From mhb0 at Lehigh.EDU Sat Jan 1 11:03:50 2005 From: mhb0 at Lehigh.EDU (Mark H. Bickhard) Date: Sat, 1 Jan 2005 11:03:50 -0500 Subject: ISI 2005 Call for Papers/Participation Message-ID: Interactivist Summer Institute 2005 September 19-23, 2005 Madren Conference Center Clemson University, Clemson, South Carolina, USA Join us in exploring the frontiers of understanding of life, mind, and cognition. There is a growing recognition - across many disciplines - that phenomena of life and mind, including cognition and representation, are emergents of far-from-equilibrium, interactive, autonomous systems. Mind and biology, mind and agent, are being re-united. The classical treatment of cognition and representation within a formalist framework of encodingist assumptions is widely recognized as a fruitless maze of blind alleys. From neurobiology to robotics, from cognitive science to philosophy of mind and language, dynamic and interactive alternatives are being explored. Dynamic systems approaches and autonomous agent research join in the effort. The interactivist model offers a theoretical approach to matters of life and mind, ranging from evolutionary- and neuro-biology - including the emergence of biological function - through representation, perception, motivation, memory, learning and development, emotions, consciousness, language, rationality, sociality, personality and psychopathology. This work has developed interfaces with studies of central nervous system functioning, the ontology of process, autonomous agents, philosophy of science, and all areas of psychology, philosophy, and cognitive science that address the person. The conference will involve both tutorials addressing central parts and aspects of the interactive model, and papers addressing current work of relevance to this general approach. This will be our third Summer Institute; the first was in 2001 at Lehigh University, Bethlehem, PA, USA, and the second was in 2003 in Copenhagen, Denmark. The intention is for this Summer Institute to become a traditional biennial meeting where those sharing the core ideas of interactivism will meet and discuss their work, try to reconstruct its historical roots, put forward current research in different fields that fits the interactivist framework, and define research topics for prospective graduate students. People working in philosophy of mind, linguistics, social sciences, artificial intelligence, cognitive robotics, theoretical biology, and other fields related to the sciences of mind are invited to send their paper submission or statement of interest for participation to the organizers. http://www.lehigh.edu/~interact/isi2005/index.htm Mark H. Bickhard Lehigh University 17 Memorial Drive East Bethlehem, PA 18015 mark at bickhard.name http://bickhard.ws/ From cns at www.cnsorg.org Sat Jan 1 14:29:45 2005 From: cns at www.cnsorg.org (CNS) Date: Sat, 1 Jan 2005 12:29:45 -0700 Subject: FIRST CALL FOR PAPERS, CNS*2005 Message-ID: <20050101192947.M51094@www.cnsorg.org> CALL FOR PAPERS, CNS*2005: SUBMISSION DEADLINE: February 1, 2005 midnight SUBMISSIONS WILL OPEN January 15th, 2005. NOTE: New submission procedure this year Fourteenth Annual Computational Neuroscience Meeting CNS*2005 July 17 - July 21, 2005 Madison, Wisconsin, USA www.cnsorg.org CNS*2005 will be held in Madison Wisconsin from Saturday, July 17 to Wednesday, July 21, 2005. The main meeting will be July 17-19 followed by two days of workshops on July 20 and 21. Submissions can include experimental, model-based, as well as more abstract theoretical approaches to understanding neurobiological computation. We especially encourage research that mixes experimental and theoretical studies. We also accept papers that describe new technical approaches to theoretical and experimental issues in computational neuroscience or relevant software packages. INVITED SPEAKERS: Michael Hasselmo (Boston University) Lucia Jacobs (UC Berkeley) Gyorgy Buszaki (Rutgers University) Submissions to the meeting will take the form of a 3-page summary describing the nature and scope of the work, and outlining the main results. Details regarding formatting of submissions will be posted at www.cnsorg.org. These summaries will be reviewed by the program committee and used determine acceptance for presentation at the meeting as well as to construct the oral program. Authors will also be asked to submit a standard abstract for printing in the program book. All submissions will be acknowledged by email. THE REVIEW PROCESS Summaries will be judged and accepted for the meeting based on the clarity with which the work is described and the biological relevance of the research. For this reason authors should be careful to make the connection to biology clear. CNS strongly believes in the open exchange of ideas and we reject only a small fraction of submissions (~5%). Rejections are usually based on absence of biological relevance (e.g. pure machine learning). We will notify authors of meeting acceptance by April 1. All acceptable summaries will be reviewed by two independent referees, and the oral program of the meeting will constructed based on these reviews. Most oral presentations will be 20 minutes in length, but several papers will be selected for longer "featured oral" presentations. In addition to perceived quality as an oral presentation, the novelty of the research and the diversity and coherence of the overall program will be considered. To ensure diversity, those who have given talks in the recent past will not be selected and multiple oral presentations from the same lab will be discouraged. All accepted papers not selected for oral talks may be presented during evening poster sessions. Authors will be notified of the presentation format of their papers by the end of April. PROCEEDINGS AND PUBLICATION In the past, the proceedings of the meeting were published as a special supplement to the journal Neurocomputing. The same review process was used to determine the program acceptance in the journal. This year, the proceedings of the meeting will take the form of electronic publication of all 3-page summaries of work presented at the meeting. A separate review process will be used for those electing for post-meeting journal publication. Authors wishing to submit their work for peer-reviewed publication in Neurocomputing will be required to submit complete 6-page papers by May 2nd. Manuscripts will be reviewed according to the usual standards for journal publication. Authors will notification of submission status (accept, reject, revise) and receive reviewer comments by the end of June, several weeks before the meeting. Authors will then have until September 15 to submit revised manuscripts. Final notification of acceptance based on these revisions will be sent by October 15. Detailed instructions to authors will be posted at www.cnsorg.org. -- CNS - Organization for Computational Neurosciences From martin.giese at uni-tuebingen.de Sun Jan 2 17:38:07 2005 From: martin.giese at uni-tuebingen.de (Martin Giese) Date: Sun, 02 Jan 2005 23:38:07 +0100 Subject: Job announcements (PhD position in Tuebingen) Message-ID: <41D877CF.4020904@uni-tuebingen.de> PHD POSITION AT THE LABORATORY FOR ACTION REPRESENTATION AND LEARNING, HERTIE INSTITUTE FOR CLINICAL BRAIN RESEARCH, TUEBINGEN, GERMANY We offer a PhD Position in the context of a project on the expression of emotions by body movements. The project is funded by the Human Frontier Science Program (HFSP) and realized in collaboration with the College de France, the Weizman Institute, and the University of Tilburg. Start date is as soon as possible. We seek for an individual with a background in computer science, engineering, physics, or mathematics with interest in motion capture, computer graphics, machine learning, motor control, or bioinformatics. The project will include developing new algorithms for modeling trajectories, and working with modern systems for motion capture and computer animation. The Laboratory for Action Representation and Learning (ARL) provides a highly interdisciplinary research environment combining methods from theoretical and experimental neuroscience, computer graphics, computer vision, and machine learning. ARL studies the neural mechanisms of the perception of complex movements, and algorithms for the modeling of complex movements in normals and patients. The Hertie Institute for Clinical Brain Research is one of the largest centers for neurological research in Germany. Its four departments host more than 150 researchers focusing on many different aspects of modern neurology. ARL is closely affiliated with the Max Planck Institute for Biological Cybernetics in Tbingen. Tbingen offers an international PhD program in the Graduate School for Neural and Behavioral Sciences that realized in collaboration between the University and the Max Planck Institutes. Interested candidates should send or email CVs and the names of 2 references to Martin Giese, ARL, Dept. of Cognitive Neurology, University Clinic Tuebingen, Schaffhausenstr. 113, D-72076 Tuebingen, Germany. Tel.: (+49) 7071 601 724 Email: martin.giese at uni-tuebingen.de Further information: http://www.uni-tuebingen.de/uni/knv/arl/ http://www.hih-tuebingen.de/ http://www.uni-tuebingen.de/neuroschool From thomas.hofmann at ipsi.fraunhofer.de Mon Jan 3 15:20:37 2005 From: thomas.hofmann at ipsi.fraunhofer.de (Thomas Hofmann) Date: Mon, 3 Jan 2005 21:20:37 +0100 Subject: 4 Positions for Ph.D. RAships and/or Postdocs at Darmstadt Message-ID: The Computer Science Department of the Technical University of Darmstadt invites applications for four (4) positions as Research Assistants (Wissenschaftliche Mitarbeiter/innen). We are particularly looking for applicants with interest in one or more of the following areas: * Theory, methods and applications of Machine Learning * Intelligent Information Retrieval and innovative search engines * Natural language understanding * Methods and principles of Data Mining * Reasoning, knowledge representation and probabilistic inference * Artificial Neural Networks We offer an excellent hardware and software equipment and the prospect to work on cutting-edge research projects in a dynamic and international research team. Opportunity to work towards a Ph.D. degree will be provided. Applicants are expected to contribute to the teaching assignments and research projects of the group. Rank & Salary: The salary level is determined according to the BAT (Bundes-Angestellten-Tarif) scale (BAT IIa). Positions are initially for three years with a possible further extension.=20 Qualifications: degree (Diplom, Bachelor or Masters) in computer science or a neighboring discipline is required; good knowledge in software development and programming. Positions available: starting February 1st 2005 Closing date: January 15th 2005 Application: Applications should include the standard applications documents such as curriculum vitae, copies of the relevant university certificates (Diploma, Bachelor, or Master), list of publications, and statement of research interests. Please send your application to:=20 Dekan des Fachbereiches 20,=20 Position #270 Hochschulstra=DFe 10 64289 Darmstadt, Germany The Technical University of Darmstadt is an equal opportunities employer. Women and disabled candidates are especially encouraged to apply. Applications should be accompanied by the standard application documents including letter of application, curriculum vitae, exam certificates and references. From l.wiskott at biologie.hu-berlin.de Wed Jan 5 09:31:51 2005 From: l.wiskott at biologie.hu-berlin.de (Laurenz Wiskott) Date: Wed, 5 Jan 2005 15:31:51 +0100 Subject: Neurogenesis in the Hippocampus - E-Print (and open postdoc position) Message-ID: <16859.64087.972538.74691@huxley.biologie.hu-berlin.de> WHAT IS THE FUNCTIONAL ROLE OF ADULT NEUROGENESIS IN THE HIPPOCAMPUS? by Laurenz Wiskott, Malte Rasch, and Gerd Kempermann Abstract: The dentate gyrus is part of the hippocampal memory system and special in that it generates new neurons throughout life. Here we discuss the question of what the functional role of these new neurons might be. Our hypothesis is that they help the dentate gyrus to avoid the problem of catastrophic interference when adapting to new environments. We assume that old neurons are rather stable and preserve an optimal encoding learned for known environments while new neurons are plastic to adapt to those features that are qualitatively new in a new environment. A simple network simulation demonstrates that adding new plastic neurons is indeed a successful strategy for adaptation without catastrophic interference. Available from: http://cogprints.org/4012/ Reference: Wiskott, L., Rasch, M., and Kempermann, G. (2004). What is the functional role of adult neurogenesis in the hippocampus? Cognitive Sciences EPrint Archive (CogPrints) 4012, http://cogprints.org/4012/ (). Additional Information: http://itb1.biologie.hu-berlin.de/~wiskott/Projects/Hippocampus.html Open Postdoc Position: http://itb.biologie.hu-berlin.de/~wiskott/jobs2.html -- Dr. Laurenz Wiskott, Institute for Theoretical Biology, Berlin http://itb.biologie.hu-berlin.de/~wiskott/ l.wiskott at biologie.hu-berlin.de From bogus@does.not.exist.com Thu Jan 6 12:54:51 2005 From: bogus@does.not.exist.com () Date: Thu, 6 Jan 2005 17:54:51 -0000 Subject: Postdoctoral Fellowship Message-ID: <52A8091888A23F47A013223014B6E9FE02837F98@03-CSEXCH.uopnet.plymouth.ac.uk> From schapire at CS.Princeton.EDU Thu Jan 6 09:35:17 2005 From: schapire at CS.Princeton.EDU (Robert Schapire) Date: Thu, 6 Jan 2005 09:35:17 -0500 (EST) Subject: tenure-track AI position at Princeton CS Message-ID: <200501061435.j06EZHgf028867@bolle.CS.Princeton.EDU> The Princeton University Department of Computer Science has at least one opening for a tenure-track faculty position, preferably at the level of assistant professor. This position is especially targeted in the area of artificial intelligence, very broadly defined. See the official announcement below. If you apply for this position, please also ask your references to mail or email their letters directly to the address given in the ad. Rob Schapire ================================================================= FACULTY POSITIONS Computer Science Department Princeton University We invite you to apply for Assistant Professor, tenure-track positions. We are entertaining applications in all areas of Computer Science, with particular emphasis on Artificial Intelligence. Candidates for more senior ranks with exceptional records of research will also be considered. Applicants must demonstrate superior research and scholarship potential as well as teaching ability. A Ph.D or equivalent in Computer Science or related areas is required. Successful candidates at all ranks are expected to pursue an active research program and to contribute significantly to the teaching programs of the department. Applicants should include a resume and the names of at least three people who can comment on the applicant's professional qualification. Applications should be sent to: Chair, Search Committee Princeton University Department of Computer Science 35 Olden Street Princeton, NJ 08544-2087 Email: search at cs.princeton.edu The Committee will begin to consider applications in January 2005. Princeton University is an Equal Opportunity/Affirmative Action employer. From bower at uthscsa.edu Fri Jan 7 12:42:22 2005 From: bower at uthscsa.edu (james Bower) Date: Fri, 07 Jan 2005 11:42:22 -0600 Subject: abstract deadline for biological modeling meeting Message-ID: ABSTRACT SUBMISSION DEADLINE JANUARY 15th midnight ADDITIONAL SUPPORT FOR STUDENT TRAVEL IS NOW AVAILABLE January 15th is the abstract submission deadline for the the first annual meeting for realistic biological modeling in San Antonio Texas, March 31st - April 2nd, 2005. (Wam-Bamm*05). The meeting is specifically focused on realistic biological modeling, rather than more abstract approaches to neural computation, with an emphasis both on scientific results and technical issues. Although it is being held in association with the second GENESIS Users Meeting (GUM*05) all computational biologists, not only those using GENESIS, are invited to present scientific as well as technical work. Only an abstract is required for meeting presentation. In particular we would encourage modelers using NEURON to attend and meet Michael Hines, developer of the NEURON modeling system. The first day of the meeting will be devoted to Tutorials including: Introduction to realistic neural modeling: Dr. David Beeman, University of Colorardo The NEURON simulator - recent developments: Dr. Michael Hines, Yale University From experiment to simulation - a case study: Dr. Dieter Jaeger, Emory University Controlling complex synaptic input patterns: Jeremy Edgerton, Emory University Modeling calcium and biochemical reactions: Dr. Avrama Blackwell, George Mason University Constructing large networks in GENESIS: Dr. Michael Vanier, Caltech. Parameter searching in GENESIS: Dr. Michael Vanier, Caltech Parallel (P-) GENESIS: Greg Hood, Pittsburgh Supercomputing Center XML for model specification: Dr. Sharon Crook, Arizona State University Building 3D network models with neuroConstruct: Padraig Gleeson, University College London The next two days will be devoted to invited speakers as well as contributed presentations primarily in poster form. Confirmed Invited Speakers include: Dr. Michael Hauser, University College London, "Model-based studies of cerebellar cortical circuitry" Dr. Michael Hasselmo, Boston University, "Modeling the role of entorhinal cortex, prefrontal cortex and hippocampus in memory guided behavior" Dr. Charles Wilson, University of Texas, San Antonio, "A model of autonomous irregular firing and bursting in striatal cholinergic interneurons" Dr. Larry Parsons, University of Sheifield, "what can realistic modeling tell us about cognitive function?" Dr. Graham Cummins, Center for Computational Biology, Montana State University, "Parameter estimation in realistic models of cricket dendrites" The deadline for abstract submission is January 15th, and the deadline for early registration at reduced rates is February 1st. Please visit the meeting website: http://www.WAM-BAMM.org to register, submit abstracts and for other general meeting information. Hope to see you in San Antonio this spring. Jim Bower Dave Beeman -- James M. Bower Ph.D. Research Imaging Center University of Texas Health Science Center at San Antonio 7703 Floyd Curl Drive San Antonio, TX 78284-6240 Cajal Neuroscience Center University of Texas San Antonio Phone: 210 567 8080 Fax: 210 567 8152 From j.a.bullinaria at cs.bham.ac.uk Fri Jan 7 09:18:18 2005 From: j.a.bullinaria at cs.bham.ac.uk (John Bullinaria) Date: Fri, 7 Jan 2005 14:18:18 +0000 Subject: Scholarships for MSc in Natural Computation at Birmingham, UK Message-ID: Studentships/Scholarships for MSc in Natural Computation ======================================================== School of Computer Science The University of Birmingham Birmingham, UK (http://www.cs.bham.ac.uk/research/NC/) Applications are invited for an advanced 12 month MSc programme in Natural Computation starting in September 2005. Natural Computation systems, such as artificial neural networks and genetic algorithms, use ideas and inspirations from biological, ecological, social and physical systems. The programme comprise of six taught modules in Neural Computation, Evolutionary Computation, Molecular and Quantum Computation, Nature Inspired Optimisation, Nature Inspired Learning, and Nature Inspired Design (10 credits each); two mini research projects (30 credits each); and one full scale research project (60 credits). The programme is supported by the EPSRC through its Master's Level Training Packages and by a number of leading companies. Our industrial advisory board includes representatives from BT Exact, Honda, Unilever, QinetiQ, Rolls Royce, HP Labs, e-9 Ltd and SPSS. The School of Computer Science is a research intensive school and was rated 5 for its research excellence in the latest (2001) research assessment exercise. The School has a world-leading group in natural computation and computational intelligence (http://www.cs.bham.ac.uk/research/NC/), including more than 40 researchers (including teaching and research staff and PhD students), working on a wide range of topics in natural computation and computational intelligence. We have a Centre of Excellence for Research in Computational Intelligence and Applications (CERCIA), specialising in applied research and knowledge transfer (www.cercia.ac.uk). The programme is open to candidates with a very good honours degree or equivalent qualifications in Computer Science/Engineering or closely related areas. Several fully funded EPSRC studentships (covering fees and maintenance costs) are available. These are awarded on a competitive basis according to applicants' academic achievements. Additional financial support from our industrial partners may be available during the summer project period. Further details about this programme and funding opportunities, plus an on-line application form, are available from our Web-site at: http://www.cs.bham.ac.uk/study/postgraduate-taught/msc-nc/ The Programme Director is Dr Alastair Channon (a.d.channon at cs.bham.ac.uk). From C.Campbell at bristol.ac.uk Fri Jan 7 08:00:06 2005 From: C.Campbell at bristol.ac.uk (ICG Campbell, Engineering Mathematics) Date: Fri, 07 Jan 2005 13:00:06 -0000 Subject: Advert: Professorship in AI, Bristol University Message-ID: <96228959.1105102806@ems-iggs.enm.bris.ac.uk> Advertisement for position: Professor of Artificial Intelligence, Department of Engineering Mathematics, University of Bristol, United Kingdom We seek to appoint a research leader in Artificial Intelligence to complement the strengths and further enhance the international reputation of the existing AI Group in fuzzy and probabilistic uncertainty, kernel-based methods and the mathematical treatment of learning in intelligent systems. An established track record in any aspect of AI and its applications is required, such as intelligent data analysis, uncertainty modelling, graphical methods, machine learning, emergent behaviour or robotics. A willingness to actively collaborate and engage in interdisciplinary research is also essential. The Department of Engineering Mathematics is unique in being the only research-intensive mathematics department in the UK within an engineering faculty. Its remit is therefore to pursue innovation in mathematics relevant to engineering (inclusive of computer science) and other application areas. Its research received a 5*A rating in the 2001 Research Assessment Exercise. It is anticipated the appointee will use the existing base and further appointments to build a group with an international reputation. For those interested, more details about this position can be obtained from: http://www.bris.ac.uk/boris/jobs/ads?ID=31015 The webpage for the existing AI group may be found at: http://www.enm.bris.ac.uk/ai/index.html The University webpage is at: http://www.bris.ac.uk/ ***Closing date for applications: 9.00 am on 04 February 2005 ---------------------- Colin Campbell, Engineering Mathematics C.Campbell at bristol.ac.uk From kbp at imm.dtu.dk Fri Jan 7 04:31:01 2005 From: kbp at imm.dtu.dk (Kaare Brandt Petersen) Date: Fri, 7 Jan 2005 10:31:01 +0100 (MET) Subject: The Matrix Cookbook - new version Message-ID: Dear Colleagues (Apollogies for multiple postings) A new and updated version of The Matrix Cookbook is available for download http://www.imm.dtu.dk/pubdb/views/edoc_download.php/3274/pdf/imm3274.pdf The Matrix Cookbook is a desktop reference on formulas regarding matrices such as the derivatives of determinants and traces, identities involving inverses, statistical moments and more. Apart from smaller additions and corrections, this version of The Matrix Cookbook has been updated with material on derivatives of complex matrices and matrix norm inequalities. This is largely due to the work of Michael Syskind Pedersen who has joined the project as author. Comments and corrections are most welcome. Best regards, Kaare -- Kaare Brandt Petersen * http://2302.dk From fyfe-ci0 at wpmail.paisley.ac.uk Sat Jan 8 11:21:55 2005 From: fyfe-ci0 at wpmail.paisley.ac.uk (Colin Fyfe) Date: Sat, 08 Jan 2005 16:21:55 +0000 Subject: New Book Message-ID: I have taken extracts from 8 of the PhDs completed in this university over the last few years and published them together as a book. I hope this may interest some in the connectionists community, and would be happy to receive any feedback. Colin Fyfe ----------------------------------------------- Hebbian Learning and Negative Feedback Networks Colin Fyfe Springer ISBN 1-85233-883-0 The central idea of this book is that artificial neural networks which use negative feedback of activation can use simple Hebbian learning to self-organise in such a way that they uncover interesting structure in data sets. The network in its simplest form performs a Principal Component Analysis. Extensions to the network are shown to perform Exploratory Projection Pursuit: they find low-dimensional filters of the data which reveal interesting structure in the data. For example, we might search for outliers from the main body of the data or clusters within the data set and this search can be performed in a hierarchical manner – we find one cluster in the midst of many and then re-project the data from this one cluster to attempt to find sub-clusters. There are two main ways of performing these searches and these are contrasted and compared and a composite method created which exhibits useful properties from the two underlying methods. The network can also be used to find independent components of a data set in a number of different ways. For example, one extension to the basic network is shown to perform a type of Factor Analysis – it identifies a set of factors which when OR-ed together will construct the data set. Other methods are used to perform Independent Component Analysis which is extensively used in blind source separation – extracting one signal from a linear mixture of signals. The network can also be used for clustering in a topology preserving manner: there are several ways of clustering using this network in such a way that similar data points are clustered close to one another and only similar data points are treated this way. In part 2 of the book, twinned networks are introduced: these networks have two input data streams on which they self-organise using simple Hebbian learning with negative feedback again. In their basic form, the networks are shown to perform Canonical Correlation Analysis, the statistical technique which finds those filters onto which projections of the two data streams have greatest correlation. Various extensions of the basic methods are devised in order to create methods which react to more than two data streams at a time or which deal with problems such as multicollinearity. A further extension is the twinning of the Exploratory Projection Pursuit methods from the first part of the book so that the new network identifies shared structure across two data streams. This new network is also shown to perform Independent Component Analysis. A final chapter deviates somewhat from the rest of the book since its emphasis is on an extension of the Principal Curve algorithm so that we now have two curves learning on two data streams simultaneously. Since the scope of the book is the development of new algorithms, all algorithms which are derived analytically, are illustrated on artificial data before being used on real data sets. Where it is of interest, the results are compared with those from standard statistics or from alternative artificial neural networks. Other than the final chapter, all networks are biologically plausible in that they use locally available data to self-organise to extract information from data sets. Table of Contents {1}Introduction {1.1}Artificial Neural Networks {1.2}The Organisation of this Book Part I Single Stream Networks {2}Background {2.1}Hebbian Learning {2.2}Quantification of Information {2.3}Principal Component Analysis {2.4}Weight Decay in Hebbian Learning {2.5}ANNs and PCA {2.6}Anti-Hebbian Learning {2.7}Independent Component Analysis {2.8}Conclusion {3}The Negative Feedback Network {3.1}Introduction {3.2}The $VW$ Model {3.3}Using Distance Differences {3.4}Minor Components Analysis {3.5}Conclusion {4}Peer-Inhibitory Neurons {4.1}Analysis of Differential Learning Rates {4.2}Differential Activation Functions {4.3}Emergent Properties of the Peer-Inhibition Network {4.4}Conclusion {5}Multiple Cause Data {5.1}Non-negative Weights {5.2}Factor Analysis {5.3}Conclusion {6}Exploratory Data Analysis {6.1}Exploratory Projection Pursuit {6.2}The Data and Sphering {6.3}The Projection Pursuit Network {6.4}Other Indices {6.5}Using Exploratory Projection Pursuit {6.6}Independent Component Analysis {6.7}Conclusion {7}Topology Preserving Maps {7.1}Background {7.2}The Classification Network {7.3}The Scale Invariant Map {7.4}The Subspace Map {7.5}The Negative Feedback Coding Network {7.6}Conclusion {8}Maximum Likelihood Hebbian Learning {8.1}The Negative Feedback Network and Cost Functions {8.2}$\epsilon $-Insensitive Hebbian Learning {8.3}The Maximum Likelihood EPP Algorithm {8.4}A Combined Algorithm {8.5}Conclusion Part II Dual Stream Networks {9}Two Neural Networks for Canonical Correlation Analysis {9.1}Statistical Canonical Correlation Analysis {9.2}The First Canonical Correlation Network {9.3}Experimental Results {9.4}A Second Neural Implementation of CCA {9.5}Simulations {9.6}Linear Discriminant Analysis {9.7}Discussion {10}Alternative Derivations of CCA Networks {10.1}A Probabilistic Perspective {10.2}Robust CCA {10.3}A Model Derived from Becker's Model 1 {10.4}Discussion {11}Kernel and Nonlinear Correlations {11.1}Nonlinear Correlations {11.2}The Search for Independence {11.3}Kernel Canonical Correlation Analysis {11.4}Relevance Vector Regression {11.5}Appearance-Based Object Recognition {11.6}Mixtures of Linear Correlations {12}Exploratory Correlation Analysis {12.1}Exploratory Correlation Analysis {12.2}Experiments {12.3}Connection to CCA {12.4}FastECA {12.5}Local Filter Formation From Natural Stereo Images {12.6}Twinned Maximum Likelihood Learning {12.7}Unmixing of Sound Signals {12.8}Conclusion {13}Multicollinearity and Partial Least Squares {13.1}The Ridge Model {13.2}Application to CCA {13.3}Extracting Multiple Canonical Correlations {13.4}Experiments on Multicollinear Data {13.5}A Neural Implementation of Partial Least Squares {13.6}Conclusion {14}Twinned Principal Curves {14.1}Twinned Principal Curves {14.2}Properties of Twinned Principal Curves {14.3}Twinned Self-Organising Maps {14.4}Discussion {15}The Future {15.1}Review {15.2}Omissions {15.3}Current and Future Work Appendices A Negative Feedback Artificial Neural Networks {A.1}The Interneuron Model {A.2}Other Models {A.3}Related Biological Models B Previous Factor Analysis Models {B.1} F\"{o}ldi\'{a}k's Sixth Model {B.2}Competitive Hebbian Learning {B.3}Multiple Cause Models {B.4}Predictability Minimisation {B.5}Mixtures of Experts {B.6}Probabilistic Models C Related Models for ICA {C.1}Jutten and Herault {C.2}Nonlinear PCA {C.3}Information Maximisation {C.4}Penalised Minimum Reconstruction Error {C.5}FastICA D Previous Dual Stream Approaches {D.1}The I-Max Model {D.2}Stone's Model {D.3}Kay's Neural Models {D.4}Borga's Algorithm E Data Sets {E.1}Artificial Data Sets {E.2}Real Data Sets Legal disclaimer -------------------------- The information transmitted is the property of the University of Paisley and is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Statements and opinions expressed in this e-mail may not represent those of the company. Any review, retransmission, dissemination and other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender immediately and delete the material from any computer. -------------------------- From ezequiel at sussex.ac.uk Mon Jan 10 06:45:25 2005 From: ezequiel at sussex.ac.uk (Ezequiel Di Paolo) Date: Mon, 10 Jan 2005 11:45:25 +0000 (GMT) Subject: Advert: Postdoctoral positions at Leeds and Sussex Universities In-Reply-To: <96228959.1105102806@ems-iggs.enm.bris.ac.uk> Message-ID: Post-Doctoral Positions, Universities of Leeds & Sussex Complex Adaptive Networks Computational Neuroscience, Bio-Inspired Robotics & Adaptive Behaviour "Spatially Embedded Complex Systems Engineering" Four postdoctoral fellowships are available immediately for research in computational and mathematical modelling, particularly of spatial factors in neural and neuro-chemical systems, and the IT systems underpinning air-traffic control. Two postdocs (PD1 & PD2) will be located in the Biosystems group within the School of Computing at the University of Leeds (http://www.informatics.leeds.ac.uk/), and two (PD3 & PD4) will be located in the Centre for Computational Neuroscience and Robotics (http://www.informatics.sussex.ac.uk/ccnr/) and the Complex Products Systems Group (http://www.cops.ac.uk/) at the University of Sussex. However, all four will work closely as part of an extended multi-site research team involving 10 investigators, 6 postdocs and 2 PhD students. PD1 (Ref 310233 - Leeds): Suitable for a talented, experienced researcher with a background in one or more of the following areas: adaptive behaviour, evolutionary computing, dynamical systems theory, simulation modelling. Excellent computational, mathematical and modelling skills are required. Ability to engage in profitable collaboration across different disciplines is essential. PD1 will work most closely with Seth Bullock and Ezequiel Di Paolo. PD2 (Ref 310234 - Leeds) & PD3 (Sussex): Suitable for talented researchers with experience in one or more of the following areas: computational neuroscience, dynamical systems modelling, evolutionary computing, time series analysis and spatial analysis Excellent computational, mathematical and modelling skills are required, some experience of neural modelling is desirable. (PD2) will work most closely with Netta Cohen and Seth Bullock; (PD3) with Ezequiel Di Paolo, Jianfeng Feng, Phil Husbands, and Mick O'Shea. PD4: Suitable for a talented researcher with experience in one or more of the following areas: adaptive systems engineering, machine learning, evolutionary computing, air-traffic control systems. Excellent computational, mathematical and modelling skills are required as well as the capability to engage in profitable collaboration with social scientists and open dialogue with industrial partners, familiarity with air-traffic control would be advantageous but not necessary. PD4 will work most closely with Ezequiel Di Paolo, Phil Husbands, and Paul Nightingale. These posts are part of an exciting multidisciplinary project spanning Leeds, Sussex and UCL, in which computer scientists, geographers, neuroscientists, policy researchers and engineers will study adaptive behaviour across a range of significant spatially-extended systems (neuroscience, geoscience, air-traffic control). The research teams will be led by Dr. Seth Bullock at the University of Leeds, Dr. Ezequiel Di Paolo at Sussex University and Prof. Mike Batty at University College London, but will work together closely for the duration of the project. See further particulars for more details. All highly motivated candidates with a PhD in computer science, biology, cognitive science, psychology, physics or other relevant disciplines are encouraged to apply. Informal enquiries (with CV attached) are welcome at the email addresses below: PD1: Seth Bullock, seth at comp.leeds.ac.uk PD2: Netta Cohen, netta at comp.leeds.ac.uk PD3 & PD4: Ezequiel Di Paolo, ezequiel at sussex.ac.uk Further particulars and job descriptions can be accessed from here: http//www.comp.leeds.ac.uk/seth/secse/secse.html To download application forms for the Leeds posts (PD1 and PD2) visit http://www.leeds.ac.uk and click on "jobs". Email (or post) completed application forms and a full CV to Judi Drew (judi at comp.leeds.ac.uk), School of Computing, University of Leeds, Leeds, LS2 9JT. To apply for the Sussex posts (PD3 and PD4) email a full CV and covering note to Ezequiel Di Paolo. The project is funded by EPSRC. Starting salaries approx. ? 22,000 depending on experience. Posts are available for three-and-a-half years. Starting date: 1 April 05, or soon after. There is no deadline but each position will be filled as soon as a suitable candidate is found. Applications received by 10 Feb, 2005 are guaranteed full consideration. Applications from UK, EU and non-EU residents are welcome. The University of Leeds and the university of Sussex are equal opportunity employers. ------ From triesch at ucsd.edu Tue Jan 11 18:36:07 2005 From: triesch at ucsd.edu (Jochen Triesch) Date: Tue, 11 Jan 2005 15:36:07 -0800 Subject: PostDoc and Graduate Student Positions at the Frankfurt Institute for Advanced Studies Message-ID: <41E462E7.3010907@ucsd.edu> 2 PhD and 1 Postdoc Position Available -------------------------------------- The newly founded Frankfurt Institute for Advanced Studies (FIAS) is looking for 1 Postdoc and 2 PhD students in the area of theoretical neuroscience (broadly construed). The positions are in the group of Jochen Triesch. The group's research areas include: Neural Computation, Vision (Computer, Robot, and Human Vision), Computational and Robotic Models of Cognitive Development. There will be ample opportunity to interact with other researchers at FIAS, the close-by Max Planck Institute for Brain Research, and the Johann Wolfgang Goethe University Frankfurt. The official language at the institute is English. The successful applicant for the PostDoc Position will join FIAS as a "junior fellow". The position is initially for one year, renewable for up to 3 years. Candidates should have a recent PhD in a quantitative discipline (physics, mathematics, computer science, electrical engineering or related fields) and a keen interest in several of the lab's research areas. A tax-free scholarship of 30,000 Euro per year (equivalent to about 50k US$ before tax) will be offered. Successful applicants for the Graduate Student Positions will join the three year PhD program at the new Frankfurt International Graduate School for Sciences (FIGSS). Candidates should have a Masters degree in a quantitative discipline (see above) and a keen interest in several of the lab's research areas. Students will receive a tax-free stipend of 12,000 Euro per year. Applicants should submit: - resume (including date of birth, grades, awards, publications), - statement of research interests (up to 2 pages), - names and email addresses of 3 references - links to their thesis and/or publications Positions will remain open until filled. Full consideration will be given to all applications arriving by February 15, 2005. Please send applications directly to my San Diego address: Jochen Triesch Dept. of Cognitive Science, UC San Diego 9500 Gilman Drive, La Jolla, CA 92093-0515, USA Applications can also be submitted by email to triesch at ucsd.edu. Make sure that all attached files use the following filename convention: Firstname.Lastname.DocDescription.DocType Do not send .doc or .rtf documents. Instead, use .pdf or plain text formats. Important Links: Details on the positions: http://cloudbreak.ucsd.edu/~triesch/positions.html Lab home page: http://csclab.ucsd.edu Frankfurt Institute for Advanced Studies (FIAS): http://www.fias.uni-frankfurt.de/ Frankfurt International Graduate School for Science (FIGSS): http://www.fias.uni-frankfurt.de/figss/ Max Planck Institute for Brain Research: http://www.mpih-frankfurt.mpg.de --------------------------------------------------------------------------- The Frankfurt Institute for Advanced Studies is a newly founded institution dedicated to basic theoretical research in various areas of science. The Institute will serve as a superstructure for basic research, bringing together theorists from the disciplines of biology, chemistry, neuroscience, physics, and computer science in a common organizational and intellectual framework. It is an ambitious independent scientific institution while at the same time bundling research activities at the University of Frankfurt and neighboring research centers. Scientists from FIAS and from Goethe University join forces to educate graduate students in the Frankfurt International Graduate School for Science. -- Jochen Triesch, triesch at ucsd.edu http://cloudbreak.ucsd.edu/~triesch Frankfurt Institute for Advanced Studies Johann Wolfgang Goethe University Robert Mayer Str. 10, 60054 Frankfurt am Main, Germany and Dept. of Cognitive Science, UC San Diego 9500 Gilman Drive, La Jolla, CA 92093-0515, USA Tel: +1 (858) 822-3317, Fax: +1 (858) 534-1128 From movellan at mplab.ucsd.edu Wed Jan 12 14:33:57 2005 From: movellan at mplab.ucsd.edu (Javier R. Movellan) Date: Wed, 12 Jan 2005 11:33:57 -0800 Subject: Kolmogorov Open Source Tutorials Message-ID: The latest version of the Open Source tutorials from the Kolmogorov project is available at http://mplab.ucsd.edu/tutorials/tutorials.html. It includes tutorials on the following topics: * Variational EM * Generalized Factor Analysis * Multinomial Logistic Regression * Stochastic Differential Equations * Gabor Filters * The Discrete Time Kalman Filtering and Controler * Hidden Markov Models * Exponential Smoothing * Principal Component Analysis * Sequential Sampling Methods * The Singular Value Decomposition * Image Formation Models * Introduction to Probability Theory and Statistics (Textbook) * Axiomatic Set Theory * Useful Mathematical Facts * Matrix Algebra Cookbook * Matrix Calculus Cookbook -Javier R. Movellan Machine Perception Laboratory UCSD From hitzler at aifb.uni-karlsruhe.de Thu Jan 13 08:16:30 2005 From: hitzler at aifb.uni-karlsruhe.de (Pascal Hitzler) Date: Thu, 13 Jan 2005 14:16:30 +0100 Subject: CfP: IJCAI-05 Workshop on Neural-symbolic learning and reasoning Message-ID: <41E674AE.5020702@aifb.uni-karlsruhe.de> Call for Papers Workshop on Neural-Symbolic Learning and Reasoning (NeSy'05) at IJCAI-05, Edinburgh, Scotland, July 31st, 2005 ------------------------------------------------------------ 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; * Integrated neural-symbolic learning approaches; * Extraction of symbolic knowledge from trained neural networks; * Integrated neural-symbolic reasoning; * Biological inspiration for neural-symbolic integration; * Applications in robotics, semantic web, engineering, bioinformatics, etc. 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 8 pages in the case of research and experience papers, and 4 pages in the case of position papers (including figures, bibliography and appendices). 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 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 in official workshop proceedings, which 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 a special issue of the Journal of Applied Logic, Elsevier, to be published early in 2006. Important Dates --------------- Deadline for submission: 4th of March, 2005 Notification of acceptance: 18th of April, 2005 Camera-ready paper due: 16th of May, 2005 Workshop day: TBA (between 30th of July and 1st of August, 2005) IJCAI 2005 main conference dates: 30th of July to 5th of August, 2005 Workshop Organisers ------------------- Artur d'Avila Garcez (City University London, UK) Jeff Elman (University of California, San Diego, USA) Pascal Hitzler (AIFB, University of Karlsruhe, Germany) Programme Committee ------------------- Artur d'Avila Garcez (City University London, UK) Howard Blair (Syracuse University, USA) Jeff Elman (University of California San Diego, USA) Dov Gabbay (Kings College London, UK) Marco Gori (University of Siena, Italy) Barbara Hammer (University of Osnabrck, Germany) Pascal Hitzler (University Karlsruhe, Germany) Steffen Hlldobler (TU Dresden, Germany) Luis Lamb (Federal University of Rio Grande do Sul, Brazil) John Lloyd (The Australian National University, Australia) Asim Roy (Arizona State University, USA) Antony K. Seda (University College Cork, Ireland) Jude Shavlik (University of Wisconsin, USA) Rudi Setiono (National University, Singapore) Alessandro Sperduti (University of Padova, Italy) Stefan Wermter (University of Sunderland, UK) Gerson Zaverucha (UFRJ, Brazil) Keynote speakers ---------------- Steffen Hlldobler (TU Dresden, Germany) Ron Sun (Rensselaer Polytechnic Institute, USA) Additional Information ---------------------- General questions concerning the workshop should be addressed to nesy at soi.city.ac.uk Workshop website: http://www.aifb.uni-karlsruhe.de/WBS/phi/NeSy05/ -- Dr. Pascal Hitzler Institute AIFB, University of Karlsruhe, 76128 Karlsruhe email: hitzler at aifb.uni-karlsruhe.de phone: +49 721 608 4751 web: www.aifb.uni-karlsruhe.de/WBS/phi fax: +49 721 608 6580 From jf218 at hermes.cam.ac.uk Thu Jan 13 12:56:11 2005 From: jf218 at hermes.cam.ac.uk (Dr J. Feng) Date: Thu, 13 Jan 2005 17:56:11 +0000 (GMT) Subject: Call for papers: Networks, from biology to theory Message-ID: International Conference on Networks: from Biology to Theory CALL FOR PAPERS During the past decades, we have witnessed the thriving development of new mathematical, computational and theoretical approaches such as bioinformatics and neuroinformatics to tackle some fundamental issues in biology. These scientific approaches focus no longer on the individual units, like nerve cells or genes, but rather on the emerging dynamic patterns of interactions between them. This depends on the interplay between the local dynamics and activity transmissions on one side and the global structure of the underlying connection scheme on the other hand. From these questions, the concept of a network emerges as a powerful and stimulating research paradigm in mathematics, physics and computer science, with a very lively interaction between experimental findings, simulation studies, and theoretical investigations that then in turn lead to new experimental questions. In particular, since researchers in molecular cell biology and neurobiology share an interest in network theory and, conversely, can stimulate further theoretical research on networks, we want to promote this development, and bring together expertises from both experimentalists and theoreticians working on networks at a meeting in Beijing (Sino-German Centre). Such a meeting will provide an inclusive forum for the exchange of ideas for scientists from China, Germany and elsewhere. The meeting is expected to draw about 100 researches (around 30 invited) from the whole range of disciplines mentioned above, molecular cell biology, neurobiology, systems biology, mathematics, physics, computing science. The meeting topics include but are not limited to Networks in neuroinformatics: Population coding, computation with spiking networks, multi-unit recording, human-machine interfaces, synchronization in spiking neuronal networks. Networks in bioinformatics: Gene regulatory and signal transduction networks, protein-protein interaction networks, microarray data, metabolic networks. Network structures and dynamics: Random graphs and other paradigms, synchronization and desynchronization mechanisms, coupled oscillators, dynamics on multiple scales. FORMAT The single-track meeting will consist of both oral and poster sessions. Some oral presentations will be invited, while others will be drawn from short submitted abstracts. Poster presentations will be drawn from submitted abstracts. We expect we are able to provide meals, and ample time will be provided for informal discussion outside of the sessions. To actually provide an inclusive forum for the exchange of ideas between experimentalists and theoreticians, the structure of the conference will be: 2 days networks in molecular biology, 1 day formal methods, 2 days networks in neurobiology. Thus, the theoretical day in the middle will link the two different fields of applications ORGANIZING COMMITTEE Jianfeng Feng (Warwick Univ., UK, and Hunan Normal Univ., PR China), Juergen Jost (Max Planck Institute for Mathematics in the Sciences, Leipzig, Germany), Minping Qian (Peking University, PR China) SPEAKERS Around 30 speakers will be invited (half theoreticians and half experimentalists). And the rest wil be selected from submitted abstracts. LOCATION Sino-German Centre, Beijing. WHEN April 4th--8th , 2005. REGISTRATION INFORMATION: Registration is free. CONFERENCE GRANTS: SinoGerman Centre ABSTRACTS Abstracts are due by Feb. 15, 2005. Decisions will be made by Feb. 31, 2005. Abstracts should be 1-2 pages. OTHER INFORMATION http://www.informatics.sussex.ac.uk/users/jianfeng/sino-german/sino-german.html ------------------------------------------------------------------------------ Address after 1st Jan. 2005 Prof. Jianfeng Feng Centre for Scientific Computing Warwick University Coventry CV4 7AL UK http://www.cus.cam.ac.uk/~jf218 From cns at www.cnsorg.org Fri Jan 14 21:23:01 2005 From: cns at www.cnsorg.org (CNS) Date: Fri, 14 Jan 2005 19:23:01 -0700 Subject: Submission for CNS 2005 open! Message-ID: <20050115022131.M84413@www.cnsorg.org> SUBMISSIONS FOR CNS 2005 now open! __________________________________ CALL FOR PAPERS, CNS*2005: SUBMISSION DEADLINE: February 1, 2005 midnight Submissions open: January 15th, 2005 to submit a paper, go to www.cns2005.confmaster.net where you can either register as a new author or log in as a registered user and then follow the submission instructions. Submissions to the meeting will take the form of a 3-page summary describing the nature and scope of the work, and outlining the main results (must be submitted as a PDF file). These summaries will be reviewed by the program committee and used to determine acceptance for presentation at the meeting as well as to construct the scientific program. Authors will also be asked to submit a standard abstract for printing in the program book (200 words). All submissions will be acknowledged by email. Authors will be asked to state their preference as to the type of presentation they would like to give (oral, featured talk or poster presentation). Please note that only a small percentage of submissions can be included in the oral program every year (see details below). Only 2-4 papers are chosen for featured talks each year. Authors which indicate a preference for a featured talk MUST include a short, single paragraph explanation (at the beginning of their extended summary) as to why their contribution is particularly suited for a featured talk. -- CNS - Organization for Computational Neurosciences From skremer at kremer.ca Mon Jan 17 00:14:18 2005 From: skremer at kremer.ca (Stefan C. Kremer) Date: Mon, 17 Jan 2005 00:14:18 -0500 Subject: CALL FOR CONTRIBUTIONS: Correlation Learning Workshop Message-ID: << Apologies for multiple copies of this message >> ********************************************************************* FIRST CALL FOR CONTRIBUTIONS Correlation Learning Workshop The Eighteenth Canadian Conference on Artificial Intelligence University of Victoria, Victoria, British Columbia May 8th, 2005 Workshop Website: http://www.kremer.ca/CorrelationLearning A.I. '05 Website: http://www.iro.umontreal.ca/~ai05 The Correlation Learning Workshop invites participants to present original work in in Correlation Learning, defined as follows. Correlative learning is a paradigm for adaptive behaviour which uses correlations between neuronal activations, oscillations and/or changes in system energy to effect synaptic plasticity. Correlative learning has a long history in biological models of neoronal computation, and has recently garnered an increased amount of interest in the field of machine learning. The AI'05 Correlation Workshop is the opportunity for you to share, discuss and further develop ideas and techniques in correlative learning. It will bring together research from the biological community that focusses on explaining biological learning and combine it with correlative learning approaches from the machine learning community that focus on effectiveness for pattern recognition problems. Prospective participants are invited to submit a 2-page summary of a proposed 30 minute presentation by February 18th. Accepted speakers will be invited to give their presentation, participate in the workshop discussions and contribute an article for consideration in a special issue of the new, on-line (open access) journal: Canadian Journal of Natural Computation (ISSN 1703-7115). Proposals will be reviewed by the workshop organizers and judged according to their originality, technical merit and clarity of presentation. Proposal Submission: Authors are invited to submit proposals in plain text, PDF, Postscript, or MS-Word RTF via e-mail to skremer at uoguelph.ca. All e-mails must have a subject header of "AI2005 Workshop Submission" to be considered. Important Dates: Proposal submission due: February 18th, 2005 Notification of acceptance: February 28th, 2005 Workshop Date: May 8th,2005 Proposed CJNC Special Issue Publication Date: Fall, 2005 -- Dr. Stefan C. Kremer, Associate Prof., Reynolds Building, 106, Dept. of Computing & Info. Science University of Guelph, Guelph, Ontario N1G 2W1 Tel: (519)824-4120 Ext.58913 E-mail: skremer at uoguelph.ca Fax: (519)837-0323 WWW: http://q.cis.uoguelph.ca/~skremer From auke.ijspeert at epfl.ch Sun Jan 16 07:56:34 2005 From: auke.ijspeert at epfl.ch (Auke Ijspeert) Date: Sun, 16 Jan 2005 13:56:34 +0100 Subject: CFP: AMAM2005 Adaptive Motion in Animals and Machines Message-ID: <41EA6482.6080601@epfl.ch> Dear Connectionists, Researchers working on any aspect related to the adaptive control of movement and locomotion in animals and robots, might be interested in AMAM2005, the Third International Symposium on Adaptive Motion in Animals and Machines (see the CFP below). The two previous symposia in Montreal and Kyoto, which brought together researchers in neurobiology, biomechanics, neural computation, and robotics, were very exciting and fruitful events Best regards, Auke Ijspeert ****************Announcement and First Call for Papers**************** 3rd International Symposium on Adaptive Motion in Animals and Machines AMAM 2005 will take place at Technische Universit=E4t Ilmenau, Germany, September 25th - September 30th, 2005. Deadline for abstract submission: February 28^th , 2005. Please find details and the first Call for Papers at: http://www.tu-ilmenau.de/amam On behalf of the International Organizing Committee under the guidance of Prof. Kazuo Tsuchiya (Kyoto, Japan), it is our pleasure to cordially invite you to take part in this symposium. It is our dream to understand principles of animals' surprising abilities in adaptive motion and to transfer such abilities on a robot. However, principles of adaptation to various environments have not yet been clarified, and autonomous adaptation is left unsolved as a seriously difficult problem in robotics. Apparently, the adaptation ability shown by animals and needed by robots in a real world can not be explained or realized by one single function in the control system. That is, adaptation is induced at multiple levels in a wide spectrum from the central neural system to the musculo-skeletal system. We are organizing AMAM 2005 for scientists and engineers concerned with adaptation on various levels to be brought in contact, to discuss principles on each level and to investigate principles governing total systems. Some topics of particular interest to guide prospective contributors are: * Visual Adaptation Mechanisms of Systems in Locomotion * Sensory-Motor Coordination in Locomotion * Neuro-Mechanics * Locomotion of Animals * Behaviour (Locomotion and Idiomotion) of Mammals, esp. Primates, esp. Humans and Humanoids * Embodied Intelligence in Locomotion * Non-linear Dynamics in Locomotion * Adaptive Mechanics * Modeling and Analysis of Motion * Prostheses, Ortheses and Rehabilitation * Evolution of Adaptive Motion (Phylogenesis) * Ontogenesis of Adaptive Motion (from Learning to De-learning, Development and Ageing) * Technical Development of Mechanism and Control for Adaptive Motion Prof. H. Kimura, Tokyo (Japan) Prof. A.J. Ijspeert, Lausanne (Switzerland) Prof. Hartmut Witte, Ilmenau (Germany) ************************************************************************* From nello at wald.ucdavis.edu Sun Jan 16 14:52:23 2005 From: nello at wald.ucdavis.edu (Nello Cristianini) Date: Sun, 16 Jan 2005 11:52:23 -0800 (PST) Subject: School / The Analysis of Patterns / oct-nov 2005 Message-ID: <20050116114744.C47402-100000@anson.ucdavis.edu> International School "Eduardo R. Caianiello" and Workshop of the PASCAL Network of Excellence The Analysis of Patterns Centre "Ettore Majorana" for Scientific Culture, Erice, Italy October 28 - November 6, 2005 (Course days: Saturday, October 29 - Saturday, November 5th) http://www.analysis-of-patterns.net/ Automatic pattern analysis of data is a pillar of modern science, technology and business, with deep roots in statistics, machine learning, pattern recognition, theoretical computer science, and many other fields. A unified conceptual understanding of this strategic field is of great importance for researchers as well as for users of this technology. This workshop / course will emphasize the common principles and roots of modern pattern analysis technology, developed independently by many different scientific communities over the past 30 years, and their impact on modern science and technology. Students and researchers from many disciplines dealing with automatic pattern analysis form the intended audience. These include (but are not limited to) statistics, pattern recognition, data mining, machine learning, information theory, sequence analysis, bioinformatics, adaptive systems, etc The school will cover both the conceptual foundations of pattern theory as well as the technological aspects related to pattern-driven data analysis. Directors of the Course: Nello Cristianini, University of California, Davis, USA Raffaele Cerulli, Universita' di Salerno, Italy John Shawe-Taylor, University of Southampton, UK Director of the School "Eduardo Caianiello": Maria Marinaro, Universita' di Salerno, Italy From workshops at www.cnsorg.org Mon Jan 17 06:30:49 2005 From: workshops at www.cnsorg.org (Boris Gutkin) Date: Mon, 17 Jan 2005 03:30:49 -0800 Subject: CNS*05 WORKSHOPS CALL FOR PROPOSALS Message-ID: <20050117113056.M30381@www.cnsorg.org> CALL FOR PROPOSALS: CNS*2005 Workshops/Symposia 20-21 July 2005 University of Wisconsin, Madison, USA. The final two days of the CNS*2005 meeting will be devoted to workshops focusing on current issues in computational neuroscience. This year we are also considering integrating outstanding workshop proposals of general interest into the main oral program as 2 hour symposia. Workshops may take the form of 1 or 2 day mini-symposia and tutorials, in addition to the traditional informal discussions. These more formal workshops will provide an excellent opportunity for short, focused meetings on topics of particular current interest. Individual organizers are largely free to define the format and content of their workshops, provided that adequate time is reserved for discussion. The organizers of a workshop should endeavor to bring together as broad a range of pertinent viewpoints as possible. Those interested in organizing a mini-symposium or tutorial are encouraged to contact the workshops organizer, Boris Gutkin at workshops at cnsorg.org as soon as possible. Detailed instructions for submitting a workshop proposal can be found at: www.cnsorg.org Descriptions of new workshops will be added as they are accepted. Information on the CNS*2005 meeting can be obtained from the CNS Website: www.cnsorg.org From bogus@does.not.exist.com Mon Jan 17 12:51:46 2005 From: bogus@does.not.exist.com () Date: Mon, 17 Jan 2005 17:51:46 -0000 Subject: Internships for PhD students at Microsoft Research Cambridge Message-ID: From arobert at med.cornell.edu Thu Jan 20 18:04:14 2005 From: arobert at med.cornell.edu (Adrian Robert) Date: Thu, 20 Jan 2005 18:04:14 -0500 Subject: Postdoctoral position Message-ID: <9A9E4CA8-6B37-11D9-97B1-000D93B19E46@med.cornell.edu> Neuroinformatics Research Associate The Laboratory of Neuroinformatics at Cornell University's Weill Medical College in New York City seeks researchers at the post-doc level or above to join a team developing an integrated suite of analytic algorithms, parallel computational resources, databases, tools, and standards for data and algorithm description and exchange. Successful candidates will have a background in computational neuroscience or bioinformatics, and combine the ability to work in a team setting with creativity and initiative. They should have experience with one or more of: database design, Java web applications, and XML. We provide generous salary and benefits, the excitement of life in New York, and the opportunity to work with a dedicated group of neuroinformatic developers and neurophysiologists, including Daniel Gardner, Jonathan D. Victor, and distinguished collaborators in neural data acquisition, analysis, and algorithm development. See http://neurodatabase.org and http://brainml.org for further information. If interestest, please email CV, cover letter, and the names of three references to: dan at med.cornell.edu. ------------------------- Adrian Robert, Ph.D. Weill Medical College of Cornell University 1300 York Avenue D-404 Physiology and Biophysics New York, NY 10021 (212) 746-0462 From oza at email.arc.nasa.gov Thu Jan 20 18:42:05 2005 From: oza at email.arc.nasa.gov (Nikunj C. Oza) Date: Thu, 20 Jan 2005 15:42:05 -0800 Subject: CFP: Multiple Classifier Systems workshop Message-ID: **Apologies for multiple copies** NOTE: PAPER DEADLINE EXTENDED BY ONE WEEK TO JANUARY 28, 2005. ****************************************** *****MCS 2005 Call for Papers***** ****************************************** *****Paper Submission: 28th JANUARY 2005***** ********************************************************************** SIXTH INTERNATIONAL WORKSHOP ON MULTIPLE CLASSIFIER SYSTEMS Embassy Suites on Monterey Bay, Seaside, California, USA, June 13-15, 2005 Updated information: http://www.diee.unica.it/mcs E-mail: oza at email.arc.nasa.gov (Nikunj Oza) or polikar at rowan.edu (Robi Polikar) ********************************************************************* WORKSHOP OBJECTIVES MCS 2005 is the sixth workshop of a series aimed at creating a common international forum for researchers of the diverse communities working in the field of multiple classifier systems. Information on the previous editions of MCS workshop can be found on http://www.diee.unica.it/mcs. Contributions from all the research communities working in the field are welcome in order to compare the different approaches and to define the common research priorities. Special attention is also devoted to assess the applications of multiple classifier systems. The papers will be published in the workshop proceedings, and extended versions of selected papers will be considered for publication in a special issue of an international journal. WORKSHOP CHAIRS Nikunj C. Oza (NASA Ames Research Center, USA) Robi Polikar (Rowan University, USA) Josef Kittler (Univ. of Surrey, United Kingdom) Fabio Roli (Univ. of Cagliari, Italy) ORGANIZED BY NASA Ames Research Center Department of Electrical and Computer Engineering, Rowan University Puresense Environmental Sponsored by IAPR TC1 Statistical Pattern Recognition Techniques PAPER SUBMISSION Participants should submit an electronic version of the manuscript (PostScript or PDF format) to polikar at rowan.edu. The papers should not exceed 10 pages (LNCS format, see http://www.springer.de/comp/lncs/authors.html). A cover sheet with the authors names and affiliations is also requested, with the complete address of the corresponding author, and an abstract (200 words). Two members of the Scientific Committee will referee the papers. IMPORTANT NOTICE: Submission implies the willingness of at least one author to register, attend the workshop, and present the paper. Accepted papers will be published in the proceedings only if the registration form and payment for one of the authors is received. WORKSHOP TOPICS Papers describing original work in the following and related research topics are welcome: Foundations of multiple classifier systems Methods for classifier fusion Design of multiple classifier systems Neural network ensembles Bagging and boosting Mixtures of experts New and related approaches Applications INVITED SPEAKERS Leo Breiman (USA) Second speaker to be determined (see http://www.diee.unica.it/mcs for updates) SCIENTIFIC COMMITTEE J. A. Benediktsson (Iceland) H. Bunke (Switzerland) L. P. Cordella (Italy) B. V. Dasarathy (USA) R. P.W. Duin (The Netherlands) C. Furlanello (Italy) J. Ghosh (USA) V. Govindaraju (USA) T. K. Ho (USA) S. Impedovo (Italy) N. Intrator (Israel) A.K. Jain (USA) M. Kamel (Canada) L.I. Kuncheva (UK) D. Partridge (UK) A.J.C. Sharkey (UK) C.Y. Suen (Canada) K. Tumer (USA) G. Vernazza (Italy) T. Windeatt (UK) IMPORTANT DATES January 28, 2004: Paper Submission February 25, 2004: Notification of Acceptance March 25, 2004: Camera-ready Manuscript March 25, 2004: Registration WORKSHOP VENUE The workshop will be held at the Embassy Suites on Monterey Bay, Seaside, California, USA (http://www.embassymonterey.com). WORKSHOP PROCEEDINGS Accepted papers will appear in the workshop proceedings that will be published in the series Lecture Notes in Computer Science by Springer-Verlag. Extended versions of selected papers will considered for possible publication in a special issue of an international journal. -- -------------------------------------- Nikunj C. Oza, Ph.D. Tel: (650)604-2978 Research Scientist Fax: (650)604-4036 NASA Ames Research Center e-mail: oza at email.arc.nasa.gov Mail Stop 269-3 web: http://ic.arc.nasa.gov/~oza Moffett Field, CA 94035-1000 From F.AlmeidaCosta at sussex.ac.uk Tue Jan 11 15:28:21 2005 From: F.AlmeidaCosta at sussex.ac.uk (Fernando Almeida e Costa) Date: Tue, 11 Jan 2005 20:28:21 -0000 Subject: Workshop @ Ecal 2005 - Call for papers Message-ID: ********************************************************************* ..........................Call for papers........................... .....................Workshop @ ECAL 2005....................... ......Active Agents and Their Environments as Dynamical Systems..... ................www.ecal2005.org/workshops.html..................... ...........Organized by the activate.d reading group................ .....................University of Sussex........................... ********************************************************************* ECAL2005, in September, will host a workshop on "Active agents and their environments as dynamical systems" organised by the activate.d reading group from the University of Sussex. We are seeking papers within the broad range of the so called dynamical systems approach to life and cognition, from both technical and conceptual/philosophical perspectives. Papers from the workshop will be published in a special issue of the Journal of Adaptive Behavior. You may find detailed information about the workshop in our webpage at www.informatics.sussex.ac.uk/users/eji21/activate.d/workshop at ecal2005 or through the workshop webpage at www.ecal2005.org/workshops.html ******************** PROGRAMME COMMITTEE ******************** Randall Beer, Case Western University. Peter Cariani, Tufts Medical School. Edwin de Jong, Universiteit Utrecht. Ezequiel Di Paolo, University of Sussex. Dario Floreano, Ecole Polytechnique Federale de Lausanne. Inman Harvey, University of Sussex. Phil Husbands, University of Sussex. Takashi Ikegami, University of Tokyo. Scott Kelso, Florida Atlantic University. Luis Mateus Rocha, Indiana University. Tom Ziemke, University of Skovde. ***************** IMPORTANT DATES ***************** Submission deadline: 20th of May Review results: 15th of June Corrected papers due: 22nd of June Papers must be emailed in pdf format to one of the organisers (see addresses below) and will be reviewed by at least two independent reviewers, in compliance with the host conference rules. The work to be submitted may include (but is not limited to) topics such as: * Embodied cognition (the exploitation by a cognitive agent, qua cognitive, of all its physical properties). * Evolution of intrinsic and extrinsic morphologies in artificial agents. * Robotics within the framework of the DSaLC (Dynamical Systems approach to Life and Cognition). * Cognition as brain/body/environment interaction. * Online learning as dynamics occurring at different time scales. * Synthesis of dynamical systems models which exhibit adaptive behaviour. * Self-organisation, selection and neutrality in the evolution of dynamical systems. * Agency, homeostasis and autopoiesis. * The present dangers of the (conscious and unconscious) use of GOFAI principles within a DSaLC framework. * Dynamical systems tools for understanding adaptive behaviour. * Behavioural dynamics of interest to cognitive science (e.g. chaotic itinerancy, globally coupled chaotic systems). * Dynamical systems architectures (i.e. neural networks, cellular automata, other models) and their behavioural dynamics. * Models of dynamical systems coupling. Papers should be sent to either one of the workshop organisers: Fernando Almeida e Costa Eduardo Izquierdo-Torres F.AlmeidaCosta at sussex.ac.uk E.J.Izquierdo-Torres at sussex.ac.uk You may find more information about the activate.d reading group at www.informatics.sussex.ac.uk/users/eji21/activate.d -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: callpapers1.txt Url: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/00000000/c5dfa516/callpapers1.txt From terry at salk.edu Fri Jan 21 17:41:47 2005 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 21 Jan 2005 14:41:47 -0800 (PST) Subject: NEURAL COMPUTATION 17:1 In-Reply-To: <200411160058.iAG0woq64269@kepler.snl.salk.edu> Message-ID: <200501212241.j0LMfl461361@kepler.snl.salk.edu> Neural Computation - Contents - Volume 17, Number 1 - January 1, 2005 NOTES How To Pretend That Correlated Variables Are Independent by Using Difference Observations Christopher K. I. Williams Convergence of the IRWLS Procedure to the Support Vector Machine Solution Fernando Perez-Cruz, Carlos Bousono-Calzon, Chih-Jen Lin, and Antonio Artes-Rodriguez LETTERS Efficient Coding of Time-Relative Structure Using Spikes Evan Smith and Michael. S. Lewicki Bilinear Sparse Coding for Invariant Vision David B. Grimes and Rajesh P. N. Rao A Probabilistic Framework for Region-Specific Remodeling of Dendrites in Three-Dimensional Neuronal Reconstructions Rishikesh Narayanan, Anusha Narayan and Sumantra Chattarji Analysis of Cyclic Dynamics for Networks of Linear Threshold Neurons H. J. Tang, K. C. Tan, and Weinian Zhang Nonlinear and Noisy Extension of Independent Component Analysis: Theory and Its Application to a Pitch Sensation Model Shin-ichi Maeda, Wen-Jie Song and Shin Ishii Online Ranking by Projecting Koby Crammer and Yoram Singer On Learning Vector-Valued Functions Charles A. Micchelli and Massimiliano Pontil RSPOP : Rough Set-Based Pseudo Outer-Product Fuzzy Rule Identification Algorithm Kai Keng Ang and Chai Quek ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2005 - VOLUME 17 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $143 $90 $96.30 Institution $680 $727.60 $734 $612 $654.84 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From dekamps at t-online.de Sat Jan 22 16:41:51 2005 From: dekamps at t-online.de (Marc de Kamps) Date: Sat, 22 Jan 2005 22:41:51 +0100 Subject: CFP: ICANN2005 Message-ID: International Conference on Artificial Neural Networks 11-15 September 2005 Warsaw, Poland ICANN 2005 Preliminary Call for Papers The 15th International Conference on Artificial Neural Networks, ICANN 2005, will be held from September 11 to September 14, 2005, at the Gromada Hotel Conference Center, near the airport in Warsaw, Poland. ICANN is an annual meeting organized by the European Neural Network Society in cooperation with the International Neural Network Society, Japanese Neural Network Society, and the IEEE Computational Intelligence Society, and is a premier European event in all topics related to the neural networks. ICANN 2005 welcomes contributions on the theory, algorithms, applications and implementations in the following broad areas: * Computational neuroscience; * Connectionist cognitive science; * Data analysis and pattern recognition; * Graphical networks models, Bayesian networks; * Hardware implementations and embedded systems; * Neural and hybrid architectures and learning algorithms; * Neural control, reinforcement learning and robotics applications; * Neuroinformatics; * Neural dynamics and complex systems; * Real world applications; * Robotics, control, planning; * Signal and time series processing; * Self-organization; * Vision and image processing. Professor Teuvo Kohonen is Honorary Chairman of ICANN 2005. We are pleased to announce the following plenary speakers, whose talks will cover various topics in neuroscience, neural theory and applications: * Christopher Bishop (Microsoft, Cambridge, UK) * Hojjat Adeli (Columbus, OH, USA) * John Taylor (King's College London, UK) * John Shawe-Taylor (Southampton, UK) * Juergen Schmidhuber (Lugano, Switzerland) * Misha Tsodyks (Weizmann Institute, Israel) * Rolf Ktter (Dsseldorf, Germany) * Stephen H. Koslow (NIH, USA) Ideas and nominations for interesting tutorials, special sessions, workshops and experts willing to organize various session tracks are called for. Most active experts will be included in the scientific committee of the conference. Each special session should have at least 5 presentations and a conference track about twice as many. Special session chairs will be responsible for all aspects of their sessions, including soliciting, reviewing, and selecting the papers. To ensure quality of the papers the program committee of ICANN 2005 will provide final review and approval for all sessions. Proposals to organize special sessions/tracks/workshops should include: the title and form of the proposed session (track/special session/workshop); name, affiliation, mailing address and e-mail address of the proposer(s); description of the topic of the session, not exceeding 100 words, or 1000 words for tutorials. Proceedings of ICANN will be published in Springer's "Lecture Notes in Computer Science". Paper length is restricted to a maximum of 6 pages, including figures. Instructions for authors are given here . The deadlines and conference dates are: 6.01 Submission page opens 28.02 End of submission of papers to regular sessions 30.03 End of submission of papers to special sessions 30.04 Acceptance/rejection notification 15.06 Deadline for camera ready papers 1.07 Deadline for early registration 11.09 Tutorials - first day of the conference 12-14.09 The main part of the conference 15.09 Workshops For further information and/or contacts, send inquiries to icann-2005 at ibspan.waw.pl or to the ICANN 2005 Conference Secretariat Mrs. Krystyna Warzywoda Systems Research Institute, Polish Academy of Sciences ul. Newelska 6, 01-447 Warszawa, Poland WWW page: www.ibspan.waw.pl/ICANN-2005 General Program Chairs: Wlodzislaw Duch, Nicholaus Copernicus University, Torun, Poland, and Nanyang Technological University, Singapore Janusz Kacprzyk, System Research Institute, Polish Academy of Sciences, Warsaw, Poland From mtoussai at inf.ed.ac.uk Sun Jan 23 12:15:07 2005 From: mtoussai at inf.ed.ac.uk (Marc Toussaint) Date: Sun, 23 Jan 2005 17:15:07 -0000 Subject: CFP: Theory of Representations Workshop @ GECCO 2005 Message-ID: Call for Papers Workshop on "THEORY OF REPRESENTATIONS" to be held as part of the 2005 Genetic and Evolutionary Computation Conference (GECCO-2005) Washington, D.C., June 25 - 29, 2005 http://homepages.inf.ed.ac.uk/mtoussai/gecco05/index.html organized by: Marc Toussaint, University of Edinburgh, UK (mtoussai at inf.ed.ac.uk) Alden H. Wright, University of Montana, USA (alden.wright at umontana.edu) Edwin D. de Jong, Utrecht University (dejong at cs.uu.nl) The choice of representation crucially determines the performance of a heuristic search process. We believe that there have been very interesting new ideas and approaches on the subject of learning representations recently. However, a unifying point of view is currently missing and the different approaches are widely scattered in the literature with too little cross-fertilization. In this workshop we would like to gather such work and, in a discussion between the contributors from the various lines of research, fuse the various approaches and formalisms into a common framework. This framework might clarify what the scope of a theory of representations should be, what existing algorithms may be considered as cases of representation adaptation, and how the existing literature on the topic can be integrated in a broader picture -- thereby also seeking contact with related areas in Computer Science, Machine Learning and Theoretical Biology. TYPE OF CONTRIBUTIONS: We invite paper submissions on all aspects related to representations. This includes -- Reviews or general discussions of own work, work from a certain line of research, or historical work (e.g. done in theoretical biology) with the aim to contribute to a more integrative picture of what a Theory of Representations should encompass. -- Original, also preliminary, theoretical ideas or experimental studies and propositions of new heuristics when they support or point towards theoretically grounded principles. TOPICS and SUBMISSION INSTRUCTIONS: For details, please see http://homepages.inf.ed.ac.uk/mtoussai/gecco05/index.html IMPORTANT DATES: Electronic Submission Deadline March 14, 2005 Author Notifications Sent April 8, 2005 Camera-Ready Copy Deadline April 22, 2005 Workshop June 25, 2005, 14:00PM-18:00PM From retienne at jhu.edu Wed Jan 26 11:37:08 2005 From: retienne at jhu.edu (retienne) Date: Wed, 26 Jan 2005 11:37:08 -0500 Subject: Announcement: Neuromorphic Engineering Workshop 200 Message-ID: Neuromorphic Engineering Workshop call for applications Sunday, JUNE 26 - Saturday, JULY 16, 2005 TELLURIDE, COLORADO ------------------------------------------------------------------------ Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Ralph ETIENNE-CUMMINGS (Johns Hopkins University) Paul HASLER (Georgia Institute of Technology) Timmer HORIUCHI (University of Maryland) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Christof KOCH (California Institute of Technology) Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) Andre van SCHAIK (University of Sydney) ------------------------------------------------------------------------ We invite applications for a three week summer workshop that will be held in Telluride, Colorado from Sunday, June 26 to Saturday, July 16, 2005. The application deadline is Friday, March 25 and application instructions are described at the bottom of this document. We must have your completed application, including letters of recommendation, by March 25 for your application to be considered. Last year's 2004 Workshop and Summer School on Neuromorphic Engineering, sponsored by the National Science Foundation, the Institute of Neuromorphic Engineering, the Office of Naval Research, Airforce Research Office, Institute for NeuroInfomatics - ETHZ, Geogia Institute of Technology, University of Maryland - College Park, Johns Hopkins University, The Salk Institute, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology, was an exciting event and a great success. We strongly encourage interested parties to browse through the: http://www.ini.unizh.ch/telluride/ GOALS: Carver Mead introduced the term "Neuromorphic Engineering" for a new field based on the design and fabrication of artificial neural systems, such as vision systems, head-eye systems, and roving robots, whose architecture and design principles are based on those of biological nervous systems. The goal of this workshop is to bring together young investigators and more established researchers from academia with their counterparts in industry and national laboratories, working on both neurobiological as well as engineering aspects of sensory systems and sensory-motor integration. The focus of the workshop will be on active participation, with demonstration systems and hands on experience for all participants. Neuromorphic engineering has a wide range of applications from nonlinear adaptive control of complex systems to the design of smart sensors. Many of the fundamental principles in this field, such as the use of learning methods and the design of parallel hardware (with an emphasis on analog and asynchronous digital VLSI), are inspired by biological systems. However, existing applications are modest and the challenge of scaling up from small artificial neural networks and designing completely autonomous systems at the levels achieved by biological systems lies ahead. The assumption underlying this three week workshop is that the next generation of neuromorphic systems would benefit from closer attention to the principles found through experimental and theoretical studies of real biological nervous systems as whole systems. FORMAT: The three week summer workshop will include background lectures on systems neuroscience (in particular learning, oculo-motor and other motor systems and attention), practical tutorials on analog VLSI design, small mobile robots (Koalas, Kheperas, LEGO robots), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, the majority of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control * central pattern generator * robotics * multichip communication * analog VLSI * learning * neuroprosthethic decives and systems The active perception project group will emphasize vision and human sensory-motor coordination. Issues to be covered will include spatial localization and constancy, attention, motor planning, eye movements, and the use of visual motion information for motor control. The central pattern generator group will focus on small walking and undulating robots. It will look at characteristics and sources of parts for building robots, play with working examples of legged and segmented robots, and discuss CPG's and theories of nonlinear oscillators for locomotion. It will also explore the use of simple analog VLSI sensors for autonomous robots. The robotics group will use rovers and working digital vision boards as well as other possible sensors to investigate issues of sensorimotor integration, navigation and learning. The audition group aims to develop biologically plausible algorithms and aVLSI implementations of specific auditory tasks such as source localization and tracking, and sound pattern recognition. Projects will be integrated with visual and motor tasks in the context of a robot platform. The multichip communication project group will use existing interchip communication interfaces to program small networks of artificial neurons to exhibit particular behaviors such as amplification, oscillation, and associative memory. Issues in multichip communicationwill be discussed. This year we will also have some new robots kindly donated by the WowWee Toys division of Hasbro in Hong Kong. This will permit us to carry out experiments with WooWee/Hasboro hardware through Mark Tilden. LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350miles). Great Lakes Aviation and America West Express airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do not rent a car. Bring hiking boots, warm clothes, rain gear, and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around mid April 2005. Participants are expected to pay a $295.00 workshop fee at that time in order to reserve a place in the workshop. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. Travel reimbursement of up to $500 for US domestic travel and up to $800 for overseas travel will be possible if financial help is needed (please specify on the application). HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e.postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage qualified women and minority candidates to apply. Application should include: * Cover sheet with: o First name, Last name o Institution and department o Complete mailing address o Valid e-mail address * Curriculum Vitae * One-page summary of background and interests relevant to workshop * Two letters of recommendation Please send your application to: Terrence Sejnowski The Salk Institute -- CNL 10010 N. Torrey Pines Road La Jolla, California 92037 Electronic applications will not be accepted. Questions regarding the application process may be addressed to: telluride at salk.edu -- ---------------------------------------------------------------------------------------- Ralph Etienne-Cummings Associate Professor Department of Electrical and Computer Engineering 105 Barton Hall/3400 N. Charles St. 2213 AV Williams Bldg Johns Hopkins University University of Maryland Baltimore, MD 21218 College Park, MD 20742 Tel: 410 - 516 - 3494 Tel: 301 - 405 - 0470 Fax: 410 - 516 - 5566 Fax: 301 - 314 - 9281 Email: retienne at jhu.edu Email: retienne at isr.umd.edu URL: http://bach.ece.jhu.edu/~etienne URL: http://www.isr.umd.edu/~retienne From S.M.Bohte at cwi.nl Thu Jan 27 11:51:03 2005 From: S.M.Bohte at cwi.nl (Sander Bohte) Date: Thu, 27 Jan 2005 17:51:03 +0100 Subject: CFP: Learning and Adaption in Multi-Agent Systems (LAMAS) @ AAMAS 2005 Message-ID: <41F91BF7.1040302@cwi.nl> **Apologies for multiple copies** ____________________________________________________________ -- CALL FOR PAPERS -- -- Workshop on Learning and Adaptation in Multi-Agent Systems 2005 (LAMAS) -- -- To be held at AAMAS 2005, Utrecht University, the Netherlands -- -- http://lamas2005.luc.ac.be -- ____________________________________________________________ Dear Connectionists, you are invited to submit papers to the 1st Workshop on Learning and Adaption in MAS (LAMAS 2005). LAMAS 2005 will be organized within the fourth International Conference on Autonomous Agents and Multi Agent Systems in Utrecht, the Netherlands. Prospective participants must also register for the AAMAS 2005 conference. The number of participants is strictly limited. The goal of this workshop is to increase awareness and interest in adaptive agent research, encourage collaboration between ML experts and agent system experts, and give a representative overview of current research in the area of adaptive agents. Machine Learning techniques for single agent frameworks are well established. Agents operate in uncertain environments and must be able to learn and act autonomously. This task is however more complex when the agent interacts with other agents with potentially different capabilities and goals. The single agent case is structurally different from the multi agent case due to the added dimension of dynamic interactions between the adaptive agents. Multi-Agent Learning, i.e., the ability of the agents to learn how to co-operate and compete, becomes crucial in many domains. Adaptive Agents and Multi-Agent Systems (AAMAS) is an emerging multi-disciplinary area encompassing Computer Science, Software Engineering, Biology, as well as Cognitive and Social Sciences. A theoretical framework, in which rationality of learning and interacting agents can be understood, is still under development in MASs, although there have been promising first results. We invite contributions that cover on how an agent can learn using ML techniques to act individually, and/or to coordinate with one another towards individual or common goals. This is an open issue in real-time, noisy, collaborative and adversarial environments. We interpret ML techniques in a broad context. These can include the non exhaustive list of Reinforcement Learning, Genetic Algorithms, Neural Networks or Evolutionary Game Theoretic approaches to learning. Also of interest are models for coevolving agent populations. Key-applications, where these techniques can be applied, for example, consist of load balancing problems, traffic management, teamwork, trust, auctions, supply chains, etc. We consider three possible ways in which machine learning can be used to enhance the application of an Agent Based System: 1. An agent can learn the preferences and changing priorities of associated users. 2. An agent can learn about other agents in the environment in order to compete and/or cooperate with them. An agent can learn from other agents, taking advantage of their experiences and incorporating these into its own knowledge base. An agent can also learn almost selfishly and have limited communication with other agents. 3. An agent can learn about other regularities in its environment. We would particularly welcome new insights into these problems from other related disciplines and thus would like to emphasize the inter-disciplinary nature of the workshop. Among others, papers of the following kind are welcome: 1. Evaluation of the effectiveness of individual learning strategies (e.g., case-based, explanation-based, inductive, reinforcement), or multi strategy combinations. 2. Characterization of learning and adaptation methods in terms of modeling power, communication abilities, knowledge requirement, processing abilities of individual agents. For instance through the use of Game Theoretic models. 3. Developing learning and adaptation strategies, or reward structures, for environments with cooperative agents, selfish agents, partially cooperative (will cooperate only if individual goals are not sacrificed) and for environments that can contain mixture of these types of agents. 4. Analyzing convergence properties of existing algorithms and constructing algorithms that guarantee convergence and stability of group behavior. 5. Evaluating effects of knowledge acquisition mechanisms on responsiveness of agents or groups to changes in the agent population in the environment. 6. Learning to work as an effective team by taking advantage of complementary skills and resources. 7. Agents learning via passive or non-intrusive observation of user behaviors or by mimicking other agents. 8. Evolving agent behaviors or co-evolving multiple agents with similar/opposing interests. 9. Investigation of teacher-student relationships between agents or between an agent and the associated user. 10. Applications of learning agents including agents that learn to negotiate contracts, learning trustworthiness of other agents, learn to detect security threats, etc. Those wishing to present should (electronically) submit a full-scale paper, not longer than 16 pages (references and figures included) to Karl Tuyls (karl.tuyls at luc.ac.be) or Katja Verbeeck (kaverbee(at)vub.ac.be). The deadline for submission of contribution is March 14th, 2005. All contributions will be reviewed and in case of acceptance published in the workshop proceedings of the AAMAS'05 conference. Authors should submit full papers electronically in PS or PDF format. In addition, authors should submit an ASCII abstract, with the following information: title of paper; names and affiliations of authors; name, email, snail mail, phone number, and fax number of primary contact; abstract. The same information should be included on the first page of submitted papers. Papers must be written in English, with a maximum length of 16 pages. Please format papers according to the LNCS/LNAI style, a LaTex class is available at http://www.springeronline.com/sgw/cda/frontpage/0,10735,5-164-2-72376-0,00.html All correspondence will be with the specified primary contact. Post proceedings of selected and revised papers are to be published as a Springer Lecture Notes in Artificial Intelligence. ____________________________________________________________ IMPORTANT DATES: Deadline for Submission of Contributions: March 14th, 2005 Notification of Acceptance/Rejection: april 18th, 2005 Camera Ready Copy of Papers: may 15th, 2005 Workshop Date: 25th or 26th of July 2005, precise date to be announced. ____________________________________________________________ Furthermore, if you have any inquiry please do not hesitate to contact the organisers. ____________________________________________________________ Organizing Committee: Karl Tuyls (Primary Contact) karl.tuyls at luc.ac.be LUC Theoretical Computer Science Group Pieter Jan 't Hoen hoen at cwi.nl Evolutionary Systems and Applied Algorithmics Sandip Sen firstName-lastName at utulsa.edu Department of Mathematical and Computer Sciences Katja Verbeeck kaverbee(at)vub.ac.be Computational Modeling Lab ____________________________________________________________ Program Committee: Stephane Airiau, Department of Mathematical & Computer Sciences, The University of Tulsa, USA Bikramjit Banerjee, Department of Computer Science, University of Tulane, USA Ana Lucia Bazzan, Institute of Informatics, Universidade Federal do Rio Grande do Sul, Brazil Sander Bohte, CWI, Evolutionary and Applied Algorithmics group, The Netherlands Michael Goodrich, Department of Computer Science, Brigham Young University, USA Daniel Kudenko, Department of Computer Science, University of York, UK Han La Poutre, CWI, Evolutionary and Applied Algorithmics group, The Netherlands Michael Littman, Rutgers University, Department of Computer Science, USA Peter McBurney, Biocomputing and Computational Biology Group, Liverpool, UK Ann Nowe, Computational Modeling Lab, Vrije Universiteit Brussel, Belgium Simon Parsons, Department of Computer and Information Science, Brooklyn College, New York, USA. Steve Phelps, Biocomputing and Computational Biology Group, Liverpool, UK Jan Ramon, KULeuven, DTAI group, Department of Computer Science, Belgium Peter Stone, Department of Computer Sciences, The University of Texas at Austin, USA Kagan Tumer, NASA Ames Research Lab, USA Danny Weyns, Agentwise research group, KULeuven, Belgium David Wolpert, NASA Ames Research Lab, USA ____________________________________________________________ Looking forward to meeting you all at LAMAS '05 and AAMAS '05. Katja, Karl, Pieter Jan, and Sandip. -- http://lamas2005.luc.ac.be -- From Yann.Guermeur at loria.fr Thu Jan 27 16:43:39 2005 From: Yann.Guermeur at loria.fr (Yann Guermeur) Date: Thu, 27 Jan 2005 22:43:39 +0100 Subject: Post-doc in machine learning at LORIA Message-ID: <41F9608B.1030103@loria.fr> A 18 month post-doctoral position in statistical learning is avaible at the LORIA laboratory http://www.loria.fr/news in Nancy, France. The funding is from the ``Association Franaise contre les Myopathies'' (AFM), in the framework of a joint program between the AFM, the french national center for scientific research (CNRS) and IBM. We are looking for a specialist in kernel methods to apply SVMs to the identification of constitutive and alternative splicing sites in genomic sequences. No background in biology is required. This advertisement will remain valid until a good candidate is found. Contact Yann Guermeur http://www.loria.fr/~guermeur if you have any questions or want to apply. -- Yann Guermeur Tel: (+33) 03 83 59 30 18 LORIA Fax: (+33) 03 83 41 30 79 Campus Scientifique BP 239 54506 Vandoeuvre-les-Nancy Cedex email: Yann.Guermeur at loria.fr FRANCE http://www.loria.fr/~guermeur From dprokhor at ford.com Thu Jan 27 11:36:07 2005 From: dprokhor at ford.com (Prokhorov, Danil (D.V.)) Date: Thu, 27 Jan 2005 11:36:07 -0500 Subject: IJCNN 2005: final call for papers Message-ID: <9B732918BB49A14184A8EF541377CB4C02D7E66B@na1ecm58.dearborn.ford.com> Apologies for multiple postings! IJCNN 2005: FINAL CALL FOR PAPERS, DEADLINE IS JANUARY 31, 2005! Dear Colleagues, The submission deadline of January 31 is rapidly approaching for the International Joint Conference on Neural Networks (IJCNN 2005). Cosponsored by INNS and the IEEE Computational Intelligence Society and by several Universities and Ford Motor Company, IJCNN 2005 promises to be a tremendously exciting meeting with a wide range of tutorials, regular and special sessions, and post-conference workshops. Plenary speakers include Pierre Baldi, Mitsuo Kawato, Frank Lewis, Michael Petrides, and Carver Mead. IMPORTANT! Selected regular conference papers will be invited to a Special Issue of the journal Neural Networks, planned for late Summer 2005. These papers must be substantial enhancements of the IJCNN regular submissions, and they will be additionally peer reviewed. Check in to the web site http://www.ijcnn.org/ for further details--including manuscript submission. Montreal is the place to be this July 31-August 5. See you there! Danil Prokhorov IJCNN 2005 General Chair From mpoel at cs.utwente.nl Fri Jan 28 05:54:34 2005 From: mpoel at cs.utwente.nl (Mannes Poel) Date: Fri, 28 Jan 2005 11:54:34 +0100 Subject: Benelearn 2005 - Call for Participation Message-ID: <41FA19EA.2070705@cs.utwente.nl> +++++++++++++++++++++++++++++++++++++++++++++ Please distribute as widely as possible. Apologies for crossposting. +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Call for Participation Benelearn 2005 Annual Machine Learning Conference of Belgium and the Netherlands http://hmi.ewi.utwente.nl/conference/benelearn2005 Februari 17 - 18, 2005 University of Twente, Enschede, The Netherlands Early Registration deadline: Februari 1st With support from NWO, SIKS, CTIT and Senter-IOP +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Benelearn is the annual machine learning conference of Belgium and the Netherlands. It serves as a forum to exchange ideas and present recent work. Technical Program includes: 2 invited talks: - Probabilistic Logic Learning and Reasoning by K. Kersting (Machine Learning Lab, University of Freiburg, Germany) - Challenges in Multimodal Processing by S. Bengio (IDIAP, Martigny, Switserland) ---------------------------- List of accepted papers: Amplifying the Block Matrix Structure for Spectral Clustering Igor Fischer and Jan Poland Saarland University, Germany IDSIA, Manno (Lugano), Switzerland Evolving Neural Networks for Forest Fire Control Marco Wiering, Filippo Mignogna and Bernard Maassen Utrecht University, The Netherlands Experiments with Relational Neural Networks Werner Uwents and Hendrik Blockeel Catholic University of Leuven, Belgium Assessment of SVM Reliability for Microarrays Data Analysis Andrea Malossini, Enrico Blanzieri and Raymond T. Ng University of Trento, Italy University of British Columbia, Canada Speaker Prediction based on Head Orientations Rutger Rienks, Ronald Poppe and Mannes Poel University of Twente, The Netherlands Strong Asymptotic Assertions for Discrete MDL in Regression and Classification Jan Poland and Marcus Hutter IDSIA, Manno (Lugano), Switzerland Detecting Deviation in Multinomially Distributed Data Jan Peter Patist Vrije Universiteit Amsterdam, The Netherlands Monotone Constraints in Frequent Tree Mining Jeroen De Knijf and Ad Feelders Utrecht University, The Netherlands Best-Response Play in Partially Observable Card Games Frans Oliehoek, Matthijs Spaan and Nikos Vlassis University of Amsterdam, The Netherlands Master Algorithms for Active Experts Problems based on Increasing Loss Values Jan Poland and Marcus Hutter IDSIA, Manno (Lugano), Switzerland Maximizing Expected Utility in Coevolutionary Search Edwin de Jong Utrecht University, The Netherlands Reliability yields Information Gain Ida Sprinkhuizen-Kuyper, Evgueni Smirnov and Georgi Nalbantov University of Maastricht, The Netherlands Erasmus University Rotterdam, The Netherlands Facial Expression Analysis using Multi-layer Perceptrons Michal Sindlar and Marco Wiering Utrecht University, The Netherlands Reinforcement Learning using Optimistic Process Filtered Models Funlade Sunmola and Jeremy Wyatt University of Birmingham, United Kingdom ---------------------------- The registration form and further information can be found at the conference website: http://hmi.ewi.utwente.nl/conference/benelearn2005 The Organizing Comittee: Martijn van Otterlo (University of Twente, the Netherlands) Mannes Poel (University of Twente, the Netherlands) Anton Nijholt (University of Twente, the Netherlands) Sponsors: Netherlands Organisation for Scientific Research (NWO) http://www.nwo.nl Dutch research school for Information and Knowledge Systems (SIKS) http://www.siks.nl/ Centre for Telematics and Information Technology (CTIT) SRO NICE. http://www.ctit.utwente.nl/research/sro/nice/index.html Senter-IOP http://www.senter.nl/asp/page.asp?alias=iop From stricker at ipk-gatersleben.de Fri Jan 28 06:58:10 2005 From: stricker at ipk-gatersleben.de (Marc Strickert) Date: Fri, 28 Jan 2005 12:58:10 +0100 Subject: Thesis on LVQ and SOM for sequences online available Message-ID: <41FA28D2.3040901@ipk-gatersleben.de> Please find the PhD thesis "Self-Organizing Neural Networks for Sequence Processing" by Marc Strickert, Department of Mathematics and Computer Science, University of Osnabr?ck, Germany, 2004 in the internet: Thesis.pdf Size: 1.58 MBytes http://elib.ub.uni-osnabrueck.de/publications/diss/E-Diss384_thesis.pdf Supervisors: Prof. Dr. Barbara Hammer, Prof. Dr. Helge Ritter Abstract: This work investigates the self-organizing representation of temporal data in prototype-based neural networks. Extensions of the supervised learning vector quantization (LVQ) and the unsupervised self-organizing map (SOM) are considered in detail. For LVQ learning, adaptive metrics are studied with a particular focus on the built-in detection of data attributes involved for a given classifcation task; generalized relevance LVQ (GRLVQ) and supervised relevance neural gas with general metrics (SRNGGM) are discussed. For unsupervised sequence processing, two modifcations of SOM are pursued: the SOM for structured data (SOMSD) realizing an efficient back- reference to the previous best matching neuron in a triangular low-dimensional neural lattice, and the merge SOM (MSOM) expressing the temporal context as a fractal combination of the previously most active neuron and its context. The first SOMSD extension tackles data dimension reduction and planar visualization, the second MSOM is designed for obtaining higher quantization accuracy. The supplied experiments underline the high data modeling quality of the presented methods. Keywords: vector quantization, self-organization, relevance learning, classification, clustering, sequence processing, context, fractal representation, GRLVQ, SRNG, MSOM. From the table of contents 1 Introduction 2 2 Data preprocessing for temporal networks I Supervised LVQ-type learning 3 Learning Vector Quantization (LVQ) 4 LVQ with cost function Generalized Relevance LVQ (GRLVQ) Supervised Relevance Neural Gas (SRNG) 5 BB-Tree: Rules from trained GRLVQ or SRNG networks 6 Experiments: Mushroom data, Hypothyroid data, Speaker identifcation, DNA splice site recognition II Unsupervised SOM-type learning 7 Self-Organizing Maps (SOM) 8 SOMSD with lattice topology and alternative lattices 9 Experiments: Mackey-Glass time series, Binary automata, Reber grammar 10 Merge SOM (MSOM) with data topology 11 Experiments: Mackey-Glass time series, Binary automata, Reber grammar, Speaker identifcation by a posteriori MSOM labeling III Discussion and Outlook 107 -- ____ Marc Strickert ____ http://pgrc-16.ipk-gatersleben.de/~stricker/ ____ mail: stricker at ipk-gatersleben.de ____ Institute of Plant Genetics and Crop Plant Research (IPK) ____ Pattern Recognition Group (PRG) / Department of Cytogenetics ____ Corrensstr. 3, D-06466 Gatersleben, Germany. (Room A-0.05) ____ Tel./Fax: ++49 (0) 39482 - 5 182 / - 5 137. From mhb0 at Lehigh.EDU Sat Jan 1 11:03:50 2005 From: mhb0 at Lehigh.EDU (Mark H. Bickhard) Date: Sat, 1 Jan 2005 11:03:50 -0500 Subject: ISI 2005 Call for Papers/Participation Message-ID: Interactivist Summer Institute 2005 September 19-23, 2005 Madren Conference Center Clemson University, Clemson, South Carolina, USA Join us in exploring the frontiers of understanding of life, mind, and cognition. There is a growing recognition - across many disciplines - that phenomena of life and mind, including cognition and representation, are emergents of far-from-equilibrium, interactive, autonomous systems. Mind and biology, mind and agent, are being re-united. The classical treatment of cognition and representation within a formalist framework of encodingist assumptions is widely recognized as a fruitless maze of blind alleys. From neurobiology to robotics, from cognitive science to philosophy of mind and language, dynamic and interactive alternatives are being explored. Dynamic systems approaches and autonomous agent research join in the effort. The interactivist model offers a theoretical approach to matters of life and mind, ranging from evolutionary- and neuro-biology - including the emergence of biological function - through representation, perception, motivation, memory, learning and development, emotions, consciousness, language, rationality, sociality, personality and psychopathology. This work has developed interfaces with studies of central nervous system functioning, the ontology of process, autonomous agents, philosophy of science, and all areas of psychology, philosophy, and cognitive science that address the person. The conference will involve both tutorials addressing central parts and aspects of the interactive model, and papers addressing current work of relevance to this general approach. This will be our third Summer Institute; the first was in 2001 at Lehigh University, Bethlehem, PA, USA, and the second was in 2003 in Copenhagen, Denmark. The intention is for this Summer Institute to become a traditional biennial meeting where those sharing the core ideas of interactivism will meet and discuss their work, try to reconstruct its historical roots, put forward current research in different fields that fits the interactivist framework, and define research topics for prospective graduate students. People working in philosophy of mind, linguistics, social sciences, artificial intelligence, cognitive robotics, theoretical biology, and other fields related to the sciences of mind are invited to send their paper submission or statement of interest for participation to the organizers. http://www.lehigh.edu/~interact/isi2005/index.htm Mark H. Bickhard Lehigh University 17 Memorial Drive East Bethlehem, PA 18015 mark at bickhard.name http://bickhard.ws/ From cns at www.cnsorg.org Sat Jan 1 14:29:45 2005 From: cns at www.cnsorg.org (CNS) Date: Sat, 1 Jan 2005 12:29:45 -0700 Subject: FIRST CALL FOR PAPERS, CNS*2005 Message-ID: <20050101192947.M51094@www.cnsorg.org> CALL FOR PAPERS, CNS*2005: SUBMISSION DEADLINE: February 1, 2005 midnight SUBMISSIONS WILL OPEN January 15th, 2005. NOTE: New submission procedure this year Fourteenth Annual Computational Neuroscience Meeting CNS*2005 July 17 - July 21, 2005 Madison, Wisconsin, USA www.cnsorg.org CNS*2005 will be held in Madison Wisconsin from Saturday, July 17 to Wednesday, July 21, 2005. The main meeting will be July 17-19 followed by two days of workshops on July 20 and 21. Submissions can include experimental, model-based, as well as more abstract theoretical approaches to understanding neurobiological computation. We especially encourage research that mixes experimental and theoretical studies. We also accept papers that describe new technical approaches to theoretical and experimental issues in computational neuroscience or relevant software packages. INVITED SPEAKERS: Michael Hasselmo (Boston University) Lucia Jacobs (UC Berkeley) Gyorgy Buszaki (Rutgers University) Submissions to the meeting will take the form of a 3-page summary describing the nature and scope of the work, and outlining the main results. Details regarding formatting of submissions will be posted at www.cnsorg.org. These summaries will be reviewed by the program committee and used determine acceptance for presentation at the meeting as well as to construct the oral program. Authors will also be asked to submit a standard abstract for printing in the program book. All submissions will be acknowledged by email. THE REVIEW PROCESS Summaries will be judged and accepted for the meeting based on the clarity with which the work is described and the biological relevance of the research. For this reason authors should be careful to make the connection to biology clear. CNS strongly believes in the open exchange of ideas and we reject only a small fraction of submissions (~5%). Rejections are usually based on absence of biological relevance (e.g. pure machine learning). We will notify authors of meeting acceptance by April 1. All acceptable summaries will be reviewed by two independent referees, and the oral program of the meeting will constructed based on these reviews. Most oral presentations will be 20 minutes in length, but several papers will be selected for longer "featured oral" presentations. In addition to perceived quality as an oral presentation, the novelty of the research and the diversity and coherence of the overall program will be considered. To ensure diversity, those who have given talks in the recent past will not be selected and multiple oral presentations from the same lab will be discouraged. All accepted papers not selected for oral talks may be presented during evening poster sessions. Authors will be notified of the presentation format of their papers by the end of April. PROCEEDINGS AND PUBLICATION In the past, the proceedings of the meeting were published as a special supplement to the journal Neurocomputing. The same review process was used to determine the program acceptance in the journal. This year, the proceedings of the meeting will take the form of electronic publication of all 3-page summaries of work presented at the meeting. A separate review process will be used for those electing for post-meeting journal publication. Authors wishing to submit their work for peer-reviewed publication in Neurocomputing will be required to submit complete 6-page papers by May 2nd. Manuscripts will be reviewed according to the usual standards for journal publication. Authors will notification of submission status (accept, reject, revise) and receive reviewer comments by the end of June, several weeks before the meeting. Authors will then have until September 15 to submit revised manuscripts. Final notification of acceptance based on these revisions will be sent by October 15. Detailed instructions to authors will be posted at www.cnsorg.org. -- CNS - Organization for Computational Neurosciences From martin.giese at uni-tuebingen.de Sun Jan 2 17:38:07 2005 From: martin.giese at uni-tuebingen.de (Martin Giese) Date: Sun, 02 Jan 2005 23:38:07 +0100 Subject: Job announcements (PhD position in Tuebingen) Message-ID: <41D877CF.4020904@uni-tuebingen.de> PHD POSITION AT THE LABORATORY FOR ACTION REPRESENTATION AND LEARNING, HERTIE INSTITUTE FOR CLINICAL BRAIN RESEARCH, TUEBINGEN, GERMANY We offer a PhD Position in the context of a project on the expression of emotions by body movements. The project is funded by the Human Frontier Science Program (HFSP) and realized in collaboration with the College de France, the Weizman Institute, and the University of Tilburg. Start date is as soon as possible. We seek for an individual with a background in computer science, engineering, physics, or mathematics with interest in motion capture, computer graphics, machine learning, motor control, or bioinformatics. The project will include developing new algorithms for modeling trajectories, and working with modern systems for motion capture and computer animation. The Laboratory for Action Representation and Learning (ARL) provides a highly interdisciplinary research environment combining methods from theoretical and experimental neuroscience, computer graphics, computer vision, and machine learning. ARL studies the neural mechanisms of the perception of complex movements, and algorithms for the modeling of complex movements in normals and patients. The Hertie Institute for Clinical Brain Research is one of the largest centers for neurological research in Germany. Its four departments host more than 150 researchers focusing on many different aspects of modern neurology. ARL is closely affiliated with the Max Planck Institute for Biological Cybernetics in Tbingen. Tbingen offers an international PhD program in the Graduate School for Neural and Behavioral Sciences that realized in collaboration between the University and the Max Planck Institutes. Interested candidates should send or email CVs and the names of 2 references to Martin Giese, ARL, Dept. of Cognitive Neurology, University Clinic Tuebingen, Schaffhausenstr. 113, D-72076 Tuebingen, Germany. Tel.: (+49) 7071 601 724 Email: martin.giese at uni-tuebingen.de Further information: http://www.uni-tuebingen.de/uni/knv/arl/ http://www.hih-tuebingen.de/ http://www.uni-tuebingen.de/neuroschool From thomas.hofmann at ipsi.fraunhofer.de Mon Jan 3 15:20:37 2005 From: thomas.hofmann at ipsi.fraunhofer.de (Thomas Hofmann) Date: Mon, 3 Jan 2005 21:20:37 +0100 Subject: 4 Positions for Ph.D. RAships and/or Postdocs at Darmstadt Message-ID: The Computer Science Department of the Technical University of Darmstadt invites applications for four (4) positions as Research Assistants (Wissenschaftliche Mitarbeiter/innen). We are particularly looking for applicants with interest in one or more of the following areas: * Theory, methods and applications of Machine Learning * Intelligent Information Retrieval and innovative search engines * Natural language understanding * Methods and principles of Data Mining * Reasoning, knowledge representation and probabilistic inference * Artificial Neural Networks We offer an excellent hardware and software equipment and the prospect to work on cutting-edge research projects in a dynamic and international research team. Opportunity to work towards a Ph.D. degree will be provided. Applicants are expected to contribute to the teaching assignments and research projects of the group. Rank & Salary: The salary level is determined according to the BAT (Bundes-Angestellten-Tarif) scale (BAT IIa). Positions are initially for three years with a possible further extension.=20 Qualifications: degree (Diplom, Bachelor or Masters) in computer science or a neighboring discipline is required; good knowledge in software development and programming. Positions available: starting February 1st 2005 Closing date: January 15th 2005 Application: Applications should include the standard applications documents such as curriculum vitae, copies of the relevant university certificates (Diploma, Bachelor, or Master), list of publications, and statement of research interests. Please send your application to:=20 Dekan des Fachbereiches 20,=20 Position #270 Hochschulstra=DFe 10 64289 Darmstadt, Germany The Technical University of Darmstadt is an equal opportunities employer. Women and disabled candidates are especially encouraged to apply. Applications should be accompanied by the standard application documents including letter of application, curriculum vitae, exam certificates and references. From l.wiskott at biologie.hu-berlin.de Wed Jan 5 09:31:51 2005 From: l.wiskott at biologie.hu-berlin.de (Laurenz Wiskott) Date: Wed, 5 Jan 2005 15:31:51 +0100 Subject: Neurogenesis in the Hippocampus - E-Print (and open postdoc position) Message-ID: <16859.64087.972538.74691@huxley.biologie.hu-berlin.de> WHAT IS THE FUNCTIONAL ROLE OF ADULT NEUROGENESIS IN THE HIPPOCAMPUS? by Laurenz Wiskott, Malte Rasch, and Gerd Kempermann Abstract: The dentate gyrus is part of the hippocampal memory system and special in that it generates new neurons throughout life. Here we discuss the question of what the functional role of these new neurons might be. Our hypothesis is that they help the dentate gyrus to avoid the problem of catastrophic interference when adapting to new environments. We assume that old neurons are rather stable and preserve an optimal encoding learned for known environments while new neurons are plastic to adapt to those features that are qualitatively new in a new environment. A simple network simulation demonstrates that adding new plastic neurons is indeed a successful strategy for adaptation without catastrophic interference. Available from: http://cogprints.org/4012/ Reference: Wiskott, L., Rasch, M., and Kempermann, G. (2004). What is the functional role of adult neurogenesis in the hippocampus? Cognitive Sciences EPrint Archive (CogPrints) 4012, http://cogprints.org/4012/ (). Additional Information: http://itb1.biologie.hu-berlin.de/~wiskott/Projects/Hippocampus.html Open Postdoc Position: http://itb.biologie.hu-berlin.de/~wiskott/jobs2.html -- Dr. Laurenz Wiskott, Institute for Theoretical Biology, Berlin http://itb.biologie.hu-berlin.de/~wiskott/ l.wiskott at biologie.hu-berlin.de From bogus@does.not.exist.com Thu Jan 6 12:54:51 2005 From: bogus@does.not.exist.com () Date: Thu, 6 Jan 2005 17:54:51 -0000 Subject: Postdoctoral Fellowship Message-ID: <52A8091888A23F47A013223014B6E9FE02837F98@03-CSEXCH.uopnet.plymouth.ac.uk> From schapire at CS.Princeton.EDU Thu Jan 6 09:35:17 2005 From: schapire at CS.Princeton.EDU (Robert Schapire) Date: Thu, 6 Jan 2005 09:35:17 -0500 (EST) Subject: tenure-track AI position at Princeton CS Message-ID: <200501061435.j06EZHgf028867@bolle.CS.Princeton.EDU> The Princeton University Department of Computer Science has at least one opening for a tenure-track faculty position, preferably at the level of assistant professor. This position is especially targeted in the area of artificial intelligence, very broadly defined. See the official announcement below. If you apply for this position, please also ask your references to mail or email their letters directly to the address given in the ad. Rob Schapire ================================================================= FACULTY POSITIONS Computer Science Department Princeton University We invite you to apply for Assistant Professor, tenure-track positions. We are entertaining applications in all areas of Computer Science, with particular emphasis on Artificial Intelligence. Candidates for more senior ranks with exceptional records of research will also be considered. Applicants must demonstrate superior research and scholarship potential as well as teaching ability. A Ph.D or equivalent in Computer Science or related areas is required. Successful candidates at all ranks are expected to pursue an active research program and to contribute significantly to the teaching programs of the department. Applicants should include a resume and the names of at least three people who can comment on the applicant's professional qualification. Applications should be sent to: Chair, Search Committee Princeton University Department of Computer Science 35 Olden Street Princeton, NJ 08544-2087 Email: search at cs.princeton.edu The Committee will begin to consider applications in January 2005. Princeton University is an Equal Opportunity/Affirmative Action employer. From bower at uthscsa.edu Fri Jan 7 12:42:22 2005 From: bower at uthscsa.edu (james Bower) Date: Fri, 07 Jan 2005 11:42:22 -0600 Subject: abstract deadline for biological modeling meeting Message-ID: ABSTRACT SUBMISSION DEADLINE JANUARY 15th midnight ADDITIONAL SUPPORT FOR STUDENT TRAVEL IS NOW AVAILABLE January 15th is the abstract submission deadline for the the first annual meeting for realistic biological modeling in San Antonio Texas, March 31st - April 2nd, 2005. (Wam-Bamm*05). The meeting is specifically focused on realistic biological modeling, rather than more abstract approaches to neural computation, with an emphasis both on scientific results and technical issues. Although it is being held in association with the second GENESIS Users Meeting (GUM*05) all computational biologists, not only those using GENESIS, are invited to present scientific as well as technical work. Only an abstract is required for meeting presentation. In particular we would encourage modelers using NEURON to attend and meet Michael Hines, developer of the NEURON modeling system. The first day of the meeting will be devoted to Tutorials including: Introduction to realistic neural modeling: Dr. David Beeman, University of Colorardo The NEURON simulator - recent developments: Dr. Michael Hines, Yale University From experiment to simulation - a case study: Dr. Dieter Jaeger, Emory University Controlling complex synaptic input patterns: Jeremy Edgerton, Emory University Modeling calcium and biochemical reactions: Dr. Avrama Blackwell, George Mason University Constructing large networks in GENESIS: Dr. Michael Vanier, Caltech. Parameter searching in GENESIS: Dr. Michael Vanier, Caltech Parallel (P-) GENESIS: Greg Hood, Pittsburgh Supercomputing Center XML for model specification: Dr. Sharon Crook, Arizona State University Building 3D network models with neuroConstruct: Padraig Gleeson, University College London The next two days will be devoted to invited speakers as well as contributed presentations primarily in poster form. Confirmed Invited Speakers include: Dr. Michael Hauser, University College London, "Model-based studies of cerebellar cortical circuitry" Dr. Michael Hasselmo, Boston University, "Modeling the role of entorhinal cortex, prefrontal cortex and hippocampus in memory guided behavior" Dr. Charles Wilson, University of Texas, San Antonio, "A model of autonomous irregular firing and bursting in striatal cholinergic interneurons" Dr. Larry Parsons, University of Sheifield, "what can realistic modeling tell us about cognitive function?" Dr. Graham Cummins, Center for Computational Biology, Montana State University, "Parameter estimation in realistic models of cricket dendrites" The deadline for abstract submission is January 15th, and the deadline for early registration at reduced rates is February 1st. Please visit the meeting website: http://www.WAM-BAMM.org to register, submit abstracts and for other general meeting information. Hope to see you in San Antonio this spring. Jim Bower Dave Beeman -- James M. Bower Ph.D. Research Imaging Center University of Texas Health Science Center at San Antonio 7703 Floyd Curl Drive San Antonio, TX 78284-6240 Cajal Neuroscience Center University of Texas San Antonio Phone: 210 567 8080 Fax: 210 567 8152 From j.a.bullinaria at cs.bham.ac.uk Fri Jan 7 09:18:18 2005 From: j.a.bullinaria at cs.bham.ac.uk (John Bullinaria) Date: Fri, 7 Jan 2005 14:18:18 +0000 Subject: Scholarships for MSc in Natural Computation at Birmingham, UK Message-ID: Studentships/Scholarships for MSc in Natural Computation ======================================================== School of Computer Science The University of Birmingham Birmingham, UK (http://www.cs.bham.ac.uk/research/NC/) Applications are invited for an advanced 12 month MSc programme in Natural Computation starting in September 2005. Natural Computation systems, such as artificial neural networks and genetic algorithms, use ideas and inspirations from biological, ecological, social and physical systems. The programme comprise of six taught modules in Neural Computation, Evolutionary Computation, Molecular and Quantum Computation, Nature Inspired Optimisation, Nature Inspired Learning, and Nature Inspired Design (10 credits each); two mini research projects (30 credits each); and one full scale research project (60 credits). The programme is supported by the EPSRC through its Master's Level Training Packages and by a number of leading companies. Our industrial advisory board includes representatives from BT Exact, Honda, Unilever, QinetiQ, Rolls Royce, HP Labs, e-9 Ltd and SPSS. The School of Computer Science is a research intensive school and was rated 5 for its research excellence in the latest (2001) research assessment exercise. The School has a world-leading group in natural computation and computational intelligence (http://www.cs.bham.ac.uk/research/NC/), including more than 40 researchers (including teaching and research staff and PhD students), working on a wide range of topics in natural computation and computational intelligence. We have a Centre of Excellence for Research in Computational Intelligence and Applications (CERCIA), specialising in applied research and knowledge transfer (www.cercia.ac.uk). The programme is open to candidates with a very good honours degree or equivalent qualifications in Computer Science/Engineering or closely related areas. Several fully funded EPSRC studentships (covering fees and maintenance costs) are available. These are awarded on a competitive basis according to applicants' academic achievements. Additional financial support from our industrial partners may be available during the summer project period. Further details about this programme and funding opportunities, plus an on-line application form, are available from our Web-site at: http://www.cs.bham.ac.uk/study/postgraduate-taught/msc-nc/ The Programme Director is Dr Alastair Channon (a.d.channon at cs.bham.ac.uk). From C.Campbell at bristol.ac.uk Fri Jan 7 08:00:06 2005 From: C.Campbell at bristol.ac.uk (ICG Campbell, Engineering Mathematics) Date: Fri, 07 Jan 2005 13:00:06 -0000 Subject: Advert: Professorship in AI, Bristol University Message-ID: <96228959.1105102806@ems-iggs.enm.bris.ac.uk> Advertisement for position: Professor of Artificial Intelligence, Department of Engineering Mathematics, University of Bristol, United Kingdom We seek to appoint a research leader in Artificial Intelligence to complement the strengths and further enhance the international reputation of the existing AI Group in fuzzy and probabilistic uncertainty, kernel-based methods and the mathematical treatment of learning in intelligent systems. An established track record in any aspect of AI and its applications is required, such as intelligent data analysis, uncertainty modelling, graphical methods, machine learning, emergent behaviour or robotics. A willingness to actively collaborate and engage in interdisciplinary research is also essential. The Department of Engineering Mathematics is unique in being the only research-intensive mathematics department in the UK within an engineering faculty. Its remit is therefore to pursue innovation in mathematics relevant to engineering (inclusive of computer science) and other application areas. Its research received a 5*A rating in the 2001 Research Assessment Exercise. It is anticipated the appointee will use the existing base and further appointments to build a group with an international reputation. For those interested, more details about this position can be obtained from: http://www.bris.ac.uk/boris/jobs/ads?ID=31015 The webpage for the existing AI group may be found at: http://www.enm.bris.ac.uk/ai/index.html The University webpage is at: http://www.bris.ac.uk/ ***Closing date for applications: 9.00 am on 04 February 2005 ---------------------- Colin Campbell, Engineering Mathematics C.Campbell at bristol.ac.uk From kbp at imm.dtu.dk Fri Jan 7 04:31:01 2005 From: kbp at imm.dtu.dk (Kaare Brandt Petersen) Date: Fri, 7 Jan 2005 10:31:01 +0100 (MET) Subject: The Matrix Cookbook - new version Message-ID: Dear Colleagues (Apollogies for multiple postings) A new and updated version of The Matrix Cookbook is available for download http://www.imm.dtu.dk/pubdb/views/edoc_download.php/3274/pdf/imm3274.pdf The Matrix Cookbook is a desktop reference on formulas regarding matrices such as the derivatives of determinants and traces, identities involving inverses, statistical moments and more. Apart from smaller additions and corrections, this version of The Matrix Cookbook has been updated with material on derivatives of complex matrices and matrix norm inequalities. This is largely due to the work of Michael Syskind Pedersen who has joined the project as author. Comments and corrections are most welcome. Best regards, Kaare -- Kaare Brandt Petersen * http://2302.dk From fyfe-ci0 at wpmail.paisley.ac.uk Sat Jan 8 11:21:55 2005 From: fyfe-ci0 at wpmail.paisley.ac.uk (Colin Fyfe) Date: Sat, 08 Jan 2005 16:21:55 +0000 Subject: New Book Message-ID: I have taken extracts from 8 of the PhDs completed in this university over the last few years and published them together as a book. I hope this may interest some in the connectionists community, and would be happy to receive any feedback. Colin Fyfe ----------------------------------------------- Hebbian Learning and Negative Feedback Networks Colin Fyfe Springer ISBN 1-85233-883-0 The central idea of this book is that artificial neural networks which use negative feedback of activation can use simple Hebbian learning to self-organise in such a way that they uncover interesting structure in data sets. The network in its simplest form performs a Principal Component Analysis. Extensions to the network are shown to perform Exploratory Projection Pursuit: they find low-dimensional filters of the data which reveal interesting structure in the data. For example, we might search for outliers from the main body of the data or clusters within the data set and this search can be performed in a hierarchical manner – we find one cluster in the midst of many and then re-project the data from this one cluster to attempt to find sub-clusters. There are two main ways of performing these searches and these are contrasted and compared and a composite method created which exhibits useful properties from the two underlying methods. The network can also be used to find independent components of a data set in a number of different ways. For example, one extension to the basic network is shown to perform a type of Factor Analysis – it identifies a set of factors which when OR-ed together will construct the data set. Other methods are used to perform Independent Component Analysis which is extensively used in blind source separation – extracting one signal from a linear mixture of signals. The network can also be used for clustering in a topology preserving manner: there are several ways of clustering using this network in such a way that similar data points are clustered close to one another and only similar data points are treated this way. In part 2 of the book, twinned networks are introduced: these networks have two input data streams on which they self-organise using simple Hebbian learning with negative feedback again. In their basic form, the networks are shown to perform Canonical Correlation Analysis, the statistical technique which finds those filters onto which projections of the two data streams have greatest correlation. Various extensions of the basic methods are devised in order to create methods which react to more than two data streams at a time or which deal with problems such as multicollinearity. A further extension is the twinning of the Exploratory Projection Pursuit methods from the first part of the book so that the new network identifies shared structure across two data streams. This new network is also shown to perform Independent Component Analysis. A final chapter deviates somewhat from the rest of the book since its emphasis is on an extension of the Principal Curve algorithm so that we now have two curves learning on two data streams simultaneously. Since the scope of the book is the development of new algorithms, all algorithms which are derived analytically, are illustrated on artificial data before being used on real data sets. Where it is of interest, the results are compared with those from standard statistics or from alternative artificial neural networks. Other than the final chapter, all networks are biologically plausible in that they use locally available data to self-organise to extract information from data sets. Table of Contents {1}Introduction {1.1}Artificial Neural Networks {1.2}The Organisation of this Book Part I Single Stream Networks {2}Background {2.1}Hebbian Learning {2.2}Quantification of Information {2.3}Principal Component Analysis {2.4}Weight Decay in Hebbian Learning {2.5}ANNs and PCA {2.6}Anti-Hebbian Learning {2.7}Independent Component Analysis {2.8}Conclusion {3}The Negative Feedback Network {3.1}Introduction {3.2}The $VW$ Model {3.3}Using Distance Differences {3.4}Minor Components Analysis {3.5}Conclusion {4}Peer-Inhibitory Neurons {4.1}Analysis of Differential Learning Rates {4.2}Differential Activation Functions {4.3}Emergent Properties of the Peer-Inhibition Network {4.4}Conclusion {5}Multiple Cause Data {5.1}Non-negative Weights {5.2}Factor Analysis {5.3}Conclusion {6}Exploratory Data Analysis {6.1}Exploratory Projection Pursuit {6.2}The Data and Sphering {6.3}The Projection Pursuit Network {6.4}Other Indices {6.5}Using Exploratory Projection Pursuit {6.6}Independent Component Analysis {6.7}Conclusion {7}Topology Preserving Maps {7.1}Background {7.2}The Classification Network {7.3}The Scale Invariant Map {7.4}The Subspace Map {7.5}The Negative Feedback Coding Network {7.6}Conclusion {8}Maximum Likelihood Hebbian Learning {8.1}The Negative Feedback Network and Cost Functions {8.2}$\epsilon $-Insensitive Hebbian Learning {8.3}The Maximum Likelihood EPP Algorithm {8.4}A Combined Algorithm {8.5}Conclusion Part II Dual Stream Networks {9}Two Neural Networks for Canonical Correlation Analysis {9.1}Statistical Canonical Correlation Analysis {9.2}The First Canonical Correlation Network {9.3}Experimental Results {9.4}A Second Neural Implementation of CCA {9.5}Simulations {9.6}Linear Discriminant Analysis {9.7}Discussion {10}Alternative Derivations of CCA Networks {10.1}A Probabilistic Perspective {10.2}Robust CCA {10.3}A Model Derived from Becker's Model 1 {10.4}Discussion {11}Kernel and Nonlinear Correlations {11.1}Nonlinear Correlations {11.2}The Search for Independence {11.3}Kernel Canonical Correlation Analysis {11.4}Relevance Vector Regression {11.5}Appearance-Based Object Recognition {11.6}Mixtures of Linear Correlations {12}Exploratory Correlation Analysis {12.1}Exploratory Correlation Analysis {12.2}Experiments {12.3}Connection to CCA {12.4}FastECA {12.5}Local Filter Formation From Natural Stereo Images {12.6}Twinned Maximum Likelihood Learning {12.7}Unmixing of Sound Signals {12.8}Conclusion {13}Multicollinearity and Partial Least Squares {13.1}The Ridge Model {13.2}Application to CCA {13.3}Extracting Multiple Canonical Correlations {13.4}Experiments on Multicollinear Data {13.5}A Neural Implementation of Partial Least Squares {13.6}Conclusion {14}Twinned Principal Curves {14.1}Twinned Principal Curves {14.2}Properties of Twinned Principal Curves {14.3}Twinned Self-Organising Maps {14.4}Discussion {15}The Future {15.1}Review {15.2}Omissions {15.3}Current and Future Work Appendices A Negative Feedback Artificial Neural Networks {A.1}The Interneuron Model {A.2}Other Models {A.3}Related Biological Models B Previous Factor Analysis Models {B.1} F\"{o}ldi\'{a}k's Sixth Model {B.2}Competitive Hebbian Learning {B.3}Multiple Cause Models {B.4}Predictability Minimisation {B.5}Mixtures of Experts {B.6}Probabilistic Models C Related Models for ICA {C.1}Jutten and Herault {C.2}Nonlinear PCA {C.3}Information Maximisation {C.4}Penalised Minimum Reconstruction Error {C.5}FastICA D Previous Dual Stream Approaches {D.1}The I-Max Model {D.2}Stone's Model {D.3}Kay's Neural Models {D.4}Borga's Algorithm E Data Sets {E.1}Artificial Data Sets {E.2}Real Data Sets Legal disclaimer -------------------------- The information transmitted is the property of the University of Paisley and is intended only for the person or entity to which it is addressed and may contain confidential and/or privileged material. Statements and opinions expressed in this e-mail may not represent those of the company. Any review, retransmission, dissemination and other use of, or taking of any action in reliance upon, this information by persons or entities other than the intended recipient is prohibited. If you received this in error, please contact the sender immediately and delete the material from any computer. -------------------------- From ezequiel at sussex.ac.uk Mon Jan 10 06:45:25 2005 From: ezequiel at sussex.ac.uk (Ezequiel Di Paolo) Date: Mon, 10 Jan 2005 11:45:25 +0000 (GMT) Subject: Advert: Postdoctoral positions at Leeds and Sussex Universities In-Reply-To: <96228959.1105102806@ems-iggs.enm.bris.ac.uk> Message-ID: Post-Doctoral Positions, Universities of Leeds & Sussex Complex Adaptive Networks Computational Neuroscience, Bio-Inspired Robotics & Adaptive Behaviour "Spatially Embedded Complex Systems Engineering" Four postdoctoral fellowships are available immediately for research in computational and mathematical modelling, particularly of spatial factors in neural and neuro-chemical systems, and the IT systems underpinning air-traffic control. Two postdocs (PD1 & PD2) will be located in the Biosystems group within the School of Computing at the University of Leeds (http://www.informatics.leeds.ac.uk/), and two (PD3 & PD4) will be located in the Centre for Computational Neuroscience and Robotics (http://www.informatics.sussex.ac.uk/ccnr/) and the Complex Products Systems Group (http://www.cops.ac.uk/) at the University of Sussex. However, all four will work closely as part of an extended multi-site research team involving 10 investigators, 6 postdocs and 2 PhD students. PD1 (Ref 310233 - Leeds): Suitable for a talented, experienced researcher with a background in one or more of the following areas: adaptive behaviour, evolutionary computing, dynamical systems theory, simulation modelling. Excellent computational, mathematical and modelling skills are required. Ability to engage in profitable collaboration across different disciplines is essential. PD1 will work most closely with Seth Bullock and Ezequiel Di Paolo. PD2 (Ref 310234 - Leeds) & PD3 (Sussex): Suitable for talented researchers with experience in one or more of the following areas: computational neuroscience, dynamical systems modelling, evolutionary computing, time series analysis and spatial analysis Excellent computational, mathematical and modelling skills are required, some experience of neural modelling is desirable. (PD2) will work most closely with Netta Cohen and Seth Bullock; (PD3) with Ezequiel Di Paolo, Jianfeng Feng, Phil Husbands, and Mick O'Shea. PD4: Suitable for a talented researcher with experience in one or more of the following areas: adaptive systems engineering, machine learning, evolutionary computing, air-traffic control systems. Excellent computational, mathematical and modelling skills are required as well as the capability to engage in profitable collaboration with social scientists and open dialogue with industrial partners, familiarity with air-traffic control would be advantageous but not necessary. PD4 will work most closely with Ezequiel Di Paolo, Phil Husbands, and Paul Nightingale. These posts are part of an exciting multidisciplinary project spanning Leeds, Sussex and UCL, in which computer scientists, geographers, neuroscientists, policy researchers and engineers will study adaptive behaviour across a range of significant spatially-extended systems (neuroscience, geoscience, air-traffic control). The research teams will be led by Dr. Seth Bullock at the University of Leeds, Dr. Ezequiel Di Paolo at Sussex University and Prof. Mike Batty at University College London, but will work together closely for the duration of the project. See further particulars for more details. All highly motivated candidates with a PhD in computer science, biology, cognitive science, psychology, physics or other relevant disciplines are encouraged to apply. Informal enquiries (with CV attached) are welcome at the email addresses below: PD1: Seth Bullock, seth at comp.leeds.ac.uk PD2: Netta Cohen, netta at comp.leeds.ac.uk PD3 & PD4: Ezequiel Di Paolo, ezequiel at sussex.ac.uk Further particulars and job descriptions can be accessed from here: http//www.comp.leeds.ac.uk/seth/secse/secse.html To download application forms for the Leeds posts (PD1 and PD2) visit http://www.leeds.ac.uk and click on "jobs". Email (or post) completed application forms and a full CV to Judi Drew (judi at comp.leeds.ac.uk), School of Computing, University of Leeds, Leeds, LS2 9JT. To apply for the Sussex posts (PD3 and PD4) email a full CV and covering note to Ezequiel Di Paolo. The project is funded by EPSRC. Starting salaries approx. ? 22,000 depending on experience. Posts are available for three-and-a-half years. Starting date: 1 April 05, or soon after. There is no deadline but each position will be filled as soon as a suitable candidate is found. Applications received by 10 Feb, 2005 are guaranteed full consideration. Applications from UK, EU and non-EU residents are welcome. The University of Leeds and the university of Sussex are equal opportunity employers. ------ From triesch at ucsd.edu Tue Jan 11 18:36:07 2005 From: triesch at ucsd.edu (Jochen Triesch) Date: Tue, 11 Jan 2005 15:36:07 -0800 Subject: PostDoc and Graduate Student Positions at the Frankfurt Institute for Advanced Studies Message-ID: <41E462E7.3010907@ucsd.edu> 2 PhD and 1 Postdoc Position Available -------------------------------------- The newly founded Frankfurt Institute for Advanced Studies (FIAS) is looking for 1 Postdoc and 2 PhD students in the area of theoretical neuroscience (broadly construed). The positions are in the group of Jochen Triesch. The group's research areas include: Neural Computation, Vision (Computer, Robot, and Human Vision), Computational and Robotic Models of Cognitive Development. There will be ample opportunity to interact with other researchers at FIAS, the close-by Max Planck Institute for Brain Research, and the Johann Wolfgang Goethe University Frankfurt. The official language at the institute is English. The successful applicant for the PostDoc Position will join FIAS as a "junior fellow". The position is initially for one year, renewable for up to 3 years. Candidates should have a recent PhD in a quantitative discipline (physics, mathematics, computer science, electrical engineering or related fields) and a keen interest in several of the lab's research areas. A tax-free scholarship of 30,000 Euro per year (equivalent to about 50k US$ before tax) will be offered. Successful applicants for the Graduate Student Positions will join the three year PhD program at the new Frankfurt International Graduate School for Sciences (FIGSS). Candidates should have a Masters degree in a quantitative discipline (see above) and a keen interest in several of the lab's research areas. Students will receive a tax-free stipend of 12,000 Euro per year. Applicants should submit: - resume (including date of birth, grades, awards, publications), - statement of research interests (up to 2 pages), - names and email addresses of 3 references - links to their thesis and/or publications Positions will remain open until filled. Full consideration will be given to all applications arriving by February 15, 2005. Please send applications directly to my San Diego address: Jochen Triesch Dept. of Cognitive Science, UC San Diego 9500 Gilman Drive, La Jolla, CA 92093-0515, USA Applications can also be submitted by email to triesch at ucsd.edu. Make sure that all attached files use the following filename convention: Firstname.Lastname.DocDescription.DocType Do not send .doc or .rtf documents. Instead, use .pdf or plain text formats. Important Links: Details on the positions: http://cloudbreak.ucsd.edu/~triesch/positions.html Lab home page: http://csclab.ucsd.edu Frankfurt Institute for Advanced Studies (FIAS): http://www.fias.uni-frankfurt.de/ Frankfurt International Graduate School for Science (FIGSS): http://www.fias.uni-frankfurt.de/figss/ Max Planck Institute for Brain Research: http://www.mpih-frankfurt.mpg.de --------------------------------------------------------------------------- The Frankfurt Institute for Advanced Studies is a newly founded institution dedicated to basic theoretical research in various areas of science. The Institute will serve as a superstructure for basic research, bringing together theorists from the disciplines of biology, chemistry, neuroscience, physics, and computer science in a common organizational and intellectual framework. It is an ambitious independent scientific institution while at the same time bundling research activities at the University of Frankfurt and neighboring research centers. Scientists from FIAS and from Goethe University join forces to educate graduate students in the Frankfurt International Graduate School for Science. -- Jochen Triesch, triesch at ucsd.edu http://cloudbreak.ucsd.edu/~triesch Frankfurt Institute for Advanced Studies Johann Wolfgang Goethe University Robert Mayer Str. 10, 60054 Frankfurt am Main, Germany and Dept. of Cognitive Science, UC San Diego 9500 Gilman Drive, La Jolla, CA 92093-0515, USA Tel: +1 (858) 822-3317, Fax: +1 (858) 534-1128 From movellan at mplab.ucsd.edu Wed Jan 12 14:33:57 2005 From: movellan at mplab.ucsd.edu (Javier R. Movellan) Date: Wed, 12 Jan 2005 11:33:57 -0800 Subject: Kolmogorov Open Source Tutorials Message-ID: The latest version of the Open Source tutorials from the Kolmogorov project is available at http://mplab.ucsd.edu/tutorials/tutorials.html. It includes tutorials on the following topics: * Variational EM * Generalized Factor Analysis * Multinomial Logistic Regression * Stochastic Differential Equations * Gabor Filters * The Discrete Time Kalman Filtering and Controler * Hidden Markov Models * Exponential Smoothing * Principal Component Analysis * Sequential Sampling Methods * The Singular Value Decomposition * Image Formation Models * Introduction to Probability Theory and Statistics (Textbook) * Axiomatic Set Theory * Useful Mathematical Facts * Matrix Algebra Cookbook * Matrix Calculus Cookbook -Javier R. Movellan Machine Perception Laboratory UCSD From hitzler at aifb.uni-karlsruhe.de Thu Jan 13 08:16:30 2005 From: hitzler at aifb.uni-karlsruhe.de (Pascal Hitzler) Date: Thu, 13 Jan 2005 14:16:30 +0100 Subject: CfP: IJCAI-05 Workshop on Neural-symbolic learning and reasoning Message-ID: <41E674AE.5020702@aifb.uni-karlsruhe.de> Call for Papers Workshop on Neural-Symbolic Learning and Reasoning (NeSy'05) at IJCAI-05, Edinburgh, Scotland, July 31st, 2005 ------------------------------------------------------------ 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; * Integrated neural-symbolic learning approaches; * Extraction of symbolic knowledge from trained neural networks; * Integrated neural-symbolic reasoning; * Biological inspiration for neural-symbolic integration; * Applications in robotics, semantic web, engineering, bioinformatics, etc. 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 8 pages in the case of research and experience papers, and 4 pages in the case of position papers (including figures, bibliography and appendices). 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 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 in official workshop proceedings, which 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 a special issue of the Journal of Applied Logic, Elsevier, to be published early in 2006. Important Dates --------------- Deadline for submission: 4th of March, 2005 Notification of acceptance: 18th of April, 2005 Camera-ready paper due: 16th of May, 2005 Workshop day: TBA (between 30th of July and 1st of August, 2005) IJCAI 2005 main conference dates: 30th of July to 5th of August, 2005 Workshop Organisers ------------------- Artur d'Avila Garcez (City University London, UK) Jeff Elman (University of California, San Diego, USA) Pascal Hitzler (AIFB, University of Karlsruhe, Germany) Programme Committee ------------------- Artur d'Avila Garcez (City University London, UK) Howard Blair (Syracuse University, USA) Jeff Elman (University of California San Diego, USA) Dov Gabbay (Kings College London, UK) Marco Gori (University of Siena, Italy) Barbara Hammer (University of Osnabrck, Germany) Pascal Hitzler (University Karlsruhe, Germany) Steffen Hlldobler (TU Dresden, Germany) Luis Lamb (Federal University of Rio Grande do Sul, Brazil) John Lloyd (The Australian National University, Australia) Asim Roy (Arizona State University, USA) Antony K. Seda (University College Cork, Ireland) Jude Shavlik (University of Wisconsin, USA) Rudi Setiono (National University, Singapore) Alessandro Sperduti (University of Padova, Italy) Stefan Wermter (University of Sunderland, UK) Gerson Zaverucha (UFRJ, Brazil) Keynote speakers ---------------- Steffen Hlldobler (TU Dresden, Germany) Ron Sun (Rensselaer Polytechnic Institute, USA) Additional Information ---------------------- General questions concerning the workshop should be addressed to nesy at soi.city.ac.uk Workshop website: http://www.aifb.uni-karlsruhe.de/WBS/phi/NeSy05/ -- Dr. Pascal Hitzler Institute AIFB, University of Karlsruhe, 76128 Karlsruhe email: hitzler at aifb.uni-karlsruhe.de phone: +49 721 608 4751 web: www.aifb.uni-karlsruhe.de/WBS/phi fax: +49 721 608 6580 From jf218 at hermes.cam.ac.uk Thu Jan 13 12:56:11 2005 From: jf218 at hermes.cam.ac.uk (Dr J. Feng) Date: Thu, 13 Jan 2005 17:56:11 +0000 (GMT) Subject: Call for papers: Networks, from biology to theory Message-ID: International Conference on Networks: from Biology to Theory CALL FOR PAPERS During the past decades, we have witnessed the thriving development of new mathematical, computational and theoretical approaches such as bioinformatics and neuroinformatics to tackle some fundamental issues in biology. These scientific approaches focus no longer on the individual units, like nerve cells or genes, but rather on the emerging dynamic patterns of interactions between them. This depends on the interplay between the local dynamics and activity transmissions on one side and the global structure of the underlying connection scheme on the other hand. From these questions, the concept of a network emerges as a powerful and stimulating research paradigm in mathematics, physics and computer science, with a very lively interaction between experimental findings, simulation studies, and theoretical investigations that then in turn lead to new experimental questions. In particular, since researchers in molecular cell biology and neurobiology share an interest in network theory and, conversely, can stimulate further theoretical research on networks, we want to promote this development, and bring together expertises from both experimentalists and theoreticians working on networks at a meeting in Beijing (Sino-German Centre). Such a meeting will provide an inclusive forum for the exchange of ideas for scientists from China, Germany and elsewhere. The meeting is expected to draw about 100 researches (around 30 invited) from the whole range of disciplines mentioned above, molecular cell biology, neurobiology, systems biology, mathematics, physics, computing science. The meeting topics include but are not limited to Networks in neuroinformatics: Population coding, computation with spiking networks, multi-unit recording, human-machine interfaces, synchronization in spiking neuronal networks. Networks in bioinformatics: Gene regulatory and signal transduction networks, protein-protein interaction networks, microarray data, metabolic networks. Network structures and dynamics: Random graphs and other paradigms, synchronization and desynchronization mechanisms, coupled oscillators, dynamics on multiple scales. FORMAT The single-track meeting will consist of both oral and poster sessions. Some oral presentations will be invited, while others will be drawn from short submitted abstracts. Poster presentations will be drawn from submitted abstracts. We expect we are able to provide meals, and ample time will be provided for informal discussion outside of the sessions. To actually provide an inclusive forum for the exchange of ideas between experimentalists and theoreticians, the structure of the conference will be: 2 days networks in molecular biology, 1 day formal methods, 2 days networks in neurobiology. Thus, the theoretical day in the middle will link the two different fields of applications ORGANIZING COMMITTEE Jianfeng Feng (Warwick Univ., UK, and Hunan Normal Univ., PR China), Juergen Jost (Max Planck Institute for Mathematics in the Sciences, Leipzig, Germany), Minping Qian (Peking University, PR China) SPEAKERS Around 30 speakers will be invited (half theoreticians and half experimentalists). And the rest wil be selected from submitted abstracts. LOCATION Sino-German Centre, Beijing. WHEN April 4th--8th , 2005. REGISTRATION INFORMATION: Registration is free. CONFERENCE GRANTS: SinoGerman Centre ABSTRACTS Abstracts are due by Feb. 15, 2005. Decisions will be made by Feb. 31, 2005. Abstracts should be 1-2 pages. OTHER INFORMATION http://www.informatics.sussex.ac.uk/users/jianfeng/sino-german/sino-german.html ------------------------------------------------------------------------------ Address after 1st Jan. 2005 Prof. Jianfeng Feng Centre for Scientific Computing Warwick University Coventry CV4 7AL UK http://www.cus.cam.ac.uk/~jf218 From cns at www.cnsorg.org Fri Jan 14 21:23:01 2005 From: cns at www.cnsorg.org (CNS) Date: Fri, 14 Jan 2005 19:23:01 -0700 Subject: Submission for CNS 2005 open! Message-ID: <20050115022131.M84413@www.cnsorg.org> SUBMISSIONS FOR CNS 2005 now open! __________________________________ CALL FOR PAPERS, CNS*2005: SUBMISSION DEADLINE: February 1, 2005 midnight Submissions open: January 15th, 2005 to submit a paper, go to www.cns2005.confmaster.net where you can either register as a new author or log in as a registered user and then follow the submission instructions. Submissions to the meeting will take the form of a 3-page summary describing the nature and scope of the work, and outlining the main results (must be submitted as a PDF file). These summaries will be reviewed by the program committee and used to determine acceptance for presentation at the meeting as well as to construct the scientific program. Authors will also be asked to submit a standard abstract for printing in the program book (200 words). All submissions will be acknowledged by email. Authors will be asked to state their preference as to the type of presentation they would like to give (oral, featured talk or poster presentation). Please note that only a small percentage of submissions can be included in the oral program every year (see details below). Only 2-4 papers are chosen for featured talks each year. Authors which indicate a preference for a featured talk MUST include a short, single paragraph explanation (at the beginning of their extended summary) as to why their contribution is particularly suited for a featured talk. -- CNS - Organization for Computational Neurosciences From skremer at kremer.ca Mon Jan 17 00:14:18 2005 From: skremer at kremer.ca (Stefan C. Kremer) Date: Mon, 17 Jan 2005 00:14:18 -0500 Subject: CALL FOR CONTRIBUTIONS: Correlation Learning Workshop Message-ID: << Apologies for multiple copies of this message >> ********************************************************************* FIRST CALL FOR CONTRIBUTIONS Correlation Learning Workshop The Eighteenth Canadian Conference on Artificial Intelligence University of Victoria, Victoria, British Columbia May 8th, 2005 Workshop Website: http://www.kremer.ca/CorrelationLearning A.I. '05 Website: http://www.iro.umontreal.ca/~ai05 The Correlation Learning Workshop invites participants to present original work in in Correlation Learning, defined as follows. Correlative learning is a paradigm for adaptive behaviour which uses correlations between neuronal activations, oscillations and/or changes in system energy to effect synaptic plasticity. Correlative learning has a long history in biological models of neoronal computation, and has recently garnered an increased amount of interest in the field of machine learning. The AI'05 Correlation Workshop is the opportunity for you to share, discuss and further develop ideas and techniques in correlative learning. It will bring together research from the biological community that focusses on explaining biological learning and combine it with correlative learning approaches from the machine learning community that focus on effectiveness for pattern recognition problems. Prospective participants are invited to submit a 2-page summary of a proposed 30 minute presentation by February 18th. Accepted speakers will be invited to give their presentation, participate in the workshop discussions and contribute an article for consideration in a special issue of the new, on-line (open access) journal: Canadian Journal of Natural Computation (ISSN 1703-7115). Proposals will be reviewed by the workshop organizers and judged according to their originality, technical merit and clarity of presentation. Proposal Submission: Authors are invited to submit proposals in plain text, PDF, Postscript, or MS-Word RTF via e-mail to skremer at uoguelph.ca. All e-mails must have a subject header of "AI2005 Workshop Submission" to be considered. Important Dates: Proposal submission due: February 18th, 2005 Notification of acceptance: February 28th, 2005 Workshop Date: May 8th,2005 Proposed CJNC Special Issue Publication Date: Fall, 2005 -- Dr. Stefan C. Kremer, Associate Prof., Reynolds Building, 106, Dept. of Computing & Info. Science University of Guelph, Guelph, Ontario N1G 2W1 Tel: (519)824-4120 Ext.58913 E-mail: skremer at uoguelph.ca Fax: (519)837-0323 WWW: http://q.cis.uoguelph.ca/~skremer From auke.ijspeert at epfl.ch Sun Jan 16 07:56:34 2005 From: auke.ijspeert at epfl.ch (Auke Ijspeert) Date: Sun, 16 Jan 2005 13:56:34 +0100 Subject: CFP: AMAM2005 Adaptive Motion in Animals and Machines Message-ID: <41EA6482.6080601@epfl.ch> Dear Connectionists, Researchers working on any aspect related to the adaptive control of movement and locomotion in animals and robots, might be interested in AMAM2005, the Third International Symposium on Adaptive Motion in Animals and Machines (see the CFP below). The two previous symposia in Montreal and Kyoto, which brought together researchers in neurobiology, biomechanics, neural computation, and robotics, were very exciting and fruitful events Best regards, Auke Ijspeert ****************Announcement and First Call for Papers**************** 3rd International Symposium on Adaptive Motion in Animals and Machines AMAM 2005 will take place at Technische Universit=E4t Ilmenau, Germany, September 25th - September 30th, 2005. Deadline for abstract submission: February 28^th , 2005. Please find details and the first Call for Papers at: http://www.tu-ilmenau.de/amam On behalf of the International Organizing Committee under the guidance of Prof. Kazuo Tsuchiya (Kyoto, Japan), it is our pleasure to cordially invite you to take part in this symposium. It is our dream to understand principles of animals' surprising abilities in adaptive motion and to transfer such abilities on a robot. However, principles of adaptation to various environments have not yet been clarified, and autonomous adaptation is left unsolved as a seriously difficult problem in robotics. Apparently, the adaptation ability shown by animals and needed by robots in a real world can not be explained or realized by one single function in the control system. That is, adaptation is induced at multiple levels in a wide spectrum from the central neural system to the musculo-skeletal system. We are organizing AMAM 2005 for scientists and engineers concerned with adaptation on various levels to be brought in contact, to discuss principles on each level and to investigate principles governing total systems. Some topics of particular interest to guide prospective contributors are: * Visual Adaptation Mechanisms of Systems in Locomotion * Sensory-Motor Coordination in Locomotion * Neuro-Mechanics * Locomotion of Animals * Behaviour (Locomotion and Idiomotion) of Mammals, esp. Primates, esp. Humans and Humanoids * Embodied Intelligence in Locomotion * Non-linear Dynamics in Locomotion * Adaptive Mechanics * Modeling and Analysis of Motion * Prostheses, Ortheses and Rehabilitation * Evolution of Adaptive Motion (Phylogenesis) * Ontogenesis of Adaptive Motion (from Learning to De-learning, Development and Ageing) * Technical Development of Mechanism and Control for Adaptive Motion Prof. H. Kimura, Tokyo (Japan) Prof. A.J. Ijspeert, Lausanne (Switzerland) Prof. Hartmut Witte, Ilmenau (Germany) ************************************************************************* From nello at wald.ucdavis.edu Sun Jan 16 14:52:23 2005 From: nello at wald.ucdavis.edu (Nello Cristianini) Date: Sun, 16 Jan 2005 11:52:23 -0800 (PST) Subject: School / The Analysis of Patterns / oct-nov 2005 Message-ID: <20050116114744.C47402-100000@anson.ucdavis.edu> International School "Eduardo R. Caianiello" and Workshop of the PASCAL Network of Excellence The Analysis of Patterns Centre "Ettore Majorana" for Scientific Culture, Erice, Italy October 28 - November 6, 2005 (Course days: Saturday, October 29 - Saturday, November 5th) http://www.analysis-of-patterns.net/ Automatic pattern analysis of data is a pillar of modern science, technology and business, with deep roots in statistics, machine learning, pattern recognition, theoretical computer science, and many other fields. A unified conceptual understanding of this strategic field is of great importance for researchers as well as for users of this technology. This workshop / course will emphasize the common principles and roots of modern pattern analysis technology, developed independently by many different scientific communities over the past 30 years, and their impact on modern science and technology. Students and researchers from many disciplines dealing with automatic pattern analysis form the intended audience. These include (but are not limited to) statistics, pattern recognition, data mining, machine learning, information theory, sequence analysis, bioinformatics, adaptive systems, etc The school will cover both the conceptual foundations of pattern theory as well as the technological aspects related to pattern-driven data analysis. Directors of the Course: Nello Cristianini, University of California, Davis, USA Raffaele Cerulli, Universita' di Salerno, Italy John Shawe-Taylor, University of Southampton, UK Director of the School "Eduardo Caianiello": Maria Marinaro, Universita' di Salerno, Italy From workshops at www.cnsorg.org Mon Jan 17 06:30:49 2005 From: workshops at www.cnsorg.org (Boris Gutkin) Date: Mon, 17 Jan 2005 03:30:49 -0800 Subject: CNS*05 WORKSHOPS CALL FOR PROPOSALS Message-ID: <20050117113056.M30381@www.cnsorg.org> CALL FOR PROPOSALS: CNS*2005 Workshops/Symposia 20-21 July 2005 University of Wisconsin, Madison, USA. The final two days of the CNS*2005 meeting will be devoted to workshops focusing on current issues in computational neuroscience. This year we are also considering integrating outstanding workshop proposals of general interest into the main oral program as 2 hour symposia. Workshops may take the form of 1 or 2 day mini-symposia and tutorials, in addition to the traditional informal discussions. These more formal workshops will provide an excellent opportunity for short, focused meetings on topics of particular current interest. Individual organizers are largely free to define the format and content of their workshops, provided that adequate time is reserved for discussion. The organizers of a workshop should endeavor to bring together as broad a range of pertinent viewpoints as possible. Those interested in organizing a mini-symposium or tutorial are encouraged to contact the workshops organizer, Boris Gutkin at workshops at cnsorg.org as soon as possible. Detailed instructions for submitting a workshop proposal can be found at: www.cnsorg.org Descriptions of new workshops will be added as they are accepted. Information on the CNS*2005 meeting can be obtained from the CNS Website: www.cnsorg.org From bogus@does.not.exist.com Mon Jan 17 12:51:46 2005 From: bogus@does.not.exist.com () Date: Mon, 17 Jan 2005 17:51:46 -0000 Subject: Internships for PhD students at Microsoft Research Cambridge Message-ID: From arobert at med.cornell.edu Thu Jan 20 18:04:14 2005 From: arobert at med.cornell.edu (Adrian Robert) Date: Thu, 20 Jan 2005 18:04:14 -0500 Subject: Postdoctoral position Message-ID: <9A9E4CA8-6B37-11D9-97B1-000D93B19E46@med.cornell.edu> Neuroinformatics Research Associate The Laboratory of Neuroinformatics at Cornell University's Weill Medical College in New York City seeks researchers at the post-doc level or above to join a team developing an integrated suite of analytic algorithms, parallel computational resources, databases, tools, and standards for data and algorithm description and exchange. Successful candidates will have a background in computational neuroscience or bioinformatics, and combine the ability to work in a team setting with creativity and initiative. They should have experience with one or more of: database design, Java web applications, and XML. We provide generous salary and benefits, the excitement of life in New York, and the opportunity to work with a dedicated group of neuroinformatic developers and neurophysiologists, including Daniel Gardner, Jonathan D. Victor, and distinguished collaborators in neural data acquisition, analysis, and algorithm development. See http://neurodatabase.org and http://brainml.org for further information. If interestest, please email CV, cover letter, and the names of three references to: dan at med.cornell.edu. ------------------------- Adrian Robert, Ph.D. Weill Medical College of Cornell University 1300 York Avenue D-404 Physiology and Biophysics New York, NY 10021 (212) 746-0462 From oza at email.arc.nasa.gov Thu Jan 20 18:42:05 2005 From: oza at email.arc.nasa.gov (Nikunj C. Oza) Date: Thu, 20 Jan 2005 15:42:05 -0800 Subject: CFP: Multiple Classifier Systems workshop Message-ID: **Apologies for multiple copies** NOTE: PAPER DEADLINE EXTENDED BY ONE WEEK TO JANUARY 28, 2005. ****************************************** *****MCS 2005 Call for Papers***** ****************************************** *****Paper Submission: 28th JANUARY 2005***** ********************************************************************** SIXTH INTERNATIONAL WORKSHOP ON MULTIPLE CLASSIFIER SYSTEMS Embassy Suites on Monterey Bay, Seaside, California, USA, June 13-15, 2005 Updated information: http://www.diee.unica.it/mcs E-mail: oza at email.arc.nasa.gov (Nikunj Oza) or polikar at rowan.edu (Robi Polikar) ********************************************************************* WORKSHOP OBJECTIVES MCS 2005 is the sixth workshop of a series aimed at creating a common international forum for researchers of the diverse communities working in the field of multiple classifier systems. Information on the previous editions of MCS workshop can be found on http://www.diee.unica.it/mcs. Contributions from all the research communities working in the field are welcome in order to compare the different approaches and to define the common research priorities. Special attention is also devoted to assess the applications of multiple classifier systems. The papers will be published in the workshop proceedings, and extended versions of selected papers will be considered for publication in a special issue of an international journal. WORKSHOP CHAIRS Nikunj C. Oza (NASA Ames Research Center, USA) Robi Polikar (Rowan University, USA) Josef Kittler (Univ. of Surrey, United Kingdom) Fabio Roli (Univ. of Cagliari, Italy) ORGANIZED BY NASA Ames Research Center Department of Electrical and Computer Engineering, Rowan University Puresense Environmental Sponsored by IAPR TC1 Statistical Pattern Recognition Techniques PAPER SUBMISSION Participants should submit an electronic version of the manuscript (PostScript or PDF format) to polikar at rowan.edu. The papers should not exceed 10 pages (LNCS format, see http://www.springer.de/comp/lncs/authors.html). A cover sheet with the authors names and affiliations is also requested, with the complete address of the corresponding author, and an abstract (200 words). Two members of the Scientific Committee will referee the papers. IMPORTANT NOTICE: Submission implies the willingness of at least one author to register, attend the workshop, and present the paper. Accepted papers will be published in the proceedings only if the registration form and payment for one of the authors is received. WORKSHOP TOPICS Papers describing original work in the following and related research topics are welcome: Foundations of multiple classifier systems Methods for classifier fusion Design of multiple classifier systems Neural network ensembles Bagging and boosting Mixtures of experts New and related approaches Applications INVITED SPEAKERS Leo Breiman (USA) Second speaker to be determined (see http://www.diee.unica.it/mcs for updates) SCIENTIFIC COMMITTEE J. A. Benediktsson (Iceland) H. Bunke (Switzerland) L. P. Cordella (Italy) B. V. Dasarathy (USA) R. P.W. Duin (The Netherlands) C. Furlanello (Italy) J. Ghosh (USA) V. Govindaraju (USA) T. K. Ho (USA) S. Impedovo (Italy) N. Intrator (Israel) A.K. Jain (USA) M. Kamel (Canada) L.I. Kuncheva (UK) D. Partridge (UK) A.J.C. Sharkey (UK) C.Y. Suen (Canada) K. Tumer (USA) G. Vernazza (Italy) T. Windeatt (UK) IMPORTANT DATES January 28, 2004: Paper Submission February 25, 2004: Notification of Acceptance March 25, 2004: Camera-ready Manuscript March 25, 2004: Registration WORKSHOP VENUE The workshop will be held at the Embassy Suites on Monterey Bay, Seaside, California, USA (http://www.embassymonterey.com). WORKSHOP PROCEEDINGS Accepted papers will appear in the workshop proceedings that will be published in the series Lecture Notes in Computer Science by Springer-Verlag. Extended versions of selected papers will considered for possible publication in a special issue of an international journal. -- -------------------------------------- Nikunj C. Oza, Ph.D. Tel: (650)604-2978 Research Scientist Fax: (650)604-4036 NASA Ames Research Center e-mail: oza at email.arc.nasa.gov Mail Stop 269-3 web: http://ic.arc.nasa.gov/~oza Moffett Field, CA 94035-1000 From F.AlmeidaCosta at sussex.ac.uk Tue Jan 11 15:28:21 2005 From: F.AlmeidaCosta at sussex.ac.uk (Fernando Almeida e Costa) Date: Tue, 11 Jan 2005 20:28:21 -0000 Subject: Workshop @ Ecal 2005 - Call for papers Message-ID: ********************************************************************* ..........................Call for papers........................... .....................Workshop @ ECAL 2005....................... ......Active Agents and Their Environments as Dynamical Systems..... ................www.ecal2005.org/workshops.html..................... ...........Organized by the activate.d reading group................ .....................University of Sussex........................... ********************************************************************* ECAL2005, in September, will host a workshop on "Active agents and their environments as dynamical systems" organised by the activate.d reading group from the University of Sussex. We are seeking papers within the broad range of the so called dynamical systems approach to life and cognition, from both technical and conceptual/philosophical perspectives. Papers from the workshop will be published in a special issue of the Journal of Adaptive Behavior. You may find detailed information about the workshop in our webpage at www.informatics.sussex.ac.uk/users/eji21/activate.d/workshop at ecal2005 or through the workshop webpage at www.ecal2005.org/workshops.html ******************** PROGRAMME COMMITTEE ******************** Randall Beer, Case Western University. Peter Cariani, Tufts Medical School. Edwin de Jong, Universiteit Utrecht. Ezequiel Di Paolo, University of Sussex. Dario Floreano, Ecole Polytechnique Federale de Lausanne. Inman Harvey, University of Sussex. Phil Husbands, University of Sussex. Takashi Ikegami, University of Tokyo. Scott Kelso, Florida Atlantic University. Luis Mateus Rocha, Indiana University. Tom Ziemke, University of Skovde. ***************** IMPORTANT DATES ***************** Submission deadline: 20th of May Review results: 15th of June Corrected papers due: 22nd of June Papers must be emailed in pdf format to one of the organisers (see addresses below) and will be reviewed by at least two independent reviewers, in compliance with the host conference rules. The work to be submitted may include (but is not limited to) topics such as: * Embodied cognition (the exploitation by a cognitive agent, qua cognitive, of all its physical properties). * Evolution of intrinsic and extrinsic morphologies in artificial agents. * Robotics within the framework of the DSaLC (Dynamical Systems approach to Life and Cognition). * Cognition as brain/body/environment interaction. * Online learning as dynamics occurring at different time scales. * Synthesis of dynamical systems models which exhibit adaptive behaviour. * Self-organisation, selection and neutrality in the evolution of dynamical systems. * Agency, homeostasis and autopoiesis. * The present dangers of the (conscious and unconscious) use of GOFAI principles within a DSaLC framework. * Dynamical systems tools for understanding adaptive behaviour. * Behavioural dynamics of interest to cognitive science (e.g. chaotic itinerancy, globally coupled chaotic systems). * Dynamical systems architectures (i.e. neural networks, cellular automata, other models) and their behavioural dynamics. * Models of dynamical systems coupling. Papers should be sent to either one of the workshop organisers: Fernando Almeida e Costa Eduardo Izquierdo-Torres F.AlmeidaCosta at sussex.ac.uk E.J.Izquierdo-Torres at sussex.ac.uk You may find more information about the activate.d reading group at www.informatics.sussex.ac.uk/users/eji21/activate.d -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: callpapers1.txt Url: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/00000000/c5dfa516/callpapers1-0001.txt From terry at salk.edu Fri Jan 21 17:41:47 2005 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 21 Jan 2005 14:41:47 -0800 (PST) Subject: NEURAL COMPUTATION 17:1 In-Reply-To: <200411160058.iAG0woq64269@kepler.snl.salk.edu> Message-ID: <200501212241.j0LMfl461361@kepler.snl.salk.edu> Neural Computation - Contents - Volume 17, Number 1 - January 1, 2005 NOTES How To Pretend That Correlated Variables Are Independent by Using Difference Observations Christopher K. I. Williams Convergence of the IRWLS Procedure to the Support Vector Machine Solution Fernando Perez-Cruz, Carlos Bousono-Calzon, Chih-Jen Lin, and Antonio Artes-Rodriguez LETTERS Efficient Coding of Time-Relative Structure Using Spikes Evan Smith and Michael. S. Lewicki Bilinear Sparse Coding for Invariant Vision David B. Grimes and Rajesh P. N. Rao A Probabilistic Framework for Region-Specific Remodeling of Dendrites in Three-Dimensional Neuronal Reconstructions Rishikesh Narayanan, Anusha Narayan and Sumantra Chattarji Analysis of Cyclic Dynamics for Networks of Linear Threshold Neurons H. J. Tang, K. C. Tan, and Weinian Zhang Nonlinear and Noisy Extension of Independent Component Analysis: Theory and Its Application to a Pitch Sensation Model Shin-ichi Maeda, Wen-Jie Song and Shin Ishii Online Ranking by Projecting Koby Crammer and Yoram Singer On Learning Vector-Valued Functions Charles A. Micchelli and Massimiliano Pontil RSPOP : Rough Set-Based Pseudo Outer-Product Fuzzy Rule Identification Algorithm Kai Keng Ang and Chai Quek ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2005 - VOLUME 17 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $64.20 $114 $54 $57.78 Individual $100 $107.00 $143 $90 $96.30 Institution $680 $727.60 $734 $612 $654.84 * includes 7% GST MIT Press Journals, 5 Cambridge Center, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu ----- From dekamps at t-online.de Sat Jan 22 16:41:51 2005 From: dekamps at t-online.de (Marc de Kamps) Date: Sat, 22 Jan 2005 22:41:51 +0100 Subject: CFP: ICANN2005 Message-ID: International Conference on Artificial Neural Networks 11-15 September 2005 Warsaw, Poland ICANN 2005 Preliminary Call for Papers The 15th International Conference on Artificial Neural Networks, ICANN 2005, will be held from September 11 to September 14, 2005, at the Gromada Hotel Conference Center, near the airport in Warsaw, Poland. ICANN is an annual meeting organized by the European Neural Network Society in cooperation with the International Neural Network Society, Japanese Neural Network Society, and the IEEE Computational Intelligence Society, and is a premier European event in all topics related to the neural networks. ICANN 2005 welcomes contributions on the theory, algorithms, applications and implementations in the following broad areas: * Computational neuroscience; * Connectionist cognitive science; * Data analysis and pattern recognition; * Graphical networks models, Bayesian networks; * Hardware implementations and embedded systems; * Neural and hybrid architectures and learning algorithms; * Neural control, reinforcement learning and robotics applications; * Neuroinformatics; * Neural dynamics and complex systems; * Real world applications; * Robotics, control, planning; * Signal and time series processing; * Self-organization; * Vision and image processing. Professor Teuvo Kohonen is Honorary Chairman of ICANN 2005. We are pleased to announce the following plenary speakers, whose talks will cover various topics in neuroscience, neural theory and applications: * Christopher Bishop (Microsoft, Cambridge, UK) * Hojjat Adeli (Columbus, OH, USA) * John Taylor (King's College London, UK) * John Shawe-Taylor (Southampton, UK) * Juergen Schmidhuber (Lugano, Switzerland) * Misha Tsodyks (Weizmann Institute, Israel) * Rolf Ktter (Dsseldorf, Germany) * Stephen H. Koslow (NIH, USA) Ideas and nominations for interesting tutorials, special sessions, workshops and experts willing to organize various session tracks are called for. Most active experts will be included in the scientific committee of the conference. Each special session should have at least 5 presentations and a conference track about twice as many. Special session chairs will be responsible for all aspects of their sessions, including soliciting, reviewing, and selecting the papers. To ensure quality of the papers the program committee of ICANN 2005 will provide final review and approval for all sessions. Proposals to organize special sessions/tracks/workshops should include: the title and form of the proposed session (track/special session/workshop); name, affiliation, mailing address and e-mail address of the proposer(s); description of the topic of the session, not exceeding 100 words, or 1000 words for tutorials. Proceedings of ICANN will be published in Springer's "Lecture Notes in Computer Science". Paper length is restricted to a maximum of 6 pages, including figures. Instructions for authors are given here . The deadlines and conference dates are: 6.01 Submission page opens 28.02 End of submission of papers to regular sessions 30.03 End of submission of papers to special sessions 30.04 Acceptance/rejection notification 15.06 Deadline for camera ready papers 1.07 Deadline for early registration 11.09 Tutorials - first day of the conference 12-14.09 The main part of the conference 15.09 Workshops For further information and/or contacts, send inquiries to icann-2005 at ibspan.waw.pl or to the ICANN 2005 Conference Secretariat Mrs. Krystyna Warzywoda Systems Research Institute, Polish Academy of Sciences ul. Newelska 6, 01-447 Warszawa, Poland WWW page: www.ibspan.waw.pl/ICANN-2005 General Program Chairs: Wlodzislaw Duch, Nicholaus Copernicus University, Torun, Poland, and Nanyang Technological University, Singapore Janusz Kacprzyk, System Research Institute, Polish Academy of Sciences, Warsaw, Poland From mtoussai at inf.ed.ac.uk Sun Jan 23 12:15:07 2005 From: mtoussai at inf.ed.ac.uk (Marc Toussaint) Date: Sun, 23 Jan 2005 17:15:07 -0000 Subject: CFP: Theory of Representations Workshop @ GECCO 2005 Message-ID: Call for Papers Workshop on "THEORY OF REPRESENTATIONS" to be held as part of the 2005 Genetic and Evolutionary Computation Conference (GECCO-2005) Washington, D.C., June 25 - 29, 2005 http://homepages.inf.ed.ac.uk/mtoussai/gecco05/index.html organized by: Marc Toussaint, University of Edinburgh, UK (mtoussai at inf.ed.ac.uk) Alden H. Wright, University of Montana, USA (alden.wright at umontana.edu) Edwin D. de Jong, Utrecht University (dejong at cs.uu.nl) The choice of representation crucially determines the performance of a heuristic search process. We believe that there have been very interesting new ideas and approaches on the subject of learning representations recently. However, a unifying point of view is currently missing and the different approaches are widely scattered in the literature with too little cross-fertilization. In this workshop we would like to gather such work and, in a discussion between the contributors from the various lines of research, fuse the various approaches and formalisms into a common framework. This framework might clarify what the scope of a theory of representations should be, what existing algorithms may be considered as cases of representation adaptation, and how the existing literature on the topic can be integrated in a broader picture -- thereby also seeking contact with related areas in Computer Science, Machine Learning and Theoretical Biology. TYPE OF CONTRIBUTIONS: We invite paper submissions on all aspects related to representations. This includes -- Reviews or general discussions of own work, work from a certain line of research, or historical work (e.g. done in theoretical biology) with the aim to contribute to a more integrative picture of what a Theory of Representations should encompass. -- Original, also preliminary, theoretical ideas or experimental studies and propositions of new heuristics when they support or point towards theoretically grounded principles. TOPICS and SUBMISSION INSTRUCTIONS: For details, please see http://homepages.inf.ed.ac.uk/mtoussai/gecco05/index.html IMPORTANT DATES: Electronic Submission Deadline March 14, 2005 Author Notifications Sent April 8, 2005 Camera-Ready Copy Deadline April 22, 2005 Workshop June 25, 2005, 14:00PM-18:00PM From retienne at jhu.edu Wed Jan 26 11:37:08 2005 From: retienne at jhu.edu (retienne) Date: Wed, 26 Jan 2005 11:37:08 -0500 Subject: Announcement: Neuromorphic Engineering Workshop 200 Message-ID: Neuromorphic Engineering Workshop call for applications Sunday, JUNE 26 - Saturday, JULY 16, 2005 TELLURIDE, COLORADO ------------------------------------------------------------------------ Avis COHEN (University of Maryland) Rodney DOUGLAS (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Ralph ETIENNE-CUMMINGS (Johns Hopkins University) Paul HASLER (Georgia Institute of Technology) Timmer HORIUCHI (University of Maryland) Giacomo INDIVERI (Institute of Neuroinformatics, UNI/ETH Zurich, Switzerland) Christof KOCH (California Institute of Technology) Terrence SEJNOWSKI (Salk Institute and UCSD) Shihab SHAMMA (University of Maryland) Andre van SCHAIK (University of Sydney) ------------------------------------------------------------------------ We invite applications for a three week summer workshop that will be held in Telluride, Colorado from Sunday, June 26 to Saturday, July 16, 2005. The application deadline is Friday, March 25 and application instructions are described at the bottom of this document. We must have your completed application, including letters of recommendation, by March 25 for your application to be considered. Last year's 2004 Workshop and Summer School on Neuromorphic Engineering, sponsored by the National Science Foundation, the Institute of Neuromorphic Engineering, the Office of Naval Research, Airforce Research Office, Institute for NeuroInfomatics - ETHZ, Geogia Institute of Technology, University of Maryland - College Park, Johns Hopkins University, The Salk Institute, and by the Center for Neuromorphic Systems Engineering at the California Institute of Technology, was an exciting event and a great success. We strongly encourage interested parties to browse through the: http://www.ini.unizh.ch/telluride/ GOALS: Carver Mead introduced the term "Neuromorphic Engineering" for a new field based on the design and fabrication of artificial neural systems, such as vision systems, head-eye systems, and roving robots, whose architecture and design principles are based on those of biological nervous systems. The goal of this workshop is to bring together young investigators and more established researchers from academia with their counterparts in industry and national laboratories, working on both neurobiological as well as engineering aspects of sensory systems and sensory-motor integration. The focus of the workshop will be on active participation, with demonstration systems and hands on experience for all participants. Neuromorphic engineering has a wide range of applications from nonlinear adaptive control of complex systems to the design of smart sensors. Many of the fundamental principles in this field, such as the use of learning methods and the design of parallel hardware (with an emphasis on analog and asynchronous digital VLSI), are inspired by biological systems. However, existing applications are modest and the challenge of scaling up from small artificial neural networks and designing completely autonomous systems at the levels achieved by biological systems lies ahead. The assumption underlying this three week workshop is that the next generation of neuromorphic systems would benefit from closer attention to the principles found through experimental and theoretical studies of real biological nervous systems as whole systems. FORMAT: The three week summer workshop will include background lectures on systems neuroscience (in particular learning, oculo-motor and other motor systems and attention), practical tutorials on analog VLSI design, small mobile robots (Koalas, Kheperas, LEGO robots), hands-on projects, and special interest groups. Participants are required to take part and possibly complete at least one of the projects proposed. They are furthermore encouraged to become involved in as many of the other activities proposed as interest and time allow. There will be two lectures in the morning that cover issues that are important to the community in general. Because of the diverse range of backgrounds among the participants, the majority of these lectures will be tutorials, rather than detailed reports of current research. These lectures will be given by invited speakers. Participants will be free to explore and play with whatever they choose in the afternoon. Projects and interest groups meet in the late afternoons, and after dinner. In the early afternoon there will be tutorial on a wide spectrum of topics, including analog VLSI, mobile robotics, auditory systems, central-pattern-generators, selective attention mechanisms, etc. Projects that are carried out during the workshop will be centered in a number of working groups, including: * active vision * audition * motor control * central pattern generator * robotics * multichip communication * analog VLSI * learning * neuroprosthethic decives and systems The active perception project group will emphasize vision and human sensory-motor coordination. Issues to be covered will include spatial localization and constancy, attention, motor planning, eye movements, and the use of visual motion information for motor control. The central pattern generator group will focus on small walking and undulating robots. It will look at characteristics and sources of parts for building robots, play with working examples of legged and segmented robots, and discuss CPG's and theories of nonlinear oscillators for locomotion. It will also explore the use of simple analog VLSI sensors for autonomous robots. The robotics group will use rovers and working digital vision boards as well as other possible sensors to investigate issues of sensorimotor integration, navigation and learning. The audition group aims to develop biologically plausible algorithms and aVLSI implementations of specific auditory tasks such as source localization and tracking, and sound pattern recognition. Projects will be integrated with visual and motor tasks in the context of a robot platform. The multichip communication project group will use existing interchip communication interfaces to program small networks of artificial neurons to exhibit particular behaviors such as amplification, oscillation, and associative memory. Issues in multichip communicationwill be discussed. This year we will also have some new robots kindly donated by the WowWee Toys division of Hasbro in Hong Kong. This will permit us to carry out experiments with WooWee/Hasboro hardware through Mark Tilden. LOCATION AND ARRANGEMENTS: The summer school will take place in the small town of Telluride, 9000 feet high in Southwest Colorado, about 6 hours drive away from Denver (350miles). Great Lakes Aviation and America West Express airlines provide daily flights directly into Telluride. All facilities within the beautifully renovated public school building are fully accessible to participants with disabilities. Participants will be housed in ski condominiums, within walking distance of the school. Participants are expected to share condominiums. The workshop is intended to be very informal and hands-on. Participants are not required to have had previous experience in analog VLSI circuit design, computational or machine vision, systems level neurophysiology or modeling the brain at the systems level. However, we strongly encourage active researchers with relevant backgrounds from academia, industry and national laboratories to apply, in particular if they are prepared to work on specific projects, talk about their own work or bring demonstrations to Telluride (e.g. robots, chips, software). Internet access will be provided. Technical staff present throughout the workshops will assist with software and hardware issues. We will have a network of PCs running LINUX and Microsoft Windows for the workshop projects. We also plan to provide wireless internet access and encourage participants to bring along their personal laptop. No cars are required. Given the small size of the town, we recommend that you do not rent a car. Bring hiking boots, warm clothes, rain gear, and a backpack, since Telluride is surrounded by beautiful mountains. Unless otherwise arranged with one of the organizers, we expect participants to stay for the entire duration of this three week workshop. FINANCIAL ARRANGEMENT: Notification of acceptances will be mailed out around mid April 2005. Participants are expected to pay a $295.00 workshop fee at that time in order to reserve a place in the workshop. The cost of a shared condominium will be covered for all academic participants but upgrades to a private room will cost extra. Participants from National Laboratories and Industry are expected to pay for these condominiums. Travel reimbursement of up to $500 for US domestic travel and up to $800 for overseas travel will be possible if financial help is needed (please specify on the application). HOW TO APPLY: Applicants should be at the level of graduate students or above (i.e.postdoctoral fellows, faculty, research and engineering staff and the equivalent positions in industry and national laboratories). We actively encourage qualified women and minority candidates to apply. Application should include: * Cover sheet with: o First name, Last name o Institution and department o Complete mailing address o Valid e-mail address * Curriculum Vitae * One-page summary of background and interests relevant to workshop * Two letters of recommendation Please send your application to: Terrence Sejnowski The Salk Institute -- CNL 10010 N. Torrey Pines Road La Jolla, California 92037 Electronic applications will not be accepted. Questions regarding the application process may be addressed to: telluride at salk.edu -- ---------------------------------------------------------------------------------------- Ralph Etienne-Cummings Associate Professor Department of Electrical and Computer Engineering 105 Barton Hall/3400 N. Charles St. 2213 AV Williams Bldg Johns Hopkins University University of Maryland Baltimore, MD 21218 College Park, MD 20742 Tel: 410 - 516 - 3494 Tel: 301 - 405 - 0470 Fax: 410 - 516 - 5566 Fax: 301 - 314 - 9281 Email: retienne at jhu.edu Email: retienne at isr.umd.edu URL: http://bach.ece.jhu.edu/~etienne URL: http://www.isr.umd.edu/~retienne From S.M.Bohte at cwi.nl Thu Jan 27 11:51:03 2005 From: S.M.Bohte at cwi.nl (Sander Bohte) Date: Thu, 27 Jan 2005 17:51:03 +0100 Subject: CFP: Learning and Adaption in Multi-Agent Systems (LAMAS) @ AAMAS 2005 Message-ID: <41F91BF7.1040302@cwi.nl> **Apologies for multiple copies** ____________________________________________________________ -- CALL FOR PAPERS -- -- Workshop on Learning and Adaptation in Multi-Agent Systems 2005 (LAMAS) -- -- To be held at AAMAS 2005, Utrecht University, the Netherlands -- -- http://lamas2005.luc.ac.be -- ____________________________________________________________ Dear Connectionists, you are invited to submit papers to the 1st Workshop on Learning and Adaption in MAS (LAMAS 2005). LAMAS 2005 will be organized within the fourth International Conference on Autonomous Agents and Multi Agent Systems in Utrecht, the Netherlands. Prospective participants must also register for the AAMAS 2005 conference. The number of participants is strictly limited. The goal of this workshop is to increase awareness and interest in adaptive agent research, encourage collaboration between ML experts and agent system experts, and give a representative overview of current research in the area of adaptive agents. Machine Learning techniques for single agent frameworks are well established. Agents operate in uncertain environments and must be able to learn and act autonomously. This task is however more complex when the agent interacts with other agents with potentially different capabilities and goals. The single agent case is structurally different from the multi agent case due to the added dimension of dynamic interactions between the adaptive agents. Multi-Agent Learning, i.e., the ability of the agents to learn how to co-operate and compete, becomes crucial in many domains. Adaptive Agents and Multi-Agent Systems (AAMAS) is an emerging multi-disciplinary area encompassing Computer Science, Software Engineering, Biology, as well as Cognitive and Social Sciences. A theoretical framework, in which rationality of learning and interacting agents can be understood, is still under development in MASs, although there have been promising first results. We invite contributions that cover on how an agent can learn using ML techniques to act individually, and/or to coordinate with one another towards individual or common goals. This is an open issue in real-time, noisy, collaborative and adversarial environments. We interpret ML techniques in a broad context. These can include the non exhaustive list of Reinforcement Learning, Genetic Algorithms, Neural Networks or Evolutionary Game Theoretic approaches to learning. Also of interest are models for coevolving agent populations. Key-applications, where these techniques can be applied, for example, consist of load balancing problems, traffic management, teamwork, trust, auctions, supply chains, etc. We consider three possible ways in which machine learning can be used to enhance the application of an Agent Based System: 1. An agent can learn the preferences and changing priorities of associated users. 2. An agent can learn about other agents in the environment in order to compete and/or cooperate with them. An agent can learn from other agents, taking advantage of their experiences and incorporating these into its own knowledge base. An agent can also learn almost selfishly and have limited communication with other agents. 3. An agent can learn about other regularities in its environment. We would particularly welcome new insights into these problems from other related disciplines and thus would like to emphasize the inter-disciplinary nature of the workshop. Among others, papers of the following kind are welcome: 1. Evaluation of the effectiveness of individual learning strategies (e.g., case-based, explanation-based, inductive, reinforcement), or multi strategy combinations. 2. Characterization of learning and adaptation methods in terms of modeling power, communication abilities, knowledge requirement, processing abilities of individual agents. For instance through the use of Game Theoretic models. 3. Developing learning and adaptation strategies, or reward structures, for environments with cooperative agents, selfish agents, partially cooperative (will cooperate only if individual goals are not sacrificed) and for environments that can contain mixture of these types of agents. 4. Analyzing convergence properties of existing algorithms and constructing algorithms that guarantee convergence and stability of group behavior. 5. Evaluating effects of knowledge acquisition mechanisms on responsiveness of agents or groups to changes in the agent population in the environment. 6. Learning to work as an effective team by taking advantage of complementary skills and resources. 7. Agents learning via passive or non-intrusive observation of user behaviors or by mimicking other agents. 8. Evolving agent behaviors or co-evolving multiple agents with similar/opposing interests. 9. Investigation of teacher-student relationships between agents or between an agent and the associated user. 10. Applications of learning agents including agents that learn to negotiate contracts, learning trustworthiness of other agents, learn to detect security threats, etc. Those wishing to present should (electronically) submit a full-scale paper, not longer than 16 pages (references and figures included) to Karl Tuyls (karl.tuyls at luc.ac.be) or Katja Verbeeck (kaverbee(at)vub.ac.be). The deadline for submission of contribution is March 14th, 2005. All contributions will be reviewed and in case of acceptance published in the workshop proceedings of the AAMAS'05 conference. Authors should submit full papers electronically in PS or PDF format. In addition, authors should submit an ASCII abstract, with the following information: title of paper; names and affiliations of authors; name, email, snail mail, phone number, and fax number of primary contact; abstract. The same information should be included on the first page of submitted papers. Papers must be written in English, with a maximum length of 16 pages. Please format papers according to the LNCS/LNAI style, a LaTex class is available at http://www.springeronline.com/sgw/cda/frontpage/0,10735,5-164-2-72376-0,00.html All correspondence will be with the specified primary contact. Post proceedings of selected and revised papers are to be published as a Springer Lecture Notes in Artificial Intelligence. ____________________________________________________________ IMPORTANT DATES: Deadline for Submission of Contributions: March 14th, 2005 Notification of Acceptance/Rejection: april 18th, 2005 Camera Ready Copy of Papers: may 15th, 2005 Workshop Date: 25th or 26th of July 2005, precise date to be announced. ____________________________________________________________ Furthermore, if you have any inquiry please do not hesitate to contact the organisers. ____________________________________________________________ Organizing Committee: Karl Tuyls (Primary Contact) karl.tuyls at luc.ac.be LUC Theoretical Computer Science Group Pieter Jan 't Hoen hoen at cwi.nl Evolutionary Systems and Applied Algorithmics Sandip Sen firstName-lastName at utulsa.edu Department of Mathematical and Computer Sciences Katja Verbeeck kaverbee(at)vub.ac.be Computational Modeling Lab ____________________________________________________________ Program Committee: Stephane Airiau, Department of Mathematical & Computer Sciences, The University of Tulsa, USA Bikramjit Banerjee, Department of Computer Science, University of Tulane, USA Ana Lucia Bazzan, Institute of Informatics, Universidade Federal do Rio Grande do Sul, Brazil Sander Bohte, CWI, Evolutionary and Applied Algorithmics group, The Netherlands Michael Goodrich, Department of Computer Science, Brigham Young University, USA Daniel Kudenko, Department of Computer Science, University of York, UK Han La Poutre, CWI, Evolutionary and Applied Algorithmics group, The Netherlands Michael Littman, Rutgers University, Department of Computer Science, USA Peter McBurney, Biocomputing and Computational Biology Group, Liverpool, UK Ann Nowe, Computational Modeling Lab, Vrije Universiteit Brussel, Belgium Simon Parsons, Department of Computer and Information Science, Brooklyn College, New York, USA. Steve Phelps, Biocomputing and Computational Biology Group, Liverpool, UK Jan Ramon, KULeuven, DTAI group, Department of Computer Science, Belgium Peter Stone, Department of Computer Sciences, The University of Texas at Austin, USA Kagan Tumer, NASA Ames Research Lab, USA Danny Weyns, Agentwise research group, KULeuven, Belgium David Wolpert, NASA Ames Research Lab, USA ____________________________________________________________ Looking forward to meeting you all at LAMAS '05 and AAMAS '05. Katja, Karl, Pieter Jan, and Sandip. -- http://lamas2005.luc.ac.be -- From Yann.Guermeur at loria.fr Thu Jan 27 16:43:39 2005 From: Yann.Guermeur at loria.fr (Yann Guermeur) Date: Thu, 27 Jan 2005 22:43:39 +0100 Subject: Post-doc in machine learning at LORIA Message-ID: <41F9608B.1030103@loria.fr> A 18 month post-doctoral position in statistical learning is avaible at the LORIA laboratory http://www.loria.fr/news in Nancy, France. The funding is from the ``Association Franaise contre les Myopathies'' (AFM), in the framework of a joint program between the AFM, the french national center for scientific research (CNRS) and IBM. We are looking for a specialist in kernel methods to apply SVMs to the identification of constitutive and alternative splicing sites in genomic sequences. No background in biology is required. This advertisement will remain valid until a good candidate is found. Contact Yann Guermeur http://www.loria.fr/~guermeur if you have any questions or want to apply. -- Yann Guermeur Tel: (+33) 03 83 59 30 18 LORIA Fax: (+33) 03 83 41 30 79 Campus Scientifique BP 239 54506 Vandoeuvre-les-Nancy Cedex email: Yann.Guermeur at loria.fr FRANCE http://www.loria.fr/~guermeur From dprokhor at ford.com Thu Jan 27 11:36:07 2005 From: dprokhor at ford.com (Prokhorov, Danil (D.V.)) Date: Thu, 27 Jan 2005 11:36:07 -0500 Subject: IJCNN 2005: final call for papers Message-ID: <9B732918BB49A14184A8EF541377CB4C02D7E66B@na1ecm58.dearborn.ford.com> Apologies for multiple postings! IJCNN 2005: FINAL CALL FOR PAPERS, DEADLINE IS JANUARY 31, 2005! Dear Colleagues, The submission deadline of January 31 is rapidly approaching for the International Joint Conference on Neural Networks (IJCNN 2005). Cosponsored by INNS and the IEEE Computational Intelligence Society and by several Universities and Ford Motor Company, IJCNN 2005 promises to be a tremendously exciting meeting with a wide range of tutorials, regular and special sessions, and post-conference workshops. Plenary speakers include Pierre Baldi, Mitsuo Kawato, Frank Lewis, Michael Petrides, and Carver Mead. IMPORTANT! Selected regular conference papers will be invited to a Special Issue of the journal Neural Networks, planned for late Summer 2005. These papers must be substantial enhancements of the IJCNN regular submissions, and they will be additionally peer reviewed. Check in to the web site http://www.ijcnn.org/ for further details--including manuscript submission. Montreal is the place to be this July 31-August 5. See you there! Danil Prokhorov IJCNN 2005 General Chair From mpoel at cs.utwente.nl Fri Jan 28 05:54:34 2005 From: mpoel at cs.utwente.nl (Mannes Poel) Date: Fri, 28 Jan 2005 11:54:34 +0100 Subject: Benelearn 2005 - Call for Participation Message-ID: <41FA19EA.2070705@cs.utwente.nl> +++++++++++++++++++++++++++++++++++++++++++++ Please distribute as widely as possible. Apologies for crossposting. +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Call for Participation Benelearn 2005 Annual Machine Learning Conference of Belgium and the Netherlands http://hmi.ewi.utwente.nl/conference/benelearn2005 Februari 17 - 18, 2005 University of Twente, Enschede, The Netherlands Early Registration deadline: Februari 1st With support from NWO, SIKS, CTIT and Senter-IOP +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Benelearn is the annual machine learning conference of Belgium and the Netherlands. It serves as a forum to exchange ideas and present recent work. Technical Program includes: 2 invited talks: - Probabilistic Logic Learning and Reasoning by K. Kersting (Machine Learning Lab, University of Freiburg, Germany) - Challenges in Multimodal Processing by S. Bengio (IDIAP, Martigny, Switserland) ---------------------------- List of accepted papers: Amplifying the Block Matrix Structure for Spectral Clustering Igor Fischer and Jan Poland Saarland University, Germany IDSIA, Manno (Lugano), Switzerland Evolving Neural Networks for Forest Fire Control Marco Wiering, Filippo Mignogna and Bernard Maassen Utrecht University, The Netherlands Experiments with Relational Neural Networks Werner Uwents and Hendrik Blockeel Catholic University of Leuven, Belgium Assessment of SVM Reliability for Microarrays Data Analysis Andrea Malossini, Enrico Blanzieri and Raymond T. Ng University of Trento, Italy University of British Columbia, Canada Speaker Prediction based on Head Orientations Rutger Rienks, Ronald Poppe and Mannes Poel University of Twente, The Netherlands Strong Asymptotic Assertions for Discrete MDL in Regression and Classification Jan Poland and Marcus Hutter IDSIA, Manno (Lugano), Switzerland Detecting Deviation in Multinomially Distributed Data Jan Peter Patist Vrije Universiteit Amsterdam, The Netherlands Monotone Constraints in Frequent Tree Mining Jeroen De Knijf and Ad Feelders Utrecht University, The Netherlands Best-Response Play in Partially Observable Card Games Frans Oliehoek, Matthijs Spaan and Nikos Vlassis University of Amsterdam, The Netherlands Master Algorithms for Active Experts Problems based on Increasing Loss Values Jan Poland and Marcus Hutter IDSIA, Manno (Lugano), Switzerland Maximizing Expected Utility in Coevolutionary Search Edwin de Jong Utrecht University, The Netherlands Reliability yields Information Gain Ida Sprinkhuizen-Kuyper, Evgueni Smirnov and Georgi Nalbantov University of Maastricht, The Netherlands Erasmus University Rotterdam, The Netherlands Facial Expression Analysis using Multi-layer Perceptrons Michal Sindlar and Marco Wiering Utrecht University, The Netherlands Reinforcement Learning using Optimistic Process Filtered Models Funlade Sunmola and Jeremy Wyatt University of Birmingham, United Kingdom ---------------------------- The registration form and further information can be found at the conference website: http://hmi.ewi.utwente.nl/conference/benelearn2005 The Organizing Comittee: Martijn van Otterlo (University of Twente, the Netherlands) Mannes Poel (University of Twente, the Netherlands) Anton Nijholt (University of Twente, the Netherlands) Sponsors: Netherlands Organisation for Scientific Research (NWO) http://www.nwo.nl Dutch research school for Information and Knowledge Systems (SIKS) http://www.siks.nl/ Centre for Telematics and Information Technology (CTIT) SRO NICE. http://www.ctit.utwente.nl/research/sro/nice/index.html Senter-IOP http://www.senter.nl/asp/page.asp?alias=iop From stricker at ipk-gatersleben.de Fri Jan 28 06:58:10 2005 From: stricker at ipk-gatersleben.de (Marc Strickert) Date: Fri, 28 Jan 2005 12:58:10 +0100 Subject: Thesis on LVQ and SOM for sequences online available Message-ID: <41FA28D2.3040901@ipk-gatersleben.de> Please find the PhD thesis "Self-Organizing Neural Networks for Sequence Processing" by Marc Strickert, Department of Mathematics and Computer Science, University of Osnabr?ck, Germany, 2004 in the internet: Thesis.pdf Size: 1.58 MBytes http://elib.ub.uni-osnabrueck.de/publications/diss/E-Diss384_thesis.pdf Supervisors: Prof. Dr. Barbara Hammer, Prof. Dr. Helge Ritter Abstract: This work investigates the self-organizing representation of temporal data in prototype-based neural networks. Extensions of the supervised learning vector quantization (LVQ) and the unsupervised self-organizing map (SOM) are considered in detail. For LVQ learning, adaptive metrics are studied with a particular focus on the built-in detection of data attributes involved for a given classifcation task; generalized relevance LVQ (GRLVQ) and supervised relevance neural gas with general metrics (SRNGGM) are discussed. For unsupervised sequence processing, two modifcations of SOM are pursued: the SOM for structured data (SOMSD) realizing an efficient back- reference to the previous best matching neuron in a triangular low-dimensional neural lattice, and the merge SOM (MSOM) expressing the temporal context as a fractal combination of the previously most active neuron and its context. The first SOMSD extension tackles data dimension reduction and planar visualization, the second MSOM is designed for obtaining higher quantization accuracy. The supplied experiments underline the high data modeling quality of the presented methods. Keywords: vector quantization, self-organization, relevance learning, classification, clustering, sequence processing, context, fractal representation, GRLVQ, SRNG, MSOM. From the table of contents 1 Introduction 2 2 Data preprocessing for temporal networks I Supervised LVQ-type learning 3 Learning Vector Quantization (LVQ) 4 LVQ with cost function Generalized Relevance LVQ (GRLVQ) Supervised Relevance Neural Gas (SRNG) 5 BB-Tree: Rules from trained GRLVQ or SRNG networks 6 Experiments: Mushroom data, Hypothyroid data, Speaker identifcation, DNA splice site recognition II Unsupervised SOM-type learning 7 Self-Organizing Maps (SOM) 8 SOMSD with lattice topology and alternative lattices 9 Experiments: Mackey-Glass time series, Binary automata, Reber grammar 10 Merge SOM (MSOM) with data topology 11 Experiments: Mackey-Glass time series, Binary automata, Reber grammar, Speaker identifcation by a posteriori MSOM labeling III Discussion and Outlook 107 -- ____ Marc Strickert ____ http://pgrc-16.ipk-gatersleben.de/~stricker/ ____ mail: stricker at ipk-gatersleben.de ____ Institute of Plant Genetics and Crop Plant Research (IPK) ____ Pattern Recognition Group (PRG) / Department of Cytogenetics ____ Corrensstr. 3, D-06466 Gatersleben, Germany. (Room A-0.05) ____ Tel./Fax: ++49 (0) 39482 - 5 182 / - 5 137.