activities for the further development and networking of experimental and theoretical neuroscientific as well as technological capacities in order to investigate the neural basics of learning. Funding for up to five years is provided for interdisciplinary cooperation projects which supply a substantial contribution to the investigation of brain algorithms, to the understanding of dynamics and plasticity of the neural processes of learning und their technical applications. Written project outlines must be submitted to the project management organization (PT-DLR) by 30 September 2008 at the latest. In a second step, applicants whose project outlines have received a positive evaluation will be invited to submit a formal application. For the complete announcement please visit: http://www.bmbf.de/foerderungen/12434.php -- Dr. Katrin Brandt Bernstein Coordination Site of the National Network for Computational Neuroscience Albert-Ludwigs-Universit?t Freiburg Hansastr. 9A 79104 Freiburg Germany phone: +49 761 203 9594 fax: +49 761 203 9585 e-mail: brandt at bcos.uni-freiburg.de homepage: www.nncn.de From mr287 at georgetown.edu Mon May 26 19:29:17 2008 From: mr287 at georgetown.edu (Maximilian Riesenhuber) Date: Mon, 26 May 2008 19:29:17 -0400 Subject: Connectionists: Postdoctoral Position: Computational neuroscience, neural data analysis, "augmented cognition" Message-ID: <483B47CD.3040809@georgetown.edu> 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 single-trial analysis of high-density EEG data, as part of a larger collaborative project aiming to develop a real-time neurally-based target detection system combining machine and biological vision. The candidate is expected to take on a main role in the analysis of the acquired EEG data and their integration in our computational model of object recogntion in cortex, which in turn will influence experimental design, with the goal of exploring ways to maximally utilize the brain's perceptual processing bandwidth. 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. This position is also of interest for PhDs in computer science or engineering with an interest in moving into computational neuroscience. 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 need to be US citizens or permanent residents. The project is a collaboration between several companies and universities. 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 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. Georgetown University has a vibrant neuroscience community with over forty labs participating in the Interdisciplinary Program in Neuroscience. Its Center for Functional and Molecular Imaging (of which our lab is a member) features a recently upgraded research-dedicated 3T scanner and several EEG and NIRS recording systems. Georgetown's scenic campus is located at the edge of Washington, DC, one of the most intellectual and culturally rich cities in the country. 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. --MAX ********************************************************************** 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 Randy.OReilly at colorado.edu Tue May 27 03:18:51 2008 From: Randy.OReilly at colorado.edu (Randall C. O'Reilly) Date: Tue, 27 May 2008 01:18:51 -0600 Subject: Connectionists: Postdoc on PFC/BG/Cognitive Control Message-ID: <200805270118.51518.Randy.OReilly@colorado.edu> A postdoctoral position is available starting June 1, 2008, for research on computational models of the neural basis of higher level cognitive function, working in collaboration with Randall O'Reilly (CU Boulder), John Anderson and Christian Lebiere (CMU). We have funding to explore how the prefrontal cortex and basal ganglia can support higher levels of cognitive function ("executive control"), leveraging the convergent approaches of the ACT-R computational modeling framework on the more abstract and computationally powerful end of the spectrum, and more biologically-detailed models using the Leabra modeling framework. The ideal candidate would have familiarity with these computational modeling frameworks, and expertise in one of them, as well as knowledge of the relevant cognitive neuroscience literature on executive function in the prefrontal cortex and basal ganglia. The primary research will be computational, so extensive computational modeling expertise is required, as is a PhD in a relevant discipline. Interested individuals should send a curriculum vitae, representative publications, a statement of research interests, and three letters of reference via email to Randy.OReilly at colorado.edu. Applications will be reviewed as they are received, continuing until the position is filled. The University of Colorado at Boulder is committed to providing a safe and productive learning and living community. To achieve that goal, we conduct background investigations for all final applicants being considered for employment. The University of Colorado is committed to diversity and equality in education and employment. - Randy From hitzler at aifb.uni-karlsruhe.de Tue May 27 05:42:18 2008 From: hitzler at aifb.uni-karlsruhe.de (Pascal Hitzler) Date: Tue, 27 May 2008 11:42:18 +0200 Subject: Connectionists: CfP: NatuReS: Nature inspired Reasoning for the Semantic Web Message-ID: <483BD77A.7060704@aifb.uni-karlsruhe.de> ============================================================= F I R S T CALL FOR PAPERS NatuReS 2008 First International Workshop on Nature Inspired Reasoning for the Semantic Web (at ISWC 2008) Submissions-deadline: July 25, 2008. Website: http://natures.few.vu.nl --- The goal of this workshop is to bring together researchers from the Semantic Web community with more Nature inspired communities, such as the people interested in Computational Intelligence (CI), Neural Networks and to discuss current trends in Semantic Web. We encourage the submission of papers investigating the use of nature inspired techniques to address knowledge representation and reasoning problems. Those problems includes (but are not restricted to) the following topics: * Data storage and retrieval * Data integration* * Complex reasoning* Some keywords : * Neural Networks, * Evolutionary computing (EA and others), * Potential field methods, * Simulated annealing, * Artificial immune systems, * Epidemic protocols (Gossiping), * Swarm intelligence (Ants, PSO, flocking birds) * Ontology alignment * Reasoning * Distributed Knowledge Management System * Complex systems * Data integration * Semantic Web * RDF Submitted paper should not exceed 15 pages (LNCS style) and must be written in English. --- Program Committee * ?zalp Babaoglu, University Bologna, Italy * Bernardo Cuenca Grau, Oxford, UK * Guszti Eiben, Vrije Universiteit, Amsterdam * Artur Garcez, City University London, UK * Andreas Harth, DERI, Galway * Barbara Hammer, Clausthal, Germany * Frank van Harmelen, Vrije Universiteit, Amsterdam * Alexander L?ser, SAP * Peter Mika, Yahoo, Barcelona, Spain * Nicolas Monmarch?, Polytech? Tours, France * Hans-J?rgen Ohlbach, University of Muenchen, Germany * Axel Polleres, DERI, Galway * Lael Schooler, MPI, Berlin * Christoph Schmitz, 1&1 Internet AG, Karlsruhe * Martijn Schut, Vrije Universiteit, Amsterdam * Giorgos Stamou, National Technical University of Athens, Greece * Peter Tino, University of Birmingham, UK Organising committee * Christophe Gu?ret, Vrije Universiteit, Amsterdam * Pascal Hitzler, University of Karlsruhe, Germany * Stefan Schlobach, Vrije Universiteit, Amsterdam --- The first international workshop on Nature inspired Reasoning for the Semantic Web (NatuReS) is sponsored by the EU funded Large Knowledge Collider (LarKC, http://www.larkc.eu) -- PD Dr. Pascal Hitzler Institute AIFB, University of Karlsruhe (TH), 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 Springer Lehrbuch: http://www.semantic-web-grundlagen.de