From bowlby at bu.edu Tue Jan 2 12:19:02 2007 From: bowlby at bu.edu (Brian Bowlby) Date: Tue, 2 Jan 2007 12:19:02 -0500 Subject: Connectionists: 11th ICCNS: Call for Abstracts and Confirmed Invited Speakers Message-ID: <8BE5105E-B5AA-4591-A36F-37C3C57B7890@bu.edu> Apologies if you receive more than one copy of this message. ELEVENTH INTERNATIONAL CONFERENCE ON COGNITIVE AND NEURAL SYSTEMS May 16 ? 19, 2007 Boston University 677 Beacon Street Boston, Massachusetts 02215 USA http://cns.bu.edu/meetings/ Sponsored by the Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems (http://cns.bu.edu/) with financial support from the National Science Foundation (http://cns.bu.edu/CELEST/) This interdisciplinary conference is attended each year by approximately 300 people from 30 countries around the world. As in previous years, the conference will focus on solutions to the questions: HOW DOES THE BRAIN CONTROL BEHAVIOR? HOW CAN TECHNOLOGY EMULATE BIOLOGICAL INTELLIGENCE? The conference is aimed at researchers and students of computational neuroscience, cognitive science, neural networks, neuromorphic engineering, and artificial intelligence. It includes invited lectures and contributed lectures and posters by experts on the biology and technology of how the brain and other intelligent systems adapt to a changing world. The conference is particularly interested in exploring how the brain and biologically-inspired algorithms and systems in engineering and technology can learn. Single-track oral and poster sessions enable all presented work to be highly visible. Three-hour poster sessions with no conflicting events will be held on two of the conference days. Posters will be up all day, and can also be viewed during breaks in the talk schedule. CONFIRMED INVITED CONFERENCE SPEAKERS Jorge L. Armony (McGill University) Exploring the role of the amygdala in emotional processing Gary Aston-Jones (Medical University of South Carolina) The cortex in context: Locus coeruleus, optimal performance, and maximal utility Nelson Cowan (University of Missouri-Columbia) Differences between long-term, short-term, and working memory Shimon Edelman (Cornell University) Learning language: Rationalists do it by the rules, empiricists do it to the rules James Enns (University of British Columbia ) Unconscious but under control: The role of intention in automated vision and action Michael Graziano (Princeton University) The organization of behavioral repertoire in motor cortex Jennifer Groh (Duke University) Looking at sounds: Neural computations for associating visual and auditory events Stephen Grossberg (Boston University) (Plenary Lecture) An emerging unified theory of cerebral cortex: From vision to cognition Alice Healy (University of Colorado) Training, retention, and transfer of knowledge and skills Marcia K. Johnson (Yale University) Using fMRI to explore components of reflective processing Philip Kellman (UCLA) Abstract relations in perception and perceptual learning Bart Krekelberg (Rutgers University) The neural basis of speed perception Joseph E. LeDoux (New York University) (Plenary Lecture) Fearful brains in an anxious world Hal Pashler (University of California San Diego) Enhancing learning and slowing forgetting: Some elementary (but neglected) questions Luiz Pessoa (Indiana University) Dynamic emotion perception: Neuroimaging studies of visual attention, awareness, and perceptual decisions Pieter Roelfsema (University of Amsterdam) Cortical algorithms for perceptual grouping Deb Roy (Massachusetts Institute of Technology) Meaning machines Reza Shadmehr (Johns Hopkins University) Motor adaptation and the timescales of memory Frank Tong (Vanderbilt University) From brain reading to mind reading: fMRI studies of human visual perception Workshop on Biologically-Inspired Cognitive Architectures Daniel Bullock (Boston University) Modeling neural circuits for reward-guided learning, evaluation, planning, and decision Dario Floreano (Swiss Federal Institute of Technology) Enactive robot vision Deepak Khosla (HRL) Biologically-Inspired Cognitive Architecture for integrated LEarning, Action and Perception (BICA-LEAP) John Laird (University of Michigan) TOSCA: Design and development challenges in brain-based cognitive architecture William Ross (MIT Lincoln Laboratory) Biologically inspired what-where video surveillance systems Patrick Winston (Massachusetts Institute of Technology) Steps toward artificial intelligence CALL FOR ABSTRACTS Session Topics: * vision * object recognition * image understanding * neural circuit models * audition * neural system models * speech and language * mathematics of neural systems * unsupervised learning * robotics * supervised learning * hybrid systems (fuzzy, evolutionary, digital) * reinforcement and emotion * neuromorphic VLSI * sensory-motor control * industrial applications * cognition, planning, and attention * other * spatial mapping and navigation Contributed abstracts must be received, in English, by January 31, 2007. Email notification of acceptance will be provided by February 28, 2007. A meeting registration fee must accompany each Abstract. The fee will be returned if the Abstract is not accepted for presentation. Fees of accepted Abstracts will be returned on request only until April 13, 2007. Each Abstract must fit on one side of an 8.5" x 11" page with 1" margins on all sides in a single-spaced, single-column format with a font of 10 points or larger. The title, authors, affiliations, and surface and email addresses should begin each Abstract. A cover letter should include the abstract title; corresponding author and presenting author name, address, telephone, fax, and email address; requested preference for oral or poster presentation; and a first and second choice from the topics above, including whether it is biological (B) or technological (T) work [Example: first choice: vision (T); second choice: neural system models (B)]. Talks will be 15 minutes long. Posters will be displayed for a full day. Overhead, slide, and LCD computer projector facilities will be available for talks. Accepted Abstracts will be printed in the conference proceedings volume. No extended paper will be required. Four copies of the Abstract should be mailed to Cynthia Bradford, Boston University, CNS Department, 677 Beacon Street, Boston MA 02215 USA. Abstracts may also be submitted electronically as M/S Word files to cindy at bu.edu using the phrase ?11th ICCNS abstract submission? in the subject line. Fax submissions will not be accepted. REGISTRATION INFORMATION: Early registration is recommended using the registration form below. Student registrations must be accompanied by a letter of verification from a department chairperson or faculty/ research advisor. STUDENT TRAVEL FELLOWSHIPS: Fellowships for PhD candidates and postdoctoral fellows who do not live in the Boston area are available to help cover travel costs. The application deadline is January 31, 2007. Email notification will occur by February 28, 2007. Fellowship applications must be submitted as paper hardcopy to the abstract submission address shown above. Each application should include the applicant's CV; faculty or PhD research advisor's name, address, and email address; relevant courses and other educational data; and a list of research articles. A letter from the listed faculty or PhD advisor on institutional stationery must accompany the application and summarize how the candidate may benefit from the meeting. Fellowship applicants who also submit an Abstract need to include the registration fee payment with their Abstract submission. Fellowship checks will be distributed after the meeting. REGISTRATION FORM Eleventh International Conference on Cognitive and Neural Systems May 16-19, 2007 Boston University Department of Cognitive and Neural Systems 677 Beacon Street Boston, Massachusetts 02215 USA Fax: +1 617 353 7755 Mr/Ms/Dr/Prof:_____________________________________________________ Affiliation:_________________________________________________________ Address:__________________________________________________________ City, State, Postal Code:______________________________________________ Phone and Fax:_____________________________________________________ Email:____________________________________________________________ The registration fee includes the conference proceedings, a reception on Friday night, and 3 coffee breaks each day. CHECK ONE: ( ) $95 Conference (Regular) ( ) $65 Conference (Student) METHOD OF PAYMENT (please fax or mail): [ ] Enclosed is a check made payable to "Boston University" Checks must be made payable in US dollars and issued by a US correspondent bank. Each registrant is responsible for any and all bank charges. [ ] I wish to pay by credit card (MasterCard, Visa, or Discover Card only) Name as it appears on the card:___________________________________________ Type of card: _____________________________ Expiration date:________________ Account number: _______________________________________________________ Signature:____________________________________________________________ ? From bowlby at bu.edu Tue Jan 2 11:55:10 2007 From: bowlby at bu.edu (Brian Bowlby) Date: Tue, 2 Jan 2007 11:55:10 -0500 Subject: Connectionists: GRADUATE TRAINING IN THE DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS AT BOSTON UNIVERSITY Message-ID: ************************************************************************ **************************************************** GRADUATE TRAINING IN THE DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS AT BOSTON UNIVERSITY ************************************************************************ **************************************************** The Boston University Department of Cognitive and Neural Systems (CNS) offers comprehensive graduate training in the neural and computational principles, mechanisms, and architectures that underlie human and animal behavior and the application of neural network architectures to the solution of technological problems. CNS is a world leader in computational neuroscience, connectionist cognitive science, and biologically-inspired technology. It has developed a unique interdisciplinary curriculum of seventeen graduate courses with which to train its graduate students. CNS research activities include the major new NSF Center of Excellence for Learning in Education, Science, and Technology (CELEST; http://cns.bu.edu/celest). Applications for Fall 2007 admission and financial aid are now being accepted for PhD, MA, and BA/MA degree programs. For program details, please see the CNS Brochure at: http://cns.bu.edu/brochure Paper applications may be downloaded from: http://www.bu.edu/grs/academics/admissions/index.html Online applications may be submitted via: http://www.bu.edu/link/bin/uiscgi_graduate_application.pl?College=grs Alternatively, you may request materials via email by sending your full name and mailing address to amos at cns.bu.edu; or write, telephone, or fax: Mr. Robin Amos Department of Cognitive and Neural Systems Boston University 677 Beacon Street Boston, MA 02215 617/353-9481 (phone) 617/353-7755 (fax) Applications for admission and financial aid should be received by the Graduate School Admissions Office no later than January 15. Late applications will be considered until May 1; after that date applications will be considered only as special cases. Applicants are required to submit undergraduate (and, if applicable, graduate) transcripts, three letters of recommendation, a personal statement, and Graduate Record Examination (GRE) general test scores. Non-degree students may also enroll in CNS courses on a part-time basis. ************************************************************************ **************************************************** DESCRIPTION OF THE DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS The Department of Cognitive and Neural Systems (CNS) provides advanced training and research experience for graduate students and qualified undergraduates interested in the neural and computational principles, mechanisms, and architectures that underlie human and animal behavior, and the application of neural network architectures to the solution of technological problems. The department?s training and research focus on two broad questions. The first question is: How does the brain control behavior? This is a modern form of the Mind/ Body Problem. The second question is: How can technology emulate biological intelligence? This question needs to be answered to develop intelligent technologies that are well suited to human societies. These goals are symbiotic because brains are unparalleled in their ability to intelligently adapt on their own to complex and novel environments. Models of how the brain accomplishes this are developed through systematic empirical, mathematical, and computational analysis in the department. Autonomous adaptation to a changing world is also needed to solve many of the outstanding problems in technology, and the biological models have inspired qualitatively new designs for applications. CNS is a world leader in developing biological models that can quantitatively simulate the dynamics of identified brain cells in identified neural circuits, and the behaviors that they control. This new level of understanding is producing comparable advances in intelligent technology. CNS is a graduate department that is devoted to the interdisciplinary training of graduate students. The department awards MA, PhD, and BA/ MA degrees. Its students are trained in a broad range of areas concerning computational neuroscience, cognitive science, and neuromorphic systems. The biological training includes study of the brain mechanisms of vision and visual object recognition; audition, speech, and language understanding; recognition learning, categorization, and long-term memory; cognitive information processing; self-organization and development, navigation, planning, and spatial orientation; cooperative and competitive network dynamics and short-term memory; reinforcement and motivation; attention; adaptive sensory-motor planning, control, and robotics; biological rhythms; consciousness; mental disorders; and the mathematical and computational methods needed to support advanced modeling research and applications. Technological training includes methods and applications in image processing, multiple types of signal processing, adaptive pattern recognition and prediction, information fusion, and intelligent control and robotics. The foundation of this broad training is the unique interdisciplinary curriculum of seventeen interdisciplinary graduate courses that have been developed at CNS. Each of these courses integrates the psychological, neurobiological, mathematical, and computational information needed to theoretically investigate fundamental issues concerning mind and brain processes and the applications of artificial neural networks and hybrid systems to technology. A student?s curriculum is tailored to his or her career goals with academic and research advisors. In addition to taking interdisciplinary courses within CNS, students develop important disciplinary expertise by also taking courses in departments such as biology, computer science, engineering, mathematics, and psychology. Also students work individually with one or more research advisors to learn how to carry out advanced interdisciplinary research in their chosen research areas. As a result of this breadth and depth of training, CNS students have succeeded in finding excellent jobs in both academic and technological areas after graduation. The CNS Department interacts with colleagues in several Boston University research centers, and with Boston-area scientists collaborating with these centers. The units most closely linked to the department are the Center for Adaptive Systems, the major new NSF Center of Excellence for Learning in Education, Science, and Technology (CELEST; http://cns.bu.edu/celest) and the CNS Technology Laboratory (http://cns.bu.edu/techlab). Students interested in neural network hardware can work with researchers in CNS and at the College of Engineering. In particular, CNS is part of a major ONR MURI Center for Intelligent Biomimetic Image Processing and Classification that includes colleagues who are developing neuromorphic VLSI chips. Other research resources include the campus-wide Program in Neuroscience, which unites cognitive neuroscience, neurophysiology, neuroanatomy, neuropharmacology, and neural modeling across the Charles River Campus and the School of Medicine; in sensory robotics, biomedical engineering, computer and systems engineering, and neuromuscular research within the College of Engineering; in dynamical systems within the Department of Mathematics; in theoretical computer science within the Department of Computer Science; and in biophysics and computational physics within the Department of Physics. Key colleagues in these units hold joint appointments in CNS in order to expedite training and research interactions with CNS core faculty and students. In addition to its basic research and training program, the department organizes an active colloquium series, various research and seminar series, and international conferences and symposia, to bring distinguished scientists from experimental, theoretical, and technological disciplines to the department. The department is housed in its own four-story building, which includes ample space for faculty and student offices and laboratories (active perception, auditory neuroscience, computer vision and computational neuroscience, sensory-motor control, speech and language, technology and visual psychophysics), as well as an auditorium, classroom, seminar rooms, a library, and a faculty- student lounge. The department has a powerful computer network for carrying out large-scale simulations of behavioral and brain models and applications. FACULTY AND RESEARCH STAFF OF THE DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS AND CENTER FOR ADAPTIVE SYSTEMS Jelle Atema Professor of Biology Director, Boston University Marine Program (BUMP) PhD, University of Michigan Sensory biology, chemical signals, animal behavior, receptor physiology, behavioral ecology, chemical ecology, computational models, robotics http://www.bu.edu/biology/Faculty_Staff/atema.html Helen Barbas Professor, Department of Health Sciences, Sargent College PhD, Physiology/Neurophysiology, McGill University, Canada Organization of the prefrontal cortex, investigation of pathways that transmit signals to prefrontal cortices from structures associated with sensory, cognitive, mnemonic and emotional processes http://www.bu.edu/sargent/people/faculty/barbas_helen.html Virginia Best Research Associate, Department of Cognitive and Neural Systems PhD, Physiology, University of Sydney, Australia Auditory processing in humans, with a focus on spatial hearing, spatial attention and speech perception Daniel H. Bullock Associate Professor of Cognitive and Neural Systems, and Psychology PhD, Experimental Psychology, Stanford University Sensory-motor performance and learning, voluntary control of action, serial order and timing, cognitive development http://cns.bu.edu/Profiles/Bullock.html Yongqiang Cao Senior Research Associate, Department of Cognitive and Neural Systems Ph.D., Applied Mathematics, York University, United Kingdom Brain modeling and biologically inspired computing; 3D vision, pattern recognition and large scale data mining http://www.math.yorku.ca/Who/Grads/yqcao/ Gail A. Carpenter Professor of Cognitive and Neural Systems and Mathematics PhD, Mathematics, University of Wisconsin, Madison Learning and memory, vision, synaptic processes, pattern recognition, remote sensing, medical database analysis, machine learning, differential equations, neural network technology transfer http://cns.bu.edu/~gail/ Michael A. Cohen Associate Professor of Cognitive and Neural Systems and Computer Science PhD, Psychology, Harvard University Speech and language processing, measurement theory, neural modeling, dynamical systems, cardiovascular oscillations physiology and time series http://cns.bu.edu/Profiles/Cohen.html H. Steven Colburn Professor of Biomedical Engineering PhD, Electrical Engineering, Massachusetts Institute of Technology Audition, binaural interaction, auditory virtual environments, signal processing models of hearing http://www.bu.edu/dbin/bme/faculty/?prof=colburn&faculty=12&first=0 Howard Eichenbaum Professor of Psychology Chairman, Department of Psychology Director, Center for Memory and Brain Director, Cognitive Neurobiology Laboratory PhD, Psychology, University of Michigan Neurophysiological studies of how the hippocampal system mediates declarative memory http://www.bu.edu/psych/faculty/eichenbaum/ William D. Eldred III Professor of Biology PhD, University of Colorado, Health Science Center Visual neurobiology and neurochemical signal transduction in the retina http://www.bu.edu/biology/Faculty_Staff/eldred.html Daniel Franklin CELEST Director of Curriculum Development, Cognitive and Neural Systems PhD, Cognitive and Neural Systems, Boston University (pending) MBA, Statistics and Organizational Design, Boston University Learning and memory, development, education; deliver new and enhanced curriculum modules for use by teachers with students of all ages Jean Berko Gleason Professor Emereitus of Psychology PhD, Harvard University Psycholinguistics http://www.bu.edu/psych/faculty/gleason/ Sucharita Gopal Professor of Geography PhD, University of California at Santa Barbara Neural networks, computational modeling of behavior, geographical information systems, fuzzy sets, spatial cognition, multi-scale modeling, and information technology http://www.bu.edu/geography/people/faculty/gopal/ Anatoli Gorchetchnikov Research Associate, Department of Cognitive and Neural Systems PhD, Cognitive and Neural Systems, Boston University Theoretical modeling of spatial navigation in humans and animals with the emphasis on the hippocampal function, create printed educational materials on natural and artificial learning mechanisms Stephen Grossberg Wang Professor of Cognitive and Neural Systems Professor of Mathematics, Psychology, and Biomedical Engineering Chairman, Department of Cognitive and Neural Systems Director, Center for Adaptive Systems Director, Center of Excellence for Learning in Education, Science, and Technology Director, Center for Intelligent Biomimetic Image Processing and Classification PhD, Mathematics, Rockefeller University Vision, audition, language, learning and memory, reward and motivation, cognition, development, sensory-motor control, mental disorders, applications http://cns.bu.edu/Profiles/Grossberg Frank Guenther Associate Professor of Cognitive and Neural Systems PhD, Cognitive and Neural Systems, Boston University MSE, Electrical Engineering, Princeton University Speech production, speech perception, biological sensory-motor control and functional brain imaging http://cns.bu.edu/~guenther/ Catherine L. Harris Associate Professor of Psychology PhD, Cognitive Science and Psychology, University of California at San Diego Visual word recognition, psycholinguistics, cognitive semantics, second language acquisition, computational models of cognition http://www.bu.edu/psych/faculty/charris/ Michael E. Hasselmo Professor of Psychology Director, Graduate Studies, Department of Psychology Director, Computational Neurophysiology Laboratory PhD, Experimental Psychology, Oxford University, United Kingdom Computational modeling and experimental testing of neuromodulatory mechanisms involved in encoding, retrieval and consolidation http://www.bu.edu/psych/faculty/hasselmo/ Allyn Hubbard Professor of Electrical and Computer Engineering PhD, Electrical Engineering, University of Wisconsin VLSI circuit design: digital, analog, subthreshold analog, biCMOS, CMOS; information processing in neurons, neural net chips, synthetic aperture radar (SAR) processing chips, sonar processing chips; auditory models and experiments http://www.bu.edu/dbin/bme/faculty/?prof=aeh Dae-Shik Kim Associate Professor of Anatomy and Neurobiology Director, Center for Biomedical Imaging (CBI) PhD, Neurophysiology, Max-Planck Institute for Brain Research Functional and connectivity mapping of the human visual cortex http://www.bu.edu/dbin/anatneuro/our_people/faculty/kim.php Thomas G. Kincaid Professor of Electrical, Computer and Systems Engineering, College of Engineering PhD, Electrical Engineering, Massachusetts Institute of Technology Signal and image processing, neural networks, non-destructive testing Mark Kon Professor of Mathematics PhD, Massachusetts Institute of Technology Neural network theory, functional analysis, mathematical physics, partial differential equations http://math.bu.edu/people/mkon/s_index.html Norbert Kopco Research Associate, Department of Cognitive and Neural Systems PhD, Cognitive and Neural Systems, Boston University Lecturer, Department of Cybernetics and AI, Technical, University of Kosice, Slovakia Spatial auditory perception; behavioral studies and modeling of speech and non-speech perception in complex environments, auditory localization, plasticity, attention, and crossmodal factors in spatial hearing http://cns.bu.edu/~kopco/ Nancy Kopell Professor of Mathematics PhD, Mathematics, University of California at Berkeley Dynamics of networks of neurons, applied mathematics and dynamical systems http://cbd.bu.edu/members/nkopell.html Jacqueline A. Liederman Professor of Psychology Director, Brain, Behavior and Cognition Program PhD, Psychology, University of Rochester Developmental neuropsychology, neuropsychology, physiological psychology, dynamics of interhemispheric cooperation; prenatal correlates of neurodevelopmental disorders http://www.bu.edu/psych/faculty/liederman/ Ennio Mingolla Professor of Cognitive and Neural Systems and Psychology PhD, Psychology, University of Connecticut Visual perception, mathematical modeling of visual processes http://cns.bu.edu/~ennio/ Geoffrey Stuart Morrison Research Fellow, Department of Cognitive and Neural Systems PhD, Linguistics, University of Alberta, Canada Modeling of first and second language speech perception learning http://cns.bu.edu/~gsm2 Alfonso Nieto-Castanon Research Associate, Department of Cognitive and Neural Systems PhD, Cognitive and Neural Systems, Boston University Speech, statistics, signal processing, computational neuroscience Joseph Perkell Adjunct Professor of Cognitive and Neural Systems Senior Research Scientist, MIT Research Lab of Electronics, Speech Communication Group PhD, Massachusetts Institute of Technology Motor control of speech production http://rleweb.mit.edu/rlestaff/p-perk.htm Marc Pomplun Adjunct Assistant Professor of Cognitive and Neural Systems Assistant Professor of Computer Science, University of Massachusetts, Boston PhD, Computer Science, University of Bielefeld, Germany Eye movements, visual attention, modeling of cognitive processes, human-computer interaction http://www.cs.umb.edu/~marc/ Adam Reeves Adjunct Professor of Cognitive and Neural Systems Professor of Psychology, Northeastern University PhD, Psychology, City University of New York Psychophysics, cognitive psychology, vision http://www.psych.neu.edu/people/faculty/reeves.html Kevin Reilly Research Associate, Department of Cognitive and Neural Systems PhD, Speech and Hearing Science, University of Washington, Seattle Speech production, sensory-motor control and learning, computational neuroscience Michele Rucci Assistant Professor of Cognitive and Neural Systems PhD, Scuola Superiore S.-Anna, Pisa, Italy Vision, sensory-motor control and learning, and computational neuroscience http://cns.bu.edu/~rucci Elliot Saltzman Associate Professor of Physical Therapy, Sargent College Senior Scientist, Haskins Laboratories, New Haven, CT PhD, Developmental Psychology, University of Minnesota Modeling and experimental studies of human sensorimotor control and coordination of the limbs and speech articulators, focusing on issues of timing in skilled activities http://www.bu.edu/sargent/people/faculty/saltzman_elliot.html Fabrizio Santini Research Associate, Department of Cognitive and Neural Systems PhD, Computer Science, University of Florence, Italy Neuromorphic robotics, vision, neuroprocessors and large neural system simulations Robert Savoy Adjunct Associate Professor of Cognitive and Neural Systems Assistant in Experimental Psychology; Director, fMRI Education; Instructor Department of Radiology, Massachusetts General Hospital President, HyperVision Incorporated, Lexington, MA PhD, Experimental Psychology, Harvard University Computational neuroscience; visual psychophysics of color, form, and motion perception Teaching about functional MRI and other brain mapping methods http://www.nmr.mgh.harvard.edu/martinos/people/showPerson.php? people_id=148 Eric Schwartz Professor of Cognitive and Neural Systems; Electrical, Computer and Systems Engineering; & Anatomy and Neurobiology PhD, High Energy Physics, Columbia University Computational neuroscience, machine vision, neuroanatomy, neural modeling http://cns.bu.edu/pub/ericlee/ Robert Sekuler Adjunct Professor of Cognitive and Neural Systems Research Professor of Biomedical Engineering, College of Engineering, Biomolecular Engineering Research Center Frances and Louis H. Salvage Professor of Psychology, Brandeis University Consultant in neurosurgery, Boston Children's Hospital PhD, Psychology, Brown University Visual motion, brain imaging, relation of visual perception, memory, and movement http://people.brandeis.edu/~sekuler/ Barbara Shinn-Cunningham Associate Professor of Cognitive and Neural Systems and Biomedical Engineering Director of Graduate Studies, Department of Cognitive and Neural Systems PhD, Electrical Engineering and Computer Science, Massachusetts Institute of Technology Psychoacoustics, audition, auditory localization, binaural hearing, sensorimotor adaptation, mathematical models of human performance http://cns.bu.edu/~shinn/ David Somers Associate Professor of Psychology PhD, Cognitive and Neural Systems, Boston University Functional MRI, psychophysical, and computational investigations of visual perception and attention http://www.bu.edu/psych/faculty/somers/ Chantal E. Stern Associate Professor of Psychology and Program in Neuroscience, Boston University Associate Professor of Radiology, Harvard Medical School Director, Cognitive Neuroimaging Laboratory PhD, Experimental Psychology, Oxford University, United Kingdom Functional neuroimaging studies (fMRI and MEG) of learning and memory http://www.bu.edu/psych/faculty/stern/ Timothy Streeter Research Associate, Department of Cognitive and Neural Systems MS, Physics, University of New Hampshire MA, Cognitive and Neural Systems, Boston University Spatial auditory perception, perceptual adaptation Malvin C. Teich Professor of Electrical and Computer Engineering, Biomedical Engineering, and Physics PhD, Cornell University Quantum optics and imaging, photonics, wavelets and fractal stochastic processes, biological signal processing and information transmission http://people.bu.edu/teich/ Joseph Z. Tsien Professor of Pharmacology and Biomedical Engineering Director, Center for Systems Neurobiology PhD, Molecular Biology, University of Minnesota Neural mechanisms of learning, memory and concepts; neural codes and brain-machine-interface http://www.bumc.bu.edu/Dept/Content.aspx?DepartmentID=65&PageID=9355 Lucia Vaina Professor of Biomedical Engineering Research Professor of Neurology, School of Medicine PhD, Sorbonne Dres Science, National Politechnique Institute, Toulouse, France Computational visual neuroscience; theoretical engineering and neuroinformatics http://www.bu.edu/bravi/people/lucia.html Takeo Watanabe Associate Professor of Psychology Director, Vision Sciences Laboratory PhD, Behavioral Sciences, University of Tokyo, Japan Perception of objects and motion and effects of attention on perception using psychophysics and brain imaging (f-MRI) http://people.bu.edu/takeo/takeo/takeo.html Jeremy Wolfe Adjunct Professor of Cognitive and Neural Systems Professor of Ophthalmology, Harvard Medical School Psychophysicist, Brigham & Women?s Hospital, Surgery Department Director of Psychophysical Studies, Center for Clinical Cataract Research PhD, Massachusetts Institute of Technology Visual attention, pre-attentive and attentive object representation http://www.brighamandwomens.org/surgery/research/facultypages/ WolfeResearch.asp Curtis Woodcock Professor of Geography Director, Geographic Applications, Center for Remote Sensing PhD, University of California, Santa Barbara Biophysical remote sensing, particularly of forests and natural vegetation, canopy reflectance models and their inversion, spatial modeling, and change detection; biogeography; spatial analysis; geographic information systems; digital image processing http://www.bu.edu/cees/people/faculty/woodcock/ CNS DEPARTMENT COURSE OFFERINGS CAS CN500 Computational Methods in Cognitive and Neural Systems CAS CN510 Principles and Methods of Cognitive and Neural Modeling I CAS CN520 Principles and Methods of Cognitive and Neural Modeling II CAS CN530 Neural and Computational Models of Vision CAS CN540 Neural and Computational Models of Adaptive Movement Planning and Control CAS CN550 Neural and Computational Models of Recognition, Memory and Attention CAS CN560 Neural and Computational Models of Speech Perception and Production CAS CN570 Neural and Computational Models of Conditioning, Reinforcement, Motivation and Rhythm CAS CN580 Introduction to Computational Neuroscience GRS CN700 Computational and Mathematical Methods in Neural Modeling GRS CN710 Advanced Topics in Neural Modeling: Comparative Analysis of Learning Systems GRS CN720 Neural and Computational Models of Planning and Temporal Structure in Behavior GRS CN730 Models of Visual Perception GRS CN740 Topics in Sensory-Motor Control GRS CN760 Topics in Speech Perception and Recognition GRS CN780 Topics in Computational Neuroscience GRS CN810 Topics in Cognitive and Neural Systems: Visual Event Perception GRS CN811 Topics in Cognitive and Neural Systems: Visual Perception GRS CN911, 912 Research in Neural Networks for Adaptive Pattern Recognition GRS CN915, 916 Research in Neural Networks for Vision and Image Processing GRS CN921, 922 Research in Neural Networks for Speech and Language Processing GRS CN925, 926 Research in Neural Networks for Adaptive Sensory-Motor Planning and Control GRS CN931, 932 Research in Neural Networks for Conditioning and Reinforcement Learning GRS CN935, 936 Research in Neural Networks for Cognitive Information Processing GRS CN941, 942 Research in Nonlinear Dynamics of Neural Networks GRS CN945, 946 Research in Technological Applications of Neural Networks GRS CN951, 952 Research in Hardware Implementations of Neural Networks CNS students also take a wide variety of courses in related departments. In addition, students participate in a weekly colloquium series, an informal lecture series, and student-run special interest groups, and attend lectures and meetings throughout the Boston area; and advanced students work in small research groups. LABORATORY AND COMPUTER FACILITIES The department is funded by fellowships, grants, and contracts from federal agencies and private foundations that support research in life sciences, mathematics, artificial intelligence, and engineering. Facilities include laboratories for experimental research and computational modeling in visual perception; audition, speech and language processing; sensory-motor control and robotics; and technology transfer. Data analysis and numerical simulations are carried out on a state-of-the-art network comprised of Sun workstations, Macintoshes, and both 32-bit and 64-bit PCs. A PC farm running BU?s own version of Linux (BU Linux v4.6 based on Fedora Core 3) is available as a distributed computational environment. All students have department supplied PCs on their desktops (running either Microsoft Windows XP Pro or BU Linux) allowing them to run their simulations either locally or remotely on one of the department?s workstations. Mathematical simulation and modeling are carried out using standard software packages such as Mathematica or Matlab, as well as SPlus and VisSim. The department also maintains a core collection of books and journals, and has access both to the Boston University libraries and to the many other collections of the Boston Library Consortium. In addition, several specialized facilities and software are available for use. These include: ACTIVE PERCEPTION LABORATORY Models of the visual system often examine steady-state levels of neural activity during presentations of visual stimuli. It is difficult, however, to envision how such steady-states could occur under natural viewing conditions, given that the projection of the visual scene on the retina is never stationary. The Active Perception Laboratory is dedicated to the investigation of the interactions between visual perception and behavior. Research focuses on the theoretical and computational analysis of the influences of motor activity on the sampling and representation of visual information, the coupling of models of neuronal systems with robotic systems, and the design of psychophysical experiments with human subjects. The Active Perception Laboratory includes extensive computational facilities that allow the execution of large-scale simulations of neural systems. Additional facilities include instruments for the psychophysical investigation of eye movements during visual analysis, including an accurate and non-invasive eye tracker, and robotic systems for the simulation of different types of behavior. The Active Perception Laboratory hosts Mr. T, a humanoid robot with two 6 degrees-of-freedom arms and a head/eye system designed to replicate visual input signals to the human eye. AUDITORY NEUROSCIENCE LABORATORY The Auditory Neuroscience Laboratory in the Department of Cognitive and Neural Systems is an experimental and theoretical laboratory focused on auditory perception, particular spatial auditory perception, plasticity, and attention. The laboratory contains numerous PCs used both as workstations for students to model and analyze data and to control laboratory equipment and run experiments. The other major equipment in the laboratory includes special-purpose signal processing and sound generating equipment, electromagnetic head tracking systems, a two-channel spectrum analyzer, and other miscellaneous equipment for producing, measuring, analyzing, and monitoring auditory stimuli. The Auditory Neuroscience Laboratory consists of three adjacent rooms in the basement of 677 Beacon Street (the home of the CNS Department). One room houses an 8 ft. by 8 ft. single-walled sound-treated booth as well as space for students. The second room is primarily used as student workspace for developing and debugging experiments. The third space houses a robotic arm, capable of automatically positioning a small acoustic speaker anywhere on the surface of a sphere of adjustable radius, allowing automatic measurement of the signals reaching the ears of a listener for a sound source from different positions in space, including the effects of room reverberation. COMPUTER VISION - COMPUTATIONAL NEUROSCIENCE LABORATORY The Computer Vision/Computational Neuroscience Laboratory is comprised of an electronics workshop, including a surface-mount workstation, PCD fabrication tools, and an Alterra EPLD design system; an active vision laboratory including actuators and video hardware; and systems for computer aided neuroanatomy and application of computer graphics and image processing to brain sections and MRI images. The laboratory supports research in the areas of neural modeling, computational neuroscience, computer vision, robotics, and fMRI imaging. The major question being addressed is the nature of representation of the visual world in the brain, in terms of observable neural architectures such as topographic mapping and columnar architecture. The application of novel architectures for image processing for computer vision and robotics is also a major topic of interest. Recent work in this area has included the design and patenting of novel actuators for robotic active vision systems, the design of real-time algorithms for use in mobile robotic applications, and the design and construction of miniature autonomous vehicles using space-variant active vision design principles. Recently one such vehicle has successfully driven itself on the streets of Boston. Applications of fMRI imaging to measuring the topographic structure of human primary and extra-striate visual cortex are a current focus of research. SENSORY-MOTOR CONTROL LABORATORY The Sensory-Motor Control Laboratory supports experimental studies of sensory-motor behavior and computational studies of neural circuits that enable learned voluntary action. Equipment includes a computer- controlled, helmet-mounted, video-based, eye-head tracking system. The latter?s camera samples eye position at 240Hz and also allows reconstruction of what subjects are attending to as they freely scan a scene under normal lighting. Thus the system affords a wide range of visuo-motor studies. To facilitate computational studies, the laboratory is connected to the Department?s and University?s extensive network of Linux and Windows workstations and Linux computational servers. SPEECH AND LANGUAGE LABORATORY The Speech Laboratory includes facilities for analog-to-digital and digital-to-analog software conversion. Ariel equipment allows reliable synthesis and playback of speech waveforms. An Entropic signal-processing package provides facilities for detailed analysis, filtering, spectral construction, and formant tracking of the speech waveform. Various large databases, such as TIMIT and TIdigits, are available for testing algorithms of speech recognition. The laboratory also contains a network of Windows-based PC computers equipped with software for the analysis of functional magnetic resonance imaging (fMRI) data, including region-of-interest (ROI) based analyses involving software for the parcellation of cortical and subcortical brain regions in structural MRI images. TECHNOLOGY LABORATORY The Technology Laboratory fosters the development of neural network models derived from basic scientific research, and facilitates the transition of the resulting technologies to software and applications. The Lab was established in 2001, with a grant from the Air Force Office of Scientific Research: ?Information Fusion for Image Analysis: Neural Models and Technology Development.? Current projects include multi-level fusion and data mining in a geospatial context, in collaboration with the Boston University Center for Remote Sensing; and medical image analysis, in collaboration with the Center for Biomedical Imaging at the Boston University Medical Center. This research and development effort builds on models of opponent-color visual processing, contour and texture processing, and Adaptive Resonance Theory (ART) pattern learning and recognition, as well as other models of vision, associative learning, and prediction. Additional projects include collaborations with the Harvard Medical School, to develop methods for analysis of large-scale medical databases, currently to predict HIV resistance to antiretroviral therapy; and with HRL (formerly Hughes Research Laboratories), to develop robotic platforms. Associated basic research projects are conducted within the joint context of scientific data and technological constraints. Emerging neural network technologies are embedded in the CNS Image Processing Toolkit and the CNS Neural Classifier Toolkit. Software, articles, and educational materials are available through the CELEST Technology Website (http://cns.bu.edu/ techlab/), a growing resource for the NSF Center for Excellence for Learning in Education, Science, and Technology (http://cns.bu.edu/ celest/). VISUAL PSYCHOPHYSICS LABORATORY The Visual Psychophysics Laboratory includes a group of faculty and graduate students that conducts psychophysical and computational modeling studies of many aspects of visual perception, including motion perception, shape-from-texture, contour extraction, and visual navigation. See: http://cns.bu.edu/vislab/. The laboratory occupies an 800-square-foot suite, including three dedicated rooms for data collection, and houses a variety of computer-controlled display platforms, including Macintosh, Windows and Linux workstations. Ancillary resources for visual psychophysics include a computer- controlled video camera, stereo viewing devices, a photometer, and a variety of display-generation, data-collection, and data-analysis software. AFFILIATED LABORATORIES Affiliated CAS/CNS faculty members have additional laboratories ranging from visual and auditory psychophysics and neurophysiology, anatomy, and neuropsychology to engineering and chip design. These facilities are used in the context of faculty/student collaborations. ************************************************************************ **************************************************** DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS GRADUATE TRAINING ANNOUNCEMENT Department of Cognitive and Neural Systems Boston University 677 Beacon Street Boston, MA 02215 Phone: 617/353-9481 Fax: 617/353-7755 Email: amos at cns.bu.edu Web: http://cns.bu.edu/ ************************************************************************ **************************************************** From help at cs.cmu.edu Thu Jan 4 12:08:03 2007 From: help at cs.cmu.edu (help@cs.cmu.edu) Date: Thu, 4 Jan 2007 12:08:03 -0500 (EST) Subject: Connectionists: Administrative Test Message Message-ID: This is is a test message from the Mailing List Server Administrator. Please disregard. From Dave_Touretzky at cs.cmu.edu Fri Jan 5 03:29:24 2007 From: Dave_Touretzky at cs.cmu.edu (Dave_Touretzky@cs.cmu.edu) Date: Fri, 05 Jan 2007 03:29:24 -0500 Subject: Connectionists: problems with the Connectionists list Message-ID: <3155.1167985764@ammon.boltz.cs.cmu.edu> Dear Connectionists subscribers: For the last several weeks we've been experiencing problems with the Connectionists list. Postings were not getting through. The problem was finally resolved yesterday by our systems staff, and a large backlog of posts, some stale by now, was transmitted to the list. I believe the list is working properly again. I apologize for the service interruption. -- Dave Touretzky, CONNECTIONSITS moderator From jose at tractatus.rutgers.edu Fri Jan 5 12:38:05 2007 From: jose at tractatus.rutgers.edu (Stephen J. Hanson) Date: Fri, 05 Jan 2007 12:38:05 -0500 Subject: Connectionists: BRAIN READING USING FULL BRAIN SUPPORT VECTOR MACHINES FOR OBJECT RECOGNITION: There is no face identification area." Message-ID: <1168018686.5685.576.camel@localhost> This is a new paper to appear to in NEURAL COMPUTATION which may be of interest: Abstract Over the last decade object recognition work has confounded voxel response detection with potential voxel class identification. Consequently, the claim that there are areas of the brain that are necessary and sufficient for object identification cannot be resolved with existing associative methods (e.g. GLM) that are dominant in brain imaging methods. In order to explore this controversy we trained full brain (40k voxels) single TR classifiers on data from 10 subjects in two different recognition tasks on the most controversial classes of stimuli ("HOUSE" and "FACE") and show 97.4% median out-of-sample (unseen TRs) generalization. This performance allowed us to reliably and uniquely assay the classifier's voxel diagnosticity in all individual subject's brains: In this two class case there may be specific areas diagnostic for HOUSE stimuli (e.g. "LO") or for FACE stimuli (e.g "STS"), however, in contrast to the detection results common in this literature neither the FFA or PPA are shown to be uniquely diagnostic for FACEs or PLACEs respectively. /http://www.psych.rutgers.edu/~jose/hanson_halchenko_inpress.pdf Steve Hanson -- Stephen J. Hanson Professor Psychology Department Rutgers University (Newark Campus) Research Professor Information Science, NJIT Director of RUMBA Center, Rutgers Co-Director of Advanced Imaging Lab, UMDNJ/Rutgers email: jose at tractatus.rutgers.edu fax: 973-353-1171 tel: 973-353-5440 x 228 From pfua at fing.edu.uy Fri Jan 5 14:45:46 2007 From: pfua at fing.edu.uy (Pascal Fua) Date: Fri, 05 Jan 2007 17:45:46 -0200 Subject: Connectionists: Post-doctoral Fellow in Image/Video Content Analysis and Recognition at EPFL Message-ID: <459EAAEA.3020007@fing.edu.uy> The images and visual representation group ( http://ivrgwww.epfl.ch ) and the computer vision laboratory ( http://cvlab.epfl.ch ) have a joint opening for a post-doctoral fellow in the field of image and video content analysis and recognition. The position is initially offered for 18 months, with the possibility of renewal for an additional 18. Description The addition of context information (technical metadata, other sensor data, other text data, etc.) promises to greatly increase the potential to better segment, analyze, and recognize media content, and even to semantically annotate it. In the current and emerging wired environment, low level feature image/video systems will become increasingly intertwined with physical reality, will be based on resources shared over the Internet and will be supporting social interactions. This will impact the image/video analysis and recognition, requiring the ability to deal with the inherent uncertainty in the varied context information. Position The images and visual representation group and the computer vision laboratory at EPFL offer a creative international environment, a possibility to conduct highly competitive research on a global scale and involvement in teaching. Within the project, there are opportunities to cooperate with national and international research and industrial partners. There is the possibility to gain valuable experience in the emerging field of context aware imaging systems, in terms of new theoretical models and algorithms and in prototype systems. In addition, active participation in research projects and advising a small group of highly motivated Ph.D. students is expected. Salaries are in the range CHF 70000 to 80000 per year, the precise amount to be determined by EPFL's department of human resources. Education The candidate must hold a Ph.D. degree with top performance in a field related to image/video content analysis and recognition. Strong mathematics and programming skills (C or C++ and Matlab) are a plus. S/he should have a track record in conducting original highly competitive scientific research and publishing the results in top conferences and scientific journals. Maturity, self-motivation, and the ability to work both independently and as a team player in local and international research teams are expected. French language skills are not required, English is mandatory. Application Applications can either be sent via email or letter: Prof. Sabine Susstrunk EPFL-IC-LCAV2, Batiment BC Station 14 CH-1015 Lausanne Switzerland E-mail: sabine.susstrunk at epfl.ch They must contain a statement of interest, a CV, a list of publications, and the names of three references. -- -------------------------------------------------------------------- Prof. P. Fua (Pascal.Fua at epfl.ch) Tel: 41/21-693-7519 FAX: 41/21-693-7520 Url: http://cvlab.epfl.ch/~fua/ -------------------------------------------------------------------- From isabelle at clopinet.com Fri Jan 5 17:39:09 2007 From: isabelle at clopinet.com (Isabelle Guyon) Date: Fri, 05 Jan 2007 14:39:09 -0800 Subject: Connectionists: Workshop on data representation discovery Message-ID: <459ED38D.4080902@clopinet.com> IJCNN07 Workshop on Data Representation Discovery Thursday, August 16, 2007 Orlando, Florida Paper submission deadline: January 31st 2007 URL: http://clopinet.com/isabelle/Projects/agnostic/ With the proper data representation, learning becomes almost trivial! Topics of interest include, but are not limited to: - space embedding, space dimensionality reduction, latent variable methods - preprocessing (noise modeling, spectral transformations, etc.) - feature extraction (including feature construction and feature selection) - dynamic representations (selective attention; top down expectancy with bottom-up evidence resolution; dynamic feature selection) - biologically/psychologically inspired data representations - data representations for image, speech, and video processing - data representations for molecules, including applications in drug discovery and bioinformatics - data representations for text processing, including language translation - supervised, unsupervised, semi-supervised methods of learning data representations - learning representations with neural networks - learning representations with evolutionary computing - learning kernels (in kernel methods), learning similarity measures, learning distance metrics - transformation invariant representations, robust representations - multi-level data representations - multi-objective data representations - theoretical and empirical assessement of data representations The emphasis will be more on generic principled methods rather than on ad-hoc solutions. The results of the "Agnostic Learning vs. Prior Knowledge" challenge will be discussed at the workshop. The challenge is open until March 1st, 2007: http://www.agnostic.inf.ethz.ch/. Win one of seven prizes! From minai_ali at yahoo.com Fri Jan 5 09:18:11 2007 From: minai_ali at yahoo.com (Ali Minai) Date: Fri, 5 Jan 2007 06:18:11 -0800 (PST) Subject: Connectionists: IJCNN 2007 - Request for Workshop Proposals Message-ID: <388816.17409.qm@web61012.mail.yahoo.com> The Organizing Committee for the 2007 International Joint Conference on Neural Networks (IJCNN 2007) invites proposals for workshops to be held in Orlando, August 17-18, 2007, following the regular program of IJCNN 2007. Workshops can be half-day (4 hours) or full-day (8 hours) in duration. The Committee especially encourages proposals in active interdisciplinary areas such as computational neuroscience, cognitive modeling, neural implants, brain-machine interfaces, biomorphic & neuromorphic engineering, evolutionary robotics, situated learning systems, multi-agent systems, swarms, self-reconfiguring systems, bioinformatics, etc. Proposals in more traditional areas of neural networks are also welcome. 1-3 page proposals should be sent electronically to the Workshops Chair (Ali Minai) at: Ali.Minai at uc.edu by Jan 31, 2007. The format for proposals and other information can be found at: http://www.ijcnn2007.org/workshops.htm The proposals will be evaluated competitively, and notifications of acceptance will be sent by March 1, 2007. Information on IJCNN 2007 is available at: http://www.ijcnn2007.org Ali Minai Workshops Chair IJCNN 2007 --------------------------------------------------------------------- Ali A. Minai Associate Professor Department of Electrical & Computer Engineering University of Cincinnati Cincinnati, OH 45221-0030 Phone: (513) 556-4783 Fax: (513) 556-7326 Email: aminai at ececs.uc.edu minai_ali at yahoo.com WWW: http://www.ececs.uc.edu/~aminai/ ---------------------------------------------------------------------- From mlmta at bio-complexity.com Sat Jan 6 21:58:56 2007 From: mlmta at bio-complexity.com (mlmta@bio-complexity.com) Date: Sat, 6 Jan 2007 20:58:56 -0600 (CST) Subject: Connectionists: Conference: MLMTA'07, Machine Learning: Models, Technologies & Applications Message-ID: <54359.128.208.10.6.1168138736.squirrel@69.65.24.130> ##################################################################### CALL FOR PAPERS ##################################################################### MLMTA'07 - The 2007 International Conference on Machine Learning: Models, Technologies & Applications Monte Carlo Resort, Las Vegas, Nevada, USA June 25-28, 2007 http://www.world-academy-of-science.org/worldcomp07 ##################################################################### The 2007 International Conference on Machine Learning: Models, Technologies & Applications (MLMTA'07) will be held in Las Vegas, Nevada, June 25-28, 2007. MLMTA'07 aims to bring together researches from computer science, applied statistics, applied mathematics and engineering working in the field of Machine Learning. In addition to traditional topics in development and application of statistical methods in data analysis MLMTA'07 has this year a special focus on methods utilizing the 'systems view' of a problem. Due to the fact that graph-based methods have proven to be an useful mathematical representation of problems in this class submitted papers developing or applying graph-based statistical methods are of utmost interest. TOPICS OF INTEREST include, but are not limited to: o General Machine Learning Theory # Statistical learning theory # Unsupervised and Supervised Learning # Multivariate analysis # Hierarchical learning models # Relational learning models # Bayesian methods # Meta learning # Stochastic optimization # Simulated annealing # Heuristic optimization techniques # Neural networks # Evolutionary algorithms in learning # Reinforcement learning # Multi-criteria reinforcement learning # General Learning models # Multiple hypothesis testing # Decision making # Markov chain Monte Carlo (MCMC) methods # Non-parametric methods # Graphical models # Gaussian graphical models # Bayesian networks # Sequential Monte Carlo methods # Particle filter # Time series prediction # Fuzzy logic and learning # Inductive learning and applications # Grammatical inference o General Graph-based Machine Learning Techniques # Graph kernel and graph distance methods # Graph-based semi-supervised learning # Graph clustering # Graph learning based on graph transformations # Graph learning based on graph grammars # Graph learning based on graph matchings # General theoretical aspects of graph learning # Statistical modeling of graphs # Information-theoretical approaches of graphs # Motif search # Network inference # General issues in graph and tree mining o Machine Learning Applications # Aspects of knowledge structures # Computational Finance # Computational Intelligence # Knowledge acquisition and discovery techniques # Induction of document grammars # Supervised and unsupervised classification of web data # General Structure-based approaches in information retrieval # General Structure-based approaches in web authoring # General Structure-based approaches in information extraction # General Structure-based approaches in web content mining # Graph and tree mining approaches for analyzing web-based document structures # Analysis of link structures # Latent semantic analysis # Aspects of natural language processing # Categorization of web-based units # Aspects of text technology # Computational linguistics and application # Computational vision # Bioinformatics # Biostatistics # Computational Biology # High-throughput data analysis # Biological network analysis: * protein-protein networks * signaling networks * metabolic networks * transcriptional regulatory networks # Graph Inference based on biological data # Graph-based models in biostatistics # Optimization methods in bioinfomatics and biochemistry # Speech and Signal Processing # Computational Neuroscience # Computational Chemistry # Computational Statistics # Systems Biology # Algebraic Biology # Further applications of ML-methods in chemistry, biomedical analysis # computer vision, and neuroscience IMPORTANT DATES * February 20, 2007 - Draft papers due * March 20, 2007 - Notification of acceptance * April 20, 2007 - Camera ready papers & pre-registration due * June 25-28, 2007 - MLMTA'07 Please visit the conference website at http://www.bio-complexity.com/MLMTA_index.html Conference Organization * Hamid R. Arabnia, University of Georgia, Georgia, USA * Frank Emmert-Streib, University of Washington, Seattle, USA * Matthias Dehmer, Max F. Perutz Laboratories, Vienna Bio Center, Vienna, Austria For more information email: MLMTA || bio-complexity.com or visit the conference website http://www.bio-complexity.com/MLMTA_index.html ################################################################################# From Yann.Guermeur at loria.fr Mon Jan 8 05:46:29 2007 From: Yann.Guermeur at loria.fr (Yann Guermeur) Date: Mon, 08 Jan 2007 11:46:29 +0100 Subject: Connectionists: CFP special session ASMDA 2007 Message-ID: <45A22105.2010807@loria.fr> Dear Colleagues, I would like to inform you of the following call for papers. Best regards, Yann Guermeur ----------------------------------------------------------------------- *** Call For Papers The 12th International Conference on Applied Stochastic Models and Data Analysis (ASMDA 2007, http://www.asmda.com/id7.html) will take place in Chania, Crete, Greece from May 29 until June 1, 2007. It will include a special session entitled "Supervised Prediction with Neural Networks and SVMs". The papers of this session will appear in the proceedings of the conference. During the last decade, significant advances have been made in the theory and practice of supervised classification, kernel machines as a prime example. They have deeply changed the way classification problems are tackled and generated many new approaches. It is especially the case for multi-category classification, which comes out as an independent field of research. The object of this special session is to collect contributions in the different domains of supervised classification with neural networks and kernel machines: bounds on the risk, feature selection methods, training algorithms and model selection methods. Efficient implementations of known inductive principles or complex kernel methods, are also welcome. Of particular interest will be contributions dedicated to multi-category classification. *** Organization * Program committee - Koby Crammer, Department of Computer and Information Science, University of Pennsylvania, USA - Yann Guermeur, LORIA, CNRS, France - Yoonkyung Lee, Department of Statistics, The Ohio State University, USA - Liva Ralaivola, LIF, University Provence/Aix-Marseille I, France - Olivier Teytaud, LRI, INRIA, France * Important dates -Deadline for submission: February, 20, 2007 -Notification of acceptance: March, 10, 2007 -Final version of the paper: March, 15, 2007 * Format of submissions and submission procedure Manuscripts should be in the format described at the ASMDA 2007 conference website, http://www.asmda.com/id19.html. They should be no longer than 8 pages using the asmda2007.cls style file. The template is available at http://www.asmda.com/sitebuildercontent/sitebuilderfiles/PaperTemplateasmda2007latex.zip Submissions (ps or pdf files) should be sent by email to the following address: Yann.Guermeur at loria.fr ----------------------------------------------------------------------- -- 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 d.mareschal at bbk.ac.uk Mon Jan 8 11:49:03 2007 From: d.mareschal at bbk.ac.uk (Denis Mareschal) Date: Mon, 8 Jan 2007 16:49:03 +0000 Subject: Connectionists: Phd opportunities in London Message-ID: Dear all, Please circulate to any relevant students. PLEASE DO NOT REPLY DIRECTLY TO ME. Best regards, Denis Mareschal ------------------------------------------------------ PhD Opportunities in PSYCHOLOGY and Computational Cognitive Neuroscience The School of Psychology, Birkbeck, University of London offers supervision in Cognitive Sciences, Human Development, and Family and Psychosocial Studies Birkbeck is part of the University of London and is situated in the central Bloomsbury area of London. The School of Psychology has a moderate sized, dynamic international postgraduate community that provides both a cutting edge and intimate environment for learning and research. Supervision is available from staff within the School itself (http://www.bbk.ac.uk/psyc/staff/academic) and at the research Centres affiliated with the School of Psychology: Centre for Brain and Cognitive Development http://www.cbcd.bbk.ac.uk/cbcd.html Centre for Psychosocial Studies http://www.bbk.ac.uk/psyc/cps/index_html Institute for the Study of Children, Family and Social Issues http://www.iscfsi.bbk.ac.uk Applicants in cognitive, cognitive neuroscience, and computational cognitive neuroscience are particularly sought. Financial support is available on a competitive basis through EPSRC, ESRC, MRC, and internal College Studentships. The School of Psychology also has ESRC recognition. Initial deadline for application is 16 March 2007. Further information can be obtained from: http://www.bbk.ac.uk/psyc/prospective/pgresearch/phd_research The School of Psychology hosts a number of overseas students with financial support from the Commonwealth Trust, the ORS, and various national science training foundations. it also hosts a Marie Curie Training Centre of Excellence and is an ideal host site for Marie Curie fellowships application The School also offers a Masters in Psychological Research Methods, as a possible route into the PhD programme. For more information, please visit: http://www.bbk.ac.uk/psyc/prospective/pgtaught/msc_research_methods For all enquiries email: j.vallerine at psychology.bbk.ac.uk -- ================================================= Professor Denis Mareschal Centre for Brain and Cognitive Development School of Psychology Birkbeck College University of London Malet St., London WC1E 7HX, UK tel +44 (0)20 7631-6582/6226 reception: 6207 fax +44 (0)20 7631-6312 http://www.psyc.bbk.ac.uk/people/academic/mareschal_d/ ================================================= From yilu.zhang at gm.com Mon Jan 8 18:06:19 2007 From: yilu.zhang at gm.com (yilu.zhang@gm.com) Date: Mon, 8 Jan 2007 18:06:19 -0500 Subject: Connectionists: CFP: Neural Networks and Data Mining for Fault Diagnosis and Failure Prognosis of Engineering Systems Message-ID: Call for papers: Neural Networks and Data Mining for Fault Diagnosis and Failure Prognosis of Engineering Systems A Special Session of International Joint Conference on Neural Networks August 12-17, Orlando, Florida http://www.ijcnn2007.org/ (Submission deadline: 1/31/2007) The increasing complexity of engineering systems and the increasing interactions among components boost the number of system states exponentially, which poses a big challenge to the diagnosis and prognosis of such systems. When designing a complex system, it is difficult to exhaust and understand all the operation states for failure mode and effects analysis (FMEA). The difficulties are compounded by the demand of short time-to-market for new systems. When maintaining a complex system, it is difficult to isolate and resolve all the failure modes. As a result, many cases are reported in service bays as ?no trouble found? or ?customer concern not duplicated.? It becomes very challenging to execute the growing condition-based maintenance (CBM) strategy when system prognosis and predictive maintenance are required. Effective and efficient diagnosis and prognosis technologies are called for across industries, especially for those safety-critical systems that require reliable and uninterrupted operations. Among other technologies, data mining offers unique and promising potential to complex system diagnosis. Data mining is the process of automatically searching large volumes of data for patterns. In the system diagnosis and prognosis context, the patterns can be anything from hidden relationship, root cause, to degradation trend. In the design stage, data mining can gain insight into the hardware/software interactions. In the validation stage, data mining can spot the weakest link in the system. In the maintenance stage, data mining can identify shared symptoms for fault isolation and shared failure precursors for predictive maintenance. Overall, data mining serves as a cost/time effective way to reduce massive engineering data into diagnostic and prognostic knowledge. Its application spans over the whole system lifecycle from development, deployment, to service. Data mining is not a new concept to the neural networks community. Neural networks is one of the widely used modeling and learning techniques for data mining. At the same time, data mining for complex system diagnosis and prognosis has its unique challenges in enterprise-level data collection, diagnostic knowledge discovery and management, and field deployment. This special session invites research papers from both academia and industry to identify the challenges, present successful practices, share lessons learned, and define roadmaps for further advance in the area of neural networks and data mining for complex system diagnosis and prognosis. Topics of interest include, but are not limited to - Neural networks and data mining algorithms for system monitoring and diagnosis - Neural networks and data mining algorithms for system prognostics and predictive maintenance - Categorical and parametric data hybrid analysis for anomaly detection and fault isolation - Diagnostic data collection, cleaning, and management over system lifecycle - Fusion of diagnostic knowledge extracted from data and from domain experts - Evaluation of diagnostic knowledge derived from data - Diagnostic data mining practice in system development and validation - Diagnostic data mining practice in system deployment and maintenance - Interactive data mining practice in diagnosis and prognosis algorithm development - Other enabling technologies for complex engineering system diagnosis and prognosis Detailed instructions for paper submission are available at http://www.ijcnn2007.org/. The deadline is January 31, 2007. Please select ?Neural Networks and Data Mining for Fault Diagnosis and Failure Prognosis of Engineering Systems? as the ?main research topic? in order to be considered as a submission to this special session. Special session organizers: George Vachtsevanos, Professor School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta, Georgia Email: gjv at ece.gatech.edu Yilu Zhang, Senior Researcher Electrical & Controls Integration Lab GM R&D Center Warren, Michigan Email: yilu.zhang at gm.com Feng (Fred) Xue, Information Scientist Industrial Artificial Intelligence Lab GE Global Research Center Niskayuna, New York Email: xue at research.ge.com Weizhong Yan, Research Engineer Industrial Artificial Intelligence Lab GE Global Research Center Niskayuna, New York Email: yan at crd.ge.com ----------- Yilu Zhang, Ph.D. Senior Researcher Electrical & Controls Integration Lab GM R&D and Planning General Motors Corporation MC: 480-106-390 30500 Mound Road Warren, MI 48090 Voice: (586) 986-4717 Fax: (586) 986-3003 yilu.zhang at gm.com From Eugene.Izhikevich at nsi.edu Wed Jan 10 03:45:06 2007 From: Eugene.Izhikevich at nsi.edu (Eugene M. Izhikevich) Date: Wed, 10 Jan 2007 00:45:06 -0800 Subject: Connectionists: Scholarpedia Lecture Notes: Call for Submissions Message-ID: <45A4A792.4030505@nsi.edu> Scholarpedia intends to host lecture notes (courses, tutorials) on computational neuroscience and related fields. A series of lecture notes is treated as any other article in Scholarpedia, except that it consists of multiple subpages corresponding to multiple lectures. As any other Scholarpedia article, 1.Lecture notes should be written by the leading authority in the field. 2.The notes will be peer-reviewed. 3.Upon acceptance, the author will become the curator of the lecture notes. 4.Other Scholars could edit the notes, but the modifications do not appear until the curator approves them. The goal is to have a number of high-quality lecture notes freely available on-line. Each series serves as a basis of a course delivered by many professors in many universities. The professors and their students could modify the notes through the wiki-style mechanism built-in in Scholarpedia, add new material, figures, exercises, and so on. Curators will have the opportunity to evaluate such modifications before they are made public. This is an experiment. The number of topics is limited to 5 during the spring semester of 2007. Please, send your proposals to Eugene M. Izhikevich . Scholarpedia is a free peer-reviewed encyclopedia that combines philosophies of Wikipedia and Encyclopedia Britannica. More information is at http://www.scholarpedia.org -- Eugene M. Izhikevich, Ph.D., http://www.izhikevich.com The Neurosciences Institute, Eugene.Izhikevich at nsi.edu 10640 John J. Hopkins Drive tel:(858) 626-2063 San Diego, CA, 92121, USA fax:(858) 626-2099 From l.s.smith at cs.stir.ac.uk Wed Jan 10 09:29:21 2007 From: l.s.smith at cs.stir.ac.uk (Leslie Smith) Date: Wed, 10 Jan 2007 14:29:21 +0000 Subject: Connectionists: Post at Stirling University, Scotland Message-ID: CARMEN (Code Analysis, Repository and Modelling for e-Neuroscience) is a neuroinformatics project coordinated by the Institute of Neuroscience at Newcastle University (www.ncl.ac.uk/ion/) which brings together a consortium of 19 investigators from 11 UK Universities with expertise in experimental neuroscience, computing science and statistical data analysis. Some information on CARMEN may be found at http://bioinf.ncl.ac.uk/carmen/index.php/Main_Page. This post (due to start 1 April 2007) is a two-year appointment to develop advanced techniques for spike detection and sorting algorithms for neurophysiological signals. Applicants should have a strong background in signal analysis and/or statistical techniques for data analysis. See http://www.personnel.stir.ac.uk/recruitment/recruitment_pdfs/ res_12836.pdf for further particulars. Email Professor Leslie Smith (lss at cs.stir.ac.uk) to discuss if you are interested. Professor Leslie S. Smith, Dept of Computing Science and Mathematics, University of Stirling, Stirling FK9 4LA, Scotland l.s.smith at cs.stir.ac.uk Tel (44) 1786 467435 Fax (44) 1786 464551 www http://www.cs.stir.ac.uk/~lss/ UKRI IEEE NNS Chapter Chair: http://www.cs.stir.ac.uk/ieee-nns-ukri/ -- The University of Stirling is a university established in Scotland by charter at Stirling, FK9 4LA. Privileged/Confidential Information may be contained in this message. If you are not the addressee indicated in this message (or responsible for delivery of the message to such person), you may not disclose, copy or deliver this message to anyone and any action taken or omitted to be taken in reliance on it, is prohibited and may be unlawful. In such case, you should destroy this message and kindly notify the sender by reply email. Please advise immediately if you or your employer do not consent to Internet email for messages of this kind. From franco at ulisse.cib.na.cnr.it Wed Jan 10 10:40:27 2007 From: franco at ulisse.cib.na.cnr.it (FVentriglia) Date: Wed, 10 Jan 2007 16:40:27 +0100 Subject: Connectionists: Final Call For Papers: BVAI 2007 Message-ID: <20070110153956.19EB912011@ulisse.cib.na.cnr.it> ********************************************************************* Subject: Final Call For Papers: BVAI 2007 ********************************************************************* *** Apologies for multiple copies *** 2nd International Symposium on "Brain, Vision and Artificial Intelligence" (BVAI 2007) Naples-Italy, October 10-12, 2007 BVAI 2007 is organised by researchers of the Institute of Cybernetics "E. Caianiello" of the Italian National Research Council, and will be held in Naples, Italy, 10-12 October 2007. The scientific program will include, besides eight invited talks, contributed papers that will be presented in plenary oral or poster sessions. Original and unpublished papers on BVAI 2007 main research areas and related topics are welcome. Main research areas The basic Brain: Neurobiology, Biophysics and Computational Theories Natural Vision: Visual Neuroscience, Visual Perception and Visual Cognition Artificial Vision: Pattern Recognition, Computer Vision, Biometrics Artificial Intelligence: Intelligent Systems, Robotics and Human Computer Interaction. Invited Speakers: Michael Arbib (USA) Matteo Carandini (USA) Karl Gegenfurtner (Germany) Jos? del R. Millan (Switerland) Petr Lansky (Czech) Oliviero Stock (Italy) John K. Tsotsos (Canada) Massimo Tistarelli (Italy) Important Dates: Paper Submission 1 March 2007 Acceptance Notification 11 May 2007 Camera-ready Papers 11 June 2007 BVAI 2007 Proceedings, including all accepted contributions, will be published by Springer-Verlag in the series Lecture Notes in Computer Science ( www.springer.com/lncs). In addition, two special issues of international journals are planned, which will include extended versions of selected BVAI 2007 papers. Visit the WWW BVAI 2007 Page http://biocib.cib.na.cnr.it/BVAI2007 for more details and updated information. Email Contact: bvai2007 at biocib.cib.na.cnr.it Add a bookmark to: http://biocib.cib.na.cnr.it/BVAI2007 -------------- next part -------------- No virus found in this outgoing message. Checked by AVG Free Edition. Version: 7.5.432 / Virus Database: 268.16.8/621 - Release Date: 09/01/2007 13.37 From tom.ziemke at his.se Thu Jan 11 02:44:52 2007 From: tom.ziemke at his.se (Tom Ziemke) Date: Thu, 11 Jan 2007 08:44:52 +0100 Subject: Connectionists: postdoc positions in cognitive/emotional robotics Message-ID: <45A5EAF4.7070703@his.se> POSTDOC POSITIONS IN COGNITIVE/EMOTIONAL ROBOTICS University of Skovde, Sweden Two postdoc positions are available in our lab as part of a four-year project on bio-inspired cognitive/emotional robotics (Jan 2006 - Dec 2009), funded by an European grant, involving 10 labs across Europe, with our group as a coordinator. The primary aim of the ICEA project is to develop a cognitive systems architecture integrating cognitive, emotional and bioregulatory mechanisms, based on the architecture of the mammalian brain. Ideal applicants would have a doctoral degree (soon) and research experience/interests in some of these areas: embodied cognition, adaptive robotics, artificial life, bio-inspired robotics, cognitive modeling (in particular cognitive architectures), computational neuroscience, neural networks, rat/rodent behavior, robot learning, theories and models of affect, emotion, motivation. Starting date: early 2007 (as soon as possible). For additional information contact Tom Ziemke (tom.ziemke at his.se). Interested candidates should send a brief statement of research interests, a CV and/or some representative publications. From Ibrahim.Esat at brunel.ac.uk Thu Jan 11 05:46:36 2007 From: Ibrahim.Esat at brunel.ac.uk (ibi) Date: Thu, 11 Jan 2007 10:46:36 -0000 Subject: Connectionists: Call for papers, Biologically inspired computing, special issue of the Journal of Integrated Design and Process Science Message-ID: <002401c7356d$ca6fcb20$918b5386@RoyaM> Call for Papers The Journal of Integrated Design and Process Science will publish a special issue on biologically inspired computing. If you are interested to submit a paper please let me know. All submitted papers will be processed, and if accepted, will be published in the July issue of the journal. More information about the society of Design and Process Science can be found on http://www.sdpsnet.org Deadline for submission of papers is 23rd of February 2007. Prof. I. Esat (ibrahim.esat at brunel.ac.uk) Head of Applied Mechanics Group School of Engineering and Design Brunel University Uxbridge Middlesex UB8 3PH UK From y.demiris at imperial.ac.uk Tue Jan 9 20:01:36 2007 From: y.demiris at imperial.ac.uk (Yiannis Demiris) Date: Wed, 10 Jan 2007 01:01:36 +0000 Subject: Connectionists: CFP: IEEE International Conference on Development and Learning 2007, Imperial College, 11-13 July Message-ID: Dear colleagues, the following CFP might be of interest to you. Please excuse multiple copies you might receive. All information contained below can be accessed from http://www.icdl07.org where updates to this call for papers will also be posted. With best wishes, Yiannis -- Dr Yiannis Demiris, Lecturer, Intelligent Systems and Networks Group, Department of Electrical and Electronic Engineering, Imperial College London, South Kensington Campus, Exhibition Road, London, SW7 2BT, UK Tel: +44(0)2075946300, Fax: +44(0)2075946274 http://www.iis.ee.ic.ac.uk/yiannis ---- 1st CALL FOR PAPERS IEEE International Conference on Development and Learning 2007 Imperial College London, 11-13 July 2007 http://www.icdl07.org http://www.icdl07.org/cfp.pdf Development and Learning are fundamental properties of any cognitive system, whether natural or artificial, and have attracted the attention of psychologists, neuroscientists, roboticists and artificial intelligence researchers. The International Conference on Development and Learning strives to bring together this interdisciplinary audience to encourage understanding and cross-fertilization of ideas from the different disciplines. Now in its 6th year, ICDL 2007 will have the theme of "Assisting Development" to encourage participants to consider the application of their research to the conceptualization, design and implementation of systems that can assist development. Topics of interest include (but are not restricted to): * General Principles of Development and Learning in Humans and Robots * Neural, Behavioral and Computational Plasticity * Biologically Inspired Mental Architectures for Development * Embodied Cognition: Foundations and Applications * Social Development in Humans and Robots * Language Development and Learning * Dynamic Systems Approaches * Emergence of Structures through Development * Development of Perceptual and Motor Systems * Models of Developmental Disorders * Architectures and software/hardware platforms for assisting development. Papers will be peer-reviewed by the international program committee, and will be judged on their originality, scientific rigor, and significance of the results. Accepted papers will be included in the conference proceedings. Accepted authors will be given the opportunity to submit related data and video demonstrations for inclusion on an accompanying DVD. Call for Contributions Papers are invited in any of the topics detailed above; submissions should follow the instructions on the conference webpage at http://www.icdl07.org Submission will open on 1st of February 2007. Important dates: Submissions deadline: March 5, 2007 Decisions to authors: May 1, 2007 Camera ready papers due: June 1, 2007 Conference: 11-13 July 2007 For further information, see www.icdl07.org or contact the organizers below: Chair Dr Yiannis Demiris Department of EEE, Imperial College London y.demiris at imperial.ac.uk http://www.iis.ee.ic.ac.uk/yiannis Program chairs Prof. Denis Mareschal School of Psychology Birkbeck College University of London d.mareschal at bbk.ac.uk http://www.bbk.ac.uk/psyc/staff/academic/dmareschal Prof. Brian Scassellati Dept. of Computer Science Yale University scaz at cs.yale.edu http://www.cs.yale.edu/homes/scaz/ Prof. John Weng Dept. of Computer Science and Engineering Michigan State University weng at cse.msu.edu http://www.cse.msu.edu/~weng/ The conference is sponsored by IEEE Computational Intelligence Society, with additional support from euCognition. From wduch at is.umk.pl Thu Jan 11 14:22:38 2007 From: wduch at is.umk.pl (Wlodzislaw Duch) Date: Thu, 11 Jan 2007 23:22:38 +0400 Subject: Connectionists: CFP: Visualization and Support for Information and Knowledge Management Message-ID: <004b01c735b5$eab93ef0$a200a8c0@duchnote> Dear Connectionists, We are trying to bring knowledge management and information retrieval experts closer to the computational intelligence community. At the 20th International Joint Conference on Neural Networks (IJCNN'07), Renaissance Orlando Resort in Orlando, Florida, USA, http://www.ijcnn2007.org/ we plan a special session on "Visualization and Support for Information and Knowledge Management". Please let your colleagues know about it. A brief description of the scope and motivation for organizing this session: Computational intelligence finds many applications in visualization of multidimensional information, organization and retrieval of information and knowledge management. With rapidly growing access to huge amount of information through the Internet methods that can select, organize and present relevant information became extremely important. This session will focus on CI methods that are being developed for visualization of text and multimedia documents, methods for organizing and browsing data repositories, adding structure to unstructured data, development of environments that use CI techniques for organization and presentation of information. It will include theoretical developments and applications of such methods in visualizing large collections of papers, datasets, mixed content databases, digital libraries, information flows, social interest groups, semantic web objects, multimedia, biomedical data, knowledge representation, creating and using ontologies to structure knowledge. Papers on embedding methods for visualization of multivariate data, SOM semantic maps, topic maps and other issues related to this area will also be solicited. Detailed instructions for paper submission are available at http://www.ijcnn2007.org/. The deadline is January 31, 2007. Organizers: Wlodzislaw Duch School of Computer Engineering, Nanyang Technological University, Singapore; Dept. of Informatics, Nicolaus Copernicus University, Torun, Poland; Google: Duch Shiro Usui, Brain Science Institute, RIKEN, Japan Google: Shiro Usui From emmanuel.vincent at irisa.fr Thu Jan 11 12:10:15 2007 From: emmanuel.vincent at irisa.fr (Emmanuel Vincent) Date: Thu, 11 Jan 2007 18:10:15 +0100 Subject: Connectionists: Stereo Audio Source Separation Evaluation Campaign: CALL FOR PARTICIPATION Message-ID: <45A66F77.1060304@irisa.fr> *** FIRST CALL FOR PARTICIPATION *** 1st Stereo Audio Source Separation Evaluation Campaign http://sassec.gforge.inria.fr/ Participation deadline: April 13, 2007 Do you have an algorithm for source separation from few channels? Or are you interested in this challenging issue? Then you should take part in the first campaign for the evaluation of stereo audio source separation algorithms. The task is to estimate from a two-channel speech or music mixture the contribution of each source on each channel, the number of sources being equal to three or more. This campaign complements recent evaluation initiatives conducted by Lucas Parra and the PASCAL network, which focused on different numbers of sources and channels. Three types of mixtures are considered: - instantaneous mixtures, - synthetic convolutive mixtures, - live recordings. All contributions are welcome, including established, novel, blind or non-blind, two-channel or single-channel algorithms. The evaluation will be non-competitive: the results will be made available on the campaign website for listening and evaluated using multiple criteria, possibly proposed by the participants. The results will be summarized in a paper to be discussed at the ICA'07 conference (see http://www.ica2007.org/), during which the participants who wish to present a poster about their algorithm will also have the opportunity to do so. These posters will then be published on the campaign website. For more information about the campaign and to download training/test sets, see http://sassec.gforge.inria.fr/ Best regards, Emmanuel Vincent, Hiroshi Sawada, Pau Bofill, Shoji Makino and Justinian Rosca From valenti at dsi.unimi.it Fri Jan 12 05:43:10 2007 From: valenti at dsi.unimi.it (Giorgio Valentini) Date: Fri, 12 Jan 2007 11:43:10 +0100 Subject: Connectionists: CIBB 2007: second CFP Message-ID: <45A7663E.1070607@dsi.unimi.it> Apologizes for cross-posting. ************************** SECOND CALL FOR PAPERS ************************** CIBB 2007 - Fourth International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics Hotel Portofino Kulm - Portofino Vetta, Ruta di Camogli (Genova), Italy July 7-10, 2007 Conference website: http://cibb07.dsi.unimi.it The main goal of this meeting is to provide a forum open to researchers from different disciplines to present and discuss problems relative to computational techniques in bioinformatics with a particular focus on supervised and unsupervised machine learning methods. Topics of interest include, but are not limited to: sequence analysis; transcriptomics; proteomics; evolution and philogeny; comparative genomics; bio-medical text mining and imaging; heterogeneous data integration for diagnostics. For a more detailed list of covered research areas, please visit our website: http://cibb07.dsi.unimi.it. We invite to submit papers that will be published on Springer's Lecture Notes on Computer Science. Selected papers will be invited to submit an extended version to a special issue of Artificial Intelligence in Medicine. The scientific program will include, besides an invited talk of Joaquin Dopazo (Centro de Investigaci?n Pr?ncipe Felipe, Valencia, Spain), accepted papers that will be presented in plenary oral sessions. ********************* Paper submission: ********************* Papers must be written in Latex in Lecture Notes on Computer Science Springer format following the guidelines for "Proceedings and Other Multi-author Volumes (http://www.springer.com). Latex templates can be downloaded from the Springer website or from the conference website. Papers must be no longer than 6 pages, with an additional cover sheet stating paper title, keyword(s), authors names and affiliations, contact author's name and contact details including telephone/fax numbers and e-mail address, and an abstract no more than 200 words long. Papers in pdf format should be sent in attachment by e-mail to infocibb07 at dsi.unimi.it. All accepted papers submitted by registered participants to CIBB 2007 will be published in the Lecture Notes on Computer Science Series, Springer. Selected papers will be invited to submit an extended version for a special issue of Artificial Intelligence in Medicine on "Computational Intelligence methods for Bioinformatics and Biostatistics". CIBB 2007 is jointly organized by - INNS, International Neural Network Society, SIG Bioinformatics - BITS, Bioinformatics ITalian Society - SIREN, Italian Society of Neural Networks - DSI, Dipartimento di Scienze dell'Informazione, Unversit? degli Studi di Milano. - DMI, Dipartimento di Matematica e Informatica, Universit? di Salerno and in connection with WILF 2007 (http://wilf2007.disi.unige.it). ********************* Important Dates: ********************* Submission deadline: January 31 2007 Notification of acceptance: February 28 2007 Final papers due: March 31 2007 Workshop: 7-10 July 2007. ********************* Organizers: ********************* Roberto Tagliaferri, Universit? di Salerno, Italy Giorgio Valentini, Universit? degli Studi di Milano, Italy ****************************************** Scientific Program Committee: ****************************************** Klaus-Peter Adlassnig, Medical University of Vienna, Austria Pierre Baldi, University of California, Irvine, USA Alberto Bertoni, Universit? degli Studi di Milano, Italy Paola Campadelli, Universit? degli Studi di Milano, Italy Nello Cristianini, University of Bristol, UK Giovanni Cuda, Universit? di Catanzaro, Italy Diego di Bernardo, Telethon Institute of Genetics and Medicine, Italy Joaquin Dopazo, Centro de Investigaci?n Pr?ncipe Felipe, Valencia, Spain Sandrine Dudoit, University of California, Berkeley, USA Jon Garibaldi, University of Nottingham, UK Emmanuel Ifeachor, University of Plymouth, UK Nathan Intrator, Tel Aviv University, Israel Nik Kasabov, Auckland University of Technology, NZ Samuel Kaski, Helsinki University of Technology, Finland Natalio Krasnogor, University of Nottingham, UK Luciano Milanesi, ITB CNR, Italy Sushmita Mitra, Indian Statistical Institute, Kolkata, India Marco Muselli, CNR Genova, Italy Oleg Okun, University of Oulu, Finland Alberto Paccanaro,Yale University, CT, USA Giulio Pavesi, Universit? degli Studi di Milano, Italy David Alejandro Pelta, University of Granada, Spain Graziano Pesole, Universit? di Bari, Italy Leif E. Peterson, Baylor College of Medicine Houston, TX, USA Volker Roth, ETH Zurich, Switzerland Udo Seiffert, Leibniz Institute, Gatersleben, Germany Anna Tramontano, Universit? di Roma "La Sapienza", Italy Jean Philippe Vert, Centre for Computational Biology Ecole des Mines de Paris, France *************************************************************** We are looking forward to meet you in Portofino! Roberto Tagliaferri and Giorgio Valentini -- =========================================== Giorgio Valentini D.S.I. - Universita' degli Studi di Milano - Italia Phone: +39 (02) 503.16225 e-mail: valentini at dsi.unimi.it http://homes.dsi.unimi.it/~valenti =========================================== From terry at salk.edu Fri Jan 12 21:05:36 2007 From: terry at salk.edu (Terry Sejnowski) Date: Fri, 12 Jan 2007 18:05:36 -0800 Subject: Connectionists: NEURAL COMPUTATION - March, 2007 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 19, Number 3 - March 1, 2007 Article Temporal Symmetry in Primary Auditory Cortex: Implications for Cortical Connectivity Jonathan Z. Simon, Didier A. Depireux, David J. Klein, Jonathan B. Fritz, and Shihab A. Shamma Letters Optimality Model of Unsupervised Spike-Timing Dependent Plasticity: Synaptic Memory and Weight Distribution Taro Toyoizumi, Jean-Pascal Pfister, Kazuyuki Aihara, and Wulfram Gerstner Nonparametric Modeling of Neural Point Processes via Stochastic Gradient Boosting Regression Wilson Truccolo and John P. Donoghue Synchrony of Neuronal Oscillations Controlled by GABAergic Reversal Potentials Ho Young Jeong and Boris Gutkin Reinforcement Learning State Estimator Jun Morimoto and Kenji Doya Training Recurrent Networks by Evolino Jürgen Schmidhuber, Daan Wierstra, Matteo Gagliolo, and Faustion Gomez A Generalized Divergence Measure for Nonnegative Matrix Factorization Raul Kompass Support Vector Ordinal Regression Wei Chu and S. Sathiya Keerthi Neighborhood Property-Based Pattern Selection For Support Vector Machines Hyunjung Shin and Sungzoon Cho Transductive Methods for the Distributed Ensemble Classification Problem David J.Miller and Siddharth Pal ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2007 - VOLUME 19 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $63.60 $114 $54 $57.24 Individual $100 $106.00 $154 $90 $95.40 Institution $782 $828.92 $836 $704 $746.24 * includes 6% GST MIT Press Journals, 238 Main Street, Suite 500, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu http://mitpressjournals.org/neuralcomp ----- From rsun at rpi.edu Mon Jan 15 13:22:33 2007 From: rsun at rpi.edu (Professor Ron Sun) Date: Mon, 15 Jan 2007 13:22:33 -0500 Subject: Connectionists: Reminder: Deadline for Paper Submission is January 31, 2007 --- IJCNN 2007 in Orlando, Florida Message-ID: Reminder: Deadline for Paper Submission is January 31, 2007 --- IJCNN 2007 in Orlando, Florida 2007 International Joint Conference on Neural Networks Orlando, Florida August 12-17, 2007 http://www.ijcnn2007.org The 2007 International Joint Conference on Neural Networks (IJCNN 2007), sponsored by the International Neural Network Society and co- sponsored by the IEEE Computational Intelligence Society, is the premier event in the field of neural networks. It covers all topics in neural network theories and applications, including, but not limited to: - Neural network models and analysis - Connectionist cognitive science and cognitive modeling (language, reasoning, perception, learning, memory, consciousness, emotion, etc.) - Computational neuroscience - Neuroengineering - Cognitive robotics, developmental robotics, and neural robotics - Data analysis and pattern recognition - Signal processing and image processing - Neural control - Neuroinformatics - Hybrid neural-symbolic, neuro-fuzzy, neuro-evolutionary systems, etc. - Bayesian models and other graphical models - Kernel methods - Learning methods: supervised, unsupervised, and reinforcement - Approximate dynamic programming and neural network approaches to optimization - Neural dynamics, complex systems, and chaos - Hardware implementations of neural networks and neuromorphic engineering - Neural networks applications (expert systems, embedded systems, data mining, Multi-agent systems, social computing, financial engineering, bioinformatics, telecommunication, manufacturing, etc.) IJCNN 2007 will feature plenary speakers, special sessions, moderated panel discussions, pre-conference tutorials, post-conference workshops, regular technical sessions, poster sessions, and social functions. Prospective authors are invited to submit complete papers of no more than six (6) pages (including results, figures, tables, and references) in IEEE two-column format. Authors should submit their papers in PDF through the online submission system, which will be available at the website: http://www.ijcnn2007.org. Important Dates: Paper Submission Deadline (including submissions to special sessions): January 31, 2007 Pre-Conference Tutorial and Post-Conference Workshop Proposals: January 31, 2007 Decision Notification: March 31, 2007 Camera-Ready Submission: April 30, 2007 For further information: http://www.ijcnn2007.org ======================================================== Professor Ron Sun Cognitive Science Department Rensselaer Polytechnic Institute 110 Eighth Street, Carnegie 302A Troy, NY 12180, USA phone: 518-276-3409 fax: 518-276-3017 email: rsun at rpi.edu web: http://www.cogsci.rpi.edu/~rsun ======================================================= From remi.munos at inria.fr Mon Jan 15 10:18:27 2007 From: remi.munos at inria.fr (Remi Munos) Date: Mon, 15 Jan 2007 16:18:27 +0100 Subject: Connectionists: Research positions at INRIA Futurs Lille, France Message-ID: <200701151618.27308.remi.munos@inria.fr> INRIA Futurs (french public research institute in Computer Science) is creating a new research institute in Lille, France, in close cooperation with the Universities of Lille. SequeL (Sequential Learning) is a new research project of INRIA Futurs Lille in Statistical Learning and Reinforcement Learning. We are currently searching for full-time (junior or senior) Research Scientists ("Charge de Recherche" and 'Directeur de recherche") for joining this INRIA team, as well as Doctorants and Post-Doctorant. The application deadline for full-time researchers is February 15th. We are particularly interested in candidates having a background in Machine Learning, Reinforcement Learning, Statistics, Control Theory, Game Theory, Monte-Carlo methods, or other domains of Machine Learning and applied Mathematics. Lille is the largest city in the north of France, belonging to a metropolis of a million inhabitants. By train it is located 60 minutes away from Paris, 38 minutes from Bruxelles, and 100 minutes from London. Futher information is available at: ? ?http://www.grappa.univ-lille3.fr/sequel In case of interest, please contact: Philippe Preux or Remi Munos. From christopher.kermorvant at a2ia.com Mon Jan 15 13:41:11 2007 From: christopher.kermorvant at a2ia.com (Christopher Kermorvant) Date: Mon, 15 Jan 2007 19:41:11 +0100 Subject: Connectionists: Open positions in Machine Learning in Paris Message-ID: <45ABCAC7.3020109@a2ia.com> --------------------------------------------- Open positions in Machine Learning in Paris --------------------------------------------- A2iA (Artificial Intelligence and Image Analysis) has several open positions for candidates with a Master Degree or PhD in Computer Science with a strong component in Artificial Intelligence, Machine Learning and Statistics. Candidates can apply for short time training, enroll in a PhD program or apply for a research engineer permanent position. Open positions are related to research and development of software modules for automatic recognition and classification of incoming mail : * printed and handwritten word recognition * document classification * information extraction Candidate must necessarily have a strong experience in : * software development in C++ and Python * statistical machine learning Knowledge of French and English is mandatory. All positions are located at A2iA in the center of Paris (7?me arrdt), France. Please send you resume and cover letter to Christopher Kermorvant AT a2ia.com From Eugene.Izhikevich at nsi.edu Mon Jan 15 14:34:24 2007 From: Eugene.Izhikevich at nsi.edu (Eugene M. Izhikevich) Date: Mon, 15 Jan 2007 11:34:24 -0800 Subject: Connectionists: New article on Dopamine and STDP Message-ID: <45ABD740.8010608@nsi.edu> Modulation of spike-timing-dependent plasticity (STDP) by dopamine (DA) can resolve many outstanding questions in cognitive neuroscience, in particular, the neurobiological (spiking) mechanism of credit assignment problem. Details can be found in the article E.M. Izhikevich (2007) Solving the Distal Reward Problem through Linkage of STDP and Dopamine Signaling. Cerebral Cortex, 10.1093/cercor/bhl152, available at http://vesicle.nsi.edu/users/izhikevich/publications/dastdp.pdf ABSTRACT: Learning the associations between cues and rewards (classical or Pavlovian conditioning) or between cues, actions, and rewards (instrumental or operant conditioning) involves reinforcement of neuronal activity by rewards or punishments. Typically, the reward comes seconds after reward-predicting cues or reward-triggering actions, creating an explanatory conundrum known in the behavioral literature as the "distal reward problem" and in the reinforcement learning literature as the "credit assignment problem". Indeed, how does the animal know which of the many cues and actions preceding the reward should be credited for the reward? In neural terms, in which sensory cues and motor actions correspond to neuronal firings, how does the brain know what firing patterns, out of an unlimited repertoire of all possible patterns, are responsible for the reward if the patterns are no longer there when the reward arrives? How does it know which spikes of which neurons result in the reward if *many* neurons fire during the waiting period to the reward? Finally, how does the common reinforcement signal in the form of the neuromodulator dopamine (DA) influence the right synapses at the right time, if DA is released globally to many synapses? Here we show how the conundrum is resolved by a model network of cortical spiking neurons with spike-timing-dependent plasticity (STDP) modulated by dopamine (DA). Although STDP is triggered by nearly-coincident firing patterns on a millisecond time scale, slow kinetics of subsequent synaptic plasticity is sensitive to changes in the extracellular DA concentration during the critical period of a few seconds. Random firings during the waiting period to the reward do not affect STDP, and hence make the network insensitive to the ongoing activity --- the key feature that distinguishes our approach from previous theoretical studies, which implicitly assume that the network be quiet during the waiting period or that the patterns be preserved until the reward arrives. This study emphasizes the importance of precise firing patterns in brain dynamics. -- Eugene M. Izhikevich, Ph.D., http://www.izhikevich.com The Neurosciences Institute, Eugene.Izhikevich at nsi.edu 10640 John J. Hopkins Drive tel:(858) 626-2063 San Diego, CA, 92121, USA fax:(858) 626-2099 From n.yousif at imperial.ac.uk Tue Jan 16 08:39:52 2007 From: n.yousif at imperial.ac.uk (Yousif, Nada) Date: Tue, 16 Jan 2007 13:39:52 -0000 Subject: Connectionists: DBS symposium second announcement Message-ID: <18BC110D9A023542A41960EE3D066CD4022A25BC@icex3.ic.ac.uk> Apologies if received more than once. ************************************************************************ ********************************************** ************************************************************************ ********************************************** SECOND ANNOUNCEMENT ************************************************************************ ********************************************** ************************************************************************ ********************************************** Theory and Neuroinformatics in Research Related to Deep Brain Stimulation 15-16 March 2007 Imperial College London Deep Brain Stimulation (DBS) is an increasingly used therapeutic procedure which is used to treat a series of neurological and psychiatric related disorders. We are organising an international symposium where researchers from different backgrounds will be able to meet in person, identify the direction of future research, and discuss possible collaborative projects in the DBS field. The preliminary programme and registration form are now available on the conference website: http://www1.imperial.ac.uk/medicine/about/divisions/neuro/news/informati cs07/ Early registration is recommended. From Aapo.Hyvarinen at helsinki.fi Mon Jan 15 07:57:55 2007 From: Aapo.Hyvarinen at helsinki.fi (Aapo Hyvarinen) Date: Mon, 15 Jan 2007 14:57:55 +0200 (EET) Subject: Connectionists: Post-doc in computational neuroscience/statistics/intelligence Message-ID: Hello [and apologies for cross-posting], I have a post-doc position available, starting any time during the first half of 2007, for a duration of approx. one year with possibility of extension. The location is Helsinki Institute for Information Technology, in the premises of the University of Helsinki, Finland. The topic can be anything related to the research of our group as outlined on http://www.cs.helsinki.fi/hiit_bru/index_neuro.html , in particular: - probabilistic theories of early vision (natural image statistics) - causal discovery (non-gaussian multivariate statistics) - exploratory analysis of brain imaging data - theory of unsupervised learning (e.g. score matching) - [a new topic:] learning action-related representations Please send your application to: aapo.hyvarinen-at-helsinki.fi Attach at least: CV, publication list, short statement of research interests, and names and email addresses of 2-3 people willing to give their opinion on your competence. Deadline is 10th February 2007. Aapo -- --------------------------------------------------- Aapo Hyvarinen Basic Research Unit of the Helsinki Institute for Information Technology, P.O.Box 68, 00014 University of Helsinki, Finland Physical address: Room A330, Exactum Dept of Computer Science, University of Helsinki Gustaf H?llstr?min katu 2b, 00560 Helsinki, Finland Home page: www.cs.helsinki.fi/aapo.hyvarinen/ --------------------------------------------------- From jaap.van.pelt at falw.vu.nl Mon Jan 15 08:19:32 2007 From: jaap.van.pelt at falw.vu.nl (Jaap van Pelt) Date: Mon, 15 Jan 2007 14:19:32 +0100 Subject: Connectionists: ESR position available Message-ID: <45AB7F64.7000908@falw.vu.nl> Early Stage Researcher position in Neuroscience / Neuroinformatics, VU / KNAW, Amsterdam, the Netherlands. In the framework of the European Union?s Marie Curie network for human resources and mobility activity, a new project ?NeuroVers-IT? investigating Neuro-Cognitive Science and Information Technology has been set up. The project aims at collaborative, highly multidisciplinary research between 11 European well-known research institutions in the areas of neuro-/cognitive sciences / biophysics and robotics / information technologies / mathematics. For this project, the Department of Experimental Neurophysiology at the Center for Neurogenomics and Cognitive Research (CNCR) of the Vrije Universiteit (VU) in Amsterdam is looking for an Early-Stage Researcher (holding a Master?s degree entitling her/him to pursue a PhD degree). A good knowledge of spoken and written English is required, in combination with experience in neuronal network research, neurophysiology and especially computational neuroscience. The project concerns a computational modeling study in Neuro-Dynamics, in particular oscillatory activity in cortical circuits complementing experimental recordings in acute cortical slices. The work will be conducted at the Department of Experimental Neurophysiology of CNCR of the Vrije Universiteit in Amsterdam. The ESR position is presently open and lasts until 1 July 2009. To be eligible the European candidate should not be a Dutch citizen and not have resided in the Netherlands for more than 12 months in the past 3 years. For information about these positions you may contact Dr. Jaap van Pelt, CNCR, jaap.van.pelt at falw.vu.nl, or Dr. Arjen van Ooyen, CNCR, arjen.van.ooyen at falw.vu.nl Please send your written application including your CV and other relevant material before 1st Feb 2007. -- *** ADDRESS CHANGE *** !!! Please notify my new coordinates !!! Dr. Jaap van Pelt Department of Experimental Neurophysiology Center for Neurogenomics and Cognitive Research Vrije Universiteit De Boelelaan 1085, 1081 HV Amsterdam, Room C446 The Netherlands E-mail: jaap.van.pelt at falw.vu.nl Phone: +31.20.5987043 Fax: +31.20.5987112 Web: http://www.bio.vu.nl/enf/vanpelt From l.wiskott at biologie.hu-berlin.de Tue Jan 16 09:12:20 2007 From: l.wiskott at biologie.hu-berlin.de (Laurenz Wiskott) Date: Tue, 16 Jan 2007 15:12:20 +0100 Subject: Connectionists: open PhD/postdoc position at the Humboldt-University Berlin Message-ID: <17836.56644.336912.246079@huxley.biologie.hu-berlin.de> Please forward this job advertisement to students who might be interested. Thanks, Laurenz Wiskott. ___________________________________________________________________________ Open Position for a PhD-Student or Postdoc in Machine Learning at the Institute for Theoretical Biology Humboldt University Berlin ___________________________________________________________________________ Institute: Institute for Theoretical Biology Humboldt-Universit?t zu Berlin Invalidenstra?e 43 D-10115 Berlin, Germany http://itb.biologie.hu-berlin.de/ The Institute for Theoretical Biology is a young and dynamic lab with four full professors, four junior research groups, and about 60 students and researchers doing interdisciplinary and innovative research in different areas of theoretical biology. Research group: The position is available in the group of Prof. Laurenz Wiskott and is funded by the DFG (Deutsche Forschungsgemeinschaft). Research topics: The goal of this project is to develop an algorithm for nonlinear blind source separation based on slow feature analysis and to apply it to medical data analysis. Some published preliminary work can be found at http://itb1.biologie.hu-berlin.de/~wiskott/Projects/ISFA.html. Teaching: There will be some duties as a teaching assistant, e.g. for the basic mathematics courses. Time: The position is available immediately. The appointment will be for 2(+1) years. Requirements: Candidates should have an education in physics, mathematics, computer science, electrical engineering or any related field. Required are strong mathematical and programming skills as well as the ability to communicate and work well in a team. Salary: Salary will be BAT IIa-O (part time for a PhD student) and will depend on age and family status. BAT is the regular salary scale for public employees in Germany. Inquiries: Informal inquiries can be addressed to Prof. Laurenz Wiskott . Application: Complete applications should be sent to Prof. Laurenz Wiskott at the address given above. Please send only copies and not original documents, since the applications will not be sent back. You can also send applications via email, but please make sure they are complete and in a convenient format. Handicapped applicants with corresponding qualifications will be considered preferentially. To increase the proportion of female scientists, applications of qualified females are especially welcome. Deadline: None. Applications will be accepted until the position is filled, as will be indicated on the web-page of this job advertisement; see below. WWW: The following web page contains additional information: http://itb.biologie.hu-berlin.de/~wiskott/2007-01-16-DFG-BSS-ITB-WWW.html. From angelo.arleo at snv.jussieu.fr Tue Jan 16 09:46:17 2007 From: angelo.arleo at snv.jussieu.fr (Angelo Arleo) Date: Tue, 16 Jan 2007 15:46:17 +0100 Subject: Connectionists: Call for papers: Special issue of the Journal of Integrative Neuroscience Message-ID: (We apologise for multiple copies of this message) ******************************* Call for papers for a Special Issue of the Journal of Integrative Neuroscience on "Multisensory Integration and Concurrent Parallel Memory Systems for Spatial Cognition" Deadline for Submission: March 15, 2007 ******************************** Spatial cognition is the ability of an animal to acquire spatial knowledge (e.g., spatio-temporal relations among environmental cues or events), organise it properly, and employ it to adapt its motor behaviour to the specific context. Alike other high-level brain functions, spatial memory calls upon parallel information processing mediated by multiple neural substrates that interact, either cooperatively or competitively, to promote appropriate spatial learning. Similar to animals, autonomous navigating artefacts need to interact with their environment and learn both low-level sensory- motor couplings and more abstract context representations supporting their spatial behaviour. At the sensory level, different perceptual modalities provide the navigator with a manifold description of the spatial context. The integration of these multimodal signals into a coherent representation is at the core of spatial cognition. At the action selection level, determining and maintaining a goal-directed trajectory involves multiple mnemonic processes, each of which promotes a specific solution (i.e., a navigation strategy) to the overall task. The capability of dynamically weighing the contribution of distinct memory systems is relevant to the issue of adapting the spatial behaviour to the complexity of the task. This special issue aims at promoting a multidisciplinary forum between experimentalists, theoreticians, and engineers in order to improve our understanding of biological and bio-mimetic spatial learning systems. Topics appropriate for this Special Issue include (but are not limited to): * the learning mechanisms (both at the synaptic plasticity level and at a higher level) mediating the integration of multimodal signals * the characterisation of the spatial information properties determining the cue selection process during the exploration of a novel environment * the principles underlying the minimisation of destructive interference between spatial memories acquired during lifelong learning * the multiple co-existing memory systems promoting spatial navigation * the anatomo-functional interrelations between the neural substrates (e.g., hippocampus, prefrontal and parietal cortices, basal ganglia, and cerebellum) mediating spatial learning * the principles regulating the cooperative/competitive relations between these parallel memory systems and determining the on-line shift between distinct navigation strategies Contributions postulating an integrative approach permitting to investigate the links between different description levels (e.g. between neural coding and behavior) are particularly welcome. Authors proposing theoretical or computational approaches should explicitly address issues like "the biological plausibility of the models" and "how the theoretical/simulation findings can lead to a better understanding of the neurobiological mechanisms underlying spatial cognition". Drafts must be submitted to spatial.learning at gmail.com and must be prepared according to the "Guidelines for contributions" of the Journal of Integrative Neuroscience (http://www.worldscinet.com/jin/ mkt/guidelines.shtml). ---------------------------------------------------- SUMMARY of IMPORTANT DATES ---------------------------------------------------- Deadline for paper submission: March 15, 2006 Expected publication date of the special issue: fall 2007 For sake of efficient editorial organisation, we ask the authors to inform us as soon as possible about their intention to send a contribution. Sincerely, Angelo Arleo & Ricardo Chavarriaga __________________________________________________________ Angelo ARLEO, Ph.D. Researcher, Laboratory of Neurobiology of Adaptive Processes University Pierre&Marie Curie, Box 14, 9 quai St. Bernard, 75005 Paris, France Phone: +33 (0)1 44 27 32 54 Mobile: +33 (0)6 89 89 07 23 Fax: +33 (0)1 44 27 22 80 email: angelo.arleo at snv.jussieu.fr web: http://npa.snv.jussieu.fr/npa_eng.htm __________________________________________________________ From bowlby at bu.edu Tue Jan 16 10:48:08 2007 From: bowlby at bu.edu (Brian Bowlby) Date: Tue, 16 Jan 2007 10:48:08 -0500 Subject: Connectionists: 11th ICCNS: Final Call for Abstracts Message-ID: <6E877EA2-A935-42A8-97A7-52C186EE6B5B@bu.edu> ELEVENTH INTERNATIONAL CONFERENCE ON COGNITIVE AND NEURAL SYSTEMS May 16 ? 19, 2007 Boston University 677 Beacon Street Boston, Massachusetts 02215 USA http://www.cns.bu.edu/meetings/ Sponsored by the Boston University Center for Adaptive Systems and Department of Cognitive and Neural Systems (http://www.cns.bu.edu/) with financial support from the National Science Foundation (http://cns.bu.edu/CELEST/) This interdisciplinary conference is attended each year by approximately 300 people from 30 countries around the world. As in previous years, the conference will focus on solutions to the questions: HOW DOES THE BRAIN CONTROL BEHAVIOR? HOW CAN TECHNOLOGY EMULATE BIOLOGICAL INTELLIGENCE? The conference is aimed at researchers and students of computational neuroscience, cognitive science, neural networks, neuromorphic engineering, and artificial intelligence. It includes invited lectures and contributed lectures and posters by experts on the biology and technology of how the brain and other intelligent systems adapt to a changing world. The conference is particularly interested in exploring how the brain and biologically-inspired algorithms and systems in engineering and technology can learn. Single-track oral and poster sessions enable all presented work to be highly visible. Three-hour poster sessions with no conflicting events will be held on two of the conference days. Posters will be up all day, and can also be viewed during breaks in the talk schedule. CONFIRMED INVITED CONFERENCE SPEAKERS Jorge L. Armony (McGill University) Exploring the role of the amygdala in emotional processing Gary Aston-Jones (Medical University of South Carolina) The cortex in context: Locus coeruleus, optimal performance, and maximal utility Nelson Cowan (University of Missouri-Columbia) Differences between long-term, short-term, and working memory Shimon Edelman (Cornell University) Learning language: Rationalists do it by the rules, empiricists do it to the rules James Enns (University of British Columbia ) Unconscious but under control: The role of intention in automated vision and action Michael Graziano (Princeton University) The organization of behavioral repertoire in motor cortex Jennifer Groh (Duke University) Looking at sounds: Neural computations for associating visual and auditory events Stephen Grossberg (Boston University) (Plenary Lecture) An emerging unified theory of cerebral cortex: From vision to cognition Alice Healy (University of Colorado) Training, retention, and transfer of knowledge and skills Marcia K. Johnson (Yale University) Using fMRI to explore components of reflective processing Philip Kellman (UCLA) Abstract relations in perception and perceptual learning Bart Krekelberg (Rutgers University) The neural basis of speed perception Joseph E. LeDoux (New York University) (Plenary Lecture) Fearful brains in an anxious world Hal Pashler (University of California San Diego) Enhancing learning and slowing forgetting: Some elementary (but neglected) questions Luiz Pessoa (Indiana University) Dynamic emotion perception: Neuroimaging studies of visual attention, awareness, and perceptual decisions Pieter Roelfsema (University of Amsterdam) Cortical algorithms for perceptual grouping Deb Roy (Massachusetts Institute of Technology) Meaning machines Reza Shadmehr (Johns Hopkins University) Motor adaptation and the timescales of memory Frank Tong (Vanderbilt University) From brain reading to mind reading: fMRI studies of human visual perception Workshop on Biologically-Inspired Cognitive Architectures Daniel Bullock (Boston University) Modeling neural circuits for reward-guided learning, evaluation, planning, and decision Dario Floreano (Swiss Federal Institute of Technology) Enactive robot vision Deepak Khosla (HRL) Biologically-Inspired Cognitive Architecture for integrated LEarning, Action and Perception (BICA-LEAP) John Laird (University of Michigan) TOSCA: Design and development challenges in brain-based cognitive architecture William Ross (MIT Lincoln Laboratory) Biologically inspired what-where video surveillance systems Patrick Winston (Massachusetts Institute of Technology) biologically inspired Steps toward ^ artificial intelligence CALL FOR ABSTRACTS Session Topics: * vision * object recognition * image understanding * neural circuit models * audition * neural system models * speech and language * mathematics of neural systems * unsupervised learning * robotics * supervised learning * hybrid systems (fuzzy, evolutionary, digital) * reinforcement and emotion * neuromorphic VLSI * sensory-motor control * industrial applications * cognition, planning, and attention * other * spatial mapping and navigation Contributed abstracts must be received, in English, by January 31, 2007. Email notification of acceptance will be provided by February 28, 2007. A meeting registration fee must accompany each Abstract. The fee will be returned if the Abstract is not accepted for presentation. Fees of accepted Abstracts will be returned on request only until April 13, 2007. Each Abstract must fit on one side of an 8.5" x 11" page with 1" margins on all sides in a single-spaced, single-column format with a font of 10 points or larger. The title, authors, affiliations, and surface and email addresses should begin each Abstract. A cover letter should include the abstract title; corresponding author and presenting author name, address, telephone, fax, and email address; requested preference for oral or poster presentation; and a first and second choice from the topics above, including whether it is biological (B) or technological (T) work [Example: first choice: vision (T); second choice: neural system models (B)]. Talks will be 15 minutes long. Posters will be displayed for a full day. Overhead, slide, and LCD computer projector facilities will be available for talks. Accepted Abstracts will be printed in the conference proceedings volume. No extended paper will be required. Four copies of the Abstract should be mailed to Cynthia Bradford, Boston University, CNS Department, 677 Beacon Street, Boston MA 02215 USA. Abstracts may also be submitted electronically as M/S Word files to cindy at bu.edu using the phrase ?11th ICCNS abstract submission? in the subject line. Fax submissions will not be accepted. REGISTRATION INFORMATION: Early registration is recommended using the registration form below. Student registrations must be accompanied by a letter of verification from a department chairperson or faculty/ research advisor. STUDENT TRAVEL FELLOWSHIPS: Fellowships for PhD candidates and postdoctoral fellows who do not live in the Boston area are available to help cover travel costs. The application deadline is January 31, 2007. Email notification will occur by February 28, 2007. Fellowship applications must be submitted as paper hardcopy to the abstract submission address shown above. Each application should include the applicant's CV; faculty or PhD research advisor's name, address, and email address; relevant courses and other educational data; and a list of research articles. A letter from the listed faculty or PhD advisor on institutional stationery must accompany the application and summarize how the candidate may benefit from the meeting. Fellowship applicants who also submit an Abstract need to include the registration fee payment with their Abstract submission. Fellowship checks will be distributed after the meeting. REGISTRATION FORM Eleventh International Conference on Cognitive and Neural Systems May 16-19, 2007 Boston University Department of Cognitive and Neural Systems 677 Beacon Street Boston, Massachusetts 02215 USA Fax: +1 617 353 7755 Mr/Ms/Dr/Prof:_____________________________________________________ Affiliation:_________________________________________________________ Address:__________________________________________________________ City, State, Postal Code:______________________________________________ Phone and Fax:_____________________________________________________ Email:____________________________________________________________ The registration fee includes the conference proceedings, a reception on Friday night, and 3 coffee breaks each day. CHECK ONE: ( ) $95 Conference (Regular) ( ) $65 Conference (Student) METHOD OF PAYMENT (please fax or mail): [ ] Enclosed is a check made payable to "Boston University" Checks must be made payable in US dollars and issued by a US correspondent bank. Each registrant is responsible for any and all bank charges. [ ] I wish to pay by credit card (MasterCard, Visa, or Discover Card only) Name as it appears on the card:___________________________________________ Type of card: _____________________________ Expiration date:________________ Account number: _______________________________________________________ Signature:____________________________________________________________ ? From steve at cns.bu.edu Tue Jan 16 16:31:32 2007 From: steve at cns.bu.edu (Stephen Grossberg) Date: Tue, 16 Jan 2007 16:31:32 -0500 Subject: Connectionists: laminar cortical dynamics of visual form and motion interactions Message-ID: The following article is now available at http://www.cns.bu.edu/Profiles/Grossberg : Berzhanskaya, J., Grossberg, S., and Mingolla, E. Laminar cortical dynamics of visual form and motion interactions during coherent object motion perception ABSTRACT How do visual form and motion processes cooperate to compute object motion when each process separately is insufficient? Consider, for example, a deer moving behind a bush. Here the partially occluded fragments of motion signals available to an observer must be coherently grouped into the motion of a single object. A 3D FORMOTION model comprises five important functional interactions involving the brain's form and motion systems that address such situations. Because the model's stages are analogous to areas of the primate visual system, we refer to the stages by corresponding anatomical names. In one of these functional interactions, 3D boundary representations, in which figures are separated from their backgrounds, are formed in cortical area V2. These depth-selective V2 boundaries select motion signals at the appropriate depths in MT via V2-to-MT signals. In another, motion signals in MT disambiguate locally incomplete or ambiguous boundary signals in V2 via MT-to-V1-to-V2 feedback. The third functional property concerns resolution of the aperture problem along straight moving contours by propagating the influence of unambiguous motion signals generated at contour terminators or corners. Here, sparse "feature tracking signals" from, e.g., line ends, are amplified to overwhelm numerically superior ambiguous motion signals along line segment interiors. In the fourth, a spatially anisotropic motion grouping process takes place across perceptual space via MT-MST feedback to integrate veridical feature-tracking and ambiguous motion signals to determine a global object motion percept. The fifth property uses the MT-MST feedback loop to convey an attentional priming signal from higher brain areas back to V1 and V2. The model's use of mechanisms such as divisive normalization, endstopping, cross-orientation inhibition, and long-range cooperation is described. Simulated data include: the degree of motion coherence of rotating shapes observed through apertures, the coherent vs. element motion percepts separated in depth during the chopsticks illusion, and the rigid vs. non-rigid appearance of rotating ellipses. Keywords: motion perception, depth perception, perceptual grouping, prestriate cortex, V1, V2, MT, MST From avellido at lsi.upc.edu Wed Jan 17 04:57:12 2007 From: avellido at lsi.upc.edu (Alfredo Vellido) Date: Wed, 17 Jan 2007 10:57:12 +0100 Subject: Connectionists: CFP IWANN 2007 special session In-Reply-To: <002201c6d8a2$2101de70$0b8dd696@lsi.us.es> References: <002201c6d8a2$2101de70$0b8dd696@lsi.us.es> Message-ID: <45ADF2F8.3090405@lsi.upc.edu> FYI *** CALL FOR PAPERS *** Apologies for crossposting SPECIAL SESSION: Neural networks and other Machine Learning methods in cancer research Organizers: Alfredo Vellido (Tech. Univ. Catalunya, Spain), Paulo J.G. Lisboa (Liverpool John Moores University, U.K.) To be organized at IWANN 2007 9th International Work-Conference on Artificial Neural Networks Palacio de Miramar, San Sebasti?n, Spain; June 20-22, 2007 http://iwann2005.ugr.es/2007/ THE SESSION IN BRIEF: Computer-assisted decision support in medicine has the baseline role of enhancing the consistency of care. Such consistency requires the management of uncertainty, which is an important goal for the use of any intelligent technology in support of medical diagnostic and prognostic decision-making. Neural Networks and Machine Learning methods in general can be applied to a wide range of data types and problems in cancer research. In this special session, we aim to put together a collection of diverse and up-to-date Neural Network and Machine Learning approaches to different problems in the field of oncology. Further information at: www.lsi.upc.edu/~avellido/research/IWANN2007-special-session.html PAPER SUBMISSION Authors must prepare original manuscripts which should not exceed 8 pages in the Springer LNCS format. Author instructions at: http://iwann2005.ugr.es/2007/authors.html The procedure for the submission of the final papers is the same for all contributions, and it will be made through the IWANN2007 web section. The authors are asked to indicate the Special Session title to which their paper is submitted. IMPORTANT DATES 4 February 2007 - Submission of papers by authors More on dates at http://iwann2005.ugr.es/2007/dates.html CONTACT Alfredo Vellido, PhD Department of Computing Languages and Systems. Polytechnic University of Catalonia Barcelona, Spain Tel.: +34 93 4137796 Fax: +34 93 4137833 email: avellido at lsi.upc.edu Paulo J.G. Lisboa, PhD School of Computing and Mathematical Sciences. Liverpool John Moores University Liverpool, United Kingdom Tel.: +44 151 2312225 Fax: +44 151 2074594 email: P.J.Lisboa at ljmu.ac.uk From t.heskes at science.ru.nl Thu Jan 18 08:34:31 2007 From: t.heskes at science.ru.nl (Tom Heskes) Date: Thu, 18 Jan 2007 14:34:31 +0100 Subject: Connectionists: Neurocomputing volume 70 (issues 4-6) Message-ID: <45AF7767.9090206@science.ru.nl> Neurocomputing volume 70 (issues 4-6) ------- SPECIAL PAPERS (International Conference on Intelligent Computing 2005 edited by De-Shuang Huang and Prashan Premaratne) Advanced Neurocomputing Theory and Methodology (editorial) De-Shuang Huang and Prashan Premaratne A neural network learning algorithm of chemical process modeling based on the extended Kalman filter Huizhong Yang, Jiang Li and Feng Ding A novel quantum swarm evolutionary algorithm and its applications Yan Wang, Xiao-Yue Feng, Yan-Xin Huang, Dong-Bing Pu, Wen-Gang Zhou, Yan-Chun Liang and Chun-Guang Zhou Recognition of blue-green algae in lakes using distributive genetic algorithm-based neural networks Zhihong Yao, Minrui Fei, Kang Li, Hainan Kong and Bo Zhao Adaptive feature representation for robust face recognition using context-aware approach Mi Young Nam, Rezaul Bashar and Phill Kyu Rhee Intelligent video tracking based on fuzzy-reasoning segmentation Jae-Soo Cho, Byoung-Ju Yun and Yun-Ho Ko An improved ant colony algorithm for fuzzy clustering in image segmentation Yanfang Han and Pengfei Shi Center particle swarm optimization Yu Liu, Zheng Qin, Zhewen Shi and Jiang Lu Neural-fuzzy control of truck backer-upper system using a clustering method Ying Li and Yuanchun Li Neural solution to the target intercept problems in a gun fire control system Yang Weon Lee Flexible neural trees ensemble for stock index modeling Yuehui Chen, Bo Yang and Ajith Abraham A neuro-fuzzy-based system for detecting abnormal patterns in wireless-capsule endoscopic images V.S. Kodogiannis, M. Boulougoura, J.N. Lygouras and I. Petrounias Predicting Gene Ontology functions based on support vector machines and statistical significance estimation Ran Bi, Yanhong Zhou, Feng Lu and Weiqiang Wang Fuzzy kappa for the agreement measure of fuzzy classifications Weibei Dou, Yuan Ren, Qian Wu, Su Ruan, Yanping Chen, Daniel Bloyet and Jean-Marc Constans Combination of two novel LDA-based methods for face recognition Wangmeng Zuo, Kuanquan Wang, David Zhang and Hongzhi Zhang Extracting the autonomic nerve wreath of iris based on an improved snake approach Li Yu, Kuanquan Wang and David Zhang Hybrid genetic algorithms for parameter identification of a hysteresis model of magnetostrictive actuators Jiaju Zheng, Shuying Cao, Hongli Wang and Wenmei Huang Neural input selection?A fast model-based approach Kang Li and Jian-Xun Peng On-line adaptive control for inverted pendulum balancing based on feedback-error-learning Xiaogang Ruan, Mingxiao Ding, Daoxiong Gong and Junfei Qiao Immune memory clonal selection algorithms for designing stack filters Weisheng Dong, Guangming Shi and Li Zhang Probabilistic 3D object recognition from 2D invariant view sequence based on similarity Rui Nian, Guangrong Ji, Wencang Zhao and Chen Feng Face detection using template matching and skin-color information Zhong Jin, Zhen Lou, Jingyu Yang and Quansen Sun Bayes classification based on minimum bounding spheres Jigang Wang, Predrag Neskovic and Leon N. Cooper A parallel hierarchical clustering algorithm for PCs cluster system Zhonghui Feng, Bing Zhou and Junyi Shen Prediction- and simulation-error based perceptron training: Solution space analysis and a novel combined training scheme Patrick Connally, Kang Li and George W. Irwin An extreme case of the generalized optimal discriminant transformation and its application to face recognition Xiao-Jun Wu, Jie-Ping Lu, Jing-Yu Yang, Shi-Tong Wang and Josef Kittler System identification of dynamic structure by the multi-branch BPNN Hong-Nan Li and Hao Yang Symmetrical null space LDA for face and ear recognition Zhang Xiaoxun and Jia Yunde Fingerprint matching based on weighting method and the SVM Jia Jia, Lianhong Cai, Pinyan Lu and Xuhui Liu Sequence-similarity kernels for SVMs to detect anomalies in system calls Shengfeng Tian, Shaomin Mu and Chuanhuan Yin Fault tolerant control based on stochastic distributions via MLP neural networks Yumin Zhang, Lei Guo, Haisheng Yu and Keyou Zhao A tabu based neural network learning algorithm Jian Ye, Junfei Qiao, Ming-ai Li and Xiaogang Ruan A feature-dependent fuzzy bidirectional flow for adaptive image sharpening Shujun Fu, Qiuqi Ruan, Wenqia Wang, Fuzheng Gao and Heng-Da Cheng Shape recognition based on neural networks trained by differential evolution algorithm Ji-Xiang Du, De-Shuang Huang, Xiao-Feng Wang and Xiao Gu Kernel based symmetrical principal component analysis for face classification Congde Lu, Chunmei Zhang, Taiyi Zhang and Wei Zhang 2D-LPP: A two-dimensional extension of locality preserving projections Sibao Chen, Haifeng Zhao, Min Kong and Bin Luo A face and fingerprint identity authentication system based on multi-route detection Jun Zhou, Guangda Su, Chunhong Jiang, Yafeng Deng and Congcong Li Adaptive H? tracking control for a class of uncertain nonlinear systems using radial-basis-function neural networks Yan-Sheng Yang and Xiao-Feng Wang A multivariate neuro-fuzzy system for foreign currency risk management decision making Vincent C.S. Lee and Hsiao Tshung Wong Online SVM regression algorithm-based adaptive inverse control Hui Wang, Daoying Pi and Youxian Sun ------- REGULAR PAPERS Quasi-sliding mode control strategy based on multiple-linear models Jeongho Cho, Jose C. Principe, Deniz Erdogmus and Mark A. Motter Hierarchical dynamical models of motor function S.M. Stringer and E.T. Rolls Criticality of lateral inhibition for edge enhancement in neural systems Pradeep Arkachar and Meghanad D. Wagh Stability and spectra of randomly connected excitatory cortical networks R.T. Gray and P.A. Robinson A new approach to solve the traveling salesman problem Paulo Henrique Siqueira, Maria Teresinha Arns Steiner and S?rgio Scheer Convergent design of piecewise linear neural networks Hema Chandrasekaran, Jiang Li, W.H. Delashmit, P.L. Narasimha, Changhua Yu and Michael T. Manry A new image classification technique using tree-structured regional features Tommy W.S. Chow and M.K.M. Rahman ------- BRIEF PAPERS An integrate-and-fire-based auditory nerve model and its response to high-rate pulse train Fei Chen and Yuan-Ting Zhang A method for speeding up feature extraction based on KPCA Yong Xu, David Zhang, Fengxi Song, Jing-Yu Yang, Zhong Jing and Miao Li Adaptive neural network control of uncertain nonlinear systems with nonsmooth actuator nonlinearities Jing Zhou, Meng Joo Er and Jacek M. Zurada Passivity analysis of integro-differential neural networks with time-varying delays Xuyang Lou and Baotong Cui Data mining neural spike trains for the identification of behavioural triggers using evolutionary algorithms Richard Stafford and F. Claire Rind Some criteria for asymptotic stability of Cohen?Grossberg neural networks with time-varying delays Wei Wu, Bao Tong Cui and Xu Yang Lou Support vector perceptrons A. Navia-V?zquez A class of binary images thinning using two PCNNs Lifeng Shang and Zhang Yi Exponential stability of impulsive neural networks with time-varying delays and reaction?diffusion terms Jianlong Qiu ------- JOURNAL SITE: http://www.elsevier.com/locate/neucom SCIENCE DIRECT: http://www.sciencedirect.com/science/journal/09252312 From eickhoff at hni.upb.de Thu Jan 18 10:41:12 2007 From: eickhoff at hni.upb.de (Ralf Eickhoff) Date: Thu, 18 Jan 2007 16:41:12 +0100 Subject: Connectionists: =?iso-8859-1?q?CFP_-_IWANN_2007=2C_special_sessio?= =?iso-8859-1?q?n_=22Neural_inspired_architectures_for_nanoelectron?= =?iso-8859-1?q?ics=22?= Message-ID: <005401c73b17$163a6200$42af2600$@upb.de> Apologies if you receive more than one copy of this email. ---------------------------------------------------------- Dear colleagues, You are invited to submit a paper to the special session "Neural inspired architectures for nanoelectronics" which is organized during the IWANN 2007. Deadline for Paper Submissions: February 4, 2007 Paper length: 8 pages The 9th International Work-Conference on Artificial Neural Networks (IWANN'2007) (Computational and Ambient Intelligence) will take place in San Sebasti?n (Spain) June 20-22, 2007, within the context of the XXVI Summer Courses of the Basque Country University (UPV/EHU). This biennial meeting focuses on the foundations, theory, models and applications of systems inspired on nature (neural networks, fuzzy logic and evolutive systems). The major goal of this special session is the discussion and investigation of new architectures adapted to nanoscale devices and to their integration based on neural principles. Bringing together researchers from different disciplines, e.g. neuroscience and circuit technology, this special session advances the discussion and development of various ways in which the brain could serve as an inspiration for future nano-architectures. Because recent developments in the field of neural networks, cognitive science, and bio-engineering have made it possible to understand more about primary biological systems, emerging computing systems can benefit from various characteristics of the brain such as modular organization, robustness, fault tolerance, power-efficient operation, and synchronization. Concurrently, the effective use of emerging nanoscale electronics will require accompanying research on circuits and architectures to take advantage of the increased density and to handle arising challenges such as low-power operation, reliable and asynchronous computing or manageable design complexity. Combining both research fields, neural principles can serve as inspirations for designing novel and innovative architectures in these emerging technologies, which is discussed in more detail in this special session Accepted papers of this special session will be included in the proceedings. As in previous editions of IWANN, the publication of the proceedings is prepared with Springer-Verlag on Lecture Notes on Computer Science (LNCS) series, and the book will be available on-site. Further information: http://iwann2005.ugr.es/2007/ Do not hesitate to contact me! Best regards, Ralf -------------------------------------------- Dipl.-Ing. Ralf Eickhoff Dresden University of Technology Chair for Circuit Design and Network Theory Barkhausenbau 158 Helmholtzstrasse 18 01069 Dresden Tel: +49 (0)351 463-33084 Fax: +49 (0)351 463-38736 ralf.eickhoff at tu-dresden.de www.iee.et.tu-dresden.de/iee/ccn From terry at salk.edu Fri Jan 19 00:52:12 2007 From: terry at salk.edu (Terry Sejnowski) Date: Thu, 18 Jan 2007 21:52:12 -0800 Subject: Connectionists: NEURAL COMPUTATION - February, 2007 In-Reply-To: Message-ID: Neural Computation - Contents - Volume 19, Number 2 - February 1, 2007 Article The Astrocyte as a Gatekeeper of Synaptic Information Transfer Herbert Levine, Vladislav Volman, and Eshel Ben-Jacob Letters Thermodynamically-Equivalent Silicon Models of Voltage-Dependent Ion Channels Kwabena Boahen and Kai M. Hynna Spatiotemporal Conversion of Auditory Information for Cochleotopic Mapping Osamu Hoshino Reducing Spike Train Variability: A Computational Theory of Spike-Timing Dependent Plasticity Sander M. Bohte and Michael C. Mozer Fast Population coding Quentin Huys, Richard Zemel , Rama Natarajan , Peter Dayan The basal ganglia and cortex implement optimal decision making between alternative actions Rafal Bogacz and Kevin Gurney Realistically coupled neural mass models can generate EEG rhythms Roberto Sotero, Nelson Trujillo-Barreto , Yasser Iturria-Medina , Felix Carbonell , Juan Jimenez Dimension Selection for Feature Selection and Dimension Reduction with Principal and Independent Component Analsysis Inge Koch and Kanta Naito One-bit Matching Theorem for ICA, Convex-Concave Programming on Polyhedral-set, and Distribution Approximation for Combinatorics Lei Xu Boundedness and Stability for Integrodifferential Equations Modeling Neural Field with Time Delay Lou Xuyang and Baotong Cui ----- ON-LINE - http://neco.mitpress.org/ SUBSCRIPTIONS - 2007 - VOLUME 19 - 12 ISSUES Electronic only USA Canada* Others USA Canada* Student/Retired $60 $63.60 $114 $54 $57.24 Individual $100 $106.00 $154 $90 $95.40 Institution $782 $828.92 $836 $704 $746.24 * includes 6% GST MIT Press Journals, 238 Main Street, Suite 500, Cambridge, MA 02142-9902. Tel: (617) 253-2889 FAX: (617) 577-1545 journals-orders at mit.edu http://mitpressjournals.org/neuralcomp ----- From dwang at cse.ohio-state.edu Fri Jan 19 07:18:28 2007 From: dwang at cse.ohio-state.edu (DeLiang Wang) Date: Fri, 19 Jan 2007 07:18:28 -0500 Subject: Connectionists: New CASA book promotion ending soon Message-ID: <45B0B714.3010304@cse.ohio-state.edu> Dear List, A few months back we announced a 20% new book discount for Computational Auditory Scene Analysis: Principles, Algorithms, and Applications, edited by us and published by Wiley jointly with IEEE Press. This is a reminder that the discount will expire on Feb. 1. The hardback is priced at $89.95, and with the discount the price comes down to $71.96. The discount is available through Wiley's website at www.wiley.com/ieee. The promotion code is 'CASA1'. If you have problems obtaining the promotion price please contact Maria Corpuz at 'mcorpuz at wiley.com' (phone: 201-748-7668). This 10-chapter book covers the following topics comprehensively: - Fundamentals of computational auditory scene analysis - Multiple F0 estimation - Feature-based speech segregation - Model-based scene analysis - Binaural sound localization - Location-based grouping - Reverberation - Analysis of musical audio signals - Robust automatic speech recognition - Neural and perceptual modeling There is also a companion website for the book at http://www.casabook.org which contains CASA resources including sound demos, evaluation corpora, and program code. Thanks, DeLiang Wang and Guy Brown From frederic.alexandre at loria.fr Fri Jan 19 10:39:36 2007 From: frederic.alexandre at loria.fr (Frederic Alexandre) Date: Fri, 19 Jan 2007 16:39:36 +0100 Subject: Connectionists: Research Position at INRIA Lorraine, France Message-ID: <45B0E638.4020001@loria.fr> The INRIA (the french national institute for research in computer science and control) will be hiring five full-time (3 junior, 2 senior) research scientists at its INRIA Lorraine research unit in 2007. These are tenured positions. In this context, the Cortex group (http://cortex.loria.fr) is looking for candidates having a background in Computational Neuroscience and Machine Learning (cf. Scientific Context below). The application deadline is February 15th. Nancy is a mid-sized city located in eastern France, close to Belgium, Germany and Luxembourg. The INRIA research unit is located on the university campus. In case of interest please contact Frederic.Alexandre at loria.fr For more information about the application procedure please check this page: http://www.inria.fr/travailler/opportunites/chercheurs.en.html ----------------------------------------------------------------- Scientific Context: A recent and very strong trend in computer science is to develop models and algorithms in interaction with biology and medical science. Today, computing resources allow to deal with the huge amount of data and the complexity of biological phenomena. Biologists now have great expectations from computer science, through both data mining and computational modeling. Several multidisciplinary research labs have been thus created, which illustrates the increasing significance of this collaboration between biologists and computer scientists. Neuroscience is a very active field of research, where the multidisciplinary aspect is prominent. Even if they still often work separately, physiologists, neuropsychologists, computer scientists, physicists, anatomists bring together different means to study the wide complexity of the brain. Among these lines of research, computational neuroscience more specifically aims at using computational principles to better understand the brain. With regards to the progress that has been made in mathematics, computer science, anatomy, neuro-biology, physiology, imaging, and behavioral science, computational neuroscience provides a new and unique interdisciplinary cooperation framework between researchers of these scientific domains. It combines experiments with data analysis and computer simulation on the basis of strong theoretical concepts, and it aims at modelling, simulating and also understanding mechanisms that underlie neural processes such as perception, action, learning, memory or cognition. Two fields of research are generally considered: 1. The first one corresponds to understanding the adaptative and distributed computation mode that is used by neural systems. This requires a computational study of the properties of these mechanisms, such as: emergence, asynchronism, temporality, genericity, modularity, robustness and adaptability. Two levels of description are studied in the field. * Spiking models focus on very specific data and brain functions, at the neuronal level, and organize computation around fundamental neuronal events: spikes. * Behavioral models are elaborated from integrated data and multimodal functionalities and wish to understand more complex functions, described in terms of information flow, at the level of populations of neurons and more global neuronal activity. 2. The second field of research deals with experimental data (from cellular recordings to behavioral analysis) which are today available in huge quantities, more and more precise but also more and more complex to analyze. Such data can be exploited to extract new knowledge directly from living neuronal structures and to feed computational models with real information. Data mining approaches and other signal interpretation techniques are reconsidered and adapted to the specific nature of such data, i.e. temporal, highly multidimensional, noisy, multiscale and often sparse data. Results obtained from these researches are twofold: 1. Building and assessing models, as well as mining experimental data can lead to predictions and other hypotheses that can orient further research in experimental neuroscience. Today, computational models are able to offer new approaches of the complex relations between the structural and the functional level of the brain. 2. Inspiration from these elementary biological mechanisms can bring new and powerful algorithms and computation paradigms to computer science. Similarly, the fundamental duality of neurons seen as processing units and elementary data storage is a major source of inspiration to adapt processing architecture to algorithms and to embed neuronal processing in fine grain distributed processing. From sok at cs.york.ac.uk Fri Jan 19 13:17:12 2007 From: sok at cs.york.ac.uk (sok@cs.york.ac.uk) Date: Fri, 19 Jan 2007 18:17:12 +0000 (GMT) Subject: Connectionists: Studentships available: MSc in Natural Computation Message-ID: Fully Funded EPSRC Studentships/Scholarships for MSc Natural Computation Department of Computer Science, University of York, UK http://www.cs.york.ac.uk/gsp/NC Applications are invited for the advanced 12 month MSc programme in Natural Computation - computing inspired by the natural world, by biology, physics and chemistry. This course explores the state of the art in natural computation from the perspective of nature-inspired algorithms; by considering novel views of what constitute computation; and examining how the physical and bio-chemical world provides new foundations for computing. This MSc is intended to provide a route into a PhD or research in this rapidly expanding field. Students choose eight taught modules, covering Bio-inspired Computation (neural and evolutionary algorithms, artificial immune systems, swarms, L-systems, simulation of biosystems); Embodied Computation (quantum conputing, DNA and chemical computing, and evolvable hardware); and Complexity and Emergence (adaptive agents, dynamical systems and emergence). This is followed by a research project. The Department of Computer Science is a research intensive department and was rated 6* in the last research assessment exercise. The Non-Standard Computation Research Group has more than 20 researchers (including teaching and research staff, and research students) working on a wide range of topics in natural computation. Details of how to apply are on the web at http://www.cs.york.ac.uk/gsp. Typically you will have achieved at least a second class degree in Computer Science or a related discipline with an appropriate mathematical basis. We will also consider applicants who have appropriate industrial experience instead. The programme is supported by the EPSRC through its Collaborative Training Account and by a number of leading companies including Microsoft, Rolls-Royce and QinetiQ. Support from the EPSRC and Microsoft mean we have a number of studentships to award to suitably qualified students, covering fees and maintenance costs (UK students) or fees only (EU students). Programme commences October 2007. Applications will be considered until places are filled, but studentships will be allocated in July. -- ___________________________________________________________________ Dr Simon O'Keefe PHONE +44 (0)1904 432762 EMAIL: sok at cs.york.ac.uk Dept of Computer Science, University of York, York, YO10 5DD (U.K.) From rbunnao at ipam.ucla.edu Fri Jan 19 19:11:43 2007 From: rbunnao at ipam.ucla.edu (Randy Bunnao) Date: Fri, 19 Jan 2007 16:11:43 -0800 Subject: Connectionists: Announcement for Graduate Summer School: Probabilistic Models of Cognition: The Mathematics of Mind, July 9 - 27, 2007 Message-ID: <00c801c73c27$9118c820$5d2e6180@Rayleigh> * * * * PROGRAM ANNOUNCEMENT * * * * * GRADUATE SUMMER SCHOOL Probabilistic Models of Cognition: The Mathematics of Mind July 9 - 27, 2007 Program Website: http://www.ipam.ucla.edu/programs/gss2007/ Introduction - "Probabilistic Models of Cognition: The Mathematics of Mind" will involve leaders from Cognitive Science and experts from Computer Science, Mathematics and Statistics, who are interested in making bridges to Cognitive Science. The goal is to develop a common mathematical framework for all aspects of cognition, and review how it explains empirical phenomena in the major areas of cognitive science - including vision, memory, reasoning, learning, planning, and language. The summer school is motivated by recent advances which offer the promise of modeling human cognition mathematically. These advances have occurred largely because the mathematical and computational tools developed for designing artificial systems are beginning to make an impact on theoretical and empirical work in Cognitive Science. In turn, Cognitive Science offers an enormous range of complex problems which challenge and test these theories. Registration & Funding - Applications for funding (i.e. travel and housing) will be accepted up until March 15, 2007. Applications received after that date will be considered if funds are still available. For the fullest consideration we urge you to apply as early as possible. You can apply for the entire three-week program, or just a part of it. Those who want to attend and are not applying for funding can register for the program. Please apply/register through the program website. Email questions to: gss2007 at ipam.ucla.edu Contact Information: UCLA Institute for Pure and Applied Mathematics (IPAM) 460 Portola Plaza Los Angeles CA 90095-7121 P: 310 825-4755 F: 310 825-4756 Website: http://www.ipam.ucla.edu From samikula at ucdavis.edu Sat Jan 20 01:06:49 2007 From: samikula at ucdavis.edu (Shawn Mikula) Date: Fri, 19 Jan 2007 22:06:49 -0800 (PST) Subject: Connectionists: Internet-Enabled High-Resolution Brain Mapping and Virtual Microscopy Message-ID: <200701200606.l0K66n5n021220@phaenicia.ucdavis.edu> The following article is now available at http://brainmaps.org/index.php?p=publications Mikula S, Trotts I, Stone JM, and Jones EG Internet-Enabled High-Resolution Brain Mapping and Virtual Microscopy ABSTRACT Virtual microscopy involves the conversion of histological sections mounted on glass microscope slides to high resolution digital images. Virtual microscopy offers several advantages over traditional microscopy, including remote viewing and data-sharing, annotation, and various forms of data-mining. We describe a method utilizing virtual microscopy for generation of internet-enabled, high-resolution brain maps and atlases. Virtual microscopy-based digital brain atlases have resolutions approaching 100,000 dpi, which exceeds by three or more orders of magnitude resolutions obtainable in conventional print atlases, MRI, and flat-bed scanning. Virtual microscopy-based digital brain atlases are superior to conventional print atlases in five respects: 1) resolution, 2) annotation, 3) interaction, 4) data integration, and 5) data-mining. Implementation of virtual microscopy-based digital brain atlases is located at BrainMaps.org, which is based on more than 10 million megapixels (35 terabytes) of scanned images of serial sections of primate and non-primate brains with a resolution of 0.46 microns/pixel (55,000 dpi). The method can be replicated by labs seeking to increase accessibility and sharing of neuroanatomical data. Online tools offer the possibility of visualizing and exploring completely digitized sections of brains at a sub-neuronal level, and can facilitate large-scale connectional tracing, histochemical and stereological analyses. From alfredo.petrosino at uniparthenope.it Sat Jan 20 11:47:37 2007 From: alfredo.petrosino at uniparthenope.it (Alfredo Petrosino) Date: Sat, 20 Jan 2007 17:47:37 +0100 Subject: Connectionists: SCIP Session@WILF2007 Message-ID: <45ACAF250020C363@vsmtp4.tin.it> (added by postmaster@virgilio.it) Please accept our apologies if you have received multiple copies of this message. =============================================================== CALL FOR PAPERS =============================================================== Special Session of WILF2007 on "Soft Computing in Image Processing" HYPERLINK "http://wilf2007.disi.unige.it/"http://wilf2007.disi.unige.it/ Portofino Vetta - Ruta di Camogli, Genova (Italy) July 7-10, 2007 =============================================================== SUBMISSION DEADLINE : March 3 2007 =============================================================== =============================================================== SESSION AIMS =============================================================== For over four decades, researchers in the area of image analysis have developed numerous methods and systems, many of which based on probabilistic paradigms, such as the well-known Bayesian decision rule and evidence-based decision-making systems. The main assumption is that physical laws are ruled by Aristotelic logic; in other words they arise from a crisp-world assumption. Anyway, this assumption is not always true in the physical world; as a matter of fact, crisp assumptions work for some problems, while they fails miserably whenever imprecision and accuracy are not following probabilistic rules. The rise of several major seminal theories proposed in early 60 including fuzzy logic, genetic algorithms, evolutionary computation, neural networks and their combination (the soft-computing paradigm in brief) are now leading techniques, allows to incorporate imprecision and incomplete information, and to model very complex systems, making them a useful tool in many scientific areas. These new methods may become more effective and powerful in real-world applications and can offer viable and effective solutions to some of the most difficult problems in image and pattern analysis. The purpose of this special session is to demonstrate some recent successes in solving image analysis problems by soft computing techniques and hopefully to motivate other image processing researchers to utilize this technology to solve their real-world problems. It will cover a range of domains, from more traditional ones such as image analysis at low, medium and high level, including pattern recognition and all the topics inherent to computer vision, all treated by means of soft-computing techniques. Topics include but are not limited to: -Soft computing algorithms for denoising and restoration -Soft computing techniques for pattern recognition -Soft computing algorithms for digital image processing, coding and encryption -Soft computing in computer vision -Soft computing algorithms for video content-based indexing and retrieval -Soft multimedia data analysis and visualization: texture, color, content, etc. -Applications, i.e. visual surveillance, face recognition, medical imaging, remote sensing, etc. =============================================================== SUBMISSION TO THE SPECIAL SESSION =============================================================== Manuscripts, prepared according to the Springer LNCS format (see Instructions for LNCS Authors of "Proceedings and Other Multiauthor Volumes" downloadable at HYPERLINK "http://www.springer.com/"http://www.springer.com/) may not be longer than 6 pages, including a cover sheet stating (1) Paper title, (2) Keyword(s), (3) Authors names and affiliations, (4) Contact Author's name and contact details including telephone/fax numbers and e-mail address, and (5) an Abstract (200 words). The paper must be submitted by March 3 2007 using the submission system HYPERLINK "http://wilf2007.disi.unige.it/openconf/openconf-wilf2007/index.php"http://w ilf2007.disi.unige.it/openconf/openconf-wilf2007/index.php or sending directly the paper to the email address HYPERLINK "mailto:alfredo.petrosino at uniparthenope.it"alfredo.petrosino at uniparthenope.i t indicating in the subject "SCIP Session". =============================================================== PROCEEDINGS =============================================================== All papers will be blind peer-reviewed by at least two independent reviewers. All accepted papers submitted by registered participants will be published in the Lecture Notes on Computer Science Series, Springer. A selection of papers will be peer reviewed for originality, technical contents and relevance and will be considered for publication in a special issue of an international journal about image processing and computer vision we are planning. The expected publication date is mid of 2008. =============================================================== SESSION CHAIRS =============================================================== Isabelle Bloch, Ecole Nationale Sup?rieure des T?l?communications, CNRS, Dept TSI, France Alfredo Petrosino, Dept. of Applied Science, University of Naples "Parthenope", Italy -- No virus found in this outgoing message. Checked by AVG Free Edition. Version: 7.1.410 / Virus Database: 268.16.14/636 - Release Date: 18/01/2007 -- No virus found in this outgoing message. Checked by AVG Free Edition. Version: 7.1.410 / Virus Database: 268.17.1/640 - Release Date: 19/01/2007 -- No virus found in this outgoing message. Checked by AVG Free Edition. Version: 7.1.410 / Virus Database: 268.17.1/640 - Release Date: 19/01/2007 From notify at teuscher.ch Sun Jan 21 20:37:53 2007 From: notify at teuscher.ch (Christof Teuscher) Date: Sun, 21 Jan 2007 18:37:53 -0700 Subject: Connectionists: CFP | Neural and unconventional computation workshop Message-ID: ---------------------------------------------------------------------- CALL FOR CONTRIBUTIONS AND PARTICIPATION ---------------------------------------------------------------------- Neural Computation workshop as part of "Unconventional Computation: Quo Vadis?" workshop http://cnls.lanl.gov/uc07 March 21-23, 2007, Santa Fe, NM, USA Unconventional computation is an interdisciplinary research area with the main goal to enrich or go beyond the standard models. As part of the general theme of this workshop, the Santa Fe Institute is organizing a half-day workshop on Neural Computation. This workshop will bring together experimental neuroscientists, computational neuroscientists, and computer scientists to ask "Does the brain 'compute'?". If so, "In what sense?". If not, "What forms of non-computational information processing does the brain perform?". Are there "computational primitives" for the brain that represent first-level abstractions for the brain in the same sense that binary arithmetic and Boolean algebra are "computational primitives" for Von Neumann architectures? SUBMISSION and REGISTRATION: The deadline for submission of one-page abstracts for contributed presentations and posters is Friday, February 9, 2007. More information about the conference, including instructions for registering, submitting papers, reserving accommodations, and applying for travel awards, is available at the conference web site: http://cnls.lanl.gov/uc07 PUBLICATION: The journal Physica D will publish a special issue after the workshop with selected contributions from both invited speakers and the contributors. Contributions are by invitation only and will be peer reviewed just like any regular submission to the journal. We look forward to seeing you in beautiful Santa Fe! From cabestan at eel.upc.edu Sat Jan 20 15:25:49 2007 From: cabestan at eel.upc.edu (Joan Cabestany) Date: Sat, 20 Jan 2007 21:25:49 +0100 Subject: Connectionists: Remainder and last CFP for IWANN2007 Message-ID: Dear colleague, This is our remainder and last CFP for IWANN2007, the 9th International Work-Conference on Artificial Neural Networks to be held next June 20-22, 2007 in San Sebastian (Spain). You are cordially invited to participate by submitting a paper. You can participate submitting your work to a specific Special Session or to the general list of IWANN. Please, find extended information concerning the event and the special sessions at the page: http://www.iwann-conference.org/2007/ http://www.iwann-conference.org/2007/special.html The proceedings will include all the accepted communications of registered authors to the conference (tutorials, oral and posters). As in previous editions of IWANN, we will publish the proceedings with Springer-Verlag on Lecture Notes on Computer Science (LNCS) series, and the book will be available on-site. It is also foreseen the publication of an extended version of selected papers in a special issue of the Neurocomputing journal (Elsevier). As specified in the corresponding section of the above webpage, Special sessions organizers have the autonomy in promoting their sessions, appointing the possible additional reviewers for the session papers (possible including the organizer him/herself), chairing their respective sessions and proposing their co-organizer and/or co-chair. You can obtain and freely print a copy of a more detailed Call For Papers at: < http://www.iwann-conference.org/2007/pdf/call_for_papers_iwann2007.pdf> http://www.iwann-conference.org/2007/pdf/call_for_papers_iwann2007.pdf Do not hesitate to access the conference web site : < http://www.iwann-conference.org/2007> http://www.iwann-conference.org/2007or to contact us by e-mail for further questions or suggestions at: iwann2007pc at dte.uma.es We hope this conference could be of your interest. Cordially yours Joan Cabestany Alberto Prieto Francisco Sandoval Co-Chairmen of IWANN2007 Conference Very important dates: * Submission of regular papers: February 4, 2007 * Early registration: March 25, 2007 * Conference dates: June 20 to 22, 2007 ---------------------------------------------------------------------------- ------- Joan Cabestany - Professor Electronic Engineering Dept. UPC - Technical University of Catalunya Jordi Girona, 1-3 Building C4 08034 BARCELONA - Spain Phone: + 34 93 401 6742/ + 34 609 766001 E-mail: cabestan at eel.upc.edu Web: http://csse.upc.es ---------------------------------------------------------------------------- ------- From mbethge at tuebingen.mpg.de Wed Jan 24 13:22:31 2007 From: mbethge at tuebingen.mpg.de (Matthias Bethge) Date: Wed, 24 Jan 2007 19:22:31 +0100 Subject: Connectionists: Postdoc Position in Computational Neuroscience/Psychophysics References: Message-ID: ========================= open postdoc position ========================= The newly established research group `Computational Vision and Neuroscience' at the Max-Planck-Institute for Biological Cybernetics in Tuebingen has an open position for one postdoc, starting from April 2007 onwards. The ideal candidate would have a background in psychophysics and would be interested in pursuing research with a strong emphasis on computational questions. The project aims to link mathematical concepts in computational vision to empirically measurable properties of human visual processing. In particular, we seek to test and explore which nonlinear processes matter most during the transition from local, gradual cues defined in low-level image representations to the global percept caused by an image. We are seeking an outstanding candidate with a background in psychophysics and/or theoretical neuroscience in early or mid-level vision. We also expect and encourage candidates to bring in their own ideas in shaping the project. The group is funded by the `Bernstein award' to Matthias Bethge and entertains close links to the Empirical Inference Department headed by Bernhard Schoelkopf. The MPI provides an excellent research environment with possibilities for multiple interactions between neurobiological, psychophysical, and theoretical vision research. Possible collaborations of particular interest to this project include joint work with Felix Wichmann and Roland Fleming. The salary will be on the level of TVoD 13 (BAT IIa) or higher, and the duration of the contract is negotiable. For additional information, see http://www.kyb.tuebingen.mpg.de/bs/groups/cvn/, or contact mbethge at tuebingen.mpg.de . From odobez at idiap.ch Wed Jan 24 06:11:14 2007 From: odobez at idiap.ch (Jean-Marc Odobez) Date: Wed, 24 Jan 2007 12:11:14 +0100 Subject: Connectionists: postdoc/research engineer open position Message-ID: <45B73ED2.4060501@idiap.ch> The IDIAP Research Institute (http://idiap.epfl.ch or http://www.idiap.ch), an EPFL laboratory (Swiss Federal Insitute of Technology, Lausanne) seeks immediateley qualified candidates for either a postdoctoral position or an engineer in the field of computer vision and machine learning. Context : --------- The research will be conducted in the context of the CARETAKER project, a multi-site project funded by the European Community (8 partners in 7 countries), that started in 2006. The project aims at extracting structured knowledge (events defined through ontologies) from multimedia collections recorded over a network of cameras and microphones (in real public transportation sites). In this project, IDIAP will investigate and develop principled methods based on generative and discriminative (conditional random field, margin-based) modeling to address various issues in multi-person tracking, event recognition, and visual data mining (data fusion, uncertainty handling, lack or small amount of labeled training data, multi-person complex events, unusual event detection, etc). Requirement ------------ The recruited person will join a team of one postdoc and 2 PhD students, and will be involved in the research and software development of the CARETAKER project. She/he should have a strong background in statistics, applied mathematics, and computer vision. Experience in one or several of the following areas is required: - software development - computer vision and tracking - statistical learning - knowledge modeling - event recognition and discovery The applicant should be familiar with C/C++ programming under a Unix/Linux environment. Starting date: immediately Contract duration: 12 months About IDIAP: ------------ IDIAP is a research institute associated with EPFL (Swiss Federal Institute of Technology, Lausanne) active in the fields of information retrieval, speech, machine learning and vision (www.idiap.ch). IDIAP is located in the town of Martigny in Valais, a scenic region in the south of Switzerland, surrounded by the highest mountains of Europe, and offering exciting recreational activities, including hiking, climbing and skiing, as well as varied cultural activities. IDIAP is an equal opportunity employer and offers competitive salaries and conditions at all levels in a young, dynamic, and multicultural environment. Although IDIAP is located in the French part of Switzerland, English is the main working language at IDIAP. Free French courses are also provided. Application: ------------- Interested candidates should submit their application (motivation letter, detailed CV, name of three references) by email to jobs at idiap.ch. For further details please contact: Jean-Marc Odobez (Jean-Marc.Odobez at idiap.ch) Tel : +41 (0)27 721 77 26 or Daniel Gatica-Perez (gatica at idiap.ch) Tel : +41 (0)27 721 77 33 -- Jean-Marc Odobez Research scientist Jean-Marc.Odobez at idiap.ch http://www.idiap.ch IDIAP, Rue du Simplon 4 Tel : +41 (0)27 721 77 26 Case postale 592, Fax : +41 (0)27 721 77 13 CH 1920 Martigny, Suisse -- Jean-Marc Odobez Research scientist Jean-Marc.Odobez at idiap.ch http://www.idiap.ch IDIAP, Rue du Simplon 4 Tel : +41 (0)27 721 77 26 Case postale 592, Fax : +41 (0)27 721 77 13 CH 1920 Martigny, Suisse From g.goodhill at imb.uq.edu.au Fri Jan 26 04:57:34 2007 From: g.goodhill at imb.uq.edu.au (Geoffrey Goodhill) Date: Fri, 26 Jan 2007 19:57:34 +1000 Subject: Connectionists: Network 17.4 Table of Contents Message-ID: <45B9D08E.2020001@imb.uq.edu.au> Network: Computation in Neural Systems Vol 17, Number 4 (Dec 2006) TABLE OF CONTENTS VIEWPOINT Theoretical understanding of the early visual processes by data compression and data selection Li Zhaoping pp 301-334 ORIGINAL ARTICLES Phasic norepinephrine: A neural interrupt signal for unexpected events Peter Dayan & Angela J. Yu pp 335-350 Coherent ongoing subthreshold state of a cortical neural network regulated by slow- and fast-spiking interneurons Osamu Hoshino pp 351-371 Population density methods for stochastic neurons with realistic synaptic kinetics: Firing rate dynamics and fast computational methods Felix Apfaltrer, Cheng Ly & Daniel Tranchina pp 373-418 Self-organizing path integration using a linked continuous attractor and competitive network: Path integration of head direction Simon M. Stringer & Edmund T. Rolls pp 419-445 Entorhinal cortex grid cells can map to hippocampal place cells by competitive learning Edmund T. Rolls, Simon M. Stringer & Thomas Elliot pp 447-465 Journal homepage including links to above articles: http://www.tandf.co.uk/journals/titles/0954898X.asp Submissions: http://mc.manuscriptcentral.com/ncns Geoff Goodhill Editor-in-Chief, Network: Computation in Neural Systems ncns at uq.edu.au From franco at dii.unisi.it Thu Jan 25 16:05:06 2007 From: franco at dii.unisi.it (franco@dii.unisi.it) Date: Thu, 25 Jan 2007 22:05:06 +0100 (CET) Subject: Connectionists: Special Session on "Pattern Recognition in Graphical Domains" at KES2007 Message-ID: <2680.10.0.0.1.1169759106.squirrel@https://www.dii.unisi.it> ** Our apologies if you receive multiple copies of this announcement ** Special Session on "PATTERN RECOGNITION IN GRAPHICAL DOMAINS" 11th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems Vietri sul Mare, Italy 12, 13 and 14 September 2007 Call for papers Traditional machine learning applications usually cope with graphs by a preprocessing procedure that transforms structured data to simpler representations. This approach relies on what is called the "feature extraction" process, but it turns out to be quite unnatural for several situations where data are intrinsically organized as graphs, i.e. relationships exist among atomic sub-entities. Unfortunately, valuable information may be lost during the preprocessing and, as a consequence, classical methods may suffer from poor performance and generalization. Therefore, recursive or nested representations, as opposed to "flat" attribute-value data organizations, seem to be more adequate for many relevant problems arising from chemistry, bioinformatics, and the World Wide Web. Recent studies on statistical pattern recognition and neural networks show possible directions to exploit structural information in problems which are inherently of sub-symbolic nature. This special session is intended to propose a critical re-thinking of the classic learning approaches and to investigate on possible new methodologies and applications of pattern recognition in graphical domains. The scope of this session is, but not limited to: . Neural Network Models for Graphs . Support Vector Machines and Kernel Methods for Graphs . Probabilistic Models for Graphs . Statistical Relational Learning . Pattern Recognition Applications Involving Graphical Data Submission Instructions Authors are encouraged to submit high quality, original work that has neither appeared in, nor is under consideration by, other conferences/journals. All submissions will be refereed by experts in the field based on originality, significance, and clarity. The conference preceedings will be published by Springer-Verlag in Lecture Notes in AI as part of the LNCS/LNAI series. When formatting papers - that must be no more than eight (8) pages long, including figures and bibliography - please refer to the Springer-Verlag site and strictly follow the instructions for LNCS authors (http://www.springer.de/comp/lncs/authors.html). SPECIAL ISSUE ON NEUROCOMPUTING Authors of selected manuscripts will be also invited to submit an extended version of their paper for publication in a special issue of the Neurocomputing Journal, published by Elsevier Science (http://www.elsevier.nl/locate/neucom). Important Dates: March 10, 2007: Deadline for paper submission April 10, 2007: Notification of acceptance May 1, 2007: Camera-Ready paper Organized by: Chair . Monica Bianchini, University of Siena . Franco Scarselli, University of Siena Program Committee . Markus Hagenbuchner, University of Wollongong, Australia . Barbara Hammer, Clausthal University of Technology, Germany . Simone Marinai, University of Florence, Italy . Lionel Prevost, Universit? Pierre et Marie Curie, France . Jan Ramon, K. U. Leuven, Belgium . Friedhelm Schwenker, University of Ulm, Germany . Alessandro Sperduti, University of Padua, Italy More information are available at the special session site http://www.dii.unisi.it/~monica/KES2007/CFP.html From p.monaghan at psych.york.ac.uk Mon Jan 29 04:33:47 2007 From: p.monaghan at psych.york.ac.uk (Padraic Monaghan) Date: Mon, 29 Jan 2007 09:33:47 -0000 (GMT) Subject: Connectionists: postdoc computational modelling of reading Message-ID: <2044.144.32.163.159.1170063227.squirrel@psycix.york.ac.uk> We have a vacancy for a postdoctoral researcher in the Department of Psychology at the University of York on computational modelling of visual word processing. The Department of Psychology at the University of York has achieved the highest possible ratings for research and teaching in the UK. The Department has facilities for computational, experimental, and imaging research of the highest calibre. York is also a very very nice place to live. The project will be run in concert with Jo Arciuli at Charles Sturt University in Bathurst, Australia. The successful candidate will have a good first degree in Psychology, Linguistics, Computer Science or a related-discipline. The candidate will also preferably have a PhD with experience of computational modeling, psycholinguistics, and cognitive psychology. The post is for 11 months commencing 1 April 2007. Salary is ?25,633 per annum. The closing date for applications is 16 February, further details and information on applying are here: http://www.york.ac.uk/univ/mis/cfm/vacancies/vac_detail.cfm?vacno=DR0749&mode=standard Please address informal enquiries to Padraic Monaghan pjm21 at york.ac.uk Thanks. From wduch at is.umk.pl Sat Jan 27 07:28:26 2007 From: wduch at is.umk.pl (Wlodzislaw Duch) Date: Sat, 27 Jan 2007 16:28:26 +0400 Subject: Connectionists: Data mining challenge: classifying clinical free text. Message-ID: <000301c7420e$a608fa10$6500a8c0@duchnote> You are invited to participate in an international data mining challenge. The goal is to assign all relevant codes (called ICD-9-CM codes) to short clinical free texts. The Challenge provides an opportunity for research groups to test the applicability of their natural language processing and machine learning algorithms on real medical text data. Challenge details and on-line registration is found at http://www.computationalmedicine.org/challenge/index.php Important Dates are: 23 Jan 2007 Registration begins 1 Feb 2007 Training data sets released 28 Feb 2007 Registration ends 1 Mar 2007 Challenge data set released 18 Mar 2007 Last day to submit results 1 Apr 2007 Challenge results announced Challenge organizers include Cincinnati Children's Hospital Medical Center Division of Biomedical Informatics, the University of Cincinnati, Department of Radiology, Ohio State University's Department of Linguistics, Nicolaus Copernicus University, and the Center for Computational Pharmacology at the University of Colorado Health Sciences Center. The Challenge is partly funded by an Ohio Third Frontier, Wright Center of Innovation grant. Travel award is generously donated by Cincom Systems. Questions should be e-mailed to information at computationalmedicine.org From arthur at tuebingen.mpg.de Mon Jan 29 11:34:05 2007 From: arthur at tuebingen.mpg.de (Arthur Gretton) Date: Mon, 29 Jan 2007 17:34:05 +0100 Subject: Connectionists: Machine learning summer school 2007 Message-ID: <1170088445.4292.3.camel@localhost.localdomain> ~* Invitation to the *~ ==*== Machine Learning Summer School, Tuebingen, 2007 ==*== Registration is now open for MLSS 2007, the 9th summer school in a series beginning in 2002. It is intended for students and researchers alike, who are interested in machine learning. Its goal is to present some of the topics at the core of modern machine learning, from fundamentals to state-of-the-art practice. URL: http://www.mlss.cc/tuebingen07/ Dates: Monday August 20 - Friday August 31, 2007 (2 weeks) Location: Max Planck Campus, Tuebingen, Germany Application Deadline: April 1st 2007 Past Schools: http://www.mlss.cc Poster: http://www.mlss.cc/tuebingen07/poster/ Email contact: mlss07 at tuebingen.mpg.de Topics will be covered both in lectures (4-6 per subject) and in practical courses (where students will have the chance to implement methods for themselves), and are taught by world experts in their fields. In addition, informal evening talks will cover a variety of application areas in which machine learning has successfully been applied. Material is directed both at outstanding participants without previous knowledge in machine learning, and at those wishing to broaden their expertise in the area; this includes PhD, Masters, and advanced undergraduate students, postdocs, academics, and IT professionals. The MLSS also provides an excellent opportunity for interaction with top researchers in a broad cross-section of machine learning disciplines. Lecture courses =============== Andrew Blake Topics in image and video processing Olivier Bousquet Statistical learning theory Nicolo Cesa-Bianchi Online Learning Arnaud Doucet Sequential Monte Carlo methods Zoubin Ghahramani Graphical models Gene Golub Linear algebra, computations and applications Carl Rasmussen Bayesian inference and Gaussian processes Gunnar Raetsch Introduction to bioinformatics Bernhard Schoelkopf, Kernel methods Alexander Smola Yoram Singer Structured learning Lieven Vandenberghe Convex Optimisation Practical courses ================= Joaquin Quinonero Candela Gaussian Processes Manuel Davy Sampling in practice Matthias Hein, Spectral Clustering and other graph based algorithms Ulrike von Luxburg Matthias Seeger Variational Bayesian Inference Yee Whye Teh Dirichlet Processes Evening talks ============= Andreas Dengel Knowledge management Uwe Hanebeck Information Processing in Sensor/Actuator Networks Oliver Kohlbacher Bioinformatics Joachim Weickert Image analysis and regularization PhD, Masters, and undergraduate students are eligible for scholarships that cover registration, accommodation and/or travel costs. Recipients will be chosen based on academic merit and financial need. Due to space constraints, we expect only to admit a fraction of all applicants; however, the lectures will be videotaped and will be available online through the www.pascal-network.org site. The summer school will be held for the second time in Tuebingen, a town with a historic city centre dating from 1500. Tuebingen also hosts one of Germany's oldest universities, and is the former residence of Kepler, Melanchthon, Hoelderlin, Hegel, Hesse, and the current pope. The Max Planck campus is located on a hill overlooking the old town, and incorporates a common area and garden for informal interactions between speakers and students. From cabestan at eel.upc.edu Tue Jan 30 11:42:59 2007 From: cabestan at eel.upc.edu (Joan Cabestany) Date: Tue, 30 Jan 2007 17:42:59 +0100 Subject: Connectionists: New submission deadline to IWANN2007: February 11, 2007 Message-ID: <00c601c7448d$b3971910$0132a8c0@ahadee.upc.es> Dear colleague, As you probably know, IWANN2007, the 9th International Work-Conference on Artificial Neural Networks will be held next June 20-22, 2007 in San Sebastian (Spain). Some people asked us for some additional time to submit papers. We can inform you that: THE VERY LAST DATE WILL BE FEBRUARY 11, 2007. Otherwise, it will be very difficult to organize the review process in a proper way. Do not hesitate to access the conference web site for additional details and to get access to the submission facilities: < http://www.iwann-conference.org/2007> -------> e-mail for further questions or suggestions at: iwann2007pc at dte.uma.es Cordially yours Joan Cabestany Alberto Prieto Francisco Sandoval Co-Chairmen of IWANN2007 Conference Very important dates: * ***** NEW **** Submission of regular papers: February 11, 2007 * Early registration: March 25, 2007 * Conference dates: June 20 to 22, 2007